arXiv subjects

Lingjia Liu

Publications and source records attributed to Lingjia Liu.

At least 55 records · Page 3Linked to original sources

arXiv2023

Detect to Learn: Structure Learning with Attention and Decision Feedback for MIMO-OFDM Receive Processing

The limited over-the-air (OTA) pilot symbols in multiple-input-multiple-output orthogonal-frequency-division-multiplexing (MIMO-OFDM) systems presents a major challenge for detecting transmitted data symbols at the receiver, especially for machine learning-based approaches. While it is crucial to explore effective ways to exploit pilots, one can also take advantage of the data symbols to improve detection performance. Thus, this paper introduces an online attention-based approach, namely RC-AttStructNet-DF, that can efficiently utilize pilot symbols and be dynamically updated with the detected payload data using the decision feedback (DF) mechanism. Reservoir computing (RC) is employed in the time domain network to facilitate efficient online training. The frequency domain network adopts the novel 2D multi-head attention (MHA) module to capture the time and frequency correlations, and the structural-based StructNet to facilitate the DF mechanism. The attention loss is designed to learn the frequency domain network. The DF mechanism further enhances detection performance by dynamically tracking the channel changes through detected data symbols. The effectiveness of the RC-AttStructNet-DF approach is demonstrated through extensive experiments in MIMO-OFDM and massive MIMO-OFDM systems with different modulation orders and under various scenarios.

eess.SP↗

arXiv2023

Towards Explainable Machine Learning: The Effectiveness of Reservoir Computing in Wireless Receive Processing

Deep learning has seen a rapid adoption in a variety of wireless communications applications, including at the physical layer. While it has delivered impressive performance in tasks such as channel equalization and receive processing/symbol detection, it leaves much to be desired when it comes to explaining this superior performance. In this work, we investigate the specific task of channel equalization by applying a popular learning-based technique known as Reservoir Computing (RC), which has shown superior performance compared to conventional methods and other learning-based approaches. Specifically, we apply the echo state network (ESN) as a channel equalizer and provide a first principles-based signal processing understanding of its operation. With this groundwork, we incorporate the available domain knowledge in the form of the statistics of the wireless channel directly into the weights of the ESN model. This paves the way for optimized initialization of the ESN model weights, which are traditionally untrained and randomly initialized. Finally, we show the improvement in receive processing/symbol detection performance with this optimized initialization through simulations. This is a first step towards explainable machine learning (XML) and assigning practical model interpretability that can be utilized together with the available domain knowledge to improve performance and enhance detection reliability.

eess.SP↗

arXiv2023

On the Role of 5G and Beyond Sidelink Communication in Multi-Hop Tactical Networks

This work investigates the potential of 5G and beyond sidelink (SL) communication to support multi-hop tactical networks. We first provide a technical and historical overview of 3GPP SL standardization activities, and then consider applications to current problems of interest in tactical networking. We consider a number of multi-hop routing techniques which are expected to be of interest for SL-enabled multi-hop tactical networking and examine open-source tools useful for network emulation. Finally, we discuss relevant research directions which may be of interest for 5G SL-enabled tactical communications, namely the integration of RF sensing and positioning, as well as emerging machine learning tools such as federated and decentralized learning, which may be of great interest for resource allocation and routing problems that arise in tactical applications. We conclude by summarizing recent developments in the 5G SL literature and provide guidelines for future research.

cs.NI↗

arXiv2023

Bayesian Inference-assisted Machine Learning for Near Real-Time Jamming Detection and Classification in 5G New Radio (NR)

The increased flexibility and density of spectrum access in 5G New Radio (NR) has made jamming detection and classification a critical research area. To detect coexisting jamming and subtle interference, we introduce a Bayesian Inference-assisted machine learning (ML) methodology. Our methodology uses cross-layer critical signaling Key Performance Indicator data collected on a Non-Standalone (NSA) 5G NR testbed to leverage supervised learning models, and are further assessed, calibrated, and revealed using Bayesian Network Model (BNM)-based inference. The models can operate on both instantaneous and sequential time-series data samples, achieving an Area under Curve above 0.954 for instantaneous models and above 0.988 for sequential models including the echo state network (ESN) from the Reservoir Computing (RC) family, for various jamming scenarios. Our approach not only serves as a validation method and a resilience enhancement tool for ML-based jamming detection, but also enables root cause identification for any observed performance degradation. The introduced BNM-based inference proof-of-concept is successful in addressing 72.2% of the erroneous predictions of the RC-based sequential detection model caused by insufficient training data samples collected in the observation period, thereby demonstrating its applicability in 5G NR and Beyond-5G (B5G) network infrastructure and user devices.

eess.SP↗

arXiv2023

Learning to Estimate: A Real-Time Online Learning Framework for MIMO-OFDM Channel Estimation

In this paper we introduce StructNet-CE, a novel real-time online learning framework for MIMO-OFDM channel estimation, which only utilizes over-the-air (OTA) pilot symbols for online training and converges within one OFDM subframe. The design of StructNet-CE leverages the structure information in the MIMO-OFDM system, including the repetitive structure of modulation constellation and the invariant property of symbol classification to inter-stream interference. The embedded structure information enables StructNet-CE to conduct channel estimation with a binary classification task and accurately learn channel coefficients with as few as two pilot OFDM symbols. Experiments show that the channel estimation performance is significantly improved with the incorporation of structure knowledge. StructNet-CE is compatible and readily applicable to current and future wireless networks, demonstrating the effectiveness and importance of combining machine learning techniques with domain knowledge for wireless communication systems.

eess.SP↗

arXiv2023

DRL meets DSA Networks: Convergence Analysis and Its Application to System Design

In dynamic spectrum access (DSA) networks, secondary users (SUs) need to opportunistically access primary users' (PUs) radio spectrum without causing significant interference. Since the interaction between the SU and the PU systems are limited, deep reinforcement learning (DRL) has been introduced to help SUs to conduct spectrum access. Specifically, deep recurrent Q network (DRQN) has been utilized in DSA networks for SUs to aggregate the information from the recent experiences to make spectrum access decisions. DRQN is notorious for its sample efficiency in the sense that it needs a rather large number of training data samples to tune its parameters which is a computationally demanding task. In our recent work, deep echo state network (DEQN) has been introduced to DSA networks to address the sample efficiency issue of DRQN. In this paper, we analytically show that DEQN comparatively requires less amount of training samples than DRQN to converge to the best policy. Furthermore, we introduce a method to determine the right hyperparameters for the DEQN providing system design guidance for DEQN-based DSA networks. Extensive performance evaluation confirms that DEQN-based DSA strategy is the superior choice with regard to computational power while outperforming DRQN-based DSA strategies.

eess.SP↗

arXiv2023

5G-Advanced Towards 6G: Past, Present, and Future

Since the start of 5G work in 3GPP in early 2016, tremendous progress has been made in both standardization and commercial deployments. 3GPP is now entering the second phase of 5G standardization, known as 5G-Advanced, built on the 5G baseline in 3GPP Releases 15, 16, and 17. 3GPP Release 18, the start of 5G-Advanced, includes a diverse set of features that cover both device and network evolutions, providing balanced mobile broadband evolution and further vertical domain expansion and accommodating both immediate and long-term commercial needs. 5G-Advanced will significantly expand 5G capabilities, address many new use cases, transform connectivity experiences, and serve as an essential step in developing mobile communications towards 6G. This paper provides a comprehensive overview of the 3GPP 5G-Advanced development, introducing the prominent state-of-the-art technologies investigated in 3GPP and identifying key evolution directions for future research and standardization.

cs.IT↗

arXiv2023

Distributed Learning Meets 6G: A Communication and Computing Perspective

With the ever-improving computing capabilities and storage capacities of mobile devices in line with evolving telecommunication network paradigms, there has been an explosion of research interest towards exploring Distributed Learning (DL) frameworks to realize stringent key performance indicators (KPIs) that are expected in next-generation/6G cellular networks. In conjunction with Edge Computing, Federated Learning (FL) has emerged as the DL architecture of choice in prominent wireless applications. This article lays an outline of how DL in general and FL-based strategies specifically can contribute towards realizing a part of the 6G vision and strike a balance between communication and computing constraints. As a practical use case, we apply Multi-Agent Reinforcement Learning (MARL) within the FL framework to the Dynamic Spectrum Access (DSA) problem and present preliminary evaluation results. Top contemporary challenges in applying DL approaches to 6G networks are also highlighted.

cs.NI↗

arXiv2022

RC-Struct: A Structure-based Neural Network Approach for MIMO-OFDM Detection

In this paper, we introduce a structure-based neural network architecture, namely RC-Struct, for MIMO-OFDM symbol detection. The RC-Struct exploits the temporal structure of the MIMO-OFDM signals through reservoir computing (RC). A binary classifier leverages the repetitive constellation structure in the system to perform multi-class detection. The incorporation of RC allows the RC-Struct to be learned in a purely online fashion with extremely limited pilot symbols in each OFDM subframe. The binary classifier enables the efficient utilization of the precious online training symbols and allows an easy extension to high-order modulations without a substantial increase in complexity. Experiments show that the introduced RC-Struct outperforms both the conventional model-based symbol detection approaches and the state-of-the-art learning-based strategies in terms of bit error rate (BER). The advantages of RC-Struct over existing methods become more significant when rank and link adaptation are adopted. The introduced RC-Struct sheds light on combining communication domain knowledge and learning-based receive processing for 5G/5G-Advanced and Beyond.

cs.IT↗

arXiv2022

Optimizing Number, Placement, and Backhaul Connectivity of Multi-UAV Networks

Multi-Unmanned Aerial Vehicle (UAV) Networks is a promising solution to providing wireless coverage to ground users in challenging rural areas (such as Internet of Things (IoT) devices in farmlands), where the traditional cellular networks are sparse or unavailable. A key challenge in such networks is the 3D placement of all UAV base stations such that the formed Multi-UAV Network (i) utilizes a minimum number of UAVs while ensuring -- (ii) backhaul connectivity directly (or via other UAVs) to the nearby terrestrial base station, and (iii) wireless coverage to all ground users in the area of operation. This joint Backhaul-and-coverage-aware Drone Deployment (BoaRD) problem is largely unaddressed in the literature, and, thus, is the focus of the paper. We first formulate the BoaRD problem as Integer Linear Programming (ILP). However, the problem is NP-hard, and therefore, we propose a low complexity algorithm with a provable performance guarantee to solve the problem efficiently. Our simulation study shows that the Proposed algorithm performs very close to that of the Optimal algorithm (solved using ILP solver) for smaller scenarios, where the area size and the number of users are relatively small. For larger scenarios, where the area size and the number of users are relatively large, the proposed algorithm greatly outperforms the baseline approaches -- backhaul-aware greedy and random algorithm, respectively by up to 17% and 95% in utilizing fewer UAVs while ensuring 100% ground user coverage and backhaul connectivity for all deployed UAVs across all considered simulation setting.

cs.IT↗

arXiv2021

Efficient Data Exchange in Unmanned Aerial Vehicle Networks Utilizing Unsupervised Learning-Based Clustering

An unmanned aerial vehicle (UAV) network can serve as an aerial relay to periodically receive packets from macro base stations (BSs). Severe packet loss may happen especially when UAVs have bad wireless connections to a BS. In this paper, a data exchange scheme is proposed utilizing unsupervised learning to enable efficient lost packet retrieval through reliable wireless transmissions between UAVs instead of through retransmissions of macro BSs with a longer delay and higher overhead. With the proposed scheme, all UAVs are assigned to multiple clusters and a UAV can only request its lost packets to UAVs in the same cluster. By this way, UAVs in different clusters could carry out their lost packets retrieval processes simultaneously to expedite data exchange. The agglomerative hierarchical clustering, a type of unsupervised learning, is used to conduct clustering, guaranteeing that UAVs clustered together could supply and supplement each other's lost packets. To further enhance data exchange efficiency, a data exchange mechanism is designed, where the priority of UAVs performing data exchange is determined by the number of their lost packets or the number of requested packets that they can provide. The introduced data exchange mechanism can make each request-reply process maximally beneficial to other UAVs' lost packet retrieval in the same cluster. A new random backoff procedure based on the carrier sense multiple access with collision avoidance (CSMA/CA) is designed to support the data exchange mechanism. Finally, simulation studies are conducted to demonstrate the effectiveness and superiority of our proposed data exchange scheme.

cs.IT↗

arXiv2021

Clustering-based Multicast Scheme for UAV Networks

When an unmanned aerial vehicle (UAV) network is utilized as an aerial small base station (BS), like a relay deployed far away from macro BSs, existing multicast methods based on acknowledgement (ACK) feedback and retransmissions may encounter severe delay and signaling overhead due to hostile wireless environments caused by a long-distance propagation and numerous UAVs. In this paper, a novel multicast scheme is designed for UAV networks serving as an aerial small BS, where a UAV experiencing a packet loss will request the packet from other UAVs in the same cluster rather than relying on retransmissions of BSs. The technical details of the introduced multicast scheme are designed with the carrier sense multiple access with collision avoidance (CSMA/CA) protocol for practicability and without loss of generality. Then, the Poisson cluster process is employed to model UAV networks to capture their dynamic network topology, based on which distance distributions are derived using tools of stochastic geometry for analytical tractability. Additionally, critical performance indicators of the designed multicast scheme are analyzed. Through extensive simulation studies, the superiority of the designed multicast scheme is demonstrated and the system design insight related to the proper number of clusters is revealed.

eess.SY↗

arXiv2021

Learning to Equalize OTFS

Orthogonal Time Frequency Space (OTFS) is a novel framework that processes modulation symbols via a time-independent channel characterized by the delay-Doppler domain. The conventional waveform, orthogonal frequency division multiplexing (OFDM), requires tracking frequency selective fading channels over the time, whereas OTFS benefits from full time-frequency diversity by leveraging appropriate equalization techniques. In this paper, we consider a neural network-based supervised learning framework for OTFS equalization. Learning of the introduced neural network is conducted in each OTFS frame fulfilling an online learning framework: the training and testing datasets are within the same OTFS-frame over the air. Utilizing reservoir computing, a special recurrent neural network, the resulting one-shot online learning is sufficiently flexible to cope with channel variations among different OTFS frames (e.g., due to the link/rank adaptation and user scheduling in cellular networks). The proposed method does not require explicit channel state information (CSI) and simulation results demonstrate a lower bit error rate (BER) than conventional equalization methods in the low signal-to-noise (SNR) regime under large Doppler spreads. When compared with its neural network-based counterparts for OFDM, the introduced approach for OTFS will lead to a better tradeoff between the processing complexity and the equalization performance.

eess.SP↗

arXiv2021

Federated Dynamic Spectrum Access

Due to the growing volume of data traffic produced by the surge of Internet of Things (IoT) devices, the demand for radio spectrum resources is approaching their limitation defined by Federal Communications Commission (FCC). To this end, Dynamic Spectrum Access (DSA) is considered as a promising technology to handle this spectrum scarcity. However, standard DSA techniques often rely on analytical modeling wireless networks, making its application intractable in under-measured network environments. Therefore, utilizing neural networks to approximate the network dynamics is an alternative approach. In this article, we introduce a Federated Learning (FL) based framework for the task of DSA, where FL is a distributive machine learning framework that can reserve the privacy of network terminals under heterogeneous data distributions. We discuss the opportunities, challenges, and opening problems of this framework. To evaluate its feasibility, we implement a Multi-Agent Reinforcement Learning (MARL)-based FL as a realization associated with its initial evaluation results.

eess.SP↗

arXiv2021

Adversarial Classification of the Attacks on Smart Grids Using Game Theory and Deep Learning

Smart grids are vulnerable to cyber-attacks. This paper proposes a game-theoretic approach to evaluate the variations caused by an attacker on the power measurements. Adversaries can gain financial benefits through the manipulation of the meters of smart grids. On the other hand, there is a defender that tries to maintain the accuracy of the meters. A zero-sum game is used to model the interactions between the attacker and defender. In this paper, two different defenders are used and the effectiveness of each defender in different scenarios is evaluated. Multi-layer perceptrons (MLPs) and traditional state estimators are the two defenders that are studied in this paper. The utility of the defender is also investigated in adversary-aware and adversary-unaware situations. Our simulations suggest that the utility which is gained by the adversary drops significantly when the MLP is used as the defender. It will be shown that the utility of the defender is variant in different scenarios, based on the defender that is being used. In the end, we will show that this zero-sum game does not yield a pure strategy, and the mixed strategy of the game is calculated.

cs.LG↗

arXiv2021

UAV Swarm-Enabled Aerial Reconfigurable Intelligent Surface

Reconfigurable intelligent surface (RIS) offers tremendous spectrum and energy efficiency in wireless networks by adjusting the amplitudes and/or phases of passive reflecting elements to optimize signal reflection. With the agility and mobility of unmanned aerial vehicles (UAVs), RIS can be mounted on UAVs to enable three-dimensional signal reflection. Compared to the conventional terrestrial RIS (TRIS), the aerial RIS (ARIS) enjoys higher deployment flexibility, reliable air-to-ground links, and panoramic full-angle reflection. However, due to UAV's limited payload and battery capacity, it is difficult for a UAV to carry a RIS with a large number of reflecting elements. Thus, the scalability of the aperture gain could not be guaranteed. In practice, multiple UAVs can form a UAV swarm to enable the ARIS cooperatively. In this article, we first present an overview of the UAV swarm-enabled ARIS (SARIS), including its motivations and competitive advantages compared to TRIS and ARIS, as well as its new transformative applications in wireless networks. We then address the critical challenges of designing the SARIS by focusing on the beamforming design, SARIS channel estimation, and SARIS's deployment and movement. Next, the potential performance enhancement of SARIS is showcased and discussed with preliminary numerical results. Finally, open research opportunities are illustrated.

eess.SP↗

arXiv2021

Towards Intelligent RAN Slicing for B5G: Opportunities and Challenges

To meet the diverse demands for wireless communication, fifth-generation (5G) networks and beyond (B5G) embrace the concept of network slicing by forging virtual instances (slices) of its physical infrastructure. While network slicing constitutes dynamic allocation of core network and radio access network (RAN) resources, this article emphasizes RAN slicing (RAN-S) design. Forming on-demand RAN-S that can be flexibly (re)-configured while ensuring slice isolation is challenging. A variety of machine learning (ML) techniques have been recently introduced for traffic forecasting and classification, resource usage prediction, admission control, scheduling, and dynamic resource allocation in RAN-S. Albeit these approaches grant opportunities towards intelligent RAN-S design, they raise critical challenges that need to be examined. This article underlines the opportunities and the challenges of incorporating ML into RAN-S by reviewing the cutting-edge ML-based techniques for RAN-S. It also draws few directions for future research towards intelligent RAN-S (iRAN-S).

cs.NI↗

arXiv2021

Making Intelligent Reflecting Surfaces More Intelligent: A Roadmap Through Reservoir Computing

This article introduces a neural network-based signal processing framework for intelligent reflecting surface (IRS) aided wireless communications systems. By modeling radio-frequency (RF) impairments inside the "meta-atoms" of IRS (including nonlinearity and memory effects), we present an approach that generalizes the entire IRS-aided system as a reservoir computing (RC) system, an efficient recurrent neural network (RNN) operating in a state near the "edge of chaos". This framework enables us to take advantage of the nonlinearity of this "fabricated" wireless environment to overcome link degradation due to model mismatch. Accordingly, the randomness of the wireless channel and RF imperfections are naturally embedded into the RC framework, enabling the internal RC dynamics lying on the edge of chaos. Furthermore, several practical issues, such as channel state information acquisition, passive beamforming design, and physical layer reference signal design, are discussed.

eess.SP↗