An effective power quality prediction for regional power grid can provide\nvaluable references and contribute to the discovering and solving of power\nquality problems. So a predicting model for power quality steady state index\nbased on chaotic theory and least squares support vector machine (LSSVM) is\nproposed in this paper. At first, the phase space reconstruction of original\npower quality data is performed to form a new data space containing the attractor.\nThe new data space is used as training samples for the LSSVM. Then\nin order to predict power quality steady state index accurately, the particle\nswarm algorithm is adopted to optimize parameters of the LSSVM model.\nAccording to the simulation results based on power quality data measured in\na certain distribution network, the model applies to several indexes with\nhigher forecasting accuracy and strong practicability.
Loading....