Análisis Exhaustivo de los Sistemas de Gestión de la Energía en Hogares Inteligentes

Abstract

Introduction: In recent years, the manner in that human beings inhabits it has transformed thanks to the fast advance in technologies applied to the home, revolutionizing the form in that people interact with their domestic environment to provide comfort, security, and efficiency,  Allowing the homes nowadays stop being static buildings,   to becoming in monitoring and control technology gifted systems, facilitating to users the supervision and regulation of appliances as lighting, air conditioning, entertainment, and security access, that is known as Smart Home. One of the challenges in Smart Homes is energy efficiency.  With increasing user dependence on the use of electronic devices and connected systems, optimizing energy use to reduce billing costs and minimize the impact on the environment makes the use of smart energy management systems relevant.

Objective: This paper aims to present a conceptual review and applications related to Energy Management Systems in Smart Homes.

Method: For the development of this paper, specialized databases such as SCOPUS, Science Direct, and IEEE were consulted, using query strings related to Smart Home and Energy Management Systems (HEMS).

Results:  There is a marked trend towards the use of classical and stochastic optimization methods, such as linear programming (LP), Particle Swarm (PSO), multi-agent systems, and among others, to address the minimization (or maximization) problems that arise in smart energy management.  The application of Machine Learning (ML) based methods to add predictability and efficient scheduling in HEMS was also reported.

Conclusions: The papers consulted show that there is a marked trend towards the use of classical and stochastic optimization methods, such as linear programming (LP), particle clustering (PSO), multi-agent systems, and among others, to address the minimization (or maximization) problems that arise in smart energy management.  The application of Machine Learning (ML) based methods to add predictability and efficient scheduling in HEMS was also reported.