激光杂志
激光雜誌
격광잡지
LASER JOURNAL
2014年
7期
36-38,42
,共4页
俞秀婷%覃锡忠%贾振红%傅云瑾%曹传玲%常春
俞秀婷%覃錫忠%賈振紅%傅雲瑾%曹傳玲%常春
유수정%담석충%가진홍%부운근%조전령%상춘
模拟退火%粒子群算法%Elman神经网络%话务量预测
模擬退火%粒子群算法%Elman神經網絡%話務量預測
모의퇴화%입자군산법%Elman신경망락%화무량예측
Simulated annealing%Particle swarm optimization%Elman neural network%Traffic prediction
文章提出一种模拟退火(SA)与粒子群优化(PSO)算法相结合的算法来优化Elman神经网络权值和阈值。当PSO处于停滞状态时,利用粒子群优化算法的全局寻优性质,以及SA能跳出局部最优解的特性,在搜索到的最优位置处用模拟退火算法继续寻找最优解,并对具有动态递归性能的Elman神经网络进行学习训练,这样就能对忙时话务量进行预测。结果表明,与传统Elman神经网络和PSO-Elman神经网络相比,基于模拟退火粒子群算法训练的神经网络具有更高的预测精度和良好的自适应性。
文章提齣一種模擬退火(SA)與粒子群優化(PSO)算法相結閤的算法來優化Elman神經網絡權值和閾值。噹PSO處于停滯狀態時,利用粒子群優化算法的全跼尋優性質,以及SA能跳齣跼部最優解的特性,在搜索到的最優位置處用模擬退火算法繼續尋找最優解,併對具有動態遞歸性能的Elman神經網絡進行學習訓練,這樣就能對忙時話務量進行預測。結果錶明,與傳統Elman神經網絡和PSO-Elman神經網絡相比,基于模擬退火粒子群算法訓練的神經網絡具有更高的預測精度和良好的自適應性。
문장제출일충모의퇴화(SA)여입자군우화(PSO)산법상결합적산법래우화Elman신경망락권치화역치。당PSO처우정체상태시,이용입자군우화산법적전국심우성질,이급SA능도출국부최우해적특성,재수색도적최우위치처용모의퇴화산법계속심조최우해,병대구유동태체귀성능적Elman신경망락진행학습훈련,저양취능대망시화무량진행예측。결과표명,여전통Elman신경망락화PSO-Elman신경망락상비,기우모의퇴화입자군산법훈련적신경망락구유경고적예측정도화량호적자괄응성。
This paper presents a hybrid algorithm that combines simulated annealing (SA) algorithm with parti-cle swarm optimization (PSO) algorithm to optimize the weights and threshold of Elman neural network. By using the advantages of global optimization of PSO, when it is trapped into local optimum, SA is employed to jump out of local optimal solution to find the global optimal solution. The hybrid algorithm is used to train Elman neural network with dynamic recursive properties. The approach is carried out on the forecasting of the busy telephone traffic. The experimental results show that SAPSO-Elman neural network has better precision and adaptability compared with the traditional neural network.