Forecasting of Energy Commodities
The ARES group develops data-driven tools for forecasting and optimization in renewable-based energy systems. Our activities focus on the use of machine learning and statistical methods to improve the accuracy of renewable power and load forecasts, supporting the reliable operation of hybrid power stations and microgrids.
Recent studies include the application of regression and neural network models to predict electric load demand in small island systems, and the development of machine-learning correction methods to enhance day-ahead forecasts of solar and wind power generation. These research efforts contribute to the improvement of energy management, scheduling, and storage control in isolated grids with high renewable penetration.
Last update
06.11.2025