Manuscript received January 20, 2025; revised February 22, 2025; accepted March 7, 2025; published May 20, 2025
Abstract—In a sustainable development approach focused on
three pillars, reducing the ecological footprint of anthropogenic
activities is a major issue. In France, the building sector, which
includes the residential and tertiary sectors, is one of the most
energy-intensive sectors. Natural gas (fossil energy) is the
energy vector most used to meet the significant energy needs of
residential buildings. To reduce the carbon footprint, the
energy renovation of residential and tertiary buildings can
prove to be a key pillar for meeting sustainable development
indicators and thus safeguarding our environment. The use of
artificial intelligence, in this case neural networks, could make
it possible to achieve enormous energy savings since it can
analyze the building in its smallest details, studying the
performances and specificities of existing energy systems and
then propose improvements and renovation scenarios that are
much more adapted to the behavior and model of the building.
In concrete terms, how can neural networks be used, through
learning, to suggest relevant actions for improving energy
performance? This article first presents the role that artificial
intelligence, in this case neural networks, could play in the
context of the energy renovation of existing buildings, then a
neural network applied to a project in order to propose actions
to improve energy performance and more efficient renovation
scenarios. The authors made a combined use of neural networks
and genetic algorithms allowing respectively a rapid evaluation
and optimization of the data sought.
Keywords—static analysis, dynamic analysis, malware
detection, hybrid approach, energy performance
Cite: Aboudoul-Manaf Issifou, Smain Femmam, Nadia Femmam, and Samia Nefti-Meziani, "Neural Networks to Better Identify Actions and Scenarios for Improving Energy Performance of Existing Buildings," International Journal of Machine Learning vol. 15, no. 2, pp. 40-44, 2025.
Copyright © 2025 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).