5G OPTIMIZATION: MATHEMATICAL MODELS, ALGORITHMS AND REALITY
DOI:
https://doi.org/10.18372/2310-5461.65.19931Keywords:
5G, network optimization, energy efficiency, resource management algorithms, mathematical models, bandwidthAbstract
The purpose of this article is to provide a comprehensive overview of modern methods for optimizing fifth-generation (5G) networks using mathematical models and algorithms. The article presents an in-depth analysis of approaches aimed at enhancing the performance of 5G networks, with a focus on minimizing latency, ensuring high energy efficiency, and improving spectral efficiency—key parameters for meeting the demands of modern mobile services and mission-critical applications. The discussion covers theoretical methods such as linear and nonlinear programming, stochastic modeling, machine learning algorithms, and robust optimization techniques, which play a crucial role in designing effective solutions for dynamic and resource-constrained 5G environments.
Despite significant progress made in recent years, numerous challenges remain before these technologies can be fully implemented in real-world commercial networks. One of the key issues is the gap between theoretical models, which often rely on simplifying assumptions, and the complex reality of mobile network operation, characterized by dynamic traffic patterns, unstable communication channels, and limited energy and computational resources, especially at the network edge. The article also addresses factors that limit the practical use of existing optimization algorithms, including high computational costs, data processing delays, and difficulties in scaling to large numbers of connected devices.
To address these challenges, the article discusses promising research directions, including the integration of artificial intelligence, mobile edge computin), self-organizing networks, and hybrid optimization methods that combine the strengths of different approaches to achieve greater flexibility and adaptability. In particular, the implementation of decentralized control systems is considered promising, as they allow real-time responses to changes in the network environment.
By gaining deeper insight into current challenges and technological opportunities, this article provides a valuable roadmap for future academic and applied research in 5G optimization. Continued exploration in the field of resource management—including efficient spectrum allocation, latency reduction, improved energy efficiency, and increased resilience to external influences—is critical for achieving stable, high-performance, and reliable operation of next-generation wireless networks, in line with the demands of the digital society and the evolution of Internet of Things, autonomous transport, and industrial automation technologies.
References
Avanci announces 5G Vehicle license agreement with Toyota. 2022. URL:https://www.businesswire.com/news/home/20241009928121/en/Avanci-announces-5G-Vehicle-license-agreement-with-Toyota. (access data 24/02/2025)
Harvesting energy for IoT devices using small droplets of liquid. 2020. URL:https://www.innovationnewsnetwork.com/harvesting-energy-for-iot-devices-using-small-droplets-of-liquid/3778/. (access data 24/02/2025)
P. Yu, F. Zhou, X. Zhang, X. Qiu, M. Kadoch. Deep Learning-Based Resource Allocation for 5G Broadband TV Service. IEEE Transactions on Broadcasting, Vol. 66, No. 4, pp. 800-813, 2020, DOI: 10.1109/TBC.2020.2968730
Ali Taleb Zadeh Kasgari, Walid Saad. Stochastic optimization and control framework for 5G network slicing with effective isolation. Journal of Network and Systems Management. 2018, Vol. 26, No. 4. P. 926-965. DOI:10.1109/CISS.2018.8362271
Kim, J., Park, S., & Lee, T. Analysis of Strategies for Minimising End-to-End Latency in 5GNetworks. International Conference on Broadband Communica-tions for Next Generation Networks and Multimedia Applications (CoBCom), Graz, Austria, 2022, pp. 1-6, DOI:10.1109/CoBCom55489.2022.9880722
I. P. Chochliouros, A.S. Spiliopoulou, P. Lazaridis. Dynamic Network Slicing: Challenges and Opportunities. 16th IFIP International Conference on Artificial Intelligence Applications and Innovations, Jun 2020, Neos Marmaras, Greece. pp.47-60, DOI:10.1007/978-3-030-49190-1_5hal-03677631
C. Zhang, Y. -L. Ueng, C. Studer. Artificial Intelligence for 5G and Beyond 5G: Implementations, Algorithms, and Optimizations. IEEE Journal on Emerg-ing and Selected Topics in Circuits and Systems, vol. 10, no. 2, pp. 149-163, 2020, DOI: 10.1109/ JETCAS.2020.3000103
Ahmed Elbanna. 5G Status Study - Challenges, standardization, network archi-tecture and planned net-work development. Diskussionsbeitrag Nо. 449, 2019, URL:https://www.wik.org/en/publications/ publication/no-449-5g-status-study-challenges-standardization-network-architecture-and-planned-net-work-development
Bosch bullish on industry 5G despite early reality check. 2024, URL:https://www.mobileworldlive.com/ industry/bosch-bullish-on-industry-5g-despite-early-reality-check/ (access data 24/02/2025)
Unlocking the Power of Artificial Intelligence in Manufacturing with Siemens Industrial Edge, 2025, URL:https://blog.siemens.com/2024/02/ unlocking-the-power-of-artificial-intelligence-in-manufacturing-with-siemens-industrial-edge/ (access data 24/02/2025)
How Edge Computing Supports Autonomous Vehicles. 2024, URL:https://www.controleng.com/how-ai-and-machine-learning-can-drive-sustainable-5g/ (access data 24/02/2025)
Foxconn Enhances Production Efficiency and Cuts Costs with Seuic's Scan-ning Solution. 2024, URL:https://www.linkedin.com/pulse/foxconn-enhances-production-efficiency-cuts-costs-seuics-scanning-yoy7c?trk=organization_guest_main-feed-card_feed-article-content (access da-ta 24/02/2025)
Intelligent network management in action. 2024, URL:https://www.ultihash.io/use-cases/intelligent-network-management-in-telecommunications (access data 24/02/2025)
Massive MIMO for 5G networks. 2022, URL:https://www.ericsson.com/en/reports-and-papers/white-papers/advanced-antenna-systems-for-5g-networks (access data 24/02/2025)
E. M. Migabo, The Future of Power Supply Design for Next Generation Net-works (5G and Beyond) Base Stations. Vanderbijlpark, South Africa, 2024, pp.383-389, DOI: 10.1109/IMITEC 60221.2024.10850977.
N. Correia, F. AL-Tam and J. Rodriguez, Adaptive Spectrum Allocation for 5G Wireless Communication Scenarios Pisa, Italy, 2020, pp. 1-6, DOI: 10.1109/CAMAD50429. 2020.9209267
T. Taleb, K. Samdanis, B. Mada, H. Flinck, On Multi-Access Edge Computing: A Survey of the Emerging 5G Network Edge Cloud Architecture and Orches-tration IEEE Communications Surveys & Tutorials, 2017, Vol. 19, Issue 3, P. 1657 – 1681, DOI:10.1109/COMST.2017.2705720.
B. Al Homssi, A. Al-Hourani, K. G. Chavez, S. Chandrasekharan. Energy-Efficient IoT for 5G: A Framework for Adaptive Power and Rate Control. ICSPCS, Cairns, QLD, Australia, 2018, pp. 1-6, DOI: 10.1109/ICSPCS.2018.8631733.
A. Abrol and R. K. Jha. Power Optimization in 5G Networks: A Step Towards GrEEn Communication, IEEE Access, Vol. 4, pp.1355-1374, 2016, DOI:10.1109/ ACCESS.2016.2549641.
A. Jain, P. Jain, A. Verma, L. Gopal and P. Chaudhary. AI-Driven Dynamic Network Slicing for Resource Optimization in 5G Networks: Implementation and Performance Evaluation. CYBERCOM, India, 2024, pp. 720-724, DOI: 10.1109/CYBERCOM63683.2024.10803129.
F. Tang, Y. Zhou and N. Kato. Deep Reinforcement Learning for Dynamic Uplink/Downlink Resource Allocation in High Mobility 5G HetNet. IEEE Journal on Selected Areas in Communications, Vol. 38, Nо. 12, pp. 2773-2782, 2020, DOI:10.1109/JSAC. 2020.3005495
S. Nimmala, R. Chilukuri, S. Janbhasha, P. Manasa, M. Mahendar. An Intelli-gent Bio-AI for Optimized Resource Allocation in 5G Networks. IDC IoT, Bengaluru, India, 2025, pp. 614-619, DOI:10.1109/ IDCIOT64235.2025.10914981
C. Souza, M. Falcao, A. Balieiro. Modelling and Analysis of 5G Networks Based on MEC-NFV for URLLC Services. IEEE Latin America Transactions, Vol. 19, No. 10, pp. 1745-1753, 2021, DOI: 10.1109/TLA.2021.9477275
A. Hairuman, A. Zahra, G. P. Kusuma. MEC Deployment with Distributed Cloud in 4G Network for 5G Success. Semarang, Indonesia, 2019, pp. 1-6, DOI:10.1109/ICITACEE.2019.8904270
Z. A. El Houda, B. Brik, A. Ksentini and L. Khoukhi. A MEC-Based Architec-ture to Secure IoT Applications using Federated Deep Learning. IEEE Internet of Things Magazine, Vol. 6, No. 1, pp. 60-63, 2023, DOI:10.1109/IOTM.001.2100238.
S. A. Bhat, I. B. Sofi and C. -Y. Chi. Edge Computing and Its Convergence With Blockchain in 5G and Beyond: Security, Challenges, and Opportunities. IEEE Access, Vol. 8, pp. 205340-205373, 2020, DOI:10.1109/ACCESS.2020.3037108.
Zoubeir Mlika. Network Slicing with MEC and Deep Reinforcement Learning for the Internet of Vehicles. 2022. DOI:10.48550/ arXiv.2201.11295
C. Zhang, Y. -L. Ueng, C. Studer and A. Burg. Artificial Intelligence for 5G and Beyond 5G: Implementations, Algorithms, and Optimizations. IEEE Jour-nal on Emerging and Selected Topics in Circuits and Systems, 2020, Vol. 10, No. 2, pp. 149-163, DOI:10.1109/JETCAS.2020.3000103.
Dileesh Chandra Bikkasani. AI-Driven 5G Network Optimization: A Compre-hensive Review of Resource Allocation, Traffic Management and Dynamic Network Slicing. American Journal of Artificial Intelligence, Vol. 8, Issue 2, 2024. DOI: 10.11648/j.ajai.20240802.14
G. Celli, E. Costamagna and A. Fanni. Genetic algorithms for telecommunica-tion network optimization. IEEE International Conference on Systems, Van-couver, Canada, 1995, Vol.2, pp. 1227-1232, DOI: 10.1109/ICSMC.1995.537939.
Seiamak Vahid, Rahim Tafazolli, Marcin Filo. Small Cells for 5G Mobile Networks. 2019. URL:https://doi.org/10.1002/9781118867464.ch3
The Pivotal Role of AI and Machine Learning in Huawei Network Manager, 2023. URL:https://forum.huawei.com/enterprise/intl/en/thread/the-pivotal-role-of-ai-and-machine-learning-in-huawei-network-manager/738147786895015936? blogId=738147786895015936 (access data 24/02/2025)
Tesla AI Day: What to Expect for the Future of Self-Driving Cars. URL:https://www.eetimes.eu/tesla-ai-day-what-to-expect-for-the-future-of-self-driving-cars/ (access data 24/02/2025)
Ensuring energy-efficient networks with artificial intelligence. URL:https://www.ericsson.com/en/reports-and-papers/ericsson-technology-review/articles/ ensuring-energy-efficient-networks-with-ai (access data 24/02/2025)
Siemens Enhances Industrial Copilot with Generative AI Offering. URL:https://www.digitalengineering247.com/article/siemens-enhances-industrial-copilot-with-generative-ai-offering/design (access data 24/02/2025)
A. Dlamini, E. Migabo and S. Mbuyu. Low Power Wide Area Networks (LPWAN) Technologies for Bulk IoT: A Critical Review of Reliability and En-ergy Efficiency, Vanderbijlpark, South Africa, 2024, pp. 351-360, DOI:10.1109/IMITEC60221.2024.10851092.
J. Pandya. Bandwidth and Power Cost Optimized MAC Protocols for IoT over VLC. IEEE-hydcon, Hyderabad, India, 2020, pp. 1-4, DOI:10.1109/HYDCON48903.2020.9242755.
Huawei. AI in the 5G-A Era: Scenarios, Key Technologies, and Evolution Trends, Communications of Huawei Research, 2024. URL:https://www.huawei.com/en/huaweitech/future-technologies/5ga-scenarios-key-technologies-evolution-trends (access data 24/02/2025)
Ericsson. Ericsson Key activities addressing climate change, рр 12, ITU Jour-nal on Future Networks, 2022. URL:https://www.itu.int/dms_pub/itu-t/oth/06/0f/T060f00601700909pdfe.pdf (access data 24/02/2025)
How Siemens Energy uses AWS for its IIoT platform and smart manufactur-ing, 2023. URL:https://aws.amazon.com/ru/blogs/iot/how-siemens-energy-uses-aws-for-its-iiot-platform-and-smart-manufacturing/ (access data 24/02/2025)
Vodafone. Technology and Innovation Artificial Intelligence. URL:https://www.vodafone.com/about-vodafone/what-we-do/artificial-intelligence?alias=about-vodafone&alias=what-we-do&alias=innovation&alias=artificial-intelligence (access data 24/02/2025)
Науковий вісник НЛТУ України URL:https://nv.nltu.edu.ua/index.php/journal/article/view/2657?utm_source=chatgpt.com (access data 24/02/2025)
Estonian e-Residency, or Transparent Digital Citizen. URL:https://svoboda.global/estonia-e-residency/ (access data 24/02/2025)
Md Al Amin, Hemanth Tummala, Rushabh Shah. Balancing Patient Privacy and Health Data Security: The Role of Compliance in Protected Health Infor-mation (PHI) Sharing. Colorado, 2024, USA. URL:https://doi.org/10.48550/arXiv.2407.02766
P. Wang, W. Sun, H. Zhang, W. Ma and Y. Zhang, Distributed and Secure Federated Learning for Wireless Computing Power Networks, IEEE Transac-tions on Vehicular Technology, vol. 72, no. 7, pp. 9381-9393, 2023, DOI:10.1109/TVT.2023.3247859.
P. Endla, R. S. Pure, A. Soni, C. Andal, D. Jagadeeswari and K. N. Devi. Intelligent 5G Evolution: AI-Augmented Hybrid Model with Network Slicing and Autonomous Self-Healing for Future-Ready Connectivity. International Conference on Electronics and Renewable Systems (ICEARS), Tuticorin, In-dia, 2025, pp. 839-846, DOI:10.1109/ICEARS64219.2025.10941272.