DISTRIBUTED ARTIFICIAL INTELLIGENCE MODELS IN PERSPECTIVE COMMUNICATION NETWORKS

Abstract

6G technology will create an intelligent, highly scalable, dynamic and programmable wireless network capable of serving a variety of heterogeneous wireless devices. Various 6G modules and devices will generate colossal amounts of distributed data, so post-NGN (New Generation Networks) will need to implement a number of machine learning methods that will solve significantly complicated network problems. To overcome these problems, distributed learning methods can be used, allowing devices to train models jointly, without exchanging raw data, which reduces communication costs, delays, and increases data privacy level as well. Distributed machine learning models will play an important role in 6G networks, since they have a number of advantages over centralized methods, however, the implementation of distributed algorithms in resource-constrained wireless environments can be challenging. It is important to take into account the wireless environment uncertainty associated with various disturbing factors and limited wireless (transmission power, radio frequency spectrum) and hardware resources (computing power). Consequently, it is important to choose the suitable machine learning algorithm based on the wireless environment characteristics and the resource requirements of the learning process. The article reviews the application of distributed artificial intelligence models in new generation communication networks for resource management and data processing purposes. The general algorithms and approaches of distributed machine learning, applications, methods and models are described. The article analyzes the ways in which distributed artificial intelligence models can solve various problems in communication networks, including optimizing resource use and ensuring high performance and availability of network services.