مقالة

AI-Driven Self-Organizing Networks (SON) for 5G OPEX Reduction: A Comprehensive Survey and Conceptual Framework

This paper investigates the application of Artificial Intelligence (AI) in Self-Organizing Networks (SON) for 5G networks, focusing on coverage enhancement and reduction of Operational Expenditures (OPEX). A conceptual AI-Self Organizing Networks (SON) framework integrated with O RAN architecture is proposed, and an illustrative Python-based simulation is conducted to demonstrate potential trends in coverage probability, energy consumption, and estimated OPEX savings. The simulation results indicate that AI-SON can achieve near-optimal coverage (coverage probability 0.9985) while reducing energy usage and maintenance costs, with an estimated OPEX reduction of 2030% compared to baseline strategies. The study clarifies that the simulation is illustrative and not experimentally validated, providing a foundation for future rigorous evaluations.

...
Mohamed Hankal
Electrical Engineering Department, Faculty of Engineering, Sana’a University, Sana’a, Yemen.
11651
NGMN Alliance, “5G White Paper”, February
11652
3GPP TR 22.864: "Feasibility Study on New
11653
Services and Markets Technology Enablers -
11654
Network Operation; Stage 1 (Release 15)",
11655
September 2016. 16
11656
“lteencyclopedia.” [Online]. Available:
11657
https://sites.google.com/site/lteencyclopedia/ho
11658
me [Accessed: 11-Apr-2022].
11659
D. Warren and C. Dewar, “Understanding 5G:
11660
Perspective on Future Technological
11661
Advancements in Mobile,” GSMA Intell., Dec.
11662
A. Imran, M. A. Imran, A. Abu-Dayya, and R.
11663
Tafazolli, “Self Organization of Tilts in Relay
11664
Enhanced Networks: A Distributed Solution,”
11665
IEEE Trans. Wirel. Commun., vol. 13, no. 2, pp.
11666
–779, Feb. 2014.
11667
Ajay R. Mishra “Fundamentals of Network
11668
Planning and Optimisation 2G/3G/4G: Evolution
11669
to 5G”, (2018).
11670
Saad Z. Asif “5G Mobile Communications
11671
Concepts and Technologies”. (2018).
11672
Mobile Network Services. [Online]. Available:
11673
https://getsolupro.com/businessareas/telecommunicationsengineering/services/m
11674
obile-networks-services/ [Accessed: 15-May2022].
11675
K. Horn et al., 'Reinforcement Learning for RAN
11676
Optimization', IEEE Communications Surveys,
11677
Appendices
11678
Appendix A: Simulation Code (Summary)
11679
The simulation used to generate the
11680
illustrative plots is a synthetic Python model.
11681
Key steps: 1. Define user density range (10-200
11682
users/km^2). 2. Model coverage probability
11683
baseline as logistic decline with density. 3.
11684
Model AI-SON improvements by shifting
11685
logistic parameters and adding small gains. 4.
11686
Plot and export figures for inclusion. A
11687
production-grade simulation would replace
11688
synthetic models with stochastic geometry,
11689
path-loss maps, and packet-level simulators
11690
such as ns-3 with 5G m
##plugins.themes.bootstrap3.displayStats.noStats##

المقاييس

0
المشاهدات
0
التنزيلات
0
الاقتباسات

كيفية الاقتباس

AI-Driven Self-Organizing Networks (SON) for 5G OPEX Reduction: A Comprehensive Survey and Conceptual Framework. (2026). مجلة جامعة صنعاء للعلوم التطبيقية والتكنولوجيا, 4(1), 1496-1506. https://doi.org/10.59628/jast.v4i1.2291

المؤلفات المشابهة

يمكنك أيضاً إبدأ بحثاً متقدماً عن المشابهات لهذا المؤلَّف.

الأعمال الأكثر قراءة لنفس المؤلف/المؤلفين