基于LMD-IMVO-LSSVM的短期风速预测  

Short-term wind speed prediction based on LMD-IMVO-LSSVM

作　　者：桑茂景 谢丽蓉[1] 李进卫 王斌[1,3] 杨欢 Sang Maojing;Xie Lirong;Li Jinwei;Wang Bin;Yang Huan(Wind and Light Energy Storage Sub-Chamber of State Key Laboratory for Control and Simulation of Power System and Power Generation Equipment,Xinjiang University,Urumqi 830047,China;CSIC of Haiwei(Xinjiang)New Energy Co.,Ltd.,Urumqi 830002,China;Shandong Iron&Steel Group Rizhao Co.,Ltd.,Rizhao 276805,China;State Key Laboratory of Control and Simulation of Power Systems and Generation Equipments Dept.of Electrical Engineering,Tsinghua University,Beijing 100084,China)

机构地区：[1]新疆大学电力系统及发电设备控制和仿真国家重点实验室风光储分室,新疆乌鲁木齐830047 [2]中船重工海为(新疆)新能源有限公司,新疆乌鲁木齐830002 [3]山东钢铁集团日照有限公司,山东日照276805 [4]清华大学电力系统及发电设备控制和仿真国家重点实验室,北京100084

出　　处：《可再生能源》2021年第9期1197-1203,共7页Renewable Energy Resources

基　　金：国家自然科学基金资助项目(51667021);新疆维吾尔自治区区域协同创新专项(科技援疆计划)(2018E02072);新疆维吾尔自治区高校科研计划自然科学重点项目(XJEDU2020I004);清华大学电力系统及大型发电设备安全控制与仿真国家重点实验室开放研究课题(SKLD20M20)。

摘　　要：风速信号具有的随机性和波动性的特点给风速预测的准确性带来了巨大挑战。现有的风速预测方法较多,但大都难以满足风电场需求的预测效果。文章提出了一种基于LMD-IMVO-LSSVM的短期风速预测方法。首先采用局部均值分解(LMD)方法将原始风速序列分解为若干个平稳的风速子序列,结合改进多元宇宙优化算法(IMVO)寻优最小二乘支持向量机(LSSVM)的可调参数预测方法,建立了LMD-IMVO-LSSVM的风速预测组合模型;然后对分解得到的每个平稳子序列进行单独的预测,叠加各子序列预测结果,即得到最终的风速预测值。通过实验仿真分析得出,文章提出的组合预测模型可大大提高风速预测的准确性。The randomness and volatility of wind speed signals bring a significant challenge to wind speed prediction accuracy.To improve the accuracy of wind speed prediction,the Local Mean Decomposition(LMD)method is adopted to decompose the original wind speed sequence into several stationary wind speed sub-sequences.Optimized parameters of Least Squares Support Vector Machine(LSSVM)were optimized using Improved Multi-Verse Optimizer(IMVO)to build the LMD-IMVO-LSSVM wind speed prediction model.Finally,the prediction results of each subsequence are superposed to obtain the final wind speed prediction value.Simulation results show that the combined prediction model can significantly improve the accuracy of wind speed prediction.

关 键 词：风速预测 局部均值分解 改进多元宇宙优算法 最小二乘支持向量机 

分 类 号：TK81[动力工程及工程热物理—流体机械及工程]