Intelligent Handover Management in 5G Mobile Networks based on Recurrent Neural Networks
Bohdan Shubyn, Taras Maksymyuk · 2019
In modern mobile networks, we are seeing a huge leap in the uses of traffic by subscribers, so it is becoming increasingly difficult to ensure the proper operation of the network. In this paper, we propose to use an intelligent approach to network management, namely handover management. The main idea is to use neural networks, which, based on knowledge of user mobility, can predict ways of moving a group of subscribers between cells, which provide the maximum effectiveness of the implementation of the handover. From the results, we see that the neural network can predict traffic with an accuracy of more than 90%, and if you use the proper equipment and explore more durable traffic statistics, then this value can be significantly increased.