Reference:
J. Lago, G. Marcjasz, B. De Schutter, and R. Weron, "EPFTOOLBOX: The first open-access PYTHON library for driving research in electricity price forecasting (EPF)," WORMS Software (WORking papers in Management Science Software) WORMS/C/21/01, Department of Operations Research and Business Intelligence, Wroclaw University of Science and Technology, Wroclaw, Poland, 2021.Abstract:
The library includes three distinct modules. (1) The DATA MANAGEMENT module provides functionality to manage, process, and obtain data for EPF. The module also provides access to data from five different day-ahead electricity markets: EPEX-BE, EPEX-FR, EPEX-DE, NordPool, and PJM. (2) The MODELS module grants access to state-of-the-art forecasting methods for day-ahead electricity prices - the Lasso-Estimated AutoRegressive (LEAR) model and the Deep Neural Network (DNN) model - that require no expert knowledge and can be automatically employed. (3) The EVALUATION module provides with an easy-to-use interface for evaluating forecasts in EPF. This module includes both scalar metrics like MAE or MASE as well as statistical tests to evaluate the statistical significance in forecasting performance. The EPFTOOLBOX library is thoroughly described in: J. Lago, G. Marcjasz, B. De Schutter, R. Weron (2021) "Forecasting day-ahead electricity prices: A review of state-of-the-art algorithms, best practices and an open-access benchmark", Applied Energy 293, 116983 (https://doi.org/10.1016/j.apenergy.2021.116983; open access).Downloads:
Related paper:
Bibtex entry: