基于改进的人工神经网络对存储系统性能进行预测的方法
|
摘要
测量和评估网络存储系统的性能是用户和企业普遍关心的重点问题之一,因BP神经网络具有强大的非线性映射能力,文中提出了一种利用改进的BP神经网络实现对网络IO性能进行预测的方法。改进的主要内容包括:1)利用马尔科夫链进行预测,更新输出层输出;2)当算法选择概率达到一定值后,利用人工蜂群算法对权值进行优化。最后模拟预测模型的实现过程,将预测结果与传统的BP神经网络进行对比。实验结果证明:该算法能够在基本不增加算法运行时间的情况下提高存储性能预测的求解精度和收敛速度。
Measuring and evaluating the performance of network storage system is one of the key problems to users and corporations.For the strong nonlinear mapping function of the BP-ANN,a new improved algorithm for network I/O performance prediction was proposed by improved BP-ANN,and the new algorithm includes two aspects.Firstly,Mar-kov Chain is used to forecast and update the output of output layer.Secondly,the artificial bee colony algorithm is used to optimize the weights when the probability of algorithm selection reaches a certain value.The implementation process of evaluation model was simulated,and the results were compared with BP-ANN.The experimental results show that the presented approach can significantly improve the solution accuracy and convergence speed of evaluating the performance of network storage system almost without increasing the running time.
Measuring and evaluating the performance of network storage system is one of the key problems to users and corporations.For the strong nonlinear mapping function of the BP-ANN,a new improved algorithm for network I/O performance prediction was proposed by improved BP-ANN,and the new algorithm includes two aspects.Firstly,Mar-kov Chain is used to forecast and update the output of output layer.Secondly,the artificial bee colony algorithm is used to optimize the weights when the probability of algorithm selection reaches a certain value.The implementation process of evaluation model was simulated,and the results were compared with BP-ANN.The experimental results show that the presented approach can significantly improve the solution accuracy and convergence speed of evaluating the performance of network storage system almost without increasing the running time.
引文
[1] 崔宝江,刘军,王刚,等.网络存储系统 I/O 响应时间边界性能研究[J].通信学报,2006,27(1):69-74.
[2] 陈琼,郑启伦,凌卫新.采用计数器存储权值的人工神经网络的实现[J].计算机工程与应用,2001,20:22-25.
[3] KARABOGA D.An idea based on honey bee swarm for numerical optimization[R].Erciyes University,Kayseri,Turkey,TechnicalReport-TR06,2005.
[4] KARABOGA D,AKAY B,OZTURK C.Artificial Bee Colony (ABC) optimization algotithm for training feed-forward neural networks[C]//LNCS:Modeling Decisions for Artificial Intelligence.Springer-Verlag,2007:18-329.
[5] BEATRIZ A G,HUMBERTO S,ROBERTO A.VáZQUEZ.Artificial neural network synthesis by means of artificial bee colony (ABC) algorithm[C]//2011 IEEE Congress of Evolutionary Computation (CEC).2011:331-338.
[6] 暴励.人工蜂群算法的混合策略研究[D].太原:太原科技大学,2010.
[7] ZHU G,KWONG S.Gbest-Guided artificial bee colony algo- rithm for numerical function optimization[J].Applied mathematics and Computation,2010,217(7):3166-3173.
[8] 周新宇,吴志健,王文明.基于正交实验设计的人工蜂群算法[J].软件学报,2015,26(9):2167-2190.
[9] 冷昕,张树群,雷兆宜.改进的人工蜂群算法在神经网络中的应用[J].计算机工程与应用,2016,52(11):7-10.
[10] 王允霞.蜂群算法的研究及其在人工神经网络中的应用[D].广州:华南理工大学,2013:25-27.
[11] 向万里,马寿峰.基于轮盘赌反向选择机制的蜂群优化算法[J].计算机应用研究,2013(1):86-89.
[12] 魏波,喻飞,徐星,等.基于改进轮盘赌策略的交互式演化算法[J].计算机与数字工程,2014(10):1762-1767.
[13] ROMANOVSKII V.Discrete Markov’s chains[M].Moscow:Gostexizdat,1949.
[14] WHITTAKER J A,THOMASON M G.A Markov Chain Mo- del for Statistical software testing[J].IEEE Transactions on Software Engineering,1994,30(10):812-824.
[15] MAREK I,SZYLD D B.Algebraic schwarz methods for the numerical solution of Markov chains[J].Linar Algebraic and its Applications,2004,386:67-81.
[16] POGGI P,NOTTON G,MUSELLI M.Stochastic study of hourly total solar radiation in Corsica using a Markov model[J].International Journal of Climatology,2000,20(14):1843-1860.
[17] LI Y Z,LUAN R,NIU J C.Forecast of power generation for grid-connected photovoltaic system based on grey model and Markov chain[C]//3rd IEEE Conference on Industrial Electronics and Applications.Singapore:IEEE,2008:1729-1733.
[18] 刁莹.用数学建模方法评价存储系统性能[D].哈尔滨:哈尔滨工程大学,2013:82-88.
[19] 林已杰.一种基于马尔科夫和神经网络的软件衰退预测方法研究[D].重庆:西南大学,2010:31-32.
[20] KARABOGA D,GORKEMLI B,OZTURK C,Karaboga N.A comprehensive survey:Artificial bee colony (ABC) algorithm and applications[J].Artificial Intelligence Review,2014,42(1):21-57.
[2] 陈琼,郑启伦,凌卫新.采用计数器存储权值的人工神经网络的实现[J].计算机工程与应用,2001,20:22-25.
[3] KARABOGA D.An idea based on honey bee swarm for numerical optimization[R].Erciyes University,Kayseri,Turkey,TechnicalReport-TR06,2005.
[4] KARABOGA D,AKAY B,OZTURK C.Artificial Bee Colony (ABC) optimization algotithm for training feed-forward neural networks[C]//LNCS:Modeling Decisions for Artificial Intelligence.Springer-Verlag,2007:18-329.
[5] BEATRIZ A G,HUMBERTO S,ROBERTO A.VáZQUEZ.Artificial neural network synthesis by means of artificial bee colony (ABC) algorithm[C]//2011 IEEE Congress of Evolutionary Computation (CEC).2011:331-338.
[6] 暴励.人工蜂群算法的混合策略研究[D].太原:太原科技大学,2010.
[7] ZHU G,KWONG S.Gbest-Guided artificial bee colony algo- rithm for numerical function optimization[J].Applied mathematics and Computation,2010,217(7):3166-3173.
[8] 周新宇,吴志健,王文明.基于正交实验设计的人工蜂群算法[J].软件学报,2015,26(9):2167-2190.
[9] 冷昕,张树群,雷兆宜.改进的人工蜂群算法在神经网络中的应用[J].计算机工程与应用,2016,52(11):7-10.
[10] 王允霞.蜂群算法的研究及其在人工神经网络中的应用[D].广州:华南理工大学,2013:25-27.
[11] 向万里,马寿峰.基于轮盘赌反向选择机制的蜂群优化算法[J].计算机应用研究,2013(1):86-89.
[12] 魏波,喻飞,徐星,等.基于改进轮盘赌策略的交互式演化算法[J].计算机与数字工程,2014(10):1762-1767.
[13] ROMANOVSKII V.Discrete Markov’s chains[M].Moscow:Gostexizdat,1949.
[14] WHITTAKER J A,THOMASON M G.A Markov Chain Mo- del for Statistical software testing[J].IEEE Transactions on Software Engineering,1994,30(10):812-824.
[15] MAREK I,SZYLD D B.Algebraic schwarz methods for the numerical solution of Markov chains[J].Linar Algebraic and its Applications,2004,386:67-81.
[16] POGGI P,NOTTON G,MUSELLI M.Stochastic study of hourly total solar radiation in Corsica using a Markov model[J].International Journal of Climatology,2000,20(14):1843-1860.
[17] LI Y Z,LUAN R,NIU J C.Forecast of power generation for grid-connected photovoltaic system based on grey model and Markov chain[C]//3rd IEEE Conference on Industrial Electronics and Applications.Singapore:IEEE,2008:1729-1733.
[18] 刁莹.用数学建模方法评价存储系统性能[D].哈尔滨:哈尔滨工程大学,2013:82-88.
[19] 林已杰.一种基于马尔科夫和神经网络的软件衰退预测方法研究[D].重庆:西南大学,2010:31-32.
[20] KARABOGA D,GORKEMLI B,OZTURK C,Karaboga N.A comprehensive survey:Artificial bee colony (ABC) algorithm and applications[J].Artificial Intelligence Review,2014,42(1):21-57.