Abstract
In a peer-to-peer file-sharing system, a client desiring a particular file must choose a source from which to download. The problem of selecting a good data source is difficult because some peers may not be encountered more than once, and many peers are on low-bandwidth connections. Despite these facts, information obtained about peers just prior to the download can help guide peer selection. A client can gain additional time savings by aborting bad download attempts until an acceptable peer is discovered. We denote as peer selection the entire process of switching among peers and finally settling on one. Our main contribution is to use the methodology of machine learning for the construction of good peer selection strategies from past experience. Decision tree learning is used for rating peers based on low-cost information, and Markov decision processes are used for deriving a policy for switching among peers. Preliminary results with the Gnutella network demonstrate the promise of this approach.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Gwertzman, J., Seltzer, M.: The case for geographical push-caching. In: Proceedings of the 1995 Workshop on Hot Operating Systems, pp. 51–55 (1995)
Guyton, J.D., Schwartz, M.F.: Locating nearby copies of replicated Internet servers. In: Proceedings of SIGCOMM 1995, Boston, MA, pp. 288–298 (1995)
Yoshikawa, C., Chun, B., Eastham, P., Vadhat, A., Anderson, T., Culler, D.: Using smart clients to build scalable services. In: Proceedings of the First USENIX Symposium on Internet Technologies and Systems (1997)
Sayal, M., Breitbart, Y., Scheuermann, P., Vigralek, P.: Selection algorithms for replicated web servers. Performance Evaluation Review 26, 44–50 (1998)
Carter, R.L., Crovella, M.E.: On the network impact of dynamic server selection. Computer Networks 31, 2529–2558 (1999)
Dykes, S.G., Robbins, K.A., Jeffery, C.L.: An empirical evaluation of client-side server selection algorithms. In: Proceedings of INFOCOM 2000, pp. 1361–1370 (2000)
Stemm, M., Katz, R., Seshan, S.: A network measurement architecture for adaptive applications. In: Proceedings of INFOCOM 2000 (2000)
Zegura, E.W., Ammar, M.H., Fei, Z., Bhattacharjee, S.: Application-layer anycasting: A server selection architecture and use in a replicated web service. IEEE/ACM Transactions on Networking 8, 455–466 (2000)
Hanna, K.M., Natarajan, N., Levine, B.N.: Evaluation of a novel two-step server selection metric. In: Proceedings of IEEE International Conference on Network Protocols, Paris, France (2001)
Quinlan, J.R.: C4.5: Programs for Machine Learning. Morgan Kaufmann, San Mateo (1993)
Utgoff, P.E., Berkman, N.C., Clouse, J.A.: Decision tree induction based on efficient tree restructuring. Machine Learning 29, 5–44 (1997)
Puterman, M.L.: Markov Decision Processes. J. Wiley & Sons, New York (1994)
Bellman, R.E.: Dynamic Programming. Princeton University Press, Princeton (1957)
Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)
Williams, R.J.: Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine Learning 8, 229–256 (1992)
Byers, J., Luby, M., Mitzenmacher, M.: Accessing multiple mirror sites in parallel: Using tornado codes to speed up downloads. In: Proceedings of INFOCOM 1999 (1999)
Rodriguez, P., Biersack, E.W.: Dynamic parallel-access to replicated content in the Internet. IEEE/ACM Transactions on Networking 10, 455–464 (2002)
Zeitoun, A., Jomjoom, H., El-Gendy, M.: Scalable parallel-access for mirrored servers. In: Proceedings of IASTED International Conference on Applied Informatics, Innsbruck, Austria (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Bernstein, D.S., Feng, Z., Levine, B.N., Zilberstein, S. (2003). Adaptive Peer Selection. In: Kaashoek, M.F., Stoica, I. (eds) Peer-to-Peer Systems II. IPTPS 2003. Lecture Notes in Computer Science, vol 2735. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-45172-3_22
Download citation
DOI: https://doi.org/10.1007/978-3-540-45172-3_22
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40724-9
Online ISBN: 978-3-540-45172-3
eBook Packages: Springer Book Archive