In 4G networks, the emergence of machine communications such as connected vehicles increases the high demand of uplink transmissions, thus, degrading the quality of service per user equipment. Enforcing quality-of-service in such cellular network is challenging, as radio phenomenon, as well as user (and their devices) mobility and dynamics, are uncontrolled. To solve this issue, estimating what the quality of transmissions will be in a short future for a connected user is essential. For that purpose, we argue that radio metrics are key features whose evolutions can help predicting the bandwidth that the considered connections can take advantage of in the following hundreds of milliseconds. The paper then describes how a 4G testbed has been deployed in order to study the correlation between radio noise and throughput in uplink transmissions. Based on radio measurements, the main supervised machine learning algorithms are used, such as Random Forest and Support Vector Machine to predict the uplink received bandwidth. For a specific user service, we are able to predict the end-to-end received bandwidth, i.e. the amount of received data on the server side during a specific period at a very low scale of 100 ms. Results also prove that uplink bandwidth predictions are less accurate compared to bandwidth prediction for downlink based on radio measurements.

In cellular networks, the emergence of machine communications such as connected vehicles increases the high demand of uplink transmissions, thus, degrading the quality of service per user equipment. Enforcing quality-of-service in such cellular network is challenging, as radio phenomena, as well as user (and their devices) mobility and dynamics, are uncontrolled. To solve this issue, estimating what the quality of transmissions will be in a short future for a connected user is essential. For that purpose, we argue that lower layer metrics are a key feature whose evolution can help predict the bandwidth that the considered connections can take advantage of in the following hundreds of milliseconds. The paper then describes how a 4G testbed has been deployed in order to investigate throughput prediction in uplink transmissions at a small time granularity of 100 ms. Based on lower layer metrics (physical and mac layers), the main supervised machine learning algorithms are used, such as Linear Regressor and Random Forest to predict the uplink received bandwidth in different radio phenomena environment. Hence, a deep investigation of the impact of radio issues on bandwidth prediction is conducted. Further, our evaluation shows that the prediction is highly accurate: at the time granularity of 100 ms, the average prediction error is in the range of 6% to 12% for all the scenarios we explored.

The proliferation of sophisticated applications and services comes with diverse performance requirements. The 5G cellular network is advocated to support this diversity through an end-to-end network slicing. Even though the slicing is not a novel concept, its implementation in the RAN still remains challenging. In this article, we aim to enforce the real time 5G slicing from radio resources perspective in a multi-cell system. For that, two exact optimization models are proposed. Due to their high convergence time, three heuristics are developed and evaluated with the optimal models. Results are promising, as two heuristics are highly enforcing the real time RAN slicing.