动态评价粒子群优化及风电场微观选址
Dynamic evaluation based particle swarm optimization and wind farm micrositing
摘要点击 1378  全文点击 1989  投稿时间:2010-01-05  修订日期:2010-06-17
查看全文  查看/发表评论  下载PDF阅读器
DOI编号  10.7641/j.issn.1000-8152.2011.4.CCTA100019
  2011,28(4):449-456
中文关键词  动态评价  粒子群优化算法  风电场微观选址
英文关键词  dynamic evaluation  particle swarm optimization algorithm  micrositing of wind farm
基金项目  国家“863”计划资助项目(2007AA05Z426); 国家自然科学基金资助项目(61075064).
作者单位E-mail
万春秋 清华大学 自动化系 wancq07@mails.tsinghua.edu.cn 
王峻 同济大学 控制科学与工程系  
杨耕 清华大学 自动化系  
张兴 清华大学 航天航空学院  
中文摘要
      提出了动态评价方法处理一类约束优化问题. 将目标函数值和约束违反量进行动态归一化处理, 再进行加权求和, 动态评价解的优化性能. 不仅解决了惩罚因子确定困难的问题, 而且增加了优化算法的多样性, 提高了优化算法搜索全局最优解的能力. 将动态评价方法引入粒子群算法, 求解风电场微观选址优化问题. 仿真结果表明, 动态评价方法提高了风电场发电量和风能利用效率. 此外,该方法可广泛应用于其他优化算法以求解约束优化问题.
英文摘要
      A dynamic fitness evaluation method is proposed to handle constrained optimization problems. The values of the objective and the constraint violation are both dynamically normalized and summed up with corresponding weights to evaluate the fitness values. The proposed method not only overcomes the difficulty in tuning the coefficients of penalty function, but also increases the diversity and global search ability of the optimization algorithm. It is applied to the particle swarm optimization algorithm to solve the optimization problem in micrositing a wind farm. Simulation results demonstrate that the power generated by the wind farm is increased, so is the efficiency of wind energy exploitation. Moreover, the proposed method can be widely applied to other optimization algorithms to solve constrained optimization problems.