Model-Free Approach to Fair Solar PV Curtailment Using Reinforcement Learning

TL;DR

This paper explores a reinforcement learning approach to fairly and efficiently manage solar PV curtailment in residential systems, addressing overvoltage issues without requiring detailed feeder parameters.

Contribution

It introduces a reinforcement learning method for fair PV curtailment that learns optimal strategies without needing precise feeder data, outperforming traditional methods.

Findings

All fairness metrics can be learned efficiently.

Reinforcement learning achieves near-optimal fair curtailment.

The approach improves fairness in PV energy distribution.

Abstract

The rapid adoption of residential solar photovoltaics (PV) has resulted in regular overvoltage events, due to correlated reverse power flows. Currently, PV inverters prevent damage to electronics by curtailing energy production in response to overvoltage. However, this disproportionately affects households at the far end of the feeder, leading to an unfair allocation of the potential value of energy produced. Globally optimizing for fair curtailment requires accurate feeder parameters, which are often unknown. This paper investigates reinforcement learning, which gradually optimizes a fair PV curtailment strategy by interacting with the system. We evaluate six fairness metrics on how well they can be learned compared to an optimal solution oracle. We show that all definitions permit efficient learning, suggesting that reinforcement learning is a promising approach to achieving both safe and fair PV coordination.