Towards an Optimal Management of the 5G Cloud-RAN through a Spatio-Temporal Prediction of Users’ Dynamics

Abstract

In the emerging 5G architecture, the Cloud-Radio Access Network (Cloud-RAN) offers the possibility to dynamically configure virtual resources and network functionalities very close to end-users, while jointly considering bandwidth, computing, latency, and memory capabilities requested by heterogeneous applications, the channel quality experienced by end-users, mobility, and any kind of system constraints. By capitalizing on recent scientific results and standardization activities on 5G, this short paper presents a preliminary design of an ETSI-NFV compliant architecture willing to support the implementation of advanced protocols, algorithms, and methodologies for the optimal management of the 5G Cloud-RAN. Its components and functionalities have been sketched by harmoniously integrating Software-Defined Networking (SDN) facilities, Multi-access Edge Computing (MEC), and deep learning. Herein, spatio-temporal users' dynamics are collected by SDN controllers and predicted by a high-level orchestrator through a Convolutional Long Short-Term Memory scheme. Then, the outcomes of the prediction process are adopted to dynamically configure the Cloud-RAN (i.e., by using any kind of customizable algorithm). Some of the capabilities of the proposed approach are preliminarily evaluated by considering the autonomous driving use case and real mobility traces. Moreover, the paper concludes by reporting an overview of future directions of this research activity.

Anticipatory Allocation of Communication and Computational Resources at the Edge Using Spatio-Temporal Dynamics of Mobile Users

“…To bridge this gap, this work formulates an innovative methodology for the anticipatory allocation of communication and computational resources at the network edge (i.e., task offloading), based on the knowledge of spatio-temporal dynamics of mobile users. The conceived approach significantly extends the very preliminary contributions presented, by the same authors of this work, in [48] and [49]. The considered architecture adopts a Software-Defined Networking (SDN) approach to monitor users' mobility over time.…”

“…Here, gNBs are part of the 3GPP network integrated within the ETSI-MEC architecture. They provide wireless connectivity to mobile users through heterogeneous technical components at the radio interface [48], [61]. It is important to remark that gNBs can be connected to each other in different ways.…”

“…At the end, there is a fully-connected layer with the Rectified Linear Unit (ReLU) activation function [38] to predict the expected distribution of users, after the observation window T , for a specific look-ahead temporal horizon N . The predictor is configured in order to minimize the Mean Square Error (MSE) loss function, which minimizes the difference between the ground truth and the predicted distribution of users [48], [65]. The Adam optimization [67], with a learning rate equal to 0.001, is used to iteratively update the network weights.…”

“…The considered architecture adopts a Software-Defined Networking (SDN) approach to monitor users' mobility over time. Then, starting from the outcomes of the preliminary contributions presented by the same authors in [48] and [49], it exploits a deep learning architecture based on Convolutional Long Short-Term Memory (ConvLSTM) [50] for predicting the distribution of users among cells and their related service demands over a look-ahead temporal horizon. A centralized Multi-access Edge Orchestrator uses this information to anticipatorily distribute users' demands among available MEC servers, while satisfying communication and computational constraints at the network edge and the upper bound for latency expected by mobile users.…”

Toward Programmability of Radio Resource Control Based on O-RAN

“…The DataInactivity timer indicates how long the UE context and established radio bearers must be stored during UE inactivity. Typically, the DataInactivity timer is statically configured in the RAN slider with value between few seconds to a few tens of seconds [16]. With the deployment of O-RAN, this timer may be dynamically controlled in case of e. g. emergency situations.…”