Probabilistic Forecasting of Day-Ahead Electricity Prices and their Volatility with LSTMs
This work addresses the problem of accurate electricity price forecasting for power system management and smart applications, particularly in the context of increased volatility post-Ukraine invasion, representing an incremental improvement with a hybrid method.
The authors tackled the challenge of forecasting highly volatile day-ahead electricity prices in the German-Luxembourg market, developing an LSTM model that jointly predicts mean and standard deviation for probabilistic forecasting, achieving faithful reproduction of both prices and volatility.
Accurate forecasts of electricity prices are crucial for the management of electric power systems and the development of smart applications. European electricity prices have risen substantially and became highly volatile after the Russian invasion of Ukraine, challenging established forecasting methods. Here, we present a Long Short-Term Memory (LSTM) model for the German-Luxembourg day-ahead electricity prices addressing these challenges. The recurrent structure of the LSTM allows the model to adapt to trends, while the joint prediction of both mean and standard deviation enables a probabilistic prediction. Using a physics-inspired approach - superstatistics - to derive an explanation for the statistics of prices, we show that the LSTM model faithfully reproduces both prices and their volatility.