基于混沌模糊神经网络方法的短期负荷预测

针对模糊神经网络的BP学习算法提出改进,引入全局性较强的混沌搜索算法,提出一种基于混沌搜索学习算法的模糊神经网络模型.将改进的模型应用于短期负荷预测建模,应用我国南方某市电网的实际负荷数据进行实证研究.仿真结果显示改进后的模糊神经网络较改进前在同一样本预测中精确度提高了2.5%,增加算法运行时间仅为3.1 s,说明本文提出的新的负荷预测建模方法具有更好的预测效果.

Short-Term Load Forecasting Based on Artificial Neural Network and Fuzzy Theory

The promotion of the flaw was proposed by introducing the chaotic searching algorithm into the fuzzy neural networks as its learning tactic. Then, the improved model was implemented, based on a South China power gird operational load data. Simulation results showed that the forecasting precision of the proposed method was enhanced by 2.5 %, while the time cost only increased by 3.1 seconds, indicating that the improved algorithm could gain better forecasting effect.