摘要
用Hopfield神经网络解决经济符合分配(economic load dispatch,ELD)时,有两个关键问题:减小振荡和迭代步数。为加速收敛,本文提出两种自适应Hopfield神经网络计算方法一自适应坡度调整法和自适应偏移量调整法,通过调整自适应学习率改进Hopfield神经网络。结果与传统Hopfield神经网络和模拟退火方法非常接近,且收敛步数较传统Hopfield方法大为减少。可有效的解决经济负荷分配问题。
A large number of iterations and oscillation are those of the major concern in solving the economic load dispatch（ELD） problem using the Hopfield neural network.This paper develops two different methods,which are the slope adjustment and bias adjustment methods,in order to speed up the convergence of the Hopfield neural network system..The results are compared with those of the simulated annealing approach and the traditional Hopfield neural network approach.To guarantee and for faster using energy functions and applied to the slope and bias adjustment methods.The results of the traditional and adaptive learning rate methods＇ are compared in economic load dispatch problem.
作者简介
周明（1981-）男.研究方向：计算机控制与系统辨识。
