Forecasting of Energy Load Demand and Energy Production from Renewable Sources using In-Memory Computing

Within the conducted project, we focused on a time series approach in order to predict the short-term energy demand value. We applied the time series methods at an individual dwelling level. We formulated a hypothesis: forecasting accuracy (which is directly related to costs) can be substantially increased by the application of various individual forecasting methods not only on the level of each customer but also for each generation unit (wind turbine, photovoltaic panel) performed in quasi real-time using SAP HANA parallelism. Through this new insights into the analyzed data can be gained. The additional goal of the project was to evaluate the possibility of adding different exogenous variables to the models and being able to quickly analyze their significance.

Project duration: Spring 2013
External project website: