6533b7d7fe1ef96bd126858e

RESEARCH PRODUCT

Performance evaluation of fuzzy-neural HTTP request distribution for Web clusters

Krzysztof ZatwarnickiLeszek Borzemski

subject

Soft computingArtificial neural networkComputer sciencebusiness.industryResponse timeWorkloadFeedback loopcomputer.software_genreFuzzy logicServerThe InternetArtificial intelligenceData miningbusinesscomputer

description

In this paper we present the performance evaluation of our fuzzy-neural HTTP request distribution algorithm called FNRD, which assigns each incoming request to the server in the Web cluster with the quickest expected response time. The fuzzy mechanism is used to estimate the expected response times. A neural-based feedback loop is used for real-time tuning of response time estimates. To evaluate the system, we have developed a detailed simulation and workload model using CSIM19 package. Our simulations show that FNRD can be more effective than its competitors.

http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=ORCID&SrcApp=OrcidOrg&DestLinkType=FullRecord&DestApp=WOS_CPL&KeyUT=WOS:000239600000021&KeyUID=WOS:000239600000021