Sustainable computing approaches for remaining useful life estimation in lithium-ion batteries: Models, datasets, and intelligent battery management systems

The growing adoption of Electric Vehicles (EVs) has intensified the need for accurate Remaining Useful Life (RUL) prediction and intelligent Battery Management Systems (BMS) to ensure safety, reliability, and sustainable operation of Li-ion batteries. This review provides a structured synthesis of recent advancements in RUL estimation methodologies, categorizing them into data-driven, model-based, hybrid, and filtering approaches. In addition to methodological developments, the paper systematically examines publicly available Li-ion battery datasets, highlighting their characteristics, experimental conditions, and limitations, and discussing their influence on model generalizability and benchmarking practices. Unlike prior reviews that treat RUL prediction or BMS functionalities separately, this work explicitly integrates RUL estimation within BMS architectures, addressing energy management, thermal regulation, safety monitoring, and real-time implementation constraints. Furthermore, deployment considerations such as computational efficiency, uncertainty quantification, and embedded system limitations are critically analyzed from a sustainable computing perspective. By connecting datasets, modeling strategies, system integration, and deployment challenges, this review offers a comprehensive framework to guide future research toward scalable, interpretable, and real-time RUL prediction solutions for next-generation EV battery systems.