Neural Network Based Home Energy Management for Modelling and Controlling Home Appliances under Demand Response

Nowadays, the consumption of homes is around 40% of the total world consumption. Furthermore, 21% of the total greenhouse gas emissions are produced by homes. The emergence of smart grids has presented new opportunities for home energy management (HEM) systems for the purpose of reducing energy in the residential sector. Demand response (DR) tool that curtails and shifts demand to enhance the consumption of energy at home. It usually creates optimal schedules for energy consumption by considering load profiles, the cost of energy, level of comfort people, and environmental concerns. The deployment of smart meters, it is possible to control the load by using HEM system with demand response (DR) enabled appliances. Without a proper system, it is difficult to efficiently control the energy in houses. In this work, a Neural Network technique as a controller to control the energy in the building with DR strategy is developed to control and reduce peak demand load. Reduce the electricity cost and power consumption for the appliances while maintaining customer comfort is the motivation of this work. The electrical appliance such as air conditioning (AC), electric water heater (WH), washing machine (WM), and refrigerator (RF) were modeled using the Matlab program. The designed model can make an accurate decision in scheduling and shifting the operation of the electrical appliance at the peak time by scheduling the s domestic household at a specific time with no affecting the customer's preference. (paper)