Intelligent Energy Optimization for Sustainable Green Buildings Using Artificial Intelligence

Abstract

Buildings use a lot of energy and generate carbon emissions, so there is a need for an energy-management system that is intelligent enough to optimize energy use, save energy, and maintain the comfort of the people who inhabit the building while reducing carbon emissions. Building-management strategies currently operate in a static manner, with separate optimization for HVAC, lighting, appliances, and renewable resources. This paper suggests an AI-based framework called GreenOptNet, which incorporates multimodal sensor fusion, occupancy determination, HVAC and lighting control adaptation, appliance scheduling, coordinating renewable energy, and sustainability evaluation. This framework was tested with smart building energy, occupancy, environmental, solar-generation, and battery data. GreenOptNet was successful in energy savings of 43.68%, energy use of 84.72 kWh, HVAC efficiency of 98.53%, and occupant comfort of 98.84%. It also recorded a 96.74% renewable energy use and a 46.85% reduction in carbon emissions and operational cost savings of 44.36%. Ablation analyses confirmed that each module of the frameworks contributed, and statistical testing showed significant improvement over the compared models. The results have indicated that GreenOptNet is an effective, reliable, and sustainable solution for intelligent energy management in nextgeneration green buildings.