融合直觉模糊灰色理论的制造云服务QoS评价方法  

QoS evaluation method for manufacturing cloud services combining with intuitionistic fuzzy and grey theory

作　　者：陈君 赵小会 郭立颖 季虹 李维乾 CHEN Jun;ZHAO Xiaohui;GUO Liying;JI Hong;LI Weiqian(School of Computer Science/The Shaanxi Key Laboratory of Clothing Intelligence,Xi’an Polytechnic University,Xi’an 710048,China)

机构地区：[1]西安工程大学计算机科学学院/陕西省服装设计智能化重点实验室,陕西西安710048

出　　处：《西安工程大学学报》2023年第3期101-108,共8页Journal of Xi’an Polytechnic University

基　　金：国家自然科学基金(62106189);陕西省高速公路施工机械重点实验室开放基金(300102250510);西安工程大学科研基金(BS201847)。

摘　　要：为了使用户能够快速从大量功能相似的制造云服务中做出合理选择,在考虑评价指标多样性和评价信息不确定性的基础上,结合灰色理论,给出了一种制造云服务评价方法。首先,构建制造云服务QoS评价模型,并阐述模型的运作机制。其次,搭建了制造云服务的评价指标体系,通过引入直觉模糊数实现非量化指标定义。随后,提出基于直觉模糊灰色关联的云服务排序方法,通过结合云服务制造商评价矩阵和云服务使用者评价矩阵,共同构建云服务直觉模糊综合矩阵,并获取最优属性矩阵,进而求解各制造云服务评价属性和最优服务属性的灰色关联度系数,从而确定关联度,为用户提供排序参考。实验结果表明:提出的算法随着属性权重值的改变,候选服务的排序结果也会发生改变,表明算法具有一定的灵活性。最后,将候选制造云服务的服务质量用该文算法和直觉模糊TOPSIS法、熵权TOPSIS法进行贴近度的对比,算法的贴近度全部大于对比算法,相对于直觉模糊TOPSIS法提升约为12%,相对于熵权TOPSIS法提升约为44%,验证了其合理性和实用性。In order to enable users to quickly make a reasonable choice from a large number of manufacturing cloud services with similar functions,on the basis of diversity of the evaluation indicators and the uncertainty of evaluation information,the evaluation method of manufacturing cloud services was proposed in conjunction with grey theory.Firstly,the QoS evaluation model of manufacturing cloud service was constructed and described.Secondly,evaluation structure was established,and the non-quantitative indicator was also defined by intuitionistic fuzzy number.Furthermore,the manufacturing cloud service ranking method based on intuitionistic fuzzy and grey theory was designed.With constructing intuitionistic fuzzy comprehensive matrix and obtaining optimal attribute matrix,the grey correlation coefficienTSbetween evaluation attributes and the optimal service attributes were solved for each manufacturing cloud service,and then the correlation degree was determined so as to provide a ranking reference for users.The experimental resulTSshow that:Then the proposed algorithm changes with the attribute weight value,and the ranking resulTSof the candidate services also change,indicating that the algorithm has a certain flexibility.Finally,the service quality of the candidate manufacturing cloud service was compared with the proposed algorithm and the intuitive fuzzy TOPSIS method and the entropy right TOPSIS method.The closeness of the proposed algorithm is all greater than the comparison algorithm,which is improved by about 12%compared with the intuitive fuzzy TOPSIS method and about 44%compared with the entropy right TOPSIS method,which verifies iTSrationality and practicability.

关 键 词：云制造 云服务 QOS 直觉模糊 灰色关联 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]