Any-Quantile Probabilistic Forecasting of Short-Term Electricity Demand
This work addresses uncertainty management in power systems, offering a practical solution for risk mitigation in electricity demand forecasting.
The paper tackles the challenge of accurate distributional forecasting for short-term electricity demand by proposing a novel general approach capable of predicting arbitrary quantiles, achieving state-of-the-art results validated on 35 hourly time-series for European countries.
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 approach can be seamlessly applied to two distinct neural architectures leading to the state-of-the-art distributional forecasting results in the context of short-term electricity demand forecasting task. We empirically validate our method on 35 hourly electricity demand time-series for European countries. Our code is available here: https://github.com/boreshkinai/any-quantile.