An ensemble learning model for estimating the virtual energy storage capacity of aggregated air-conditioners

Renewable energy resources (RES) pose several challenges due to their natural intermittency when integrated into a distribution network. A smart energy storage system (SESS) alleviates these challenges, which is achieved by integrating thermostatically controlled loads (TCLs) such as air conditioners (ACs). Hence, this study proposes a virtual energy storage system (VESS) by modeling the ACs analogous to an electro-chemical battery. Besides, non-linearity in energy consumption patterns of ACs due to consumer behavior makes predictive energy analysis critical to deplete the discrepancy between supply and demand. Therefore, this study proposes an ensemble learning (EL) technique to predict the virtual energy storage (VES) capacity of ACs. The prediction stage relies on various machine learning (ML) methods, like support vector regression (SVR) and artificial neural network (ANN). Based on these ML techniques, this study proposes an SVRs-ANN-based EL model to predict the VES capacity during the discharging cycle. Each weak learner in the EL model is trained using a significant features subset with the aid of the k-fold cross-validation method to build a more generalized model for unseen data. The performance of the EL model is estimated using minute-based smart meter data set and empirically manifested that the EL model outperforms conventional approaches. The R-2 and root mean squared error (RMSE) of the EL model reach 1 and 1.03x10(-7), respectively, and results demonstrate lower RMSE values and higher performance than conventional methods. The results obtained have shown the robustness of the proposed EL model to operate ACs in energy-saving mode instead of load shifting. Although ACs are not controlled in the experiments, the experimental validation proved that the EL model accurately predicts the daily VES capacity of ACs without violating consumer satisfaction.