贪心算法结合Hopfield神经网络优化配电变电站规划

A NEW DISTRIBUTION SUBSTATION PLANNING ALGORITHM BASED ON GREEDY ALGORITHM AND HOPFIELD NEURAL NETWORK

提出了一种城市电网规划中变电站规划优化的新算法。该算法先用贪心算法(greedy algorithm)快速求解新建变电站的座数及各变电站的容量,再利用Hopfield神经网络校核新建变电站的位置和各变电站的供电范围,最后确定各变电站的真实容量。在求解过程中,该方法考虑了已有变电站的改造问题。从全局最优的原则出发,可求得具有实际价值的最优或近似最优解。该方法在求解变电站供电范围时无需对数据进行归一化处理,且易于编程。该方法可为变电站规划提供一种新的思路。

A new algorithm for distribution substation planning is presented. In which the greedy algorithm is first used to work out the number of new substations and the capacity of each substation (including the existent substation), then the Hopfield neural network is used to determine the positions of new substations and the service region of each substation, finally, according to the service region of each substation, the real capacity of each substation is decided while the renovation of the existent substations is considered. Start from the principle of global optimization the optimum solution or approximate optimum solution can be obtained. Using this algorithm the data need not normalize in the working-out of the service regions of the substations. The new algorithm can make the existent substations adequately involved into the optimizing procedure, and the programming of this algorithm is easy to implement. This algorithm can provide a new approach to substation planning.