A Survey on Mobile Edge Computing Infrastructure: Design, Resource Management, and Optimization Approaches

Abstract

Emerging 5G cellular networks are expected to face a dramatic increase in the volume of mobile traffic and IoT user requests due to the massive growth in mobile devices and the emergence of new compute-intensive applications. Running high-intensive compute applications on resource-constrained mobile devices has recently become a major concern, given the constraints of finite computation and limited storage capacities. Mobile Edge Computing (MEC) has recently become the key technology to overcome these issues by providing cloud computing capabilities and placing IT infrastructures at the mobile network edge. In this survey, we present a list of relevant research papers for the MEC infrastructure implementation phases, including (1) MEC infrastructure designing and dimensioning, (2) MEC infrastructure virtualization using Network Function Virtualization (NFV) concept, and the use of virtualized service placement and auto-scaling methods to deploy an agile system framework, (3) MEC resource management frameworks, and (4) approaches used to optimize the MEC resources on the physical infrastructure. The main focus of this survey is to determine the required aspects to implement an auto-scaled and proactive MEC-NFV infrastructure to support a dynamic and heterogenous mobile users' demand at mobile network operators.INDEX TERMS Mobile edge computing, MEC infrastructure design and dimensioning, mobile network operator, optimization approaches, proactive, resource management, virtualization, NFV, VNF autoscaling, VNF placement.

Machine-Driven Design and Dimensioning of NFV-Enabled MEC Infrastructure to Support Heterogeneous Latency-Critical Applications

“…The objective function is to minimize the overall cost of deploying the MEC-NFV infrastructure at the mobile operator while ensuring that the SFC acceptance ratio and the latency requirements are withing the guaranteed thresholds. Based on eq (13), the total cost for such a system can be divided into three terms expressed as follows: (1) The installation cost of the physical resources placed in each MEC server m ∈ M that denotes the design and dimensioning cost, (2) the cost of assigning virtual resource 𝑟 ∈ 𝑅 to deploy for SFC 𝑓 ∈ F that consists of mapping VNFs 𝑣 ∈ 𝑉 𝑓 with different types 𝑡 ∈ 𝑇 to network nodes m ∈ M and the shareable instances' activation license fee that includes the cost of resources overhead already, and (3) the bandwidth cost of mapping path 𝜋 ∈ Π (𝑚,𝑚 ′ ) to a virtual link k(𝑣, 𝑣 ′ ) ∈ Κ 𝑓 , f ∈ F while ensuring that the total end-to-end (E2E) latency for all SFC requests received from the mobile users at different locations is under the guaranteed threshold.…”

“…The 5G era has witnessed tremendous growth in mobile subscriptions and mobile data traffic. Based on Ericsson's latest forecast for 2020-2026, global mobile subscriptions are expected to grow from 7.9 billion to 8.8 billion, and international mobile data traffic is expected to double [1]. Expansion of mobile network coverage drives to significant increase in *Correspondence: L.A. Haibeh, M.C.E Yagoub, and A. Jarray are with the School of Electrical and Computer Engineering, University of Ottawa, Ottawa, ON K1N 6N5, Canada (emails: labou068@uottawa.ca, myagoub@uottawa.ca, ajarray@uottawa.ca).…”

Integration of ICN and MEC in 5G and Beyond Networks: Mutual Benefits, Use Cases, Challenges, Standardization, and Future Research

“…In the MEC field, Mao et al [28] provided a survey on communication in MEC. Recently, Pham et al [3], Filali et al [29] and Haibeh et al [37] authored comprehensive surveys on MEC with a 5G perspective in 2020 but they does not focus on ICN integration with MEC. In [33], Grewe et al present a detailed futuristic vehicular scenario with ICN in combination with MEC.…”

Importance of Workload Prediction of Virtualized RAN in the Edge Micro Data Center

“…Fast computing is no longer a desirable aspect rather than mandatory functionalities for the next generation networks, especially in the edge. Through its increased performance, 5G can enhance edge computing applications by reducing latency, bettering application response times, and improving the ability of enterprises to collect and process data [3].…”