A Prosumer Model Based on Smart Home Energy Management and Forecasting Techniques

This work presents an optimization framework based on mixed-integer programming techniques for a smart home’s optimal energy management. In particular, through cost-minimization objective function, the developed approach determines day-ahead scheduling of all load types that can be either inelastic or take part in demand response programs and charging/discharging electric vehicle storage. The underlying system also interact with power grid, exchanging electricity sales purchases. incorporates renewable sources form wind solar power, which generate electrical directly consumed requirements, directed to batteries charging needs (storage, vehicles), sold back grid acquiring revenues. Three short-term forecasting processes are implemented real-time prices, photovoltaics, generation. model is built hybrid combination K-medoids algorithm Elman neural network. performs clustering training set used input selection. held via results indicate different renewables’ availability highly influences allocation, renewables-based charging–discharging cycle storage vehicle.