Deep learning based physical layer security for terrestrial communications in 5G and beyond networks: A survey

The key principle of physical layer security (PLS) is to permit the secure transmission of confidential data using efficient signal-processing techniques. Also, deep learning (DL) has emerged as a viable option to address various security concerns and enhance the performance of conventional PLS techniques in wireless networks. DL is a strong data exploration technique which can be used to learn normal and abnormal behavior of 5G and beyond wireless networks in an insecure channel paradigm. Also, since DL techniques can successfully predict future new instances by learning from existing ones, they can successfully predict new attacks, which frequently involve mutations of earlier attacks. Thus, motivated by the benefits of DL and PLS, this survey provides a comprehensive review that overviews how DL-based PLS techniques can be employed for solving various security concerns in 5G and beyond networks. The survey begins with an overview of physical layer threats and security concerns in 5G and beyond networks. Then, we present a detailed analysis of various DL and deep reinforcement learning (DRL) techniques that are applicable to PLS applications. We present the specific use-cases of PLS design for each type of technique, including attack detection, physical layer authentication (PLA), and other PLS techniques. Then, we present an in-depth overview of the key areas of PLS where DL can be used to enhance the security of wireless networks, such as automatic modulation classification (AMC), secure beamforming, PLA, etc. Performance evaluation metrics for DL-based PLS design are subsequently covered. Finally, we provide insights to the readers about various challenges and future research trends in the design of DL-based PLS for terrestrial communications in 5G and beyond networks.     

An Overview of Key Technologies in Physical Layer Security

The open nature of radio propagation enables ubiquitous wireless communication. This allows for seamless data transmission. However, unauthorized users may pose a threat to the security of the data being transmitted to authorized users. This gives rise to network vulnerabilities such as hacking, eavesdropping, and jamming of the transmitted information. Physical layer security (PLS) has been identified as one of the promising security approaches to safeguard the transmission from eavesdroppers in a wireless network. It is an alternative to the computationally demanding and complex cryptographic algorithms and techniques. PLS has continually received exponential research interest owing to the possibility of exploiting the characteristics of the wireless channel. One of the main characteristics includes the random nature of the transmission channel. The aforesaid nature makes it possible for confidential and authentic signal transmission between the sender and the receiver in the physical layer. We start by introducing the basic theories of PLS, including the wiretap channel, information-theoretic security, and a brief discussion of the cryptography security technique. Furthermore, an overview of multiple-input multiple-output (MIMO) communication is provided. The main focus of our review is based on the existing key-less PLS optimization techniques, their limitations, and challenges. The paper also looks into the promising key research areas in addressing these shortfalls. Lastly, a comprehensive overview of some of the recent PLS research in 5G and 6G technologies of wireless communication networks is provided.     

5G/NGPON Evolution and Convergence: Developing on Spatial Multiplexing of Optical Fiber Links for 5G Infrastructures

ABSTRACT

The offering of demanding telecommunication services as promised by the 5G specifications raise the necessity for high capacity, flexible, adaptive, and power conserving fronthaul. Toward this goal, the role of the passive optical network which is responsible for interconnecting the central office (CO) with the cell-sites is crucial. Among the latest related technologies that need to be integrated in the context of the next generation passive optical networks (NGPONs), the most promising for increasing the provided bandwidth, is the optical spatial multiplexing. In this paper, we present the key 5G technologies, focusing on spatial division multiplexing, which constitutes the main innovation of the blueSPACE 5G Infrastructure Public Private Partnership (5G PPP) project. Exploiting the recent developments on multicore fibers (MCFs), optical beamforming networks (OBFNs), analog radio over fiber (ARoF), and spatial-spectral resources granularity in the context of Spectrally Spatially Flexible Optical Networks (SS-FONs), we describe a complete approach for the 5G fronthaul, emphasizing on the efficient allocation of optical resources while aiming at minimizing energy consumption. The modeled optimization problem is thoroughly presented, and the introduced scheme is evaluated through a real-world based simulation scenario, exhibiting quite promising results.     

A vision towards integrated 6G communication networks: Promising technologies,architecture, and use-cases

The evolution of the previous mobile communication generations has led to innovative goals of the Internet of Everything (IoE) in the 5G. However, addressing all IoE-associated problems in 5G is difficult and a long-term process. As the key performance indicators (KPIs) of the 5G services are highly diverse, it is an intimidating task to develop a single platform enabling all KPIs. The vision of next-generation 6G wireless communications lies not only in enhancing these targets but also in providing new services. Numerous extensively envisaged future services, including life-critical services and wireless brain–computer interactions, will be critically dependent on an instant, virtually unlimited wireless connectivity. In this direction, the 6G is envisioned to have primely five service objectives; further-enhanced mobile broadband (FeMBB), ultra-massive machine type communication (umMTC), extremely reliable low latency communication (ERLLC), long-distance and high-mobility communications (LDHMC), and extremely low-power communications (ELPC). The 3D global integration of the wireless communication networks is lacking in the 5G, which is targeted by the future 6G. In this paper, we present an exhaustive review of the 6G wireless communication network. We explore the various existing mobile communication generations concerning data rate, frequency band, bandwidth allotted, latency, and applications. We also highlight various current trends and issues in the 5G communication network, which drives research for the 6G communication network. Our focus is to provide a comprehensive survey on the future 6G. So, we explored the objectives and design principles for 6G. This paper highlights the key 6G technology drivers. This paper also proposes an architectural design for 6G. Moreover, we carry out a case-study of 6G architecture operational design and compare the result with previous generation architecture designs. Further, 6G envisioned open research challenges, research directions, and recent advancements are also highlighted in this paper. Furthermore, we discuss possible use-cases in terms of real-time interactions of the biological, physical, and digital world, and also how these use-cases are going to serve in 6G.     

Novel memory efficient LDPC decoders for beyond 5G

Beyond-5G wireless networks are expected to gain a excellent trade-off among computational accuracy, latency, and efficient use of available resources. This poses a significant challenge to the channel decoder. In this paper, a novel memory efficient algorithm for decoding Low-Density Parity-Check (LDPC) codes is proposed with a view to reduce the implementation complexity and hardware resources. The algorithm, called Check Node Self-Update (CNSU) algorithm, is based on layered normalized min-sum (LNMS) decoding algorithm while utilizing iteration parallel techniques to integrate both Variable Nodes (VNs) message and A-Posterior Probability(APP) message into the Check Nodes (CNs) message, which eliminates memories of both the VNs message and the APP message as well as updating module of APP message in CNs unit. Based on the proposed CNSU algorithm, design of partially parallel decoder architecture and serial simulations followed by implementation on the Stratix II EP2S180 FPGA are presented. The results show that the proposed algorithm and implementation bring a significant gain in efficient using of available resources, include reducing hardware memory resources and chip area while keeping the benefit of bit-error-rate (BER) performance and speeding up of convergence with LNMS, which are beneficial to apply in Beyond-5G wireless networks.     

Multiuser detection for the uplink of clustered 5G systems with universal frequency reuse

With 5G (Fifth generation) cellular communications, systems have to be able to cope with a massive increase of mobile devices and services and simultaneously improve the system’s spectral efficiency, as well as dealing with high interference levels. Base Station (BS) cooperation architectures jointly with block transmission techniques, such as OFDM (Orthogonal Frequency Division Multiplexing) for the downlink and SC-FDE (Single-Carrier with Frequency-Domain Equalization) for the uplink, are proven to be suitable for broadband wireless transmission systems. In BS cooperation systems MTs (Mobile Terminals) in adjacent cells share the same physical channel allowing the reducing of the frequency reuse and improving the spectral efficiency of cellular systems. In this paper we present a set of multiuser detection techniques for the uplink transmission in clustered architectures based on the C-RAN (Centralized-Radio Access Network) concept. We consider BS cooperation systems employing a universal frequency reuse approach. Our performance results demonstrate that by employing clustered techniques for the detection procedure it is possible to reduce substantially the signal processing complexity and the side information that must be transmitted by the backhaul structure.     

Development and Performance Analysis of a Photonics-Assisted RF Converter for 5G Applications

This article presents a simple, ultra-wideband and tunable radiofrequency (RF) converter for 5G cellular networks. The proposed optoelectronic device performs broadband photonics-assisted upconversion and downconversion using a single optical modulator. Experimental results demonstrate RF conversion from DC to millimeter waves, including 28 and 38 GHz that are potential frequency bands for 5G applications. Narrow linewidth and low phase noise characteristics are observed in all generated RF carriers. An experimental digital performance analysis using different modulation schemes illustrates the applicability of the proposed photonics-based device in reconfigurable optical wireless communications.     

Experience-driven learning-based intelligent hybrid beamforming for massive MIMO mmWave communications

We have studied massive MIMO hybrid beamforming (HBF) for millimeter-wave (mmWave) communications, where the transceivers only have a few radio frequency chain (RFC) numbers compared to the number of antenna elements. We propose a hybrid beamforming design to improve the system’s spectral, hardware, and computational efficiencies, where finding the precoding and combining matrices are formulated as optimization problems with practical constraints. The series of analog phase shifters creates a unit modulus constraint, making this problem non-convex and subsequently incurring unaffordable computational complexity. Advanced deep reinforcement learning techniques effectively handle non-convex problems in many domains; therefore, we have transformed this non-convex hybrid beamforming optimization problem using a reinforcement learning framework. These frameworks are solved using advanced deep reinforcement learning techniques implemented with experience replay schemes to maximize the spectral and learning efficiencies in highly uncertain wireless environments. We developed a twin-delayed deep deterministic (TD3) policy gradient-based hybrid beamforming scheme to overcome Q-learning’s substantial overestimation. We assumed a complete channel state information (CSI) to design our beamformers and then challenged this assumption by proposing a deep reinforcement learning-based channel estimation method. We reduced hybrid beamforming complexity using soft target double deep Q-learning to exploit mmWave channel sparsity. This method allowed us to construct the analog precoder by selecting channel dominant paths. We have demonstrated that the proposed approaches improve the system’s spectral and learning efficiencies compared to prior studies. We have also demonstrated that deep reinforcement learning is a versatile technique that can unleash the power of massive MIMO hybrid beamforming in mmWave systems for next-generation wireless communication.     

An efficient packet parser architecture for software-defined 5G networks

Software-defined networks (SDN) has emerged with the capability to program in order to enhance flexibility, management, and testing of new ideas in the next generation of networks by removing current network limitations. Network virtualization and functionalization are critical elements supporting the delivery of future network services, especially in 5G networks. With the integration of virtualization and functionalization, network resources can be provisioned on-demand, and network service functions can be composed and chained dynamically to cater to various requirements. 5G networks are expected to rely heavily on SDN, which has been widely applied in core network design. To have a software-defined 5G network, not only is new spectrum and interface needed from SDN, but also a programmable and efficient hardware infrastructure is required. Admittedly, hardware components and infrastructure play an important role in supporting 5G networks. In other words, the software-defined 5G network data plane must have the required flexibility and programmability to support upcoming needs and technologies. Technological solutions need to respond to actual requests in infrastructure. Packet parsers in the data plane of software-defined 5G networks are one of the most important components because of the variation in the type of network headers and protocols. Each SDN switch needs to identify headers for processing input packets in the data plane, where the packet parser operates. Multiple implementations of packet parsers have been done on different substrates that occupy large hardware resources and areas on chip. However, they are not suitable for software-defined 5G networks. Certain architectures have been presented for packet parsing, aimed at accelerating the process of header parsing, however no attention has been paid toward reducing the area and the volume of the needed hardware resources and programmability in the data plane. This paper presents a new and efficient architecture for packet parsers on Field Programmable Gate Arrays (FPGA), called Efficient FPGA Packet Parser (EFPP) in a designed software-defined 5G network. This architecture emphasizes the removal of Ternary Content Addressable Memory (TCAM) to decrease hardware resources and efficiency in the data plane. Moreover, this architecture uses the chip’s processing speed and reconfiguration capabilities to support new protocols and network headers while maintaining flexibilities on software-defined 5G networks. EFPP is applied to chips on FPGA Xilinx ZedBoard Zynq, and the resources consumed around 7.5% LookUp Table, 1.9% Flip-Flops, and 5.8% of the memory. EFPP was also more area efficient. According to our results, EFPP would reduce the area and volume of hardware compared to other peer works.     

Particle swarm optimization based network selection in heterogeneous wireless environment

Deployment of heterogeneous wireless networks is spreading throughout the world as users want to be connected anytime, anywhere, and anyhow. Meanwhile, users are increasingly interested in multimedia applications such as audio, video streaming and Voice over IP (VoIP), which require strict Quality of Service (QoS) support. Provisioning of Always Best Connected (ABC) network with such constraints is a challenging task. Considering the availability of various access technologies, it is difficult for a network operator to find reliable criteria to select the best network that ensures user satisfaction while reducing multiple network selection. Designing an efficient Network selection algorithm, in this type of environment, is an important research problem. In this paper, we propose a novel network selection algorithm utilizing signal strength, available bit rate, signal to noise ratio, achievable throughput, bit error rate and outage probability metrics as criteria for network selection. The selection metrics are combined with PSO for relative dynamic weight optimization. The proposed algorithm is implemented in a typical heterogeneous environment of EDGE (2.5G) and UMTS (3G). Switching rate of the user between available networks has been used as the performance metric. Moreover, a utility function is used to maintain desired QoS during transition between networks, which is measured in terms of the throughput. It is shown here that PSO based approach yields optimal network selection in heterogeneous wireless environment.     

A Hybrid Scheme of MCS Selection and Spectrum Allocation for URLLC Traffic under Delay and Reliability Constraints

The Ultra-Reliable Low-Latency Communication (URLLC) is expected to be an important feature of 5G and beyond networks. Supporting URLLC in a resource-efficient manner demands optimal Modulation and Coding Scheme (MCS) selection and spectrum allocation. This paper presents a study on MCS selection and spectrum allocation to support URLLC. The essential idea is to establish an analytical connection between the delay and reliability requirements of URLLC data transmission and the underlying MCS selection and spectrum allocation. In particular, the connection factors in fundamental aspects of wireless data communication include channel quality, coding and modulation, spectrum allocation and data traffic characteristics. With this connection, MCS selection and spectrum allocation can be efficiently performed based on the delay and reliability requirements of URLLC. Theoretical results in the scenario of a 5G New Radio system are presented, where the Signal-to-Noise Ratio (SNR) thresholds for adaptive MCS selection, data-transmission rate and delay, as well as spectrum allocation under different configurations, including data duplication, are discussed. Simulation results are also obtained and compared with the theoretical results, which validate the analysis and its efficiency.     

A survey on 5G: The next generation of mobile communication

The rapidly increasing number of mobile devices, voluminous data, and higher data rate are pushing to rethink the current generation of the cellular mobile communication. The next or fifth generation (5G) cellular networks are expected to meet high-end requirements. The 5G networks are broadly characterized by three unique features: ubiquitous connectivity, extremely low latency, and very high-speed data transfer. The 5G networks would provide novel architectures and technologies beyond state-of-the-art architectures and technologies. In this paper, our intent is to find an answer to the question: “what will be done by 5G and how?” We investigate and discuss serious limitations of the fourth generation (4G) cellular networks and corresponding new features of 5G networks. We identify challenges in 5G networks, new technologies for 5G networks, and present a comparative study of the proposed architectures that can be categorized on the basis of energy-efficiency, network hierarchy, and network types. Interestingly, the implementation issues, e.g., interference, QoS, handoff, security–privacy, channel access, and load balancing, hugely effect the realization of 5G networks. Furthermore, our illustrations highlight the feasibility of these models through an evaluation of existing real-experiments and testbeds.     

Multi-task learning approach for modulation and wireless signal classification for 5G and beyond: Edge deployment via model compression

Future communication networks must address the scarce spectrum to accommodate extensive growth of heterogeneous wireless devices. Efforts are underway to address spectrum coexistence, enhance spectrum awareness, and bolster authentication schemes. Wireless signal recognition is becoming increasingly more significant for spectrum monitoring, spectrum management, secure communications, among others. Consequently, comprehensive spectrum awareness on the edge has the potential to serve as a key enabler for the emerging beyond 5G (fifth generation) networks. State-of-the-art studies in this domain have (i) only focused on a single task – modulation or signal (protocol) classification – which in many cases is insufficient information for a system to act on, (ii) consider either radar or communication waveforms (homogeneous waveform category), and (iii) does not address edge deployment during neural network design phase. In this work, for the first time in the wireless communication domain, we exploit the potential of deep neural networks based multi-task learning (MTL) framework to simultaneously learn modulation and signal classification tasks while considering heterogeneous wireless signals such as radar and communication waveforms in the electromagnetic spectrum. The proposed MTL architecture benefits from the mutual relation between the two tasks in improving the classification accuracy as well as the learning efficiency with a lightweight neural network model. We additionally include experimental evaluations of the model with over-the-air collected samples and demonstrate first-hand insight on model compression along with deep learning pipeline for deployment on resource-constrained edge devices. We demonstrate significant computational, memory, and accuracy improvement of the proposed model over two reference architectures. In addition to modeling a lightweight MTL model suitable for resource-constrained embedded radio platforms, we provide a comprehensive heterogeneous wireless signals dataset for public use.     

Enabling 5G indoor services for residential environment using VLC technology

Visible light communication (VLC) has emerged as a viable complement to traditional radio frequency (RF) based systems and as an enabler for high data rate communications for beyond-5G (B5G) indoor communication systems. In particular, the emergence of new B5G-based applications with quality of service (QoS) requirements and massive connectivity has recently led to research on the required service-levels and the development of improved physical (PHY) layer methods. As part of recent VLC standards development activities, the IEEE has formed the 802.11bb “Light Communications (LC) for Wireless Local Area Networking” standardization group. This paper investigates the network requirements of 5G indoor services such as virtual reality (VR) and high-definition (HD) video for residential environments using VLC. In this paper, we consider such typical VLC scenarios with additional impairments such as light-emitting diode (LED) nonlinearity and imperfect channel feedback, and propose hyperparameter-free mitigation techniques using Reproducing Kernel Hilbert Space (RKHS) methods. In this context, we also propose using a direct current biased optical orthogonal frequency division multiplexing (DCO-OFDM)-based adaptive VLC transmission method that uses precomputed bit error rate (BER) expressions for these RKHS-based detection methods and performs adaptive BER-based modulation-order switching. Simulations of channel impulse responses (CIRs) show that the adaptive transmission method provides significantly improved error rate performance, which makes it promising for high data rate VLC-based 5G indoor services.     

Security concerns on machine learning solutions for 6G networks in mmWave beam prediction

6G – sixth generation – is the latest cellular technology currently under development for wireless communication systems. In recent years, machine learning (ML) algorithms have been applied widely in various fields, such as healthcare, transportation, energy, autonomous cars, and many more. Those algorithms have also been used in communication technologies to improve the system performance in terms of frequency spectrum usage, latency, and security. With the rapid developments of ML techniques, especially deep learning (DL), it is critical to consider the security concern when applying the algorithms. While ML algorithms offer significant advantages for 6G networks, security concerns on artificial intelligence (AI) models are typically ignored by the scientific community so far. However, security is also a vital part of AI algorithms because attackers can poison the AI model itself. This paper proposes a mitigation method for adversarial attacks against proposed 6G ML models for the millimeter-wave (mmWave) beam prediction using adversarial training. The main idea behind generating adversarial attacks against ML models is to produce faulty results by manipulating trained DL models for 6G applications for mmWave beam prediction. We also present a proposed adversarial learning mitigation method’s performance for 6G security in mmWave beam prediction application a fast gradient sign method attack. The results show that the defended model under attack’s mean square errors (i.e., the prediction accuracy) are very close to the undefended model without attack.     

Beamforming array techniques for acoustic emission monitoring of large concrete structures

This paper introduces a novel method of acoustic emission (AE) analysis which is particularly suited for field applications on large plate-like reinforced concrete structures, such as walls and bridge decks. Similar to phased-array signal processing techniques developed for other non-destructive evaluation methods, this technique adapts beamforming tools developed for passive sonar and seismological applications for use in AE source localization and signal discrimination analyses. Instead of relying on the relatively weak P-wave, this method uses the energy-rich Rayleigh wave and requires only a small array of 4–8 sensors. Tests on an in-service reinforced concrete structure demonstrate that the azimuth of an artificial AE source can be determined via this method for sources located up to 3.8 m from the sensor array, even when the P-wave is undetectable. The beamforming array geometry also allows additional signal processing tools to be implemented, such as the VESPA process (VElocity SPectral Analysis), whereby the arrivals of different wave phases are identified by their apparent velocity of propagation. Beamforming AE can reduce sampling rate and time synchronization requirements between spatially distant sensors which in turn facilitates the use of wireless sensor networks for this application.     

Genetic optimization of 5G-NR LDPC codes for lowering the error floor of BICM systems

With the wide range of commercial uses of fifth generation (5G), new radio (NR) communication networks, the wireless transmission becomes more efficient, reliable and faster. At the same time, high-quality signal transmission for 5G networks and beyond has also encountered new opportunities and challenges. Channel coding is a key technology to ensure reliable information transmission and service quality. However, the 5G-NR LDPC coded bit-interleaved coded modulation (BICM) sometimes suffers from relatively high error floors, so it can not always guarantee the high-quality and low-delay wireless transmission. In this paper, we propose a further redesign of the 5G-NR LDPC coded BICM based on genetic algorithm (GenAlg). By adjusting the number of the non-zero elements, the corresponding positions and shifting values in base matrix, we optimize the 5G-NR LDPC codes with GenAlg according to the error performances of coded BICM schemes. Simulation results show that the optimized 5G-NR LDPC codes which still support length and rate compatible coding have lower error floors with a little performance loss int the waterfall region compared to the standard 5G-NR LDPC codes with different modulation orders.     

UWB LOS/NLOS identification in multiple indoor environments using deep learning methods

Indoor location-aware service is booming in daily life and business activities, making the demand for precise indoor positioning systems thrive. The identification between line-of-sight (LOS) and non-line-of-sight (NLOS) is critical for wireless indoor time-of-arrival-based localization methods. Ultra-Wide-Band (UWB) is considered low cost among the many wireless positioning systems. It can resolve multi-path and have high penetration ability. This contribution addresses UWB NLOS/LOS identification problem in multiple environments. We propose a LOS/NLOS identification method using Convolutional Neural Network parallel with Gate Recurrent Unit, named Indoor NLOS/LOS identification Neural Network. The Convolutional Neural Network extracts spatial features of UWB channel impulse response data. While the Gate Recurrent Unit is an effective approach for designing deep recurrent neural networks which can extract temporal features. By integrating squeeze-and-extraction blocks into these architectures we can assign weights on channel-wise features. We simulated UWB channel impulse response signals in residential, office, and industrial scenarios based on the IEEE 802.15.4a channel model report. The presented network was tested in simulation scenarios and an open-source real-time measured dataset. Our method can solve NLOS identification problems for multiple indoor environments. Thus more versatile compare with networks only working in one scenario. Popular machine learning methods and deep learning methods are compared against our method. The test results show that the proposed network outperforms benchmark methods in simulation datasets and real-time measured datasets.     

Joint User Scheduling,Relay Selection,and Power Allocation for Multi-Antenna Opportunistic Beamforming Systems

Opportunistic beamforming (OBF) is a potential technique in the fifth generation (5G) and beyond 5G (B5G) that can boost the performance of communication systems and encourage high user quality of service (QoS) through multi-user selection gain. However, the achievable rate tends to be saturated with the increased number of users, when the number of users is large. To further improve the achievable rate, we proposed a multi-antenna opportunistic beamforming-based relay (MOBR) system, which can achieve both multi-user and multi-relay selection gains. Then, an optimization problem is formulated to maximize the achievable rate. Nevertheless, the optimization problem is a non-deterministic polynomial (NP)-hard problem, and it is difficult to obtain an optimal solution. In order to solve the proposed optimization problem, we divide it into two suboptimal issues and apply a joint iterative algorithm to consider both the suboptimal issues. Our simulation results indicate that the proposed system achieved a higher achievable rate than the conventional OBF systems and outperformed other beamforming schemes with low feedback information.     

Enabling Optical Network Test Bed for 5G Tests

In this work, we show some experimental approaches concerning optical network design dedicated to 5G infrastructures. In particular, we show some implementations of network slicing based on Carrier Ethernet forwarding, which will be very suitable in the context of 5G heterogeneous networks, especially looking at services for vertical enterprises. We also show how to adopt a central unit (orchestrator) to automatically manage such logical paths according to quality-of-service requirements, which can be monitored at the user location. We also illustrate how novel all-optical processes, such as the ones based on all-optical wavelength conversion, can be used for multicasting, enabling development of TV broadcasting based on 4G–5G terminals. These managing and forwarding techniques, operating on optical links, are tested in a wireless environment on Wi-Fi cells and emulating LTE and WiMAX systems by means of the NS-3 code.