蝗虫优化相关向量机模型在径流预测中的应用

针对径流序列不稳定导致预测精度不高的问题,提出一种基于变分模态分解(VMD)和蝗虫优化算法(GOA)优化相关向量机(RVM)的组合径流预测模型。首先对原始非平稳的径流序列采用VMD得到若干个相对稳定的分量序列,再分别建立RVM预测模型,并采用GOA优化RVM中核函数的参数,最后累加所有分量的预测值得到径流序列的预测值。实例结果发现,较传统的BP神经网络、支持向量机及基于经验模态分解的支持向量机等模型,该模型预测精度更高,预测结果能为水电站的经济运行、水资源的有效利用等提供决策依据。

Application of Relevant Vector Machine Based Grasshopper Optimization Algorithm in Runoff Prediction

A combined runoff prediction model based variational mode decomposition (VMD) and grasshopper optimization algorithm (GOA) optimized relevant vector machine (RVM) was proposed to solve the problem of low prediction accuracy caused by unstable runoff sequence. Firstly, several relatively stable component sequences in the original nonstationary runoff series were obtained by the VMD. Then, the RVM prediction model was established, and GOA was used to optimize the parameters of the kernel function in the RVM. Finally, the predicted values of each component were accumulated to obtain the prediction values of the original runoff time series. The case results show that the prediction accuracy of the model was higher than that of the traditional BP neural network, support vector machine, and support vector machine based empirical mode decomposition, which could provid decision-making basis for economic operation of hydropower stations and effective utilization of water resources.