Load Forecasting Based on Smart Electricity Meters

摘要

The classical solutions for load forecasting based on collected data from supervisory control and data acquisition (SCADA) system,cannot accurately reflect actual changes in the load due to the measurement data contains not only the user load but also the line loss.This paper proposes a load-forecasting method based on smart electricity meters by adopting the least squares support vector machine prediction algorithm.Experimental results show that the proposed method has high prediction accuracy,whose the average relative error is just 0.77％.