Search

In the realm of 5G communication systems, the accuracy of Channel State Information (CSI) prediction is vital for optimizing performance. This letter introduces a pioneering approach: the Spectral-Temporal Graph Neural Network (STEM GNN), which fuses spatial relationships and temporal dynamics of the wireless channel using the Graph Fourier Transform. We compare the STEM GNN approach with conventional Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) models for CSI prediction. Our findings reveal a significant enhancement in overall communication system performance through STEM GNNs. For instance, in one scenario, STEM GNN achieves a sum rate of 5.009 bps/Hz which is $11.9\%$ higher than that of LSTM and $35\%$ higher than that of RNN. The spectral-temporal analysis capabilities of STEM GNNs capture intricate patterns often overlooked by traditional models, offering improvements in beamforming, interference mitigation, and ultra-reliable low-latency communication (URLLC).

Millimeter-waves' propagation characteristics create prospects for spatial and temporal spectrum sharing in a variety of contexts, including cognitive spectrum sharing (CSS). However, CSS along with omnidirectional sensing, is not efficient at mmWave frequencies due to their directional nature of transmission, as this limits secondary networks' ability to access the spectrum. This inspired us to create an analytical approach using stochastic geometry to examine the implications of directional cognitive sensing in mmWave networks. We explore a scenario where multiple secondary transmitter-receiver pairs coexist with a primary transmitter-receiver pair, forming a cognitive network. The positions of the secondary transmitters are modelled using a homogeneous Poisson point process (PPP) with corresponding secondary receivers located around them. A threshold on directional transmission is imposed on each secondary transmitter in order to limit its interference at the primary receiver. We derive the medium-access-probability of a secondary user along with the fraction of the secondary transmitters active at a time-instant. To understand cognition's feasibility, we derive the coverage probabilities of primary and secondary links. We provide various design insights via numerical results. For example, we investigate the interference-threshold's optimal value while ensuring coverage for both links and its dependence on various parameters. We find that directionality improves both links' performance as a key factor. Further, allowing location-aware secondary directionality can help achieve similar coverage for all secondary links., Comment: 30 pages, 12 figures

Recently, deep neural networks have emerged as a solution to solve NP-hard wireless resource allocation problems in real-time. However, multi-layer perceptron (MLP) and convolutional neural network (CNN) structures, which are inherited from image processing tasks, are not optimized for wireless network problems. As network size increases, these methods get harder to train and generalize. User pairing is one such essential NP-hard optimization problem in wireless communication systems that entails selecting users to be scheduled together while minimizing interference and maximizing throughput. In this paper, we propose an unsupervised graph neural network (GNN) approach to efficiently solve the user pairing problem. Our proposed method utilizes the Erdos goes neural pipeline to significantly outperform other scheduling methods such as k-means and semi-orthogonal user scheduling (SUS). At 20 dB SNR, our proposed approach achieves a 49% better sum rate than k-means and a staggering 95% better sum rate than SUS while consuming minimal time and resources. The scalability of the proposed method is also explored as our model can handle dynamic changes in network size without experiencing a substantial decrease in performance. Moreover, our model can accomplish this without being explicitly trained for larger or smaller networks facilitating a dynamic functionality that cannot be achieved using CNNs or MLPs.

Deep learning-based massive MIMO CSI feedback has received a lot of attention in recent years. Now, there exists a plethora of CSI feedback models mostly based on auto-encoders (AE) architecture with an encoder network at the user equipment (UE) and a decoder network at the gNB (base station). However, these models are trained for a single user in a single-channel scenario, making them ineffective in multi-user scenarios with varying channels and varying encoder models across the users. In this work, we address this problem by exploiting the techniques of multi-task learning (MTL) in the context of massive MIMO CSI feedback. In particular, we propose methods to jointly train the existing models in a multi-user setting while increasing the performance of some of the constituent models. For example, through our proposed methods, CSINet when trained along with STNet has seen a $39\%$ increase in performance while increasing the sum rate of the system by $0.07bps/Hz$.

In this letter, we present in detail the system-level modeling of reconfigurable intelligent surface (RIS)-assisted cellular systems by considering a 3-dimensional channel model between base station, RIS, and user. We prove that the optimal placement of RIS to achieve wider coverage is exactly opposite to the base station, under the constraint of single RIS in each sector. We propose a novel beamforming design for RIS-assisted cellular systems and derive the achievable sum rate in the presence of ideal, discrete, and random phase shifters at RIS. Through extensive system-level evaluations, we then show that the proposed beamforming design achieves significant improvements as compared to the state-of-the-art algorithms.

Channel State Information (CSI) Feedback plays a crucial role in achieving higher gains through beamforming. However, for a massive MIMO system, this feedback overhead is huge and grows linearly with the number of antennas. To reduce the feedback overhead several compressive sensing (CS) techniques were implemented in recent years but these techniques are often iterative and are computationally complex to realize in power-constrained user equipment (UE). Hence, a data-based deep learning approach took over in these recent years introducing a variety of neural networks for CSI compression. Specifically, transformer-based networks have been shown to achieve state-of-the-art performance. However, the multi-head attention operation, which is at the core of transformers, is computationally complex making transformers difficult to implement on a UE. In this work, we present a lightweight transformer named STNet which uses a spatially separable attention mechanism that is significantly less complex than the traditional full-attention. Equipped with this, STNet outperformed state-of-the-art models in some scenarios with approximately $1/10^{th}$ of the resources.

The focus of this white paper is on machine learning (ML) in wireless communications. 6G wireless communication networks will be the backbone of the digital transformation of societies by providing ubiquitous, reliable, and near-instant wireless connectivity for humans and machines. Recent advances in ML research has led enable a wide range of novel technologies such as self-driving vehicles and voice assistants. Such innovation is possible as a result of the availability of advanced ML models, large datasets, and high computational power. On the other hand, the ever-increasing demand for connectivity will require a lot of innovation in 6G wireless networks, and ML tools will play a major role in solving problems in the wireless domain. In this paper, we provide an overview of the vision of how ML will impact the wireless communication systems. We first give an overview of the ML methods that have the highest potential to be used in wireless networks. Then, we discuss the problems that can be solved by using ML in various layers of the network such as the physical layer, medium access layer, and application layer. Zero-touch optimization of wireless networks using ML is another interesting aspect that is discussed in this paper. Finally, at the end of each section, important research questions that the section aims to answer are presented.

Beamforming is the key enabler for wireless communications in the mmWave bands. 802.11ad and WiGig are wireless technologies that currently use the 60 GHz unlicensed mmWave spectrum via beamforming techniques. It is likely that 5G systems will be considered for 60GHz unlicensed spectrum (apart from other unlicensed bands) deployments and hence must co-exist with 802.11ad and WiGig. 3GPP is taking steps towards achieving the same and the standardization for this is underway. The first step to achieve this co-existence is to find the interference-free directions, in other words identify the directions in which the nodes using these incumbent technologies are communicating and eliminate those directions from further communications. Such a mechanism can help to exploit the spatial holes rather than avoid communications even when only a few spatial directions are used by incumbents. Such a mechanism trivially increases the throughput of the proposed 5G systems. However, since the incumbent technologies may be unknown to the 5G mmWave nodes and their behavior may also be unknown apriori (for instance, parameters such as duty cycle, power levels, CSMA parameter used by 802.11ad are unknown to the 5G nodes), this spatial direction finding must be performed in a blind manner. In this paper, we use multi-armed bandits-based algorithms, a variant of machine learning algorithms, to blindly detect the beam directions (both along azimuth and elevation i.e., 3D-beamforming) used for communication by the incumbents. This work paves the way for combining the powerful of machine learning algorithms into 5G unlicensed mmWave systems. Numerical results show the superior performance of these algorithms over techniques that are commonly employed in such blind settings., Comment: This paper is an extension of the ICC 2017 paper titled "Beam Learning". It was written before the onslaught of deep learning techniques

The Full Dimension-MIMO (FD-MIMO) technology is capable of achieving huge improvements in network throughput with simultaneous connectivity of a large number of mobile wireless devices, unmanned aerial vehicles, and the Internet of Things (IoT). In FD-MIMO, with a large number of antennae at the base station and the ability to perform beamforming, the capacity of the physical downlink shared channel (PDSCH) has increased a lot. However, the current specifications of the 3rd Generation Partnership Project (3GPP) does not allow the base station to perform beamforming techniques for the physical downlink control channel (PDCCH), and hence, PDCCH has neither the capacity nor the coverage of PDSCH. Therefore, PDCCH capacity will still limit the performance of a network as it dictates the number of users that can be scheduled at a given time instant. In Release 11, 3GPP introduced enhanced PDCCH (EPDCCH) to increase the PDCCH capacity at the cost of sacrificing the PDSCH resources. The problem of enhancing the PDCCH capacity within the available control channel resources has not been addressed yet in the literature. Hence, in this paper, we propose a novel beamformed PDCCH (BF-PDCCH) design which is aligned to the 3GPP specifications and requires simple software changes at the base station. We rely on the sounding reference signals transmitted in the uplink to decide the best beam for a user and ingeniously schedule the users in PDCCH. We perform system level simulations to evaluate the performance of the proposed design and show that the proposed BF-PDCCH achieves larger network throughput when compared with the current state of art algorithms, PDCCH and EPDCCH schemes.

The volume of mobile data traffic has been driven to an unprecedented high level due to the proliferation of smartphones/mobile devices that support a wide range of broadband applications and services, requiring a next generation mobile communication system, i.e., the fifth generation (5G). Millimeter wave (mmWave) bands can offer much larger available spectrum bandwidth and thus are considered as one of the most promising approaches to significantly boost the capacity in 5G NR. However, devices and network radio nodes operating on mmWave bands suffer from phase noise and without correction of phase noise, the performance of the network could potentially suffer significant losses. In this paper, we investigate the effects of phase noise and provide comprehensive solutions to track the phase noise by using phase tracking reference signals (PT-RS), as currently standardized in 3GPP Release 15. The design aspects such as PT-RS pattern, interference randomization, multi-TRP operation, etc., are investigated and evaluation results are also provided., Comment: 5 pages, 12 figures, accepted by VTC Fall 2018

In this paper, we study jamming attacks against wireless networks. Specifically, we consider a network of base stations (BS) or access points (AP) and investigate the impact of a fixed number of jammers that are randomly deployed according to a Binomial point process. We shed light on the network performance in terms of a) the outage probability and b) the error probability of a victim receiver in the downlink of this wireless network. We derive analytical expressions for both these metrics and discuss in detail how the jammer network must adapt to the various wireless network parameters in order to effectively attack the victim receivers. For instance, we will show that with only 1 jammer per BS/AP a) the outage probability of the wireless network can be increased from 1% (as seen in the non-jamming case) to 80% and b) when retransmissions are used, the jammers cause the effective network activity factor (and hence the interference among the BSs) to be doubled. Furthermore, we show that the behavior of the jammer network as a function of the BS/AP density is not obvious. In particular, an interesting concave-type behavior is seen which indicates that the number of jammers required to attack the wireless network must scale with the BS density only until a certain value beyond which it decreases. In the context of error probability of the victim receiver, we study whether or not some recent results related to jamming in the point-to-point link scenario can be extended to the case of jamming against wireless networks. Numerical results are presented to validate the theoretical inferences presented., Comment: 32 double-spaced pages, 18 figures. Submitted to IEEE Transactions on Wireless Communications

Can an intelligent jammer learn and adapt to unknown environments in an electronic warfare-type scenario? In this paper, we answer this question in the positive, by developing a cognitive jammer that adaptively and optimally disrupts the communication between a victim transmitter-receiver pair. We formalize the problem using a novel multi-armed bandit framework where the jammer can choose various physical layer parameters such as the signaling scheme, power level and the on-off/pulsing duration in an attempt to obtain power efficient jamming strategies. We first present novel online learning algorithms to maximize the jamming efficacy against static transmitter-receiver pairs and prove that our learning algorithm converges to the optimal (in terms of the error rate inflicted at the victim and the energy used) jamming strategy. Even more importantly, we prove that the rate of convergence to the optimal jamming strategy is sub-linear, i.e. the learning is fast in comparison to existing reinforcement learning algorithms, which is particularly important in dynamically changing wireless environments. Also, we characterize the performance of the proposed bandit-based learning algorithm against multiple static and adaptive transmitter-receiver pairs.

The 3-user multiple-input single-output (MISO) broadcast channel (BC) with hybrid channel state information at the transmitter (CSIT) is considered. In this framework, there is perfect and instantaneous CSIT from a subset of users and delayed CSIT from the remaining users. We present new results on the degrees of freedom (DoF) of the 3-user MISO BC with hybrid CSIT. In particular, for the case of 2 transmit antennas, we show that with perfect CSIT from one user and delayed CSIT from the remaining two users, the optimal DoF is 5/3. For the case of 3 transmit antennas and the same hybrid CSIT setting, it is shown that a higher DoF of 9/5 is achievable and this result improves upon the best known bound. Furthermore, with 3 transmit antennas, and the hybrid CSIT setting in which there is perfect CSIT from two users and delayed CSIT from the third one, a novel scheme is presented which achieves 9/4 DoF. Our results also reveal new insights on how to utilize hybrid channel knowledge for multi-user scenarios.

Distributed storage systems in the presence of a wiretapper are considered. A distributed storage system (DSS) is parameterized by three parameters (n, k,d), in which a file stored across n distributed nodes, can be recovered from any k out of n nodes. If a node fails, any d out of (n-1) nodes help in the repair of the failed node. For such a (n,k,d)-DSS, two types of wiretapping scenarios are investigated: (a) Type-I (node) adversary which can wiretap the data stored on any l4, we present extensions of these results to a (n, n-1,n-1)-DSS, in presence of a Type-II adversary that can observe the repair data of any l=(n-2) nodes. The key technical contribution of this work is in developing novel information theoretic converse proofs for the Type-II adversarial scenario. From our results, we show that in the presence of Type-II attacks, the only efficient point in the storage-vs-exact-repair-bandwidth tradeoff is the MBR (minimum bandwidth regenerating) point. This is in sharp contrast to the case of a Type-I attack in which the storage-vs-exact-repair-bandwidth tradeoff allows a spectrum of operating points beyond the MBR point., Comment: submitted to IEEE Transactions on Information Theory

Jamming attacks can significantly impact the performance of wireless communication systems. In addition to reducing the capacity, such attacks may lead to insurmountable overhead in terms of re-transmissions and increased power consumption. In this paper, we consider the multiple-input single-output (MISO) broadcast channel (BC) in the presence of a jamming attack in which a subset of the receivers can be jammed at any given time. Further, countermeasures for mitigating the effects of such jamming attacks are presented. The effectiveness of these anti-jamming countermeasures is quantified in terms of the degrees-of-freedom (DoF) of the MISO BC under various assumptions regarding the availability of the channel state information (CSIT) and the jammer state information at the transmitter (JSIT). The main contribution of this paper is the characterization of the DoF region of the two user MISO BC under various assumptions on the availability of CSIT and JSIT. Partial extensions to the multi-user broadcast channels are also presented., Comment: submitted to IEEE Transactions on Information Theory