Machine learning optimization model for reducing the electricity loads in residential energy forecasting

Abstract

Recently, households have consumed more power by overusing refrigerators, mobiles, washing machines, and electrical appliances. The incoming energy needs to be optimized, and this research uses machine learning for energy forecasting to reduce the overconsumption of power. Intelligent buildings are additionally associated with Heating, Air Conditioning (HVAC), and Ventilation Units. Due to the limited devices, it acquires only minimum communication capability. In this paper, deep learning with Meta-heuristic based algorithm has been proposed to address the constraints such as multi-objective optimization and fitness function and address the energy consumption of HVAC units. It uses a gated recurrent circuit (GRU) with a gorilla troop optimizer (GTO) to optimize the energy efficiently. This study uses the HVAC model to analyze smart buildings and addresses power consumption through HVAC systems based on power loss, price management, and reactive power. The simulation environment is performed using python at various experiments with various scenarios for proposed evaluation. Here, integrity in intelligent buildings is considered. The results outcomes are compared with other HVAC devices using different metrics and communication protocols. It has been proven that the proposed model is more effective in reducing the system's energy consumption than other approaches.