Exploring energy performance certificates through visualization Tania Cerquitelli * , Evelina Di Corso * , Stefano Proto * , Alfonso Capozzoli † , Fabio Bellotti * , Maria G. Cassese * , Elena Baralis * , Marco Mellia ‡ , Silvia Casagrande § , Martina Tamburini § * Department of Control and Computer engineering, Politecnico di Torino, Torino, Italy † Department of Energy, Politecnico di Torino, Torino, Italy ‡ Department of Electronics and Telecommunications, Politecnico di Torino, Torino, Italy § Edison Spa, Torino, Italy *†‡ name.surname@polito.it § name.surname@edison.it ABSTRACT Energy Performance Certifcates (EPCs) provide interesting infor- mation on the standard-based calculation of energy performance, thermo-physical and geometrical related properties of a build- ing. Because of the volume of available data (issued as open data) and the heterogeneity of the attributes, the exploration of these energy-related data collection is challenging. This paper presents INDICE (INformative DynamiC dashboard Engine), a new data visualization framework able to automatically explore large collections of EPCs. INDICE explores EPCs through both querying and analytics tasks, and intuitively presents the output through informative dashboards. The latter include dynamic and interactive maps along with diferent informative charts allow- ing diferent stakeholders (e.g., domain and non-domain expert users) to explore and interpret the extracted knowledge at dif- ferent spatial granularity levels. The objective of INDICE is to create energy maps useful for the characterization of the energy performance of buildings located in diferent areas. The exper- imental evaluation, performed on a real set of EPCs related to a major Italian region in the North West of Italy, demonstrates the efectiveness of INDICE in exploring an EPC dataset through diferent data and knowledge visualization techniques. 1 INTRODUCTION Nowadays large volumes of energy-related data are continuously collected in diferent domains. To reduce wasteful energy con- sumption, several orthogonal applications (e.g., buildings, IoT- based devices, wireless networks) increased their policy priority on energy efciency. According to the U.S. Department of En- ergy, in industrialized countries more than 40% of total energy is consumed in buildings [14]. In the last few years many eforts have been devoted to improve building energy efciency with dif- ferent fnal goals: (i) facilitating proactive energy-saving services [32], (ii) characterizing data streams of energy consumption of individual residential consumers in buildings [5ś7], (iii) charac- terizing heating energy demand through the analysis of energy performance certifcates of buildings [4, 9, 11], and (iv) reducing emissions and energy consumption for buildings [20]. © 2019 Copyright held by the author(s). Published in the Workshop Proceedings of the EDBT/ICDT 2019 Joint Conference (March 26, 2019, Lisbon, Portugal) on CEUR-WS.org. To enhance the efectiveness of data and knowledge explo- ration, a variety of data visualization techniques have been pro- posed. In [22, 23, 26] the authors exploited choropleth maps to analyze the energy consumption and the electricity consump- tion per unit area, respectively. Instead, in [21], the authors used dynamic simulations of building energy consumption and build- ing information to develop urban energy maps with high spatial resolutions. However, all the above works proposed static maps to analyze the average values of some features of interest. The exploitation of dynamic and navigable maps tailored to the anal- ysis of energy-related data has not been proposed so far. The authors in [24] propose an interactive 3D visualization to analyze the Linking Open Data (LOD) cloud adopting the metaphor of urban area. The visualization is interactive, meaning that the user can enlarge any part of the model, modify the perspective, change the shape of the buildings and their positioning, view all the connections or only those belonging to a specifc data set. A parallel research efort has been devoted to explore and summa- rize geolocated time series data through maps [8]. Moreover, a great research efort has been done in [17], in which the authors propose a city energy model based on the requests and need for visualization from a group of energy consultants. Their proposed model ofers stakeholders a powerful tool for evaluating both the current state and future scenarios. This paper presents INDICE (INformative DynamiC dashboard Engine), a data visualization framework generating interactive and navigable dashboards through the analysis of a set of Energy Performance Certifcates (EPCs). An EPC is a legal requirement when constructing, selling or renting a building, and it provides interesting information on the calculated standard energy perfor- mance, thermo-physical and geometrical properties of existing buildings. The multi-tiered framework INDICE has been pro- posed to efectively deal with large collection of EPCs. With respect to the other works, our framework brings together many diferent analysis techniques to help non-expert users make sense of Energy Performance Certifcates. Indeed, after a pre-processing step, cluster analysis allows discovering groups of EPCs with sim- ilar features. To summarize the energy performance of buildings at diferent granularities, INDICE generates informative dash- boards tailored to diferent energy stakeholders, combining both a rich set of interesting knowledge and ease of use. The proposed informative dashboards exploit diferent kinds of energy maps to show data and knowledge at diferent spatial