In modern wireless communication scenarios, non-orthogonal multiple access (NOMA) provides high throughput and spectral efficiency for fifth generation (5G) and beyond 5G systems. Traditional NOMA detectors are based on successive interference cancellation (SIC) techniques at both uplink and downlink NOMA transmissions. However, due to imperfect SIC, these detectors are not suitable for defense applications. In this paper, we investigate the 5G multiple-input multiple-output NOMA deep learning technique for defense applications and proposed a learning approach that investigates the communication system’s channel state information automatically and identifies the initial transmission sequences. With the use of the proposed deep neural network, the optimal solution is provided, and performance is much better than the traditional SIC-based NOMA detectors. Through simulations, the analytical outcomes are verified.
PaulSPatiUC.SAR image registration using an improved SAR-SIFT algorithm and Delaunay-triangulation-based local matching. IEEE J Select Topic Appl Earth Observ Remote Sens2019; 12: 2958-2966.
2.
PandyaSWakchaureMAShankarR, et al. Analysis of NOMA-OFDM 5G wireless system using deep neural network. J Defens Model Simulat. Epub ahead of print 28 March 2021. DOI: 1548512921999108.
3.
ShankarRKumarIMishraRK.Pairwise error probability analysis of dual hop relaying network over time selective Nakagami-m fading channel with imperfect CSI and node mobility. Traitement Sign2019; 36: 281-295.
4.
GökenÇYılmazADizdarO. Evaluation of 5G new radio non-orthogonal multiple access methods for military applications. arXiv preprint arXiv:1805.01125. 3 May 2018.
5.
DaiLWangBDingZ, et al. A survey of non-orthogonal multiple access for 5G. IEEE Commun Surv Tutor2018; 20: 2294–2323.
6.
LuoJTangJSoDK, et al. A deep learning-based approach to power minimization in multi-carrier NOMA with SWIPT. IEEE Access2019; 7: 17450-17460.
7.
ShankarR.Examination of a non-orthogonal multiple access scheme for next generation wireless networks. J Defens Model Simulat. Epub ahead of print 14 September2020. DOI: 10.1177/1548512920951277.
8.
OettingJDJenT.The mobile user objective system. Johns Hopkins APL Techn Dig2011; 30: 103–112.
9.
LiuCHLiangDC.Heterogeneous networks with power-domain NOMA: coverage, throughput, and power allocation analysis. IEEE Trans Wirel Commun2018; 17: 3524–3539.
10.
LeMTFerranteGCCasoG, et al. On information-theoretic limits of code-domain NOMA for 5G. IET Commun2018; 12: 1864-1871.
11.
ChenXJiaRNgDW.On the design of massive non-orthogonal multiple access with imperfect successive interference cancellation. IEEE Trans Commun2018; 67: 2539–2551.
12.
HiguchiKBenjebbourA.Non-orthogonal multiple access (NOMA) with successive interference cancellation for future radio access. IEICE Trans Commun2015; 98: 403–414.
13.
LuoJTangJSoDKC, et al. A deep learning-based approach to power minimization in multi-carrier NOMA with SWIPT. IEEE Access2019; 7: 17450–17460.
14.
YeNLiXYuH, et al. Deep learning aided grant-free NOMA toward reliable low-latency access in tactile Internet of Things. IEEE Trans Ind Informat2019; 15: 2995–3005.
15.
KangJMKimIMChunCJ.Deep learning-based MIMO-NOMA with imperfect SIC decoding. IEEE Syst J2019; 14: 3414-3417.
16.
LuoJTangJSoDK, et al. A deep learning-based approach to power minimization in multi-carrier NOMA with SWIPT. IEEE Access2019; 7: 17450–17460.
17.
LiuMSongTGuiG.Deep cognitive perspective: Resource allocation for NOMA-Based heterogeneous IoT with imperfect SIC. IEEE Internet Things J2019; 6: 2885–2894.
18.
GuiGHuangHSongY, et al. Deep learning for an effective nonorthogonal multiple access scheme. IEEE Trans Veh Technol2018; 67: 8440–8450.
19.
YeNLiXYuH, et al. Deep learning aided grant-free NOMA toward reliable low-latency access in tactile internet of things. IEEE Trans Ind Inform2019; 15: 2995–3005.
20.
MahadyIABedeerEIkkiS, et al. Sum-rate maximization of NOMA systems under imperfect successive interference cancellation. IEEE Commun Lett2019; 23: 474–477.
21.
TuanHDNasirAANguyenHH, et al. Nonorthogonal multiple access with improper Gaussian signaling. IEEE J Sel Top Sign Proc2019; 13: 496–507.
22.
ChenXJiaRNgDWK. On the design of massive non-orthogonal multiple access with imperfect successive interference cancellation. IEEE Trans Commun2019; 67: 2539–2551.
23.
AliSHossainEKimDI.Non-orthogonal multiple access (NOMA) for downlink multiuser MIMO systems: user clustering, beamforming, and power allocation. IEEE Access2016; 5: 565–577.
24.
BhardwajLMishraRKShankarR.Sum rate capacity of non-orthogonal multiple access scheme with optimal power allocation. J Defens Model Simulat. Epub ahead of print 7 January 2021. DOI: 10.1177/1548512920983531.
25.
ShankarRNandiSRupaniA.Channel capacity analysis of non-orthogonal multiple access and massive multiple-input multiple-output wireless communication networks considering perfect and imperfect channel state information. J Defens Model Simulat. Epub ahead of print 28 March2021. DOI: 10.1177/15485129211000139.
26.
BenjebbourASaitoYKishiyamaY, et al. Concept and practical considerations of non-orthogonal multiple access (NOMA) for future radio access. In: 2013 international symposium on intelligent signal processing and communication systems, Naha, Japan, 12–15 November 2013, pp.770–774.
27.
ChaudharyBPShankarRMishraRK.A tutorial on cooperative non-orthogonal multiple access networks. J Defens Model Simulat. Epub ahead of print 7 February2021. DOI: 10.1177/1548512920986627.
28.
XiaBWangJXiaoK, et al. Outage performance analysis for the advanced SIC receiver in wireless NOMA systems. IEEE Trans Veh Technol2018; 67: 6711-6715.
29.
LingBDongCDaiJ, et al. Multiple decision aided successive interference cancellation receiver for NOMA systems. IEEE Wirel Commun Lett2017; 6: 498–501.
30.
AlsmadiMMAliNAHayajnehM, et al. Down-link NOMA networks in the presence of IQI and imperfect SIC: receiver design and performance analysis. IEEE Trans Veh Technol2020; 69: 6793-6797.
31.
DoDTLeATLeeBM. NOMA in cooperative underlay cognitive radio networks under imperfect SIC. IEEE Access2020; 8: 86180-86195.
32.
De SenaASLimaFRda CostaDB, et al. Massive MIMO-NOMA networks with imperfect SIC: design and fairness enhancement. IEEE Trans Wirel Commun2020; 19: 6100–6115.
33.
LiXLiuMDengC, et al. Full-duplex cooperative NOMA relaying systems with I/Q imbalance and imperfect SIC. IEEE Wirel Commun Lett2019; 9: 17–20.
34.
AkhtarMWHassanSASaleemS, et al. STBC-aided cooperative NOMA with timing offsets, imperfect successive interference cancellation, and imperfect channel state information. IEEE Trans Veh Technol2020; 69: 11712–11727.
35.
SourabhPPatiUC.A block-based multi-feature extraction scheme for SAR image registration. IEEE Geosci Remote Sens Lett2018; 15: 1387–1391.
36.
GoodfellowIBengioYCourvilleA, et al. Deep learning. Cambridge: MIT Press, 2016.
37.
LeCunYBengioYHintonG. Deep learning. Nature2015; 521: 436–444.
38.
BengioYGoodfellowICourvilleA.Deep learning. Cambridge, MA: MIT Press, 2017.
39.
FengQChenLChenCLP, et al. Deep fuzzy clustering–a representation learning approach. IEEE Trans Fuzzy Syst2020; 28: 1420–1433.
40.
LiuWWangZLiuX, et al. A survey of deep neural network architectures and their applications. Neurocomputing2017; 234: 11–26.
41.
LinBYangHWangR, et al. Convolutional neural network-based signal demodulation method for NOMA-PON. Opt Expr2020; 28: 14357–14365.
42.
HaraKSaitoDShounoH. Analysis of function of rectified linear unit used in deep learning. In: 2015 international joint conference on neural networks (IJCNN), 12July2015, pp.1–8. IEEE.
43.
ShahAKadamEShahH, et al. Deep residual networks with exponential linear unit. In: VisionNet’16: proceedings of the third international symposium on computer vision and the internet, 21 September 2016, pp.59–65.
GuoKHuYQianZ, et al. Optimized graph convolution recurrent neural network for traffic prediction. IEEE Trans Intell Transp Syst2021; 22: 1138–1149.
46.
YangWYCaoWKimJ, et al. Applied numerical methods using MATLAB. Hoboken, NJ: John Wiley & Sons, Inc., 2020.
47.
BlankJDebK.Pymoo: multi-objective optimization in python. IEEE Access2020; 8: 89497–89509.
48.
PaperD. Build your first neural network with Google Colab. TensorFlow 2. x in the Colaboratory Cloud: an introduction to deep learning on Google’s Cloud Service. New York, NY: Apress Media LLC, 2021, pp.25–45.
49.
TiwariRDeshmukhS.Prior information-based Bayesian MMSE estimation of velocity in HetNets. IEEE Wirel Commun Lett2019; 8: 81–84.
50.
TiwariRShrivastavaSDasS.Performance analysis of patient monitoring system under different routing algorithm. In: international conference for convergence for technology-2014, Pune, 2014, pp.1–6.
51.
TiwariRDeshmukhS.MVU estimate of user velocity via gamma distributed handover count in HetNets. IEEE Commun Lett2019; 23: 482–485.
