Deep Learning For Experimental Hybrid Terrestrial and Satellite Interference Management (original) (raw)
Related papers
Interference Suppression Using Deep Learning: Current Approaches and Open Challenges
IEEE Access
In light of the finite nature of the wireless spectrum and the increasing demand for spectrum use arising from recent technological breakthroughs in wireless communication, the problem of interference continues to persist. Despite recent advancements in resolving interference issues, interference still presents a difficult challenge to effective usage of the spectrum. This is partly due to the rise in the use of license-free and managed shared bands as well as other opportunistic spectrum access solutions. As a result of this, the need for efficient spectrum usage schemes that are robust against interference has never been more important. In the past, most solutions to interference have addressed the problem by using avoidance techniques as well as mitigation approaches based on expert systems. More recently, researchers have successfully explored artificial intelligence/machine learning enabled physical layer techniques, especially deep learning which reduces or compensates for the interfering signal instead of simply avoiding it. In this paper, we address the knowledge gap in literature with respect to the state-of-the-art in deep learning-based interference suppression. Specifically, we review a wide range of techniques that have used deep learning to suppress interference by learning interference characteristics directly from data, rather than relying on expert systems. We provide a thorough technical discussion of the prominent deep learning algorithms that have been proposed in the literature and provide comparison and guidelines regarding their successful implementation in this application. In addition, we highlight challenges and potential future research directions for the successful adoption of deep learning in this critical field.
Deep Learning improves Radio Frequency Interference Classification
arXiv: Instrumentation and Methods for Astrophysics, 2020
Flagging of Radio Frequency Interference (RFI) is an increasingly important challenge in radio astronomy. We present R-Net, a deep convolutional ResNet architecture that significantly outperforms existing algorithms -- including the default MeerKAT RFI flagger, and deep U-Net architectures -- across all metrics including AUC, F1-score and MCC. We demonstrate the robustness of this improvement on both single dish and interferometric simulations and, using transfer learning, on real data. Our R-Net model's precision is approximately 9090\%90 better than the current MeerKAT flagger at 8080\%80 recall and has a 35\% higher F1-score with no additional performance cost. We further highlight the effectiveness of transfer learning from a model initially trained on simulated MeerKAT data and fine-tuned on real, human-flagged, KAT-7 data. Despite the wide differences in the nature of the two telescope arrays, the model achieves an AUC of 0.91, while the best model without transfer learning on...
Deep Learning Interference Cancellation in Wireless Networks
arXiv: Signal Processing, 2020
With the crowding of the electromagnetic spectrum and the shrinking cell size in wireless networks, crosstalk between base stations and users is a major problem. Although hand-crafted functional blocks and coding schemes are proven effective to guarantee reliable data transfer, currently deep learning-based approaches have drawn increasing attention in the communication system modeling. In this paper, we propose a Neural Network (NN) based signal processing technique that works with traditional DSP algorithms to overcome the interference problem in realtime. This technique doesn't require any feedback protocol between the receiver and transmitter which makes it very suitable for low-latency and high data-rate applications such as autonomy and augmented reality. While there has been recent work on the use of Reinforcement Learning (RL) in the control layer to manage and control the interference, our approach is novel in the sense that it introduces a neural network for signal pro...
Deep learning improves identification of Radio Frequency Interference
Monthly Notices of the Royal Astronomical Society
ABSTRACTFlagging of Radio Frequency Interference (RFI) in time–frequency visibility data is an increasingly important challenge in radio astronomy. We present R-Net, a deep convolutional ResNet architecture that significantly outperforms existing algorithms – including the default MeerKAT RFI flagger, and deep U-Net architectures – across all metrics including AUC, F1-score, and MCC. We demonstrate the robustness of this improvement on both single dish and interferometric simulations and, using transfer learning, on real data. Our R-Net model’s precision is approximately 90rmpercent90{{\ \rm per\ cent}}90rmpercent better than the current MeerKAT flagger at 80rmpercent80{{\ \rm per\ cent}}80rmpercent recall and has a 35 per cent higher F1-score with no additional performance cost. We further highlight the effectiveness of transfer learning from a model initially trained on simulated MeerKAT data and fine-tuned on real, human-flagged, KAT-7 data. Despite the wide differences in the nature of the two telescope arrays, the mo...
Deep Learning for RF Signal Classification in Unknown and Dynamic Spectrum Environments
2019 IEEE International Symposium on Dynamic Spectrum Access Networks (DySPAN), 2019
Dynamic spectrum access (DSA) benefits from detection and classification of interference sources including innetwork users, out-network users, and jammers that may all coexist in a wireless network. We present a deep learning based signal (modulation) classification solution in a realistic wireless network setting, where 1) signal types may change over time; 2) some signal types may be unknown for which there is no training data; 3) signals may be spoofed such as the smart jammers replaying other signal types; and 4) different signal types may be superimposed due to the interference from concurrent transmissions. For case 1, we apply continual learning and train a Convolutional Neural Network (CNN) using an Elastic Weight Consolidation (EWC) based loss. For case 2, we detect unknown signals via outlier detection applied to the outputs of convolutional layers using Minimum Covariance Determinant (MCD) and k-means clustering methods. For case 3, we extend the CNN structure to capture phase shifts due to radio hardware effects to identify the spoofing signal sources. For case 4, we apply blind source separation using Independent Component Analysis (ICA) to separate interfering signals. We utilize the signal classification results in a distributed scheduling protocol, where innetwork (secondary) users employ signal classification scores to make channel access decisions and share the spectrum with each other while avoiding interference with out-network (primary) users and jammers. Compared with benchmark TDMA-based schemes, we show that distributed scheduling constructed upon signal classification results provides major improvements to innetwork user throughput and out-network user success ratio.
2021
Radio spectrum awareness, including understanding radio signal activities, is crucial for improving spectrum utilization, detecting security vulnerabilities, and supporting adaptive transmissions. Related tasks include spectrum sensing, identifying systems and terminals, and understanding various protocol layers. In this paper, we investigate various identification and classification tasks related to fading channel parameters, signal distortions, Medium Access Control (MAC) protocols, radio signal types, and cellular systems. Specifically, we utilize deep learning methods in those identification and classification tasks. Performance evaluations demonstrate the effectiveness of deep learning in those radio spectrum awareness tasks.
2022
Wireless links are increasingly used to deliver critical services, while intentional interference (jamming) remains a very serious threat to such services. In this paper, we are concerned with the design and evaluation of a universal anti-jamming building block, that is agnostic to the specifics of the communication link and can therefore be combined with existing technologies. We believe that such a block should not require explicit probes, sounding, training sequences, channel estimation, or even the cooperation of the transmitter. To meet these requirements, we propose an approach that relies on advances in Machine Learning, and the promises of neural accelerators and software defined radios. We identify and address multiple challenges, resulting in a convolutional neural network architecture and models for a multi-antenna system to infer the existence of interference, the number of interfering emissions and their respective phases. This information is continuously fed into an algorithm that cancels the interfering signal. We develop a twoantenna prototype system and evaluate our jamming cancellation approach in various environment settings and modulation schemes using Software Defined Radio platforms. We demonstrate that the receiving node equipped with our approach can detect a jammer with over 99% of accuracy and achieve a Bit Error Rate (BER) as low as 10 −6 even when the jammer power is nearly two orders of magnitude (18 dB) higher than the legitimate signal, and without requiring modifications to the link modulation. In non-adversarial settings, our approach can have other advantages such as detecting and mitigating collisions.
A Low-Complexity Deep Neural Network for Signal-to-Interference-Plus-Noise Ratio Estimation
Anais do I Workshop de Redes 6G (W6G 2021), 2021
Mobile network technology has been driven by a huge demand for throughput and reliability to support new emerging services. The quality of service is based on measurements of indicators with a high level of precision. Accurate controlling of parameters to fulfil the quality requirements will be essential for future applications. In LTE and 5G standards, the Channel Quality Indicator can be calculated using different algorithms. It is key to determine the best coding and modulation as well as the power control. Thus, it depends on the exact signal-to-noise ratio estimation. MSE based on hard-decision has a very low computational cost, however, it can insert non-linearities. This paper proposes a neural network to estimate an SINR from a modified MSE function.
Journal of Communications and Networks, 2020
With recent advances, Artificial Intelligence (AI) and Machine Learning (ML) approaches have emerged to show great promise in the field of wireless communications. Although some researchers are skeptical due to issues concerning complexity and reliability, benefits include the near-optimal performance or the improvement over current state-of-the-art techniques. Luckily, the big data technology delivers an excellent advantage for studying the essential characteristics of wireless networks that can be integrated with AI and ML approaches. Moreover, the recent advances in deep learning, convolutional neural networks, and reinforcement learning hold significant promise. Indeed, they offer new design approaches for solving some challenging problems that, until recently, were considered intractable.