基于PSO睸VR的丹江口年径流预报

王迁 杨明祥 雷晓辉 舒坚 孙利民 黄雪姝

摘要：目前应用于丹江口水库年径流预报的方法主要为物理统计和人工神经网络（ANN）等方法，但这些方法普遍存在预报精度不高和稳定性不强等缺点。选择回归支持向量机（SVR）模型应用于丹江口水库年径流预报，针对惩罚系数C、核参数σ和不敏感损失系数ε三个参数在实际赋值过程中存在计算量大、难以得到最优值等问题，将粒子群优化算法（PSO）加入到SVR模型中，建立PSOSVR模型，实现了参数的自动优选。结果表明，PSOSVR模型较之SVR模型，提高了预报精度；较之ANN模型，稳定性更强，可信度更高。该模型具有较好的应用价值，可为南水北调中线工程调度方案制定提供一定的参考依据。

关键词：丹江口水库；回归支持向量机；粒子群优化算法；年径流预报；预报因子

中图分类号：TV121文献标志码：A文章编号：16721683（2018）03006507

Annual runoff forecast for Danjiangkou based on PSOSVR

WANG Qian1，YANG Mingxiang2，LEI Xiaohui2，SHU Jian1，SUN Limin3，HUANG Xueshu4

（1.School of Software，Nanchang Hangkong University，Nanchang 330063，China；2.State Key Laboratory of Water

Cycle Simulation and Regulation，China Academy of Water Resources and Hydropower Research，Beijing 100038，China；

3.Institute of Information Engineering，Chinese Academy of Sciences，Beijing 100093，China；

4.Information Center of Yellow River Conservancy Commission，Zhengzhou 450003，China）

Abstract：At present，the methods of annual runoff forecast for Danjiangkou reservoir mainly include physical statistical approach and artificial neural network （ANN）.However，these methods have the disadvantages of low accuracy and low stability.In this paper，we applied the regression support vector machine （SVR） model to the annual runoff forecast for Danjiangkou Reservoir.Considering that the penalty coefficient C，the kernel parameter σ，and the insensitive loss coefficient ε all require a large amount of calculation and it is difficult to obtain their optimal value in the actual assignment process，we added the particle swarm optimization （PSO） algorithm to the SVR model and established a PSOSVR model to realize the automatic optimization of parameters.The results showed that the PSOSVR model has higher prediction accuracy compared with the SVR model，and has better stability and reliability than the ANN model.The model has a good application value，and can provide some reference for the development of the operation scheme of the middle route of the SouthtoNorth Water Transfer Project.

Key words：Danjiangkou Reservoir；regression support vector machine；particle swarm optimization；annual runoff forecast；forecast factor

丹江口水庫位于汉江中上游，南水北调中线工程水源地[1]。丹江口水库总面积846 km2，多年平均入库水量3948亿m3，丹江口大坝加高以后，水库正常蓄水位提高至170 m，库容达到2905亿m3，水域面积达到1 02275 km2。2012年开始向南水北调中线工程沿线地区的河南、河北、北京、天津等4个省市的20多座大中城市提供用水，有效缓解中国北方部分地区的水资源严重短缺局面[2]。年径流预报由于具有较长的预见期，对水库的优化管理和综合调度有着重要的指导意义和经济价值[3]。因此分析丹江口水库年入库径流特性和演变规律，准确预报水库来水，对南水北调中线工程实际调度也有着重要意义。……