The many faces of publish/subscribe
ACM Computing Surveys (CSUR)
Issues in Analyzing the Behavior of Event Dispatching Systems
IWSSD '00 Proceedings of the 10th International Workshop on Software Specification and Design
On the modelling of publish/subscribe communication systems: Research Articles
Concurrency and Computation: Practice & Experience - Foundations of Middleware Technologies
Distributed Event-Based Systems
Distributed Event-Based Systems
Modeling the communication costs of content-based routing: the case of subscription forwarding
Proceedings of the 2007 inaugural international conference on Distributed event-based systems
Adaptive routing in publish/subscribe systems using hybrid routing algorithms
Proceedings of the 7th workshop on Reflective and adaptive middleware
Adaptive content-based routing in general overlay topologies
Proceedings of the 9th ACM/IFIP/USENIX International Conference on Middleware
Self-optimizing Hybrid Routing in Publish/Subscribe Systems
DSOM '09 Proceedings of the 20th IFIP/IEEE International Workshop on Distributed Systems: Operations and Management: Integrated Management of Systems, Services, Processes and People in IT
Proceedings of the 7th international conference on Autonomic computing
Hi-index | 0.00 |
Publish/subscribe systems are used increasingly often as a communication mechanism in loosely-coupled distributed systems. Their field of application is widespread ranging from communication platforms for real-time enterprises to Internet scale information dissemination systems. The performance of publish/subscribe systems plays an essential role for their acceptance. Especially, in mission-critical and financial areas, the system should guarantee certain predefined performance metrics such as throughput and latency. On the other hand, operators want to run publish/subscribe systems as efficiently as possible to reduce their operating costs. These requirements lead to the necessity to develop strategies for planning and managing publish/subscribe systems. In my PhD project I will introduce such strategies which target the complete life cycle of publish/subscribe systems including the design, the operation and the redesign phase. I will show how an optimized infrastructure meeting predefined requirements can be determined before the system is deployed and how this approach can be used for a redesign. This allows designers to decide about the required size and capabilities of the infrastructure they have to set up. Furthermore, I will investigate how the publish/subscribe system can continuously be optimized at runtime using a new kind of adaptive routing scheme. This way, the system will autonomously provide the best quality of service possible in dynamically changing environments and reduces management costs.