A perspective on the enabling technologies of explainable AI-based industrial packetized energy management
Daniel Gutierrez-Rojas,
Arun Narayanan,
Cássia R. Santos Nunes Almeida,
Gustavo M. Almeida,
Diana Pfau,
Yu Tian,
Xu Yang,
Alex Jung,
Pedro H.J. Nardelli
Affiliations
Daniel Gutierrez-Rojas
School of Energy Systems, Lappeenranta–Lahti University of Technology, Yliopistonkatu 34, 53850 Lappeenranta, South Karelia, Finland; Corresponding author
Arun Narayanan
School of Energy Systems, Lappeenranta–Lahti University of Technology, Yliopistonkatu 34, 53850 Lappeenranta, South Karelia, Finland
Cássia R. Santos Nunes Almeida
School of Energy Systems, Lappeenranta–Lahti University of Technology, Yliopistonkatu 34, 53850 Lappeenranta, South Karelia, Finland; Department of Electrical Engineering, Federal Center for Technological Education of Minas Gerais, Av. Amazonas 5253, Belo Horizonte, MG 30.421-169, Brazil
Gustavo M. Almeida
School of Energy Systems, Lappeenranta–Lahti University of Technology, Yliopistonkatu 34, 53850 Lappeenranta, South Karelia, Finland; Department of Chemical Engineering, School of Engineering, Federal University of Minas Gerais, Av. Amazonas 5253, Belo Horizonte, MG 30.421-169, Brazil
Diana Pfau
Department of Computer Science, Aalto University, Konemiehentie 2, 02150 Espoo, Uusima, Finland
Yu Tian
Department of Computer Science, Aalto University, Konemiehentie 2, 02150 Espoo, Uusima, Finland
Xu Yang
Department of Computer Science, Aalto University, Konemiehentie 2, 02150 Espoo, Uusima, Finland
Alex Jung
Department of Computer Science, Aalto University, Konemiehentie 2, 02150 Espoo, Uusima, Finland
Pedro H.J. Nardelli
School of Energy Systems, Lappeenranta–Lahti University of Technology, Yliopistonkatu 34, 53850 Lappeenranta, South Karelia, Finland
Summary: This paper reviews the key information and communication technologies that are necessary to build an effective industrial energy management system considering the intermittence of renewable sources like wind and solar †. In particular, we first introduce the concept of software-defined energy networks in the context of industrial cyber-physical systems aiming at the optimal energy resource allocation in terms of its environmental impact. The task is formulated as a dynamic scheduling problem where supply and demand must match at minute-level timescale, also considering energy storage units. The use of (explainable and trustworthy) artificial intelligence (AI), (informative) networked data, demand-side management, machine-type (wireless) communications, and energy-aware scheduling in industrial plants are explored in detail. The paper also provides a framework for understanding the complexities of managing renewable energy sources in industrial plants while maintaining efficiency and environmental sustainability.
