Abstract: The exponential growth of the Internet coupled with the increasing popularity of dynamically generated content on the World Wide Web, has created the need for more and faster Web servers capable of serving the over 100 million Internet users. To converge the control method has emerged as a promising technique to solve the Web QoS problem. In this paper, a model of adaptive session is presented and a session flow self-regulating algorism based on Kalman filter are proposed towards Web Server. And a Web QoS self-regulating scheme is advanced. To attain the goal of on-line system identification, the optimized estimation of QoS parameters is fulfilled by utilizing Kalman Filter in full domain. The simulation results shows that the proposed scheme can guarantee the QoS with both robustness and stability .

Key words: Web, QoS, Kalman filter

摘要： 给出了一种面向Web服务器的自适应节模型和基于卡尔曼滤波的会话流自适应控制算法，并在此基础上提出了一种Web QoS自适应控制机制，利用在线系统辨识实现动态的连接调度和进程重新分配，从而为不同的服务类提供相应的QoS保证。采用全论域范围内基于离散型卡尔曼滤波方法进行QoS参数的最优预测。仿真结果表明，该自适应Web服务器的QoS控制机制可以实现鲁棒的相对QoS保证，并且能够确保稳定性。

关键词: Web, 服务质量, 卡尔曼滤波

CLC Number: 

• jsjt9@henu.edu.cn