论文部分内容阅读
针对变电站规划问题,提出了基于加权K-means聚类的变电站供电范围划分方法,并在此基础上提出了基于加权K-means聚类和遗传算法的变电站规划算法。该算法运用遗传算法的全局搜索能力确定变电站的座数、主变台数和容量的最优组合,解决了应用加权K-means聚类算法划分变电站供电范围时初始聚类数确定的问题。加权K-means聚类算法能够综合考虑变电站的负载率和供电半径的约束,并在迭代过程中自适应调节。算例结果表明所提算法能够较好地求解变电站优化规划问题。
Aiming at the problem of substation planning, a method to divide the substation power range based on weighted K-means clustering is proposed. Based on this, a substation planning algorithm based on weighted K-means clustering and genetic algorithm is proposed. This algorithm uses the global search ability of genetic algorithm to determine the optimal combination of the number of substations, the number of main transformers and the capacity, and solves the problem of determining the initial clustering number when dividing the power supply range of substation by using weighted K-means clustering algorithm. The weighted K-means clustering algorithm can comprehensively consider the substation load rate and power supply radius constraints, and adaptively adjusted in the iterative process. The results show that the proposed algorithm can solve the substation optimal programming problem well.