Predictive model generation for load forecasting in district heating networks

District heating networks (DHNs) are promising technologies to increase the efficiency and reduce emissions of heatdistribution to residential and commercial buildings. The advent of the smart grid paradigm has introduced the usage of heating loadforecasting tools in DHNs. They provide estimates of future heating load, improving the planning of heat production and power stationmaintenance. In this work, we propose a methodology based on the integrated use of regularized regression and clustering forgenerating predictive models of future heating load in DHNs. The methodology is tested on a real case study based on a datasetprovided by AGSM, an Italian utility company that manages a DHN in the city of Verona, Italy. We generate a set of multiple-equationmodels having different degrees of complexity and show that models generated by the proposed approach outperform those trained bystandard methods. Moreover, we provide an interpretation of patterns encoded by these models, and show that they identify realoperational states of the network. The approach is completely data-driven.