摘要： 单一算法在母线负荷预测中存在稳定性弱、波动性大的问题。为此，提出基于多神经网络的母线负荷混沌优化组合预测模型。采用改进的混沌学习算法对模糊网络、小波网络和灰色网络的预测值进行混沌优化组合，确定最优的权重系数，得到最终的预测结果。算例分析表明，该组合模型性能优于单个网络模型和传统组合模型，能较大提高负荷预测的精度和收敛速度。

关键词: 母线负荷, 神经网络, 模糊网络, 小波网络, 灰色网络, 混沌学习算法, 组合模型

Abstract: Aiming at weak stability, volatility larger bus load forecasting of simple algorithm, this paper puts forward a chaos optimization combination forecasting model based on multi-neural network. This model puts the predictive value of fuzzy network, wavelet network and gray network for chaos optimization combination by the improved chaotic learning algorithm, determines the optimal weight coefficients, and gets the final prediction results. Example analysis shows that the combination model is better than a single network model and the traditional combination model, and significantly improves the precision of the load forecast and convergence speed.

Key words: bus load, neural network, fuzzy network, wavelet network, gray network, chaotic learning algorithm, combination model

中图分类号: 

• TP391