Abstract
The possibilities of increasing the likelihood of timely service and reducing the average waiting time for requests for inter-machine exchange in distributed real-time computer systems are investigated. The analyzed effect is achieved as a result of redundant multi-way transmissions of packets that are critical to delays, which provide for the replication of transmitted packets with the task for each replica of the path (route) of the sequential passage of network nodes. The condition for the timeliness of the reserved transmissions is that the accumulated waiting in the queues of the nodes making up the path, at least for one of the replicas, does not exceed the maximum permissible time. An analytical model is proposed for estimating the average delays of multi-path redundant transmissions, when determined by the average delivery time of the first of the replicas transmitted in different ways. For requests critical to service delays, the influence of the frequency of reservation (replication) of requests on the probability of their timely service and the average waiting time accumulated at the nodes of the path for the replica delivered first was analyzed.
Highlights
Great interest is shown in ensuring reliability and low latency in data exchange networks, these tasks are being addressed, including in the framework of the concept of Ultrareliable and Low-Latency Wireless Communication [1,2,3,4]
To reduce the negative impact of failures on the continuity of the computing process, reconfiguration is aimed at combining it with the migration of virtual machines [9,10] in cluster data processing systems [11,12] and multi-path routing in networks [13,14]
Similar problems must be solved in the modeloriented design of distributed computer systems [21,22,23], which function in real time, including distributed image processing and image streaming
Summary
To reduce the negative impact of failures on the continuity of the computing process, reconfiguration is aimed at combining it with the migration of virtual machines [9,10] in cluster data processing systems [11,12] and multi-path routing in networks [13,14]. Both of these technologies provide for the creation of reserve resources in order to quickly restore functioning during reconfiguration after failures. Similar problems must be solved in the modeloriented design of distributed computer systems [21,22,23], which function in real time, including distributed image processing and image streaming
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Proceedings of the 30th International Conference on Computer Graphics and Machine Vision (GraphiCon 2020). Part 2
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
