Deep learning for energy markets. (8th March 2020)

• Record Type: Journal Article
• Authors: Polson, Michael; Sokolov, Vadim
• Is Part Of: Applied stochastic models in business and industry. Volume 36:Number 1(2020)
• Page Start: 195
• Page End: 209
• Publication Date: 2020-03-08
• Subjects: deep learning -- energy pricing -- extreme value theory -- locational marginal price -- long‐short‐term memory -- machine learning -- peak prediction -- PJM interconnection -- rectified linear unit -- smart grid; Stochastic analysis -- Periodicals; Stochastic processes -- Periodicals; Business mathematics -- Periodicals; Finance -- Mathematical models -- Periodicals; Industrial management -- Mathematical models -- Periodicals; 338.00151923
• DOI: 10.1002/asmb.2518
• Languages: English
• ISSNs: 1524-1904

Abstract

Abstract: Deep Learning (DL) is combined with extreme value theory (EVT) to predict peak loads observed in energy grids. Forecasting energy loads and prices is challenging due to sharp peaks and troughs that arise due to supply and demand fluctuations from intraday system constraints. We propose a deep temporal extreme value model to capture these effects, which predicts the tail behavior of load spikes. Deep long‐short‐term memory architectures with rectified linear unit activation functions capture trends and temporal dependencies, while EVT captures highly volatile load spikes above a prespecified threshold. To illustrate our methodology, we develop forecasting models for hourly price and demand from the PJM interconnection. The goal is to show that DL‐EVT outperforms traditional methods, both in‐ and out‐of‐sample, by capturing the observed nonlinearities in prices and demand spikes. Finally, we conclude with directions for future research.