Applied Intelligence

, Volume 38, Issue 3, pp 436–464 | Cite as

Agent-based Cloud service composition

  • J. Octavio Gutierrez-Garcia
  • Kwang Mong Sim


Service composition in multi-Cloud environments must coordinate self-interested participants, automate service selection, (re)configure distributed services, and deal with incomplete information about Cloud providers and their services. This work proposes an agent-based approach to compose services in multi-Cloud environments for different types of Cloud services: one-time virtualized services, e.g., processing a rendering job, persistent virtualized services, e.g., infrastructure-as-a-service scenarios, vertical services, e.g., integrating homogenous services, and horizontal services, e.g., integrating heterogeneous services. Agents are endowed with a semi-recursive contract net protocol and service capability tables (information catalogs about Cloud participants) to compose services based on consumer requirements. Empirical results obtained from an agent-based testbed show that agents in this work can: successfully compose services to satisfy service requirements, autonomously select services based on dynamic fees, effectively cope with constantly changing consumers’ service needs that trigger updates, and compose services in multiple Clouds even with incomplete information about Cloud participants.


Agent-based Cloud computing Autonomous agents Cloud computing Cloud resource management Cloud service composition Multiagent systems 



This work was supported by the Korea Research Foundation Grant funded by the Korean Government (MEST) (KRF-2009-220-D00092). From May 18, 2010 through January 16, 2012, the first author was supported by a postdoctoral fellowship at the Multiagent and Cloud Computing Systems Laboratory at the Gwangju Institute of Science and Technology, South Korea. The first author acknowledges with thanks the support provided by Asociación Mexicana de Cultura A. C. from August 1, 2012. In addition, the authors would like to thank the Editor-in-Chief and the anonymous referees for their comments and suggestions.


  1. 1.
    Amazon EC2 FAQs (2012) Accessed 10 May 2012
  2. 2.
    Amazon EC2 Instance Types (2012) Accessed 10 May 2012
  3. 3.
    Amazon Elastic Compute Cloud—Amazon EC2 (2012) Accessed 10 May 2012
  4. 4.
    Amazon Product Advertising API License Agreement (2012) Accessed 10 May 2012
  5. 5.
    Battle R, Benson E (2008) Bridging the semantic web and web 2.0 with representational state transfer. J Web Semant 6(1):61–69 CrossRefGoogle Scholar
  6. 6.
    Bauer B, Müller JP, Odell J (2001) Agent uml: a formalism for specifying multiagent software systems. Int J Softw Eng Knowl Eng 11(3):207–230 CrossRefGoogle Scholar
  7. 7.
    Bellifemine F, Poggi A, Rimassa G (1999) JADE—a FIPA-compliant agent framework. In: Proc 4th international conference and exhibition on the practical application of intelligent agents and multi-agents, pp 97–108 Google Scholar
  8. 8.
    Blake MB, Gomaa H (2005) Agent-oriented compositional approaches to services-based cross-organizational workflow. Decis Support Syst 40(1):31–50 CrossRefGoogle Scholar
  9. 9.
    Both F, Hoogendoorn M, Mee A, Treur J, Vos M (2012) An intelligent agent model with awareness of workflow progress. Appl Intell 36(2):498–510 CrossRefGoogle Scholar
  10. 10.
    Bryson J, Martin D, McIlraith S, Stein LA (2003) Agent-based composite services in daml-s: the behavior-oriented design of an intelligent semantic web. In: Zhong N, Liu J, Yao Y (eds) Web intelligence. Springer, Heidelberg, pp 37–58 Google Scholar
  11. 11.
    Buyya R, Yeo CS, Venugopal S, Broberg J, Brandic I (2009) Cloud computing and emerging it platforms: vision, hype, and reality for delivering computing as the 5th utility. Future Gener Comput Syst 25(6):599–616 CrossRefGoogle Scholar
  12. 12.
    Chafle GB, Chandra S, Mann V, Nanda MG (2004) Decentralized orchestration of composite web services. In: Proc 13th international world wide web conference on alternate track papers & posters. ACM Press, New York, pp 134–143 CrossRefGoogle Scholar
  13. 13.
    Choudhary V (2007) Software as a service: implications for investment in software development. In: Proc 40th annual Hawaii international conference on system sciences. IEEE Computer Society, Washington, pp 209–218 Google Scholar
  14. 14.
    Cloud Hosting, Cloud Servers, Hybrid Hosting, Cloud infrastructure from GoGrid (2012) Accessed 10 May 2012
  15. 15.
    Ferber J (1999) Multi-agent systems: an introduction to distributed artificial intelligence, 1st edn. Addison-Wesley, Longman, Boston Google Scholar
  16. 16.
    Gao J, Lv H (2012) Institution-governed cross-domain agent service cooperation: a model for trusted and autonomic service cooperation. Appl Intell 37(2):223–238 CrossRefGoogle Scholar
  17. 17.
    Gershenson C, Heylighen F (2003) When can we call a system self-organizing? In: Banzhaf W, Christaller T, Dittrich P, Kim JT, Ziegler J (eds) Advances in artificial life, ECAL 2003. LNAI, vol 2801. Springer, Heidelberg, pp 606–614 Google Scholar
  18. 18.
    Google Cloud Services (2012) Accessed 10 May 2012
  19. 19.
    Graham RL, Knuth DE, Patashnik O (1994) Concrete mathematics, 2nd edn. Addison-Wesley, Reading zbMATHGoogle Scholar
  20. 20.
    Gutierrez-Garcia JO, Sim KM (2010) Agent-based service composition in cloud computing. In: Kim TH, et al (eds) GDC/CA 2010. CCIS, vol 121. Springer, Heidelberg, pp 1–10 Google Scholar
  21. 21.
    Gutierrez-Garcia JO, Sim KM (2010) Self-organizing agents for service composition in cloud computing. In: 2010 IEEE second international conference on cloud computing technology and science, USA, pp 59–66 CrossRefGoogle Scholar
  22. 22.
    Helal S, Wang M (2001) Service centric brokering in dynamic e-business agent communities. J Electron Commer Res 2(1):32–47 Google Scholar
  23. 23.
    Helal S, Wang M, Jagatheesan A, Krithivasan R (2001) Brokering based self organizing e-service communities. In: Proc 5th international symposium on autonomous decentralized systems. IEEE Computer Society, Washington, pp 349–356 CrossRefGoogle Scholar
  24. 24.
    Hewitt C (1977) Viewing control structures as patterns of passing messages. Artif Intell 8(3):323–364 CrossRefGoogle Scholar
  25. 25.
    Heylighen F, Gershenson C (2003) The meaning of self-organization in computing. IEEE Intell Syst 18(4):72–75 CrossRefGoogle Scholar
  26. 26.
    Isern D, Moreno A, Sánchez D, Hajnal Á., Pedone G, Varga L (2011) Agent-based execution of personalised home care treatments. Appl Intell 34(2):155–180 CrossRefGoogle Scholar
  27. 27.
    Kang J, Sim KM (2012) A multiagent brokering protocol for supporting Grid resource discovery. Appl Intell. doi: 10.1007/s10489-012-0347-y Google Scholar
  28. 28.
    Korhonen J, Pajunen L, Puustjarvi J (2003) Automatic composition of web service workflows using a semantic agent. In: Proc IEEE/WIC/ACM international conference on web intelligence. IEEE Computer Society, Washington, pp 5663–5666 Google Scholar
  29. 29.
    Kuzu M, Cicekli N (2012) Dynamic planning approach to automated web service composition. Appl Intell 36(1):1–28 CrossRefGoogle Scholar
  30. 30.
    Lai K, Lin M, Yu T (2010) Learning opponent’s beliefs via fuzzy constraint-directed approach to make effective agent negotiation. Appl Intell 33(2):232–246 CrossRefGoogle Scholar
  31. 31.
    Lenk A, Klems M, Nimis J, Tai S, Sandholm T (2009) What’s inside the Cloud? An architectural map of the Cloud landscape. In: Proc 2009 ICSE workshop on software engineering challenges of Cloud computing. IEEE Computer Society, Washington, pp 23–31 CrossRefGoogle Scholar
  32. 32.
    Mei L, Chan WK, Tse TH (2008) A tale of clouds: paradigm comparisons and some thoughts on research issues. In: Proc IEEE Asia–Pacific services computing conference. IEEE Computer Society, Washington, pp 464–469 Google Scholar
  33. 33.
    Mousavi A, Nordin MJ, Othman ZA (2012) Ontology-driven coordination model for multiagent-based mobile workforce brokering systems. Appl Intell 36(4):768–787 CrossRefGoogle Scholar
  34. 34.
    Murillo J, Muñoz V, Busquets D, López B (2011) Schedule coordination through egalitarian recurrent multi-unit combinatorial auctions. Appl Intell 34(1):47–63 CrossRefGoogle Scholar
  35. 35.
    Narayanan S, McIlraith S (2002) Simulation, verification and automated composition of web services. In: Proc 11th international world wide web conference. ACM Press, New York, pp 77–88 Google Scholar
  36. 36.
    O’Shea K (2012) An approach to conversational agent design using semantic sentence similarity. Appl Intell. doi: 10.1007/s10489-012-0349-9 Google Scholar
  37. 37.
    Öztürk P, Rossland K, Gundersen O (2010) A multiagent framework for coordinated parallel problem solving. Appl Intell 33(2):132–143 CrossRefGoogle Scholar
  38. 38.
    Pallis G (2010) Cloud computing: the new frontier of internet computing. IEEE Internet Comput 14(5):70–73 CrossRefGoogle Scholar
  39. 39.
    Peltz C (2003) Web services orchestration and choreography. Computer 36(10):46–52 CrossRefGoogle Scholar
  40. 40.
    Sandholm T (1993) An implementation of the contract net protocol based on marginal cost calculations. In: Proc of the 11th national conference on artificial intelligence. AAAI Press, Menlo Park, pp 256–262 Google Scholar
  41. 41.
    Sim KM (2006) Guest editorial: agent-based grid computing. Appl Intell 25(2):127–129 CrossRefGoogle Scholar
  42. 42.
    Sim KM (2009) Agent-based cloud commerce. In: Proc IEEE international conference on industrial engineering and engineering management, Hong Kong, pp 717–721 Google Scholar
  43. 43.
    Sim KM (2010) Towards complex negotiation for cloud economy. In: Chang RS, et al (eds) GPC 2010. LNCS, vol 6104. Springer, Heidelberg, pp 395–406 Google Scholar
  44. 44.
    Sim KM (2011) Agent-based cloud computing. IEEE Trans Serv Comput. doi: 10.1109/TSC.2011.52 Google Scholar
  45. 45.
    Sim KM (2012) Complex and concurrent negotiations for multiple interrelated e-markets. IEEE Trans Syst Man Cybern B Cybern. doi: 10.1109/TSMCB.2012.2204742 Google Scholar
  46. 46.
    Smith RG (1980) The contract net protocol: high-level communication and control in a distributed problem solver. IEEE Trans Comput 29(12):1104–1113 CrossRefGoogle Scholar
  47. 47.
    Sun Microsystems, Inc (2012) Determining acceptable response delays. Accessed 10 May 2012
  48. 48.
    Sycara KP (1998) Multiagent systems. AI Mag 19(2):79–92 Google Scholar
  49. 49.
  50. 50.
    Vouk MA (2008) Cloud computing—issues, research and implementations. J Comput Inf Technol 16(4):235–246 Google Scholar
  51. 51.
    Wang S, Shen W, Hao Q (2006) An agent-based web service workflow model for inter-enterprise collaboration. Expert Syst Appl 31(4):787–799 CrossRefGoogle Scholar
  52. 52.
    Weiss G (1999) Multiagent systems: a modern approach to distributed artificial intelligence. MIT Press, Cambridge Google Scholar
  53. 53.
    Wooldridge M (2009) An introduction to multiagent systems, 2nd edn. Wiley, Chichester Google Scholar
  54. 54.
    World Wide Web Consortium—W3C (2012) Web services Architecture, Accessed 10 May 2012
  55. 55.
    Zeng C, Guo X, Ou W, Han D (2009) Cloud computing service composition and search based on semantic. In: Jaatun MG, Zhao G, Rong C (eds) CloudCom. LNCS, vol 5931. Springer, Heidelberg, pp 290–300 Google Scholar
  56. 56.
    Zou G, Chen Y, Yang Y, Huang R, Xu Y (2010) AI planning and combinatorial optimization for web service composition in cloud computing. In: Proc international conference on cloud computing and virtualization, pp 1–8 Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2012

Authors and Affiliations

  1. 1.Computer Science DepartmentInstituto Tecnológico Autónomo de MéxicoMexico CityMexico
  2. 2.School of ComputingThe University of KentChatham MaritimeUK

Personalised recommendations