skip to main content


The NSF Public Access Repository (NSF-PAR) system and access will be unavailable from 10:00 PM ET on Friday, December 8 until 2:00 AM ET on Saturday, December 9 due to maintenance. We apologize for the inconvenience.

Title: Machine Learning-based Reconfigurable Intelligent Surface-aided MIMO Systems
Reconfigurable intelligent surface (RIS) technology has recently emerged as a spectral- and cost-efficient approach for wireless communications systems. However, existing hand-engineered schemes for passive beamforming design and optimization of RIS, such as the alternating optimization (AO) approaches, require a high computational complexity, especially for multiple-input-multiple-output (MIMO) systems. To over-come this challenge, we propose a low-complexity unsupervised learning scheme, referred to as learning-phase-shift neural net-work (LPSNet), to efficiently find the solution to the spectral efficiency maximization problem in RIS-aided MIMO systems. In particular, the proposed LPSNet has an optimized input structure and requires a small number of layers and nodes to produce efficient phase shifts for the RIS. Simulation results for a 16 × 2 MIMO system assisted by an RIS with 40 elements show that the LPSNet achieves 97.25% of the SE provided by the AO counterpart with more than a 95% reduction in complexity.  more » « less
Award ID(s):
2107182 2030029
Author(s) / Creator(s):
; ; ; ; ;
Date Published:
Journal Name:
Proc. IEEE Workshop on Signal Processing Advances in Wireless Communications (SPAWC)
Page Range / eLocation ID:
101 to 105
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Millimeter-wave (mmWave) communications is a key enabler towards realizing enhanced Mobile Broadband (eMBB) as a key promise of 5G and beyond, due to the abundance of bandwidth available at mmWave bands. An mmWave coverage map consists of blind spots due to shadowing and fading especially in dense urban environments. Beam-forming employing massive MIMO is primarily used to address high attenuation in the mmWave channel. Due to their ability in manipulating the impinging electromagnetic waves in an energy-efficient fashion, Reconfigurable Intelligent Surfaces (RISs) are considered a great match to complement the massive MIMO systems in realizing the beam-forming task and therefore effectively filling in the mmWave coverage gap. In this paper, we propose a novel RIS architecture, namely RIS-UPA where the RIS elements are arranged in a Uniform Planar Array (UPA). We show how RIS-UPA can be used in an RIS-aided MIMO system to fill the coverage gap in mmWave by forming beams of a custom footprint, with optimized main lobe gain, minimum leakage, and fairly sharp edges. Further, we propose a configuration for RIS-UPA that can support multiple two-way communication pairs, simultaneously. We theoretically obtain closed-form low-complexity solutions for our design and validate our theoretical findings by extensive numerical experiments. 
    more » « less
  2. Channel state information (CSI) reporting is important for multiple-input multiple-output (MIMO) wireless transceivers to achieve high capacity and energy efficiency in frequency division duplex (FDD) mode. CSI reporting for massive MIMO systems could consume large bandwidth and degrade spectrum efficiency. Deep learning (DL)-based CSI reporting integrated with channel characteristics has demonstrated success in improving CSI compression and recovery. To further improve the encoding efficiency of CSI feedback, we develop an efficient DL-based compression framework CQNet to jointly tackle CSI compression, codeword quantization, and recovery under the bandwidth constraint. CQNet is directly compatible with other DL-based CSI feedback works for further enhancement. We propose a more efficient quantization scheme in the radial coordinate by introducing a novel magnitude-adaptive phase quantization framework. Compared with traditional CSI reporting, CQNet demonstrates superior CSI feedback efficiency and better CSI reconstruction accuracy. 
    more » « less
  3. UAVs need to communicate along three dimensions (3D) with other aerial vehicles, ranging from above to below, and often need to connect to ground stations. However, wireless transmission in 3D space significantly dissipates power, often hindering the range required for these types of links. Directional transmission is one way to efficiently use available wireless channels to achieve the desired range. While multiple-input multiple-output (MIMO) systems can digitally steer the beam through channel matrix manipulation without needing directional awareness, the power resources required for operating multiple radios on a UAV are often logistically challenging. An alternative approach to streamline resources is the use of phased arrays to achieve directionality in the analog domain, but this requires beam sweeping and results in search-time delay. The complexity and search time can increase with the dynamic mobility pattern of the UAVs in aerial networks. However, if the direction of the receiver is known at the transmitter, the search time can be significantly reduced. In this work, multi-antenna channels between two UAVs in A2A links are analyzed, and based on these findings, an efficient machine learning-based method for estimating the direction of a transmitting node using channel estimates of 4 antennas (2 × 2 MIMO) is proposed. The performance of the proposed method is validated and verified through in-field drone-to-drone measurements. Findings indicate that the proposed method can estimate the direction of the transmitter in the A2A link with 86% accuracy. Further, the proposed direction estimation method is deployable for UAV-based massive MIMO systems to select the directional beam without the need to sweep or search for optimal communication performance. 
    more » « less
  4. With increasing needs of fast and reliable commu- nication between devices, wireless communication techniques are rapidly evolving to meet such needs. Multiple input and output (MIMO) systems are one of the key techniques that utilize multiple antennas for high-throughput and reliable communication. However, increasing the number of antennas in communication also adds to the complexity of channel esti- mation, which is essential to accurately decode the transmitted data. Therefore, development of accurate and efficient channel estimation methods is necessary. We report the performance of machine learning-based channel estimation approaches to enhance channel estimation performance in high-noise envi- ronments. More specifically, bit error rate (BER) performance of 2 × 2 and 4 × 4 MIMO communication systems with space- time block coding model (STBC) and two neural network-based channel estimation algorithms is analyzed. Most significantly, the results demonstrate that a generalized regression neural network (GRNN) model matches BER results of a known-channel communication for 4 × 4 MIMO with 8-bit pilots, when trained in a specific signal to noise ratio (SNR) regime. Moreover, up to 9dB improvement in signal-to-noise ratio (SNR) for a target BER is observed, compared to least square (LS) channel estimation, especially when the model is trained in the low SNR regime. A deep artificial neural network (Deep ANN) model shows worse BER performance compared to LS in all tested environments. These preliminary results present an opportunity for achieving better performance in channel estimation through GRNN and highlight further research topics for deployment in the wild. 
    more » « less
  5. null (Ed.)
    Channel state information (CSI) plays a vital role in scheduling and capacity-approaching transmission optimization of massive MIMO communication systems. In frequency division duplex (FDD) MIMO systems, forward link CSI reconstruction at transmitter relies on CSI feedback from receiving nodes and must carefully weigh the tradeoff between reconstruction accuracy and feedback bandwidth. Recent application of recurrent neural networks (RNN) has demonstrated promising results of massive MIMO CSI feedback compression. However, the cost of computation and memory associated with RNN deep learning remains high. In this work, we exploit channel temporal coherence to improve learning accuracy and feedback efficiency. Leveraging a Markovian model, we develop a deep convolutional neural network (CNN)-based framework called MarkovNet to efficiently encode CSI feedback to improve accuracy and efficiency. We explore important physical insights including spherical normalization of input data and deep learning network optimizations in feedback compression. We demonstrate that MarkovNet provides a substantial performance improvement and computational complexity reduction over the RNN-based work.We demonstrate MarkovNet’s performance under different MIMO configurations and for a range of feedback intervals and rates. CSI recovery with MarkovNet outperforms RNN-based CSI estimation with only a fraction of computational cost. 
    more » « less