Predicting battery end of life from solar off-grid system field data using machine learning

Hundreds of millions of people lack access to electricity. Decentralized solar-battery systems are key for addressing this while avoiding carbon emissions and air pollution but are hindered by relatively high costs and rural locations that inhibit timely preventive maintenance. Accurate diagnosis of battery health and prediction of end of life from operational data improves user experience and reduces costs. However, lack of controlled validation tests and variable data quality mean existing lab-based techniques fail to work. We apply a scalable probabilistic machine learning approach to diagnose health in 1,027 solar-connected lead-acid batteries, each running for 400-760 days, totaling 620 million data rows. We demonstrate 73% accurate prediction of end of life, 8 weeks in advance, rising to 82% at the point of failure. This work highlights the opportunity to estimate health from existing measurements using big data techniques, without additional equipment, extending lifetime and improving performance in real-world applications.

Automated summary

Using big data techniques, researchers accurately diagnose the health of solar-connected batteries, predicting end of life in advance to address the issue of hundreds of millions lacking access to electricity.