Optimizing a domestic battery and solar photovoltaic system with deep reinforcement learning

TL;DR

This paper applies deep reinforcement learning to optimize domestic solar battery systems, significantly reducing household electricity costs by intelligently managing battery charging and discharging in stochastic environments.

Contribution

It introduces a deep deterministic policy gradient approach for continuous control of home batteries, demonstrating effective cost savings in real-world scenarios.

Findings

Reduced household electricity expenditure to nearly $1 AUD for large batteries.

Effective in stochastic environments with variable solar and consumption patterns.

Demonstrated performance over selected weeks within a year.

Abstract

A lowering in the cost of batteries and solar PV systems has led to a high uptake of solar battery home systems. In this work, we use the deep deterministic policy gradient algorithm to optimise the charging and discharging behaviour of a battery within such a system. Our approach outputs a continuous action space when it charges and discharges the battery, and can function well in a stochastic environment. We show good performance of this algorithm by lowering the expenditure of a single household on electricity to almost \$1AUD for large batteries across selected weeks within a year.