Real Time Scheduling Theory: A Historical Perspective
Real-Time Systems
RETINA: REal-TIme Network Analyzer
IPDPS '05 Proceedings of the 19th IEEE International Parallel and Distributed Processing Symposium (IPDPS'05) - Workshop 2 - Volume 03
Modeling real-time wormhole networks by queuing theory
ISPA'05 Proceedings of the Third international conference on Parallel and Distributed Processing and Applications
Cross-layer analysis of the end-to-end delay distribution in wireless sensor networks
IEEE/ACM Transactions on Networking (TON)
Bandwidth allocation under end-to-end percentile delay bounds
International Journal of Network Management
| Hi-index | 0.00 |
This paper presents an application of real-time queuing network theory to a particular network which models a video-on-demand server.Packets from eachstream have stochastic arrival patterns, computationtimes and end-to-end delay requirements.We deriveclosed form solutions for the deadline miss rate of thepackets.This methodology can be used to design admission control policies that provide statistical quality ofservice guarantees.By considering the actual requirements rather than worst-case requirements, therealtime queuing network approach significantly increasesthe server utilization.This paper illustrates how realtime queuing network theory c an be used to accuratelypredict the behavior of real-time systems in heavy trafficconditions.It shows how one can calculate the fractionof tasks that will miss their end-to-end deadlines.Itpresents new results on product form equilibrium distributions for multi-dimensional reflected Brownianmotion processes when nodes are scheduled using EDF.Lastly, it presents simulation results to illustrate theexcellent accuracy of the real-time queuing network approach and how the methodology can be used to provide statistical QoS guarantees.