Weak Signal Detection in 5G+ Systems: A Distributed Deep Learning Framework

Internet connected mobile devices in 5G and beyond (simply 5G+) systems are penetrating all aspects of people's daily life, transforming the way we conduct business and live. However, this rising trend has also posed unprecedented traffic burden on existing telecommunication infrastructure including cellular systems, consistently causing network congestion. Although additional spectrum resources have been allocated, exponentially increasing traffic tends to always outpace the added capacity. In order to increase the data rate and reduce the latency, 5G+ systems have heavily relied on hyperdensification and higher frequency bands, resulting in dramatically increased interference temperature, and consequently significantly more weak signals (i.e., signals with low Signal-to-Noise-plus-Interference (SINR) ratio). With traditional detection mechanisms, a large number of weak signals will not be detected, and hence be wasted, leading to poor throughput in 5G+ systems. To this end, in this paper, we develop an online weak-signal detection scheme to recover weak signals for mobile users so as to significantly boost their data rates without adding additional spectrum resource. Specifically, we first formulate weak signal detection as a high dimensional user-time signal matrix factorization problem and solve this problem by devising a novel learning model, called Dual-CNN Deep Matrix Factorization (DCDMF). Then, we design an online distributed learning framework to collaboratively train and update our proposed DCDMF model between an edge network and mobile users, with correctly decoded signals at users only. By conducting simulations on real-world traffic datasets, we demonstrate that our proposed weak signal detection scheme can achieve throughput gain of up to 3.12 times, with computing latency of 0.84 ms per KB signals on average.

[1]  Xi Li,et al.  5G-TRANSFORMER: Slicing and Orchestrating Transport Networks for Industry Verticals , 2018, IEEE Communications Magazine.

[2]  Y.-P. Eric Wang,et al.  Radio access for ultra-reliable and low-latency 5G communications , 2015, 2015 IEEE International Conference on Communication Workshop (ICCW).

[3]  H. Sebastian Seung,et al.  Unsupervised Learning by Convex and Conic Coding , 1996, NIPS.

[4]  Yehuda Koren,et al.  Matrix Factorization Techniques for Recommender Systems , 2009, Computer.

[5]  Shlomo Argamon,et al.  Effects of Age and Gender on Blogging , 2006, AAAI Spring Symposium: Computational Approaches to Analyzing Weblogs.

[6]  Tao Cheng,et al.  Weak Signal Detection Based on Deep Learning , 2019, ICMSSP 2019.

[7]  Florent Chatelain,et al.  Rank-based multiple change-point detection in multivariate time series , 2014, 2014 22nd European Signal Processing Conference (EUSIPCO).

[8]  Yann LeCun,et al.  The mnist database of handwritten digits , 2005 .

[9]  Mohamed-Slim Alouini,et al.  Wireless Communications Through Reconfigurable Intelligent Surfaces , 2019, IEEE Access.

[10]  Anderson R. Ramos,et al.  Mapping between Average SINR and Supported Throughput in 5G New Radio Small Cell Networks , 2019, 2019 22nd International Symposium on Wireless Personal Multimedia Communications (WPMC).

[11]  Gustavo Alonso,et al.  Log-normal shadowing meets SINR: A numerical study of Capacity in Wireless Networks , 2007, 2007 4th Annual IEEE Communications Society Conference on Sensor, Mesh and Ad Hoc Communications and Networks.

[12]  Jun Du,et al.  SNR-Based Progressive Learning of Deep Neural Network for Speech Enhancement , 2016, INTERSPEECH.

[13]  Matti Latva-aho,et al.  Key drivers and research challenges for 6G ubiquitous wireless intelligence , 2019 .

[14]  Amitava Ghosh,et al.  5 G Evolution : A View on 5 G Cellular Technology Beyond 3 GPP Release 15 , 2019 .

[15]  Amitabha Ghosh,et al.  5G Evolution: A View on 5G Cellular Technology Beyond 3GPP Release 15 , 2019, IEEE Access.

[16]  5G Enabling Technologies: Small Cells, Full-Duplex Communications, and Full-Dimension MIMO Technologies , 2019, 5G Physical Layer Technologies.

[17]  Ronen Basri,et al.  Fast Detection of Curved Edges at Low SNR , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[18]  Cisco Visual Networking Index: Forecast and Methodology 2016-2021.(2017) http://www.cisco.com/c/en/us/solutions/collateral/service-provider/visual- networking-index-vni/complete-white-paper-c11-481360.html. High Efficiency Video Coding (HEVC) Algorithms and Architectures https://jvet.hhi.fraunhofer. , 2017 .

[19]  Shujian Huang,et al.  Deep Matrix Factorization Models for Recommender Systems , 2017, IJCAI.

[20]  Ali H. Sayed,et al.  Spectrum Sensing by Cognitive Radios at Very Low SNR , 2009, GLOBECOM 2009 - 2009 IEEE Global Telecommunications Conference.

[21]  D.E. Dodds,et al.  Synchronization of Weak Indoor GPS Signals with Doppler Using a Segmented Matched Filter and Accumulation , 2007, 2007 Canadian Conference on Electrical and Computer Engineering.

[22]  Jorge Nocedal,et al.  On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima , 2016, ICLR.

[23]  Yuguang Fang,et al.  Augmenting Transmission Environments for Better Communications: Tunable Reflector Assisted MmWave WLANs , 2020, IEEE Transactions on Vehicular Technology.

[24]  Petar Popovski,et al.  Ultra-reliable communication in 5G wireless systems , 2014, 1st International Conference on 5G for Ubiquitous Connectivity.

[25]  Mykola Brych,et al.  Fractal geometry based resource allocation for 5G heterogeneous networks , 2015, 2015 Second International Scientific-Practical Conference Problems of Infocommunications Science and Technology (PIC S&T).

[26]  Xin Yu,et al.  LPI Radar Waveform Recognition Based on Deep Convolutional Neural Network Transfer Learning , 2019, Symmetry.

[27]  Klaus I. Pedersen,et al.  Joint Link Adaptation and Scheduling for 5G Ultra-Reliable Low-Latency Communications , 2018, IEEE Access.

[28]  P. Paatero,et al.  Positive matrix factorization: A non-negative factor model with optimal utilization of error estimates of data values† , 1994 .

[29]  Alex Krizhevsky,et al.  Learning Multiple Layers of Features from Tiny Images , 2009 .

[30]  Jure Leskovec,et al.  From amateurs to connoisseurs: modeling the evolution of user expertise through online reviews , 2013, WWW.

[31]  Paolo Santi,et al.  The Node Distribution of the Random Waypoint Mobility Model for Wireless Ad Hoc Networks , 2003, IEEE Trans. Mob. Comput..

[32]  Sergio Verdú,et al.  Minimum probability of error for asynchronous Gaussian multiple-access channels , 1986, IEEE Trans. Inf. Theory.

[33]  Halim Yanikomeroglu,et al.  SINR threshold lower bound for SINR-based call admission control in CDMA networks with imperfect power control , 2005, IEEE Communications Letters.