|
| CGAQPSO优化LSSVM短期风电预测 |
| Short-Term Wind Power Prediction Based on LSSVM Optimized by Chaos Gauss Attractor Quantum-behaved Particle Swarm Optimization |
| 投稿时间：2016-07-01 修订日期：2016-09-13 |
| DOI： |
| 中文关键词: 量子粒子群 CGAQPSO 短期风电预测 LSSVM. |
| 英文关键词:QPSO CGAQPSO short-term wind power prediction LSSVM |
| 基金项目:安徽省自然资金资助项目(1408085ME105、1608085ME106)、安徽省高校自然科学基金重点项目(KJ2015A063)、安徽工程大学安徽检测技术与节能装置省级实验室开放研究基金资助. |
|
|
|
|
| 摘要点击次数: 25 |
| 全文下载次数: 0 |
| 中文摘要: |
| 为了解决传统粒子群算法(PSO)优化最小二乘支持向量机(LSSVM)风电预测精度不高的问题,本文提出一种基于混沌高斯局部吸引点量子粒子群(CGAQPSO)优化LSSVM的短期风电功率预测模型。在量子粒子群算法中引入混沌算法初始化粒子种群,提高了初始粒子遍历性；将局部吸引点改进为高斯分布局部吸引点,增强粒子全局搜索能力,从而得到混沌高斯局部吸引点量子粒子群优化算法。对基于不同类型核函数(Linear,SPOLY,SSigmoid及RBF)的LSSVM模型进行比较,选择RBF核函数来构建LSSVM风电预测模型。最后,将该风电预测模型应用于安徽某风电场,以该风电场实测风电、温度及湿度的历史数据构建基于RBF的CGAQPSO-LSSVM短期风电预测模型。实验表明,与GA、PSO和QPSO优化LSSVM预测模型相比,所提出的CGAQPSO-LSSVM模型能够有效提高风电功率预测精确度。 |
| 英文摘要: |
| In order to remedy the defects in poor accuracy of LSSVM wind power forecasting model tuned by traditional PSO, chaos Gauss attractor quantum-behaved particle swarm optimization (CGAQPSO) is proposed to optimize the parameters combination by adding chaos algorithm, Gauss attractor and dynamic expansion-contraction coefficient in QPSO algorithm. As the kernel function and its parameter have a great influence on the performance of the LSSVM model, the paper establishes LSSVM wind power prediction model based on different kernel functions, incuding Linear, Poly, RBF and Sigmoid kernel fuction, to determine the optimal one and the RBF kernel function is utilized for its optimal performance. To verify the proposed hybrid prediction model, the seven days actual data recorded in a wind farm located in Anhui of China are utilized for model construction and model test to forecast future 24h wind power.The results show that the proposed hybrid model achieves higher prediction accuracy compared with other models mentioned in the paper. |
| 查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|
