Adaptive Probabilistic Forecasting of Electricity (Net-)Load

TL;DR

This paper introduces an adaptive, probabilistic load forecasting method using Kalman filters and quantile regressions, effectively capturing load uncertainties and responding to changing conditions in power systems.

Contribution

It presents a novel adaptive probabilistic forecasting approach that combines Kalman filtering with online quantile regression, improving accuracy and responsiveness in load prediction.

Findings

Adaptive models outperform static ones in load forecasting accuracy.

Probabilistic forecasts effectively quantify uncertainty in load predictions.

Method demonstrates robustness across different geographic regions and data sets.

Abstract

Electricity load forecasting is a necessary capability for power system operators and electricity market participants. The proliferation of local generation, demand response, and electrification of heat and transport are changing the fundamental drivers of electricity load and increasing the complexity of load modelling and forecasting. We address this challenge in two ways. First, our setting is adaptive; our models take into account the most recent observations available, yielding a forecasting strategy able to automatically respond to changes in the underlying process. Second, we consider probabilistic rather than point forecasting; indeed, uncertainty quantification is required to operate electricity systems efficiently and reliably. Our methodology relies on the Kalman filter, previously used successfully for adaptive point load forecasting. The probabilistic forecasts are obtained by quantile regressions on the residuals of the point forecasting model. We achieve adaptive quantile regressions using the online gradient descent; we avoid the choice of the gradient step size considering multiple learning rates and aggregation of experts. We apply the method to two data sets: the regional net-load in Great Britain and the demand of seven large cities in the United States. Adaptive procedures improve forecast performance substantially in both use cases for both point and probabilistic forecasting.