An ensemble methodology for hierarchical probabilistic electric vehicle load forecasting at regular charging stations

Abstract

Transportation electrification is a valid option for supporting decarbonization efforts but, at the same time, the growing number of electric vehicles will produce new and unpredictable load conditions for the electrical networks. Accurate electric vehicle load forecasting becomes essential to reduce adverse effects of electric vehicle integration into the grid. In this paper, a methodology dedicated to probabilistic electric vehicle load forecasting for different geographic regions is presented. The hierarchical approach is applied to decompose the problem into sub-problems at low-level regions, which are resolved through standard probabilistic models such as gradient boosted regression trees, quantile regression forests and quantile regression neural networks, coupled with principal component analysis to reduce the dimensionality of the sub-problems. The hierarchical perspective is then finalized to forecast the aggregate load at a high-level geographic region through an ensemble methodology based on a penalized linear quantile regression model. This paper brings, as relevant contributions, the development of hierarchical probabilistic forecasting framework, its comparison with non-hierarchical frameworks, and the assessment of the role of data dimensionality refduction. Extensive experimental results based on actual electric vehicle load data are presented which confirm that the hierarchical approaches increase the skill of probabilistic forecasts up to 9.5% compared with non-hierarchical approaches.