Hierarchical Bayesian Network Model for Probabilistic Estimation of EV Battery Life

Bayesian models are applied to probabilistic analysis of phenomena which deal with multiple external stochastic factors and unmeasurable variables. Considering the large amount of available data for the EV driving, recharging and grid services such as solar charging which contains uncertainties and measurement errors, and their hierarchical effect on the battery life, this application of Bayesian models can be useful for the aging probabilistic analysis. Causality is of utmost importance for batteries as their aging is affected by a high number of hierarchical variables that depend upon external factors to the battery. Acknowledging the advantages of Bayesian models, we propose a hierarchical Bayesian model for the probabilistic battery degradation evaluation. Priors distributions are defined based on expert knowledge and Marco Chain Monte Carlo (MCMC) sampling is used to draw the posteriors. This modeling approach reflects the uncertainties of measurements and process, provides more informative results, and it is applicable to any type of input data with proper training.