Performance Guarantees for Web Server End-Systems: A Control-Theoretical Approach
IEEE Transactions on Parallel and Distributed Systems
A Fuzzy Approach for the Network Congestion Problem
ICCS '02 Proceedings of the International Conference on Computational Science-Part I
A Feedback Control Architecture and Design Methodology for Service Delay Guarantees in Web Servers
A Feedback Control Architecture and Design Methodology for Service Delay Guarantees in Web Servers
The Design and Performance of a Real-Time Notification Service
RTAS '04 Proceedings of the 10th IEEE Real-Time and Embedded Technology and Applications Symposium
Admission Control and QoS Negotiations for Soft-Real Time Applications
ICMCS '99 Proceedings of the IEEE International Conference on Multimedia Computing and Systems - Volume 2
| Hi-index | 0.00 |
In this paper, a QoS-Adaptive Notification Service (QANS) scheme is proposed to prevent system overload, in which the Fuzzy-Smith control approach is applied. Different with traditional admission control, QANS adaptively adjusts the QoS level of task to control the service frequency of service provider by real-time monitoring the event channel. As a result, the system load is controlled and the performance of notification service is guaranteed. QANS is independent of the mathematical model of event channel and provides a non-linear control action, which eliminate the control error caused by inaccurate system model and linear assumption. Experimental results show that the proposed QANS scheme outperforms traditional event channel controllers in terms of system load control, response delay, and task miss-rate.