基于WRF模式和PSO-LSSVM的风电场短期风速订正

发布时间：2018-01-15 09:03

本文关键词：基于WRF模式和PSO-LSSVM的风电场短期风速订正　出处：《电力系统保护与控制》2017年22期 　论文类型：期刊论文

【摘要】：风速预测是风电场风电功率预测的基础与前提,以数值天气预报(WRF模式)为基础进行风速预测,为了提高WRF模式预测的准确性,采用最小二乘支持向量机(Least Squares Support Vector Machine,LSSVM)对WRF模式输出的风速进行订正。同时,为提高LSSVM算法的精确度和减小拟合过程的复杂度,采用粒子群优化算法(Particle Swarm Optimization,PSO)对其参数进行优化。试验结果表明:采用LSSVM订正可以进一步减小WRF模式预测风速的误差,再经过PSO优化后,相对均方根误差和相对平均绝对误差降低了5%~10%,均方根误差下降了0.5 m/s。与未经优化的LSSVM以及极限学习机(ELM)算法对比分析后得出,粒子群优化最小二乘支持向量机(PSO-LSSVM)对WRF模式预测的风速有较好的订正效果,能进一步提高风速预测的准确性。
[Abstract]:Wind speed prediction is the basis and premise of wind power prediction in wind farm. In order to improve the accuracy of WRF model, wind speed prediction is carried out on the basis of numerical weather forecast. The least square support vector machine (LS-SVM) is used for least Squares Support Vector Machine. In order to improve the accuracy of the LSSVM algorithm and reduce the complexity of the fitting process, the wind speed of WRF mode is revised by LSSVM. Particle Swarm Optimization (PSO) algorithm is adopted. The experimental results show that the LSSVM correction can further reduce the error of WRF model in predicting wind speed, and then after PSO optimization. The relative root mean square error and the relative mean absolute error are reduced by 5% and 10% respectively. The root mean square error (RMS) decreased by 0. 5 m / s. The results were compared with the unoptimized LSSVM and LLM algorithm. Particle swarm optimization (PSO) least squares support vector machine (LSSVM) has a good effect on the wind speed prediction of WRF model, and can further improve the accuracy of wind speed prediction.
【作者单位】：南京信息工程大学信息与控制学院;南京信息工程大学气象灾害预报预警与评估协同创新中心;
【基金】：国家自然科学基金项目(41675156) 国家公益性行业(气象)科研专项(GYHY20110604) 江苏省六大人才高峰项目(WLW-021)资助江苏省研究生创新工程省立项目(SJZZ16_0155)~~
【分类号】：TM614
【正文快照】： This work is supported by National Natural Science Foundation of China(No.41675156).随着人类对能源需求的不断增加,传统的煤、石油、天然气等化石能源被大量开采,储量大幅度下降,同时化石能源的过度使用也造成了温室效应、环境污染等问题,所以清洁能源的开发和使用迫在

【相似文献】