基于构件的Web系统前馈神经网络可靠性模型

J4 ›› 2012, Vol. 34 ›› Issue (12): 66-73.

基于构件的Web系统前馈神经网络可靠性模型

聂鹏1,2，耿技1，秦志光1

（1.电子科技大学计算机科学与工程学院，四川成都 611731；2. 江西财经大学，江西南昌 330013)

收稿日期:2011-10-13 修回日期:2012-02-23 出版日期:2012-12-25 发布日期:2012-12-25
基金资助:
国家自然科学基金资助项目（60973118,60873075）；教育部培育基金资助项目（708078）；国家863计划资助项目（2011AA010706）

Component-Based Web System Back-Propagation Neural Network Reliability Model

NIE Peng1,2,GENG Ji1,QIN Zhiguang1

(1.School of Computer Science and Engineering,University of
Electronic Science and Technology of China, Chengdu 611731；
2.Jiangxi University of Finance and Economics,Nanchang 330013,China）

Received:2011-10-13 Revised:2012-02-23 Online:2012-12-25 Published:2012-12-25

摘要/Abstract

摘要：

对基于构件结构复杂度较高的Web系统进行可靠性评估时，基于状态或基于路径的软件可靠性评估模型计算复杂度较高，鲁棒性不足。为此，提出了一种计算复杂度低、鲁棒性强的基于构件的前馈神经网络可靠性模型CBPRM。CBPRM将Web系统中各构件的可靠性作为前馈神经网络输入，并基于构件可靠性敏感度对神经元进行动态优化，Web系统可靠性评估由前馈神经网络输出实现。理论分析和实验结果表明，在基于构件结构复杂度较高的Web系统可靠性评估中，CBPRM的计算复杂度低于对比模型，并可确保可靠性评估精度。

关键词: 可靠性模型, 基于构件Web系统, 可靠性敏感度, 前馈神经网络

Abstract:

The statedbased and pathbased software reliability evaluation models suffer from the high computational complexity and the absence of robustness for the componentbased Web system evaluation with high complex structures. A Componentbased BackPropagation neural network Reliability Model (CBPRM) with a low computational complexity and robustness is proposed. The CBPRM employs the component reliabilities as the backpropagation neural network inputs. Based on the component reliability sensitivities, the neurons are optimized dynamically and the backpropagation neural network outputs the final Web system reliability evaluation. The theory analysis and experiment results present that the computational complexity of the CBPRM is evidently lower than the contrast models and the reliability evaluating accuracy is assured for the componentbased Web system with high complex structures.

Key words: reliability model;componentbased Web system;reliability sensitivity;backpropagation neural networks

聂鹏1,2，耿技1，秦志光1. 基于构件的Web系统前馈神经网络可靠性模型[J]. J4, 2012, 34(12): 66-73.

NIE Peng1,2,GENG Ji1,QIN Zhiguang1. Component-Based Web System Back-Propagation Neural Network Reliability Model[J]. J4, 2012, 34(12): 66-73.

[1]	王雨露, 李飞, 杨震, 黄山, 张罡, 詹曙, . 基于深度前馈神经网络的多因子人体表面积计算模型[J]. 计算机工程与科学, 2023, 45(01): 119-126.
[2]	李静, 莫思敏 . 基于改进遗传算法的深度神经网络优化研究[J]. 计算机工程与科学, 2021, 43(08): 1503-1511.
[3]	程亦涵，黄志球，阚双龙. 一种结合AADL和IMC的系统可靠性建模方法[J]. J4, 2015, 37(08): 1517-1524.
[4]	潘华贤, 程国建, 蔡磊. 极限学习机与支持向量机在储层渗透率预测中的对比研究[J]. J4, 2010, 32(2): 131-134.
[5]	李宝林[1] 李志蜀[1] 李斌[1] 金虎[2] 王莉[1]. 基于Bayes的软件可靠性模型研究[J]. J4, 2007, 29(10): 92-94.
[6]	蒋艳凰杨学军. 多层组合分类器研究[J]. J4, 2004, 26(6): 67-69.
[7]	柳文[1] 冯建农[2]. 一种改进型快速BP训练算法[J]. J4, 1998, 20(4): 17-20.