改进人工鱼群算法在输电网规划中的应用  

Application of Improved Artificial Fish School Algorithm in Transmission Network Planning

作　　者：聂宏展[1] 吕盼[1] 乔怡[1] 姚秀萍[2] 

机构地区：[1]东北电力大学电气工程学院,吉林132012 [2]新疆电力公司电力调度中心,乌鲁木齐830002

出　　处：《电力系统及其自动化学报》2010年第2期93-98,共6页Proceedings of the CSU-EPSA

摘　　要：针对离散人工鱼群算法在求解大规模输电网规划问题时易陷入局部极值的缺点,提出一种改进人工鱼群算法。该算法引入禁忌搜索算法的记忆功能,避免迂回搜索,有效提高了计算效率;并在深入研究人工鱼搜索机制的基础上,对人工鱼寻优行为进行一系列的改进,采用最好解优先策略选择前进路径以及以排序选择的方式接受劣解,进一步提高了算法效率。IEEE Garver-6系统和18节点系统的计算结果表明,该算法用于电力系统输电网规划是有效的,具有良好计算效率和优秀的全局收敛性能。Considering the problem of low efficiency and local optimum in discrete artificial fish school algorithm（AFSA） for large scale transmission network planning,an improved artificial fish school algorithm（IAFA）is presented. Due to the shortcomings mentioned above,tabu search（TS） algorithm is introduced into IAF- SA whose memory structure can avoid circuit searching. Based on deep study on search mechanism of artificial fish,a series of improvements on search acts of artificial fish are implemented in order to increase the efficiency of algorithm furtherly. The results of IEEE Garret-6 system and the 18-bus system demonstrate feasibility of this method. The new method has high computation efficency and good global convergence.

关 键 词：电力系统 输电网规划 人工鱼群算法 禁忌搜索 混合算法 

分 类 号：TM715[电气工程—电力系统及自动化]