Predictive economic optimization of energy storage microgrids

Energy management systems currently being used to operate energy storage systems in commercial applications mostly focus on providing resilience and backup power but are generally unable to produce the predicted utility bill savings and grid services revenue as modeled by energy optimization software tools developed by national labs. This gap between actual and optimal economic performance is due to a lack of intelligence and prediction capabilities in the control algorithms as well as a lack of integration with dispatchable site loads such as electric vehicle charging and building management. This results in energy storage systems underperforming financially, which is a significant impediment to deploying energy storage at scale in the small-to-midsize commercial market. With increased electrification on the horizon, particularly vehicle and heating electrification, integrating with any dispatchable loads is also of increasing importance, since such electrification will significantly increase facility electric usage, demand, and therefore, utility bills. The objective of this Phase I SBIR proposal is the development of a low-cost, adaptive intelligent energy management system for use in small-to-midsize commercial energy storage system applications. The proposed control system will use mathematical optimization combined with artificial intelligence and machine learning techniques to produce near-optimal economic performance in grid-connected mode across multiple stacked revenue streams including rate-tariff-based utility bill savings, grid participation programs, and controllable site loads. The Phase I effort will focus on analyzing operating data from existing energy storage systems, developing the algorithms, studying and incorporating the “command and control” interface capabilities of electric vehicle supply equipment and building management systems, simulating the performance of these algorithms and interfaces using historical data, and then comparing the results to theoretical optimal performance as predicted by industry standard simulation and optimization tools. Phase II will then focus on building a fully capable software package with necessary interfaces to install a demonstration system at a candidate site. There are currently 5.9 million commercial buildings in the United States. Each of these buildings is a candidate for distributed energy resources such as solar and energy storage, but such a system will require an intelligent energy management system in order to unlock the projected economic and resilience benefits. In particular, improving the financial performance of these systems will speed the deployment of distributed energy and microgrids which will improve the resilience of both the local site and the nation’s electrical grid and critical infrastructure. Further, the deployment and integration of intelligent distributed energy and microgrid systems with controllable loads such as electric vehicle charging and building management systems will offset the anticipated cost burden of rapidly expanding electrification.