An Improved Quantile Regression Neural Network for Probabilistic Load Forecasting

Abstract

Accurate and reliable load forecasting is essential for decision-making processes in the electric power industry. As the power industry transitions toward decarbonization, distributed energy systems, and integration of smart grid features, an increasing number of decision-making processes rely on uncertainty analysis of electric load. However, traditional point forecasting cannot address the uncertainties with only one forecasting value generated at each time step. As they are capable of representing uncertainties, probabilistic forecasts such as prediction intervals and quantile forecasts are preferred. Nevertheless, their practical application is limited partly due to the long training time of multiple probabilistic forecasting models. Traditional quantile regression neural network (QRNN) can train a single model for making quantile forecasts for multiple quantiles at one time. Whereas, the training cost is still unaffordable with large datasets. This paper proposes an improved QRNN (iQRNN) to address the issues of traditional QRNN, which incorporates popular techniques in deep learning areas. A case study on a publicly available dataset shows that not only can the proposed iQRNN generate remarkably superior quantile forecasts than state-of-the-art methods, but also the proposed iQRNN is more accurate, stable, and computationally efficient than traditional QRNN.