Robust and learning-augmented algorithms for degradation-aware battery optimization

TL;DR

This paper develops robust and learning-augmented algorithms for optimizing grid-scale battery revenue, considering uncertain prices and degradation effects, with proven performance guarantees in stochastic and adversarial environments.

Contribution

It introduces a novel online mirror descent-based algorithm for degradation-aware battery optimization, incorporating learning-augmented strategies for improved performance with advice.

Findings

No-regret guarantees in stochastic settings

Finite asymptotic competitive ratio in adversarial settings

Effective learning-augmented approach with advice

Abstract

This paper studies the problem of maximizing revenue from a grid-scale battery energy storage system, accounting for uncertain future electricity prices and the effect of degradation on battery lifetime. We formulate this task as an online resource allocation problem. We propose an algorithm, based on online mirror descent, that is no-regret in the stochastic i.i.d. setting and attains finite asymptotic competitive ratio in the adversarial setting (robustness). When untrusted advice about the opportunity cost of degradation is available, we propose a learning-augmented algorithm that performs well when the advice is accurate (consistency) while still retaining robustness properties when the advice is poor.