网格环境下多服务质量约束的复合服务调度机制

摘要/Abstract

摘要： 目前,由于没有一个动态、可扩展的服务组合模型，在服务网格环境中缺乏满足多性能目标约束的、复合服务的调度机制。为此，在分析动态服务调度机制基础上,将服务质量约束引入到状态图工作流模型中，提出一种多服务质量约束的动态组合服务模型，给出了在服务组合过程中保持服务组件之间服务质量一致性的方法，并将复合服务的调度问题（即执行路径的动态选择问题）归结为多属性决策问题。采用简单加权法，以保证组合后的服务满足综合服务质量约束。通过实现的服务调度组件验证了该机制的可行性和有效性。

关键词: 服务网格, 复合服务, 服务质量, 工作流模型, 服务调度, 多属性决策, 简单加权法

Abstract: To deal with the problem of scheduling service with multiple QoS constraints in service grid, based on analysis of dynamic services scheduling mechanism, with introduction of Quality of Service (QOS) constraints to state-chart based workflow model, a model of service composition with multiple QoS constraints was presented and a method to keep QoS consistency during the process of service composition was proposed. Then, a scheduling service component was implemented by evolving the scheduling problem of executing path of composite service to the problem of Multiple Attribute Decision Making (MADM) which could be solved by using Simple Additive Weight (SAW) method. The result indicated that the proposed mechanism was feasible and efficient on scheduling dynamic composite services in service grid.

Key words:service grid; composite service; quality of service; workflow model; scheduling service; multiple attribute decision-making; simple additive weight

Key words: CIMS Research Cent., Dep. of Computer, Southeast Univ., Nanjing , , 210096, China

中图分类号:

谷清范，吴介一，张飒兵. 网格环境下多服务质量约束的复合服务调度机制[J]. .

GU Qing-fan, WU Jie-yi, ZHANG Sa-bing. Scheduling mechanism of composite grid service with multiple QoS constraints[J]. .

参考文献

［1］ FOSTER I, KESSELMAN C, NICK J, et al.The physiology of the grid: an open grid services architecture for distributed systems integration［EB/OL］. http://www.globus.org/research/papers/ogsa.pdf,2002-6-22/2004-10-5.

[2] Globus Toolkit 3.2 Documentation［EB/OL］. http://www-unix.globus.org/toolkit/ docs/3.2/index.html，2002-5-22/2004-7-28.

[3] LITZKOW M J， LIVNY M， MUTKA M W. Condor-a hunter of idle workstations［A］. Proceedings of 8th International Conference on Distributed Computing Systems［C］. Washington,D.C.,USA:IEEE Computer Society Press, 1988.104-110.

[4] BENATALLAH B，DUMAS M， SHENG Q Z， et al. Declarative composition and peer-to-peer provisioning of dynamic Web services［A］.Proceedings of the 18th International Conference on Data Engineering (ICDE.02)［C］.San Jose,USA:IEEE,2002.297-308.

[5] ZENG Liangzhao, BENATALLAH B, DUMAS M. Quality driven Web services composition［A］. Proceedings of the 12th International Conference on World Wide Web (WWW)［C］. Budapest, Hungary:ACM Press, 2003.73.

[6] GU Xiaohui, NAHRSTEDT K, CHANG R N, et al. QoS-assured service composition in managed service overlay networks［A］.Proceedings of 23rd IEEE International Conference on Distributed Computing Systems (ICDCS 2003)［C］.Providence,RI,USA:IEEE ICDCS,194-201.

[7] NABRZYSKI J, SCHOPF J M, WEGLARZ J.Grid resource management: state of the art and future trends［M］Boston,MA,USA:KLUWER Academic Publishers,2003.416-431.

[8] RAMAN B, KATZ R H. An architecture for highly available wide-area service composition［EB/OL］.http://www.cse.iitk.ac.in/～bhaskar/berkeley/ccj/ccj.pdf,2004-03-31/2004-10-05.

[9] CIAJKOWSKI K,FERGUSON D F,FOSTER I,et al.The WS-resource framework［EB/OL］.http://www.globus.org/wsrf/specs/ws-wsrf.pdf,2004-03-05/2004-10-15.

[10] WOLSKI R. Experiences with predicting resource performance on-line in computational grid settings［EB/OL］.http://www.cs.ucsb.edu/～rich/publications/acm-per.pdf,2003-03-04/2004-10-05.

[11] RAJABJ S， HIPEL K W， KILGOUR D M. Multiple criteria decision making under interdependence of actions systems［A］.IEEE Transactions on Systems Man,and Cybernetics Conference［C］.USA:SMC-14,1995.2365-2370.

[12] YOON K P，HWANG C L, Multiple attribute decision making. Quantitative applications in the social sciences［M］.London,U.K.: Sage Publications Inc.,1995.1-58.

[1]	闫志强,杨翰宇,程冠杰,刘洪荣,邓水光,刘冠宇,杨明. 基于区块链的服务质量综合评估框架与算法[J]. 计算机集成制造系统, 2021, 27(9): 2708-2720.
[2]	王婕,耿秀丽. 基于直觉模糊余弦相似度的云制造服务质量评价[J]. 计算机集成制造系统, 2021, 27(4): 1128-1134.
[3]	胡杨,吴锋,王红涛. 考虑稀缺服务与质量损失云制造服务组合问题[J]. 计算机集成制造系统, 2021, 27(12): 3639-3650.
[4]	张志坚,王鹏,柳键,罗春林,郭军华. 考虑在线评价的供应链运营决策与奖惩机制[J]. 计算机集成制造系统, 2020, 26(7): 1986-1997.
[5]	熊升华,陈振颂,陈勇刚,贺强. 基于指标模糊分割和MULTIMOORA的航空公司机队可靠性识别模型[J]. 计算机集成制造系统, 2019, 25(第2): 431-438.
[6]	陈友玲,王龙,刘舰,左丽丹,牛禹霏. 基于i-NSGA-Ⅱ-JG算法的云制造资源服务组合优选[J]. 计算机集成制造系统, 2019, 25(第11): 2892-2904.
[7]	陈友玲,刘舰,凌磊,王龙. 基于协同效应的并行制造云服务组合算法[J]. 计算机集成制造系统, 2019, 25(第1): 137-146.
[8]	王福田,李月婷,章程,张以文,刘晓,杨耘. 实例密集型商务工作流检测点选择策略[J]. 计算机集成制造系统, 2018, 24(第7): 1758-1765.
[9]	潘建梁,俞东进,陈耀旺. 基于关系矩阵的工作流日志重复任务识别算法[J]. 计算机集成制造系统, 2018, 24(第7): 1784-1792.
[10]	张云正,曾建潮,张晓红,薛颂东. 多设备租赁条件下基于服务质量评估的预防性维修策略优化[J]. 计算机集成制造系统, 2018, 24(第5): 1162-1170.
[11]	金鸿,姚锡凡,杨洲,吕盛坪. 基于教—学算法的制造云服务组合优化[J]. 计算机集成制造系统, 2018, 24(第1): 43-52.
[12]	贺可太,朱道云. 云制造服务质量评价[J]. 计算机集成制造系统, 2018, 24(第1): 53-62.
[13]	郑宏升,俞东进,张蕾. 基于萤火虫算法和动态优先级的多QoS云工作流调度[J]. 计算机集成制造系统, 2017, 23(第5期): 963-971.
[14]	徐文庭,殷昱煜,王菊仙,王兴菲,余方正. 基于CART与SlopeOne的服务质量预测算法[J]. 计算机集成制造系统, 2017, 23(第5期): 1080-1090.
[15]	余高锋,李登峰,叶银芳,邱锦明. 考虑后悔规避的异质多属性变权决策方法[J]. 计算机集成制造系统, 2017, 23(第1期): 154-161.