Beam management is a strategy to unify beamforming and channel state information (CSI) acquisition with large antenna arrays in 5G. Codebooks serve multiple uses in beam management including beamforming reference signals, CSI reporting, and analog beam training. In this paper, we propose and evaluate a machine learning-refined codebook design process for extremely large multiple-input multiple- output (X-MIMO) systems. We propose a neural network and beam selection strategy to design the initial access and refinement codebooks using end-to-end learning from beamspace representations. The algorithm, called Extreme-Beam Management (X-BM), can significantly improve the performance of extremely large arrays as envisioned for 6G and capture realistic wireless and physical layer aspects. Our results show an 8dB improvement in initial access and overall effective spectral efficiency improvements compared to traditional codebook methods.
more »
« less
This content will become publicly available on June 9, 2025
Custom Over-the-air Scalable mmWave Testbed for Fast TTD-Based Rainbow Beam Training
Millimeter-wave (mmWave) systems require a large
number of antennas, which makes the beam training challenging
and time-consuming for conventional phased arrays. Recently,
a true-time-delay (TTD) array-based beam training algorithm
has been shown as an effective solution to overcome the training
overhead in large arrays. In this paper, we present a custombuilt
over-the-air (OTA) testbed to study the effects of hardware
impairments on the TTD-based beam training and verify its
feasibility in a real system. We proposed an orthogonal matching
pursuit (OMP) based reconstruction algorithm along with a phase
calibration dictionary to combat nonidealities such as strong
frequency selectivity and phase misalignment in the received raw
IQ signal. Post-processing results showed that with the nonideality
effects properly handled, the 3D TTD beam training algorithm
can achieve high AOA estimation accuracy.
more »
« less
- Award ID(s):
- 1955306
- PAR ID:
- 10538243
- Publisher / Repository:
- IEEE
- Date Published:
- ISBN:
- 978-1-7281-9054-9
- Page Range / eLocation ID:
- 1903 to 1908
- Format(s):
- Medium: X
- Location:
- Denver, CO, USA
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
more » « less
Abstract Understanding transit times (TT) and residence times (RT) distributions of water in catchments has recently received a great deal of attention in hydrologic research since it can inform about important processes relevant to the quality of water delivered by streams and landscape resilience to anthropogenic inputs. The theory of transit time distributions (TTD) is a practical framework for understanding TT of water in natural landscapes but, due to its lumped nature, it can only hint at the possible internal processes taking place in the subsurface. While allowing for the direct observation of water movement, Electrical Resistivity Imaging (ERI) can be leveraged to better understand the internal variability of water ages within the subsurface, thus enabling the investigation of the physical processes controlling the time‐variability of TTD. In this study, we estimated time‐variable TTD of a bench‐scale bare‐soil sloping soil lysimeter through the StorAge Selection (SAS) framework, a traditional lumped‐systems method, based on sampling of output tracer concentrations, as well as through an ERI SAS one, based on spatially distributed images of water ages. We compared the ERI‐based SAS results with the output‐based estimates to discuss the viability of ERI at laboratory experiments for understanding TTD. The ERI‐derived images of the internal evolution of water ages were able to elucidate the internal mechanisms driving the time‐variability of ages of water being discharged by the system, which was characterized by a delayed discharge of younger water starting at the highest storage level and continuing throughout the water table recession.
-
more » « less
Abstract Machine learning (ML) tools are able to learn relationships between the inputs and outputs of large complex systems directly from data. However, for time-varying systems, the predictive capabilities of ML tools degrade if the systems are no longer accurately represented by the data with which the ML models were trained. For complex systems, re-training is only possible if the changes are slow relative to the rate at which large numbers of new input-output training data can be non-invasively recorded. In this work, we present an approach to deep learning for time-varying systems that does not require re-training, but uses instead an adaptive feedback in the architecture of deep convolutional neural networks (CNN). The feedback is based only on available system output measurements and is applied in the encoded low-dimensional dense layers of the encoder-decoder CNNs. First, we develop an inverse model of a complex accelerator system to map output beam measurements to input beam distributions, while both the accelerator components and the unknown input beam distribution vary rapidly with time. We then demonstrate our method on experimental measurements of the input and output beam distributions of the HiRES ultra-fast electron diffraction (UED) beam line at Lawrence Berkeley National Laboratory, and showcase its ability for automatic tracking of the time varying photocathode quantum efficiency map. Our method can be successfully used to aid both physics and ML-based surrogate online models to provide non-invasive beam diagnostics.
-
Current understanding of the dynamic and slow flow paths that support streamflow in mountain headwater catchments is inhibited by the lack of long-term hydrogeochemical data and the frequent use of short residence time age tracers. To address this, the current study combined the traditional mean transit time and the state-of-the-art fraction of young water ( F yw ) metrics with stable water isotopes and tritium tracers to characterize the dynamic and slow flow paths at Marshall Gulch, a sub-humid headwater catchment in the Santa Catalina Mountains, Arizona, USA. The results show that F yw varied significantly with period when using sinusoidal curve fitting methods (e.g., iteratively re-weighted least squares or IRLS), but not when using the transit time distribution (TTD)-based method. Therefore, F yw estimates from TTD-based methods may be particularly useful for intercomparison of dynamic flow behavior between catchments. However, the utility of 3 H to determine F yw in deeper groundwater was limited due to both data quality and inconsistent seasonal cyclicity of the precipitation 3 H time series data. Although a Gamma-type TTD was appropriate to characterize deep groundwater, there were large uncertainties in the estimated Gamma TTD shape parameter arising from the short record length of 3 H in deep groundwater. This work demonstrates how co-application of multiple metrics and tracers can yield a more complete understanding of the dynamic and slow flow paths and observable deep groundwater storage volumes that contribute to streamflow in mountain headwater catchments.more » « less
-
more » « less
Abstract In this study, we explore the use of unsteady transit time distribution (TTD) theory to model solute transport in biofilters, a popular form of nature‐based or “green” storm water infrastructure (GSI). TTD theory has the potential to address many unresolved challenges associated with predicting pollutant fate and transport through these systems, including unsteadiness in the water balance (time‐varying inflows, outflows, and storage), unsteadiness in pollutant loading, time‐dependent reactions, and scale‐up to GSI networks and urban catchments. From a solution to the unsteady age conservation equation under uniform sampling, we derive an explicit expression for solute breakthrough during and after one or more storm events. The solution is calibrated and validated with breakthrough data from 17 simulated storms at a field‐scale biofilter test facility in Southern California, using bromide as a conservative tracer. TTD theory closely reproduces bromide breakthrough concentrations, provided that lateral exchange with the surrounding soil is accounted for. At any given time, according to theory, more than half of the water in storage is from the most recent storm, while the rest is a mixture of penultimate and earlier storms. Thus, key management endpoints, such as the pollutant treatment credit attributable to GSI, are likely to depend on the evolving age distribution of water stored and released by these systems.
