A self-tuning fuzzy control approach for end-to-end QoS guarantees in web servers

Abstract

It is important to guarantee end-to-end quality of service (QoS) under heavy-load conditions. Existing work focus on server-side request processing time or queueing delays in the network core. In this paper, we propose a novel framework eQoS to monitoring and controlling client-perceived response time in Web servers. The response time is measured with respect to requests for Web pages that contain multiple embedded objects. Within the framework, we propose an adaptive fuzzy controller, STFC, to allocating server resources. It deals with the effect of process delay in resource allocation by its two-level self-tuning capabilities. Experimental results on PlanetLab and simulated networks demonstrate the effectiveness of the framework: it controls client-perceived pageview response time to be within 20% of a pre-defined target. In comparison with static fuzzy controller, experimental results show that, although the STFC has slightly worse performance in the environment where the static fuzzy controller is best tuned, because of its self-tuning capabilities, it works better in all other test cases by 25% in terms of the deviation from the target response time. In addition, due to its model independence, the STFC outperforms the linear proportional integral (PI) and adaptive PI controllers by 50% and 75%, respectively. © IFIP International Federation for Information Processing 2005.