No Arabic abstract
Existing tag signal detection algorithms inevitably suffer from a high bit error rate (BER) due to the difficulties in estimating the channel state information (CSI). To eliminate the requirement of channel estimation and to improve the system performance, in this paper, we adopt a deep transfer learning (DTL) approach to implicitly extract the features of communication channel and directly recover tag symbols. Inspired by the powerful capability of convolutional neural networks (CNN) in exploring the features of data in a matrix form, we design a novel covariance matrix aware neural network (CMNet)-based detection scheme to facilitate DTL for tag signal detection, which consists of offline learning, transfer learning, and online detection. Specifically, a CMNet-based likelihood ratio test (CMNet-LRT) is derived based on the minimum error probability (MEP) criterion. Taking advantage of the outstanding performance of DTL in transferring knowledge with only a few training data, the proposed scheme can adaptively fine-tune the detector for different channel environments to further improve the detection performance. Finally, extensive simulation results demonstrate that the BER performance of the proposed method is comparable to that of the optimal detection method with perfect CSI.
We consider an ambient backscatter communication (AmBC) system aided by an intelligent reflecting surface (IRS). The optimization of the IRS to assist AmBC is extremely difficult when there is no prior channel knowledge, for which no design solutions are currently available. We utilize a deep reinforcement learning-based framework to jointly optimize the IRS and reader beamforming, with no knowledge of the channels or ambient signal. We show that the proposed framework can facilitate effective AmBC communication with a detection performance comparable to several benchmarks under full channel knowledge.
We investigate methods for experimental performance enhancement of auto-encoders based on a recurrent neural network (RNN) for communication over dispersive nonlinear channels. In particular, our focus is on the recently proposed sliding window bidirectional RNN (SBRNN) optical fiber autoencoder. We show that adjusting the processing window in the sequence estimation algorithm at the receiver improves the reach of simple systems trained on a channel model and applied as is to the transmission link. Moreover, the collected experimental data was used to optimize the receiver neural network parameters, allowing to transmit 42 Gb/s with bit-error rate (BER) below the 6.7% hard-decision forward error correction threshold at distances up to 70km as well as 84 Gb/s at 20 km. The investigation of digital signal processing (DSP) optimized on experimental data is extended to pulse amplitude modulation with receivers performing sliding window sequence estimation using a feed-forward or a recurrent neural network as well as classical nonlinear Volterra equalization. Our results show that, for fixed algorithm memory, the DSP based on deep learning achieves an improved BER performance, allowing to increase the reach of the system.
Ambient backscatter communications is an emerging paradigm and a key enabler for pervasive connectivity of low-powered wireless devices. It is primarily beneficial in the Internet of things (IoT) and the situations where computing and connectivity capabilities expand to sensors and miniature devices that exchange data on a low power budget. The premise of the ambient backscatter communication is to build a network of devices capable of operating in a battery-free manner by means of smart networking, radio frequency (RF) energy harvesting and power management at the granularity of individual bits and instructions. Due to this innovation in communication methods, it is essential to investigate the performance of these devices under practical constraints. To do so, this article formulates a model for wireless-powered ambient backscatter devices and derives a closed-form expression of outage probability under Rayleigh fading. Based on this expression, the article provides the power-splitting factor that balances the tradeoff between energy harvesting and achievable data rate. Our results also shed light on the complex interplay of a power-splitting factor, amount of harvested energy, and the achievable data rates.
Ambient backscatter communication (AmBC) is becoming increasingly popular for enabling green communication amidst the continual development of the Internet-of-things paradigm. Efforts have been put into backscatter signal detection as the detection performance is limited by the low signal-to-interference-plus-noise ratio (SINR) of the signal at the receiver. The low SINR can be improved by adopting a multi-antenna receiver. In this paper, the optimum multi-antenna receiver that does not impose any constraints on the types of binary modulation performed by the backscatter device and the waveform used by the ambient source system is studied. The proposed receiver owns a simple structure formed by two beamformers. Bit error rate (BER) performances of the optimum receiver are derived under constant-amplitude ambient signal and Gaussian-distributed ambient signal. Moreover, to facilitate the implementation of the optimum receiver, a simplified receiver is proposed and practical approximations to required beamformers are provided. The derived optimum receiver avoids the complex direct path interference cancellation and coherent reception, but exploits the fact that backscatter signal changes the composite channel impinging at the receiver and the directivity of receiver antenna array. Comparative simulation results show that the performance of the optimum receiver achieves the same performance as the coherent receiver even though it realizes non-coherent reception. The studied receivers provide high flexibility for implementing simple and low-cost receivers in different AmBC systems.
In this letter, we propose to employ reconfigurable intelligent surfaces (RISs) for enhancing the D2D underlaying system performance. We study the joint power control, receive beamforming, and passive beamforming for RIS assisted D2D underlaying cellular communication systems, which is formulated as a sum rate maximization problem. To address this issue, we develop a block coordinate descent method where uplink power, receive beamformer and refection phase shifts are alternatively optimized. Then, we provide the closed-form solutions for both uplink power and receive beamformer. We further propose a quadratic transform based semi-definite relaxation algorithm to optimize the RIS phase shifts, where the original passive beamforming problem is translated into a separable quadratically constrained quadratic problem. Numerical results demonstrate that the proposed RIS assisted design significantly improves the sum-rate performance.