Machine learning estimation of battery state of health in residential photovoltaic systems

As the global adoption of residential battery storage systems paired with local photovoltaic (PV) generation increases, prosumers are increasingly motivated to reduce both their electricity costs and dependence on the grid. This shift highlights the importance of accurately evaluating and predicting the battery's State of Health (SOH) and Remaining Useful Life (RUL). These factors are crucial for determining the operational costs and longevity of battery systems. Traditionally, SOH predictions have relied heavily on detailed measurement data and time-intensive simulations. In response, we introduce a new AI-based approach that simplifies SOH estimation. Our method, named "ML Battery Life Predictor (MLBatLife)," leverages forecasted or historical PV generation data and load consumption patterns to quickly forecast the SOH for various battery configurations. Tested on simulated data, this tool demonstrated a high accuracy, with a coefficient of determination of 0.986 for predictions one day ahead, and an impressively low average error of 0.1 % for projections five years into the future. This innovative AI-driven technique offers substantial benefits for evaluating the economic viability and warranty parameters of battery installations in different regions. It provides a valuable resource for both industry stakeholders and energy system planners aiming to assess and anticipate battery health outcomes efficiently. • Data-driven methods precisely replicate equation-based SOH forecasts for batteries. • Five-year SOH estimates differ by less than 0.1 % from equation-based results. • Data-driven predictions are about 10k times faster than the equivalent simulation. • Machine learning estimators perform better on calendar than cycle aging.