Thesis
Achieving end-to-end delay bounds in a real-time status dissemination network
Washington State University
Master of Science (MS), Washington State University
2007
Handle:
https://hdl.handle.net/2376/103534
Abstract
Status dissemination networks are used in many critical infrastructures. Most notably they can be found ill electric utilities, oil alld gas distribution systems, and water distribution systems. The GridStat project is a status dissemination middleware framework that is being developed for the electric power grid. GridStat is an event-based application framework built on a publisher-subscriber paradigm. It has admission control for new traffic flows and uses a multicast routing protocol in the routers. When the traffic travels solely over a dedicated network, GridStat will provide the following Quality of Service (QoS) properties: reliability and real-time performance. This thesis focuses on providing real-time perforlnance, sometimes referred to as timeliness, for GridStat on a dedicated network. An analysis of current methods in bounding end-to-end packet delay based on various Guaranteed Rate (GR) scheduling algorithms is performed, witll the Delay Earliest Due Date (Delay-EDD) algorithm being proposed as the most appropriate one to be used in this case. GR scheduling algorithms can give a deadline, or delay guarantee, by which a packet of a flow will be transmitted. GR scheduling algoritllms also provide a delay guarantee for a flow that is independent of the behavior of other flows in the network. The result of using dedicated network links, admission control, resource reservation, and a guaranteed rate scheduling algorithm in the routers of a status dissemination network, is the ability to provide deterministic guarantees on end-to-end packet delay. Real-time performance for the GridStat framework is thereby achieved.
Metrics
7 Record Views
Details
- Title
- Achieving end-to-end delay bounds in a real-time status dissemination network
- Creators
- Joel Norman Helkey
- Contributors
- Carl H. Hauser (Degree Supervisor)
- Awarding Institution
- Washington State University
- Academic Unit
- Electrical Engineering and Computer Science, School of
- Theses and Dissertations
- Master of Science (MS), Washington State University
- Publisher
- Washington State University; [Pullman, Washington] :
- Identifiers
- 99900525076101842
- Language
- English
- Resource Type
- Thesis