This paper presents a cluster analysis study on energy consumption dataset to profile ”groups of customers” to whom address POWERCLOUD services. POWER CLOUD project (PON I&C2014-2020) aims to create an energy community where each consumer can become also energy producer (PROSUMER) and so exchange a surplus of energy produced by renewable sources with other users, or collectively purchase or sell wholesale energy. In this framework, an online questionnaire has been developed in order to collect data on consumers behaviour and their preferences. Together with demographic data, the most relevant information has been collected on home appliances and their actual power consumption, main sources of heating or cooling, the availability to adopt domotic solutions and in general, their availability to change their consumption profile according to renewable source. A clustering analysis was carried on the filled questionnaires using Wolfram Mathematica software, in particular FindClusters [1] function, to automatically group related segments of data. FindCluster function applies Machine Learning techniques to select and group homogeneous elements in a set of data to reduce the search space and to find the optimal solutions [2]. In our work, clustering analysis allowed to better understand the energy consumption propensity according the identified demographic variables. Thus, the outcomes highlight how the availability to adopt technologies to be used in PowerCloud energy community, increases with the growth of the family unit and, a greater propensity is major present in the age groups of 25-34 and 35-44

Clustering analysis to profile customers behaviour in POWER CLOUD energy community

Lorella Gabriele;Francesca Bertacchini;Simona Giglio;Daniele Menniti;Pietro Pantano;Anna Pinnarelli;Nicola Sorrentino;Eleonora Bilotta
2019-01-01

Abstract

This paper presents a cluster analysis study on energy consumption dataset to profile ”groups of customers” to whom address POWERCLOUD services. POWER CLOUD project (PON I&C2014-2020) aims to create an energy community where each consumer can become also energy producer (PROSUMER) and so exchange a surplus of energy produced by renewable sources with other users, or collectively purchase or sell wholesale energy. In this framework, an online questionnaire has been developed in order to collect data on consumers behaviour and their preferences. Together with demographic data, the most relevant information has been collected on home appliances and their actual power consumption, main sources of heating or cooling, the availability to adopt domotic solutions and in general, their availability to change their consumption profile according to renewable source. A clustering analysis was carried on the filled questionnaires using Wolfram Mathematica software, in particular FindClusters [1] function, to automatically group related segments of data. FindCluster function applies Machine Learning techniques to select and group homogeneous elements in a set of data to reduce the search space and to find the optimal solutions [2]. In our work, clustering analysis allowed to better understand the energy consumption propensity according the identified demographic variables. Thus, the outcomes highlight how the availability to adopt technologies to be used in PowerCloud energy community, increases with the growth of the family unit and, a greater propensity is major present in the age groups of 25-34 and 35-44
2019
9788874581016
Machine learning; Cluster analysis; Consumer behaviour
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.11770/294609
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact