研究目的
To propose an improved scheme called wake-up system based on cloud (WaSCO) that provides high availability, consumes low CPU resource and energy, and does not need any specific server to help achieve high availability.
研究成果
WaSCO outperforms the two traditional sleep proxy methods in terms of deployment cost, CPU resource cost, and energy consumption, while still maintaining high availability. The hybrid design of WaSCO, leveraging cloud infrastructure and the CGA algorithm, provides a practical solution for enterprise desktop wake-up systems.
研究不足
The technical and application constraints include the need for a stable cloud infrastructure and the potential for network latency affecting wake-up times. Areas for optimization include further reducing the number of agents and improving the efficiency of the CGA algorithm.
1:Experimental Design and Method Selection:
The design rationale is to leverage the stability and pay-on-demand of cloud service to manage agents in various subnets without using any dedicated server. The CGA algorithm is employed to select agents and maintain at least one working agent.
2:Sample Selection and Data Sources:
The experiment was conducted on a testbed system in Intel Asia Pacific Research and Design Center with 50 desktops located in the same subnet.
3:List of Experimental Equipment and Materials:
Each desktop is equipped with a 3.10-GHz Intel Core i5, 8 GB of memory, and one Gigabit Ethernet card. The Operating System is a 64-bit Window 7 Enterprise.
4:10-GHz Intel Core i5, 8 GB of memory, and one Gigabit Ethernet card. The Operating System is a 64-bit Window 7 Enterprise.
Experimental Procedures and Operational Workflow:
4. Experimental Procedures and Operational Workflow: The cloud sends a message to the selected agents in the subnet, which then send wake-on-LAN packets to wake up the target desktop. The CGA algorithm ensures running agents in each subnet, dynamically adjusts the number of agents, and selects a few desktops as agents.
5:Data Analysis Methods:
The performance of WaSCO is evaluated in terms of availability, deployment cost, energy efficiency, and resource cost compared with traditional wake-up systems.
独家科研数据包,助您复现前沿成果,加速创新突破
获取完整内容