2017 3rd International Conference on Electrical Information and Communication Technology (EICT)

1 / 2017-08-24 17:17:04

Elman neural network model for short term load forecasting based on improved demand response factor

short-term load forecasting; neural network; optimization model;

In order to adapt to the policy of electricity reform and to improve the prediction accuracy of short-term power load, a demand response model based on time-varying function is introduced by studying the demand response load, and the influencing factors of demand response are introduced in the traditional input. According to the Elman neural network is easy to fall into local extremum, improve its incentive function to optimize the prediction model.In order to establish the Elman neural network model for short term load forecasting based on improved demand response factor. The simulation of Matlab in a southern power shortage city is carried out, and the prediction performance of the Elman model is compared with the demand response factor before and after the improvement of the model. The validity and practicability of the model and algorithm are verified.