基于EEMD-SE和GARBF的短期电力负荷预测

Short-term power load forecasting based on EEMD-SE and RBF optimized by genetic algorithm

为了提高短期电力负荷的预测精度,提出了集合经验模态分解(EEMD)-样本熵(SE)和遗传算法(GA)来优化RBF神经网络的组合方法。利用EEMD分解法自适应地对负荷序列进行分解,结合样本熵对复杂度相似的子序列进行合并,有效减小了运算规模。基于各个子序列复杂度的差异构建相应的RBF神经网络模型,利用遗传算法避免神经网络陷入局部最优和收敛性问题,进而对合并的新子序列进行预测并叠加得到最终预测结果。仿真结果表明,该预测算法具有良好的预测效果,满足短期电力负荷预测的要求。

In order to improve the forecasting accuracy of short-term power load,a power load forecasting approach based on ensemble empirical mode decomposition(EEMD)-sample entropy(SE)and genetic algorithm(GA)for RBF neural network optimization is proposed in the paper.The EEMD decomposition method is used to decompose the load sequence adaptively,and according to sample entropy to combine the subsequences with similar complexity,which effectively reduces the scale of operation.Based on the difference of sub-sequence complexity,the corresponding RBF neural network model is constructed.The genetic algorithm is used to avoid the neural network falling into the local optimal and convergence problem.Then the new sub-sequences are forecasted and superimposed to obtain the final forecasting result.The simulated results show that the prediction algorithm has a satisfactory prediction effect and meets the requirements of short-term power load forecasting.