Efficiency of cluster schemes implementation for discrete dynamic programming for systems of support of dispatching technological processes in transport systems

Abstract

Abstract Within the framework of a computationally complex canonical scheduling problem, formulated by an optimization model for one-processor servicing of a finite deterministic flow of objects, a scheme of computational process of an algorithm of discrete dynamic programming in cluster implementation is considered. Variants of balancing of computational subtasks over network cluster array are investigated, purposed to reduce the volume and intensity of intranetwork interaction. It has been established that for practical improvement of efficiency of cluster algorithm, it is required not to increase the uniformity of distribution of subtasks among the cluster nodes, but to minimize the network traffic between the cluster nodes. Balancing options are proposed that allow to significantly increase localization of data in network computing. Experimental results are analytically confirmed, showing the scaling limits of implementation of discrete dynamic programming algorithms on a cluster architecture. The method for choosing the number of computational nodes and dimension of the problem being solved, which provide a threefold reduction in overhead costs for network exchange, is shown. The results obtained make it possible to objectively substantiate the choice of methodological and algorithmic approaches when choosing computer tools developing architectural and technological solutions for dispatching systems support in inland water transport.