Providing ultra‐short latency to user‐centric 5G applications at the mobile network edge

Abstract

Mobile Edge Computing (MEC) will play a key role in next-generation mobile networks to extend the range of supported delay-sensitive applications. Furthermore, an increasing attention is paid to provide user-centric services, to better address the strict requirements of novel immersive applications. In this scenario, MEC solutions need to efficiently cope with user mobility, which requires fast relocation of service instances to guarantee the desired Quality of Experience. However, service migration is still an open issue, especially for resource-constrained edge nodes interconnected by high-latency and low-bandwidth links. In this paper, by leveraging the potential of lightweight container-based virtualization techniques, we investigate a novel approach to support service provisioning in dynamic MEC environments. In particular, we present a framework where proactive service replication for stateless applications is exploited to drastically reduce the time of service migration between different cloudlets and to meet the latency requirements. The performance evaluation shows promising results of our approach with respect to classic reactive service migration. INTRODUCTIONSeveral classes of new applications are challenging the current network and cloud infrastructures. As illustrated in a recent report from International Telecommunication Union, 1 applications such as tactile internet, mobile gaming, and augmented reality are pushing new requirements, especially in terms of latency. To guarantee the desired Quality of Experience (QoE) for the end user, not only the network access delay, but also the cloud service processing should be performed within a few milliseconds. To achieve the 1 ms latency dream for the next-generation 5G cloud-enabled services, both network and cloud providers should jointly cooperate and investigate novel approaches. In this regard, academic and industrial research communities have focused on Mobile Edge Computing (MEC) solutions to exploit processing and storage capabilities at the edge of the network, as near as possible to the end user. 2,3 Indeed, the deployment of micro datacentres in the network access points, known as cloudlets, 4,5 can guarantee remarkable benefits of low latency interaction and scalability, by balancing the workload over the distributed edge infrastructure. Furthermore, bringing the cloudlet concept into the Internet of Things (IoT) scenario results in the definition of the so-called Fog Computing paradigm, which envisages a highly virtualized infrastructure composed of distributed edge nodes to monitor and analyse the most time-sensitive data generated by network connected devices. [6][7][8] In a MEC environment, a key challenge is represented by the user mobility, which could cause significant application degradation, even in small scenarios, as reported in a previous study.9,10 To guarantee service continuity and to meet the strict requirements of application latency, the MEC framework needs to properly cope with service migration between edge nodes. I...

Enhancing IoT security through network softwarization and virtual security appliances

“…A broad range of IoT‐based applications, such as autonomous cars, industrial automation systems, and Tactile Internet, present demanding requirements in terms of tolerable latency and traffic generation. To face these challenges, the multiaccess edge computing paradigm is gaining high momentum, boosting increased processing and storage capabilities towards the network edge …”

Balancing QoS and power consumption in programmable 5G infrastructures

“…To better illustrate the potential trade‐off between QoS and energy efficiency let us consider the following pure infrastructure‐as‐a‐service (IaaS) scenario. Reliability and high availability often require to deploy additional software instances of an application, which are used in case of sudden peaks of requests, failure of the primary components, and movement of users to a different location . Provisioning such instances in real time is not currently possible (though unikernel technologies leave this possibility open for the future) because of technical and administrative issues.…”

Enabling green computing in cloud environments: Network virtualization approach toward 5G support

“…Virtualization is the central technology behind 5G support and success of cloud computing paradigm for resource sharing to meet rising level of resource demand in daily resource request patterns and facilitating ultra‐short latency . Cloud computing helps to reduce carbon footprint of data centers and saves operating cost by improving resource utilization of data centers using virtualization technologies.…”