Redundant Servicing of a Flow of Heterogeneous Requests Critical to the Total Waiting Time During the Multi-path Passage of a Sequence of Info-Communication Nodes

Abstract

The possibilities are investigated and analytical models of redundant multiway servicing of a heterogeneous request flow with their replication rate depending on the maximum permissible waiting time for replicas accumulated in the queues of nodes that make up the path for real-time information and communication systems are proposed. Two options are considered for redundant servicing of a heterogeneous flow during the sequential passage of copies of requests through parallel-connected nodes grouped in groups. For the first option, when generating a request, a certain number of copies are created, for each of which a path is predefined as a sequence of nodes of different groups involved in servicing this copy. For the second option, the paths are formed dynamically at each stage, and a copy of the request, executed first at some stage of the sequential passage of groups of redundant nodes, is transferred for redundant service to the next group of nodes. At various stages of service, the redundancy ratio can vary.