Use of AI Algorithms in Different Building Typologies for Energy Efficiency towards Smart Buildings

Abstract

Buildings’ heating and cooling systems account for an important part of total energy consumption. The EU’s directives and engagements motivate building owners and relevant stakeholders in the energy and construction sectors towards net zero energy buildings by maximizing the use of renewable energy sources, ICT, and automation systems. However, the high costs of investment for the renovation of buildings, in situ use of renewable energy production, and installation of expensive ICT infrastructure and automation systems in small–medium range buildings are the main obstacles for the wide adoption of EU building directives in small- and medium-range buildings. On the other hand, the concept of sharing computational and data storage resources among various buildings can be an alternative approach to achieving smart buildings and smart cities where the main control power resides on a server. Unlike other studies that focus on the implementation of AI techniques in a building or separated buildings with local processing resources and data storage, in this work a corporate server was employed to control the heating systems in three building typologies and to examine the potential benefits of controlling existing buildings in a unified energy-savings platform. The key finding of this work is that the AI algorithms incorporated into the proposed system achieved significant energy savings in the order of 20–40% regardless of building typology, building functionality, and type of heating system, despite the COVID-19 measures for frequent ventilation of the buildings, even in cases with older-type heating systems.

Keywords

• advanced control
• AI algorithms
• building modeling
• computer server
• energy efficiency in buildings