The Disruptions of 5G on Data-Driven Technologies and Applications

Abstract

With 5G on the verge of being adopted as the next mobile network, there is a need to analyze its impact on the landscape of computing and data management. In this paper, we analyze the impact of 5G on both traditional and emerging technologies and project our view on future research challenges and opportunities. With a predicted increase of 10-100x in bandwidth and 5-10x decrease in latency, 5G is expected to be the main enabler for smart cities, smart IoT and efficient healthcare, where machine learning is conducted at the edge. In this context, we investigate how 5G can help the development of federated learning. Network slicing, another key feature of 5G, allows running multiple isolated networks on the same physical infrastructure. However, security remains the main concern in the context of virtualization, multitenancy and high device density. Formal verification of 5G networks can be applied to detect security issues in massive virtualized environments. In summary, 5G will make the world even more densely and closely connected. What we have experienced in 4G connectivity will pale in comparison to the vast amounts of possibilities engendered by 5G.

Horizontal Review on Video Surveillance for Smart Cities: Edge Devices, Applications, Datasets, and Future Trends

“…Scientists are expecting that 5G will easier life more than before with higher bandwidth and lower latency. According to Loghin et al [ 148 ] 5G is considered to be the key enabler for smart cities, smart IoT, and effective healthcare. They looked at how 5G could aid the advancement of federated learning in this context.…”

From 5G to 6G Technology: Meets Energy, Internet-of-Things and Machine Learning: A Survey

“…Two papers [171,172] proposed a resource allocation for Industry 4.0 based on softwaredefined networking and network function virtualization technologies, machine learning tools, and the slicing paradigm, in which each slice of the network is dedicated to a category of services with similar QoS requirements.…”

Dynamic Network-Assisted D2D-Aided Coded Distributed Learning

“…While training data privacy has received considerable attention in general, the degree of information leakage over a D2D link remains largely unexplored. D2D communications are considered in the survey [21] and multiple related works as a potential mechanism for leveraging user proximity to accelerate FL. Direct communications allow mitigating the impact of stragglers in FL by balancing computations between overloaded users and their more capable neighbors.…”

“…Another approach to balance the computational load and, thus, accelerate training and inference is in computation offloading from the potential stragglers to more capable proximate users [21]. While this can be achieved through device-to-device (D2D) connectivity, especially in highly heterogeneous systems with dense connectivity [19], straightforward methods of processing offloaded information may violate data privacy from the perspective of the offloading users [15].…”