When 5G Meets Deep Learning: A Systematic Review

This last decade, the amount of data exchanged on the Internet increased by over a staggering factor of 100, and is expected to exceed well over the 500 exabytes by 2020. This phenomenon is mainly due to the evolution of high-speed broadband Internet and, more specifically, the popularization and wide spread use of smartphones and associated accessible data plans. Although 4G with its long-term evolution (LTE) technology is seen as a mature technology, there is continual improvement to its radio technology and architecture such as in the scope of the LTE Advanced standard, a major enhancement of LTE. However, for the long run, the next generation of telecommunication (5G) is considered and is gaining considerable momentum from both industry and researchers. In addition, with the deployment of the Internet of Things (IoT) applications, smart cities, vehicular networks, e-health systems, and Industry 4.0, a new plethora of 5G services has emerged with very diverging and technologically challenging design requirements. These include high mobile data volume per area, high number of devices connected per area, high data rates, longer battery life for low-power devices, and reduced end-to-end latency. Several technologies are being developed to meet these new requirements, and each of these technologies brings its own design issues and challenges. In this context, deep learning models could be seen as one of the main tools that can be used to process monitoring data and automate decisions. As these models are able to extract relevant features from raw data (images, texts, and other types of unstructured data), the integration between 5G and DL looks promising and one that requires exploring. As main contribution, this paper presents a systematic review about how DL is being applied to solve some 5G issues. Differently from the current literature, we examine data from the last decade and the works that address diverse 5G specific problems, such as physical medium state estimation, network traffic prediction, user device location prediction, self network management, among others. We also discuss the main research challenges when using deep learning models in 5G scenarios and identify several issues that deserve further consideration.

[1]  Jae-Mo Kang,et al.  Deep Learning-Based MIMO-NOMA With Imperfect SIC Decoding , 2020, IEEE Systems Journal.

[2]  Carlos Hernan Tobar Arteaga,et al.  A Scaling Mechanism for an Evolved Packet Core Based on Network Functions Virtualization , 2020, IEEE Transactions on Network and Service Management.

[3]  Jinhuan Zhang,et al.  5G-Enabled Fault Detection and Diagnostics: How Do We Achieve Efficiency? , 2020, IEEE Internet of Things Journal.

[4]  Pan Li,et al.  Channel State Information Prediction for 5G Wireless Communications: A Deep Learning Approach , 2020, IEEE Transactions on Network Science and Engineering.

[5]  Ye Ouyang,et al.  Application Behaviors Driven Self-Organizing Network (SON) for 4G LTE Networks , 2020, IEEE Transactions on Network Science and Engineering.

[6]  Chin-Feng Lai,et al.  Q-learning based collaborative cache allocation in mobile edge computing , 2020, Future Gener. Comput. Syst..

[7]  Hao Jiang,et al.  Deep learning based mobile data offloading in mobile edge computing systems , 2019, Future Gener. Comput. Syst..

[8]  Dejiao Niu,et al.  A Novel Distributed Duration-Aware LSTM for Large Scale Sequential Data Analysis , 2019, Big Data.

[9]  Sihai Zhang,et al.  Mobile Edge Computing-Based Data-Driven Deep Learning Framework for Anomaly Detection , 2019, IEEE Access.

[10]  Metin Öztürk,et al.  A novel deep learning driven, low-cost mobility prediction approach for 5G cellular networks: The case of the Control/Data Separation Architecture (CDSA) , 2019, Neurocomputing.

[11]  Can Fahrettin Koyuncu,et al.  DeepDistance: A Multi-task Deep Regression Model for Cell Detection in Inverted Microscopy Images , 2019, Medical Image Anal..

[12]  Leonel Sousa,et al.  Deep Learning Architectures for Accurate Millimeter Wave Positioning in 5G , 2019, Neural Processing Letters.

[13]  Chaojin Qing,et al.  Deep Learning for CSI Feedback Based on Superimposed Coding , 2019, IEEE Access.

[14]  Sameer Sharma,et al.  RAN Resource Usage Prediction for a 5G Slice Broker , 2019, MobiHoc.

[15]  Eduardo Grampín,et al.  Machine Learning Aided Network Slicing , 2019, 2019 21st International Conference on Transparent Optical Networks (ICTON).

[16]  Branka Vucetic,et al.  Deep Learning for Hybrid 5G Services in Mobile Edge Computing Systems: Learn From a Digital Twin , 2019, IEEE Transactions on Wireless Communications.

[17]  Guan Gui,et al.  Behavioral Modeling and Linearization of Wideband RF Power Amplifiers Using BiLSTM Networks for 5G Wireless Systems , 2019, IEEE Transactions on Vehicular Technology.

[18]  Gang Feng,et al.  Intelligent Resource Scheduling for 5G Radio Access Network Slicing , 2019, IEEE Transactions on Vehicular Technology.

[19]  Marc Molla Rosello,et al.  Multi-path Scheduling with Deep Reinforcement Learning , 2019, 2019 European Conference on Networks and Communications (EuCNC).

[20]  Neng Ye,et al.  Deep Learning-Aided Constellation Design for Downlink NOMA , 2019, 2019 15th International Wireless Communications & Mobile Computing Conference (IWCMC).

[21]  Junxing Zhang,et al.  GANSlicing: A GAN-Based Software Defined Mobile Network Slicing Scheme for IoT Applications , 2019, ICC 2019 - 2019 IEEE International Conference on Communications (ICC).

[22]  Tapani Ristaniemi,et al.  Secrecy Analysis and Learning-Based Optimization of Cooperative NOMA SWIPT Systems , 2019, 2019 IEEE International Conference on Communications Workshops (ICC Workshops).

[23]  Khalid M. Hosny,et al.  New vertical handover prediction schemes for LTE-WLAN heterogeneous networks , 2019, PloS one.

[24]  Usama S. Mohamed,et al.  Deep Learning-Based Relay Selection In D2D Millimeter Wave Communications , 2019, 2019 International Conference on Computer and Information Sciences (ICCIS).

[25]  Marco Fiore,et al.  DeepCog: Cognitive Network Management in Sliced 5G Networks with Deep Learning , 2019, IEEE INFOCOM 2019 - IEEE Conference on Computer Communications.

[26]  Huarui Yin,et al.  Deep Learning Based Antenna Array Fault Detection , 2019, 2019 IEEE 89th Vehicular Technology Conference (VTC2019-Spring).

[27]  Chang Liu,et al.  Regression Task on Big Data with Convolutional Neural Network , 2019, AMLTA.

[28]  Shugong Xu,et al.  Dynamic Carrier to MCPA Allocation for Energy Efficient Communication: Convex Relaxation Versus Deep Learning , 2019, IEEE Transactions on Green Communications and Networking.

[29]  Symeon Chatzinotas,et al.  Learning-Assisted Optimization for Energy-Efficient Scheduling in Deadline-Aware NOMA Systems , 2019, IEEE Transactions on Green Communications and Networking.

[30]  Yuefeng Ji,et al.  Proactive Dynamic Network Slicing with Deep Learning Based Short-Term Traffic Prediction for 5G Transport Network , 2019, 2019 Optical Fiber Communications Conference and Exhibition (OFC).

[31]  T. Imai,et al.  Radio Propagation Prediction Model Using Convolutional Neural Networks by Deep Learning , 2019, 2019 13th European Conference on Antennas and Propagation (EuCAP).

[32]  Fredrik Gunnarsson,et al.  Inter-Frequency Radio Signal Quality Prediction for Handover, Evaluated in 3GPP LTE , 2019, 2019 IEEE 89th Vehicular Technology Conference (VTC2019-Spring).

[33]  Rakesh Misra,et al.  Towards Self-Driving Radios: Physical-Layer Control using Deep Reinforcement Learning , 2019, HotMobile.

[34]  Rahim Tafazolli,et al.  Unsupervised Deep Learning for MU-SIMO Joint Transmitter and Noncoherent Receiver Design , 2019, IEEE Wireless Communications Letters.

[35]  Gaojie Chen,et al.  A Deep Learning-Based Approach to Power Minimization in Multi-Carrier NOMA With SWIPT , 2019, IEEE Access.

[36]  Hung-Yu Wei,et al.  QoE-aware Q-learning based approach to dynamic TDD uplink-downlink reconfiguration in indoor small cell networks , 2019, Wireless Networks.

[37]  Masoud Ardakani,et al.  Decision Directed Channel Estimation Based on Deep Neural Network $k$ -Step Predictor for MIMO Communications in 5G , 2019, IEEE Journal on Selected Areas in Communications.

[38]  Brian L. Evans,et al.  Deep Learning in Downlink Coordinated Multipoint in New Radio Heterogeneous Networks , 2018, IEEE Wireless Communications Letters.

[39]  Andreas F. Molisch,et al.  Exploiting Wireless Channel State Information Structures Beyond Linear Correlations: A Deep Learning Approach , 2018, IEEE Communications Magazine.

[40]  Pinyi Ren,et al.  Deep Learning-Based Big Data-Assisted Anomaly Detection in Cellular Networks , 2018, 2018 IEEE Global Communications Conference (GLOBECOM).

[41]  Sreeram Kannan,et al.  LEARN Codes: Inventing Low-Latency Codes via Recurrent Neural Networks , 2018, ICC 2019 - 2019 IEEE International Conference on Communications (ICC).

[42]  Daqing Zhang,et al.  Deep mobile traffic forecast and complementary base station clustering for C-RAN optimization , 2018, J. Netw. Comput. Appl..

[43]  Nei Kato,et al.  A Deep-Learning-Based Radio Resource Assignment Technique for 5G Ultra Dense Networks , 2018, IEEE Network.

[44]  Shugong Xu,et al.  A Unified Deep Learning Based Polar-LDPC Decoder for 5G Communication Systems , 2018, 2018 10th International Conference on Wireless Communications and Signal Processing (WCSP).

[45]  Yang Li,et al.  A ResNet-DNN based Channel Estimation and Equalization Scheme in FBMC/OQAM Systems , 2018, 2018 10th International Conference on Wireless Communications and Signal Processing (WCSP).

[46]  Juraj Gazda,et al.  Deep Learning Based Massive MIMO Beamforming for 5G Mobile Network , 2018, 2018 IEEE 4th International Symposium on Wireless Systems within the International Conferences on Intelligent Data Acquisition and Advanced Computing Systems (IDAACS-SWS).

[47]  Jun Yin,et al.  A Self-Interference Cancellation Method Based on Deep Learning for Beyond 5G Full-Duplex System , 2018, 2018 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC).

[48]  Ekram Hossain,et al.  Deep Learning for Radio Resource Allocation in Multi-Cell Networks , 2018, IEEE Network.

[49]  Xiaohu You,et al.  An Enhanced SCMA Detector Enabled by Deep Neural Network , 2018, 2018 IEEE/CIC International Conference on Communications in China (ICCC).

[50]  Ahmed H. Zahran,et al.  Beyond throughput: a 4G LTE dataset with channel and context metrics , 2018, MMSys.

[51]  Shancang Li,et al.  5G Internet of Things: A survey , 2018, J. Ind. Inf. Integr..

[52]  Zhifeng Zhao,et al.  Deep Learning-Based Intelligent Dual Connectivity for Mobility Management in Dense Network , 2018, 2018 IEEE 88th Vehicular Technology Conference (VTC-Fall).

[53]  Dongfeng Yuan,et al.  Citywide Cellular Traffic Prediction Based on Densely Connected Convolutional Neural Networks , 2018, IEEE Communications Letters.

[54]  Félix J. García Clemente,et al.  Dynamic management of a deep learning-based anomaly detection system for 5G networks , 2018, Journal of Ambient Intelligence and Humanized Computing.

[55]  Özal Yildirim,et al.  A novel wavelet sequence based on deep bidirectional LSTM network model for ECG signal classification , 2018, Comput. Biol. Medicine.

[56]  Bruno Volckaert,et al.  Anomaly detection for Smart City applications over 5G low power wide area networks , 2018, NOMS 2018 - 2018 IEEE/IFIP Network Operations and Management Symposium.

[57]  Majid Sarrafzadeh,et al.  ECG Heartbeat Classification: A Deep Transferable Representation , 2018, 2018 IEEE International Conference on Healthcare Informatics (ICHI).

[58]  Leonel Sousa,et al.  Beamformed Fingerprint Learning for Accurate Millimeter Wave Positioning , 2018, 2018 IEEE 88th Vehicular Technology Conference (VTC-Fall).

[59]  Narciso García,et al.  Event-Based Vision Meets Deep Learning on Steering Prediction for Self-Driving Cars , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[60]  Hamed Haddadi,et al.  Deep Learning in Mobile and Wireless Networking: A Survey , 2018, IEEE Communications Surveys & Tutorials.

[61]  Vladlen Koltun,et al.  An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling , 2018, ArXiv.

[62]  Woongsup Lee,et al.  A Novel PAPR Reduction Scheme for OFDM System Based on Deep Learning , 2018, IEEE Communications Letters.

[63]  Félix J. García Clemente,et al.  A Self-Adaptive Deep Learning-Based System for Anomaly Detection in 5G Networks , 2018, IEEE Access.

[64]  Joohyung Lee,et al.  Deep Learning Based Pilot Allocation Scheme (DL-PAS) for 5G Massive MIMO System , 2018, IEEE Communications Letters.

[65]  Nam-I Kim,et al.  Deep Learning-Aided SCMA , 2018, IEEE Communications Letters.

[66]  Geoffrey Y. Li,et al.  Machine Learning for Vehicular Networks: Recent Advances and Application Examples , 2017, IEEE Vehicular Technology Magazine.

[67]  Ye Ouyang,et al.  APP-SON: Application characteristics-driven SON to optimize 4G/5G network performance and quality of experience , 2017, 2017 IEEE International Conference on Big Data (Big Data).

[68]  Mandar Kulkarni,et al.  Deep Learning Based Car Damage Classification , 2017, 2017 16th IEEE International Conference on Machine Learning and Applications (ICMLA).

[69]  Ashok Kumar Reddy Chavva,et al.  Deep Learning Based Link Failure Mitigation , 2017, 2017 16th IEEE International Conference on Machine Learning and Applications (ICMLA).

[70]  Marc Peter Deisenroth,et al.  Deep Reinforcement Learning: A Brief Survey , 2017, IEEE Signal Processing Magazine.

[71]  Jasper Goseling,et al.  Optimal Geographical Caching in Heterogeneous Cellular Networks with Nonhomogeneous Helpers , 2017, ArXiv.

[72]  Chih-Wei Huang,et al.  A study of deep learning networks on mobile traffic forecasting , 2017, 2017 IEEE 28th Annual International Symposium on Personal, Indoor, and Mobile Radio Communications (PIMRC).

[73]  Symeon Chatzinotas,et al.  A deep learning approach for optimizing content delivering in cache-enabled HetNet , 2017, 2017 International Symposium on Wireless Communication Systems (ISWCS).

[74]  Qingzeng Song,et al.  Using Deep Learning for Classification of Lung Nodules on Computed Tomography Images , 2017, Journal of healthcare engineering.

[75]  Alexander J. Smola,et al.  Latent LSTM Allocation: Joint Clustering and Non-Linear Dynamic Modeling of Sequence Data , 2017, ICML.

[76]  Roberto Cipolla,et al.  Geometric Loss Functions for Camera Pose Regression with Deep Learning , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[77]  Xiaohu Ge,et al.  5G Software Defined Vehicular Networks , 2017, IEEE Communications Magazine.

[78]  Moses Garuba,et al.  Big Data Analytics for User-Activity Analysis and User-Anomaly Detection in Mobile Wireless Network , 2017, IEEE Transactions on Industrial Informatics.

[79]  Kaibin Huang,et al.  Cache-Enabled Heterogeneous Cellular Networks: Optimal Tier-Level Content Placement , 2016, IEEE Transactions on Wireless Communications.

[80]  Yuanyuan Qiao,et al.  An improved Markov method for prediction of user mobility , 2016, 2016 12th International Conference on Network and Service Management (CNSM).

[81]  Yuanyuan Qiao,et al.  User location prediction with energy efficiency model in the Long Term‐Evolution network , 2016, Int. J. Commun. Syst..

[82]  Ahmed El Oualkadi,et al.  A Hybrid Adaptive Coding and Decoding Scheme for Multi-hop Wireless Sensor Networks , 2016, Wireless Personal Communications.

[83]  Dayong Wang,et al.  Deep Learning for Identifying Metastatic Breast Cancer , 2016, ArXiv.

[84]  Zhifeng Zhao,et al.  The Learning and Prediction of Application-Level Traffic Data in Cellular Networks , 2016, IEEE Transactions on Wireless Communications.

[85]  Yu Xue,et al.  Text classification based on deep belief network and softmax regression , 2016, Neural Computing and Applications.

[86]  Vijay K. Bhargava,et al.  Energy Efficiency in Massive MIMO-Based 5G Networks: Opportunities and Challenges , 2015, IEEE Wireless Communications.

[87]  Marco De Nadai,et al.  A multi-source dataset of urban life in the city of Milan and the Province of Trentino , 2015, Scientific Data.

[88]  Vinicius C. M. Borges,et al.  Aspirations, challenges, and open issues for software-based 5G networks in extremely dense and heterogeneous scenarios , 2015, EURASIP J. Wirel. Commun. Netw..

[89]  Jürgen Schmidhuber,et al.  LSTM: A Search Space Odyssey , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[90]  Emanuel Ferreira Coutinho,et al.  Elasticity in cloud computing: a survey , 2014, annals of telecommunications - annales des télécommunications.

[91]  Alejandro Zunino,et al.  An empirical comparison of botnet detection methods , 2014, Comput. Secur..

[92]  Lida Xu,et al.  The internet of things: a survey , 2014, Information Systems Frontiers.

[93]  Daqiang Zhang,et al.  MPaaS: Mobility prediction as a service in telecom cloud , 2013, Information Systems Frontiers.

[94]  Thomas L. Marzetta,et al.  Pilot contamination problem in multi-cell TDD systems , 2009, 2009 IEEE International Symposium on Information Theory.

[95]  Giuseppe Caire,et al.  Multiuser MIMO Achievable Rates With Downlink Training and Channel State Feedback , 2007, IEEE Transactions on Information Theory.

[96]  Jie Zhang,et al.  Accurate Fault Location Using Deep Belief Network for Optical Fronthaul Networks in 5G and Beyond , 2019, IEEE Access.

[97]  Feng Zhao,et al.  Multi-Slot Spectrum Auction in Heterogeneous Networks Based on Deep Feedforward Network , 2018, IEEE Access.

[98]  Katsutoshi Kusume,et al.  Updated scenarios , requirements and KPIs for 5 G mobile and wireless system with recommendations for future investigations , 2015 .

[99]  Geoffrey E. Hinton,et al.  Deep Learning , 2015 .

[100]  Luis M. Correia,et al.  International Symposium on Wireless Communication Systems (ISWCS) , 2008, ISWCS 2008.