Gaussian Process Regression With Hybrid Risk Measure for Dynamic Risk Management in Electricity Market

In this work we introduce an innovative approach to managing electricity costs within the framework of Germany’s evolving energy market, where dynamic tariffs are increasingly becoming central due to the integration of renewable energy sources and market price fluctuations. In line with recent German government policies, particularly the Energiewende (energy transition) and EU directives on clean energy, this work optimizes electricity procurement by forecasting hourly prices over a one-week horizon and allocating a fixed budget using Value at Risk and Conditional Value at Risk to minimize financial risk. This optimization model empowers consumers to adjust their consumption patterns based on predicted price fluctuations, aligning with Germany’s goals of promoting flexibility, reducing emissions, and integrating renewable energy into the grid. By supporting smarter consumption decisions based on enhanced cost predictability via Gaussian Process Regression , this work contributes to the realization of a sustainable, flexible, and efficient energy market as outlined in Germany’s Renewable Energy Act.