Deep Learning for Energy Markets
This work addresses forecasting challenges for energy market participants, but it is incremental as it combines existing deep learning and extreme value theory techniques.
The paper tackles the problem of predicting extreme loads and prices in energy markets, which are challenging due to sharp peaks and troughs from supply-demand fluctuations, by applying deep learning and extreme value theory. The result shows that their DL-EVT method outperforms traditional Fourier time series methods in capturing nonlinearities, as demonstrated using hourly data from 4719 nodes of the PJM interconnection.
Deep Learning is applied to energy markets to predict extreme 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 deep spatio-temporal models and extreme value theory (EVT) to capture theses effects and in particular the tail behavior of load spikes. Deep LSTM architectures with ReLU and $\tanh$ activation functions can model trends and temporal dependencies while EVT captures highly volatile load spikes above a pre-specified threshold. To illustrate our methodology, we use hourly price and demand data from 4719 nodes of the PJM interconnection, and we construct a deep predictor. We show that DL-EVT outperforms traditional Fourier time series methods, both in-and out-of-sample, by capturing the observed nonlinearities in prices. Finally, we conclude with directions for future research.