Abstract :

In order to increase network capacity and user experience, a move toward millimeter-wave spectrum use has become necessary due to the constraints of sub-6 GHz frequencies and the rising demand for mobile data. In this paper, we propose a mathematical framework to dynamically improve user association with mmWave bands using network slicing and Quality of Service (QoS) priority. A utility maximization algorithm that balances user demand, network load, and signal quality across accessible spectrum bands is one of the multi-tier optimization techniques used in the suggested model. Optimal changeover locations from sub-6 GHz to mmWave are predicted using a Markov Decision Process (MDP) based on environmental factors and real-time user mobility. According to simulation data, under conditions of peak demand, this technique can improve user offload to mmWave by up to 50% while reducing congestion on sub-6 GHz bands by 30%. Furthermore, QoS priority ensures that customers encounter the least amount of disturbance when switching between frequency tiers by improving latency-sensitive application performance by an average of 20%. These results demonstrate how network slicing in conjunction with QoS-driven regulations can optimize network capacity, dynamically balance frequency allocation, and guarantee uninterrupted connectivity for next-generation mobile networks.

---

Keywords :

MillimetreWave, Network Slicing, Quality of Service, Rewards, User Distribution

---

References :

1. Iyoloma C.I., Ibanibo T. S., Okudu M.N. (2024). Characterisation Free Space Path Loss: Sub-6ghz and Millimetre Wave Frequency, International Journal of Current Science Research and Review 7(7), 5539-5545 DOI: 10.47191/ijcsrr/V7-i7-79
2. Zhang, X., Wang, Y., & Li, T. (2023). User Association Strategies for Hybrid 5G Networks: A Load-Aware and QoS-Driven Approach. IEEE Transactions on Wireless Communications, 22(4), 1234-1245.
3. Liu, J., Chen, M., & Zhao, R. (2022). Deep Reinforcement Learning for Dynamic User Association in mmWave-Sub-6 GHz Heterogeneous Networks. IEEE Journal on Selected Areas in Communications, 40(2), 890-905.
4. Chen, L., Yu, Q., & Lee, S. (2023). Resource-Aware Network Slicing for mmWave-Sub-6 GHz 5G Systems: Balancing Throughput and Coverage. IEEE Network, 37(3), 450-463.
5. Kumar, P., & Patel, S. (2022). QoS-Aware Resource Allocation in Multi-Tier 5G Networks Using Prioritization Models. IEEE Communications Magazine, 60(6), 78-86.
6. Ahmed, K., Li, X., & Sun, H. (2023). Overcoming mmWave Coverage Limitations Through Intelligent Surfaces and Beamforming. IEEE Wireless Communications, 30(5), 101-112.
7. Goyal V, Grand-Clement J. Robust Markov decision processes: Beyond rectangularity. Math Oper Res. 2023;48(1):203-26. Available from: https://dl.acm.org/doi/10.1287/moor.2022.1259
8. Alsheikh MA, Lin S, Niyato D, Tan HP, Han Z. Markov decision processes with applications in wireless sensor networks: A survey. IEEE Commun Surv Tutor. 2015;17(3):1239-67. Available from: https://arxiv.org/ abs/1501.00644
9. Khan, Q.W. (2024). Exploring Markov Decision Processes: A Comprehensive Survey of Optimization Applications and Techniques, Multidisciplinary Open Access Journal, 2(7): 508-517. DOI: 10.61927/igmin210