Developing a New Simulation and Visualization Platform for Researching Aspects of Mobile Network Performance

Abstract

Nowadays, mobile networks represent one of the most innovative and challenging technological and research-oriented fields of work. The growth on user subscriptions and the advances introduced by Artificial Intelligence (AI) and Internet of Things (IoT), greatly enhanced the complexity and potential of communication networks. The increase on variety of devices and exchanged mobile data traffic resulted in demanding requirements for the network providers. As networks tend to scale and data to increase, some problems start to arise. Traffic congestion, packet loss and high latency being some examples. Therefore, it is important to introduce powerful tools and methods to tackle these challenges. On this perspective, several studies have highlighted AI systems, mainly Machine Learning (ML) algorithms, as the most promising methods, in the context of wireless networks, by improving the overall performance and efficiency. This work proposes to integrate several network optimization algorithms, already developed, in a common and unified visualization platform. These algorithms were developed in C# and Python and some of them use supervised and unsupervised ML techniques. The proposed solution includes multi-threading processes to deal with concurrent simulations, a proxy to communicate between platforms and a dynamic visual interface.