Power consumption forecast model using ensemble learning for smart grid

The prediction of power consumption of smart meters plays a vital role in power distribution and management in the smart grid, which depends on real-time and historical data. However, existing schemes do not meet the standard requirements of the prediction, are difficult to deploy, and do not achieve the desired accuracy. In this paper, an Ensemble learning based power consumption prediction model (EPC-PM) is proposed for the smart meter. Ensemble learning calculates the weights of base predictors and the voting engine selects the suitable predictor that has high accuracy and generates the final predicted output. The performance of base predictors is considered for the next iterations of prediction. Further, the predicted output can be used for power distribution and management by the smart grid. Experimental and statistical analysis shows that EPC-PM is more efficient than existing state-of-the-art works in terms of performance. The proposed EPC-PM improves the root mean square error, normalized root mean square error, and mean absolute error up to 0.2467, 13.45, and 0.1761, respectively, over the UMass Smart* dataset.