Advancing energy storage systems through machine learning: Current developments, technical challenges, and future directions

doi:10.1016/j.applthermaleng.2026.131023

Advancing energy storage systems through machine learning: Current developments, technical challenges, and future directions

2026-04-14

0

PRE

AI

DOI：10.1016/j.applthermaleng.2026.131023

Original

Original request for help

Save

Abstract

En 中文

• In-depth analysis of ML-driven advancements in modern energy storage technologies. • Exploration of advanced algorithms and tailored ML approaches for ESS applications. • Emphasis on ML applications in battery thermal management, thermal energy storage, and electronics cooling. • Identification of key challenges, including data scarcity, limited interpretability, and high computational cost. • Strategic recommendations to address challenges, enhance energy efficiency, and support global climate goals.

Keywords:

Machine Learning

Energy Storage Systems

Battery Thermal Management

Thermal Energy Storage

Electronics Cooling

Advancing energy storage systems through machine learning: Current developments, technical challenges, and future directions

Abstract

Journal

Organization