New Generation Computing

, 29:185 | Cite as

A Bio-inspired Method for Distributed Deployment of Services

  • Máté J. Csorba
  • Hein Meling
  • Poul E. Heegaard


We look at the well-known problem of allocating software components to compute resources (nodes) in a network, given resource constraints on the infrastructure and the quality of service requirements of the components to be allocated to nodes. This problem has many twists and angles, and has been studied extensively in the literature. Solving it is particularly problematic when there is extensive dynamism and scale involved. Typically, heuristics are needed.

In this paper, we present a new breed of heuristics for solving this problem. The distinguishing feature of our approach is a decentralized optimization framework aimed at finding near optimal mappings within reasonable time and for large scale. Three different incarnations of the problem are explored through simulations. For one problem instance, we also provide exact solutions, and show that our technique is able to find near optimal solutions with low variance. In the largest example, a public-private cloud computing scenario is used, where different clouds are associated with financial costs, and we show that our approach is capable of balancing the load as expected for such a scenario.


Service Deployment Biologically-inspired Systems Decentralized Optimization 


  1. 1.
    Albrecht, J., Oppenheimer, D., Vahdat, A. and Patterson, D. A., “Design and implementation trade-offs for wide-area resource discovery,” ACM Trans. on Internet Technology, 8, 4, Sep. 2008.Google Scholar
  2. 2.
    Amazon Elastic Compute Cloud, Last checked: Aug 19, 2010.
  3. 3.
    Bastarrica, M. C., et al., “A Binary Integer Programming Model for Optimal Object Distribution,” in 2nd Int'l. Conf. on Principles of Distributed Systems, Amiens, Dec. 1998.Google Scholar
  4. 4.
    Clark, C. et al., “Live migration of virtual machines,” in 2nd USENIX Symp. on Networked Systems Design and Implementation, May 2005.Google Scholar
  5. 5.
    Csorba, M. J. and Heegaard, P. E., “Swarm intelligence heuristics for component deployment,” in 16th Eunice Int'l Workshop and IFIP WG6.6 Workshop, LNCS 6164, Trondheim, June 2010.Google Scholar
  6. 6.
    Csorba, M. J., Heegaard, P. E. and Herrmann, P., “Cost-efficient deployment of collaborating components,” in 8th IFIP Int'l Conf. on Distributed Applications and Interoperable Systems, Oslo, June 2008.Google Scholar
  7. 7.
    Csorba, M. J., Heegaard, P. E. and Herrmann, P., “Adaptable model-based component deployment guided by artificial ants,” in 2nd Int'l Conf. on Autonomic Computing and Communication Systems, Sep. 2008.Google Scholar
  8. 8.
    Csorba, M. J., Meling, H. and Heegaard, P. E., “Laying pheromone trails for balanced and dependable component mappings,” in 4th Int'l Workshop on Self-Organizing Systems, LNCS 5918, Zurich, Dec. 2009.Google Scholar
  9. 9.
    Csorba, M. J., Meling, H. and Heegaard, P. E., “Ant system for service deployment in private and public clouds,” in 2nd Workshop on Bio-Inspired Algorithms for Distributed Systems, Washington, DC, June 2010.Google Scholar
  10. 10.
    Csorba, M. J., Meling, H., Heegaard, P. E. and Herrmann, P., “Foraging for better deployment of replicated service components,” in 9th Int'l Conf. on Distributed Applications and Interoperable Systems, LNCS 5523, Lisbon, June 2009.Google Scholar
  11. 11.
    Dorigo, M., et al., “The Ant System: Optimization by a colony of cooperating agents”, IEEE Trans. on Systems, Man, and Cybernetics Part B: Cybernetics, 26, 1, Feb. 1996.Google Scholar
  12. 12.
    Efe, K., “Heuristic models of task assignment scheduling in distributed systems,” Computer, 15, 6, June 1982.Google Scholar
  13. 13.
    Elmroth, E. and Larsson, L., “Interfaces for placement, migration, and monitoring of virtual machines in federated clouds,” in 8th Int'l Conf. on Grid and Cooperative Computing, Lanzhou, Gansu, Aug. 2009.Google Scholar
  14. 14.
    Fernandez-Baca, D., “Allocating modules to processors in a distributed system,” IEEE Trans. on Software Engineering, 15, 11, Nov. 1989.Google Scholar
  15. 15.
    Heegaard, P. E., Helvik, B. E. and Wittner, O. J., “The cross entropy ant system for network path management,” Telektronikk, 104, 01, pp. 19–40, 2008.Google Scholar
  16. 16.
    Heegaard, P. E. and Wittner, O. J., “Overhead reduction in a distributed path management system,” Computer Networks, 54, 6, pp. 1019–1041, 2010.MATHCrossRefGoogle Scholar
  17. 17.
    Heimfarth, T. and Janacik, P., “Ant based heuristic for os service distribution on adhoc networks,” Biologically Inspired Cooperative Computing, 2006.Google Scholar
  18. 18.
    Helvik, B. E. and Wittner, O., “Using the Cross Entropy Method to Guide/Govern Mobile Agent's Path Finding in Networks,” in 3rd Int'l Workshop on Mobile Agents for Telecommunication Applications, LNCS 2164, Aug 2001.Google Scholar
  19. 19.
    Hirofuchi, T., Ogawa, H., Nakada, H., Itoh, S. and Sekiguchi, S., “A live storage migration mechanism over wan for relocatable virtual machine services on clouds,” in 9th IEEE/ACM Int'l Symp. on Cluster Computing and the Grid, Shanghai, May 2009.Google Scholar
  20. 20.
    Hunt, G. C. and Scott, M. L., “The Coign Automatic Distributed Partitioning System,” in 3rd USENIX Symp. on Operating Systems Design and Implementation, New Orleans, Feb. 1999.Google Scholar
  21. 21.
    Joshi, K., Hiltunen, M. and Jung, G., “Performance Aware Regeneration in Virtualized Multitier Applications,” in DSN'09 Workshop on Proactive Failure Avoidance, Recovery and Maintenance, Lisbon, Jun. 2009.Google Scholar
  22. 22.
    Karp, R. M. and Luby, M. and Marchetti-Spaccamela, A., “A probabilistic analysis of multidimensional bin packing problems,” in 16th annual ACM Symp. on Theory of Computing, Washington, DC, May 1984.Google Scholar
  23. 23.
    Kephart, J. O. and Das, R., “Achieving self-management via utility functions,” IEEE Internet Computing, 11, pp. 40–48, 2007.CrossRefGoogle Scholar
  24. 24.
    Kichkaylo, T. et al., “Constrained Component Deployment in Wide-Area Networks Using AI Planning Techniques,” Int'l. Parallel and Distributed Processing Symposium, 2003.Google Scholar
  25. 25.
    Kraemer, F. A. and Herrmann, P., “Service specification by composition of collaborations - an example,” in Proc. of the 2006 Int'l Conf. on Web Intelligence and Intelligent Agent Technology, Hong Kong, IEEE/WIC/ACM, 2006.Google Scholar
  26. 26.
    Kusber, R., Haseloff, S. and David, K., “An Approach to Autonomic Deployment Decision Making,” in 3rd Int'l Workshop on Self-Organizing Systems, LNCS 5343, December 2008.Google Scholar
  27. 27.
    Malek, S., “A User-Centric Framework for Improving a Distributed Software System's Deployment Architecture,” Proc. of the doctoral track at the 14th ACM SIGSOFT Symposium on Foundation of Software Engineering, Portland, 2006.Google Scholar
  28. 28.
    Meling, H. and Gilje, J. L., “A Distributed Approach to Autonomous Fault Treatment in Spread,” in 7th European Dependable Computing Conference, IEEE CS, May 2008.Google Scholar
  29. 29.
    Meling, H., Montresor, A., Helvik, B. E. and Babaoglu, O., “Jgroup/ARM: a distributed object group platform with autonomous replication management,” Software: Practice and Experience, 38, 9, pp. 885–923, July 2008.Google Scholar
  30. 30.
    Pu, C., Noe, J. D. and Proudfoot, A., “Regeneration of replicated objects: A technique and its eden implementation,” IEEE Transactions on Software Engineering, 14, 7, pp. 936–945, July 1989.Google Scholar
  31. 31.
    Rouvoy, R. and Beauvois, M. and Lozano, L., Lorenzo, J. and Eliassen, F., “MUSIC: an autonomous platform supporting self-adaptive mobile applications,” in 1st workshop on Mobile middleware: embracing the personal communication device, Leuven, Dec. 2008.Google Scholar
  32. 32.
    Rubinstein, R. Y., “The Cross-Entropy Method for Combinatorial and Continuous Optimization,” Methodology and Computing in Applied Probability, 1, 2, 1999.Google Scholar
  33. 33.
    Sabharwal, R., “Grid infrastructure deployment using smartfrog technology,” in Int'l Conf. on Networking and Services, Santa Clara, USA, pp. 73–79, Jul. 2006.Google Scholar
  34. 34.
    Stützle, T. and Dorigo, M., “A short convergence proof for a class of ant colony optimization algorithms,” IEEE Trans. Evolutionary Computation, 6, 4, pp. 358–365, 2002.CrossRefGoogle Scholar
  35. 35.
    Verma, A., Ahuja, P. and Neogi, A., “pmapper: power and migration cost aware application placement in virtualized systems,” in 9th Int'l Conf. on Middleware, pp. 243–264, Dec. 2008.Google Scholar
  36. 36.
    Widell, N. and Nyberg, C., “Cross Entropy based Module Allocation for Distributed Systems,” in IASTED Int'l Conf. on Parallel and Distributed Computing Systems, Cambridge, Nov. 2004.Google Scholar
  37. 37.
    Wittner, O., “Emergent Behavior Based Implements for Distributed Network Management,” Ph.D. thesis, NTNU, Dept. of Telematics, Norway, 2003.Google Scholar
  38. 38.
    Wood, T. and Shenoy, P. J. and Venkataramani, A. and Yousif, M. S., “Black-box and Gray-box Strategies for Virtual Machine Migration,” in 4th USENIX Symp. on Networked Systems Design and Implementation, Cambridge, MA, Apr. 2007.Google Scholar
  39. 39.
    Xu, J. et al., “On the use of fuzzy modeling in virtualized data center management,” in Int'l. Conf. on Autonomic Computing, June 2007.Google Scholar
  40. 40.
    Yu, H. and Gibbons, P. B., “Optimal inter-object correlation when replicating for availability,” Distributed Computing, 21, 5, pp. 367–384, Feb. 2009.Google Scholar
  41. 41.
    Yu, H. and Vahdat, A., “Consistent and automatic replica regeneration,” ACM Trans. on Storage, 1, 1, pp. 3–37, Dec. 2004.Google Scholar
  42. 42.
    Zlochin, M. et al., “Model-based search for combinatorial optimization: A critical survey,” Annals of Operations Research, 131, pp. 373–395, 2004.Google Scholar

Copyright information

© Ohmsha and Springer Japan jointly hold copyright of the journal. 2011

Authors and Affiliations

  • Máté J. Csorba
    • 1
  • Hein Meling
    • 2
  • Poul E. Heegaard
    • 1
  1. 1.Department of TelematicsNorwegian University of Science and TechnologyTrondheimNorway
  2. 2.Department of Electrical Engineering and Computer ScienceUniversity of StavangerStavangerNorway

Personalised recommendations