Probabilistic load forecasting considering temporal correlation: Online models for the prediction of households’ electrical load

Home Energy Management Systems (HEMSs) are expected to become an inevitable part of the future smart grid technologies. To work effectively, HEMSs require reliable and accurate load forecasts. In this paper, two new modelling methods presented. They both suited for producing multivariate probabilistic forecasts, which consider temporal correlation between forecast horizons. The first method employs point forecasts generated with Recursive Least Squares (RLS) models subsequently analyses forecasts’ residuals estimate marginal distributions correlation. second is based on quantile regression distributions, a Gaussian copula linking them together. Furthermore, application approaches estimation investigated each methods. As case study, numerical experiment designed emulate online HEMS operation using data from inhabited home located in Denmark. Simulation results show robust performance proposed models, quantile–copula ensemble outperforming RLS-based predicting capturing