Classification Machine Learning Applications for Energy Management Systems in Distribution Systems to Diminish CO2 Emissions

Current distribution systems face structural changes with the rapid adoption of Alternative Generations Sources (AGS). The integration of AGS comes with challenges in key areas such as planning, operation, control, and management. Operation and management paradigms are faced by implementing Energy Management Systems (EMS) that consider the intermittency of AGS, the coordination of other distributions assets, and demand-side management strategies. However, the stochastic behavior generation and consumption agents can hinder the reliability and flexibility of such management strategies. The adoption of Machine Learning (ML) in EMS represents an area of opportunity to increase the management flexibility and reliability. By incorporating ML, EMS can learn generation and consumption characteristics and tailor the decision-making process for improved management and operation solutions to the current paradigms, leading to optimized and more sustainable systems. The contribution of this chapter is to give a classification of the different implementations of ML in the development of EMS and how these can be a defining factor in the future operation of smart cities as larger distribution systems. © 2024 selection and editorial matter, Manuel Cebral-Loureda, Elvira G. Rincón-Flores and Gildardo Sanchez-Ante.

Classification Machine Learning Applications for Energy Management Systems in Distribution Systems to Diminish CO2 Emissions Book in Scopus