Climatization and luminosity optimization of buildings using genetic algorithm, random forest, and regression models

Abstract

With the rise in popularity of artificial intelligence, coupled with the growing concern over the environment, there has been a surge in the use of intelligent energy management systems. Additionally, as more buildings transition into the smart grid and, consequently, more energy and environmental data is gathered, there has been a significant increase in the number of data-driven approaches for building management systems. This paper proposes a methodology that aims to optimize the climatization and luminosity inside a building, using a genetic algorithm, a random forest, and two polynomial models. The proposed methodology enables the real-time management of the building taking into account the user needs and preferences. Air conditioner units and light systems are optimized to minimize energy costs, while also improving the air quality and considering the users’ temperature and luminosity preferences. This paper shows the results achieved, by the proposed solution, in an office building case study. The promising results demonstrate the possibility of minimizing energy costs while maximizing the users’ comfort.

Peer-to-peer energy trading optimization in energy communities using multi-agent deep reinforcement learning

“…

Power systems are becoming increasingly distributed in terms of the management of the grid and the engagement of energy players. This allows the creation of smaller communities, such as microgrids and energy communities, usually composed of smart buildings (Mota et al 2021), in which local energy management is carried out using local energy demand and renewable energy sources (RES). In this context,

…”