Optimizing Demand Response and Renewable Energy Integration for Sustainable Residential Solutions: An Illinois Case Study

This paper presents an energy management system for a smart home equipped with rooftop photovoltaic panels, micro wind turbines, and battery storage designed to support decarbonization and reduce energy costs. Using one year of energy consumption data from a house in Herrin, Illinois, the study forecasts energy demand, solar irradiance, and wind speed for the upcoming year with Artificial Neural Networks (ANN). These forecasts inform a Mixed-Integer Linear Programming (MILP) optimization model, implemented using Gurobi, to minimize costs and optimize Distributed Energy Resources (DERs) sizing. The model also schedules demand response components, including electric vehicles, washers, dryers, and dishwashers. Results show a 29% reduction in annual energy costs. With a 7% interest rate and a 15-year equipment lifetime, the investment pays back within 4 years. This approach highlights the potential of integrating renewable energy and optimization for sustainable residential energy management. The results also show that the study can be improved by utilizing advanced forecast techniques and detailed equipment models.