Work

Data-Assimilation-Assisted Reinforcement Learning for Power Grid Control under Load Uncertainty

Year: 2026

Type: preprint

Abstract: Reliable power grid control requires sequential decisions under transmission constraints, time-varying demand, renewable variability, and imperfect load information. We investigate how load information quality affects control in a customized transmission network simulator inspired by Grid2Op and based on a DC power flow model. The environment includes stochastic spatial loads, temporally correlated renewable-like generation, energy storage, line protection, generator dispatch, and line reconnection. An Ensemble Score Filter (EnSF) corrects noisy load information before it is passed to the controller. A heuristic study first isolates the effect of this correction under a fixed feedback rule. Proximal policy optimization (PPO) agents are then trained for sequential generator and reconnection control, frozen, and evaluated with Forward, EnSF-corrected, and Truth load information on paired stochastic scenarios. EnSF consistently lowers load estimation error. Under heuristic control, the correction extends survival and reduces warning and overload exposure. With frozen PPO policies, it increases cumulative return and keeps performance closer to the Truth benchmark, with a larger advantage when load uncertainty is amplified beyond the nominal training distribution. In both experiments, EnSF reduces load-estimation error and improves the resulting control performance in the simplified transmission network.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2609.27229

Authors: Hu, Ruoyu, Bao, Feng, Zhang, Zezhong, Cao, Yanzhao, Zhang, Guannan

Institutions: Auburn University, Florida State University, Oak Ridge National Laboratory

Language: English

Topic: Electric Power System Optimization

Subfield: Electrical and Electronic Engineering

Field: Engineering

Domain: Physical Sciences

SDGs: Affordable and clean energy, Industry, innovation and infrastructure

Open Access status: green

Funders: National Science Foundation, U.S. Department of Energy, Office of Science, Advanced Scientific Computing Research