Publications

Conference publications

A. Anttonen, A. Mammela and T. Chen, “Hybrid User Association with Proactive Auxiliary Intervention for Multitier Cellular Networks,” 2019 IEEE 89th Vehicular Technology Conference (VTC2019-Spring), Kuala Lumpur, Malaysia, 2019, pp. 1-6.

doi: 10.1109/VTCSpring.2019.8746686

Abstract: In this paper, we consider a hybrid user association (HUA) problem for load balancing of multitier cellular networks. The proposed hierarchical HUA approach builds on a combination of decentralized user association (DUA) and auxiliary intervention of a central control unit (CCU). A major challenge with the CCU intervention is the time interval determined by a selected CCU control cycle during which the DUA must accept all users that satisfy the prevailing association criterion while proactively mitigating potential resource depletions. Consequently, the primary focus of this work is on relating the control cycle of the CCU intervention with the incipient resource depletions, according to a maximum allowed resource depletion probability. By uniquely combining a set of mathematical tools from stochastic geometry and queueing theory, we present a novel HUA method which evaluates the association bias values of the DUA according to a CCU-optimized load vector and enables tier-based resource depletion probability provisioning over finite control cycles. The trade-offs between the proposed HUA method and the standard DUA approach are demonstrated via network simulations with flow-level spatiotemporal dynamics.

keywords: {cellular radio;frequency allocation;optimisation;probability;queueing theory;resource allocation;stochastic processes;telecommunication traffic;proactive auxiliary intervention;multitier cellular networks;hybrid user association problem;load balancing;hierarchical HUA approach;central control unit;CCU intervention;selected CCU control cycle;incipient resource depletions;maximum allowed resource depletion probability;novel HUA method;association bias values;CCU-optimized load vector;tier-based resource depletion probability;finite control cycles;standard DUA approach;network simulations;prevailing association criterion;potential resource depletions;stochastic geometry;queueing theory;Spatiotemporal phenomena;Load modeling;Interference;Queueing analysis;Signal to noise ratio;Cellular networks;Stochastic processes},

URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8746686&isnumber=8746285

Boualouache, A., Soua, R., and Engel, T. SDN-based Pseudonym-Changing Strategy for Privacy Preservation in Vehicular Networks. 15th International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob’19). 2019.

Abstract: The pseudonym-changing approach is the de-factolocation privacy solution proposed by security standards toensure that drivers are not tracked during their journey. SeveralPseudonym Changing Strategies (PCSs) have been proposed tosynchronize Pseudonym Changing Processes (PCPs) between con-nected vehicles. However, most of the existing strategies are static,rigid and do not adapt to the vehicles’ context. In this paper, weexploit the Software Defined Network (SDN) paradigm to proposea context-aware pseudonym changing strategy (SDN-PCS) whereSDN controllers orchestrate the dynamic update of the securityparameters of the PCS. Simulation results demonstrate that SDN-PCS strategy outperforms typical static PCSs to perform efficientPCPs and protect the location privacy of vehicular network users.

Keywords: Vehicular networks ; location privacy ; pseudonym changing strategy ; SDN ; context-aware

URL: http://orbilu.uni.lu/handle/10993/40163 

Boualouache, A., Soua, R., and Engel, T. VPGA: an SDN-based Location Privacy Zones Placement Scheme for Vehicular Networks. 38th IEEE International Performance Computing and Communications Conference (IPCCC). 2019.

Abstract: Making personal data anonymous is crucial to ensure the adoption of connected vehicles. One of the privacy-sensitive information is location, which once revealed can be used by adversaries to track drivers during their journey. Vehicular Location Privacy Zones (VLPZs) is a promising approach to ensure unlinkability. These logical zones can be easily deployed over roadside infrastructures (RIs) such as gas station or electric charging stations. However, the placement optimization problem of VLPZs is NP-hard and thus an efficient allocation of VLPZs to these RIs is needed to avoid their overload and the degradation of the QoS provided within theses RIs. This work considers the optimal placement of the VLPZs and proposes a genetic-based algorithm in a software defined vehicular network to ensure minimized trajectory cost of involved vehicles and hence less consumption of their pseudonyms. The analytical evaluation shows that the proposed approach is cost-efficient and ensures a shorter response time.

Keywords: Vehicular Networks ; Security ; Location privacy Zones ; Software Defined Networks ; Genetic Algorithm

URL: http://hdl.handle.net/10993/40220

Chochliouros I.P. et al. (2019) Enhanced Mobile Broadband as Enabler for 5G: Actions from the Framework of the 5G-DRIVE Project. In: MacIntyre J., Maglogiannis I., Iliadis L., Pimenidis E. (eds) Artificial Intelligence Applications and Innovations. AIAI 2019. IFIP Advances in Information and Communication Technology, vol 560. Springer, Cham

doi: https://doi.org/10.1007/978-3-030-19909-8_3

Abstract: In the new fascinating era of 5G, new communication requirements set diverse challenges upon existing networks, both in terms of technologies and business models. One among the essential categories of the innovative 5G mobile network services is the enhanced Mobile Broadband (eMBB), mainly aiming to fulfill users’ demand for an increasingly digital lifestyle and focusing upon facilities that implicate high requirements for bandwidth. In this paper we have discussed eMBB as the first commercial use of the 5G technology. Then, we have focused upon the original context of the 5G-DRIVE research project between the EU and China, and we have identified essential features of the respective eMBB trials, constituting one of the corresponding core activities. In addition, we have discussed proposed scenarios and KPIs for assessing the scheduled experimental work, based on similar findings from other research and/or standardization activities.

Chochliouros I.P. et al. (2019) Testbeds for the Implementation of 5G in the European Union: The Innovative Case of the 5G-DRIVE Project. In: MacIntyre J., Maglogiannis I., Iliadis L., Pimenidis E. (eds) Artificial Intelligence Applications and Innovations. AIAI 2019. IFIP Advances in Information and Communication Technology, vol 560. Springer, Cham

doi: https://doi.org/10.1007/978-3-030-19909-8_7

Abstract: An essential part of the actual EU policy towards promoting and validating 5G applications and of related solutions is via the establishment of an explicit plan and of a detailed roadmap for trials, tests and experimental activities though dedicated testbeds, in parallel with the current research and development activities coming from the 5G-PPP framework. The present paper discusses the fundamental role of the proposed trials’ initiatives within the broader European framework for the establishment and the promotion of 5G and also analyses the corresponding streams as indispensable parts of the 5G-PPP context, aiming to support innovation and growth. In addition, as part of the broader initiative for trial actions we identify the case of the 5G-DRIVE project that aims to realise 5G deployment scenarios (i.e., enhanced Mobile Broadband and Vehicle-to-Everything communications), between the EU and China, by discussing the fundamental features of the respective trials sites.

Chochliouros, I., et al. Use Cases for developing enhanced Mobile Broadband Services for the promotion of 5G. Proceedings of the EuCNC 2019, Special Session No.3.

A. Kostopoulos et al., “5G Trial Cooperation Between EU and China,” 2019 IEEE International Conference on Communications Workshops (ICC Workshops), Shanghai, China, 2019, pp. 1-6.

doi: 10.1109/ICCW.2019.8756985

Abstract: The H2020 project 5G-DRIVE (5G HarmoniseD Research and TrIals for serVice Evolution between EU and China) cooperates with the Chinese twin project to trial and validate key functions of 5G networks operating at 3.5 GHz bands for enhanced Mobile Broadband (eMBB) and 3.5 GHz and 5.9 GHz bands for V2X scenarios. 5G-DRIVE will instil significant impact on the validation of standards and trigger the roll-out of real 5G networks and V2X innovative solutions driving new business opportunities and creating thereby new jobs and brand new business models. This paper presents the overall approach of 5G-DRIVE, the advances beyond the current state of the art for key 5G enabling technologies, as well as the considered use cases.

keywords: {5G mobile communication;broadband networks;cooperative communication;Chinese twin project;5G enabling technologies;5G trial cooperation;5G networks;V2X scenarios;5G harmonised research and trials for service evolution between EU and China;H2020 project 5G-DRIVE;enhanced Mobile Broadband;eMBB;frequency 3.5 GHz;frequency 5.9 GHz},

URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8756985&isnumber=8756635

S. Kukliński and L. Tomaszewski, “Key Performance Indicators for 5G network slicing,” 2019 IEEE Conference on Network Softwarization (NetSoft), Paris, France, 2019, pp. 464-471.

doi: 10.1109/NETSOFT.2019.8806692

Abstract: Network slicing technology will influence the way in which new networking solutions will be designed and operated. So far, network slicing is often linked with 5G networks, but this approach can be used to deploy any communications network(s) over a common infrastructure. The concept is still a subject of intensive research and standardization. From the point of view of network or service operator, it is necessary to define fundamental quantitative indicators for performance evaluation of the network slicing. Such parameters are often called Key Performance Indicators (KPIs). Network slicing KPIs should deal with network slicing run-time and life-cycle management and orchestration. The paper proposes a set of KPIs for network slicing taking into account the 5G network specifics.

keywords: {5G mobile communication;quality of service;telecommunication network management;virtualisation;networking solutions;communications network;network slicing run-time;life-cycle management;key performance indicators;5G network slicing technology;Network slicing;5G mobile communication;3GPP;Monitoring;Key performance indicator;Network slicing;KPI;orchestration;management;5G},

URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8806692&isnumber=8806619

S. Xue, Y. Ma, A. Li, N. Yi and R. Tafazolli, “On Unsupervised Deep Learning Solutions for Coherent MU-SIMO Detection in Fading Channels,” ICC 2019 – 2019 IEEE International Conference on Communications (ICC), Shanghai, China, 2019, pp. 1-6.

doi: 10.1109/ICC.2019.8761999

Abstract: In this paper, unsupervised deep learning solutions for multiuser single-input multiple-output (MU-SIMO) coherent detection are extensively investigated. According to the ways of utilizing the channel state information at the receiver side (CSIR), deep learning solutions are divided into two groups. One group is called equalization and learning, which utilizes the CSIR for channel equalization and then employ deep learning for multiuser detection (MUD). The other is called direct learning, which directly feeds the CSIR, together with the received signal, into deep neural networks (DNN) to conduct the MUD. It is found that the direct learning solutions outperform the equalization-and-learning solutions due to their better exploitation of the sequence detection gain. On the other hand, the direct learning solutions are not scalable to the size of SIMO networks, as current DNN architectures cannot efficiently handle many co-channel interferences. Motivated by this observation, we propose a novel direct learning approach, which can combine the merits of feedforward DNN and parallel interference cancellation. It is shown that the proposed approach trades off the complexity for the learning scalability, and the complexity can be managed due to the parallel network architecture.

keywords: {fading channels;interference suppression;multiuser channels;neural nets;SIMO communication;supervised learning;coherent MU-SIMO detection;fading channels;unsupervised deep learning solutions;multiuser single-input multiple-output coherent detection;channel state information;CSIR;channel equalization;multiuser detection;deep neural networks;direct learning solutions;sequence detection gain;direct learning approach;learning scalability;equalization-and-learning solutions;Deep learning;Fading channels;Receivers;MIMO communication;Training data;Complexity theory},

URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8761999&isnumber=8761046

Xue, Songyan & Li, A. & Wang, J. & Yi, N. & Ma, Y. & Tafazolli, Rahim & Dodgson, T.. (2019). To Learn or Not to Learn: Deep Learning Assisted Wireless Modem Design.

Abstract: Deep learning is driving a radical paradigm shift in wireless communications, all the way from the application layer down to the physical layer. Despite this, there is an ongoing debate as to what additional values artificial intelligence (or machine learning) could bring to us, particularly on the physical layer design; and what penalties there may have? These questions motivate a fundamental rethinking of the wireless modem design in the artificial intelligence era. Through several physical-layer case studies, we argue for a significant role that machine learning could play, for instance in parallel error-control coding and decoding, channel equalization, interference cancellation, as well as multiuser and multiantenna detection. In addition, we will also discuss the fundamental bottlenecks of machine learning as well as their potential solutions in this paper.

URL: https://arxiv.org/abs/1909.07791 

I.P. Chochliouros, A.S. Spiliopoulou, P. Lazaridis, A. Dardamanis, Z. Zaharis and A. Kostopoulos . (2020). Dynamic Network Slicing: Challenges and Opportunities. 5G-PINE 2020 Workshop at 16th Int. Conference on Artificial Intelligence Applications and Innovations

Xianfu Chen, Zhifeng Zhao, Celimuge Wu, Tao Chen, Honggang Zhang, Mehdi Bennis. (2020). Secrecy Preserving in Stochastic Resource Orchestration for Multi-Tenancy Network Slicing. IEEE Goblecom 2019

Abstract: Network slicing is a proposing technology to support diverse services from mobile users (MUs) over a common physical network infrastructure. In this paper, we consider radio access network (RAN)-only slicing, where the physical RAN is tailored to accommodate both computation and communication functionalities. Multiple service providers (SPs, i.e., multiple tenants) compete with each other to bid for a limited number of channels across the scheduling slots, aiming to provide their subscribed MUs the opportunities to access the RAN slices. An eavesdropper overhears data transmissions from the MUs. We model the interactions among the non-cooperative SPs as a stochastic game, in which the objective of a SP is to optimize its own expected long-term payoff performance. To approximate the Nash equilibrium solutions, we first construct an abstract stochastic game using the channel auction outcomes. Then we linearly decompose the per-SP Markov decision process to simplify the decision-makings and derive a deep reinforcement learning based scheme to approach the optimal abstract control policies. TensorFlow-based experiments verify that the proposed scheme outperforms the three baselines and yields the best performance in average utility per MU per scheduling slot.

URL: https://arxiv.org/abs/1908.07326

Xianfu Chen, Celimuge Wu, Tao Chen, Nan Wu, Honggang Zhang, Yusheng Ji. (2019). Age of Information-aware Multi-tenant Resource Orchestration in Network Slicing. IEEE CBDCom 2019 (Best paper award)

Abstract: To satisfy diverse services from mobile users (MUs) over a common network infrastructure, network slicing is envisioned as a promising technology. This paper considers radio access network (RAN)-only slicing, where the physical RAN is judiciously tailored to accommodate computation and communication functionalities. Multiple service providers (SPs, a.k.a., tenants) compete for a limited number of channels across the discrete scheduling slots in order to serve their respective subscribed MUs. From a MU perspective, the age of information of data packets from traditional mobile services and the energy consumption at mobile device are of practical importance. We characterize the interactions among the SPs via a stochastic game, in which a SP selfishly maximizes its own expected long-term payoff. To approximate the Nash equilibrium solutions, we build an abstract stochastic game exploring the local information of SPs. Furthermore, the decision-making process at a SP can be much simplified by linearly decomposing the per-SP Markov decision process, for which we derive a deep reinforcement learning based scheme to find the optimal abstract control policies. TensorFlow-based experiments validate our studies and show that the proposed scheme outperforms the three baselines and yields the best performance in average utility.

URL: https://ieeexplore.ieee.org/document/8890362

Xianfu Chen, Celimuge Wu, Tao Chen, Honggang Zhang, Zhi Liu, Yan Zhang, Mehdi Bennis. (2020). Age of information-aware radio resource management in vehicular networks: A proactive deep reinforcement learning perspective. IEEE Transactions on Wireless Communications Vol.19, issue 4, pp 2268 – 2281

doi: 10.1109/TWC.2019.2963667

Abstract: In this paper, we investigate the problem of age of information (AoI)-aware radio resource management for expected long-term performance optimization in a Manhattan grid vehicle-to-vehicle network. With the observation of global network state at each scheduling slot, the roadside unit (RSU) allocates the frequency bands and schedules packet transmissions for all vehicle user equipment-pairs (VUE-pairs). We model the stochastic decision-making procedure as a discrete-time single-agent Markov decision process (MDP). The technical challenges in solving the optimal control policy originate from high spatial mobility and temporally varying traffic information arrivals of the VUE-pairs. To make the problem solving tractable, we first decompose the original MDP into a series of per-VUE-pair MDPs. Then we propose a proactive algorithm based on long short-term memory and deep reinforcement learning techniques to address the partial observability and the curse of high dimensionality in local network state space faced by each VUE-pair. With the proposed algorithm, the RSU makes the optimal frequency band allocation and packet scheduling decision at each scheduling slot in a decentralized way in accordance with the partial observations of the global network state at the VUE-pairs. Numerical experiments validate the theoretical analysis and demonstrate the significant performance improvements from the proposed algorithm.

URL: https://arxiv.org/abs/1908.02047

Yixue Hao, Yingying Jiang, Tao Chen, Donggang Cao, Min Chen. (2019). iTaskOffloading: Intelligent Task Offloading for a Cloud-Edge Collaborative System.IEEE Network Vol. 33, issue 5 82 – 88

doi: 10.1109/MNET.001.1800486

Abstract: With the development of technologies such as the Internet of Things and artificial intelligence, mobile applications are becoming more and more intelligent. Compared to traditional applications realized by mobile cloud computing technology, these novel applications have a higher requirement for a task offloading scheme. However, the traditional task offloading schemes are hard pressed to meet latency and personalization requirements of these new applications. For intelligent application, how to realize personalized and fine-grained task offloading is still a challenging problem. Therefore, we propose a scheme called intelligent task offloading (iTaskOffloading) for a cloud-edge collaborative system, which can provide personalized task offloading. To be specific, we first propose the architecture of iTaskOffloading which includes the local device layer, edge cloud layer, remote cloud layer, and cognitive engine. Then we analyze the method of iTaskOffloading, which contains coarse-grained computing and fine-grained computing. Finally, we build a testbed to evaluate the proposed iTaskOffloading scheme using a typical intelligent application of emotion detection. The experimental results show that compared to the traditional cloud computing scheme, iTaskOffloading has less task duration.

URL: https://ieeexplore.ieee.org/document/8863731

Joint publications

Tao Chen, Matti Kutila, Yinxiang Zheng, Wei Dei, Jiangzhou Wang (2020). Key Scenarios and Technologies in EU-China V2X Trial Cooperation. ZTE communications

M. Kutila, P. Pyykonen, Q. Huang, W. Deng, W. Lei and E. Pollakis, “C-V2X Supported Automated Driving,” 2019 IEEE International Conference on Communications Workshops (ICC Workshops), Shanghai, China, 2019, pp. 1-5.

doi: 10.1109/ICCW.2019.8756871

Abstract: Automated driving is expected to improve road safety and traffic efficiency. Host vehicle onboard sensing systems typically sense the environment up to 250 m ahead of the vehicle. Today’s LiDARs can see approximately 120 m, and recognition of small objects, such as animals or dropped cargo, however, today reliably drop when range is more than 50m. Connected driving adds an electronic horizon to the onboard sensing system which could extend the sensing range and greatly improves the efficiency. Therefore, collaborative sensing in which the vehicle exchanges not only status messages but also real data has recently been intensively discussed. Current cellular 3G/4G networks have enhanced the downlink capacity for sharing large data blocks. However, uplink is limited and therefore vehicles are unable to share point clouds of what they see in front. This article investigates the opportunities of 5G-based cellular vehicle-to-everything (C-V2X) collaborative sensing based on the results of trials conducted at test sites in China and Finland. The results indicate that the round-trip is stable (<; 60 ms) even when exchanging 1 MB/s between vehicles. Finally, the automotive industry perspective is taken into account in identifying and prioritizing potential use case scenarios for utilizing 5G based connected driving applications.

keywords: {3G mobile communication;4G mobile communication;cellular radio;optical radar;road safety;road vehicles;vehicular ad hoc networks;traffic efficiency;host vehicle;LiDARs;animals;dropped cargo;electronic horizon;onboard sensing system;sensing range;collaborative sensing;current cellular 3G/4G networks;downlink capacity;data blocks;point clouds;5G-based cellular vehicle-to-everything;connected driving applications;V2X Supported Automated Driving;road safety;status messages;byte rate 1.0 MByte/s},

URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8756871&isnumber=8756635

Journal publications

S. Noor, P. Assimakopoulos and N. J. Gomes, “A Flexible Subcarrier Multiplexing System With Analog Transport and Digital Processing for 5G (and Beyond) Fronthaul,” in Journal of Lightwave Technology, vol. 37, no. 14, pp. 3689-3700, 15 July15, 2019.

doi: 10.1109/JLT.2019.2918215

Abstract: A flexible subcarrier multiplexing system combining analog transport with digital domain processing is presented. By making use of bandpass sampling and applying a systematic mapping of signals into available Nyquist zones, the multiplexing system is able to present multiple signals at the same intermediate frequency at the remote site. This simplifies the processing required for multiple antenna systems. We further propose the use of track-and-hold amplifiers at the remote site. These elements are used to extend the mapping to a mapping hierarchy, offering flexibility in frequency placement of signals and relaxation of analog-to-digital converter bandwidth and sampling rate constraints. The system allows the transport of different numerologies in a number of next generation radio access network scenarios. Experimental results for large signal multiplexes with both generic and 5th-generation mobile numerologies show error-vector magnitude performance well within specifications, validating the proposed system. Simulation results from a system model matched to these experimental results provide performance predictions for larger signal multiplexes and larger bandwidths.

keywords: {5G mobile communication;analogue-digital conversion;radio access networks;radio-over-fibre;signal sampling;subcarrier multiplexing;digital domain processing;bandpass sampling;systematic mapping;available Nyquist zones;remote site;multiple antenna systems;mapping hierarchy;analog-to-digital converter bandwidth;sampling rate constraints;system model;digital processing;5G fronthaul;analog transport;flexible subcarrier multiplexing system;error-vector magnitude;next generation radio access network scenarios;signal multiplexes;track-and-hold amplifiers;Multiplexing;Bandwidth;5G mobile communication;Frequency-domain analysis;Amplitude modulation;MIMO communication;Next generation networking;Digital signal processing;massive-MIMO (mMIMO);millimeter wave (mmW);mobile fronthaul;radio-over-fiber;subcarrier multiplexing (SCM)},

URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8720052&isnumber=8744414

S. Noor, P. Assimakopoulos, M. Wang, H.A. Abdulsada, N. Genay, L.A. Neto, P. Chanclou, N.J. Gomes. (2020). Comparison of Digital Signal Processing Approaches for Subcarrier Multiplexed 5G and Beyond Analog Fronthaul. IEEE/OSA Journal of Optical Communications and Networking, vol. 12, no.  pp. 62-71.

doi: 10.1364/JOCN.381341

Abstract: Analog fronthaul transport architectures with digital signal processing at the end stations are promising as they have the potential to achieve high spectral efficiencies, increased flexibility and reduced latency. In this paper, two digital techniques for frequency domain multiplexing/de-multiplexing large numbers of channels are contrasted: one operates on the pre-Inverse Fast Fourier Transform (IFFT) “frequency-domain” samples while the other does so on the post-IFFT “time-domain” samples. Performance criteria including computational complexity and sampling rate requirements are used in the comparison. Following modeling and simulation of the techniques, implemented within a radio-over-fiber transport architecture, error vector magnitude performance estimates are obtained. These results show that each technique has performance advantages under specific channel transport scenarios.

URL: https://kar.kent.ac.uk/79467/

E.Moutaly, P. Assimakopoulos, S. Noor, S. Faci, A. Billabert, N. J. Gomes, M. L. Diakité, C. Browning, C. Algani. (2019). Phase Modulated Radio-over-Fiber for Efficient 5G Fronthaul Uplink. Journal of Lightwave Technology vol. 37, no. 23 pp. 5821 – 5832

doi: 10.1109/JLT.2019.2940200

Abstract: AAnalog radio-over-fiber technology is gaining interest as a potential candidate for radio signal transport over the future fronthaul section of the 5th generation (and beyond) radio access network. In this paper, we propose a radio-over-fiber fronthaul with intensity modulation in the downlink and phase modulation with interferometric detection in the uplink, for simplified and power efficient remote units. We conduct an experimental investigation and verification of theoretical and simulation models of the performance of the phase-modulated uplink and demonstrate the ability of such an architecture to transport single-channel and multi-channel 5G-type radio waveforms. Experimentally verified data rates of 4.3 Gbps and simulation-based predictions, using a well matched-to-measurements model of the uplink, of 12.4 Gbps are presented, with error-vector magnitude performance well within relevant standard specifications for 64-QAM.

URL: https://kar.kent.ac.uk/76432/

Tao Chen, Matti Kutila, Yinxiang Zheng, Wei Dei, Jiangzhou Wang (2020). Key Scenarios and Technologies in EU-China V2X Trial Cooperation. ZTE communications

S. Xue, A. Li, J. Wang, N. Yi, Y. Ma, R. Tafazolli and T. E. Dodgson. (2019). To learn or not to learn: deep learning assisted wireless modem design. ZTE Communications vol. 17, no. 4, December 2019 pp. 3-11

Abstract: Deep learning is driving a radical paradigm shift in wireless communications, all the way from the application layer down to the physical layer. Despite this, there is an ongoing debate as to what additional values artificial intelligence (or machine learning) could bring to us, particularly on the physical layer design; and what penalties there may have? These questions motivate a fundamental rethinking of the wireless modem design in the artificial intelligence era. Through several physical-layer case studies, we argue for a significant role that machine learning could play, for instance in parallel error-control coding and decoding, channel equalization, interference cancellation, as well as multiuser and multiantenna detection. In addition, we discuss the fundamental bottlenecks of machine learning as well as their potential solutions in this paper.

URL: https://www.zte.com.cn/global/about/magazine/zte-communications/2019/en201904/specialtopic/en201904002.html

Other publications and articles

Author: Latif Ladid (University of Luxembourg, IPv6 Forum President)

Publication & Date: InterComms: International Communications Project (Issue 31 – 2019), 2019.

Abstract: This publication presents a thorough overview of the 5G-DRIVE project, including the objectives, project concept, trial sites, and expected impact.

LinkWeb

Author: 5G-DRIVE consortium

Publication & Date: European 5G Annual Journal (2019)

Link: Coming soon.