Use of Modified Adaptive Heuristic Critic Algorithm for Novel Scheduling Mechanism in Packet-Switched Networks

• Autorzy: Jednoralski M. , Kacprzak T.
• Języki publikacji: EN

Abstrakty

EN

In this paper a novel scheduling algorithm of packet selection in a switch node for transmission in a network channel, based on Reinforcement Learning and modified Adaptive Heuristic Critic is introduced. A comparison of two well known scheduling algorithms: Earliest Deadline First and Round Robin shows that these algorithms perform well in some cases, but they cannot adapt their behavior to traffic changes. Simulation studies show that novel scheduling algorithm outperforms Round Robin and Earliest Deadline First by adapting to changing of network conditions.

Słowa kluczowe

EN

reinforcement learning; telecommunication networks; packet scheduling

• Wydawca: Wydawnictwo Uniwersytetu Przyrodniczo-Humanistycznego w Siedlcach
• Czasopismo: Studia Informatica : systems and information technology
• Rocznik: 2005
• Tom: Vol. 2(6)
• Strony: 21--34
• Opis fizyczny: Bibliogr. 14 poz., rys., tab., wykr.

Twórcy

autor

Jednoralski M.

• Doctoral Study at the Faculty of Electrical and Electronic Engineering, Technical University of Łódź, Stefanowskiego Str. 18/22, 90-924 Łódź, Poland

autor

Kacprzak T.

• Institute of Electronics and Telecommunication, Technical University of Lodz, Wólczańska Str. 223, 90-924 Łódź, Poland

Bibliografia

• 1. P. Cichosz, 1997: Reinforcement Learning by Truncating Temporal Differences, PhD Thesis, Warsaw University of Technology.
• 2. Cisco IP Telephony QoS Design Guide, www.cisco.com, Cisco Systems 2001.
• 3. www.cisco.com,www.siemens.com,www.avaya.com, www.alcatel.com
• 4. R. Guerin U. Pennsylvania, Dept. Elec. Eng. V. Peris IBM T.J. Watson Research Center "Quality-of-Service in Packet Networks Basic Mechanisms and Directions" Computer Networks, vol 31, no 3 February 1999, pp: 169-179.
• 5. 3GPP, 3G TS 23.207: End-to-end QoS concept and architecture, www.3gpp.org, 2002.
• 6. “A brief overview of ATM protocol layer LAN emulation and traffic management” Computer Review ACM SIGCOMM April 1995.
• 7. R. Jain, Congestion Control and Traffic Management in ATM Networks: Recent Advances and A Survey, Computer Networks ISDN Systems Vol. 28, Issue 13 (October 1996) pp: 1723-1738.
• 8. Adam Grzech, Sterowanie ruchem w sieciach teleinformatycznych, OWPW, Wrocław, 2002.
• 9. Fukuda K, Takayasu H, Takayasu M., 2000: Origin of critical behavior of Ethernet, Physica A287, pp: 289-301.
• 10. Zdzisław Papier “Ruch telekomunikacyjny i przeciążenia sieci pakietowych” WKŁ Warszawa 2001.
• 11. Adam Grzech, Sterowanie ruchem w sieciach teleinformatycznych, OWPW, Wrocław , 2002.
• 12. R.S. Sutton and A.G. Barto, 1998: Reinforcement Learning: An Introduction, MIT Press, Cambridge, MA, p. 89.
• 13. Leslie P. Kaelbling, Michael L. Littman, 2000: Reinforcement Learning: A Survey, Journal of artificial Intelligence Research 4, 1996, pp: 237-285.
• 14. P.Cichosz, Systemy uczące się, WNT, Warszawa.