Prediction and Evaluation of Electricity Price in Restructured Power Systems Using Gaussian Process Time Series Modeling

The electricity market is particularly complex due to the different arrangements and structures of its participants. If energy price in this presents a conceptual well-known way, complexity will be greatly reduced. Drastic changes supply demand markets are challenge for prices (EPs), which necessitates short-term forecasting EPs. In study, two restructured power systems considered, EPs these entirely accurately predicted using Gaussian process (GP) model that adapted time series predictions. modeling, various models GP, including dynamic, static, direct, indirect, as well their mixture models, used investigated. effectiveness accuracy compared appropriate evaluation indicators. results show combinations GP have lower errors than individual dynamic indirect was chosen best model.