In this paper, a deep learning-based successive interference cancellation (SIC) scheme for use in nonorthogonal multiple access (NOMA) communication systems is investigated. NOMA has become a notable technique in the field of mobile wireless communication because of its capacity to overcome orthogonality, unlike a conventional orthogonal frequency division multiple access (OFDMA) communication system. In NOMA communication systems, SIC is one of the decoding schemes applied at receivers for downlink NOMA transmissions. In this paper, a convolutional neural network (CNN)-based SIC scheme is proposed to improve performance of the single base station and multiuser NOMA scheme. In contrast to existing SIC schemes, the proposed CNN-based SIC scheme can effectively mitigate losses resulting from imperfections of the SIC. The simulation results indicate that the CNN-based SIC method can successfully relieve conventional SIC impairments and achieve good detection performance. Consequently, a CNN-based SIC scheme can be considered as a potential technique for use in NOMA detection schemes.
Figure 12. Loss function versus number of epochs for the proposed CNN-based SIC scheme with Figure 12. Loss function versus number of epochs for the proposed CNN-based SIC scheme with varying activation functions. varying activation functions. 5. Conclusions 5. Conclusions 5. Conclusions In this paper, the practical issue of imperfect successive interference cancellation was described. In this paper, the practical issue of imperfect successive interference cancellation was described. The sInu mthirsatpealpoesrs, othf eN pOraMctAic-abla issesduew oifr eimlespsecrofemctm suucnciecsastiivone isnytsetrefmersencaceusceadncbeyllaimtiopne rwfeacst dSIeCsccraibnebde. The sum rate loss of NOMA-based wireless communication systems caused by imperfect SIC can be Tmhiet isguamte drabtye ltohsesporfo NpoOsMedAC-bNaNse-dbawsierdelSeIsCs csocmhemmuen. iTcahteiolneasrynsitnegmpsecrafuorsmedanbyceimofptehrefepcrto SpICos ceadnS bICe mitigated by the proposed CNN-based SIC scheme. The learning performance of the proposed SIC mscihtiegmateedwabsyitllhues tprraotepdosinedthCeNsiNm-ublaasteiodnSrIeCs usclthsewmieth. Tvhaeri oleuasrnpianrgampeertfeorrsm. ance of the proposed SIC scheme was illustrated in the simulation results with various parameters. schemTeh iws asstuildluystcraotnefdir imn sthteh asitmtuhelatCioNnNre-sbualstesd wditehe vparlieoaurns ipnagraampeptreoras.ch is a promising tool for This study confirms that the CNN-based deep learning approach is a promising tool for enhaTnhciesmsetnutdoyf tchoenfNirOmMs Athdaet tethctei oCnNscNh-ebmaseeadnddethepat ltehaernpirnogp oaspepdrSoIaCchs chisema epcraonmaiscihnigev teohoilghfoerr enhancement of the NOMA detection scheme and that the proposed SIC scheme can achieve higher esnuhmanrcaetmesencotmofp tahree dNOwMithA tdheeteccotniovne nsctihoenmale oanned. thTahtethree spurlotps oosfedth SisICp ascpheermcea ncafnin adchaipepveli chaitgihoenrs sum rates compared with the conventional one. The results of this paper can find applications in siunm5 Gra/6teGs wcoimrepleasrsedc owmimthutnhiec actoionnveanntidoninal woniree.l eTshses reenssuolrtsn oeft wthoirsk psawpeitrh caimn pfirnodv eadppNliOcaMtioAnsa nind 5G/6G wireless communication and in wireless sensor networks with improved NOMA and 5inGt/e6lGlig ewnitrpelreoscsescsoinmgm. unication and in wireless sensor networks with improved NOMA and intelligent processing. intelligent processing. Author Contributions: Data curation, Y.G.S. and J.L.; Project administration, I.S.; Software, D.L.; Validation, JA.-uHt.hKo.r; VCisounatrliizbautitoionn, sS:.HD.aKt.a; Wcurritaitniogn—, oYr.iGgi.Sn.a ladndrafJt.L, I..;SP.;rWojerictti nagd—mrienvisietrwat&ione,d Iit.Sin.;gS, oYf.tSw. aanred, JD.Y..LK.;. AVlallaiduatthioorns, Author Contributions: Data curation, Y.G.S. and J.L.; Project administration, I.S.; Software, D.L.; Validation, J.-H.K.; Visualization, S.H.K.; Writing—original draft, I.S.; Writing—review & editing, Y.S. and J.Y.K. All J.-H.K.; Visualization, S.H.K.; Writing—original draft, I.S.; Writing—review & editing, Y.S. and J.Y.K. All Funding:authors have Thisread researandchagreed to was supportedthe publishinedpartversibyon ofthethe manuMSIT, Korscript.ea, under the ITRC support program authors have read and agreed to the published version of the manuscript. (IITP-2020-2018-0-01424) and (IITP-2020-0-01846) supervised by the IITP, and in part by Kwangwoon University in 2020.This research was supported in part by the MSIT, Korea, under the ITRC support program(IITP-2020-2018-0-01424) and (IITP-2020-0-01846) supervised by the IITP, and in part by Kwangwoon University in 2020.
