Digital Twin-Supported BESS Decision Support of RUL-Based Maintenance

The management of battery energy storage systems (BESS) faces significant challenges due to the limitations of traditional maintenance approaches, which often make it hard to capture real-time health states and lead to inefficiencies and unexpected failures. While digital twin (DT) offers a promising solution for real-time monitoring and predictive maintenance. This gap hinders the development of comprehensive decision support systems that can optimise maintenance schedules, ultimately affecting the reliability and cost-effectiveness of BESS operations. Here, we propose a novel integration of DT with an advanced strategy: an RUL-based maintenance approach that combines remaining useful life (RUL) prediction with battery availability to optimise maintenance scheduling and spare parts management. The results illustrate that this approach improves operational decision support. By addressing the specific gap in integrating advanced data-driven strategies within a DT framework, the research enhances system reliability and reduces maintenance costs for BESS. This comprehensive solution advances the broader field by providing a robust framework for real-time decision support in BESS management.