XXIV Summer School “Francesco Turco” – Industrial Systems Engineering Exploiting data analytics for improved energy management decision-making Zambetti M.*, Cimini C.*, Pirola F.*, Pinto R.* * Department of Management, Information and Industrial Engineering, University of Bergamo, via G. Marconi 5, 24044, Dalmine (BG) – Italy (michela.zambetti@unibg.it, chiara.cimini@unibg.it, fabiana.pirola@unibg.it, roberto.pinto@unibg.it) Abstract: The adoption of Internet of Things and Cloud technologies in the context of Industry 4.0 provides manufacturing industries with the opportunity to collect data from multiple sources. Analytical tools and techniques can be then applied to support decision-making processes with valuable information. Industry 4.0 technologies have been implemented in many sectors and industries: among them, energy management - often representing one of the main costs for manufacturing companies - is considered in this study. The aim of this paper is to contribute to the understanding of how the implementation of Industry 4.0 technologies and, in particular, the analysis of energy consumption data, can change or enable decision-making thereby improving energy management. Based on a literature review and current practices, possible applications of data analytics in the energy management field are proposed and several energy management decision areas are discussed. The paper includes a case study aiming at illustrating how the implementation of Industry 4.0 technologies, supported by proper strategical and operational approaches can improve energy management integrating energy consumption data with other sources of data. Keywords: Energy management, data analytics, decision-making, Industry 4.0 1. Introduction Energy efficiency represents an increasingly important leverage to achieve financial, social and environmental enhancement (Trianni et al. 2019) and a large academic literature is dedicated to energy efficiency strategies both at macro levels, such as at industry, regional or state level and at micro level, considering energy management for site, building and processes. Focusing on the industrial and manufacturing domain, energy management specifically refers to the supply, the conversion and utilization of energy (O’Callaghan and Probert 1977) and may include lot of different practices ranging from the definition of the best energy source, to the identification of energy waste, to the optimization of energy consumption during production. The adoption of those practices and their successful implementation is the result of a decision- making process both at a strategic level, considering the best strategy to adopt and at operational levels, considering more punctual and operative actions. Industry 4.0 technologies, particularly Internet of things (IoT), enables the support and enhancement of energy consumption awareness (Shrouf and Miragliotta 2015). Indeed, the adoption of real-time energy monitoring systems enables firms to better understand their energy consumption. Moreover, integrating energy data with other sources (e.g. on production, processes etc.) can actively support decision-making in the energy management, both at the operational level and in strategic evaluations (Bevilacqua et al. 2017). However, the research in decision- making related to energy management in manufacturing seems not yet well established (Zhu et al. 2015). This paper aims at revising the opportunities that data collection enabled by the adoption of technology along with the use of analytics can bring to decision-makers in the context of energy efficiency in manufacturing. In particular, it explores how different approaches to data analysis (descriptive, predictive, and prescriptive) may influence different manufacturing decision areas which impact energy consumption and efficiency. The paper is structured as follow: Section 2 discusses the literature background about on energy management in manufacturing, presenting how data can support it. Section 3 introduces the decision-making processes involved in the energy management sector, while Section 4 presents a classification of different energy management practices in which data analytics may enhance decision-making. Section 5 presents a case study on an Italian manufacturing company, which is exploring data potentials in energy management. Section 6 presents the conclusion, including limitations and further developments. 2. Literature background: Energy Management In the past decade, research on energy management in business practice at different levels has been increasingly conducted. This can be partially attributed to the increasing relevance of sustainable manufacturing principles. Several studies have been performed in various domains, ranging from energy audit practices and the assessment of audit plans (Fleiter et al. 2012), to the 215