Wireless Network Optimization for Federated Learning with Model Compression in Hybrid VLC/RF Systems

In this paper, the optimization of network performance to support the deployment of federated learning (FL) is investigated. In particular, in the considered model, each user owns a machine learning (ML) model by training through its own dataset, and then transmits its ML parameters to a base station (BS) which aggregates the ML parameters to obtain a global ML model and transmits it to each user. Due to limited radio frequency (RF) resources, the number of users that participate in FL is restricted. Meanwhile, each user uploading and downloading the FL parameters may increase communication costs thus reducing the number of participating users. To this end, we propose to introduce visible light communication (VLC) as a supplement to RF and use compression methods to reduce the resources needed to transmit FL parameters over wireless links so as to further improve the communication efficiency and simultaneously optimize wireless network through user selection and resource allocation. This user selection and bandwidth allocation problem is formulated as an optimization problem whose goal is to minimize the training loss of FL. We first use a model compression method to reduce the size of FL model parameters that are transmitted over wireless links. Then, the optimization problem is separated into two subproblems. The first subproblem is a user selection problem with a given bandwidth allocation, which is solved by a traversal algorithm. The second subproblem is a bandwidth allocation problem with a given user selection, which is solved by a numerical method. The ultimate user selection and bandwidth allocation are obtained by iteratively compressing the model and solving these two subproblems. Simulation results show that the proposed FL algorithm can improve the accuracy of object recognition by up to 16.7% and improve the number of selected users by up to 68.7%, compared to a conventional FL algorithm using only RF.     

Contract Theory-Based Incentive Mechanism for Full Duplex Cooperative NOMA with SWIPT Communication Networks

Cooperative Non-Orthogonal Multiple Access (NOMA) with Simultaneous Wireless Information and Power Transfer (SWIPT) communication can not only effectively improve the spectrum efficiency and energy efficiency of wireless networks but also extend their coverage. An important design issue is to incentivize a full duplex (FD) relaying center user to participate in the cooperative process and achieve a win–win situation for both the base station (BS) and the center user. Some private information of the center users are hidden from the BS in the network. A contract theory-based incentive mechanism under this asymmetric information scenario is applied to incentivize the center user to join the cooperative communication to maximize the BS’s benefit utility and to guarantee the center user’s expected payoff. In this work, we propose a matching theory-based Gale–Shapley algorithm to obtain the optimal strategy with low computation complexity in the multi-user pairing scenario. Simulation results indicate that the network performance of the proposed FD cooperative NOMA and SWIPT communication is much better than the conventional NOMA communication, and the benefit utility of the BS with the stable match strategy is nearly close to the multi-user pairing scenario with complete channel state information (CSI), while the center users get the satisfied expected payoffs.     

A contemporary review on user scheduling techniques and feedback reduction strategies towards the development of 5G and beyond communications

User scheduling (US) is the process of dynamic selection of the set of active users out of all available users to serve in each time slot. This is done to optimize the system performance, such as maximizing the sum rate, achieving better fairness, and quality of service or minimizing the interference. The choice of US method depends on the desired system performance and the trade-off between fairness and efficiency. In order to achieve these performance metrics base station (BS) needs channel state information (CSI) of each user for efficient US. Moreover, US and CSI feedback are closely related in the context of conventional multiple-input multiple-output (MIMO) to massive MIMO (mMIMO) systems based on full and limited CSI, as feedback information is often used to make informed decisions on US. To address these objectives simultaneously, this survey deals with exploring different algorithms used for efficient US, various criteria for US considering different scenarios, key methods for user grouping, methods for reduced feedback, and different standard codebook based feedback methods. To be more specific and concise, this article provides a comprehensive survey on state of the art methods used for US in single cell single tier, dual stage (double tier), multi cell scenarios and feedback mechanisms used in various contexts, e.g., multiuser (MU)-MIMO, MU-mMIMO, frequency division duplexing (FDD) mMIMO framework. Moreover, a synopsis of the recently proposed advanced codebook and non-codebook based methods for the long term evolution standards, fifth generation, and beyond communications are discussed. Finally the research gaps as the future scopes are discussed in this article.     

Metasurface aided intelligent reflecting surfaces for indoor GSSK-VLC downlink

To provide high-quality communication in the indoor generalized space shift keying (GSSK) aided visible light communications (VLC) downlink transmission, especially when the line-of-sight (LoS) link is blocked, a metasurface aided intelligent reflecting surfaces (mIRS) scheme is proposed. By controlling the reflection characteristics of incident light in a deliberate manner provided in this paper, the proposed mIRS-assisted indoor GSSK-VLC downlink can significantly enhance the signal quality at the receiver end. Furthermore, the maximum likelihood (ML) and efficient preprocessing enabled sparsity orthogonal matching pursuit (OMP) detectors are respectively presented for the considered system. Finally, simulations are demonstrated to verify the effectiveness of the proposed mIRS-assisted indoor GSSK-VLC downlink transmission.     

Latency optimization for Federated Learning over Wireless Power Transfer

Federal Learning (FL) is an emerging technology in the field of machine learning (ML). Compared with traditional ML, FL is an attractive method to deal with data security issues of the user-side. So that FL can realizes its full potential in terms of low latency and high energy efficiency (EE), this paper introduces a new framework: In the wireless communication network scenario, we propose an FL architecture based on Wireless Power Transfer (WPT). By combining WPT technology and FL, we can realize green wireless communication under the premise of ensuring user privacy. We formulate a joint calculation and communication optimization problem to optimize the latency of local calculation, uplink and downlink transmission without consuming user-side energy. The problem formulas listed according to the optimization problem are non-convex. They are first transformed into convex form, and then a low-complexity iterative algorithm is used to solve them optimally. Simulations show that our proposed FL method design has achieved a significant performance improvement over other benchmark tests.     

Deep learning-based channel estimation using Gaussian mixture distribution and expectation maximum algorithm

In massive multiple-input multiple-output (MIMO), it is much challenging to obtain accurate channel state information (CSI) after radio frequency (RF) chain reduction due to the high dimensions. With the fast development of machine learning(ML), it is widely acknowledged that ML is an effective method to deal with channel models which are typically unknown and hard to approximate. In this paper, we use the low complexity vector approximate messaging passing (VAMP) algorithm for channel estimation, combined with a deep learning framework for soft threshold shrinkage function training. Furthermore, in order to improve the estimation accuracy of the algorithm for massive MIMO channels, an optimized threshold function is proposed. This function is based on Gaussian mixture (GM) distribution modeling, and the expectation maximum Algorithm (EM Algorithm) is used to recover the channel information in beamspace. This contraction function and deep neural network are improved on the vector approximate messaging algorithm to form a high-precision channel estimation algorithm. Simulation results validate the effectiveness of the proposed network.     

Data detection based on matrix decomposition for massive MIMO systems in realistic channel scenarios

Massive multiple-input multiple-output (MIMO) is a key technology for modern wireless communication systems. In massive MIMO receivers, data detection is a computationally expensive task. In this paper, we explore the performance and the computational complexity of matrix decomposition based detectors in realistic channel scenarios for different massive MIMO configurations. In addition, data detectors based on decomposition algorithms are compared to the approximate-inversion detection (AID) methods. It is shown that the alternating-direction-method-of-multipliers-based-Infinity-Norm (ADMIN) detection is promising in realistic channel environment and the performance is stable even when the ratio of the base-station (BS) antenna elements to the number of users is small. In addition, this paper studies the performance of several detectors in imperfect channel state information (CSI) and correlated channels. Our work provides valuable insights for massive MIMO systems and very large-scale integration (VLSI) designers to select the appropriate massive MIMO detector based on their specifications.     

New Interfaces and Approaches to Machine Learning When Classifying Gestures within Music

Interactive music uses wearable sensors (i.e., gestural interfaces—GIs) and biometric datasets to reinvent traditional human–computer interaction and enhance music composition. In recent years, machine learning (ML) has been important for the artform. This is because ML helps process complex biometric datasets from GIs when predicting musical actions (termed performance gestures). ML allows musicians to create novel interactions with digital media. Wekinator is a popular ML software amongst artists, allowing users to train models through demonstration. It is built on the Waikato Environment for Knowledge Analysis (WEKA) framework, which is used to build supervised predictive models. Previous research has used biometric data from GIs to train specific ML models. However, previous research does not inform optimum ML model choice, within music, or compare model performance. Wekinator offers several ML models. Thus, we used Wekinator and the Myo armband GI and study three performance gestures for piano practice to solve this problem. Using these, we trained all models in Wekinator and investigated their accuracy, how gesture representation affects model accuracy and if optimisation can arise. Results show that neural networks are the strongest continuous classifiers, mapping behaviour differs amongst continuous models, optimisation can occur and gesture representation disparately affects model mapping behaviour; impacting music practice.     

Performance of multi-user transmitter preprocessing assisted MIMO system over correlated frequency-selective channels

In this contribution we present the performance of a multi-user transmitter preprocessing (MUTP) assisted multiple-input multiple-output (MIMO) space division multiple access (SDMA) system, aided by double space time transmit diversity (DSTTD) and space time block code (STBC) processing for downlink (DL) and uplink (UL) transmissions respectively. The MUTP is invoked by singular value decomposition (SVD) which exploits the channel state information (CSI) of all the users at the base station (BS) and only an individual user’s CSI at the mobile station (MS). Specifically, in this contribution, we investigate the performance of multi-user MIMO cellular systems in frequency-selective channels from a transmitter signal processing perspective, where multiple access interference (MAI) is the dominant channel impairment. In particular, the effects of three types of delay spread distributions on MUTP assisted MIMO SDMA systems pertaining to the Long Term Evolution (LTE) channel model are analyzed. The simulation results demonstrate that MUTP can perfectly eliminate MAI in addition to obviating the need for complex multi-user detectors (MUDs) both at the BS and MS. Further, SVD-based MUTP results in better achievable symbol error rate (SER) compared to popularly known precoding schemes such as block diagonalization (BD), dirty paper coding (DPC), Tomlinson–Harashima precoding (THP) and geometric mean decomposition (GMD). Furthermore, when turbo coding is invoked, coded SVD aided MUTP results in better achievable SER than an uncoded system.     

Energy Efficiency of User-Centric,Cell-Free Massive MIMO-OFDM with Instantaneous CSI

In the user-centric, cell-free, massive multi-input, multi-output (MIMO) orthogonal frequency division multiplexing (OFDM) system, a large number of deployed access points (APs) serve user equipment (UEs) simultaneously, using the same time–frequency resources, and the system is able to ensure fairness between each user; moreover, it is robust against fading caused by multi-path propagation. Existing studies assume that cell-free, massive MIMO is channel-hardened, the same as centralized massive MIMO, and these studies address power allocation and energy efficiency optimization based on the statistics information of each channel. In cell-free, massive MIMO systems, especially APs with only one antenna, the channel statistics information is not a complete substitute for the instantaneous channel state information (CSI) obtained via channel estimation. In this paper, we propose that energy efficiency is optimized by power allocation with instantaneous CSI in the user-centric, cell-free, massive MIMO-OFDM system, and we consider the effect of CSI exchanging between APs and the central processing unit. In addition, we design different resource block allocation schemes, so that user-centric, cell-free, massive MIMO-OFDM can support enhanced mobile broadband (eMBB) for high-speed communication and massive machine communication (mMTC) for massive device communication. The numerical results verify that the proposed energy efficiency optimization scheme, based on instantaneous CSI, outperforms the one with statistical information in both scenarios.     

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.     

Robust secrecy rate maximization in IRS-assisted cognitive radio networks

In this paper, we focus on the secrecy rate maximization problem in intelligent reflecting surface (IRS)-assisted cognitive radio (CR) networks. In order to improve the security, there is a common scheme to add artificial noise (AN) to the transmitted signal, which is also applied in this paper. Further, in CR networks, the secondary users always cannot obtain accurate channel state information (CSI) about the primary user and eavesdropper. By taking jointly design for the IRS phase shift matrix, the transmitted beamforming of the secondary base station (BS), and the covariance matrix of AN, our objective is to maximize the minimal secrecy rate of all secondary users. Due to the serious coupling among the designed variables, it cannot be solved by conventional methods. We propose an alternating optimization (AO) algorithm. In simulation results, we apply primary users and secondary users randomly distributed in the communication area, which numerically demonstrate the superiority of our proposed scheme.     

Secure communication over RIS-aided underlay CR MIMO wiretap channel without Eve’s CSI

This paper investigates a reconfigurable intelligent surface (RIS)-aided underlay cognitive radio (CR) multiple-input multiple-output (MIMO) wiretap channel where the secondary transmitter (ST) communicates with primary user (PU) and secondary user (SU) in the absence of the eavesdropper’s (Eve’s) channel state information (CSI). To enhance the secrecy performance in CR MIMO wiretap channel, the power of useful signal is minimized at ST, and then the residual power is further utilized to design artificial noise (AN) based on statistical CSI at ST. Specifically, we first optimize the transmit covariance matrix at ST and the diagonal phase-shifting matrix at RIS jointly leveraging large-system approximation results. Then the power allocation for SU is optimized to obtain the minimum transmit power of useful information at ST. Besides, we further design AN with the residual power by aligning it into the null space of the SU channel and thus avert the harmful effects of AN to improve the secure communication quality of SU. Finally, through numerical simulations, we illustrate the effectiveness of the proposed algorithm and validate the existence of a trade-off between the quality-of-service (QoS) at SU and secrecy rate.     

A dual phase genetic algorithm for improved initial access in 5G millimeter wave communication

Initial access (IA) in 5G millimeter wave (mmWave) communication is the problem of establishing a directional link between the base station (BS) and the user equipment (UE). For a multiple-input multiple-output (MIMO) system, where both the BS and UE have many antennas, finding the optimal beams can be prohibitively expensive in terms of delay and computation. In this work, we propose a meta-heuristic approach which is a modified dual-phase genetic algorithm. Since it is a meta-heuristic approach, it is generic and hence does not require extensive modifications to apply to different scenarios, it also does not require context information such as prior knowledge of channel state or statistics of user behavior. The proposed method is using iterative search for the optimal beams, but switch to a different fine-grained search phase on later iterations in order to quickly converge to the local optimum. The effect of this approach is analyzed in terms of capacity achieved vs number of transmit and receive antennas at BS and UE, codebook size, outage probability, total transmitted power, and other parameters specific to this particular dual-phase method. The proposed work has shown improved performance when compared to the existing similar work done in Souto et al. (2019) in terms of capacity achieved (2.12%), reduced power consumption (8.57%), and reduced IA delay (35% to 50%).     

Distributed spatial media-based modulation for relay networks with RF mirrors

A novel distributed spatial media-based modulation scheme is proposed in this paper by cleverly utilizing distributed spatial modulation (DSM) and media-based modulation (MBM) principles. This proposed scheme is referred to as distributed channel modulation (DCM) for relay networks. In this scheme, decode-and-forward relaying protocol is adopted, and the channel states are exploited for transmitting extra information bits by using a number of radio frequency (RF) mirrors that are placed near each relay. To provide a fair comparison with the conventional state-of-the-art schemes, the symbol error rate (SER) performance of DSM scheme is evaluated. Besides, a low complexity detection technique known as iterative maximum ratio combining (i-MRC) is used in order to reduce the receiver complexity of the proposed scheme. Simulation results demonstrate that the proposed DCM scheme significantly outperforms DSM scheme for the same average rate. It is also shown that there is a negligible degradation in the SER performance of the proposed DCM scheme when i-MRC detection is used as compared to the performance with maximum likelihood (ML) detection. Furthermore, a significant reduction in the receiver complexity is achieved by using i-MRC detection technique in contrast to the results with ML detector. It has been also revealed that the proposed DCM scheme shows a performance drop of about 3 dB when the availability of an imperfect channel state information (CSI) is assumed with the presence of channel estimation errors (CEEs). Finally, simulation results have confirmed the analytical findings.     

The Downlink Performance for Cell-Free Massive MIMO with Instantaneous CSI in Slowly Time-Varying Channels

In centralized massive multiple-input multiple-output (MIMO) systems, the channel hardening phenomenon can occur, in which the channel behaves as almost fully deterministic as the number of antennas increases. Nevertheless, in a cell-free massive MIMO system, the channel is less deterministic. In this paper, we propose using instantaneous channel state information (CSI) instead of statistical CSI to obtain the power control coefficient in cell-free massive MIMO. Access points (APs) and user equipment (UE) have sufficient time to obtain instantaneous CSI in a slowly time-varying channel environment. We derive the achievable downlink rate under instantaneous CSI for frequency division duplex (FDD) cell-free massive MIMO systems and apply the results to the power control coefficients. For FDD systems, quantized channel coefficients are proposed to reduce feedback overhead. The simulation results show that the spectral efficiency performance when using instantaneous CSI is approximately three times higher than that achieved using statistical CSI.     

Performance analysis of overlay cognitive NOMA network with imperfect SIC and imperfect CSI

In this paper, we investigate a multiple users cooperative overlay cognitive radio non-orthogonal multiple access (CR-NOMA) network in the presence of imperfect successive interference cancellation (SIC) and imperfect channel state information (CSI). In the context of cellular network, cell-center cognitive secondary users act as relays to assist transmission from the primary user (PU) transmitter to the cell-edge PU receiver via NOMA. According to the received signals between the primary transmitter and multiple cognitive secondary center users, the best cell-center cognitive SU with the maximum signal to noise ratio (SNR) is selected to transmit the PU’s signals and its own signal to cell-edge users through NOMA principle. Then, the PU cell-edge user combine the signals received from direct transmission in the first phase and relay transmission from the best cell-center cognitive SU in the second phase by selection combining (SC). To measure the performance of the system quantitatively, we derive the end-to-end outage probability and capacity for the primary and secondary networks by taking the imperfect SIC and CSI into consideration. Finally, the performance analysis is validated by the simulations, and show that serious interference caused by imperfect SIC and (or) imperfect CSI reduce the system performance.     

Improving spectral efficiency via pilot assignment and subarray selection under realistic XL-MIMO channels

The main requirements for 5G and beyond connectivity include a uniform high quality of service, which can be attained in crowded scenarios by extra-large MIMO (XL-MIMO) systems. Another requirement is to support an increasing number of connected users in (over)crowded machine-type communication (mMTC). In such scenarios, pilot assignment (PA) becomes paramount to reduce pilot contamination and consequently improve spectral efficiency (SE). We propose a novel quasi-optimal low-complexity iterative pilot assignment strategy for XL-MIMO systems, based on a genetic algorithm (GA). The proposed GA-based PA procedure turns the quality of service more uniform, taking into account the normalized mean-square error (NMSE) of channel estimation from each candidate of the population. The simulations reveal that the proposed iterative procedure minimizes the channel estimation NMSE averaged over the UEs. The second procedure is the subarray (SA) selection. In XL-MIMO systems, commonly a UE is close to an SA antenna subset such that a sufficient data rate can be achieved if only a specific SA serves that UE. Thus, an SA selection procedure is investigated to make the system scalable by defining the maximum number of UEs each SA can help. Hence, the SA clusters are formatted based on the PA decision. Furthermore, we introduce an appropriate channel model for XL-MIMO, which considers a deterministic LoS component with a distance-dependent probability of existence combined with a stochastic spatially correlated Rayleigh NLoS fading component. The developed simulations and analyses rely on this suitable channel model under realistic assumptions of pilot contamination and correlated channels.     

A low complexity burst channel estimation algorithm for FDD massive MIMO systems

To fully attain array gains of massive multiple-input multiple-output (MIMO) and its energy and spectral efficiency, deriving channel state information (CSI) at the base station (BS) side is essential. However, CSI estimation of frequency-division duplex (FDD) based massive MIMO is a challenging task owning to the required pilots, which are proportional to the number of antennas at the BS side. Therefore, the pilot overhead should be inevitably mitigated in the process of downlink channel estimation of FDD technique. In this paper, we propose a novel compressed sensing (CS) algorithm which takes advantage of correlation between the received and transmitted signals to estimate the channel with high precision, and moreover, to reduce the computational complexity imposed on the BS side. The main idea behind the proposed algorithm is to sort the specific number of maximum correlations as a common support in each iteration of the algorithm. Simulation results indicate that the proposed algorithm is capable of estimating downlink channel better than the counterpart algorithms in terms of mean square error (MSE) and the computational complexity. Meanwhile, the complexity of the proposed method linearly grows up when the number of BS antennas increases.     

基于正交频分复用的水声自适应通信系统性能仿真研究

本文从平均谱效率的角度分析并讨论了基于正交频分复用(Orthogonal Frequency Division Multiplex,OFDM)技术的水声自适应通信系统的通信性能。在两种典型的水声统计信道假设下,根据信道状态信息的不同精确程度,针对不同的调制方式,对水声自适应通信系统的平均谱效率进行了理论推导,并给出了部分性能函数的解析形式,而后从多个角度给出了较为全面的数值仿真分析结果。仿真结果显示:当目标误码率为10-3时,水声自适应通信系统可以在相同发射功率下,显著地改善通信性能(约3 bit/s/Hz);在同样的目标误码率下,如果维持传输性能不变,自适应通信系统可以显著节省发射功率(约10 dB)。在信道状态信息不确知的情况下,当信道估计误差大于-15 dB,或多普勒补偿后信道的扩展因子大于0.03时,自适应系统的性能才会显著劣化。此外,在统计意义上,自适应通信方法对于系统性能的改善程度随通信距离的增加而增大。