Автоматическое построение отказоустойчивых бортовых сетей

Abstract

Fault tolerance is one of the key issues for on-board networks of autonomously operating vehicles. The number of devices in such networks is increasing; there is a need for methods for automating the design of networks, taking into account the required fault tolerance and technical limitations. Purpose: the purpose of the study is the implementation of methods and algorithms that contribute to the assessment of the fault tolerance of on-board networks, as well as the automatic generation of network structures with the required fault tolerance. Methods: The obtained methods and algorithms are based on the elements of graph theory, in particular – estimation of connectivity and shortest path search. The graphs are compiled based on the structure of the onboard network using a number of proposed rules. Structural redundancy is considered as a method of ensuring fault tolerance. The developed method provides reasonable addition of the network elements, in contrast to the often used copying of the network structure. The method consists of two stages: the new network structure is generated according to the required fault tolerance, and then iteratively refines the network structure in order to reduce hardware costs. Results: the use of the developed method simplifies and speeds up the design of on-board networks, since a formalized assessment of such a network is carried out at the design stage, before its actual assembly. The process of achieving of the required fault tolerance for large network structures takes less than a minute. Practical relevance: the presented method is implemented within the framework of the computer-aided system for design and modeling of onboard networks, a longterm approbation was carried out as part of real projects for the development of onboard networks of spacecraft. Discussion: there are no analogues of such a software implementation for on-board networks. The solutions obtained using the method in practice proved to be close to optimal; the research results have positive feedback from specialists.