Residential microgrid optimization using grey-box and black-box modeling methods

Abstract

The use of data-driven black-box HVAC and water heater models in the optimization of a single-home residential microgrid is investigated. Data-driven models do not rely on the specification of system geometry or thermal parameters, instead using time-variant, system-specific data to develop models of each controllable appliance. A comparison of modeling accuracy of grey-box models based on those found in the literature and black-box models developed using extreme gradient boosting is made. A multi-objective optimization problem is then developed with the objectives of minimizing energy cost and consumption while maximizing thermal comfort and the consumption of locally generated PV energy. Results demonstrate that data-driven black-box models have the potential to be used in place of grey-box models, which are more prone to the introduction of error by the user. Optimization using the grey-box and black-box modeling methods was performed using a genetic algorithm to verify the similarity of results using the two modeling methods. Optimization resulted in a maximum total energy savings during the optimized period of 32.3%, a maximum total peak energy reduction of 39.8%, and a maximum cost reduction of 38.1%.