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-ofservice (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.

Summary The development of the Internet of Things (IoT) and wearable technology provides an opportunity for the development of maintenance of communication. The use of wearable technology and instant messaging technology of IoT can improve the support capabilities and data interaction ability of on‐site maintenance of the communication network. Existing communication maintenance systems lack real‐time operation and maintenance of data interaction. In the field operation decision‐making and execution process, there are problems of lack of field links and inconvenient information interaction. On‐site maintenance mainly relies on maintenance personnel to actively search for information, and the retrieval results are lacking of personalization, which makes it difficult to meet the needs of on‐site maintenance of the communication network. Edge computing and information push technology can solve these problems to some extent. In this paper, we focus on the current low level in information, complicated scenes, and various information of on‐site maintenance and propose a dynamic context‐aware information push algorithm. The simulation results demonstrate that the algorithm delivers good performance in terms of precision, recall, and F1. Besides, we present a smart wearable maintenance system, an edge computing–assisted IoT platform for the real‐time guidance of technical experts and systems for on‐site maintenance personnel, aiming to improve the efficiency and quality of on‐site maintenance.

No abstract