AI-Enabled Radio Resource Allocation in 5G for URLLC and eMBB Users

Energy Efficient Communication and Computation Resource Slicing for eMBB and URLLC Coexistence in 5G and Beyond

“…From (33), it is sure that the second order derivative of the objective function A(l) is positive semi-definite. Therefore, we can conclude that the the objective function in (30) is convex. Moreover, the constraints (C1)-(C3) are linear constraints.…”

“…They leveraged the Deep Reinforcement Learning (DRL) to find the number of punctured mini-slots from all eMBB users. Then, [29] proposed the use cases of the URLLC traffic in the 5G new radio and the authors in [30] proposed the AIenabled radio resource slicing for eMBB and URLLC users.…”

“…The input data size of tasks of eMBB users and the required CPU cycles to execute one bit of input data are randomly generated between [0.1, 0.4] MB and [10,25] cycles, respectively. Then, the maximum tolerable latency to execute a computation task of each user is between [30,100] s. We set the maximum computation capacity of eMBB users between [0.1, 0.72] MHz and the maximum transmit power of each eMBB user as 100 mW. In this work, we consider a small scale fading model, and the back noise of the system is -174 dBm/Hz.…”

An Innovative Machine-Learning-Based Scheduling Solution for Improving Live UHD Video Streaming Quality in Highly Dynamic Network Environments

“…In terms of Radio Resource Management (RRM) and QoS provisioning, classical RRM functionalities would not be able to meet the stringent QoS requirements of all these immersive live streaming applications while also catering for the rest of application classes. In the context of 5G, ML is currently gaining considerable attention as it is seen as one of the key enablers for QoS provisioning [12], [18], [24]- [26] as well as for the development of intelligent services for smart cities [27]. An autonomous network resource management for QoS and QoE provisioning is proposed in [12] to predict the amount of network resources that needs to be allocated to cope with the traffic demands for live and on-demand dynamic adaptive streaming over HTTP.…”

“…However, these ML-based scheduling solutions are designed for homogeneous traffic types only. The ML framework proposed in [26] aims to optimize the resource and power allocation problem for heterogeneous traffic with the scope of improving the delay of Ultra-Reliable and Low-Latency Communications (URLLC) users and throughput of enhanced Mobile Broadband (eMBB) users. Compared to previous works, this paper proposes a ML-based scheduling and resource allocation solution to enable high level of QoS provisioning for mobile users experiencing UAV VR-based live video content while maintaining an acceptable service quality of other traffic types with diverse QoS requirements.…”