QUALITY OF SERVICE-BASED RESOURCE ALLOCATION FOR WEB CONTENT DELIVERY ON CLOUD COMPUTING INFRASTRUCTURE

摘要

Demand for web content continues to increase at exponential rates and this has intensified the challenges of satisfying customer?s Quality of Service. Several techniques for Web content delivery vis-?-vis resource allocation have been proposed, one of which is the use of Content Distribution Networks. However, in recent times, cloud computing has become a driving force in Information Technology where Service Providers? limited resources are shared among numerous users with different QoS requirements. In this work, focus is on developing a model for allocation of resources on cloud computing Infrastructure in order to improve delivery of Web content and optimize service cost. An analytical approach was adopted and expressed as an optimization problem subject to QoS metrics: delay, throughput, and bandwidth. The optimization problem was formulated as an Integer Linear Programming problem in which the decision variable takes the value of 0 or 1. A single Infrastructure-as-a-Service cloud with Virtual Machine (VM) instances running in Physical Machines (PM) was assumed. The model was considered for different values of delay, throughput, and bandwidth for each VM to obtain minimum cost of delivering Web content to users. An algorithm was developed and sample data were collected from Amazon Elastic Cloud Compute/storage pricing model to obtain optimal results. The implementation of the algorithm was done using ?A Mathematical Programming Language/Modular In-core Nonlinear Optimization Systems? (AMPL/MINOS).