Any-Quantile Probabilistic Forecasting of Short-Term Electricity Demand

arXiv:2404.17451v1 Announce Type: new
Abstract: Power systems operate under uncertainty originating from multiple factors that are impossible to account for deterministically. Distributional forecasting is used to control and mitigate risks associated with this uncertainty. Recent progress in deep learning has helped to significantly improve the accuracy of point forecasts, while accurate distributional forecasting still presents a significant challenge. In this paper, we propose a novel general approach for distributional forecasting capable of predicting arbitrary quantiles. We show that our general …

arxiv cs.lg demand electricity forecasting quantile stat.ml type