Cellular service providers (CSPs) require predicting the network performance for various reasons such as analyzing the impact of planned configuration changes and large-scale events on the network. Although network configurations are widely considered as key predictors of performance, we claim that they are insufficient for accurately predicting cellular network performance. The cellular networks are impacted by unmeasured external factors (e.g., weather, called latents), therefore, the performance prediction based solely on configurations may result in confounding effects. We show that the Mobility, Access, and Traffic (MAT) metrics should be considered in addition as network performance predictors. Using a large dataset collected from a live cellular network, we validate the claim and show the benefit of using MAT metrics for accurate performance prediction.

Cellular service providers (CSPs) aim to optimize network performance and enhance user experience by tuning network configurations. However, this process often requires continuous live network testing, which incurs significant operational costs. In this paper, we focus on predicting the impact of configuration changes using historical data, thereby reducing the need for live network tests. A key challenge in developing such a model is accounting for unobserved external factors (e.g., weather, referred to as latents) that can introduce confounding effects between configurations and performance metrics. To address this, we employ intermediate network metrics, called Mobility, Access, and Traffic (MAT) metrics, which are influenced by both configurations and latents, and in turn, affect performance metrics. We introduce Configuration Impact Prediction Analysis Toolkit (CIPAT), a novel two-stage toolkit developed using a comprehensive real-world dataset from live LTE networks. Our evaluation demonstrates that CIPAT enables CSPs to predict the performance impact of proposed configuration changes with up to 86% accuracy and 85% efficacy, thereby reducing the operational costs associated with configuration tuning.

Sensor-aided beamforming reduces the overheads associated with beam training in millimeter-wave (mmWave) multi-input-multi-output (MIMO) communication systems. Most prior work, though, neglects the challenges associated with establishing multi-user (MU) communication links in mmWave MIMO systems. In this paper, we propose a new framework for sensor-aided beam training in MU mmWave MIMO system. We leverage the beamspace representation of the channel that contains only the angles-of-departure (AoDs) of the channel’s significant multipath components. We show that a deep neural network (DNN)-based multimodal sensor fusion framework can estimate the beamspace representation of the channel using sensor data. To aid the DNN training, we introduce a novel supervised soft-contrastive loss (SSCL) function that leverages the inherent similarity between channels to extract similar features from the sensor data for similar channels. Finally, we design an MU beamforming strategy that uses the estimated beamspaces of the channels to select analog precoders for all users in a way that prevents transmission to multiple users over the same directions. Compared to the baseline, our approach achieves more than 4 times improvement in the median sum-spectral efficiency (SE) at 42 dBm equivalent isotropic radiated power (EIRP) with 4 active users. This demonstrates that sensor data can provide more channel information than previously explored, with significant implications for machine learning-based communication and sensing systems.

Millimeter wave (mmWave) technology can achieve high-speed communication due to the large available spectrum. Furthermore, the use of directional beams in mmWave system provides a natural defense against physical layer security attacks. In practice, however, the beams are imperfect due to mmWave hardware limitations such as the low-resolution of the phase shifters. These imperfections in the beam pattern introduce an energy leakage that can be exploited by an eavesdropper. To defend against such eavesdropping attacks, we propose a directional modulation-based defense technique where the transmitter applies random circulant shifts of a beamformer. We show that the use of random circulant shifts together with appropriate phase adjustment induces artificial phase noise (APN) in the directions different from that of the target receiver. Our method corrupts the phase at the eavesdropper without affecting the communication link of the target receiver. We also experimentally verify the APN induced due to circulant shifts, using channel measurements from a 2-bit mmWave phased array testbed. Using simulations, we study the performance of the proposed defense technique against a greedy eavesdropping strategy in a vehicle-to-infrastructure scenario. The proposed technique achieves better defense than the antenna subset modulation, without compromising on the communication link with the target receiver.

Eavesdropping attacks are a severe threat to millimeter-wave (mmWave) networks that use low-resolution phased arrays. Although directional beamforming in mmWave phased arrays provides natural defense against eavesdropping, the use of low-resolution phase shifters induces energy leakage into unintended directions. This energy leakage can be exploited by the adversaries. In this paper, we propose a directional modulation (DM)-based defense against eavesdropping attacks on low-resolution phased arrays. Our defense technique applies random circulant shifts to the beamformer for every symbol transmission. By appropriately adjusting the phase of the transmitted symbol, the transmitter (TX) can maintain a high-quality link with the receiver while corrupting the symbols transmitted along unintended directions. We theoretically analyze the secrecy mutual information (SMI) achieved by the proposed defense mechanism and show that our defense induces artificial phase noise (APN) along unintended directions, which increases the SMI of the system. Finally, we numerically show the superiority of the proposed defense technique over the state-of-the-art defense techniques.

Current wireless networks employ sophisticated multi-user transmission techniques to fully utilize the physical layer resources for data transmission. At the MAC layer, these techniques rely on a semi-static map that translates the channel quality of users to the potential transmission rate (more precisely, a map from the Channel Quality Index to the Modulation and Coding Scheme) for user selection and scheduling decisions. However, such a static map does not adapt to the actual deployment scenario and can lead to large performance losses. Furthermore, adaptively learning this map can be inefficient, particularly when there are a large number of users. In this work, we make this learning efficient by clustering users. Specifically, we develop an online learning approach that jointly clusters users and channel-states, and learns the associated rate regions of each cluster. This approach generates a scenario-specific map that replaces the static map that is currently used in practice. Furthermore, we show that our learning algorithm achieves sub-linear regret when compared to an omniscient genie. Next, we develop a user selection algorithm for multi-user scheduling using the learned user-clusters and associated rate regions. Our algorithms are validated on the WiNGS simulator from AT&T Labs, that implements the PHY/MAC stack and simulates the channel. We show that our algorithm can efficiently learn user clusters and the rate regions associated with the user sets for any observed channel state. Moreover, our simulations show that a deployment-scenario-specific map significantly outperforms the current static map approach for resource allocation at the MAC layer.

Designing efficient and robust beam alignment strategies for millimeter wave (mmWave) systems is important for overcoming training overheads and practical hardware impairments. In this work, we leverage side information in the form of prior knowledge of the angular support of the propagation channel (direction information) to design a compressive sensing (CS) based beam alignment algorithm. Existing CS based channel estimation approaches assume perfect phase information of the measurements, which is not the case with the low-cost off-the-shelf mmWave phased arrays. Instead, we develop a two-stage algorithm where we use the magnitude of measurements (aka non-coherent measurements); using phase retrieval (PR) followed by sparse recovery, we estimate the channel gain across various (quantized) spatial angles. To validate the proposed algorithm, we develop a fully reconfigurable mmWave testbed with custom-made 2-bit phased arrays. We perform a careful calibration to the phased arrays, thus enabling generations of precise desired beam patterns. Our implementation and real experiments validate both the proposed algorithm and calibration process by demonstrating consistency between the experimental results and the theoretical analysis.

Recent advancements in Full Duplex (FD) radio have built a promising idea for faster channel sensing in cognitive radio. Full duplex cognitive radio (FDCR) provides an efficient way to utilize the idle channel without interrupting the ongoing transmission. Currently, non-parametric sensing techniques like energy detection and its modified techniques are implemented for FDCR. In this paper, we introduce a Goodness of Fit based distribution-free sensing in FDCR. With Monte Carlo simulations and analytical approximation, we show that the proposed technique outperforms energy detection and other goodness-of-fit based sensing algorithms for FDCR.

A postphotodetection adaptive phase alignment system using an aperture array of photodetectors is presented to reduce the signal loss in an optical (free-space) heterodyne receiver resulting from wavefront misalignment (tilt) on a satellite platform. This paper compares two kinds of rectangular aperture configurations-full aperture and array aperture configurations-via a software simulation study of the error performance after DPSK demodulation for different angles of arrival (tilt) of the received signal wavefront. For the array configuration, an adaptive phase alignment system is used that phase aligns the signals from the different photodetector array elements, and constructively adds them to yield a higher signal magnitude as compared to that of signal of a single-element photodetector of the same total area. The optimum aperture length for a given wavefront misalignment is derived, and is verified via simulation.

We present the general formulation for the adaptive equalization by distribution learning introduced by Adali (see Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing, vol.3, p.297-300, April 1994) In this framework, adaptive equalization can be viewed as a parametrized conditional distribution estimation problem where the parameter estimation is achieved by learning on a multilayer perceptron (MLP). Depending on the definition of the conditioning event set either supervised or unsupervised (blind) algorithms in either recurrent or feedforward networks result. We derive the least relative entropy (LRE) algorithm for binary data communications and analyze its statistical and dynamical properties. Particularly, we show that LRE learning is consistent and asymptotically normal by working in the partial likelihood estimation framework, and that the algorithm can always recover from convergence at the wrong extreme as opposed to the MSE based MLP's by working within an extension of the well-formed cost functions framework of Wittner and Denker (1988). We present simulation examples to demonstrate this fact.