The Deferrable Server Algorithm for Enhanced Aperiodic Responsiveness in Hard Real-Time Environments
IEEE Transactions on Computers
Aperiodic servers in a deadline scheduling environment
Real-Time Systems
End-to-end scheduling to meet deadlines in distributed systems
End-to-end scheduling to meet deadlines in distributed systems
Scheduling Algorithms for Multiprogramming in a Hard-Real-Time Environment
Journal of the ACM (JACM)
On Quality of Service Optimization with Discrete QoS Options
RTAS '99 Proceedings of the Fifth IEEE Real-Time Technology and Applications Symposium
Real-time scheduling in a programmable radar signal processor
RTCSA '97 Proceedings of the 4th International Workshop on Real-Time Computing Systems and Applications
On task schedulability in real-time control systems
RTSS '96 Proceedings of the 17th IEEE Real-Time Systems Symposium
A resource allocation model for QoS management
RTSS '97 Proceedings of the 18th IEEE Real-Time Systems Symposium
Practical Solutions for QoS-Based Resource Allocation
RTSS '98 Proceedings of the IEEE Real-Time Systems Symposium
Task Period Selection and Schedulability in Real-Time Systems
RTSS '98 Proceedings of the IEEE Real-Time Systems Symposium
A Scalable Solution to the Multi-Resource QoS Problem
RTSS '99 Proceedings of the 20th IEEE Real-Time Systems Symposium
On Scheduling Tasks in Reliable Real-Time Control Systems
RTSS '99 Proceedings of the 20th IEEE Real-Time Systems Symposium
Real-time digital signal processing of component-oriented phased array radars
RTSS'10 Proceedings of the 21st IEEE conference on Real-time systems symposium
Euromicro-RTS'00 Proceedings of the 12th Euromicro conference on Real-time systems
Hierarchical adaptive QoS control for voting-based data collection in hostile scenarios
Proceedings of the 8th International Conference on Network and Service Management
Hi-index | 0.00 |
Many application level qualities are functions of available computation resources. Recent studies have handled the computation resource allocation problem to maximize the overall application quality. However, such QoS problems are fundamentally multi-dimensional optimization problems that require extensive computation. Therefore, online usage of optimization procedures may significantly reduce the computation resource available for applications. This raises the question of how to best use the optimization procedures for dynamic real-time task sets. In dynamic real-time systems, it is important to improve the performance by re-allocating the resources adapting to dynamic situations. However, the overhead of changing task parameters (i.e., algorithms and frequencies) for resource re-allocation is non-negligible in many applications. Thus, too frequent change of resource allocation may not be desirable. This paper proposes a method called service classes configuration to address the QoS problem with dynamic arrival and departure of tasks. The method avoids online usage of optimization procedures by offline designing templates (called service classes) of resource allocation, which will be adaptively used depending on online situations. The service classes are designed by best trading-off the accuracy of dynamic adaptation against the overhead of resource re-allocation. A simplified radar application is used as an illustrative example.