From coordination, forecasting and optimisation to balancing millions of assets on the grid, AI-centered systems are a potential game-changer
Reliance on a central utility to produce and transmit electricity is fading, and utilities will need to shift their business models. As we move toward an increasingly electric world, more energy will be produced by decentralised, renewable sources. Think microgrids, wind farms, private solar panels.
And Artificial Intelligence (AI) is the key to renewable energy grid resilience, leveraging decentralised renewable generation sources.
In many parts of the world, businesses are increasingly producing their own energy through solar panels, storing that energy in batteries and electric vehicles, or feeding it back to the grid.
For the energy grid, which requires split-second decisions to be made in real-time, AI algorithms are a perfect fit. The National Grid, an energy company, uses AI and machine learning (ML) to help predict how much energy the country will reap from turbines and solar panels when the wind is blowing, or the sun is shining. It has collaborated with the Alan Turing Institute to develop AI prediction models that have improved solar forecasting by one-third.
The project is similar to a collaboration between Google and AI firm DeepMind, which also use AI technologies to predict energy output from wind farms better. In 2019, Google revealed it can predict output from its wind farms 36 hours in advance, allowing the tech giant to bid to serve power to the grid ahead of time, a service that commands a higher power price.
Knowing how much power will be flowing into the grid on any given day is becoming increasingly crucial as the proportion of intermittent renewable power serving the grid goes up.
Increasingly, grid operators and developers are harnessing AI for a smooth transition to greater use of renewables. AI’s ability to provide better prediction capabilities is enabling improved demand forecasting and asset management, while its automation capability is driving operational excellence, which results in competitive advantage and cost-saving.
Supported by technologies, such as the internet of things (IoT), sensors, big data and distributed ledger technology, AI has the ability to unlock the vast potential of renewables — AI technology could bring gains on many fronts.
Also Read: Inside Google Deepmind
Prediction and forecasting
As the energy industry continues to utilise more variable generation sources, accurate forecasts of power generation and netload are becoming essential to maintain system reliability, minimise carbon emissions and maximise renewable energy resources. As an increasing amount of megawatts feeds into the grid from variable renewable energy sources, predicting capacity levels has become paramount to secure a stable and efficient grid. Now, with the application of sensor technology, solar and wind generation can provide an enormous amount of real-time data, allowing AI to predict capacity levels.
With increasingly larger data sets becoming available, predictions can now go far beyond the weather to train algorithms to predict more remarkable outcomes. For instance, how much additional power is used during a festive holiday, a large-scale international event, or how much altitude impacts a community’s energy use.
AI programs – such as IBM’s program for the US Department of Energy’s SunShot Initiative – combine self-learning weather models, datasets of historical weather data, the real-time measurement from local weather stations, sensor networks and cloud information derived from satellite imagery and sky cameras. The result has been a 30 per cent improvement in accuracy in solar forecasting, leading to gains on multiple fronts.
Forecasts of the base variables – wind speed and global horizontal irradiance, as well as the resulting power output – allows for a view on a range of time horizons, from minutes and hours ahead (for maintaining grid stability and dispatching resources) to day-ahead (optimising plant availability), to several days ahead (scheduling maintenance).
For energy traders, accurate forecasting of variable renewable energy at shorter timescales allows them to better forecast their output and to bid in the wholesale and balancing markets. More accurate short-term forecasting can result in better unit commitment and increased dispatch efficiency, thereby reducing operating reserves needed. In turn, cost savings can be passed along. The earlier and more accurate prediction, the more efficient it is for energy traders to rebalance their position. Ultimately, that means making a better financial return.
AI ensures that the power grid operates at optimal load, and grid operators can optimise the energy consumption of consumers. For grid operators, AI algorithms with vast amounts of weather data can ensure optimal use of power grids by adapting operations to the weather conditions at any time. But it is not only transmission system operators that can utilise AI; its application goes beyond central planning and can play a bigger role on the edge of the grid with machine-to-machine communication.
Equally important is accurate demand forecasting – and here, too, AI has a key role to play given its ability to optimise economic load dispatch and improve demand-side management. Increasing the installation of smart meters has enabled demand data to be sent to utility providers. AI algorithms can absorb the data, which can be sent as frequently as hourly, and predict network load and consumption habits accurately.
For consumers, utility bills can be reduced, with AI systems predicting a building’s thermal energy demand to produce heating and cooling at the correct times through optimisation of home solar and battery systems. Efficiency gains are combined with load shifting to times when electricity is cheapest, with renewable electricity available in the system. The US energy storage firm Stem’s AI-driven software has improved customer savings by approximately 5 per cent year-on-year.
Battery storage also has an important role to play in providing demand flexibility, with AI again playing a pivotal part. The Stem has developed AI algorithms to map out energy usage and allow customers to track fluctuations in energy rate to use storage more efficiently.
Similarly, US-based software-as-a-service platform provider AMS uses AI in versatile battery storage systems to optimise opportunities to purchase electricity from the grid when prices are low, and then sell back to the market when prices are high.
Another case is Australia’s Hornsdale battery, with 150MW, which operates an auto-bidder AI algorithm, developed by Tesla, that has allowed the project to capture revenue streams about five times higher than an energy trader, according to AMS.
For electricity providers, AI can also assist with operations and maintenance of asset management. AI algorithms can automatically detect disturbances in real-time of mechanical failure, thereby improving reliability and efficiency in the power system. By using data from sensors, algorithms can learn to distinguish and precisely categorise normal operating data from defined system malfunctions. GE Renewable Energy’s Predix software is embedded with AI-based algorithms that can interpret industrial data to make predictions on machine health and recommend actions to improve efficiency for assets such as wind farms.
Finally, at a regulatory level, AI unlocks legislation to be created more effectively. It also provides insight into human motivations tied to renewable energy adoption and how consumer behaviours could possibly be changed to optimise the energy system.