Maximization of Error Performance of Device-to-Device (D2D) Cooperative Communication Systems with Deep Learning AidedOptimum Threshold
Emre Çakar1, Ahmet Emir2*, Ferdi Kara3, Hakan Kaya4
1Zonguldak Bülent Ecevit University , Zonguldak, Turkey
2Zonguldak Bülent Ecevit University, Zonguldak, Turkey
3Zonguldak Bülent Ecevit University, Zonguldak, Turkey
4Zonguldak Bülent Ecevit University, Zonguldak, Turkey
* Corresponding author: ahmet.emir@beun.edu.tr
Presented at the International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA2019), Ürgüp, Turkey, Jul 05, 2019
SETSCI Conference Proceedings, 2019, 8, Page (s): 1-6 , https://doi.org/10.36287/setsci.4.5.001
Published Date: 12 October 2019
Abstract – Machine learning techniques have become practical tools for many engineering problems thanks to computational speeds, performances and solutions even in situations where complete knowledge is not available. Likewise, in all engineering fields, machine learning algorithms are widely used by researchers in wireless communication systems. In this study, the deep learning (DL) which is a subset of machine learning, is applied to cooperative communication systems in wireless communications. In cooperative communication systems, for relays using threshold-based DF (Decode - Forward) protocol, the threshold value at relays have dominant effect on system performance. In this study, in order to increase the error performance of cooperative communication systems, it is proposed to determine the threshold value of the relay adaptively from the noisy signals reaching to the relays by using DL technique. The optimal threshold value expressions by obtained using the DL model have been compared with the optimum values obtained by numerically minimizing the end-to-end (e2e) bit error probability expression of the system. The threshold values obtained by using the DL technique have matched well with the numerically calculated values. Compared to usage of fixed threshold, it has been observed that optimum threshold usage needs approximately 3dB lower Signal to Noise Ratio (SNR) for the same error probability target. Özet – Makine öğrenmesi teknikleri, hesaplama hızları, başarımları ve tam bilgiye sahip olunmayan durumlarda bile sunduğu çözümler sayesinde birçok mühendislik problemleri için vazgeçilmez bir araç haline gelmiştir. Tüm mühendislik alanlarında olduğu gibi, kablosuz iletişim sistemlerinde de makine öğrenmesi algoritmaları araştırmacılar tarafından yaygın olarak kullanılmaktadır. Bu çalışmada da makine öğrenmesi sınıfı olan derin öğrenme (Deep Learning -DL), kablosuz iletişim tekniklerinden biri olan işbirlikli iletişim (cooperative communication) sistemlerine uygulanmıştır. İşbirlikli haberleşme sistemlerinde, eşik değer tabanlı Çöz-Aktar (Decode and Forward -DF) protokolü kullanan röleler için röledeki eşik değerin ne olması gerektiği sistem performansında önemli rol oynamaktadır. Bu çalışmada, işbirlikli iletişim sistemlerinin hata başarımlarının arttırılması amacıyla röledeki eşik değerin DL tekniği kullanılarak rölelere ulaşan gürültülü veriden adaptif bir şekilde belirlenmesi önerilmektedir. DL modeli kullanılarak elde edilen optimum eşik değer ifadeleri, sistemin uçtan uca bit hata olasılığı ifadesinin nümerik olarak minimize edilmesiyle elde edilen optimum değerlerle karşılaştırılmıştır. DL tekniği kullanılarak elde edilen eşik değerler, nümerik olarak hesaplanan değerler ile oldukça yakın elde edilmiştir. Sabit eşik değer kullanımı ile optimum eşik değer kullanımı karşılaştırıldığında sistemin aynı hata olasılığında iletişim yapabilmesi için optimum eşik değer kullanımı yaklaşık 3dB daha düşük işaret gürültü oranına ihtiyaç duyduğu gözlenmiştir.
Keywords - Özet – Makine öğrenmesi teknikleri, hesaplama hızları, başarımları ve tam bilgiye sahip olunmayan durumlarda bile sunduğu çözümler sayesinde birçok mühendislik problemleri için vazgeçilmez bir araç ha
[1] Haykin, S. 1999. Neural Networks: A Comprehensive Foundation. The Knowl. Eng. Rev. 13(4):409-412
[2] Zhou, X., Wang, X. 2003. Channel Estimation for OFDM Systems Using Adaptive Radial Basis Function Networks. IEEE Trans. Veh. Tech. 52(1):48–59.
[3] Burse, K., Yadav, R.N., Shrivastava, S.C. 2010. Channel Equalization Using Neural Networks: A Review. IEEE T. Syst. Man. Cy. C, 40 (3): 352– 57.
[4] Cheng, C.H., Huang, Y.H., Chen, H.C. 2015. Channel Estimation in OFDM Systems Using Neural Network Technology Combined with a Genetic Algorithm. Soft Comput. Springer Berlin Heidelberg. 1-10 pp.
[5] I. N. Aizenberg, N. N. Aizenberg ve J. Vandewalle, “Multiple-Valued Threshold Logic and Multi-Valued Neurons”, Multi-Valued and Universal Binary Neurons, Bostan,USA, 2000, pp. 25-80.
[6] K. Güzel, “Geri Yayılımlı Çok Katmanlı Yapay Sinir Ağları-1,” [Çevrimiçi]. Available: https://medium.com/@billmuhh/geri-yayılımlı-çokkatmanlı-yapay-sinir-ağları- 1-47daa3856247 . [Erişildi: 16 11 2018].
[7] Gao, X. , Jin,S. , Wen, C. and Li,G. . " ComNet: Combination of Deep Learning and Expert Knowledge in OFDM Receivers '', IEEE Communications Letters ( Early Access ), 2018.
[8]Xu, W. , Zhon, Z. , Be’ery,Y. , You, X. and Zhang,C. " Joint Neural Network Equalizer and Decoder '', 15th International Symposium on Wireless Communication Systems (ISWCS), 2018.
[9]Liao, R. , Wen,H., Wu,J., Song, H.,Pan, F. and Lian Dong. "he Rayleigh Fading Channel Prediction via Deep Learning", Hindawi Wireless Communications and Mobile Computing, Vol. 2018, pp:1-11, 2018.
[10]Gui, G. Huang, H. ,Song, Y. and Sari , H." Deep Learning for an Effective Nonorthogonal Multiple Access Scheme ", IEEE Transactions on Vehicular Technology , Vol. 67, Iss. 9: 8440-8450, 2018.
[11] N. Ye, X. Li, H. Yu, A. Wang, W. Liu, and X. Hou, “Deep Learning Aided Grant-Free NOMA Toward Reliable Low-Latency Access in Tactile Internet of Things,” IEEE Trans. Ind. Informatics, vol. 15, no. 5, pp. 2995– 3005, 2019.
[12] N. Zhang, K. Cheng, and G. Kang, “A Machine-Learning-Based Blind Detection on Interference Modulation Order in NOMA Systems,” IEEE Commun. Lett., vol. 22, no. 12, pp. 2463–2466, 2018.
[13] M. Choi, D. Yoon, and J. Kim, “Blind Signal Classification for NonOrthogonal Multiple Access in Vehicular Networks,” pp. 1–12.
[14] T. V. Luong, Y. Ko, N. A. Vien, and D. H. N. Nguyen, “Deep LearningBased Detector for OFDM-IM,” IEEE Wirel. Commun. Lett., vol. PP, no. c, p. 1, 2019.
[15] Sendonaris, A., Erkip, E., Aazhang, B. 1998. Increasing uplink capacity via user cooperation diversity, IEEE International Symposium on Information Theory, pp.156, USA.
[16] Laneman, J.N., Tse, D.N.C., Wornell, G.W. 2001 An efficient protocol for realizing cooperative diversity in wireless networks, IEEE ISIT, 294 pp., USA
[17] Laneman, J.N., Tse, D.N.C., Wornell, G.W. 2004. Cooperative Diversity in Wireless Networks: Efficient Protocols and Outage Behavior. IEEE Trans. Inf. Theory 50 (12): 3062–80.
[18] Onat, F.A., Adinoyi, A., Fan, Y., Yanikomeroglu, H., Thompson, J.S., Marsland, I.D. 2008. Threshold Selection for SNR-Based Selective Digital Relaying in Cooperative Wireless Networks. IEEE Trans. on Wirel. Commun. 7 (11): 4226–4237.
[19] Ikki, S., M.H. Ahmed. 2007. Performance of Decode-and-Forward Cooperative Diversity Networks Over Nakagami-M Fading Channels. IEEE Global Telecommunications Conference, 4328–33 pp., USA.
[20] Onat, F.A, A., Fan, Yanikomeroglu, H., Poor, H.V. 2008. Threshold Based Relay Selection in Cooperative Wireless Networks. GLOBECOM - IEEE Global Telecommunications Conference, 1-5 pp., USA.
[21] F. Kara, H. Kaya, O. Erkaymaz, and E. Öztürk. Prediction of the optimal threshold value in df relay selection schemes based on artificial neural networks. In INnovations in Intelligent SysTems and Applications (INISTA), 2016 International Symposium on. IEEE, 2016.
[22] J. G. J. G. Andrews et al., “What will 5G be?,” IEEE J. Sel. Areas Commun., vol. 32, no. 6, pp. 1065–1082, 2014.
[23] A. Maaref and Y. Cao, “User Cooperation for 5G Wireless Access Networks,” Int. J. Wirel. Inf. Networks, vol. 22, no. 4, pp. 298–311, 2015.
[24] M. O. Hasna and M. S. Alouini, “Outage probability of multihop transmission over Nakagami fading channels,” IEEE Commun. Lett., vol. 7, no. 5, pp. 216–218, 2003.
[25] K. Xie, X. Wang, J. Wen, and J. Cao, “Cooperative Routing with Relay Assignment in Multiradio Multihop Wireless Networks,” IEEE/ACM Trans. Netw., vol. 24, no. 2, pp. 859–872, 2016.
[26] Çakar, E., Kara, F., ve Kaya, H. 2019. Error Analysis of Threshold Based Three-hop Device to Device (D2D) Communication Systems, 27th IEEE Signal Processing and Communications Applications Conference (SIU),
![]() |
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. |