2020
DOI: 10.1109/access.2020.2975004
|View full text |Cite
|
Sign up to set email alerts
|

A Survey of Online Data-Driven Proactive 5G Network Optimisation Using Machine Learning

Abstract: In the fifth-generation (5G) mobile networks, proactive network optimisation plays an important role in meeting the exponential traffic growth, more stringent service requirements, and to reduce capital and operational expenditure. Proactive network optimisation is widely acknowledged as one of the most promising ways to transform the 5G network based on big data analysis and cloud-fog-edge computing, but there are many challenges. Proactive algorithms will require accurate forecasting of highly contextualised… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1

Citation Types

0
44
0

Year Published

2020
2020
2024
2024

Publication Types

Select...
5
4

Relationship

1
8

Authors

Journals

citations
Cited by 75 publications
(44 citation statements)
references
References 173 publications
(230 reference statements)
0
44
0
Order By: Relevance
“…Data-driven proactive management will be essentially supported by ML/AI techniques. These techniques, once deployed in future networked systems, should offer a new range of networking-based services such as smart routing in networks with a cross-layer design [59], task offloading and resource allocation [60], optimized operation of next-generation mobile networks [61], distributed storage and computation at the network edge [62], and accurate localization estimation of mobile robots [63]. In parallel with this expected network evolution, novel challenges such as privacy, e.g.…”
Section: Data-triggered Management Mechanismmentioning
confidence: 99%
“…Data-driven proactive management will be essentially supported by ML/AI techniques. These techniques, once deployed in future networked systems, should offer a new range of networking-based services such as smart routing in networks with a cross-layer design [59], task offloading and resource allocation [60], optimized operation of next-generation mobile networks [61], distributed storage and computation at the network edge [62], and accurate localization estimation of mobile robots [63]. In parallel with this expected network evolution, novel challenges such as privacy, e.g.…”
Section: Data-triggered Management Mechanismmentioning
confidence: 99%
“…With the explosive growth of communication traffic and the arrival of the fifth generation (5G) of mobile broadband systems, traffic and mobility prediction are needed for an effective planning and usage of network resources [1], [2]. In this context, deep learning could be properly tailored to anticipate traffic behaviors and optimize the deployment of virtual resources and functionalities very close to end-users (i.e., at the edge of the network), while offering concrete answers to the deployment of flexible and advanced applications asking for bandwidth, computing, latency, and memory capabilities never seen before [3], [4].…”
Section: Introductionmentioning
confidence: 99%
“…Genetic algorithm, Mean-field games, Markov Decision Processes, reinforcement learning...etc.). As the scale of the complexity increases, neural networks (NN) [1]- [4] have been proposed to automate and accelerate the mapping between inputs (e.g. CSI, user demand) and output solutions (e.g.…”
Section: Introductionmentioning
confidence: 99%