Deep Learning for Selection Between RF and VLC Bands in Device-to-Device Communication

This letter focuses on the selection between radio frequency (RF) and visible light communications (VLC) bands for users exchanging data directly with each other via device-to-device (D2D) communication. We target to maximize the energy efficiency of D2D communication while the outage is minimized. Since the VLC channel can vary quickly due to the possible changes in irradiance and incidence angles, we aim to reach a quick band selection decision in a multi-user scenario based only on the knowledge of the received power and sum interference from all D2D transmitters at the individual D2D receivers. The proposed solution is based on a deep neural network making an initial band selection decision. Then, based on the DNN’s output, a fast heuristic algorithm is proposed to further improve the band selection decision. The results show that the proposal reaches a close-to-optimal performance and outperforms the existing solutions in complexity, outage ratio, and energy efficiency.

[1]  I. White,et al.  High Bandwidth GaN-Based Micro-LEDs for Multi-Gb/s Visible Light Communications , 2016, IEEE Photonics Technology Letters.

[2]  Nikos D. Sidiropoulos,et al.  Learning-Based Antenna Selection for Multicasting , 2018, 2018 IEEE 19th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC).

[3]  Harald Haas,et al.  Why would 5G need optical wireless communications? , 2017, 2017 IEEE 28th Annual International Symposium on Personal, Indoor, and Mobile Radio Communications (PIMRC).

[4]  Sadiq Thomas,et al.  Visible Light Communication: A potential 5G and beyond Communication Technology , 2019, 2019 15th International Conference on Electronics, Computer and Computation (ICECCO).

[5]  Jean-Paul M. G. Linnartz,et al.  Modeling and Analysis of Transmitter Performance in Visible Light Communications , 2019, IEEE Transactions on Vehicular Technology.

[6]  Stanislav Zvanovec,et al.  Efficient Exploitation of Radio Frequency and Visible Light Communication Bands for D2D in Mobile Networks , 2019, IEEE Access.

[7]  Martin Fodslette Møller,et al.  A scaled conjugate gradient algorithm for fast supervised learning , 1993, Neural Networks.

[8]  Yeon-Ho Chung,et al.  Optical Repeater Assisted Visible Light Device-to-Device Communications , 2016 .

[9]  Lianfen Huang,et al.  Hybrid Architecture Performance Analysis for Device-to-Device Communication in 5G Cellular Network , 2015, Mob. Networks Appl..

[10]  Troels B. Sorensen,et al.  An Empirical LTE Smartphone Power Model with a View to Energy Efficiency Evolution , 2014 .

[11]  Zdenek Becvar,et al.  Resource Allocation for D2D Communication With Multiple D2D Pairs Reusing Multiple Channels , 2019, IEEE Wireless Communications Letters.

[12]  Junyi Li,et al.  Visible light communication: opportunities, challenges and the path to market , 2013, IEEE Communications Magazine.

[13]  Lajos Hanzo,et al.  Hybrid Positioning Aided Amorphous-Cell Assisted User-Centric Visible Light Downlink Techniques , 2016, IEEE Access.

[14]  Halim Yanikomeroglu,et al.  Device-to-device communication in 5G cellular networks: challenges, solutions, and future directions , 2014, IEEE Communications Magazine.

[15]  Geoffrey Ye Li,et al.  Power of Deep Learning for Channel Estimation and Signal Detection in OFDM Systems , 2017, IEEE Wireless Communications Letters.

[16]  Taghi M. Khoshgoftaar,et al.  Survey on deep learning with class imbalance , 2019, J. Big Data.

[17]  Paul de Kerret,et al.  Team Deep Neural Networks for Interference Channels , 2018, 2018 IEEE International Conference on Communications Workshops (ICC Workshops).

[18]  Yuefeng Ji,et al.  Game theory-based mode cooperative selection mechanism for device-to-device visible light communication , 2016 .