VDC-Analyst: Design and verification of virtual desktop cloud resource allocations

P Calyam, S Rajagopalan, S Seetharam… - Computer Networks, 2014 - Elsevier
P Calyam, S Rajagopalan, S Seetharam, A Selvadhurai, K Salah, R Ramnath
Computer Networks, 2014Elsevier
One of the significant challenges for Cloud Service Providers (CSPs) hosting “virtual desktop
cloud”(VDC) infrastructures is to deliver a satisfactory quality of experience (QoE) to the
user. In order to maximize the user QoE without expensive resource overprovisioning, there
is a need to design and verify resource allocation schemes for a comprehensive set of VDC
configurations. In this paper, we present “VDC-Analyst”, a novel tool that can capture critical
quality metrics such as Net Utility and Service Response Time, which can be used to …
Abstract
One of the significant challenges for Cloud Service Providers (CSPs) hosting “virtual desktop cloud” (VDC) infrastructures is to deliver a satisfactory quality of experience (QoE) to the user. In order to maximize the user QoE without expensive resource overprovisioning, there is a need to design and verify resource allocation schemes for a comprehensive set of VDC configurations. In this paper, we present “VDC-Analyst”, a novel tool that can capture critical quality metrics such as Net Utility and Service Response Time, which can be used to quantify VDC platform readiness. This tool allows CSPs, researchers and educators to design and verify various resource allocation schemes using both simulation and emulation in two modes: “Run Simulation” and “Run Experiment”, respectively. The Run Simulation mode allows users to test and visualize resource provisioning and placement schemes on a simulation framework. Run Experiment mode allows testing on a real software-defined network testbed using emulated virtual desktop application traffic to create a realistic environment. Results from using our tool demonstrate that a significant increase in perceived user QoE can be achieved by using a combination of the following techniques incorporated in the tool: (i) optimizing Net Utility through a “Cost-Aware Utility-Maximal Resource Allocation Algorithm”, (ii) estimating values for Service Response Time using a “Multi-stage Queuing Model”, and (iii) appropriate load balancing through software-defined networking adaptations in the VDC testbed.
Elsevier
以上显示的是最相近的搜索结果。 查看全部搜索结果