会议专题

Server Cluster Dynamic Load Balancing and Performance Evaluation Based on Stochastic Petri Net

A new content-aware dynamic load balancing algorithm based on quantification and classification of requests is designed by combining the advantages of layer-4 and layer-7 scheduling for increasing the throughput of Web server clusters and reducing the response time. The algorithm performance is evaluated by stochastic Petri net modeling. An advanced stochastic Petri net model is built for the system based on our algorithm and is simulated by the Stochastic Petri Net Package. Simulation results show that compared with the dynamic WRR algorithm and CAP algorithm, our algorithm achieves performance of higher throughput and lower response time.

web server cluster dynamic load balancing algorithm stochastic Petri net performance evaluation

Zhan Huang Biao Liang

Department of computer science Jinan University Guangzhou, China

国际会议

2010 International Conference on Future Information Technology(2010年未来信息技术国际会议 ICFIT 2010)

长沙

英文

854-858

2010-12-14(万方平台首次上网日期,不代表论文的发表时间)