Adaptive User Migration based on Deep Reinforcement Learning for Cloud Radio Access Network

Adaptive User Migration based on Deep Reinforcement Learning for Cloud Radio Access Network
  IJETT-book-cover           
  
© 2025 by IJETT Journal
Volume-73 Issue-8
Year of Publication : 2025
Author : Sura F. Ismail , Dheyaa Jasim Kadhim
DOI : 10.14445/22315381/IJETT-V73I8P104

How to Cite?
Sura F. Ismail , Dheyaa Jasim Kadhim, "Adaptive User Migration based on Deep Reinforcement Learning for Cloud Radio Access Network," International Journal of Engineering Trends and Technology, vol. 73, no. 8, pp.42-56, 2025. Crossref, https://doi.org/10.14445/22315381/IJETT-V73I8P104

Abstract
A proposed design for 5G and below mobile communication systems is Cloud Radio Access Networks (C-RAN), which offers consumers seamless connectivity while meeting their constantly rising demands. Baseband Units (BBUs) and Remote Radio Heads (RRHs) make up the base station functionality in C-RAN. After that, cloud computing and virtualization techniques are used to centralize and virtualize the BBUs from multiple locations. The BBU pool is where all data processing and control are carried out, and RRHs are in charge of radio functionalities. Since one of the advanced network challenges is user mobility, particularly in high-density environments, an efficient user handover is necessary to maintain high Quality of Service (QoS) and minimize packet loss. Traditional handover mechanisms rely on fixed SINR thresholds to decide when to migrate users between RRHs. Such static methods may lead to suboptimal handovers, particularly in dynamic network environments. Therefore, this paper proposes and evaluates two intelligent user migration strategies-Fuzzy Logic and Deep Reinforcement Learning (DRL)-to replace the static SINR-based approach. Both methods aim to improve the decision-making process for RRH selection during user migration. The fuzzy logic model uses expert-defined rules based on user velocity, distance, load, and SINR to make fast and interpretable decisions. In contrast, the DRL model learns an optimal migration policy through interaction with the environment using a multi-objective reward function. All three methods-traditional, fuzzy, and DRL-are implemented and tested in a Simu5G-based C-RAN environment. The results show that both AI-based methods significantly outperform the traditional approach. Notably, the DRL method achieves the highest performance gains, with a 46.4% increase in throughput, 66.7% reduction in handover failures, and 40% decrease in latency. These results highlight the advantages of integrating AI techniques for efficient and intelligent mobility management in next-generation wireless networks.

Keywords
Cloud Radio Access Network, DRL, Fuzzy logic, RRH failure, Simu5G, User migration.

References
[1] A. Gupta, and R.K. Jha, “A Survey of 5G Network: Architecture and Emerging Technologies,” IEEE Access, vol. 3, pp. 1206-1232, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Yong Niu et al., “A Survey of Millimeter Wave Communications (mmwave) for 5G: Opportunities and Challenges,” Wireless Networks, vol. 21, no. 8, pp. 2657-2676, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Mohammed H. Alsharif et al., “Small Cells Integration with the Macro-Cell under LTE Cellular Networks and Potential Extension for 5G,” Journal of Electrical Engineering & Technology, vol. 14, no. 6, pp. 2455-2465, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Niezi Mharsi, “Cloud-Radio Access Networks: Design, Optimization and Algorithms,” Doctoral Thesis, Paris Saclay University (COMUE), pp. 1-106, 2019.
[Google Scholar] [Publisher Link]
[5] Mugen Peng, “Fronthaul-Constrained Cloud Radio Access Networks: Insights and Challenges,”
IEEE Wireless Communications, vol. 22, no. 2, pp. 152-160, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Aleksandra Checko et al., “Cloud RAN for Mobile Networks-A Technology Overview,” IEEE Communications Surveys & Tutorials, vol. 17, no. 1, pp. 405-426, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Sourjya Bhaumik et al., “CloudIQ: A Framework for Processing Base Stations in a Data Center,” Mobicom'12: The 18th Annual International Conference on Mobile Computing and Networking, Istanbul, Turkey, pp. 125-136, 2012.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Fengyu Tian, Peng Zhang, and Zheng Yan, “A Survey on C-RAN Security,” IEEE Access, vol. 5, pp. 13372-13386, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Yonghua Lin et al., “Wireless Network Cloud: Architecture and System Requirements,” IBM Journal of Research and Development, vol 54, no. 1, pp. 4:1-4:12, 2010.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Osvaldo Simeone et al., “Cloud Radio Access Network: Virtualizing Wireless Access for Dense Heterogeneous Systems,” Journal of Communications and Networks, vol. 18, no. 2, pp. 135-149, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Ekram Hossain, and Monowar Hasan, “5G Cellular: Key Enabling Technologies and Research Challenges,” IEEE Instrumentation & Measurement Magazine, vol. 18, no. 3, pp. 11-21, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Zainab H. Fakhri, Firas Sabir, and H.S. Al-Raweshidy, “An Interference Mitigation Scheme for Millimetre Wave Heterogeneous Cloud Radio Access Network with Dynamic RRH Clustering,” 2019 International Symposium on Networks, Computers and Communications (ISNCC), Istanbul, Turkey, pp. 1-8, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Yao Sun et al., “The Smart Handoff Policy for Millimeter Wave Heterogeneous Cellular Networks,” IEEE Transactions on Mobile Computing, vol. 17, no. 6, pp. 1456-1468, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Li Sun, Jing Hou, and Tao Shu, “Spatial and Temporal Contextual Multi-Armed Bandit Handovers in Ultra-Dense mmWave Cellular Networks,” IEEE Transactions on Mobile Computing, vol. 20, no. 12, pp. 3423-3438, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Maria Diamanti et al., “Unified User Association and Contract-Theoretic Resource Orchestration in NOMA Heterogeneous Wireless Networks,” IEEE Open Journal of the Communications Society, vol. 1, pp. 1485-1502, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Diego Castro-Hernandez, and Raman Paranjape, “Optimization of Handover Parameters for LTE/LTE-A in-Building Systems,” IEEE Transactions on Vehicular Technology, vol. 67, no. 6, pp. 5260-5273, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Kun-Lin Tsai, Han-Yun Liu, and Yu-Wei Liu, “Using Fuzzy Logic to Reduce Ping-Pong Handover Effects in LTE Networks,” Soft Computing, vol. 20, no. 5, pp. 1683-1694, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Abdulraqeb Alhammadi et al., “Advanced Handover Self-Optimization Approach for 4G/5G Hetnets Using Weighted Fuzzy Logic Control,” 2019 15th International Conference on Telecommunications (ConTEL), Graz, Austria, pp. 1-6, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Abdulraqeb Alhammadi et al., “Velocity-Aware Handover Self-Optimization Management for Next Generation Networks,” Applied Sciences, vol. 10, no. 4, pp. 1-14, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Ketyllen C. Silva et al., “Self-Tuning Handover Algorithm Based on Fuzzy Logic in Mobile Networks with Dense Small Cells,” 2018 IEEE Wireless Communications and Networking Conference (WCNC), Barcelona, Spain, pp. 1-6, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Michael S. Mollel et al., “Intelligent Handover Decision Scheme Using Double Deep Reinforcement Learning,” Physical Communication, vol. 42, pp. 1-13, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Taewoon Kim, Chanjun Chun, and Wooyeol Choi, “Optimal User Association Strategy for Large-Scale IoT Sensor Networks with Mobility on Cloud RANs,” Sensors, vol. 19, no. 20, pp. 1-19, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[23] Tugce Bilen, Berk Canberk, and Kaushik R. Chowdhury, “Handover Management in Software-Defined Ultra-Dense 5G Networks,” IEEE Network, vol. 31, no. 4, pp. 49-55, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[24] Yalin Zhang, Liang Xiong, and Jia Yu, “Deep Learning Based User Association in Heterogeneous Wireless Networks,” IEEE Access, vol. 8, pp. 197439-197447, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[25] Kinda Khawam et al., “Coordinated Framework for Spectrum Allocation and User Association in 5G HetNets with mmWave,” IEEE Transactions on Mobile Computing, vol. 21, no. 4, pp. 1226-1243, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[26] Mohamed Sana et al., “Multi Agent Reinforcement Learning for Adaptive User Association in Dynamic mmWave Networks,” IEEE Transactions on Wireless Communications, vol. 19, no. 10, pp. 6520-6534, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[27] Judhajit Sanyal, and Tuhina Samanta, “Game Theoretic Approach to Enhancing D2D Communications in 5G Wireless Networks,” International Journal of Wireless Information Networks, vol. 28, no. 4, pp. 421-436, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[28] Minglei You et al., “Delay Guaranteed Joint User Association and Channel Allocation for Fog Radio Access Networks,” IEEE Transactions on Wireless Communications, vol. 20, no. 6, pp. 3723-3733, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[29] Lin Zhu et al., “Cluster-Based Energy-Efficient Joint User Association and Resource Allocation for B5G Ultra-Dense Network,” Physical Communication, vol. 46, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[30] Rui Liu et al., “User Association for Millimeter-Wave Networks: A Machine Learning Approach,” IEEE Transactions on Communications, vol. 68, no. 7, pp. 4162-4174, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[31] Yuyi Mao, Jun Zhang, and Khaled B. Letaief, “Dynamic Computation Offloading for Mobile-Edge Computing with Energy Harvesting Devices,” IEEE Journal on Selected Areas in Communications, vol. 34, no. 12, pp. 3590-3605, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[32] Evolved Universal Terrestrial Radio Access (E-UTRA), Radio Resource Control (RRC), Protocol Specification (3GPP TS 36.331 version 10.7.0 Release 10), ETSI TS 136 331, V10.7.0 (2012-11), European Telecommunications Standards Institute, 2012. [Online]. Available: https://www.etsi.org/deliver/etsi_ts/136300_136399/136331/10.07.00_60/ts_136331v100700p.pdf
[33] Giovanni Nardini et al., “Simu5G-An OMNeT++ Library for End-to-End Performance Evaluation of 5G Networks,” IEEE Access, vol. 8, pp. 181176-181191, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[34] Rehenuma Tasnim Rodoshi, “Reinforcement Learning-based User Association for Cloud Radio Access Networks,” Master Thesis, Chosun University Graduate School, pp. 1-73, 2021.
[Google Scholar] [Publisher Link]