Day-ahead Probabilistic Forecasting of Smart Households’ Demand Response Capacity under Incentive-based Demand Response Program

Abstract

The advancement in technology and development in electricity market make it possible for smart households (SHs) to participate in the incentive-based demand response (IBDR) programs. As the agent of SHs' participation in the IBDR program, it is crucial for load aggregators (LAs) to understand the SHs' demand response (DR) capacity when trading with the system operator in the day-ahead market. Therefore, this paper proposes a probabilistic forecasting model to forecast the aggregated SHs' DR capacity and model its uncertainty in the day-ahead market in LAs' point of view. Firstly, a home energy management system (HEMS) is adapted to perform an optimal scheduling for SHs and to model the customers' responsive behavior in the IBDR program; secondly, several features which may have significant impacts on the aggregated DR capacity are extracted; finally, a quantile regression (QR) based probabilistic forecast model is proposed to provide a probabilistic forecasting for available aggregated SHs' DR capacity in the day-ahead market.