By Topic

On adaptive communication in asynchronous real-time distributed systems

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

2 Author(s)
B. Ravindran ; Bradley Dept. of Electr. & Comput. Eng., Virginia Tech. Univ., Blacksburg, VA, USA ; B. Zhang

Presents adaptive communication heuristic algorithms for periodic tasks in asynchronous real-time distributed systems. The heuristic algorithms adapt the application to workload changes through trans-node message-level adaptation mechanisms. We present adaptive communication heuristics for IEEE 802.5 token ring networks that support the priority-driven protocol, and for FDDI networks that use the timed token protocol. The heuristic algorithms adapt periodic computations of the application to workload changes by re-prioritizing application messages and by dynamically changing token holding times at processor nodes, respectively. The objective of the heuristics is to minimize (end-to-end) missed deadline ratios of the tasks. We study the performance of the techniques through a combination of benchmarking and simulation. The performance of the heuristics is compared with an adaptive resource management algorithm that performs adaptation by dynamically replicating application processes for load sharing. The experimental results indicate that the adaptive communication strategies outperform the process replication algorithm for load patterns that cause communication latencies to grow faster than execution latencies. Moreover, we also observe that the adaptive communication algorithms perform as good as the process replication algorithm for load patterns that cause execution latencies to grow faster than communication latencies.

Published in:

Engineering of Computer Based Systems, 2001. ECBS 2001. Proceedings. Eighth Annual IEEE International Conference and Workshop on the

Date of Conference: