The Electric Power Research Institute is working with utilities and the AI community to release data sets for developing and training models. These data sets can be used to increase efficiency, enhance predictive modeling and enable more effective identification of damage to equipment that may need to be repaired or replaced.
Microsoft has also developed a means of helping power companies enhance their predictive analytics through Power BI, a suite of business analytics tools that the company says can “improve and transform the way sustainable energy is managed and generate value across energy production, supply, distribution, and consumption using data-driven insights.”
Data analytics tools such as Power BI can be used by utilities to predict and plan for future customer demand. Microsoft says its product can “transform reactive decisions to predictive and preventive strategies with enhanced critical equipment and resource management in energy production and distribution channels.”
AI Can Help Drive Resource Management Within the Energy Sector
Majumdar spoke at an AI and Electric Power Roundtable hosted by the Electric Power Research Institute earlier this year. “The people who focus on data do not generally have expertise regarding the electricity industry, and vice versa. We have entities like EPRI trying to connect the two, and this is of enormous value.”
When it comes to resource management, the industry publication POWER reports that “EPRI is developing models and tools which will enable operators to enhance their responsiveness and flexibility to utility grid signals in the most cost-effective way. Coupled with the digitization of building control systems, AI predictive models will provide utilities and customers greater affordability, resiliency, environmental performance, and reliability.”
Another example of this AI capability was announced in November 2019, when Baker Hughes, C3.ai and Microsoft went public with an alliance they said will make it easier for customers to adopt scalable AI solutions run on Microsoft Azure. According to a Microsoft statement released at the time, “As a result, energy businesses will have a secure and reliable suite of enterprise-scale AI applications optimized to run on Azure. These solutions are tailored to address challenges across the entire value chain, from inventory optimization and energy management to predictive maintenance and process and equipment reliability.”
AI-Powered Energy Storage Can Increase Efficiency
According to EPRI, current new-energy storage systems “are typically 4-hour duration or less, corresponding to peaking capacity and ancillary services needs. However, in the coming years as storage is deployed to replace higher capacity factor conventional generation, absorb longer periods of renewable overgeneration, and support resilience during severe weather events there is a potential need for longer duration storage.”
Utility Dive reports that the Department of Energy is looking to AI and machine learning to accelerate research for long-duration energy storage. At the DOE’s Long Duration Storage Shot Summit on Sept. 23, Deputy Energy Secretary David Turk said bringing long-duration storage to the grid wouldn't just make it possible to rely on more renewable energy, but also "increase resilience and lower energy burdens" for vulnerable communities.
According to Utility Dive, the Rapid Operational Validation Initiative, or ROVI — the proposed initiative from DOE's national labs — seeks to close the information gap for electricity providers “by using machine learning and artificial intelligence to model performance of different long-duration storage technologies, including predicting how the technology will lose performance or hold up physically over time. The initiative would rely on industry data and digital twins of the storage systems to model the long-term performance.”