基于人工免疫网络的短期负荷预测模型

SHORT-TERM LOAD FORECASTING USING ARTIFICIAL IMMUNE NETWORK

为了克服传统神经网络预测方法在网络结构设计、学习算法和收敛效果等方面存在的缺陷,通过借鉴免疫网络调节与免疫规划,该文提出了一种基于人工免疫网络的短期负荷预测模型。在人工免疫网络的设计中,创造性地融入了免疫调节原理,利用免疫规划来进化网络结构,采用了新的个体编码方式、神经元适应度函数和自适应混沌变异算子,通过免疫规划进行网络结构的设计,并结合免疫网络调节的进化算法进行网络的学习。电力系统短期负荷预测的计算实例表明,基于人工免疫网络的负荷预测方法与传统神经网络预测方法相比,具有较强的自适应能力和较好的效果。

A short-term load forecasting model based on the Artificial Immune Network (AIN) is presented to overcome the weaknesses of the method of the traditional Neural Network for Short-term Load Forecasting. In the design of the AIN, the principle of Immune Network Regulation is used in a creative way and the method of Immune Programming is used to evolve the network structure. The new encode strategy, the new fitness of cell and the new self-adaptive chaos mutation operator are adopted in the AIN. The results of an example show that the adaptive ability and the forecasting effect of the AIN method are better than those of the traditional Neural Network method.