ECE doctoral student Mohammed Al-Saffar and professor Petr Musilek have recently published an article in IEEE Transactions on Smart Grid titled Reinforcement Learning based Distributed BESS Management for Mitigating Overvoltage Issues in Systems with High PV Penetration.
High levels of penetration of distributed photovoltaic generators can cause serious overvoltage issues, especially during periods of high power generation and light loads. Although battery energy storage systems (BESS) at the PV generation sites can be used to absorb extra power during the light load periods, their capacity may not be sufficient to allow charging every time power absorption is desired. To tackle this, the authors propose a cooperative state of charge control scheme to alleviate the BESS capacity problem through Monte Carlo tree search based reinforcement learning (MCTS-RL). Their proposed intelligent method coordinates the distributed batteries from other regions to provide voltage regulation in a distribution network.
An open-access version of the full article is available here: https://lnkd.in/gRzj9hC