Microgrid control under uncertainty
Year: 2024
Type: article
Abstract: Microgrids – decentralized electrical grids that can function both in conjunction with wide area macrogrids and without – are a powerful tool to address energy resiliency and climate change mitigation. Microgrid control, however, remains a challenge; their bespoke nature and the existence of multiple sources of uncertainty lead to a control problem that traditional grid modeling and control techniques are ill-suited to handle. We build a microgrid interface that allows off-policy reinforcement learning to achieve performance better than model predictive control and rule based control benchmarks under battery model uncertainty and comparable performance with benchmarks under no uncertainty. We utilize domain randomization and random network distillation exploration strategies to improve reinforcement learning performance. We show that reinforcement learning achieves comparable or better performance on seven of ten analyzed microgrid scenarios of different architectures in forecasts of varying lengths. Our model code is available at https://github.com/ahalev/Microgrid-Control-Under-Uncertainty and our microgrid simulator is available at https://github.com/ahalev/python-microgrid.
Authors: Avishai Halev, Yongshuai Liu, Xin Liu
Institution: University of California, Davis
Language: English
Subfield: Control and Systems Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: hybrid
Estimated APC paid: $3,270
Funders: Total, University of California, Davis
OpenAlex ID: W4403085922