Forecasting for Battery Storage: Choosing the Error Metric

We describe our approach to the Western Power Distribution (WPD) Presumed Open Data (POD) 6 MWh battery storage capacity forecasting competition, in which we finished second. The competition entails two distinct aims maximise daily evening peak reduction and using as much solar photovoltaic energy possible. For latter, combine a Bayesian (MCMC) linear regression model with an average generation distribution. former, introduce new error metric that allows even simple weighted combined score very well performance metric.