Intelligent Media Forensics and Traffic Handling Scheme in 5G Edge Networks

Abstract

The 5th generation (5G) communications evolved with heterogeneous user terminals and applications. A convergence of Mobile Edge Computing (MEC) and Software-Defined Networks (SDN) delivers gigantic challenges and opportunities for enhancing computing resources and user Quality of Service (QoS) in fronthaul and backhaul networks. Due to the precipitous expansion of user media in the 5G epoch, efficient media forensics methods are mandatory for specifying and offering effective safety handling based on individual application requirements. According to the exponential increment of Heterogeneous Internet of Things (HetIoT) devices, gigantic traffic will generate through bottleneck 5G fronthaul gateways. 5G fronthaul network environments consist of inadequate resources to surmount the enormous user traffic and communications, QoS will be reduced when the existence of traffic congestion occurs. To confront the aforementioned issues, this paper proposed intelligent media forensics and traffic handling scheme for controlling the Uplink (UL) transmission according to the Downlink (DL) statuses. Support Vector Machine (SVM) algorithm was applied to conduct the media forensics and MEC server integrated into fronthaul gateways, in which gateways resources are divided into UL and DL. Caching technology will be a part of 5G environments, and DL will be utilized for traffic caching. So, it is compulsory to adjust the communication traffic according to UL/DL resource utilization and control the forwarding traffic which relies on resource availability. The experiment was conducted by using computer software, and the proposed scheme illustrated a noteworthy outperformance over the conventional method in terms of diverse significant QoS factors including reliability, latency, and communication throughput.

Intelligent Offloading Decision and Resource Allocations Schemes Based on RNN/DQN for Reliability Assurance in Software-Defined Massive Machine-Type Communications

“…e DRL effectively handles offloading decisions and resource allocation (RA) in massive NS [24][25][26][27]. erefore, the resource constraint of edge components (e.g., base station, network device, etc.)…”

Challenges of Network Forensic Investigation in Fog and Edge Computing

“…In contrast, ref. [36] considers forensics in edge networks with a focus on media transmission over 5G; similarly, ref. [37] considers them for smart homes.…”

A differential privacy‐preserving deep learning caching framework for heterogeneous communication network systems

“…NSP places these videos on small cell base stations, and it can effectively reduce repeated video transmission through its backhaul channel. Math et al 41 used deep learning for traffic caching, adjusted communication traffic according to resource utilization, and controlled forwarding traffic depending on resource availability. Zhang et al 42 constructed a novel MEGA architecture to solve the problem of insufficient cache storage space, serving delay‐sensitive real‐time video streaming in heterogeneous wireless networks that support the edge.…”