Building adaptive systems using ensemble
Software—Practice & Experience - Special issue on multiprocessor operating systems
Static scheduling algorithms for allocating directed task graphs to multiprocessors
ACM Computing Surveys (CSUR)
Survivability analysis of networked systems
ICSE '01 Proceedings of the 23rd International Conference on Software Engineering
Computer
An Architecture-Based Approach to Self-Adaptive Software
IEEE Intelligent Systems
Building Survivable Services Using Redundancy and Adaptation
IEEE Transactions on Computers
Parallel program performance prediction using deterministic task graph analysis
ACM Transactions on Computer Systems (TOCS)
Extending the Limits of DMAS Survivability: The UltraLog Project
IEEE Intelligent Systems
A taxonomy of scientific workflow systems for grid computing
ACM SIGMOD Record
Parallel Computing - Heterogeneous computing
Software reuse: survey and research directions
Journal of Management Information Systems - Special section: Managing virtual workplaces and teleworking with information technology
Efficient scheduling algorithm for component-based networks
Future Generation Computer Systems
Adaptive software testing with fixed-memory feedback
Journal of Systems and Software
Performance modeling for dynamic algorithm selection
ICCS'03 Proceedings of the 2003 international conference on Computational science
Hi-index | 0.00 |
As a result of technological advances, a typical type of software systems has emerged. A large number of distributed software components are networked together through a task flow structure, and each component may have alternative algorithms among which it can choose to process tasks. However, the increased complexity and vulnerability to adverse events of such systems give rise to the need for more sophisticated yet scalable control mechanisms. In this study a control mechanism is designed to meet the need. First, stress environments are implicitly modeled by quantifying the resource availability of the system through sensors. Second, a mathematical programming model is built with the resource availability incorporated and with the stability in system behavior assured. Third, a multi-tier auction market is designed to solve the programming model by distributing computation and communication overheads. By periodically opening the auction market, the system can achieve desirable performance adaptively to changing stress environment while assuring stability and scalability properties. The control mechanism devised in this paper contributes to the efforts of managing the ever-increasing complexity of modern software systems.