Showing papers in "IEEE Transactions on Cognitive Communications and Networking in 2020"
TL;DR: This article describes the working principles of reconfigurable intelligent surfaces (RIS) and elaborate on different candidate implementations using metasurfaces and reflectarrays, and discusses the channel models suitable for both implementations and the feasibility of obtaining accurate channel estimates.
Abstract: Recently there has been a flurry of research on the use of reconfigurable intelligent surfaces (RIS) in wireless networks to create smart radio environments. In a smart radio environment, surfaces are capable of manipulating the propagation of incident electromagnetic waves in a programmable manner to actively alter the channel realization, which turns the wireless channel into a controllable system block that can be optimized to improve overall system performance. In this article, we provide a tutorial overview of reconfigurable intelligent surfaces (RIS) for wireless communications. We describe the working principles of reconfigurable intelligent surfaces (RIS) and elaborate on different candidate implementations using metasurfaces and reflectarrays. We discuss the channel models suitable for both implementations and examine the feasibility of obtaining accurate channel estimates. Furthermore, we discuss the aspects that differentiate RIS optimization from precoding for traditional MIMO arrays highlighting both the arising challenges and the potential opportunities associated with this emerging technology. Finally, we present numerical results to illustrate the power of an RIS in shaping the key properties of a MIMO channel.
459 citations
TL;DR: Fundamental challenges such as UAVs standardization, channel modeling, interference mitigation, collision avoidance and optimal trajectory design using deep reinforcement learning (RL) algorithms, energy harvesting techniques, security, and regulations are explored in light of most recent research development.
Abstract: In recent years, unmanned aerial vehicles (UAVs) have attained significant interest in different applications including aerial surveillance, providing wireless coverage, precision agriculture, power lines & oil rigs monitoring and construction, etc. The UAVs implicit peculiarities, e.g., swift mobility, increase in payload capabilities and airborne time, place it as a potential candidate for many applications in next-generation wireless communications. In this article, a comprehensive study on UAVs challenges, potential applications, and regulations is presented. In particular, fundamental challenges such as UAVs standardization, channel modeling, interference mitigation, collision avoidance and optimal trajectory design using deep reinforcement learning (RL) algorithms, energy harvesting techniques, security, and regulations are explored in light of most recent research development. Moreover, we propose a set of UAVs regulations to ensure its steady social integration and new business opportunities. Finally, various problems and future research directions regarding UAVs are presented.
135 citations
TL;DR: Simulation results show that the proposed AI-based collaborative computing approach can adapt to a highly dynamic environment with outstanding performance and the service cost can be minimized via the optimal workload assignment and server selection in collaborative computing.
Abstract: Mobile edge computing (MEC) is a promising technology to support mission-critical vehicular applications, such as intelligent path planning and safety applications. In this paper, a collaborative edge computing framework is developed to reduce the computing service latency and improve service reliability for vehicular networks. First, a task partition and scheduling algorithm (TPSA) is proposed to decide the workload allocation and schedule the execution order of the tasks offloaded to the edge servers given a computation offloading strategy. Second, an artificial intelligence (AI) based collaborative computing approach is developed to determine the task offloading, computing, and result delivery policy for vehicles. Specifically, the offloading and computing problem is formulated as a Markov decision process. A deep reinforcement learning technique, i.e., deep deterministic policy gradient, is adopted to find the optimal solution in a complex urban transportation network. By our approach, the service cost, which includes computing service latency and service failure penalty, can be minimized via the optimal workload assignment and server selection in collaborative computing. Simulation results show that the proposed AI-based collaborative computing approach can adapt to a highly dynamic environment with outstanding performance.
131 citations
TL;DR: This paper designs and implements a generative model that learns the sample space of the I/Q values of known transmitters and uses the learned representation to generate signals that imitate the transmissions of these transmitters.
Abstract: Recent advances in wireless technologies have led to several autonomous deployments of such networks. As nodes across distributed networks must co-exist, it is important that all transmitters and receivers are aware of their radio frequency (RF) surroundings so that they can adapt their transmission and reception parameters to best suit their needs. To this end, machine learning techniques have become popular as they can learn, analyze and predict the RF signals and associated parameters that characterize the RF environment. However, in the presence of adversaries, malicious activities such as jamming and spoofing are inevitable, making most machine learning techniques ineffective in such environments. In this paper we propose the Radio Frequency Adversarial Learning (RFAL) framework for building a robust system to identify rogue RF transmitters by designing and implementing a generative adversarial net (GAN). We hope to exploit transmitter specific “signatures” like the in-phase (I) and quadrature (Q) imbalance (i.e., the I/Q imbalance ) present in all transmitters for this task, by learning feature representations using a deep neural network that uses the I/Q data from received signals as input. After detection and elimination of the adversarial transmitters RFAL further uses this learned feature embedding as “fingerprints” for categorizing the trusted transmitters. More specifically, we implement a generative model that learns the sample space of the I/Q values of known transmitters and uses the learned representation to generate signals that imitate the transmissions of these transmitters. We program 8 universal software radio peripheral (USRP) software defined radios (SDRs) as trusted transmitters and collect “over-the-air” raw I/Q data from them using a Realtek Software Defined Radio (RTL-SDR), in a laboratory setting. We also implement a discriminator model that discriminates between the trusted transmitters and the counterfeit ones with 99.9% accuracy and is trained in the GAN framework using data from the generator. Finally, after elimination of the adversarial transmitters, the trusted transmitters are classified using a convolutional neural network (CNN), a fully connected deep neural network (DNN) and a recurrent neural network (RNN) to demonstrate building of an end-to-end robust transmitter identification system with RFAL. Experimental results reveal that the CNN, DNN, and RNN are able to correctly distinguish between the 8 trusted transmitters with 81.6%, 94.6% and 97% accuracy respectively. We also show that better “trusted transmission” classification accuracy is achieved for all three types of neural networks when data from two different types of transmitters (different manufacturers) are used rather than when using the same type of transmitter (same manufacturer).
110 citations
TL;DR: This work proposes deep actor-critic reinforcement learning based policies for both centralized and decentralized content caching for offload data traffic in wireless networks and considers both the cache hit rate and transmission delay as performance metrics.
Abstract: With the purpose to offload data traffic in wireless networks, content caching techniques have recently been studied intensively. Using these techniques and caching a portion of the popular files at the local content servers, the users can be served with less delay. Most of the content replacement policies are based on the content popularity, that depends on the users’ preferences. In practice, such information varies over time. Therefore, an approach to determine the file popularity patterns must be incorporated into caching policies. In this context, we study content caching at the wireless network edge using a deep reinforcement learning framework with Wolpertinger architecture. In particular, we propose deep actor-critic reinforcement learning based policies for both centralized and decentralized content caching. For centralized edge caching, we aim at maximizing the cache hit rate. In decentralized edge caching, we consider both the cache hit rate and transmission delay as performance metrics. The proposed frameworks are assumed to neither have any prior information on the file popularities nor know the potential variations in such information. Via simulation results, the superiority of the proposed frameworks is verified by comparing them with other policies, including least frequently used (LFU), least recently used (LRU), and first-in-first-out (FIFO) policies.
107 citations
TL;DR: A collaborative learning-based routing scheme for multi-access vehicular edge computing environment that employs a reinforcement learning algorithm based on end-edge-cloud collaboration to find routes in a proactive manner with a low communication overhead and is preemptively changed based on the learned information.
Abstract: Some Internet-of-Things (IoT) applications have a strict requirement on the end-to-end delay where edge computing can be used to provide a short delay for end-users by conducing efficient caching and computing at the edge nodes. However, a fast and efficient communication route creation in multi-access vehicular environment is an underexplored research problem. In this paper, we propose a collaborative learning-based routing scheme for multi-access vehicular edge computing environment. The proposed scheme employs a reinforcement learning algorithm based on end-edge-cloud collaboration to find routes in a proactive manner with a low communication overhead. The routes are also preemptively changed based on the learned information. By integrating the “proactive” and “preemptive” approach, the proposed scheme can achieve a better forwarding of packets as compared with existing alternatives. We conduct extensive and realistic computer simulations to show the performance advantage of the proposed scheme over existing baselines.
104 citations
TL;DR: A combination of deep reinforcement learning (DRL) and the long-short-term memory (LSTM) network is adopted to accelerate the convergence speed of the algorithm and the quality of experience (QoE) is introduced to evaluate the results of UAV sharing.
Abstract: The formation flights of multiple unmanned aerial vehicles (UAV) can improve the success probability of single-machine. Dynamic spectrum interaction solves the problem of the ordered communication of multiple UAVs with limited bandwidth via spectrum interaction between UAVs. By introducing reinforcement learning algorithm, UAVs can continuously obtain the optimal strategy by continuously interacting with the environment. In this paper, two types of UAV formation communication methods are studied. One method allows for information sharing between two UAVs in the same time slot. The other method is the adoption of a dynamic time slot allocation scheme to complete the alternate use of time slots by the UAV to realize information sharing. The quality of experience (QoE) is introduced to evaluate the results of UAV sharing, and the M/G/1 queuing model is used for priority and to evaluate the packet loss of UAV. In terms of algorithms, a combination of deep reinforcement learning (DRL) and the long-short-term memory (LSTM) network is adopted to accelerate the convergence speed of the algorithm. The experimental results show that, compared with the Q-learning and deep Q-network (DQN) methods, the proposed method achieves faster convergence and better performance with respect to the throughput rate.
96 citations
TL;DR: This paper provides a novel technique based on multi-objective optimization to efficiently allocate resources in the multi-user NOMA systems supporting downlink transmission that improves spectrum and energy efficiency while satisfying the constraints on users quality of services (QoS) requirements, transmit power budget and successive interference cancellation.
Abstract: Non-orthogonal multiple access (NOMA) holds the promise to be a key enabler of 5G communication. However, the existing design of NOMA systems must be optimized to achieve maximum rate while using minimum transmit power. To do so, this paper provides a novel technique based on multi-objective optimization to efficiently allocate resources in the multi-user NOMA systems supporting downlink transmission. Specifically, our unique optimization technique jointly improves spectrum and energy efficiency while satisfying the constraints on users quality of services (QoS) requirements, transmit power budget and successive interference cancellation. We first formulate a joint problem for spectrum and energy optimization and then employ dual decomposition technique to obtain an efficient solution. For the sake of comparison, a low complexity single-objective NOMA optimization scheme is also provided as a benchmark scheme. The simulation results show that the proposed joint approach not only performs better than the traditional benchmark NOMA scheme but also significantly outperforms its counterpart orthogonal multiple access (OMA) scheme in terms of both energy and spectral efficiency.
93 citations
TL;DR: Several new techniques are proposed, including denoising auto-encoder with fuzzy clustering (DAFC) and recombination embedding network, focusing on how to use context information and how to alleviate overfitting problem.
Abstract: In recent years, deep neural networks have achieved exciting results in a variety of tasks, and many fields try to introduce neural network techniques. In mobile edge computing, there are not many attempts that build neural network models in service recommendation or QoS (quality-of-service) prediction. The method proposed in this article is an attempt to employ neural network technique for QoS prediction. Compared to the pure use of QoS records, the exploration for context information in QoS prediction also still needs a lot of efforts. But an increasing number of features are highly likely to result in overfitting problem, especially in the case that the data size is small. To solve those problems, in this article, we propose several new techniques, including denoising auto-encoder with fuzzy clustering (DAFC) and recombination embedding network, focusing on how to use context information and how to alleviate overfitting problem. DAFC uses the denoising auto-encoder, which helps the fuzzy clustering algorithm overcome the defect that the performance is easy to be impacted by the number of clusters. Extensive experiments under different data densities show that these two network structures indeed improve the performance and reduce the overfitting problem.
92 citations
TL;DR: To exploit the full potential of symbiotic radio, a systematic view is provided and three fundamental tasks in SR are addressed, enhancing the backscattering link via active load; achieving highly reliable communications through joint decoding; and capturing PTx’s RF signals using reconfigurable intelligent surfaces.
Abstract: The heterogenous wireless services and exponentially growing traffic call for novel spectrum- and energy-efficient wireless communication technologies. Recently, a new technique, called symbiotic radio (SR), is proposed to exploit the benefits and address the drawbacks of cognitive radio (CR) and ambient backscattering communications (AmBC), leading to mutualism spectrum sharing and highly reliable backscattering communications. In particular, the secondary transmitter (STx) in SR transmits messages to the secondary receiver (SRx) over the RF signals originating from the primary transmitter (PTx) based on cognitive backscattering communications, thus the secondary system shares not only the radio spectrum, but also the power, and infrastructure with the primary system. In return, the secondary transmission provides beneficial multipath diversity to the primary system, therefore the two systems form mutualism spectrum sharing. More importantly, joint decoding is exploited at SRx to achieve highly reliable backscattering communications. In this article, to exploit the full potential of SR, we provide a systematic view for SR and address three fundamental tasks in SR: (1) enhancing the backscattering link via active load; (2) achieving highly reliable communications through joint decoding; and (3) capturing PTx’s RF signals using reconfigurable intelligent surfaces. Emerging applications, design challenges and open research problems will also be discussed.
86 citations
TL;DR: This paper presents ORACLE, a novel system based on convolutional neural networks to identify a unique radio from a large pool of devices by deep-learning the fine-grained hardware impairments imposed by radio circuitry on physical-layer I/Q samples, and proposes an impairment hopping spread spectrum (IHOP) technique that is resilient to spoofing attacks.
Abstract: Due to the unprecedented scale of the Internet of Things, designing scalable, accurate, energy-efficient and tamper-proof authentication mechanisms has now become more important than ever. To this end, in this paper we present ORACLE, a novel system based on convolutional neural networks (CNNs) to “fingerprint” (i.e., identify) a unique radio from a large pool of devices by deep-learning the fine-grained hardware impairments imposed by radio circuitry on physical-layer I/Q samples. First, we show how hardware-specific imperfections are learned by the CNN framework. Then, we extensively evaluate the performance of ORACLE on several first-of-its-kind large-scale datasets of WiFi-transmissions collected “in the wild”, as well as a dataset of nominally-identical (i.e., equal baseband signals) WiFi devices, reaching 80-90% accuracy is many cases with the error gap arising due to channel-induced effects. Finally, we show through an experimental testbed, how this accuracy can reach over 99% by intentionally inserting and learning the effect of controlled impairments at the transmitter side, to completely remove the impact of the wireless channel. Furthermore, to scale this approach for classifying potential thousands of radios, we propose an impairment hopping spread spectrum (IHOP) technique that is resilient to spoofing attacks.
TL;DR: The proposedDL-based channel estimator can dynamically track the channel status without any prior knowledge about the channel model and statistic characteristics and has better Mean Square Error (MSE) performance compared with the traditional algorithms and some other DL-based architectures.
Abstract: The research about deep learning application for physical layer has been received much attention in recent years. In this paper, we propose a Deep Learning (DL) based channel estimator under time varying Rayleigh fading channel. We build up, train and test the channel estimator using Neural Network (NN). The proposed DL-based estimator can dynamically track the channel status without any prior knowledge about the channel model and statistic characteristics. The simulation results show the proposed NN estimator has better Mean Square Error (MSE) performance compared with the traditional algorithms and some other DL-based architectures. Furthermore, the proposed DL-based estimator also shows its robustness with the different pilot densities.
TL;DR: This paper develops and evaluates a resource allocation approach for cognitive radios implemented with SDR technology over two testbeds of the ORCA federation, based on a Markov Random Field framework realizing a distributed cross-layer computation for the secondary nodes of the cognitive radio network.
Abstract: Software Defined Radio (SDR)-enabled cognitive radio network architectures are expected to play an important role in the future 5G networks. Despite the increased research interest, the current implementations are of small-scale and provide limited functionality. In this paper, we contribute towards the alleviation of the limitations in SDR deployments by developing and evaluating a resource allocation approach for cognitive radios implemented with SDR technology over two testbeds of the ORCA federation. Resource allocation is based on a Markov Random Field (MRF) framework realizing a distributed cross-layer computation for the secondary nodes of the cognitive radio network. The proposed framework implementation consists of self-contained modules developed in GNU Radio realizing cognitive functionalities, such as spectrum sensing, collision detection, etc. We demonstrate the feasibility of the MRF based resource allocation approach and provide extensive results and performance analysis that highlight its key features. The latter provide useful insights about the advantages of our framework, while allowing to pinpoint current technological barriers of broader interest.
TL;DR: A framework based on deep reinforcement learning (DRL) is developed to solve the spectrum allocation problem in the emerging integrated access and backhaul (IAB) architecture with large scale deployment and dynamic environment by integrating an actor-critic spectrum allocation (ACSA) scheme and deep neural network (DNN) to achieve real-time spectrum allocation in different scenarios.
Abstract: We develop a framework based on deep reinforcement learning (DRL) to solve the spectrum allocation problem in the emerging integrated access and backhaul (IAB) architecture with large scale deployment and dynamic environment. The available spectrum is divided into several orthogonal sub-channels, and the donor base station (DBS) and all IAB nodes have the same spectrum resource for allocation, where a DBS utilizes those sub-channels for access links of associated user equipment (UE) as well as for backhaul links of associated IAB nodes, and an IAB node can utilize all for its associated UEs. This is one of key features in which 5G differs from traditional settings where the backhaul networks are designed independently from the access networks. With the goal of maximizing the sum log-rate of all UE groups, we formulate the spectrum allocation problem into a mix-integer and non-linear programming. However, it is intractable to find an optimal solution especially when the IAB network is large and time-varying. To tackle this problem, we propose to use the latest DRL method by integrating an actor-critic spectrum allocation (ACSA) scheme and deep neural network (DNN) to achieve real-time spectrum allocation in different scenarios. The proposed methods are evaluated through numerical simulations and show promising results compared with some baseline allocation policies.
TL;DR: A new learning-based anomaly detection framework for service-provision systems with micro-services architectures using service execution logs and query traces and two-stage identification via a sequential model and temporal-spatial analysis is proposed.
Abstract: Service-oriented 5G mobile systems are commonly believed to reshape the landscape of the Internet with ubiquitous services and infrastructures. The micro-services architecture has attracted significant interests from both academia and industry, offering the capabilities of agile development and scale capacity. The emerging mobile edge computing is able to firmly maintain efficient resource utility of 5G systems, which can be empowered by micro-services. However, such capabilities impose significant challenges on micro-services system management. Although substantial data are produced for system maintenance, the interleaved temporal-spatial information has not been fully exploited. Additionally, the flooding data impose heavy pressures on automatic analysis tools. Automated digestion of data is in an urgent need for system maintenance. In this paper, we propose a new learning-based anomaly detection framework for service-provision systems with micro-services architectures using service execution logs (temporally) and query traces (spatially). It includes two major parts: logging and tracing representation, and two-stage identification via a sequential model and temporal-spatial analysis. The experimental results show that the temporal-spatial features can accurately capture the nature of operational data. The proposed framework performs well on anomaly detection, and helps gain in-depth insights of large-scale systems.
TL;DR: In this paper, the authors provide an overview on the intelligent communication in the past two decades to illustrate the revolution of its capability from cognition to artificial intelligence (AI), which is an efficient approach to provide more access opportunities to connect massive wireless devices.
Abstract: It has been 20 years since the concept of cognitive radio (CR) was proposed, which is an efficient approach to provide more access opportunities to connect massive wireless devices. To improve the spectrum efficiency, CR enables unlicensed usage of licensed spectrum resources. It has been regarded as the key enabler for intelligent communications. In this article, we will provide an overview on the intelligent communication in the past two decades to illustrate the revolution of its capability from cognition to artificial intelligence (AI). Particularly, this article starts from a comprehensive review of typical spectrum sensing and sharing, followed by the recent achievements on the AI-enabled intelligent radio. Moreover, research challenges in the future intelligent communications will be discussed to show a path to the real deployment of intelligent radio. After witnessing the glorious developments of CR in the past 20 years, we try to provide readers a clear picture on how intelligent radio could be further developed to smartly utilize the limited spectrum resources as well as to optimally configure wireless devices in the future communication systems.
TL;DR: Experimental results indicate that the proposed Deep RL approach significantly improves radar detection performance in congested spectral environments compared to policy iteration and SAA.
Abstract: This work addresses dynamic non-cooperative coexistence between a cognitive pulsed radar and nearby communications systems by applying nonlinear value function approximation via deep reinforcement learning (Deep RL) to develop a policy for optimal radar performance. The radar learns to vary the bandwidth and center frequency of its linear frequency modulated (LFM) waveforms to mitigate interference with other systems for improved target detection performance while also sufficiently utilizing available frequency bands to achieve a fine range resolution. We demonstrate that this approach, based on the Deep ${Q}$ -Learning (DQL) algorithm, enhances several radar performance metrics more effectively than policy iteration or sense-and-avoid (SAA) approaches in several realistic coexistence environments. The DQL-based approach is also extended to incorporate Double ${Q}$ -learning and a recurrent neural network to form a Double Deep Recurrent ${Q}$ -Network (DDRQN), which yields favorable performance and stability compared to DQL and policy iteration. The practicality of the proposed scheme is demonstrated through experiments performed on a software defined radar (SDRadar) prototype system. Experimental results indicate that the proposed Deep RL approach significantly improves radar detection performance in congested spectral environments compared to policy iteration and SAA.
TL;DR: In this paper, the authors proposed a proactive handover framework for millimeter-wave networks, where handover timings are optimized while obstacle-caused data rate degradations are predicted before the degradation occurs.
Abstract: For millimeter-wave networks, this paper presents a paradigm shift for leveraging time-consecutive camera images in handover decision problems. While making handover decisions, it is important to predict future long-term performance—e.g., the cumulative sum of time-varying data rates—proactively to avoid making myopic decisions. However, this study experimentally notices that a time-variation in the received powers is not necessarily informative for proactively predicting the rapid degradation of data rates caused by moving obstacles. To overcome this challenge, this study proposes a proactive framework wherein handover timings are optimized while obstacle-caused data rate degradations are predicted before the degradations occur. The key idea is to expand a state space to involve time-consecutive camera images, which comprises informative features for predicting such data rate degradations. To overcome the difficulty in handling the large dimensionality of the expanded state space, we use a deep reinforcement learning for deciding the handover timings. The evaluations performed based on the experimentally obtained camera images and received powers demonstrate that the expanded state space facilitates (i) the prediction of obstacle-caused data rate degradations from 500 ms before the degradations occur and (ii) superior performance to a handover framework without the state space expansion.
TL;DR: A Deep Q-Network is implemented to address the challenge of unknown system dynamics and computational expenses and the simulation results show that DQN can achieve near-optimal performance among different system scenarios only based on partial observations and ACK signals.
Abstract: In this paper, the problem of dynamic spectrum sensing and aggregation is investigated in a wireless network containing ${N}$ correlated channels, where these channels are occupied or vacant following an unknown joint 2-state Markov model. At each time slot, a single cognitive user with certain bandwidth requirement either stays idle or selects a segment comprising ${C}$ ( ${C} ) continuous channels to sense. Then, the vacant channels in the selected segment will be aggregated for satisfying the user requirement. The user receives a binary feedback signal indicating whether the transmission is successful or not (i.e., ACK signal) after each transmission, and makes next decision based on the sensing channel states. Here, we aim to find a policy that can maximize the number of successful transmissions without interrupting the primary users (PUs). The problem can be considered as a partially observable Markov decision process (POMDP) due to without full observation of system environment. We implement a Deep Q-Network (DQN) to address the challenge of unknown system dynamics and computational expenses. The performance of DQN, Q-Learning, and the Improvident Policy with known system dynamics is evaluated through simulations. The simulation results show that DQN can achieve near-optimal performance among different system scenarios only based on partial observations and ACK signals.
TL;DR: This paper investigates for the first time the coexistence of VLC and RF networks, assuming that both networks are served by a common backhaul network, as well as both perfect and imperfect channel state information (CSI).
Abstract: The synergy between visible light communication (VLC) and radio frequency (RF) networks has attracted a considerable amount of attention due to the envisioned improvements compared to conventional systems, mainly in terms of data rate and coverage. In this paper, we investigate for the first time the coexistence of VLC and RF networks, assuming that both networks are served by a common backhaul network, as well as both perfect and imperfect channel state information (CSI). In this context, we propose an optimal resource allocation scheme that maximizes the corresponding data rate, while also taking into account the fairness among the involved users. This is of paramount importance because in such heterogeneous networks, a standard rate maximization approach yields a severely degraded performance for the weaker users. In order to provide a tractable solution to the formulated problem, which is non-convex, we transform this into an equivalent convex one. Moreover, a simplified power allocation problem is solved, which provides comparable results with substantially lower complexity. Finally, extensive simulations illustrate the validity and effectiveness of the proposed analysis, and provide valuable insights on the impact of the imperfect CSI on the overall network performance.
TL;DR: The proposed algorithm outperforms the other compared schemes and demonstrates the secrecy diversity order and secrecy diversity gains of the UAV assisted relay cognitive network under Nakagami- ${m}$ channel.
Abstract: In view of the scarcity of spectrum resources in wireless communication, it is studied in this paper over the two-hop cognitive secrecy transmission scheme of decoding and forwarding (DF) unmanned aerial vehicles (UAVs) assisted relay with energy harvesting under Nakagami- ${m}$ channel. It is worth noting that the terminal node is equipped with multiple antennas and the optimal antenna selection can be adopted for signal reception. Meanwhile, the UAV assisted relay uses time switching (TS) and power splitting (PS) energy harvesting techniques and adopts optimal secrecy capacity selection scheme. It is successfully derived for the exact closed form expressions of non-zero secrecy capacity probability and optimal secrecy outage probability while the eavesdropper has no channel state information (CSI). Moreover, the system asymptotic secrecy outage probability demonstrates the secrecy diversity order and secrecy diversity gains of the UAV assisted relay cognitive network under Nakagami- ${m}$ channel. Furthermore, joint optimization of power splitting factor and other parameters can effectively increase the system secrecy capacity and improve the system secrecy performance. Simulation results verify the correctness of the theoretical derivation and the effectiveness of the proposed scheme, which demonstrate that the proposed algorithm outperforms the other compared schemes.
TL;DR: This paper investigates the cooperative transmission and resource allocation in cloud based integrated terrestrial-satellite networks, where a resource pool at the cloud acts as the integrated resource management and control center of the entire network.
Abstract: This paper investigates the cooperative transmission and resource allocation in cloud based integrated terrestrial-satellite networks, where a resource pool at the cloud acts as the integrated resource management and control center of the entire network. Considering the operator offers two levels of services of different quality of service (QoS) and price, we formulate a two-layer game based resource allocation problem to maximize the utility of the operator, which is composed of the Stackelberg game between the operator and users, the evolutionary game between all users, and the energy minimization problem. By solving the evolutionary game with replicator dynamics, the selections of users are obtained for any pricing strategy. Then, based on the service selections of users, the energy minimization problem is solved to allocate power and computation resources among users while satisfying the QoS constraints. By analyzing the evolution relationship between the utility and the pricing strategy, we eventually find the Stackelberg equilibrium point of the system, and obtain the optimal pricing as well as the resource allocation strategies for the operator. Finally, numerical results are provided to analyze the behavior of users in the game model, and evaluate the performance of the optimal pricing and resource allocation strategies.
TL;DR: A traffic-flow prediction algorithm that is based on long short-term memory (LSTM) with an attention mechanism to train mobile-traffic data in single-site mode and an intelligent IoT-based mobile traffic prediction-and-control architecture capable of dynamically dispatching communication and computing resources are developed.
Abstract: The popularity of smart mobile devices has led to a tremendous increase in mobile traffic, which has put a considerable strain on the fifth generation of mobile communication networks (5G). Among the three application scenarios covered by 5G, ultra-high reliability and ultra-low latency (uRLLC) communication can best be realized with the assistance of artificial intelligence. For a combined 5G, edge computing and IoT-Cloud (a platform that integrates the Internet of Things and cloud) in particular, there remains many challenges to meet the uRLLC latency and reliability requirements despite a tremendous effort to develop smart data-driven methods. Therefore, this paper mainly focuses on artificial intelligence for controlling mobile-traffic flow. In our approach, we first develop a traffic-flow prediction algorithm that is based on long short-term memory (LSTM) with an attention mechanism to train mobile-traffic data in single-site mode. The algorithm is capable of effectively predicting the peak value of the traffic flow. For a multi-site case, we present an intelligent IoT-based mobile traffic prediction-and-control architecture capable of dynamically dispatching communication and computing resources. In our experiments, we demonstrate the effectiveness of the proposed scheme in reducing communication latency and its impact on lowering packet-loss ratio. Finally, we present future work and discuss some of the open issues.
TL;DR: A reinforcement learning (RL) framework based on slow fading parameters and statistical information is proposed, which can significantly optimize the total capacity of V2I links and ensure the latency and reliability requirements of the V2V links.
Abstract: A 5G network is the key driving factor in the development of vehicle-to-vehicle (V2V) communication technology, and V2V communication in 5G has recently attracted great interest. In the V2V communication network, users can choose different transmission modes and power levels for communication, to guarantee their quality-of-service (QoS), high capacity of vehicle-to-infrastructure (V2I) links and ultra-reliability of V2Vlinks. Aiming atV2V communication mode selection and power adaptation in 5G communication networks, a reinforcement learning (RL) framework based on slow fading parameters and statistical information is proposed. In this paper, our objective is to maximize the total capacity of V2I links while guaranteeing the strict transmission delay and reliability constraints of V2V links. Considering the fast channel variations and the continuous-valued state in a high mobility vehicular environment, we use a multi-agent double deep Q-learning (DDQN) algorithm. Each V2V link is considered as an agent, learning the optimal policy with the updated Q-network by interacting with the environment. Experiments verify the convergence of our algorithm. The simulation results show that the proposed scheme can significantly optimize the total capacity of the V2I links and ensure the latency and reliability requirements of the V2V links.
TL;DR: An Adapted REinforcement Learning VNF Performance Prediction module for Autonomous VNF Placement, namely AREL3P is presented, based on a particular form of Reinforcement Learning adapted to predictions that makes placement decisions more resilient to dynamic conditions, as well as portable to other network nodes, and able to generalize in heterogeneous network environments.
Abstract: The autonomous placement of Virtual Network Functions (VNFs) is a key aspect of Zero-touch network and Service Management (ZSM) in Fifth Generation (5G) networking. Therefore, current orchestration frameworks need to be enhanced, accordingly. To address this need, this work presents an Adapted REinforcement Learning VNF Performance Prediction module for Autonomous VNF Placement, namely AREL3P. Our solution design bears a dual novelty. First, it leverages end-to-end service-level performance predictions for placing VNFs. Second, whereas the majority of other Machine Learning efforts in the literature use Supervised Learning (SL) techniques, AREL3P is based on a particular form of Reinforcement Learning adapted to predictions. This makes placement decisions more resilient to dynamic conditions, as well as portable to other network nodes, and able to generalize in heterogeneous network environments. Backed by a meticulous performance evaluation over a real 5G end-to-end testbed, we verify the above properties after integrating AREL3P to Open Source Management and Orchestration (OSM MANO) decisions. Among other highlights, we show increased VNF performance predictions accuracy by 40–45%, and an overall improved VNF placement efficiency against other SL benchmarks reflected by near-optimal decision scores in 23 out of a total of 27 investigated scenarios.
TL;DR: A depthwise separable convolutional strategy is introduced to build a lightweight deep neural network to reduce its computational cost and detection accuracy and the proposed INES method is applied into the practical construction site for the validation of a specific IIoT application.
Abstract: Decentralized edge computing techniques have been attracted strongly attentions in many applications of intelligent Internet of Things (IIoT). Among these applications, intelligent edge surveillance (INES) methods play a very important role to recognize object feature information automatically from surveillance video by virtue of edge computing together with image processing and computer vision. Traditional centralized surveillance techniques recognize objects at the cost of high latency, high cost and also require high occupied storage. In this paper, we propose a deep learning-based INES technique for a specific IIoT application. First, a depthwise separable convolutional strategy is introduced to build a lightweight deep neural network to reduce its computational cost. Second, we combine edge computing with cloud computing to reduce network traffic. Third, our proposed INES method is applied into the practical construction site for the validation of a specific IIoT application. The detection speed of the proposed INES reaches 16 frames per second in the edge device. After the joint computing of edge and cloud, the detection precision can reach as high as 89%. In addition, the operating cost at the edge device is only one-tenth of that of the centralized server. Experiment results are given to confirm the proposed INES method in terms of both computational cost and detection accuracy.
TL;DR: A novel spectrum sharing technique is proposed using 5G enabled bidirectional cognitive deep learning nodes (BCDLN) along with dynamic spectrum sharing long short-term memory (DSLSTM), and expressions are derived for the spectrum allocated to multiple sources to obtain their spectrum targets as a variant of the participation node spectrum sharing ratio (PNSSR).
Abstract: With the rapid increase in communication technologies, shortage of spectrum will be a major issue faced in the coming years. Cognitive radio is a promising solution to this problem and works on the principle of sharing between cellular subscribers and ad-hoc Device to Device (D2D) users. Existing 5G spectrum sharing techniques work as per a fixed rule and are pre-established. Also, recent game theoretic approaches for spectrum sharing uses unrealistic assumptions with less likely practical implications. Here, a novel spectrum sharing technique is proposed using 5G enabled bidirectional cognitive deep learning nodes (BCDLN) along with dynamic spectrum sharing long short-term memory (DSLSTM). A joint spectrum allocation and management is carried out with wireless cyclic prefix orthogonal frequency division multiple access (CP-OFDMA). The BCDLN self-learning nodes with decision making capability route information to several destinations at a constant spectrum sharing target, and cooperate via DSLSTM. BCDLN based on time balanced and unbalanced channel knowledge is also examined. With the proposed framework, expressions are derived for the spectrum allocated to multiple sources to obtain their spectrum targets as a variant of the participation node spectrum sharing ratio (PNSSR). The impression of noise when all nodes broadcast with equal spectrum allocation is also investigated.
TL;DR: This work proposes and implements Artificial Intelligence (AI)-based Abnormality Detection techniques at the physical (PHY)-layer in CR enabled by learning Generative Models and shows that both of the proposed methods are capable of detecting abnormal signals in the spectrum and pave the road towards Self-Aware radio.
Abstract: Introducing a data-driven Self-Awareness (SA) module in Cognitive Radio (CR) can support the system to establish secure networks against various attacks from malicious users. Such users can manipulate the radio spectrum in order to make the CR learn wrong behaviours and take mistaken actions. A basic SA module includes the ability to learn generative models and detect abnormalities inside the radio spectrum. In this work, we propose and implement Artificial Intelligence (AI)-based Abnormality Detection techniques at the physical (PHY)-layer in CR enabled by learning Generative Models. Specifically, two real-world practical applications related to different data dimensionality and sampling rates are presented. The first application implements the Conditional Generative Adversarial Network (C-GAN) investigated on generalized state vectors extracted from spectrum representation samples to study the dynamic behaviour of the wideband signal. While the second application is based on learning a Dynamic Bayesian Network (DBN) model from a generalized state vector which contains sub-bands information extracted from the radio spectrum. Results show that both of the proposed methods are capable of detecting abnormal signals in the spectrum and pave the road towards Self-Aware radio.
TL;DR: A joint rate splitting problem is formulated to optimally allocate rates for transmission links between two antenna arrays on the UAV to minimize the energy consumption of a UAV in the centralized and distributed MEC computation modes under the constraints of transmission rate and computational time.
Abstract: In the Internet of Things (IoT), numerous low complexity and energy constrained devices are employed to collect and transmit data simultaneously, where the unmanned aerial vehicle (UAV) is an efficient means to relay the signals. Considering the limited power and computational capability of UAV, mobile edge computing (MEC) is carried out to enhance the usage of UAV-aided IoT networks. In order to develop robust UAV-aided MEC systems, energy efficient transmission schemes and low-latency computational resource allocation become crucial to cope with the energy limitation of UAV and computing delay of MEC. In this paper, we develop UAV-aided MEC systems, where UAVs collect data from IoT devices and then transmit to MEC-based access points for computation. In order to minimize the energy consumption of a UAV in the centralized and distributed MEC computation modes under the constraints of transmission rate and computational time, respectively, a joint rate splitting problem is formulated to optimally allocate rates for transmission links between two antenna arrays on the UAV. In addition, the altitude of UAV is analyzed and designed. From simulation results, it shows the proposed architecture is able to provide robust and high quality transmission rate for the UAV-aided MEC systems.
TL;DR: A new approach for blind channel equalization and decoding, variational inference, and variational autoencoders (VAEs) in particular, is introduced and significant and consistent improvements in the error rate of the reconstructed symbols are demonstrated, compared to existing blind equalization methods, thus enabling faster channel acquisition.
Abstract: A new approach for blind channel equalization and decoding, variational inference, and variational autoencoders (VAEs) in particular, is introduced. We first consider the reconstruction of uncoded data symbols transmitted over a noisy linear intersymbol interference (ISI) channel, with an unknown impulse response, without using pilot symbols. We derive an approximate maximum likelihood estimate to the channel parameters and reconstruct the transmitted data. We demonstrate significant and consistent improvements in the error rate of the reconstructed symbols, compared to existing blind equalization methods such as constant modulus, thus enabling faster channel acquisition. The VAE equalizer uses a convolutional neural network with a small number of free parameters. These results are extended to blind equalization over a noisy nonlinear ISI channel with unknown parameters. We then consider coded communication using low-density parity-check (LDPC) codes transmitted over a noisy linear or nonlinear ISI channel. The goal is to reconstruct the transmitted message from the channel observations corresponding to a transmitted codeword, without using pilot symbols. We demonstrate improvements compared to the expectation maximization (EM) algorithm using turbo equalization. Furthermore, unlike EM, the computational complexity of our method does not have exponential dependence on the size of the channel impulse response.