基于改进灰色关联分析的BA-BP短期负荷预测

针对短期电力负荷随机性强、预测精度低等问题,提出了基于模糊灰色聚类与蝙蝠优化神经网络的短期负荷预测模型。采用模糊聚类方法选择相似日粗集,然后用改进的灰色关联分析法选取相似日;为了克服传统BP算法易陷入局部极值和收敛速度慢等问题,利用相似日集中的样本训练蝙蝠优化的BP神经网络预测模型。以某地区的历史数据为实际算例,将文中所提算法与普通的BP神经网络、传统灰色关联与蝙蝠优化的BP神经网络预测结果相比,结果表明所提方法有很高预测精度和稳定性,在实际中有一定应用价值。

Short-term load forecasting based on improved grey relational analysis BA-BP neural network

In view of the strong randomness and low prediction accuracy of short-term forecasting, a short-term load forecasting model based on fuzzy grey clustering and bat optimization neural network is proposed. Fuzzy clustering method was used to select rough sets of similar days, and then improved grey correlation analysis method was used to select the similar days. In order to overcome the problem that the traditional BP algorithm is prone to fall into local extremum and slow convergence speed, BP neural network prediction model optimized by training bats with samples of similar daily concentration is used. Taking the historical data of a certain area as a practical example, comparing the proposed algorithm with the common BP neural network, traditional gray correlation and bat optimized BP neural network prediction results, the results show that the proposed method has high prediction accuracy and Stability has certain application value in practice.