Hopfield神经网络在机组组合问题中的应用

提出利用多层Hopfield神经网络求解机组组合优化问题。通过构造合适的能量函数使得单层Hopfield神经网络可以解决某一时刻的机组出力问题，与之相对应的多层神经网络可以解决任意时间段的机组出力问题。多层Hopfield神经网络的层数由所需求解问题的时间段确定。给出单层及多层神经网络的能量函数及求解算法，能量函数考虑到机组升降功率和出力上下限的约束。通过对已有文献的算例进行计算比对，所得结果和遗传算法基本一致，但Hopfield神经网络通过解微分方程组来确定最优解，计算时间相对较少。

Application of Hopfield neural network in unit commitment problem

This paper presented an algorithm, based on multi-layer Hopfield neural network, for determining unit commitment. By constructing an appropriate energy function, a single layer Hopfield neural network can solve the problem of assigning output power of generators at any given time. Based on this single layer Hopfield neural network, a multi-layer Hopfield neural network was presented. The multi-layer Hopfield neural network can solve the problem of power system unit commitment. The energy functions of single layer and multi-layer Hopfield neural network and the corresponding algorithm were given. The restricted conditions of the balance between power supply and demand, maximum and minimum outputs of power plants were considered in the energy function. An example shows that the result got by Hopfield neural network is like to that got by genetic algorithm, but the calculation time is much less.