Autonomous Mobile Programs

ABSTRACT

To manage load on large and dynamic networks we propose Autonomous Mobile Programs (AMPs) that periodically use a cost model to decide where to execute in the network. Unusually this form of autonomous mobility affects only where the program executes and not what it does. We present a generic AMP cost model, together with a validated instantiation and comparative performance results for two AMPs. Experiments on a homogeneous network show that collections of AMPs quickly obtain and maintain optimal or near-optimal balance. The advantages of our decentralised approach are scalability to very large and dynamic networks, improved balance, and guaranteed maximum overhead. The disadvantages are higher overheads and the necessity of both a cost model and explicit mobility control.

References

1. {1} J. Abawajy. Autonomic Job Scheduling Policy for Grid Computing. In Computationl Science - ICCS 2005, part 3, pages 213-220. Springer, May 2005.
2. {2} X. Y. Deng, G. Michaelson, and P. Trinder. Towards High Level Autonomous Mobility. In H.-W. Loidl, editor, Draft proceedings of Trends in Functional Programming , pages 97-112, Munic, Germany, November 2004.
3. {3} X. Y. Deng, G. Michaelson, and P. Trinder. Autonomous Mobility Skeletons. Journal of Parallel Computing, accepted March 2006.
4. {4} C. Fournet, F. L. Fessant, L. Maranget, and A. Schmitt. Jocaml: a Language for Concurrent Distributed and Mobile Programming. In Proceedings of the Fourth Summer School on Advanced Functional Programming, pages 19-24, St Anne's College, Oxford, August 2002. Springer-Verlag.
5. {5} A. Group. Sun's Grid Computing Solutions Outdistance the Competition, May 2002. http://www.sun.com/software/grid/docs/Grid_competitive.pdf.
6. {6} J. O. Kephart and D. M. Chess. The vision of autonomic computing. Computer, 36(1):41-50, 2003.
7. {7} D. B. Lange and M. Oshima. Mobile agents with Java: The Aglet API. World Wide Web, 1(3):111-121, 1998. http://dx.doi.org/10.1023/A:1019267832048.
8. {8} P. E. Merloti. Optimization Algorithms Inspired by Biological Ants and Swarm Behavior. Technical report, San Diego State University, Artificial Intelligence, CS550, San Diego, June 2004.
9. {9} C. V. Travis Desell, Kaoutar El Maghraoui. Load Balancing of Autonomous Actors over Dynamic Networks. page 90268.1, 2004.
10. {10} T. Wheeler. Voyager Architecture Best Practices. Technical report, Recursion Software, March 2005. http://www.recursionsw.com/Voyager/2005-03- 31-Voyager_Architecture_Best_Practices.pdf.
11. {11} M. Wooldridge. Agent-based software engineering. IEE Proceedings Software Engineering, 144(1):26- 37, 1997.
12. {12} WWW. Platform. http://www.platform/products/LSF.
13. {13} A. Y. Zomaya and Y.-H. Teh. Observations on Using Genetic Algorithms for Dynamic Load-Balancing. IEEE Trans. Parallel Distrib. Syst., 12(9):899-911, 2001.

Index Terms

• Computing methodologies

  • Artificial intelligence

    • Distributed artificial intelligence

      • Intelligent agents

  • Modeling and simulation

    • Model development and analysis

• Human-centered computing

  • Collaborative and social computing

• Social and professional topics

  • Professional topics

    • Management of computing and information systems

      • System management

        • Centralization / decentralization