Due to the explosive growth of the Internet users, intensity of requests to the most popular web-sites often exceeds processing power of the servers. Thus novel mechanisms are needed for IP based service delivery to scale in a client-transparent way. This paper addresses the above problem considering also utilization of the available processing power of servers. In many developed caching systems, a fixed share of the processing power is dedicated to higher priority services leading to lowered overall through-put of the server system. Here we introduce and simulate a QoS aware caching method that offers lower response delay for higher quality services while minimizing the average response delay. Response delay is optimized by sharing cache memory fairly between the different QoS classes.
|Title of host publication||Proceedings of the International Conference on Telecommunications, ICT 2002|
|Subtitle of host publication||Beijing, China, 23-26 June 2002|
|Publisher||Publishing House of Electronics Industry|
|Publication status||Published - 2002|
|MoE publication type||A4 Article in a conference publication|