In a Smart grid, implementation of value-added services such as distribution automation (DA) and Demand Response (DR)  rely heavily on the availability of accurate electricity consumption forecasts. Machine learning based forecasting systems, due to their ability to handle nonlinear patterns, appear promising for the purpose. An empirical evaluation of eight machine learning based systems for electricity consumption forecasting, based on Extreme Learning machines (ELM), Ensemble Regression Trees (ERT), Artificial Neural Network (ANNs) and regression is presented in this study. Forecasting systems thus designed, are validated on consumption data collected from 5275 users. Result indicate that ELM based electricity consumption forecasting systems are not only more accurate than other systems considered, they are considerably faster as well. © Springer International Publishing AG 2017.
cited By 0; Conference of 6th Computer Science On-line Conference, CSOC 2017 ; Conference Date: 26 April 2017 Through 29 April 2017; Conference Code:190739
J. A. Balaji, Dr. Harish Ram D. S., and Dr. Binoy B. Nair, “Machine learning approaches to electricity consumption forecasting in automated metering infrastructure (AMI) systems: An empirical study”, Advances in Intelligent Systems and Computing, vol. 574, pp. 254-263, 2017.