基于PSO-LSSVM的海水淡化负荷预测  

Seawater Desalination Load Forecasting Based on PSO-LSSVM

作　　者：金璐[1] 钟鸣[1] 张景霞 成岭[1] 陈培育[3] JIN Lu;ZHONG Ming;ZHANG Jingxia;CHENG Ling;CHEN Peiyu(China Electric Power Research Institute,Beijing 100192,China;College of Information Science and Engineering, Northeastern University,Shenyang 110819,China;State Grid Tianjin Electric Power Research Institute, Tianjin 300384, China)

机构地区：[1]中国电力科学研究院,北京100192 [2]东北大学信息科学与工程学院,辽宁沈阳110819 [3]国网天津市电力公司电力科学研究院,天津300384

出　　处：《智慧电力》2019年第2期49-55,共7页Smart Power

基　　金：国家自然科学基金资助项目(61703081);国家电网公司科学技术项目(YD71-18-006)~~

摘　　要：为了将海水淡化负荷与分布式可再生能源或电网结合协同运行,进一步提高海水淡化用户的综合经济效益,提出了精准预测海水淡化负荷的方法。首先对影响海水淡化负荷的相关因素应用灰色关联分析理论构建相似日的小样本集合,而后建立多输入单输出的最小二乘支持向量机(LSSVM)模型。针对LSSVM模型,提出了通过粒子群算法(PSO)优化相关参数γ和σ~2的新预测方法。最后利用某海岛冬季用水数据对模型进行仿真验证,结果表明,该模型可达到参数最优化选择的目的,提高了预测精度,能够满足海水淡化负荷预测的需要。In order to further improve the comprehensive economic benefits of seawater desalination users through the coordinated operation of seawater desalination load, distributed renewable energy and power grid, this paper proposes a method to accurately predict the seawater desalination load. Firstly, a small sample set of similar day is established for related factors affecting the seawater desalination load with gray correlation analysis theory. Then a multi-input single-output least squares support vector machine (LSSVM) model is established. In the light of the LSSVM model, a new prediction method for optimizing related parameters γ and σ2 by particle swarm optimization (PSO) is proposed. Finally, the model is validated by using the water consumption data from an island in winter. The results show that the model can achieve the purpose of parameter optimization, improve the prediction accuracy and meet the needs of the seawater desalination load forecasting.

关 键 词：海水淡化 负荷预测 LSSVM PSO 

分 类 号：TM732[电气工程—电力系统及自动化]