基于免疫遗传算法优化的神经网络配电网网损计算  

Calculation of line losses in distribution systems using artificial neural network aided by immune genetic algorithm

作　　者：李秀卿[1] 汪海 许传伟 许峰 赵丽娜[1] 孟庆然[1] 刘大为 

机构地区：[1]东北电力大学电气工程学院,吉林吉林132012 [2]齐齐哈尔供电公司,黑龙江齐齐哈尔161005 [3]黑河供电公司,黑龙江黑河164300 [4]长春供电公司,吉林长春130000

出　　处：《电力系统保护与控制》2009年第11期36-39,49,共5页Power System Protection and Control

摘　　要：提出了一种基于免疫遗传算法(IGA)的BP神经网络方法计算配电网的理论线损。该算法在遗传算法(GA)的基础上引入生物免疫系统中的多样性保持机制和抗体浓度调节机制,有效地克服了GA算法的搜索效率低、个体多样性差及早熟现象,提高了算法的收敛性能。为了解决BP神经网络权值随机初始化带来的问题,用多样性模拟退火算法(SAND)进行神经网络权值初始化,并给出了算法详细的设计步骤。仿真结果表明,同混合遗传算法相比,该算法设计的BP神经网络具有较快的收敛速度和较强的全局收敛性能,比现有其它计算配电网理论线损的方法更为准确。A new method of designing BP neural networks based on immune genetic algorithm （IGA） is proposed for calculating line losses in distribution systems. The mechanisms of diversity maintaining and antibody density regulation exhibited in a biological immune system are introduced into IGA based on genetic algorithm （GA）. The proposed algorithm overcomes the problems of GA on search efficiency, individual diversity and premature and enhances the convergent performance effectively. In order to solve the problem of random initial weights, simulated annealing algorithm for diversity is used to initialize weight vectors, and the detailed design steps of the algorithm are given. Simulated results show that the BP neural networks designed by IGA have better performance in convergent speed and global convergence compared with hybrid genetic algorithm and that the method is more accurate than other ones.

关 键 词：BP神经网络 免疫遗传算法 模拟退火算法 线损 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] TM714.3[自动化与计算机技术—控制科学与工程]