蜜桃APP

蜜桃APP Department of Electrical Engineering Associate Chair Mehdi Farasat has received a $445,503 grant from the National Science Foundation (NSF) to develop advanced control and energy-management technologies that could help make ocean wave energy a more reliable and grid-compatible source of electricity.

The project, titled 鈥淧hysics-Informed Data-Driven Control of Wave Energy Converters: Predictive Wave-Force Modeling and Reinforcement-Learned Virtual Inertia for Stable Grid Integration,鈥� addresses a fundamental challenge facing wave energy鈥攃onverting variable, wave-driven mechanical motion into electrical power that is reliable, controllable and compatible with the requirements of modern electric grids.

Ocean waves represent a significant energy resource along U.S. coastlines. However, the variability of wave conditions creates challenges for forecasting, energy storage, power conversion and grid integration. Farasat鈥檚 project will develop an integrated, predictive and coordinated control framework designed to enable arrays of wave energy converters to operate cooperatively while using advanced hybrid energy storage to smooth power fluctuations and support stable grid operation.

鈥淲ave energy has enormous potential, particularly for coastal, islanded and remote communities, but realizing that potential requires technologies that can manage the inherent variability of the ocean,鈥� Farasat said. 鈥淭his project brings together physics-based modeling, machine learning, reinforcement learning, energy storage and advanced power-electronics control to create a more intelligent and resilient approach to integrating wave energy with the electric grid.鈥�

The research will focus on a grid-connected offshore energy system consisting of an array of direct-drive linear-generator wave energy conversion systems, a hybrid supercapacitor and undersea energy storage system, and power electronic converters that connect the wave-energy array and storage system to the electric grid.

A central component of the project is the development of physics-informed machine learning models capable of forecasting wave excitation forces and short-term power availability using sparse ocean measurements. By combining physical knowledge of wave energy systems with data-driven learning, the models will provide forecasts that can be used proactively rather than relying solely on real-time responses to changing sea conditions.

These forecasts will inform multi-agent reinforcement learning strategies, in which individual wave energy converters function as cooperative agents. The agents will coordinate their converter actions to increase overall array power production while simultaneously respecting the operating limitations of individual devices and the requirements of the electric grid.

The research also has potential broader impacts for the development of marine renewable energy in the United States. By addressing key technical barriers to reliable wave-energy integration, the project could help advance wave energy as a dependable electricity resource and support greater energy resilience for coastal, islanded and remote communities.

The project will additionally create educational and research opportunities at the intersection of marine energy, power electronics, machine learning and power-system control, preparing students and researchers to address emerging challenges in distributed energy resources and grid modernization.

Farasat鈥檚 research contributes to 蜜桃APP鈥檚 broader efforts to advance innovative energy technologies and address challenges facing coastal communities and the nation鈥檚 evolving electric power infrastructure. The project highlights the potential of interdisciplinary approaches that combine electrical engineering, artificial intelligence, energy storage and power electronics to develop more resilient and sustainable power systems.