Unmanned aerial vehicles (UAVs) have stroke great interested both by the academic community and the industrial community due to their diverse military applications and civilian applications. Furthermore, UAVs are also envisioned to be part of future airspace traffic. The application functions delivery relies on information exchange among UAVs as well as between UAVs and ground stations (GSs), which further closely depends on aeronautical channels. However, there is a paucity of comprehensive surveys on aeronautical channel modeling in line with the specific aeronautical characteristics and scenarios. To fill this gap, this paper focuses on reviewing the air-to-ground (A2G), ground-to-ground (G2G), and air-to-air (A2A) channel measurements and modeling for UAV communications and aeronautical communications under various scenarios. We also provide the design guideline for managing the link budget of UAV communications taking account of link losses and channel fading effects. Moreover, we also analyze the receive/transmit diversity gain and spatial multiplexing gain achieved by multiple-antenna-aided UAV communications. Finally, we discuss the remaining challenge and open issues for the future development of UAV communication channel modeling.

/pdf/a-comprehensive-survey-on-uav-communication-channel-modeling-41snqetr75.pdf

A Comprehensive Survey on UAV Communication Channel Modeling

The rapid development of communication systems poses unprecedented challenges, e.g., handling exploding wireless signals in a real-time and fine-grained manner. Recent advances in data-driven machine learning algorithms, especially deep learning (DL), show great potential to address the challenges. However, waveforms in the physical layer may not be suitable for the prevalent classical DL models, such as convolution neural network (CNN) and recurrent neural network (RNN), which mainly accept formats of images, time series, and text data in the application layer. Therefore, it is of considerable interest to bridge the gap between signal waveforms to DL amenable data formats. In this article, we develop a framework to transform complex-valued signal waveforms into images with statistical significance, termed contour stellar image (CSI), which can convey deep level statistical information from the raw wireless signal waveforms while being represented in an image data format. In this article, we explore several potential application scenarios and present effective CSI-based solutions to address the signal recognition challenges. Our investigation validates that CSI is a promising method to bridge the gap between signal recognition and DL.

Contour Stella Image and Deep Learning for Signal Recognition in the Physical Layer

Complex networks have been studied intensively for a decade, but research still focuses on the limited case of a single, non-interacting network. Modern systems are coupled together and therefore should be modelled as interdependent networks. A fundamental property of interdependent networks is that failure of nodes in one network may lead to failure of dependent nodes in other networks. This may happen recursively and can lead to a cascade of failures. In fact, a failure of a very small fraction of nodes in one network may lead to the complete fragmentation of a system of several interdependent networks. A dramatic real-world example of a cascade of failures (‘concurrent malfunction’) is the electrical blackout that affected much of Italy on 28 September 2003: the shutdown of power stations directly led to the failure of nodes in the Internet communication network, which in turn caused further breakdown of power stations. Here we develop a framework for understanding the robustness of interacting networks subject to such cascading failures. We present exact analytical solutions for the critical fraction of nodes that, on removal, will lead to a failure cascade and to a complete fragmentation of two interdependent networks. Surprisingly, a broader degree distribution increases the vulnerability of interdependent networks to random failure, which is opposite to how a single network behaves. Our findings highlight the need to consider interdependent network properties in designing robust networks.

http://absimage.aps.org/image/MAR10/MWS_MAR10-2009-001087.pdf

Catastrophic cascade of failures in interdependent networks

Big data analytics meets social media: A systematic review of techniques, open issues, and future directions

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.

Deep Reinforcement Learning Control for Radar Detection and Tracking in Congested Spectral Environments

Recently, the development of marine industries has increasingly attracted attention from all over the world. A wide-area and seamless maritime communication network has become a critical supporting approach. In this article, we propose a novel architecture named the maritime giant cellular network (MagicNet) relying on seaborne floating towers deployed in a honeycomb topology. The tower-borne giant-cell base stations are capable of providing wide-area seamless coverage for maritime users and can construct multihop line-of-sight (LoS) links connecting to terrestrial networks. Then the MagicNet-aided maritime network architecture is expounded in terms of five dimensions (i.e., space, air, shore, surface, and underwater), which is compatible with existing systems including maritime satellite networks and maritime Internet of Things, and supports a range of compelling industrial applications. Moreover, we introduce a joint multicast beamforming and relay system for the sake of supporting high-speed and low-cost information services for near-shore areas, as well as a three-tier space-air-surface hybrid network in order to provide reliable wide-area communications for deep offshore areas. Finally, we discuss the open issues and future works on MagicNet.

MagicNet: The Maritime Giant Cellular Network

Network systems, such as Internet, smart grids, transportation networks, social networks, etc., play a critical role in human society. However, due to their inherent vulnerability as well as the limited management and operational capability, these network systems are constantly under the threat of malicious attackers. Therefore, in such attack-defense scenarios, it is particularly significant to make the best use of defenders’ limited resources and capability. In this paper, we propose a networked Colonel Blotto game for the attack–defense strategy, where the attackers and defenders allocate the limited resources on each node, and their utility depends on certain network performance metrics, which are defined for evaluating the performance of the whole network system. Furthermore, considering the complexity of the equilibrium analysis in large-scale network systems, a coevolution-based algorithm is proposed for obtaining the practical action sets as well as achieving the mixed-strategy Nash equilibrium. Finally, relying on four real-world network systems, i.e., computer networks, Internet of vehicles, air transportation systems, and social networks, simulation results show the effectiveness and feasibility of our proposed model, which is conducive to the design, management, and maintenance of network systems.

Colonel Blotto Games in Network Systems: Models, Strategies, and Applications

In order to beneficially exploit the scarce wireless spectral resources, spectrum sharing between communication and radar systems has become a promising research topic. However, traditional network association strategies may not result in efficient hybrid communication and radar systems. We circumvent this problem by formulating a partially observable Markov decision processes (POMDP) aided network association scheme, where the radar user acts as the primary user (PU), while the cognitive communication user is the secondary user (SU). For maximizing the network throughput, whilst minimizing the interference imposed on the radar user, the communication user is configured for adaptively selecting its underlay or overlay access mode. Moreover, a low-complexity near-optimal reinforcement learning algorithm is proposed for the co-design by considering both its complexity and feasibility. Finally, we quantify the performance of our proposed POMDP based network association scheme.

/pdf/network-association-in-machine-learning-aided-cognitive-48e67ktnbh.pdf

Network Association in Machine-Learning Aided Cognitive Radar and Communication Co-Design

In view of the compelling applications in both military and civilian fields, wireless sensor networks (WSNs) have attracted an unprecedented focus on their easy configuration and low cost. Due to the openness of wireless media and constrained resources of WSNs, it is of paramount importance to timely discern the malicious intrusion and unauthorized manipulation. In this paper, we engage in providing an intrusion detection mechanism relying on a novel multi-criteria game. In our model, the interaction between potential attackers and defenders is formulated as a two-player non-zero-sum multi-criteria game, where multiple objectives, i.e. the information security, reputation and energy consumption, are considered when searching for the Pareto equilibrium. Moreover, a light weighting strategy is proposed in order to construct the payoff vector. Finally, simulation results and theoretical analysis show the effectiveness and feasibility of our proposed mechanism.

Intrusion detection for wireless sensor networks: A multi-criteria game approach

Unmanned Aerial Vehicle (UAV) technology has been widely applied in both military and civilian applications. With the increasing complexity of application scenarios, the coordination of multiple UAVs has become a hot topic. However, the limited capability of UAVs make it hard to achieve stable and reliable control. Considering this practical problem, we propose a cloud-based UAV system. It extricates the computing and data storage from UAVs and utilizes the cloud to process the sensor data and to maintain the stable operation of multi-UAV systems. Firstly, we analyze the cloud-based system's on-demand service ability and its impact on UAVs' control procedure. Secondly, we propose a UAV cloud control system (CCS) which serves as a network control system. Moreover, the stable condition of the UAV cloud control system is derived. It reveals the relationship between the acquisition rate of sensor data and the stability of the cloud-based UAV system. Finally, simulations are conducted to verify the effectiveness of previous theoretical analysis.

Sanghai Guan

Papers

MagicNet: The Maritime Giant Cellular Network

Colonel Blotto Games in Network Systems: Models, Strategies, and Applications

Network Association in Machine-Learning Aided Cognitive Radar and Communication Co-Design

Intrusion detection for wireless sensor networks: A multi-criteria game approach

Reliability of Cloud Controlled Multi-UAV Systems for On-Demand Services