基于模糊原理的中间件自适应优化

Adaptive Mid-Ware Performance Turning Based on Fuzzy Control

J2EE中间件系统得到了广泛的使用。为了提高服务性能,需要配置系统参数。传统的手工配置法费时费力,而且在负载变化的环境中不能自适应改变,造成了性能随时间越来越低下。为此,我们提出了基于模糊控制J2EE应用服务器自适应调优系统。系统实时监控性能数据,并基于模糊决策器,动态改变参数,优化性能。通过测试表明,该系统能减少响应时间,提高系统性能。

J2EE is widely used mid-ware system, which needs to configure parameter to improve performance. This is unfortunately a necessary task in order to achieve optimal performance under dynamic workload environment. In this paper, we present a new adaptive J2EE performance turning system, which dynamically monitors and measures the system behaviors, independently feeds these measures into our model, and uses the results derived from the model to adaptively self-configure the systems. Experimental results demonstrate the feasibility and practicality of our architecture and approach in adaptively self-configuring J2EE-based middleware systems.