Page Header

Optimal Power Allocation in NOMA System Based on Artificial Intelligence Methods

Igor Jovanovic, Kritsada Mamat

Abstract


This paper considers the Non-Orthogonal Multiple Access (NOMA) technique which is one of the core technologies in 5G and beyond. To distinguish users in the power domain, Superposition coding and Successive Interference Cancellation (SIC) are applied at the transmitter and receiver. Power allocation is shown to be significant in affecting the system performance. This work proposes an application of two Artificial Intelligence (AI) methods, Q-learning and Genetic Algorithm (GA), in order to optimize the power allocation in the NOMA system. Namely, the maximization of the minimum bitrate of the overall system as well as the transformation of the NOMA system into both Q-learning and GA components are obtained by setting and solving the power allocation optimization problem. Numerical results demonstrate that Artificial intelligence algorithms provide a higher minimum bitrate in comparison with the existing theoretical power allocation methods. Besides bitrate, the complexity of both methods is analyzed. It is concluded that Q-learning has an exponential, while GA has a linear complexity with the increase of the total number of users.


Keywords


NOMA; power allocation; Artificial Intelligence; Q-learning, Genetic Algorithm

[1] L. Dai, B. Wang, Z. Ding, Z. Wang, S. Chen, and L. Hanzo, A survey of non-orthogonal multiple access for 5G, IEEE Communication Surveys Tutorials, 2018, 20(3), 2294-2323.

[2] M. Zeng, A. Yadav, O.A. Dobre, G.I. Tsiropoulos and H.V. Poor, On the sum rate of MIMO-NOMA and MIMO-OMA systems, IEEE Wireless Communications Letters, 2017, 6(20), 534-537.

[3] D. Zhang, Y. Liu, Z. Ding, Z. Zhou, A. Nallanathan and T. Sato, Performance analysis of non-regenerative massive-MIMO-NOMA relay systems for 5G, IEEE Transactions on Communications, 2017, 65(1), 4777-4790.

[4] Y. Liu, G. Pan, H. Zhang and M. Song, On the capacity comparison between MIMO-NOMA and MIMO-OMA, IEEE Access, 2016, 4, 2123-2190.

[5] J. Cui, Z. Ding and P. Fan, A novel power allocation scheme under outage constraints in NOMA systems, IEEE Signal Processing Letters, 2016, 23(9), 1226-1230.

[6] D. Ni, L. Hao, Q.T. Tran and X. Qian, Transmit power minimization for downlink multi-cell multi-carrier NOMA networks, IEEE Communications Letters, 2018, 22(12), 2459-2462.

[7] Y. Zhang, X. Zhao, S. Geng, Z. Zhou, P. Qin, L. Zhang and L. Yang, Power allocation algorithms for stable successive interference cancellation in millimeter wave NOMA systems, IEEE Transactions on Vehicular Technology, 2018, 22(12), 2459-2462.

[8] Y. Kwon, H. Baek and J. Lim, Uplink NOMA using power allocation for UAV-Aided CSMA/CA Networks, IEEE Systems Journal, 2021, 15(2), 2378-2381.

[9] J. Bae and Y. Han, Joint power and time allocation for Two-Way cooperative NOMA, IEEE Transactions on Vehicular Technology, 2019, 68(12), 12443-12447.

[10] M.R.G. Aghdam, B.M. Tazehkand and R. Abdolee, Joint optimal power allocation and beamforming for MIMO-NOMA in mmWave communications, IEEE Wireless Communications Letters, 2022, 11(5), 938-941.

[11] www.simplilearn.com/tutorials/artificial-intelligence-tutorial/artificial-intelligence-applications. (Accessed on 18 January 2023)

[12] R.S. Sutton and A.G. Barto, Reinforcement Learning: An introduction, 2nd Ed., MIT Press, Cambridge, Massachusetts, London, 2017.

[13] M. Chen, W. Saad and C. Yin, Optimized uplink-downlink decoupling in LTE-U networks: An echo state approach, IEEE International Conference on Communications (ICC-Malaysia 2016), Proceeding, 2016, 1-6.

[14] H. Sun, X. Chen, Q. Shi, M. Hong, X. Fu and N.D. Sidiropoulos, Learning to optimize: Training deep neural networks for interference management, IEEE Transactions on Signal Processing, 2018, 6(20), 5438-5453.

[15] E. Mete and T. Girici, Q-Learning based scheduling with successive interference cancellation, IEEE Access, 2020, 8, 172034-172042.

[16] P. Aermsa-Ard, C. Wangsamad and K. Mamat, On applying Q-Learning to optimize power allocation in 2-users NOMA system, The journal of Industrial Technology, 2023, 19(1), 104-116. (in Thai)

[17] Ö.F. Gemici, F. Kara, I. Hokelek, G.K. Kurt and H.A. Çırpan, Resource allocation for NOMA downlink systems: Genetic algorithm approach, 40th International Conference on Telecommunications and Signal Processing (TSP), Proceeding, 2017, 114-118.

[18] S. Lee, J. Kim and S. Cho, Resource Allocation for NOMA based D2D system using genetic algorithm with continuous pool, 2019 International Conference on Information and Communication Technology Convergence (ICTC), Proceeding, 2019, 705-707.

[19] M.M. El-Sayed, A.S. Ibrahim and M.M. Khairy, Power allocation strategies for Non-Orthogonal multiple access, International Conference on Selected Topics in Mobile & Wireless Networking (MoWNeT-Egytp 2016), Proceeding, 2016, 1-6.

[20] E. Cantu-Paz, Selection intensity in genetic algorithm algorithms with generation gaps, Genetic and Evolutionary Computation Conference (Las Vegas, NY 2000), Proceeding, 2000, 1-8.

[21] D.R. da S. Medeiros, M.F. Torquato and M.A.C. Fernandes, Embedded genetic algorithm for low-power, low-cost, and low-size-memory devices, Engineering Report, 2020, 2(9), 1-28.

Full Text: PDF

DOI: 10.14416/j.ind.tech.2024.04.003

Refbacks

  • There are currently no refbacks.