Economic Interest of Heating and Hot Water Prediction System for Residential District

This work presents a data-intensive solution topredict heating and hot water consumption. The ability topredict locally those flexible sources considering meteorologicaluncertainty can play a key role in the management of microgrid. A microgrid is a building block of future smart grid, it canbe defined as a network of low voltage power generating units, storage devices and loads. The main novelties of our approach isto provide an easy implemented and flexible solution which usedsupervised learning techniques. This paper presents an industrialmethodology to predict heating and hot water consumption usingtime series analyzes and tree ensemble algorithm. Consideringthe winter season 2012-2013 for the training, the heating and hotwater predictions is correctly estimated 90% +/- 1.2 for the winterseason 2013-2014. The results are based on the data collected ina building in Chamoson (Switzerland) and simulations. The aimis to provide to the virtual power plant the possibility to pilot anpart of energy consumption. The input data for the pilot is theeconomic parameter. Considering the economic input data for theenergy management, a new heasting and hot water consumption is provided for one week.