Context-Based Intelligent Scheduling and Knowledge Push Algorithms for AR-Assist Communication Network Maintenance

Abstract

Maintenance is an important aspect in the lifecycle of communication network devices. Prevalent problems in the maintenance of communication networks include inconvenient data carrying and sub-optimal scheduling of work orders, which significantly restrict the efficiency of maintenance work. Moreover, most maintenance systems are still based on cloud architectures that slow down data transfer. With a focus on the completion time, quality, and load balancing of maintenance work, we propose in this paper a learning-based virus evolutionary genetic algorithm with multiple quality-of-service (QoS) constraints to implement intelligent scheduling in an edge network. The algorithm maintains the diversity of the population and improves the speed of convergence using a fitness function and a learning-based population generation mechanism. The test results demonstrate that the algorithm delivers good performance in terms of load balancing and QoS guarantee. We also propose a knowledge push algorithm based on a context model for intelligently pushing relevant knowledge according to the given conditions. The simulation results demonstrate that our scheme can improve the efficiency of on-site maintenance.