Interpretable Deep Reinforcement Learning for Optimizing Heterogeneous Energy Storage Systems

TL;DR

This paper introduces an interpretable deep reinforcement learning approach for optimizing heterogeneous energy storage systems, combining cost-effective scheduling with transparent decision-making to enhance renewable energy utilization.

Contribution

It proposes a novel prototype-based policy network that offers interpretable scheduling strategies for heterogeneous PV-ESS, integrating real-world cost considerations.

Findings

The method achieves effective energy arbitrage optimization.

It provides naturally explainable scheduling decisions.

Outperforms black-box models in practical scenarios.

Abstract

Energy storage systems (ESS) are pivotal component in the energy market, serving as both energy suppliers and consumers. ESS operators can reap benefits from energy arbitrage by optimizing operations of storage equipment. To further enhance ESS flexibility within the energy market and improve renewable energy utilization, a heterogeneous photovoltaic-ESS (PV-ESS) is proposed, which leverages the unique characteristics of battery energy storage (BES) and hydrogen energy storage (HES). For scheduling tasks of the heterogeneous PV-ESS, cost description plays a crucial role in guiding operator's strategies to maximize benefits. We develop a comprehensive cost function that takes into account degradation, capital, and operation/maintenance costs to reflect real-world scenarios. Moreover, while numerous methods excel in optimizing ESS energy arbitrage, they often rely on black-box models with opaque decision-making processes, limiting practical applicability. To overcome this limitation and enable transparent scheduling strategies, a prototype-based policy network with inherent interpretability is introduced. This network employs human-designed prototypes to guide decision-making by comparing similarities between prototypical situations and encountered situations, which allows for naturally explained scheduling strategies. Comparative results across four distinct cases underscore the effectiveness and practicality of our proposed pre-hoc interpretable optimization method when contrasted with black-box models.