Digitization of power sector
Introduction
The
digital revolution is affecting the power industry. If the last decade was
about developing hardware capable of generating cheap, plentiful renewable
energy, the next one will be about making energy generation systems smarter. A
set of technological and macroeconomic forces is converging to trigger a deep
transformation of the energy industry. The world needs more power to extend
electricity access to over one billion people and to support stable growth and
rising living standards for billions more. This requires developing new energy
supplies, while building and upgrading grid infrastructure.
Three trends are impacting the global
energy sector at an unprecedented pace: decarbonization, digitization, and
decentralization. Energy policy and regulations have to adopt quickly to
respond to these technology-driven trends that are enabling empowered energy
consumers and transforming demand and supply. Get the policy framework right
and distributed generation offers new opportunities for countries to provide secure,
affordable, and environmentally sustainable energy. Policy frameworks that do
not integrate distributed energy resources will face investment challenges and
may slip down the Energy Trilemma Index.
Technology drivers
Macroeconomic forces are now coming
together with a new wave of major technological innovations that have begun to
challenge the traditional setup of the energy sector. These innovations are
driven by a convergence of digital and a physical technology that is starting
to unfold across all industries it is likely to be as transformational and
powerful as the industrial revolution. These factors needs three mutually
reinforcing trends: The Industrial Internet merges big data and cloud-based
analytics with industrial machinery, resulting in greater efficiency and
increased operating performance. This is already making significant impact in
the grid (smart meters), Next up is digitization of central generation and
power consumption including distributed generation; Advanced Manufacturing
weaves together design, product engineering, manufacturing, supply chain,
distribution and servicing into one cohesive intelligent system, delivering
greater speed and flexibility at lower cost; this is transforming how capital
intensive critical equipment such as gas or wind turbines are being
manufactured; and The Global Brain integrates the collective intelligence of
human beings across the globe through digital communication, resulting in crowd
sourcing, open collaboration, and a much faster pace of innovation; this trend
in the power industry will have the most impact from a developer oriented
software platform and its constituent application economy development.
The Future of Work is changing the nature
of economies of scale, and blurring the lines between manufacturing and
services—and it is beginning to deliver substantial gains in productivity and
efficiency for individual companies and entire industries. A 2012
estimate suggested that just a 1%
efficiency improvement would yield over $60 billion in efficiency gains in the
power industry over a 15-year period, some $90 billion savings in the Oil and
Gas industry $60 billion in the healthcare industry, and about $30 billion each
in aviation and in rail transport. The
Industrial Internet technologies that we have been developing since then are
yielding efficiency improvements well in excess of those original lower-bound
estimates. We are now seeing double-digit performance gains across our
industries of operation.
In the power sector, the most recent
estimates indicate that digitizing central generation could yield value of up
to $100 million for new wind farms (up to 20% higher MW), up to $230 million
for a new combined cycle gas power plant, and up to $50 million for an existing
combined cycle gas powered plant. Across the whole power industry, this equates
to up to $75 billion of impact for new combined cycle gas turbine and wind
turbine orders, with additional value for upgrades to existing assets.
Digital innovations have already begun to
transform the energy industry. They help open the way for multi-directional
energy flows in the grid, for real-time demand adjustment in response to supply
conditions, for a smarter combination of different energy supply sources and more.
Together, these changes brought about through digital innovation will increase
the efficiency, affordability, reliability, and sustainability of the system
Need
for New Power Structure
In several emerging countries or regions,
there is a massive need to expand access to electricity. Today, about 1.3
billion people in the world lack access to electricity; just in India, 250
million people do not have access. Large areas of Sub-Saharan Africa face the
same challenge; the gap with time is not shirking
Reliable access to power is essential to
improve the living conditions of populations across the world. It is also
essential to enable the development of stronger manufacturing industries that
can fuel economic growth and support the rise of a middle class. In short,
access to power is absolutely necessary to allow emerging market countries to
continue their economic convergence process.
As populations in large emerging markets
populations improve their standards of living towards those currently enjoyed
by advanced economies, natural resources consumption will grow at a fast pace.
Sustainability is already a global priority—its importance will only grow in
the coming decades. Countries will have to develop new strategies and solutions
to make energy consumption more efficient, and improve the effectiveness and
resiliency of energy distribution networks.
Developed countries, where electrification
rates are already at or close to 100%, will also need to reduce emissions from
power plants and improve energy efficiency as their economies continue to grow.
Moreover, aging infrastructure in both generation and grid, as well as, an
aging workforce, represent significant challenges.
Meanwhile, there is still significant scope
to further reduce inefficiencies and losses in generation, transmission and
distribution, to help ensure sufficient electricity provision across the global
economy in a sustainable manner.
The future of energy is a new value chain augmented
and interconnected by digital technologies, where both power and information
flow in multiple directions, all actors add value to the system, and the
overall efficiency and resilience of the system hinge on information sharing,
openness, collaboration, coordination, and the right set of incentives. The end
result will be a system that provides electricity in the most reliable,
sustainable, and economic manner.
Impact of
changes on Power system
The energy value chain will become more complex, encompassing
a multiplicity of moving parts with different priorities and incentives, as
well as a wider mix of supply sources. Ensuring that power can be delivered
reliably, without outages or unforeseen changes in quality will require a
commensurately sophisticated effort of monitoring and control.'
Exponential
growth in low-cost processing power advances in big data management and growing
cloud capabilities, coupled with the acceleration in analytics and
machine-learning, have the potential to transform the way we produce, buy and
sell electricity. The advent of distributed generation, solar and wind options,
roof tops and two way metering has made it mandatory to adopt digitization, in
order to control run and use the power system whist maintaining its integrity. Smart
metering and time of use meters plus consumer devices that can respond to
signals from the system all make digitization essential to achieve cost
reductions in supply and provision of energy. At the same time, the convergence
of digital and physical innovations, together with advances in energy technologies,
has begun to impact the industry.
These advances help open the way for
bi-directional energy flows in the grid, for real-time demand adjustment, for a
smarter combination of energy supply sources and to deliver higher electricity
output from existing assets, as well as enhanced performance from future
infrastructure investment.
These challenges also present unprecedented
opportunities. The future of the power sector is a new value chain
augmented and interconnected by digital technologies—one where both power and
information flow in multiple directions; all actors add value; and the overall
efficiency, cost-effectiveness, resilience, and sustainability of the system
are enhanced through information sharing, openness, collaboration, and
coordination between stakeholders through the right set of incentives.
New
Power and Energy System
It will encompass three key elements:
(1) A digital centralized generation pool,
relying on a mix of fossil fuel and renewable sources; (2) a digital grid,
connecting generation and consumption, and enabling the multidirectional flows
of energy and information; and (3) a digital consumption setup, improving
consumption patterns along with distributed generation and storage capacity.
Energy providers will join a new breed of
digital-industrial companies. This will require changing their business models
to take full advantage of new digital capabilities: balancing the fuel mix
through big data analytics, accelerating the adoption of natural gas and renewable;
optimizing plant operation by using analytics to reduce cost and emissions
while maximizing economic output; and developing new ways to interact with
customers. The power grid will realize its potential as a platform,
accelerating innovation and efficiency gains.
This transformation will not be easy. It
will require investing in infrastructure and new technologies; changing
mindsets, public policies, and business models; investing in people through
education and on-the-job skills upgrading; and developing open standards and
ensuring interoperability. It will require the highest degree of cyber security
against potential data privacy and system security risks.
The convergence of digital and physical technologies
provides opportunity of unprecedented magnitude. It could provide a future of energy that
realizes the goal of ubiquitous access to clean, reliable, sustainable and
secure electricity, while fostering economic growth through the creation of new
energy ecosystems.
Benefits of digitalization in the power industry
As
electricity markets evolve for integrating large amounts of renewable energies
and for improving energy efficiency of different sectors, energy and utility
companies find it difficult to keep their margins and integrating new
technologies they didn’t know before. Today, hundreds of startups and big
companies provide technologies and platforms that allow power producers,
utilities and other companies in the energy sector to reduce their operating
costs, increase revenues and exploit new business opportunities. Digitalization
of Energy Systems, a report by Bloomberg New Energy Finance (BNEF), predicts
significant shifts in the intelligence of digital technologies used in energy
from today to 2025, and a big change in the sectors of the energy system that
most benefit from these technologies. The same study shows that investments in
digital energy are growing at 20% rate every year, reaching $55 billion
globally last year. These are shared among smart meters, energy management
systems and automated demand response or micro grid load scheduling. The
benefits of digitization include:
An optimized maintenance – the transition from
preventive to predictive reduces the costs of ownership by maintaining the
reliability and availability of an asset. Preventive and
conditions-based maintenance allow asset owners to reduce their O&M costs,
by the enhanced planning of the maintenance activities, in this way unnecessary
work is avoided. Maintenance on a running machine which is in good condition
puts the assets in jeopardy rather than improving them, plus reduced downtime
period is ensured by identifying the point of failure quickly.
The ability
to cut down asset management costs by freeing up asset managers’ significant
time so that they can focus on the responsibilities that really matter. According
to a McKinsey Global Institute study, only 39% of an employee’s time is spent
on role-specific tasks. The other 61% is spent on slogging through email,
trying to find a missing file, or syncing with co-workers. Many asset
management activities, such as managing contracts, tasks and expenses, can be
digitalized, reducing the time spent by people doing the job. Also, invoices,
bills and reports can be greatly automated, thus bringing huge efficiency gains
to the whole organization.
By managing
electricity loads in response to price signals, these players are able to
participate in the market and benefit from lower power costs. Accurate
energy forecasting for variable renewable energies allows avoiding imbalance
costs which are increasing in many countries. When these assets are coupled
with flexibility sources or controllable consumption loads, forecasting energy
and electricity prices becomes crucial to optimize load scheduling and
participation to different energy and ancillary markets. Technologies today
allow optimizing the behavior of complex systems made of different production
units, energy storage systems and energy consumers.
Digital
energy is the path to unlock new business opportunities Innovative
business models unlock new revenue and profit sources by offering innovative
services. Digital technologies allow asset managers to become virtual power
plant managers, utilities to implement new business models based on distributed
generation and solar installers to build energy communities.
Digital tools
give companies in the energy sector new ways to interact with their customers,
making them more loyal. Many utilities and other energy service organizations are
seeking to transition from electricity provider to trusted energy advisor.
Whether they are residential or industrial consumers or even owners of power
plants, digital services allow enhancing the interaction with the customer.
Custom web and mobile apps are helping energy & utility companies to
enhance the overall perceived satisfaction with the brand. Advanced reporting
tools allow O&M contractors and asset managers to improve the transparency
with the owner and to effectively deliver the information when and how it’s
needed.
New Power
Structure
It will encompass three key elements: a
digital centralized generation pillar, relying on a mix of fossil fuel and
renewable sources; a digital grid, connecting generation and consumption,
enabling the multidirectional flows of energy and information; and a digital
consumption pillar, which will play an important role not just in improving
consumption patterns, but in adding generation and storage capacity. Centralized
power generation will remain critical even with the rise of distributed energy
resources. It will provide the majority of the power supply, and ensure the
continuity and reliability of electricity provision. The longstanding goal of
ensuring reliable, affordable and safe access to electricity remains unchanged
in the future of energy, and can only be guaranteed by a strong centralized
power generation system.
Planning, Generation and Transmission
Digital technologies will transform power generation
from the very earliest stages, starting with the design and siting of power
plants, and continuing through the operations and maintenance phases. The
planning process will utilize comprehensive big-data analysis of the energy
network. Data from distribution grid assets such as advanced meters,
intelligent feeder monitoring and distributed resources can be combined with
transmission data from phasor measurement units and other monitoring devices to
develop predicted sub-hourly scenarios. These analyses will enable designers to
simulate the load demand on a power plant. They will also estimate the
financial viability of the plant under different alternative configurations,
through a better understanding of the plant’s complex interactions with all
other resources in the energy system. This can also help utilities balance
their generation portfolio.
Renewable power plants are particularly impacted by
location. Shading or vegetation can affect how much light reaches a solar
plant; wind farms are dependent on wind patterns A Digital Wind Farm, instead of settling for
the least common denominator model, will allow to customize every turbine to
its unique location on the farm. This can only be done by integrating the
advances in digital infrastructure (cloud computation, advanced load and
weather simulation algorithms, satellite topology images, etc.) and hardware technologies
(modular turbines that allow different configurations such as optimum hub
height, blade length and generator rating). The location of a new centralized
power generation facility will also need to take into account the necessary
Transmission and Distribution (T&D) infrastructure. T&D siting often
involves a lengthy process of engaging multiple stakeholders to devise the
appropriate pathway between power plants and load centers.
Today, new data tools such as advanced geospatial
platforms and power flow modeling can evaluate the best grid layout and
determine appropriate capacity requirements. Assessing sub-hourly interval data
can help develop detailed scenarios to understand the tradeoff between
installing or upgrading distribution lines and adding distributed energy
resources, or how those resources may impact power flow. These digital
capabilities are even more important when the environment becomes subject to
faster, more frequent and more complex changes because of new revenue streams
and system requirements such as frequency response, and new markets such as
ancillary and capacity markets. These require more real time decisions and an
improved transparency between plant capabilities and market dispatch.
Operational
Factors
Power generation will be able to rely on an
increasingly diverse and flexible range of supply sources: centralized
generation through fossil fuels, nuclear or renewables, distributed generation,
and stored energy. Balancing the supply mix on a real time basis will be
essential to maximize the energy output and cost-effectiveness of the whole
system.
Once the plant/farm is in operation,
digital tools can enhance its performance and profitability. Today’s power
plant and wind farm do not use integrated data and plant or fleet level software
applications to run their complex operations efficiently. A typical power plant
is a complex system that requires constant optimization across various
tradeoffs between availability, output, efficiency, maintainability, wear &
tear and flexibility. If these trade-offs are not tackled by using all
available data and the right software applications, the plant is operating at a
lower-efficiency profile, resulting in lower returns on the capital investments
already made. Use of various digitization tools can significantly increase the
operating profile of an existing power plant.
Software can provide power producers with
both “inside the fence” and system-wide views, enabling them to maximize the
plant’s operational efficiency while responding optimally to changing
conditions on the grid and in the overall power market.
What power plants need today are “Software
Defined Operations”. Which are : Deeper insights into a power plant or wind
farm operations to help with more forward looking decisions; breaking down the barriers between silos in
turn providing inputs for how to manage the market side of the power generation
business; and predictive or condition-based maintenance is a defining benefit
of the Industrial internet.
Digital tools will track and maintain
historical performance baselines for individual assets as well as the whole
plant, comparing it to real time performance monitored on a continuous basis.
Any variance from “expected behavior” derived from these baselines or expected
operation will trigger an alert. Advanced analytics will then determine whether
the variance signals a potential future malfunction, its root cause and the
likely timeframe over which the malfunction will occur. Analytics will also
provide a cost-benefit analysis of how much longer the unit can perform, and at
what load, before the issue must be addressed. This will allow the power
producer to address issues proactively, reorganize workflow around planned
maintenance and avoid outages. The resulting increase in uptime will improve a
plant’s economic value.
Digital technologies can also assess a
machine’s expected performance characteristics given the prevailing ambient
conditions. This combines a digital assessment of the machine’s “state of
readiness” based on sensor readings with temperature, humidity, and other data
that can impact its output. These data points can be compared with the historical
baseline and expected performance curve to detect any variance or
anomalies.Software that understands a machine’s physical capabilities relative
to its theoretical potential can do more than simply detect variance; it can
adjust operating parameters in real time to maximize efficiency and minimize
cost.
Aggregating and analyzing data across
assets “within the fence” can establish operating levels for individual assets
that optimize the entire plant system. In turn, as the plant operates more
efficiency, its overall emissions can decline, improving the plant’s
environmental footprint. Without these analytics, each asset would be
individually configured, which might result in a suboptimal performance for the
total plant. For example, digital wind farms that use analytics to adjust individual
turbine performance to maximize system benefit can improve total plant output
by up to 20%
A plant’s economic evaluation combines an
output assessment with system or market data. In deregulated markets, this
entails analyzing energy and/or ancillary product pricing for real-time or
advanced delivery commitments. In regulated contexts, this may include
assessing zonal demand, available transmission capacity, and the cost of
dispatching other available plants. Once digital tools have determined the machine’s
output capability, they can perform an optimization algorithm to provide
suggested operating levels to maximize economic value. This may include
recommendations on how to bid a plant’s output among various energy or
ancillary markets, or at what time a plant should be dispatched.
Digital technologies also hold huge
potential to improve fuel procurement and storage, which can account for up to
90% of a plant’s operating cost. Digital tools can improve fuel procurement by
identifying the most cost-effective fuel suppliers, and tracking fuel transport
and storage. Online platforms can run reverse auctions to enable multiple fuel
suppliers to compete.
Once a supplier has been identified,
digital tools can ensure that the power producer can track fuel delivery and
storage, such as monitoring the location of LNG or coal deliveries and ensuring
that appropriate quantities are transferred to reserves. Digital technologies
can also help drive transparency around commodity pricing, enabling power producers
to determine how they can adjust their hedging strategies to manage fuel cost
volatility.
Software can provide power producers with
both “inside the fence” and system-wide views, enabling them to maximize the
plant’s operational efficiency while responding optimally to changing
conditions on the grid and in the overall power market
What power plants need today are “Software
Defined Operations”. Deeper insights into a power plant or wind farm operations
to help with more forward looking decisions, and breaking down the barriers
between silos in turn providing inputs for how to manage the market side of the
power generation business
Predictive or condition-based maintenance
is a defining benefit of the Industrial internet. Digital tools will track and
maintain historical performance baselines for individual assets as well as the
whole plant, comparing it to real time performance monitored on a continuous
basis. Any variance from “expected behavior” derived from these baselines or
expected operation will trigger an alert. Advanced analytics will then
determine whether the variance signals a potential future malfunction, its root
cause and the likely timeframe over which the malfunction will occur. Analytics
will also provide a cost-benefit analysis of how much longer the unit can
perform, and at what load, before the issue must be addressed. This will allow
the power producer to address issues proactively, reorganize workflow around
planned maintenance and avoid outages. The resulting increase in uptime will improve
a plant’s economic value.
Digital technologies can also assess a
machine’s expected performance characteristics given the prevailing ambient
conditions. This combines a digital assessment of the machine’s “state of
readiness” based on sensor readings with temperature, humidity, and other data
that can impact its output. These data points can be compared with the
historical baseline and expected performance curve to detect any variance or
anomalies.
Software that understands a machine’s
physical capabilities relative to its theoretical potential can do more than
simply detect variance; it can adjust operating parameters in real time to
maximize efficiency and minimize cost.
Aggregating and analyzing data across
assets “within the fence” can establish operating levels for individual assets
that optimize the entire plant system. In turn, as the plant operates more
efficiency, its overall emissions can decline, improving the plant’s
environmental footprint. Without these analytics, each asset would be individually
configured, which might result in a suboptimal performance for the total plant.
For example, digital wind farms that use analytics to adjust individual turbine
performance to maximize system benefit can improve total plant output by up to
20%l,a digital consumption pillar, which will play an important role not just
in improving consumption patterns, but in adding generation and storage
capacity.
Digitalisation comes with up-front costs,
but technology’s ability to improve productivity can pay dividends. Digital
technology can help to solve some of these challenges. For instance,
intelligent data systems are enabling network operators to handle large volumes
of intermittent wind, solar and other renewable power, and to accommodate more
distributed power producers. For plant operators, building a database that
forms a digital twin version of the physical plant can lead to the development
of analytics that can trigger service and maintenance actions, even before
problems occur.
Power companies perceive that digital
technology will support the core fundamentals of their businesses with cost
management as a major focus and also as
a means of optimizing processes. Gains
can also be made in operations and maintenance, alongside improvements in
production capacity, safety and information management.
Digitalization has the potential to boost the
production capacity of their facility by at least 10 % although 40% savings are
also expected by some. . Companies think
digitalization will reduce operating costs by anywhere from 10 per cent to 50
per cent, with an average of just over 27 per cent.
Economics and technical advantages will
drive digitisation in the energy system, but major challenges remain. Power
companies are awash with data – a modern gas-fired power plant is equipped with
more than 10,000 sensors – but most have a long way to go before they can use
this effectively to trim costs, increase sales, and boost efficiency and
reliability not one uses more than half the data they collect. The average is
27 per cent. Establishing an intelligent
engineering master data management system can be key to helping organisations
improve on these numbers , data analysis would be easier with digital
information management and it would
enable them to make more informed decisions.
Digitisation comes with up-front costs,
but technology’s ability to improve productivity can pay dividends it is because of the enormous capital
expenditures required by the industry that it becomes so important to wring
every last drop of productivity from power assets, and software is
indispensable in this effort. And digitisation will bring great rewards. But
it will also bring change and uncertainty to what is a relatively conservative,
risk-averse industry
More than 50 percent of energy leaders said
they expect a rapid increase in distributed generation — to a share of 15
percent or higher — of the installed generation capacity in their country by
2025. Indeed, Oliver Wyman estimates that every
two minutes
a home or business in Europe and North America goes solar. This pace of change
is expected to accelerate with technological developments in storage options
that can support distributed generation. As one energy leader we interviewed
noted, "The pace of innovation on batteries and re-charging has increased
at a faster pace than expected."
New
Possibilities resulting from Digitization
Benchmarking across plants will now become
possible, as data is transmitted back from assets “inside the fence” to be
aggregated and analyzed. Operational anomalies can be identified and corrected,
and plants that perform better than expected can be rewarded. Operational
platforms that identify maintenance issues can proactively transfer data to IT
systems that manage maintenance personnel and supply chain vendors, ensuring
that the necessary parts are replaced by the right personnel at the most
optimal time. Through the use of analytics and a holistic IT/OT perspective,
power producers can optimize their plant performance and improve their
portfolio’s sustainability while minimizing maintenance costs.
The black box behind applications that help
digitize a power plant or a wind farm is a concept called “Digital Twin.”
“Digital Twin” is a collection of physics-based methods and technologies that
are used to model the present state of every asset in a Digital Power Plant or
a Digital Wind Farm. The models start by providing guidance on “design limits”
of a power generation unit at the commissioning stage or infer- ring the design
limit for an existing plant/farm by matching the equipment to thousands of
other similar equipment in the database.
These models are then continuously updated,
and learn to accurately represent the “present” state of a plant or farm during
its lifetime. The models accurately represent the plant or farm under a large
number of variations related to operation—fuel mix, ambient temperature, air
quality, moisture, load, weather forecast models, and market pricing. Using these digital twin models and
state-of-the-art techniques of optimization, control, and forecasting, the
applications can more accurately predict outcomes along different axes of
availability, performance, reliability, wear & tear, flexibility, and
maintainability. The models in conjunction with the sensor data give us the
ability to predict the plant’s performance, evaluate different scenarios,
understand tradeoffs, and enhance efficiency
The technology needed to run the complex
algorithms described above is different from the traditional IT architecture
prevalent in the industrial world currently. What is required is a scalable
framework to run industrial analytics, It
needs to have a seamless integration between the data layer (using a data lake
and cloud computing paradigm), a model layer and the application layer. What
the users will see is the experience captured in the application layer
Impacts of
Digitization
The World Economic Forum estimates that $1.3 trillion
could be generated by digitalizing electricity generation worldwide between
2016 and 2025. It lists five initiatives in particular – better management of
asset performance, real-time platforms data, integration of energy storage and
customer-centric solutions – that it believes will individually unlock at least
$100 billion of value over the ten-year period.
The digital grid will underpin the future energy
network: it will enable bi-directional flows of electricity, transmit
information and price signals, and ensure optimal balance of supply and demand.
Together, this will enhance grid reliability, reduce losses, and integrate
distributed resources which can help decarbonize the system. Digital tools will
play a significant role in achieving these outcomes. Utilities today manage
their T&D operations through several technology systems, including outage
management, customer information, maintenance management and meter data
management among others. However, using digital tools and intelligent
monitoring devices, T&D operators will be able to utilize an integrated
digital system that will enable them to identify reliability issues, address
customer problems, and ensure optimal electricity delivery in a more efficient
manner.
Today, T&D operators often rely on manual,
reactive intervention to ensure reliable grid operation. For example, without
the installation of advanced meters and other intelligent devices, utility
operators must piece together customer phone calls and other input to detect a
power quality issue or an outage, prolonging the time between identifying the
root cause of a delivery problem and deploying a solution.. Digital tools can
detect and locate an outage, identify the root cause, and rapidly restore
power. For instance, advanced meters can indicate an outage; geospatial data platforms
can help navigate personnel to the right geographic area, and advanced
distribution systems can dynamically reroute electricity. As more power is
generated using distributed resources, micro grids can provide enhanced
delivery and resilience. Digital tools can provide algorithms to island these
resources from the grid, ensuring that critical load demand continues to be
satisfied until main grid operation is restored.
Distributed energy resource adoption is
growing, driven by favorable economics and technical advances. Onsite
generation has become increasingly cost-efficient due to greater gas
availability and rapid cost declines in solar and storage technologies.
Intelligent load devices that reduce or shift energy use are becoming main stream
through user-friendly mobile interfaces, turning consumers into
"producers-consumers."
These technologies can bring benefits to the power
system, including addressing demand more efficiently, deferring T&D
investment, improving power quality, and increasing grid resiliency. However,
distributed resources also present operational challenges. They may cause rapid
voltage fluctuation, create bi-directional flows on radial distribution lines,
or adversely affect transformer and other grid asset lifetimes.
Software can help monitor and control these distributed
assets, as well as ensure that both consumers and the grid can benefit from
their installation. It can analyze sensor data from substations, feeders, and
connected devices to identify grid areas that may be at capacity, or
experiencing volatile demand or power quality issues. Data from smart inverters
or other devices can be analysed and merged with operational grid data to
provide utilities with a single view to monitor and control distributed
resources.
As distributed resources gain traction, they can
operate as a network, and in effect become a “virtual” power plant. For
distributed resources where output can be dispatched or controlled, software
can utilise local demand projections, relevant market pricing, and output
potential to ramp distributed generation or curtail demand in a coordinated
manner. Utility systems can monitor and control distribution grid devices to
ensure stability when distributed resources are in operation.
In reshaping the digital grid, it will be important to
build in a high degree of flexibility to allow for experimentation and to adapt
to future technological breakthroughs. Grid flexibility will also be
instrumental in ensuring high reliability in a context characterized by more
flexible and variable consumer demand and intermittent renewable energy sources
T&D
operators must also address both technical and non-technical losses. To reduce
technical loss due to natural power dissipation, software that processes voltage,
current, real and reactive power, and phase can make real-time adjustments. To
address non-technical loss, data from smart meters, intelligent devices, and
distribution grid sensors can identify where there may be theft or other power
loss.
Consumption end innovations
The transformation of the energy system has
arguably been accelerated by changes on the consumption side. Advances in solar
and in energy storage are allowing traditional energy consumers to become
energy producers. Advanced meters, connected devices, and energy management
systems are providing consumers with greater transparency and control over
their energy use. Together, these trends will help consumers lower their energy
spend while enabling them to provide overall benefits to the system in the form
of lower peak demand and more economic energy and ancillary services.
With solar panels on the roof and an
electric vehicle (EV) in the garage, a traditional consumer can start to play a
much more active and multi-dimensional role in the energy system. When the customer’s
photovoltaic (PV) energy generation falls short of consumption needs, customer
will supplement it with energy supply from the digital grid; when generation
exceeds needs can turn into a supplier, feeding energy into the digital grid.
The battery of her electrical vehicle can act as a distributed storage system
and help manage the demand and supply fluctuations in the household and potentially
in the energy system as a whole.
Digital energy management can interface
between a consumer’s equipment and the grid, regulating both energy consumption
and the mix of supply sources utilized based on the price signals provided by
the grid itself. At times when the grid faces peak demand, its prices will
rise, and the home energy management system will respond by reducing
consumption and/or switching from grid-provided power to locally-sited
generation or battery-stored power, where those are available.
Consumers can gain better visibility into when
and how they consume electricity, thanks to the continued rollout of smart
meters and other connected devices, enabling advanced analytics to deliver
data-driven insights through intuitive user interfaces on computers and mobile
devices.This is a big shift from a situation where most consumers still limit
their interaction with the energy provider to payin their bills and reporting
outages. Now consumers can better understand their energy consumption and change
their
strategies accordingly: residential
customers can benchmark themselves against similar households and identify a
menu of possible actions to reduce their spending; commercial and industrial
customers can shift some of their consumption to off-peak periods to benefit
from lower tariffs, or they can identify operational inefficiencies that can be
addressed to lower consumption.
Through the digital grid, this process will
generate a continuous flow of data on consumption behaviors, load fluctuations,
adaptation to price signals and supply responses—data that will help raise the
efficiency of the entire system. To maximize the potential benefits of greater
consumer engagement—where consumers are seen in their new and greater role of
co-suppliers—the energy system of the future will need to satisfy two
conditions: Provide a system of price incentives designed to reward
contributions to the system and to nudge consumers towards a behavior that can
maximize system-level efficiency; Offer a monitoring and control system
flexible enough to accommodate different degrees of customer engagement
according to individual preferences.
Some consumers will embrace the opportunity
to actively reshape their consumption strategy, whether driven by concern for
the environment or a desire to minimize costs; these consumers should have the
opportunity to closely monitor and modify their consumption with the high
frequency they desire. Other consumers will be content with setting basic
goals, parameters and constraints without having to spend too much time
understanding load fluctuations and pricing schemes. These consumers should be
able to rely on a smart energy system that will maximize efficiency subject to
the consumer’s choice of basic settings.
Pricing schemes should reward consumption
and distributed production behaviours that contribute to maximising system
efficiency; they should also recognize the value of the information that
different patterns of behaviour provide, while similarly assessing the value that
consumers and other distributed actors derive from access to the grid’s
infrastructure
New Power
Sector Business Model
Digital technologies are set to completely
transform the entire power sector value chain. This will require utilities and
other traditional entities to adapt and adopt new business models, while
emerging players introduce new services and capabilities. It will also require
a set of enabling conditions for new investments, policies and regulations.
Energy providers will join a new breed of
digital-industrial companies.This will require changing their business model to
fully take advantage of new digital capabilities. A first priority will be to
use the insights provided by big data analytics in order to balance the fuel
mix. Conventional thermal generation will remain a vital component of the
energy mix for decades to come,9 but new technologies will accelerate the
adoption of natural gas and renewables, requiring software to manage and
optimise the generation portfolio. Mind shift In general, management and
operations of power producers will have to adopt a “data-first” mentality,
always thinking in terms of the potential insights that can be gleaned from
data and analytics to improve the value of the service.
Digital tools can also give energy
providers new ways to interact with consumers. Many utilities and other energy
service organizations are seeking to transition from electricity provider to
trusted energy advisor. This requires utilities to work with customers in new
ways to identify and tailor solutions. For example, detailed interval data as
well as information from connected devices can help utilities and other service
providers to develop onsite power solutions to increase reliability or
efficiency retrofits to reduce spend. Social media can help utilities
communicate with customers regarding outage restoration or peak demand events,
or simply engage customers in a discussion around energy services or
conservation
Progress to present
Transformation of the industry is already
underway, it is happening now; plant
digitalization is a rapidly growing focus across the industry with most
organizations working on their strategy and initiatives. An overhaul of the power industry is long
overdue. Power generation networks have become much more complex in recent
years, thanks mainly to the rise in renewable energy power generation and the
growing number of small, distributed power producers. Demand for power is also
increasing in many countries, yet grid infrastructure is often old and
creaking. Equipment is both difficult and costly to maintain, but tighter
regulations are driving the industry to be more efficient and cleaner
than ever.
Platforms have quickly emerged as a
defining characteristic of the digital economy. Their role and value in
consumer sectors is by now recognized: they are both an enabler of efficiencies
and a key avenue of value monetization. Platform business models have
revolutionized the way that value is created, delivered and monetized across a
set of interdependent providers, users and intermediaries. As a concept,
platform- driven businesses are not new. They have existed in the physical realm
for centuries: a “bazaar” or “market” is a platform that brings sellers and
consumers together in some central location for a trade, enabling faster
diffusion of information (through physical co-location) and more efficient
transactions.
Digital-age platforms do a lot more,
however. They unlock the potential of under-utilized capacity. They enable
instantaneous and universal access to information through digital apps on
mobile devices; they turn data into analytical insights that can dramatically
increase efficiency by accelerating the feedback loop between price changes,
and supply and demand responses. They also accelerate innovation and value
creation. Common operating systems that enable the rapid and wide deployment of
new digital consumer apps have reached the point where “there is an app for
everything”. A similar proliferation will take place in the industrial world.
The electric grid embodies many of the
platform characteristics. It connects multiple users of a network, enabling the
exchange of products, services and information. Traditionally however, the
platform potential of the electric grid has been limited by the very specific
nature of the sector.
Economies of scale, the exclusive role of
centralized generation and the lack of data collection and response mechanisms
dictated a very simple hub-and-spokes model, with centralized power producers
supplying electricity and charging bulk tariffs regulated to allow them to
cover investment and operational costs while ensuring affordable safe and
reliable power access to consumers.
With the rise of distributed generation and
demand management set to complement centralized power, the electric grid has
for the first time, an opportunity to become a true platform, enabling a
symbiotic relationship between central and distributed resources, utilizing a
wide range of data such as weather and vegetation changes, granular load
projections by neighborhoods, central generation and distributed resource
output capabilities, demand response capability, and grid asset health to find
the optimal resource mix and power flow path to maximize grid reliability and
minimize delivered electricity cost.
These digital platforms will enable central
and distributed resource providers to determine location prices for energy and
ancillary services, and consumers to determine how best and when to use energy.
In the event that a reliability issue such as an outage must be handled, the
digital platform will autonomously communicate with grid devices to reroute
power flow, island critical loads using micro grids, and ensure that the proper
steps are taken to restore the grid to proper operation safely and quickly.
With
a long track record of using SCADA and ICS platforms to drive business and
operational efficiency, oil and gas firms are most eager to embrace IoT, with
88 per cent considering enablement as a priority.Utilities are not far behind,
while over three-quarters of firms investing in IoT say it is a top priority
for the coming year. One reason for this growing interest in IoT technologies
is the fact that it plays into several other key areas such as IT automation,
Power
providers see it as a great way not only to improve safety and quality of life
for citizens but also to improve internal efficiencies and service
reliability. These include companies
like Oklahoma Gas & Electric, which has deployed a robust IoT network,
helping to reduce operational costs, lower emissions, minimize the number of
service vehicles on the roads and empower consumers to manage their own energy
supply. The beauty of the firm’s expandable IoT network is that it had also
been used to connect 250,000 LED street lights — improving service levels,
reducing energy consumption and accelerating resolution of outages.
Florida
Power and Light (FPL) used advanced metering infrastructure (AMI) and automated
feeder switches (AFS) to boost resilience in the face of frequent storm-related
outages. It worked: the firm claimed it avoided 118,000 outages and restored
power within two days to 99 per cent of others affected during last year’s
Hurricane Matthew.
Other
utilities players including Baltimore Gas & Electric, ComEd, BC Hydro and
Pepco Holdings are doing similarly innovative things with smart grids. These
initiatives aren’t just confined to North America, either: smart lighting
projects, for example, can be found all over the world, in places like Glasgow,
Paris, Copenhagen and London.
While
the benefits are potentially huge, there are also major IoT challenges
potentially holding up deployments there have been problems
Network
performance was also high up on the priority list, illustrating the continued
importance of latency and bandwidth to effective IoT systems. Next come
standards — a key requirement for over half of IT bosses. In fact, 45 per cent
demanded open standards for smart city solutions, while a similar number said
the same for utilities projects. Open standards are vital to keeping costs down
and choice of products high for IT leaders. They promote performance, security
and reliability, while backwards compatibility helps ensure that legacy assets
don’t get stranded.
US firms appeared to be most mature in their
approach to IoT, with two-thirds (65 per cent) claiming to have a fully
implemented IoT strategy in place, versus just 47 per cent in the UK, 44 per
cent in Sweden and a quarter (24 per cent) in Denmark. It’s clear, therefore,
that the rate of IoT adoption will vary by geography, as it does by industry.
UK firms seem to have the most trouble at present, with just 3 per cent
claiming their projects were completely challenge-free.
Ultimately,
the most important thing to remember is the end user. Power suppliers and
utilities firms looking to utilize IoT technologies to drive internal and
external benefits will only achieve success if they get the consumer on board.
This makes awareness raising and education programs vitally important to sell
your customers the benefits of any new IoT project. Your eye-catching new
solution might have the potential to transform the customer experience, lower
costs, improve efficiencies and drive greater business agility, but if your
customers aren’t with you, all that planning and investment may be in vain.
We’ve
already well and truly entered the IoT age. But unlocking value from these
technologies requires more than blind investments in technology. Those
organisations most likely to pull ahead of their competitors will be the ones
that focus on security, performance and standards to drive success.
Enabling conditions
While there will be tremendous benefit
gained from further digitizing the energy sector, challenges beyond technology
and policy remain. In particular, a grid with seamless interaction between
central and distributed resources will require open standards and
interoperability. Any platform that manages assets as critical as the energy
infrastructure will need to be secure physically, but especially digitally.
Finally, a new generation of personnel will be required to facilitate the
industry’s transition to a digital future as a significant portion of the
current workforce retires.
Open standards and interoperability: As with any ecosystem
that includes a multitude of technologies, products and stakeholders, a common
set of standards is necessary for industry development and continued
innovation. This need is magnified in the case of the Industrial Internet—a
convergence of multiple technologies with advanced connectivity across devices
and systems. To maximize the potential value of Industrial Internet
innovations, it is essential that different systems and assets be able to
communicate with each other, share data and respond to common monitoring and
control systems. Moreover, as these connected devices interact with utility and
other personnel, data standards can help drive consistent analytical views to
aid in decision making
While progress has been made, more will need to be done
to involve the emerging technology and service providers, along with the
existing set of utility and OEM stakeholders. Even in the pre-digital age, the
efficiency and value of power grids has often been held back by a tendency to
“balkanize” the grid along state lines;
in the digital age, artificial and arbitrary barriers to interconnectedness and
interoperability would carry a much larger opportunity cost.
Cyber security: The digitization of energy opens a new
form of vulnerability, exposing network participants to potential data privacy
and system security risks. Reducing these risks to a minimum is a top priority.
There has been progress on multiple fronts. Vendors are
developing and deploying solutions that include assessment services, firewall
and security infrastructure. The U.S. Department of Energy and National
Institute of Standards and Technology have put forth comprehensive programs to develop
frameworks that address the risk to the electric grid, as well implementation
guidelines and maturity models for cyber security. As government and private
enterprises invest in digital technologies, they must continue to implement a
robust cyber security infrastructure.
Education
and skills development
Population
ageing in advanced economies is mirrored by the ageing of the workforce across a
number of industries—and the power industry is no exception. The prospective
simultaneous retirement of large cohorts of experienced workers is set to
create a problematic skills shortage just as the industry faces a challenging
transformation. While younger generations of workers will bring new skills to
the industry, it is crucial that the knowledge and experience accumulated by
more senior workers is captured and embodied in the companies’ institutional
memory, accessible to the new workforce. Digital innovations that facilitate
communication and collaboration as well as the creation of a digital memory
capturing the experience of the workforce should be used to this purpose.
Energy companies need people with software
and analytical skills to reap the benefits of the digital transformation. They
must invest in employee education and training, distribute and encourage the
use of mobile devices, and partner with universities and other vocational
training institutions to build data science capabilities.
Attracting new talent and workers with
digital skills is becoming increasingly important as utilities also face a
retiring workforce. Digital knowledge management systems can be used to capture
processes, institutional knowledge, and other relevant operational data from
the current workforce. Through the use of blogs, social media, conferencing,
and other real-time knowledge-transfer platforms, retiring specialists can
ensure that their experienced perspective can be captured and disseminated to
newer employees in a fast and seamless way.
Power generating plant
Digitization
The power sector
has somewhat conflicting objectives: How do you lower the cost of electricity;
achieve environmental; and business goals. The challenges facing the power industry
are many and span from pairing with renewables to competing with newer plants to
changing fuel economics. Power plants must adapt and respond to these challenges
to remain viable. Power plants generate an overwhelming amount of data. The
challenge is to know what to do with the data generated and also about how the
data would be of use in achieving objectives.
A digital power plant
applies sensor data and software to do more than human operators can do alone. This
is especially relevant as competition continues to drive plant headcount and operating
cost reduction while experienced experts retire and retention of even existing knowledge
is a challenge There are various options for building the software infrastructure
that is at the heart of a digital power plant. The first decision to make is whether
to develop software internally invest in a comprehensive software overhaul or purchase
application solutions that build on your existing software investments. All of which
come with their own set of costs and outcomes. The second decision is to prioritize
the challenges that can be cost-effectively addressed and avoid the danger of trying
to do too much at once.
Each plant faces different
challenges. Some are based on environmental factors or operating modes unique to
that plant. Therefore, the experience of each plant adds valuable feedback to validate
designs and improve O&M practices from fleet-wide learning. The path to digitization lies in being clear about:
end goal in creating a digital power plant; and determining priorities and timeline.
Conclusions
The power industry has begun an exciting
digital journey, one that will bring a deep transformation of the entire value
chain. A set of macroeconomic and technological forces have catalysed this
transformation, creating new challenges but also new opportunities for the
industry.
Access to electricity across developed and
emerging markets is critical to global growth. Today with over a billion people
without electricity access and growing energy demand from rising living
standards of billions more, the industry faces a formidable challenge.
Supplying secure and reliable power in a sustainable manner will require
investment in new generation and transmission-distribution infrastructure,
making the existing system more energy efficient as well as diversifying the
fuel mix.
Advances in distributed energy
technologies, energy storage, and connected devices are making it possible for
consumers to also play a role in the generation and distribution of energy,
opening the way for bi-directional energy flows and optimizing peak demand.
Utilities are deploying digital technologies to integrate distributed
technologies, manage fluctuating demand and quickly resolve outages to realize
industry goals. The penetration of
digital technology adoption however is limited. Operational challenges of
sustained profitability, data deluge and an aging workforce still remain
significant.
The convergence of digital and physical
technologies that is unfolding across industry can turn these challenges into
unprecedented opportunities. The power sector needs a digital strategy that
enables a new value chain augmented and interconnected by digital technologies.
The new structure links digital generation and digital consumption by a new
digital energy grid that can also serve as an intelligent technology platform
and a marketplace for new revenue sources, pricing schemes that incentivize
innovation for existing and new players in the energy ecosystem. A digitized
value chain will yield a system with greater reliability, affordability and
sustainability. In the energy sector, machines will merge with data analytics
at a scale like never before. This will result in substantial value gains
starting from the planning and siting of power generation plants to their
operations. Moreover it will enable a more dynamic management of central and
distributed power. Meanwhile, digital consumption will become more efficient,
participative and responsive to demand and power supply conditions.
Power producers and utilities are embarking
on a journey to digitize their processes. This will require not just investment
in new technologies, but also a shift in mindset and business models—and the
shift will need to be faster than ever before. Digital innovations rely on
openness and collaboration to realize their full value. Therefore, power
producers and utilities will need to break down barriers separating their
organizational silos. To do so, their CEOs, CIOs and COOs need to select the
right technology partners that can help them bridge the IT and OT domain
expertise. Internal and external collaboration will be mutually reinforcing. As
this new wave of innovations brings together very different areas of expertise
at an accelerated pace, partnerships are essential to succeed.
This transformation will need high
coordination among stakeholders. Energy providers will join a new breed of
digital-industrial companies, by investing in new technologies and finding new
ways to provide tailored solutions to customers. It will need development of
open standards and interoperability between products, the nurturing of a new
generation of personnel, and the highest level of cyber security.
Given its paramount importance for economic
growth, energy will be a national security priority for every country. In
developing new energy supply sources and infrastructure, ensuring the highest
level of efficiency, security and resilience will be of the utmost importance.
This will include an optimal degree of
supply diversification, including for imported energy, to reduce the risk of
disruptions that may be caused by natural disasters or geopolitical shocks. It
will also include a high standard of security safeguards around the energy
infrastructure. As digital technology becomes pervasive, cyber security will
become one of the most important pillars of energy security
In order to achieve both of the above
objectives, system operators will need to be able to monitor—in real time— the
state and performance of all assets linked to the network. This will enable
them to continuously assess demand and supply expressed by all elements on the
system, as well as their responsiveness to price signals. Identifying new
revenue sources/correctly valuing and allocating the cost of investments and
other efforts that add value to the system.
The traditional model that compensated utilities
with volumetric tariffs is becoming suboptimal. The energy system of the future
will need to develop a set of incentives that induces all players to add value
through actions and information provision, ensuring adequate compensation for
investment and incentivizing sufficient risk-taking for innovation and
experimentation.
The management of industrial technology has
traditionally been split between two separate fields: information technology
(IT) and operations technology (OT). IT worked from the top down, deploying and
maintaining data-driven infrastructure largely to the management side of
business. OT built from the ground up, starting with machinery, equipment, and assets
and moving up to monitoring and control systems. With smart machines, big data,
and the Industrial Internet, the worlds of IT and OT suddenly collided. Data,
once the purview of IT, is now ubiquitous on the operations floor. In order to
fulfill the promise of using data to enhance productivity, IT and OT, developed
separately with independent systems architectures, need to come together and
find common ground to develop a new information-driven infrastructure
Each of these challenges represents a
powerful opportunity. The convergence of digital and physical innovation can
dramatically accelerate progress across all the critical dimensions listed
above. As is becoming evident in other industries, as digital intelligence
becomes embodied in industrial equipment it opens up an entirely new dimension
for efficiency improvements. Digitally enabled interconnected devices can
perform a much wider range of functions, benefit from faster performance
improvements, and deliver disproportionately greater value to their users than
their traditional versions.
The first step of the Industrial Internet
maturity is to connect all critical assets in the energy value chain. This is
not a trivial task as we are referring to nearly hundreds of discrete
components with at least a dozen different communications and networking protocols.
These devices will generate 24 Exabyte’s of data by 2020. We estimate at least
50% of this data will be stored and analyzed in various forms of clouds (public,
private or hybrid).
In many cases, utilities have already
embarked on this digital journey. They are deploying operational technologies
such as generation and distribution asset smart sensors & controls,
substation and distribution automation and smart meters. The industry has begun
to develop a vision for a digitized future through various smart grid
initiatives such as improved grid resilience and energy efficiency. However
many assets still lack the capacity to collect and transmit data. Those that are
so enabled transmit volumes of data into local repositories that are not
accessible remotely; the few that are connected do not have the cloud
capabilities to generate actionable insights in real time.
Digital maturity will be achieved by
equipping energy assets across the generation, transmission, distribution, and
consumption value chain with sensors and cloud-based analytics. This is
becoming increasingly possible as sensor, bandwidth, and computing costs
continue to decline. Moreover, as information and operational technologies
continue to converge, emerging digital platforms will create a more connected
and intelligent power system. These platforms will do so by improving planning,
operations and maintenance procedures for each asset in the energy value chain
.
The future of energy is a new value chain
augmented and interconnected by digital technologies, where both power and
information flow in multiple directions, all actors add value to the system,
and the overall efficiency and resilience of the system hinge on information
sharing, openness, collaboration, coordination, and the right set of
incentives. The end result will be a system that provides electricity in the
most reliable, sustainable, and economic manner. The new structure wil comprise;
a digital centralized generation pillar, relying on a mix of fossil fuel and
renewable sources; a digital grid, connecting generation and consumption,
enabling the multidirectional flows of energy and information; and Centralized
power generation will remain critical even with the rise of distributed energy
resources. It will provide the majority of the power supply, and ensure the
continuity and reliability of electricity provision. The longstanding goal of
ensuring reliable, affordable and safe access to electricity remains unchanged
in the future of energy, and can only be guaranteed by a strong centralized
power generation system. Digital technologies will transform power generation
from the very earliest stages, starting with the design and siting of power
plants, and continuing through the operations and maintenance phases.
Power Sector
outlook in 2019
The three Ds of energy:
decarbonization; decentralization; and digitalization. Decarbonization of the power sector still
seems fairly clear – the options haven’t changed so much; energy efficiency, renewables, nuclear and CCS.
Although, the costs and policies have changed enormously over time and
renewables have made great advances. For 2019 we can expect to see further
advances and more geographies around the world in which renewables can
out-compete traditional forms of generation and face the market more and more.
This means renewables developers and investors getting comfortable with more
market and less regulatory risk.
The
step-change that we see is two-fold: on the one-hand, computing power
increasing and enabling greater levels of AI and machine learning; and
secondly, the amount of data available for those computers to analyze. These
two combine to mean that better decisions are made and are also automated.
These are the key areas we expect to see further progress in 2019 in
digitalization in energy:
Fault
prediction and dynamic maintenance: This is one of the clearest uses of AI which enables
operators to predict equipment failures by using sensor data from various units
to significantly reduce their costs of downtime and maintenance. Pöyry has an
offering for this called KRTI4.0. On the retail side, a startup Verv is
offering a meter device which identifies individual home appliances and tries
to predict faults or a device being accidentally left on by building up
individual profiles from the meter data.
Investment
optimisation:
BP’s venture arm invested in an AI startup called Beyond Limits to dig through
seismic images and geological models to increase the chances of success when
drilling wells. Another example of longer-term investment decisions is the US
Department of Energy project where machine learning is being used on satellite
imagery and operation data to prioritise reinforcement at vulnerable points of
the grid to improve resiliency.
Energy
efficiency:
Deepmind, which is a part of Google, has championed the use of Reinforcement
Learning to reduce energy use in its data centres by a claimed 15 per cent. The
model learnt by looking at years of operational data and then issued changes to
individual units within the operating constraints of the plant.
Better
prediction:
Deepmind is also currently in talks with National Grid of the UK to better
forecast demand of the system with the stated goal of reducing the entire
country’s energy usage by 10 per cent. Another example is improved prediction
of wind power production to reduce imbalance costs by 50 per cent which was
achieved by a company called Swhere.
Trading: According to the
FT, systematic and algorithmic trading now account for nearly 60 per cent of
the traded volume on just the CME energy product group – highest level of any
commodity group. Anecdotal evidence from mid-2018 is that over 50 per cent of
trades on the EPEX Spot intraday market are algo-trades (although the total
volumes are still smaller than trades executed by human). Sophisticated machine
learning models are also being deployed by speculators which are relying on
large streams of diverse data to respond to the market changes quickly.
Retail: retailers are using
machine learning to understand patterns of customer behavior, to attract and
retain customers and even to predict bill (non)-payment. Customer call centers
are being fronted by algorithms which chat to customers (verbally or online)
and deal with queries.
Customers: For customers, AI
solutions are also gaining traction, and many retailers are offering these
systems as part of an integrated package. Devices such as Amazon’s Alexa enable
the customer to seamlessly interact with their thermostat (such as Centrica’s
Hive). This increasing customer interaction with the device leads to the
development of a more personalized usage profile, which reduces bills for the
consumer and also helps the energy provider to accurately forecast demand.
It
would seem then that the digitalization opportunities in energy are large. It
will be a vital enabler of decarbonization is some areas in the future such as
flexible demand shifting to meet supply. The opportunities available rely
heavily though on sufficient volumes of good quality data being available. So,
expect more sensors and more data acquisition throughout the energy sector in
2019. And in time with growing autonomy expect the focus to switch to the
appropriate monitoring, alerts and controls. “AI is the new electricity –
enabling us to do more.”
Digitalization has become a
worldwide focus and the race to become the global leader in Artificial
Intelligence (AI) is becoming increasingly competitive, with many countries,
including Canada, China, and the UK releasing strategies in the last twenty months
to promote the use and development of AI.
Wind energy is one of the most
innovative, forward-looking and fast-paced industry sectors. With the U.S. wind
energy cost continuing to fall below the cost of coal and gas, wind energy
asset owners and operators are redefining their approach to operations and
maintenance (O&M) through adopting technologies that introduce greater
efficiencies and streamline processes. Many have invested, and are continuing
to invest, in predictive maintenance solutions, which combine improved SCADA
data analytics, CMS systems, and oil monitoring with AI and machine learning.
AI platforms work by identifying
deviations between expected component behaviors and actual behaviors, which are
then flagged allowing an inspection team to identify the fault and fix it in
advance of the fault causing a catastrophic failure or significant down time.
This, as a result, extends the lifetime of the asset in question.
Ideally, such a solution should
serve to not only flag to an asset owner that a failure is occurring, but also
the nature of the issue, the rate at which the failure is occurring and the
remaining useful life of the asset. This is where real-world engineering
expertise plays a key role in shaping the AI solution.
Though AI, machine learning and
digital twin are current buzzwords, they have the potential to create
significant confusion in our industry. Below, we will examine six key market
trends in order to cut through some of the “chatter” around these terms, to
determine with greater clarity how to make digitalization work for the wind
energy industry, rather than the other way around.
Bigger
Is Not Always Better
Small, agile companies may have the
advantage over large industrials when bringing innovative digital products into
the market. Independent players that are closely connected to the marketplace,
thus ascertaining a clear sense of market needs, have an advantage over bigger,
more generalist companies. The ‘top-down’ approach employed by larger
industrials can come with a significant price tag attached; often proposed
solutions are abstract in practice and constrained by their legacy systems,
creating a challenge for the asset owners and operators when it comes to
implementing the solutions. The digital products offered by larger industrials
have typically been developed around their own equipment; hence, the analytics
are optimized for their equipment. Oftentimes, independent, agile companies can
offer more flexibility by the way of pricing, customized solutions and
equipment-agnostics analytics. It is interesting to note that it is often these
bigger players that appear to struggle in the wind energy market.
Digitalization
Focused on Value, Not Tools
Numerous multi-national corporations
have embarked upon a digitalization journey by investing heavily in digital
technologies and tools only to have these investments fail to materialize in
business value. To avoid repeating these costly mistakes, a clear understanding
of the business value delivered by digital tools needs to be established as the
first step.
After that, an investment strategy
to develop, partner or acquire the relevant digital technologies should follow.
This will lead to a more “value-focused” digital transformation, which should,
in time, result in a clear demonstration of the value that digital technologies
bring to the industry.
Digitization
Before Digitalization
Despite the importance of data and
information to unleash the full power of AI and machine learning, some critical
wind energy data falls into the category of not being “digitized” or stored in
an “AI ready” or “IIoT” format. Furthermore, O&M teams currently spend 80
percent of their time organizing inspection data, which means they have less
time to focus on utilizing their core skills to address engineering issues.
Tools that enable the O&M teams
to “digitize” their inspection and maintenance data enable them to spend an
increased amount of time tracking failures, responding to developing technical
and safety issues and determining where the maintenance budget should be
focused.
A fully digitalized and connected
predictive maintenance approach is becoming increasingly important sector-wide;
asset owners require the right data to be in place in order to maximize the
investment of AI/machine learning. Asset and operations managers have cited a
need for higher-quality data to improve the reliability of their organizations’
assets. The challenge lies in ensuring data is stored in a unified format and
easily accessible. Cloud-based mobile inspection and maintenance software
transforms inspection and maintenance reporting practices, creating substantial
safety and efficiency gains for the organization, and generates good quality
data, increasing the efficiency also of Digitalization processes.
Overcoming
“False Positives” And “False Negatives”
In its enthusiasm to adopt
innovative digital solutions, the industry may be in danger of undermining the
progress made in predictive maintenance to date, by driving an increase in
“false positives” that, in turn, will result in increased OPEX costs for
operators. Clearly, there are only so many times that maintenance personnel can
be sent out to respond to identified failures — which fail to materialize into
an actual fault — before confidence is lost in the technology concerned.
Equally, “false negatives” are bad
news to the industry too. A cautionary tale of “false negatives” in AI involves
researchers training a Neural Network (NN) to detect camouflaged tanks in
photography for the US Army, succeeding, only to realize the NN had learned to
distinguish cloudy days from sunny days, instead of distinguishing camouflaged
tanks from empty forest. These issues with AI and machine learning must be
carefully managed to avoid the industry experiencing a turn from enthusiasm to
disappointment whilst AI is still in its infancy stage in wind energy.
The AI technology currently
available in the market is narrow AI, which means that it is able to handle
just one particular task. It is still impossible for AI technology to fully
complete the work of an all-round engineer solving complex engineering
problems. Development of Industrial AI is even more challenging than the AI we
use in our daily life through the likes of cloud-based smart home hubs, due to
the lack of good-quality training datasets.
U.S. operators are finding that AI
needs to be informed by real-world engineering expertise. A focus on
engineering-led approaches — from agile companies which have grown up from an
engineering base with a strong industry track record — is best positioned to
harness all the improvements promised by AI.
It is therefore imperative that the
two approaches, AI and engineering-led predictive maintenance, are not seen as
opposites, and that operators’ use of emerging technologies is underpinned by
deep engineering knowledge.
Data
Access
During this digital transformation
journey, turbine owners are increasingly running into obstacles relating to
limited data access from their own assets. Without full access to data, owners
cannot fully understand the health of their asset and manage it in an optimal
way. Ultimately, results from AI/machine learning are only as good as the data
available. It is possible for asset owners to come up against a barrier in a
number of different ways, from insufficient data acquisition systems or infrastructure,
meaning data isn’t collected in the first place, to a contractual limit that
means owners and operators aren’t able to freely access all the data collected
about their turbine performance.
That said, it is possible for the
industry to surmount challenges in the areas of data collection, data handling
and data access, so that turbine performance can be optimized, and the U.S.
wind market remains competitive. For the former, innovative digital hardware
and IIoT sensors are becoming increasingly cost-effective, making it easy to
justify investment in improving data acquisition and infrastructure systems.
With the latter, if U.S. wind farm owners collectively start holding their
suppliers to account when it comes to data access, greater volumes of data will
become increasingly available, ensuring a smoother procurement process.
DIY
or Do-It-For-Me?
These factors naturally lead to one
final consideration in evaluating your own predictive maintenance approaches:
whether to carry out all assessment and monitoring in-house or outsource it to
a predictive maintenance provider. The former, DIY approach may lend itself
well to organizations whose personnel possess a broad and in-depth O&M
experience in industries with a long track record in applying predictive
analytics, and who are well placed to advise on the implementation of
predictive maintenance approaches for wind assets. Equally, you may already be
using some form of condition monitoring technology, and this familiarity could
serve as the basis for a more fully developed predictive maintenance solution.
Over time, after working with and alongside experts from your predictive
maintenance supplier, you will develop levels of expertise that require less
hand-holding and make some level of DIY feasible.
Alternatively, it may prove more
resource- and cost-effective for your predictive maintenance partner to
continue to use their existing expertise to monitor, detect and predict
failures remotely and advise on the most suitable course of action, at least in
the short-term. In the long run, and as your on-site team become more familiar
with predictive maintenance technology and techniques, you could consider
moving from this Do-It-For-Me approach, to a semi-DIY set-up before taking full
control. Of course, for this to be an option, you’ll need to be working with a
provider that can deliver this level of flexibility and a tailored approach.
If an asset owner or operator
decides to go with the DIY approach eventually, it is still advisable to invest
in a powerful digital platform, which could increase the efficiency up to
ten-fold. After all, the core competence of asset owners and operators usually
falls on energy production instead of AI/machine learning and digital product
development. To have a strong technology partner in this area will enable a
pain-free implementation of the DIY strategy in the short term as well as the
longer-term maintenance of the most up-to-date digital technology in the
current competitive and fast-evolving market.
Understanding these myths,
challenges and potential approaches is a key first step in taking advantage of
the opportunities on offer. When combined with real-world engineering
expertise, AI and machine learning have the potential to transform decision
making for wind energy asset owners. With benefits on offer including the
ability to assess turbine condition, optimize maintenance programs and bring
down the levelized cost of energy, asset owners would do well to take the lead
in adopting approaches that combine AI and engineering expertise.
No comments:
Post a Comment