A reliable Energy Demand Management plays a vital role in the well-being and the security of modern societies. Thus, it is established as an important research topic in recent decades.
Accurate forecasts deliver powerful insights into the volume and trends of future energy consumption and provide crucial information for the decision-makers to schedule and plan operations in complex energy systems. Forecasting errors lead to unbalanced supply-demand relations, which have a negative impact on the operational costs and, more importantly, on the safety of supply networks and service quality.
Consequently, high precision in forecasts of future energy trends is a decisive matter for complex energy transmission and distribution systems.
In the Predictive Methods Group, we develop innovative, high-quality forecasting algorithms in the energy domain. Our research includes complex data analysis, both descriptive analytics (data mining and statistical analysis) and predictive analytics (machine learning and AI).
In addition to the point-wise forecast, we focus on developing advanced AI methods that benefit from the information available in the spatial-temporal correlations of high-dimensional complex gas network data.
Our goal is also to improve algorithms for the prediction of energy time series in general, for example, for forecasting in multi-energy systems or renewable energy sources.
We collaborate closely with industry partners and other research institutes.