Intelligent Energy Consumption for Smart Homes using Fused Machine Learning Technique

Abstract

Energy is an essential contribution for practically all exercises and is, in this way, imperative for development in personal satisfaction. Because of this explanation, valuable energy has turned into an expansion sought after for many years, particularly utilizations in smart homes and structures as individuals create quickly and improve their way of life dependent on current innovation. The energy requirement is higher than the production of energy, which makes a shortage of energy. Many new plans are being created to satisfy the energy consumer interest. Energy utilization in the housing area is 30-40% of the multitude of areas. A smart home's existence and growth has raised the need for more intelligence in applications such as resource management, energy efficiency, security, and health monitoring so that the home can learn about residents' activities and predict future needs. An energy management technique is being applied in this research work to overcome the challenges of energy consumption optimization. Data fusion has recently attracted much attention for energy efficiency in buildings, where numerous types of information may be processed. The proposed research developed a model by using the data fusion approach to predict energy consumption in terms of accuracy and miss rate. The proposed approach simulation results are being associated with the previously published techniques. Additionally, the prediction accuracy of the anticipated method attains 92%, which is higher than the previous published approaches.