电力系统潮流的一种神经计算方法

A NEURAL-TYPE PARALLEL ALGORITHM FOR LOAD-FLOW COMPUTATION

将人工神经网络中的正交背传算法应用于电力系统潮流计算，提出了一种电力系统潮流的神经计算方法。这种方法具有内在的高度并行特性。

In this paper.the Orthogonalized Backpropagation Algorithm.which is a training procedure for adjusting the weights of a neural-type network.is introduced for Load-Flow computation of electric power systems. In this framework the parallel neural-like net work is used for representation of the Load Flow problem.and OBA is used for the training of the weights.where the values of the weights correspond to the estimates of the bus voltages. This algorithm is inherently parallel. The preliminary evaluations indicate that the proposed algorithm compares favorably with existing methods.