Page 75 - ITU Journal Future and evolving technologies – Volume 2 (2021), Issue 2

ITU Journal on Future and Evolving Technologies, Volume 2 (2021), Issue 2

A RESOURCE MANAGEMENT SURVEY FOR MISSION‑CRITICAL AND TIME‑CRITICAL
APPLICATIONS IN MULTIACCESS EDGE COMPUTING

1
Nina Santi and Nathalie Mitton 2
1 Inria, France, nina.santi@inria.fr, Inria, France, nathalie.mitton@inria.fr
2
NOTE: Corresponding author: Nina Santi, nina.santi@inria.fr

Abstract – Multiaccess Edge Computing (MEC) brings additional computing power in proximity of mobile users, reducing
latency, saving energy and alleviating the network’s bandwidth. This proximity is bene icial, especially for mission‑critical
applications where each second matters, such as disaster management or military operations. Moreover, it enables MEC
resources embedded on mobile units like drones or robots that are lexible to be deployed for mission‑critical applications.
However, the MEC servers are capacity‑limited and thus need an acute management of their resources. The mobile resources
also need a smart deployment scheme to deliver their services ef iciently. In this survey, we review mission‑critical applica‑
tions, resource allocation and deployment of mobile resources techniques in the context of the MEC. First, we introduce the
technical speci ics and uses of MEC in mission‑critical applications to highlight their needs and requirements. Then, we dis‑
cuss the resource allocation schemes for MEC and assess their it depending on the application needs. In the same fashion, we
inally review the deployment of MEC mobile resources. We believe this work could serve as a helping hand to design ef icient
MEC resource management schemes that respond to challenging environments such as mission‑critical applications.

Keywords – Disaster management, multiaccess computing, resource allocation, resource deployment, unmanned aerial
vehicles

1. INTRODUCTION edge of the network, i.e., next to users or things produ-
cing data [5]. This proximity provides advantages over
Mission‑critical applications require particular attention
the cloud, namely: i) latency reduction [5, 6, 7] ii) energy
as they may imply life or important assets losses, which
saving [5, 6], iii) augmented privacy [6, 7] and iv) location

entails entail tremendous consequences in their fai-

and context awareness [5, 6]. These its represent

lure. We can consider disaster management applica-

the key to carrying out the strong requirements of
tions, where time is a precious resource: the irst 72
real‑time applications. It is especially the case for
hours, the golden relief time, is particularly critical to
mission‑critical and time‑critical applications where time

locate and res‑ cue people [1]. Military applications

is an important resource [7]. Different edge computing

are also mission‑ critical as they defend citizens from

paradigms exist, each more or less speci ic. Fog
external threats and defend the country. IoT technology

computing and edge com‑ puting both bring cloud
combined with cloud computing has the potential to services to the edge of the net‑ work, hence can be

assist rescuers and agents to gain every precious second, confused [8]. However, edge com‑ puting focuses

by gathering information, analyzing the situation and
more on things while fog computing focuses on the

providing support services. It will also help agents overall infrastructure from the edge to the cloud [5, 8].

organize and coordinate their op‑ eration to handle the Cloudlets are “data center in a box” close to users and

situation [2]. Cloud computing retains many accessible by WiFi. They take example of WiFi access

advantages, like reduced costs [3] and is easily scalable point but with computing capacities to deliver cloud
[4]. However, cloud computing is constrained by its services close to users with little maintenance and low
remote location from end users, leading to high latency power [9]. However, they have been discarded be‑

and delays. This problem is increased by the heavy data cause of their WiFi access that implies limited coverage,
generation from IoT devices that burden the net‑ dif icult mobility support between cloudlets and security

work and possibly creating bottlenecks when tasks are concerns. Similar to cloudlets, micro‑data‑centers consist

not processed rapidly enough [5]. In addition, mission‑ of 10 servers or less and are placed next to users [10].

critical applications operate in challenging environments Finally, Mobile Edge Computing (MEC) is de ined by

with a damaged or scarce network, making the cloud dif‑ ETSI in 2015 as edge computing incorporated in Radio

icult to reach. Hence, cloud computing may not it all Access Networks (RANs) to serve mobile users [11] as

the mission‑critical applications’ challenges and require‑ shown in Figure 1. The term mobile edge computing has
ments. evolved to multiaccess computing [12], allowing

In recent years, a new trend has arisen, moving cloud heterogeneous Ra‑ dio Access Technologies (RATs), like

computing capacities to the edge of the network. This 5G, L TE, Wi‑Fi and so on, in the paradigm and so

paradigm is called edge computing where connected de‑ broadening its use cases. In this paper, we therefore

vices send their tasks to computing nodes located at the employ MEC as multiaccess edge computing as a generic
© International Telecommunication Union, 2021 61