arXiv subjects

Wolfgang Utschick

Publications and source records attributed to Wolfgang Utschick.

At least 109 records · Page 6Linked to original sources

arXiv2021

Learning the CSI Denoising and Feedback Without Supervision

In this work, we develop a joint denoising and feedback strategy for channel state information in frequency division duplex systems. In such systems, the biggest challenge is the overhead incurred when the mobile terminal has to send the downlink channel state information or corresponding partial information to the base station, where the complete estimates can subsequently be restored. To this end, we propose a novel learning-based framework for denoising and compression of channel estimates. Unlike existing studies, we extend a recently proposed approach and show that based solely on noisy uplink data available at the base station, it is possible to learn an autoencoder neural network that generalizes to downlink data. Subsequently, half of the autoencoder can be offloaded to the mobile terminals to generate channel feedback there as efficiently as possible, without any training effort at the terminals or corresponding transfer of training data. Numerical simulations demonstrate the excellent performance of the proposed method.

cs.IT↗

arXiv2021

An Asymptotically Optimal Approximation of the Conditional Mean Channel Estimator based on Gaussian Mixture Models

This paper investigates a channel estimator based on Gaussian mixture models (GMMs). We fit a GMM to given channel samples to obtain an analytic probability density function (PDF) which approximates the true channel PDF. Then, a conditional mean channel estimator corresponding to this approximating PDF is computed in closed form and used as an approximation of the optimal conditional mean estimator based on the true channel PDF. This optimal estimator cannot be calculated analytically because the true channel PDF is generally not available. To motivate the GMM-based estimator, we show that it converges to the optimal conditional mean estimator as the number of GMM components is increased. In numerical experiments, a reasonable number of GMM components already shows promising estimation results.

cs.IT↗

arXiv2021

Novelty Detection and Analysis of Traffic Scenario Infrastructures in the Latent Space of a Vision Transformer-Based Triplet Autoencoder

Detecting unknown and untested scenarios is crucial for scenario-based testing. Scenario-based testing is considered to be a possible approach to validate autonomous vehicles. A traffic scenario consists of multiple components, with infrastructure being one of it. In this work, a method to detect novel traffic scenarios based on their infrastructure images is presented. An autoencoder triplet network provides latent representations for infrastructure images which are used for outlier detection. The triplet training of the network is based on the connectivity graphs of the infrastructure. By using the proposed architecture, expert-knowledge is used to shape the latent space such that it incorporates a pre-defined similarity in the neighborhood relationships of an autoencoder. An ablation study on the architecture is highlighting the importance of the triplet autoencoder combination. The best performing architecture is based on vision transformers, a convolution-free attention-based network. The presented method outperforms other state-of-the-art outlier detection approaches.

cs.CV↗

arXiv2021

Distributed Joint Multi-cell Optimization of IRS Parameters with Linear Precoders

We present distributed methods for jointly optimizing Intelligent Reflecting Surface (IRS) phase-shifts and beamformers in a cellular network. The proposed schemes require knowledge of only the intra-cell training sequences and corresponding received signals without explicit channel estimation. Instead, an SINR objective is estimated via sample means and maximized directly. This automatically includes and mitigates both intra- and inter-cell interference provided that the uplink training is synchronized across cells. Different schemes are considered that limit the set of known training sequences from interferers. With MIMO links an iterative synchronous bi-directional training scheme jointly optimizes the IRS parameters with the beamformers and combiners. Simulation results show that the proposed distributed methods show a modest performance degradation compared to centralized channel estimation schemes, which estimate and exchange all cross-channels between cells, and perform significantly better than channel estimation schemes which ignore the inter-cell interference.

cs.IT↗

arXiv2021

Learning a Compressive Sensing Matrix with Structural Constraints via Maximum Mean Discrepancy Optimization

We introduce a learning-based algorithm to obtain a measurement matrix for compressive sensing related recovery problems. The focus lies on matrices with a constant modulus constraint which typically represent a network of analog phase shifters in hybrid precoding/combining architectures. We interpret a matrix with restricted isometry property as a mapping of points from a high- to a low-dimensional hypersphere. We argue that points on the low-dimensional hypersphere, namely, in the range of the matrix, should be uniformly distributed to increase robustness against measurement noise. This notion is formalized in an optimization problem which uses one of the maximum mean discrepancy metrics in the objective function. Recent success of such metrics in neural network related topics motivate a solution of the problem based on machine learning. Numerical experiments show better performance than random measurement matrices that are generally employed in compressive sensing contexts. Further, we adapt a method from the literature to the constant modulus constraint. This method can also compete with random matrices and it is shown to harmonize well with the proposed learning-based approach if it is used as an initialization. Lastly, we describe how other structural matrix constraints, e.g., a Toeplitz constraint, can be taken into account, too.

eess.SP↗

arXiv2021

Learning the CSI Recovery in FDD Systems

We propose an innovative machine learning-based technique to address the problem of channel acquisition at the base station in frequency division duplex systems. In this context, the base station reconstructs the full channel state information in the downlink frequency range based on limited downlink channel state information feedback from the mobile terminal. The channel state information recovery is based on a convolutional neural network which is trained exclusively on collected channel state samples acquired in the uplink frequency domain. No acquisition of training samples in the downlink frequency range is required at all. Finally, after a detailed presentation and analysis of the proposed technique and its performance, the "transfer learning'' assumption of the convolutional neural network that is central to the proposed approach is validated with an analysis based on the maximum mean discrepancy metric.

cs.IT↗

arXiv2021

A Machine Learning Approach to DoA Estimation and Model Order Selection for Antenna Arrays with Subarray Sampling

In this paper, we study the problem of direction of arrival estimation and model order selection for systems employing subarray sampling. Thereby, we focus on scenarios, where the number of active sources is not smaller than the number of simultaneously sampled antenna elements. For this purpose, we propose new schemes based on neural networks and estimators that combine neural networks with gradient steps on the likelihood function. These methods are able to outperform existing estimators in terms of mean squared error and model selection accuracy, especially in the low snapshot domain, at a drastically lower computational complexity.

eess.SP↗

arXiv2021

Unsupervised Learning of Adaptive Codebooks for Deep Feedback Encoding in FDD Systems

In this work, we propose a joint adaptive codebook construction and feedback generation scheme in frequency division duplex (FDD) systems. Both unsupervised and supervised deep learning techniques are used for this purpose. Based on a recently discovered equivalence of uplink (UL) and downlink (DL) channel state information (CSI) in terms of neural network learning, the codebook and associated deep encoder for feedback signaling is based on UL data only. Subsequently, the feedback encoder can be offloaded to the mobile terminals (MTs) to generate channel feedback there as efficiently as possible, without any training effort at the terminals or corresponding transfer of training and codebook data. Numerical simulations demonstrate the promising performance of the proposed method.

cs.IT↗

arXiv2021

An Entropy Based Outlier Score and its Application to Novelty Detection for Road Infrastructure Images

A novel unsupervised outlier score, which can be embedded into graph based dimensionality reduction techniques, is presented in this work. The score uses the directed nearest neighbor graphs of those techniques. Hence, the same measure of similarity that is used to project the data into lower dimensions, is also utilized to determine the outlier score. The outlier score is realized through a weighted normalized entropy of the similarities. This score is applied to road infrastructure images. The aim is to identify newly observed infrastructures given a pre-collected base dataset. Detecting unknown scenarios is a key for accelerated validation of autonomous vehicles. The results show the high potential of the proposed technique. To validate the generalization capabilities of the outlier score, it is additionally applied to various real world datasets. The overall average performance in identifying outliers using the proposed methods is higher compared to state-of-the-art methods. In order to generate the infrastructure images, an openDRIVE parsing and plotting tool for Matlab is developed as part of this work. This tool and the implementation of the entropy based outlier score in combination with Uniform Manifold Approximation and Projection are made publicly available.

cs.LG↗

arXiv2020

Mixed Monotonic Programming for Fast Global Optimization

While globally optimal solutions to many convex programs can be computed efficiently in polynomial time, this is, in general, not possible for nonconvex optimization problems. Therefore, locally optimal approaches or other efficient suboptimal heuristics are usually applied for practical implementations. However, there is also a strong interest in computing globally optimal solutions of nonconvex problems in offline simulations in order to benchmark the faster suboptimal algorithms. Global solutions often rely on monotonicity properties. A common approach is to reformulate problems into a canonical monotonic optimization problem where the monotonicity becomes evident, but this often comes at the cost of nested optimizations, increased numbers of variables, and/or slow convergence. The framework of mixed monotonic programming (MMP) proposed in this paper avoids such performance-deteriorating reformulations by revealing hidden monotonicity properties directly in the original problem formulation. By means of a wide range of application examples from the area of signal processing for communications (including energy efficiency for green communications, resource allocation in interference networks, scheduling for fairness and quality of service, as well as beamformer design in multiantenna systems), we demonstrate that the novel MMP approach leads to tremendous complexity reductions compared to state-of-the-art methods for global optimization. However, the framework is not limited to optimizing communication systems, and we expect that similar speed-ups can be obtained for optimization problems from other areas of research as well.

cs.IT↗

arXiv2020

Improper Signaling versus Time-Sharing in the Two-User Gaussian Interference Channel with TIN

So-called improper complex signals have been shown to be beneficial in the single-antenna two-user Gaussian interference channel under the assumptions that all input signals are Gaussian and that we treat interference as noise (TIN). This result has been obtained under a restriction to pure strategies without time-sharing, and it was extended to the case where the rates, but not the transmit powers, may be averaged over several transmit strategies. In this paper, we drop such restrictions and discuss the most general case of coded time-sharing, where both the rates and the powers may be averaged. Since coded time-sharing can in general not be expressed by means of a convex hull of the rate region, we have to account for the possibility of time-sharing already during the optimization of the transmit strategy. By means of a novel channel enhancement argument, we prove a surprising result: proper signals are optimal if coded time-sharing is allowed. In addition to establishing this result, we present an algorithm to compute the corresponding achievable rate region.

cs.IT↗

arXiv2019

Two-User SIMO Interference Channel with TIN: Improper Signaling versus Time-Sharing

In the two-user Gaussian interference channel with Gaussian inputs and treating interference as noise (TIN), improper complex signals can be beneficial if time-sharing is not allowed or if only the data rates are averaged over several transmit strategies (convex hull formulation). On the other hand, proper (circularly symmetric) signals have recently been shown to be optimal if coded time-sharing is considered, i.e., if both the data rates and the transmit powers are averaged. In this paper, we show that both conclusions remain the same if single-input multiple-output (SIMO) systems with multiple antennas at the receivers are considered. The proof for the case with coded time-sharing is via a novel enhanced channel concept for the two-user SIMO interference channel, which turns out to deliver a tight outer bound to the TIN rate region with coded time-sharing. The result for the case without coded time-sharing is demonstrated by studying specific examples in which a newly proposed composite real gradient-projection method for improper signaling can outperform the globally optimal proper signaling strategy. In addition, we discuss how the achievable TIN rate region with coded time-sharing can be computed numerically.

cs.IT↗

arXiv2019

Reproducible Evaluation of Neural Network Based Channel Estimators And Predictors Using A Generic Dataset

A low-complexity neural network based approach for channel estimation was proposed recently, where assumptions on the channel model were incorporated into the design procedure of the estimator. Instead of using data from a measurement campaign as done in previous work, we evaluate the performance of the convolutional neural network (CNN) based channel estimator by using a reproducible mmWave environment of the DeepMIMO dataset. We further propose a neural network based predictor which is derived by starting from the linear minimum mean squared error (LMMSE) predictor. We start by deriving a weighted sum of LMMSE predictors which is motivated by the structure of the optimal MMSE predictor. This predictor provides an initialization (weight matrices, biases and activation function) to a feed-forward neural network based predictor. With a properly learned neural network, we show that it is possible to easily outperform the LMMSE predictor based on the Jakes assumption of the underlying Doppler spectrum in an reproducible indoor scenario of the DeepMIMO dataset.

cs.IT↗

arXiv2019

Learning The MMSE Channel Predictor

We present a neural network based predictor which is derived by starting from the linear minimum mean squared error (LMMSE) predictor and by further making two key assumptions. With these assumptions, we first derive a weighted sum of LMMSE predictors which is motivated by the structure of the optimal MMSE predictor. This predictor provides an initialization (weight matrices, biases and activation function) to a feed-forward neural network based predictor. With a properly learned neural network, we show that under the given channel model assumptions it is possible to easily outperform the LMMSE predictor based on the Jakes assumption of the underlying Doppler spectrum.

cs.IT↗

arXiv2019

Maximizing the Partial Decode-and-Forward Rate in the Gaussian MIMO Relay Channel

It is known that circularly symmetric Gaussian signals are the optimal input signals for the partial decode-and-forward (PDF) coding scheme in the Gaussian multiple-input multiple-output (MIMO) relay channel, but there is currently no method to find the optimal covariance matrices nor to compute the optimal achievable PDF rate since the optimization is a non-convex problem in its original formulation. In this paper, we show that it is possible to find a convex reformulation of the problem by means of an approximation and a primal decomposition. We derive an explicit solution for the inner problems as well as an explicit gradient for the outer problem, so that the efficient cutting-plane method can be applied for solving the outer problem. As the accuracy of this provably convergent algorithm might be impaired by the previous approximation, we additionally propose a modified algorithm, for which we cannot give a converge guarantee, but which provides rigorous upper and lower bounds to the optimum of the original rate maximization. In numerical simulations, these bounds become tight in all considered instances of the problem, showing that the proposed method manages to find the global optimum in all these instances.

cs.IT↗

arXiv2019

Model Order Selection in DoA Scenarios via Cross-Entropy based Machine Learning Techniques

In this paper, we present a machine learning approach for estimating the number of incident wavefronts in a direction of arrival scenario. In contrast to previous works, a multilayer neural network with a cross-entropy objective is trained. Furthermore, we investigate an online training procedure that allows an adaption of the neural network to imperfections of an antenna array without explicitly calibrating the array manifold. We show via simulations that the proposed method outperforms classical model order selection schemes based on information criteria in terms of accuracy, especially for a small number of snapshots and at low signal-to-noise-ratios. Also, the online training procedure enables the neural network to adapt with only a few online training samples, if initialized by offline training on artificial data.

eess.SP↗

arXiv2019

hynet: An Optimal Power Flow Framework for Hybrid AC/DC Power Systems

High-voltage direct current (HVDC) systems are increasingly incorporated into today's AC power grids, necessitating optimal power flow (OPF) tools for the analysis, planning, and operation of such hybrid systems. To this end, we introduce hynet, a Python-based open-source OPF framework for hybrid AC/DC grids with point-to-point and radial multi-terminal HVDC systems. hynet's design promotes ease of use and extensibility, which is supported by the particular mathematical model and software design presented in this paper. The system model features a unified representation of AC and DC subgrids as well as a concise and flexible converter model, which enable the compact description of a hybrid AC/DC power system and its OPF problem. To support convex relaxation based OPF solution techniques, a state space relaxation is introduced to obtain a unified OPF formulation that is analogous to the OPF of AC power systems. This enables the direct generalization of relaxation-related results for AC grids to hybrid AC/DC grids, which is shown for the semidefinite and second-order cone relaxation as well as associated results on exactness and locational marginal prices. Finally, hynet's object-oriented software design is discussed, which provides extensibility via inheritance and standard design patterns, and its robust and competitive performance is illustrated with case studies.

math.OC↗

arXiv2019

Feature- and Structure-Preserving Network Reduction for Large-Scale Transmission Grids

Many countries are currently challenged with the extensive integration of renewable energy sources, which necessitates vast capacity expansion measures. These measures in turn require comprehensive power flow studies, which are often computationally highly demanding. In this work a reduction strategy for large-scale grid models is introduced which not only reduces the model complexity but also preserves the structure and designated grid features. The objective is to ensure that areas crucial to the behavior and the relation of all elements to their physical counterparts remain unchanged. This is accomplished through a specifically designed reduction method for suitable areas identified through topological, electrical and market-based approaches for which we provide an open-source implementation. We show that the proposed strategy adapts to various models and accomplishes a strong reduction of buses and branches while retaining a low dispatch and branch flow deviation. Furthermore, the accuracy of the reduction generalizes well to other scenarios.

math.OC↗