Space Air Ground

Aeronautical Ad Hoc Networking 

[1] J. Zhang, T. Chen, S. Zhong, J. Wang, W. Zhang, X. Zuo, R. Maunder and L. Hanzo, "Aeronautical Ad Hoc Networking for the Internet-Above-the-Clouds," Proceedings of the IEEE, vol. 107, no. 5, pp. 868-911, 2019, doi: 10.1109/JPROC.2019.2909694. [Full paper] 

[2]J. Zhang, L. Xiang, D. Liu, J. Cui, S. X. Ng, R. Maunder, T. Graeupl, C. Uwe and L. Hanzo, "Semi-Stochastic Aircraft Mobility Modelling for Aeronautical Networks: An Australian Case-Study Based on Real Flight Data," IEEE Transactions on Vehicular Technology, vol. 70, no. 10, pp. 10763-10779, 2021, doi: 10.1109/TVT.2021.3104118. [Full paper]

[Slides]

[More publications]

[1] Aeronautical Ad Hoc Networking for the Internet-Above-the-Clouds

The engineering vision of relying on the “smart sky” for supporting air traffic and the “internet-above-the clouds”for in-flight entertainment has become imperative for the future aircraft industry. Aeronautical ad hoc networking(AANET) constitutes a compelling concept for providing broadband communications above clouds by extending the coverage of air-to-ground (A2G) networks to oceanic and remote airspace via autonomous and self-configured wireless networking among commercial passenger airplanes.This paper provides an overview of AANET solutions by characterizing the associated scenarios, requirements, and challenges. Explicitly, the research addressing the key techniques of AANETs, such as their mobility models, network scheduling and routing, security, and interference, is reviewed. Furthermore, we also identify the remainingchallenges associated with developing AANETs and presenttheir prospective solutions as well as open issues. The designframework of AANETs and the key technical issues are investigatedalong with some recent research results. Furthermore,a range of performance metrics optimized in designing AANETsand a number of representative multiobjective optimizationalgorithms are outlined.

 AANET topology and the corresponding logical topology. (a) PHY topology. (b) Logical topology

[2] Semi-Stochastic Aircraft Mobility Modelling for Aeronautical Networks: An Australian Case-Study Based on Real Flight Data

Terrestrial Internet access is gradually becoming thenorm across the globe. However, there is a growing demand forInternet access of passenger airplanes. Hence, it is essential todevelop aeronautical networks above the clouds. Therefore, theconception of an aircraft mobility model is one of the prerequisitefor aeronautical network design and optimization. However, thereis a paucity of realistic aircraft mobilitymodels capable of generatinglarge-scale flight data. To fill this knowledge-gap, we develop a semi-stochastic aircraft mobility model based on large-scale real historical Australian flights acquired both on June 29th, 2018and December 25th, 2018, which represent the busiest day and the quietest day of 2018, respectively. The semi-stochastic aircraft mobility model is capable of generating an arbitrary number of flights, which can emulate the specific features of aircraft mobility.The semi-stochastic aircraft mobility model was then analysed and validated both by the physical layer performance and network layer performance in the case study ofAustralian aeronautical networks, demonstrating that it is capable of reflecting the statistical characteristics of the real historical flights.

[top]

Single-Objective Optimizations

[1]  C. Xu, J. Zhang, T. Bai, P. Botsinis, R. Maunder, R. Zhang and L. Hanzo, "Adaptive Coherent/Non-Coherent Single/Multiple-Antenna Aided Channel Coded Ground-to-Air Aeronautical Communication," *IEEE Transactions on Communications,* vol. 67, no. 2, pp. 1099-1116, 2019

[2] J. Cui, D. Liu, J. Zhang, H. Yetgin, S. X. Ng, R. G. Maunder, L. Hanzo,"Minimum-Delay Routing for Integrated Aeronautical Ad Hoc Networks Relying on Real Flight Data in the North-Atlantic Region", in IEEE OJVT, vol. 2, pp. 310-320, 2021.[Full paper] 

[More publications]

[1] Adaptive Coherent/Non-Coherent Single/Multiple-Antenna Aided Channel Coded Ground-to-Air Aeronautical Communication

First of all, we conceive a generic multiple-symbol differential sphere detection (MSDSD) solution for both single- and multiple-antenna-based non-coherent schemes in both uncoded and coded scenarios, where the high-mobility aeronautical Ricean fading features are taken into account.The bespoke design is the first MSDSD solution in the open literature that is applicable to the generic differential space-time modulation (DSTM) for transmission over Ricean fading. In thelight of this development, the recently developed differentialspatial modulation and its diversity counterpart of differentialspace-time block coding using index shift keying are specificallyrecommended for aeronautical applications owing to theirlow-complexity single-RF and finite-cardinality features. Moreover, we further devise a non-coherent decision-feedback differential detection and a channel-state information estimation aided coherent detection, which also take into account the same Ricean features. Finally, the advantages of the proposed techniques indifferent scenarios lead us to propose for the aeronautical systems to adaptively: 1) switch between coherent and non-coherent schemes; 2) switch between single- and multiple-antenna-based schemes as well as; and 3) switch between high-diversity and high-throughput DSTM schemes.

[2] Minimum-Delay Routing for Integrated Aeronautical Ad Hoc Networks Relying on Real Flight Data in the North-Atlantic Region

Relying on multi-hop communication techniques, aeronautical ad hoc networks (AANETs) seamlessly integrate ground base stations (BSs) and satellites into aircraft communications for enhancing the on-demand connectivity of planes in the air. Our research starts from assessing the performance of the classic shortest-path routing algorithm in the context of the real flight data collected in the North-Atlantic Region. Specifically, in this integrated AANET context we investigate the shortest-path routing problem with the objective of minimizing the total delay of the in-flight connection from the ground BS subject to certain minimum-rate constraints for all selected links in support of low-latency and high-speed services. Inspired by the best-first search and priority queue concepts, we model the problem formulated by a weighted digraph and find the optimal route based on the shortest-path algorithm.  

 [See example]

[top]

Multi-Objective Optimizations

[1] J. Cui, S. X. Ng, D. Liu, J. Zhang, A. Nallanathan and L. Hanzo, “Multi-objective optimization for integrated ground-air-space networks,” IEEE VTM, 2021. [Full paper]

[2] J. Cui, H. Yetgin, D. Liu, J. Zhang, S. X. Ng and L. Hanzo, "Twin-Component Near-Pareto Routing Optimization for AANETs in the North-Atlantic Region Relying on Real Flight Statistics," in IEEE OJVT, 2021.[Full paper]

[3] J. Zhang, S. Chen, F. Wang, S. X. Ng, R. G. Maunder, and L. Hanzo, "Priority-Aware Secure Precoding Based on Multi-Objective Symbol Error Ratio Optimization," IEEE Transactions on Communications, vol. 69, no. 3, pp. 1912-1929, 2021. [Full paper]

[More publications]

[1] Multi-objective optimization for integrated ground-air-space networks

With space and aerial platforms deployed at differentaltitudes, integrated ground-air-space (IGAS) networks willhave multiple vertical layers, hence forming a three-dimensional(3D) structure. These 3D IGAS networks integrating both aerialand space platforms into terrestrial communications constitute apromising architecture for building fully connected global nextgeneration networks (NGNs). This article presents a systematictreatment of 3D networks from the perspective of multi-objectiveoptimization. Given the inherent features of these 3D links,the resultant 3D networks are more complex than conventionalterrestrial networks. To design 3D networks accommodating thediverse performance requirements of NGNs, this article providesa multi-objective optimization framework for 3D networks interms of their diverse performance metrics. We conclude byidentifying a range of future research challenges in designing3D networks and by highlighting a suite of potential solutions. 

Requirements of KPIs for IMT-2000, IMT-Advance, IMT-2020 and the future networks

[2] Twin-Component Near-Pareto Routing Optimization for AANETs in the North-Atlantic Region Relying on Real Flight Statistics

Integrated ground-air-space (IGAS) networks intrinsically amalgamate terrestrial and non-terrestrial communication techniques in support of universal connectivity across the globe. Multi-hop routing over the IGAS networks has thepotential to provide long-distance highly directional connectionsin the sky. For meeting the latency and reliability requirementsof in-flight connectivity, we formulate a multi-objective multi-hoprouting problem in aeronautical ad hoc networks (AANETs) forconcurrently optimizing multiple end-to-end performance metricsin terms of the total delay and the throughput. In contrast tosingle-objective optimization problems that may have a uniqueoptimal solution, the problem formulated is a multi-objectivecombinatorial optimization problem (MOCOP), which generallyhas a set of trade-off solutions, called the Pareto optimal set. Dueto the discrete structure of the MOCOP formulated, finding thePareto optimal set becomes excessively complex for large-scalenetworks. Therefore, we employ a multi-objective evolutionary algorithm (MOEA), namely the classic NSGA-II for generating an approximation of the Pareto optimal set. Explicitly, with the intrinsic parallelism of MOEAs, the MOEA employed starts with a set of candidate solutions for creating and reproducing new solutions via genetic operators. Finally, we evaluate the MOCOPformulated for different networks generated both from simulateddata as well as from real historical flight data. Our simulation results demonstrate that the utilized MOEA has the potential of finding the Pareto optimal solutions for small-scale networks, while also finding a set of high-performance nondominated solutions for large-scale networks.

[See Example 1 and Example 2]

[3] Priority-Aware Secure Precoding Based on Multi-Objective Symbol Error Ratio Optimization

The secrecy capacity based on the assumption of having continuous distributions for the input signals constitutes one of the fundamental metrics for the existing physical layer security (PHYS) solutions. However, the input signals of real-world communication systems obey discrete distributions. Furthermore, apart from the capacity, another ultimate performance metric of a communication system is its symbol error ratio (SER). In this paper, we pursue a radically new approach to PHYS by considering rigorous direct SER optimization exploiting the discrete nature of practical modulated signals. Specifically, we propose a secure precoding technique based on a multi-objective SER criterion, which aims for minimizing the confidential messages’ SER at their legitimate user, while maximizing the SER of the confidential messages leaked to the illegitimate user. The key to this challenging multi-objective optimization problem is to introduce a priority factor that controls the priority of directly minimizing the SER of the legitimate user against directly maximizing the SER of the leaked confidential messages. Furthermore, we define a new metric termed as the security-level, which is related to the conditional symbol error probability of the confidential messages leaked to the illegitimate user. Additionally, we also introduce the secure discrete-input continuous-output memoryless channel (DCMC) capacity referred to as secure-DCMC-capacity, which serves as a classical security metric of the confidential messages, given a specific discrete modulation scheme. The impacts of both the channel’s Rician factor and the correlation factor of antennas on the security-level and the secure-DCMC-capacity are investigated. Our simulation results demonstrate that the proposed priority-aware secure precoding based on the direct SER metric is capable of securing transmissions, even in the challenging scenario, where the eavesdropper has three receive antennas, while the legitimate user only has a single one.

[top]

Deep Learning for AANETs

[1] D. Liu, J. Cui, J. Zhang, C. Yang, and L. Hanzo, "Deep Reinforcement Learning Aided Packet-Routing for Aeronautical Ad-Hoc Networks Formed by Passenger Planes," IEEE Transactions on Vehicular Technology, vol. 70, no. 5, pp. 5166-5171, 2021. [Full paper]

[2] D. Liu, J. Zhang, J. Cui, S. X. Ng, R. G. Maunder, and L. Hanzo, "Deep-Learning-Aided Packet Routing in Aeronautical Ad Hoc Networks Relying on Real Flight Data: From Single-Objective to Near-Pareto Multiobjective Optimization," IEEE Internet of Things Journal, vol. 9, no. 6, pp. 4598-4614, 2022. [Full paper]

[3] D. Liu, J. Zhang, J. Cui, S. X. Ng, R. G. Maunder, and L. Hanzo, "Deep Learning Aided Routing for Space-Air-Ground Integrated Networks Relying on Real Satellite, Flight, and Shipping Data," IEEE Wireless Communications, vol. 29, no. 2, pp. 177-184, 2022. [Full paper]

[4] T. M. Hoang, D. Liu, T. V. Luong, J. Zhang, and L. Hanzo, "Deep Learning Aided Physical-Layer Security: The Security Versus Reliability Trade-Off," IEEE Transactions on Cognitive Communications and Networking, vol. 8, no. 2, pp. 442-453, 2022. [Full paper]

[More publications]

 [1]  Deep Reinforcement Learning Aided Packet-Routing for Aeronautical Ad-Hoc Networks Formed by Passenger Planes

Data packet routing in aeronautical ad-hoc networks (AANETs) is challenging due to their high-dynamic topology. In this paper, we invoke deep reinforcement learning for routing in AANETs aiming at minimizing the end-to-end (E2E) delay. Specifically, a deep Q-network (DQN) is conceived for capturing the relationship between the optimal routing decision and the local geographic information observed by the forwarding node. The DQN is trained in an offline manner based on historical flight data and then stored by each airplane for assisting their routing decisions during flight. To boost the learning efficiency and the online adaptability of the proposed DQN-routing, we further exploit the knowledge concerning the system's dynamics by using a deep value network (DVN) conceived with a feedback mechanism. Our simulation results show that both DQN-routing and DVN-routing achieve lower E2E delay than the benchmark protocol, and DVN-routing performs similarly to the optimal routing that relies on perfect global information.

[2] Deep-Learning-Aided Packet Routing in Aeronautical Ad Hoc Networks Relying on Real Flight Data: From Single-Objective to Near-Pareto Multiobjective Optimization

Data packet routing in aeronautical ad-hoc networks (AANETs) is challenging due to their high-dynamic topology. In this paper, we invoke deep learning (DL) to assist routing in AANETs. We set out from the single objective of minimizing the end-to-end (E2E) delay. Specifically, a deep neural network (DNN) is conceived for mapping the local geographic information observed by the forwarding node into the information required for determining the optimal next hop. The DNN is trained by exploiting the regular mobility pattern of commercial passenger airplanes from historical flight data. After training, the DNN is stored by each airplane for assisting their routing decisions during flight relying solely on local geographic information. Furthermore, we extend the DL-aided routing algorithm to a multi-objective scenario, where we aim for simultaneously minimizing the delay, maximizing the path capacity, and maximizing the path lifetime. Our simulation results based on real flight data show that the proposed DL-aided routing outperforms existing position-based routing protocols in terms of its E2E delay, path capacity as well as path lifetime, and it is capable of approaching the Pareto front that is obtained using global link information.

[3] Deep Learning Aided Routing for Space-Air-Ground Integrated Networks Relying on Real Satellite, Flight, and Shipping Data

Current maritime communications mainly rely on satellites having meager transmission resources, hence suffering from poorer performance than modern terrestrial wireless networks. With the growth of transcontinental air traffic, the promising concept of aeronautical ad hoc networking relying on commercial passenger airplanes is potentially capable of enhancing satellite-based maritime communications via air-to-ground and multi-hop air-to-air links. In this article, we conceive space-air-ground integrated networks (SAGINs) for supporting ubiquitous maritime communications, where the low-earth-orbit satellite constellations, passenger airplanes, terrestrial base stations, ships, respectively, serve as the space-, air-, ground- and sea-layer. To meet heterogeneous service requirements, and accommodate the time-varying and self-organizing nature of SAGINs, we propose a deep learning (DL) aided multi-objective routing algorithm, which exploits the quasi-predictable network topology and operates in a distributed manner. Our simulation results based on real satellite, flight, and shipping data in the North Atlantic region show that the integrated network enhances the coverage quality by reducing the end-to-end (E2E) delay and by boosting the E2E throughput as well as improving the path-lifetime. The results demonstrate that our DL-aided multi-objective routing algorithm is capable of achieving near Pareto-optimal performance.

[4] Deep Learning Aided Physical-Layer Security: The Security Versus Reliability Trade-Off

This paper considers a communication system whose source can learn from channel-related data, thereby making a suitable choice of system parameters for security improvement. The security of the communication system is optimized using deep neural networks (DNNs). More explicitly, the associated security vs reliability trade-off problem is characterized in terms of the symbol error probabilities and the discrete-input continuous-output memoryless channel (DCMC) capacities. A pair of loss functions were defined by relying on the Lagrangian and on the monotonic-function based techniques. These were then used for managing the learning/training process of the DNNs for finding near-optimal solutions to the associated non-convex problem. The Lagrangian technique was shown to approach the performance of the exhaustive search. We concluded by characterizing the security vs reliability trade-off in terms of the intercept probability vs the outage probability.

[top]

UAV Communications

[1] C. Xu, T. Bai, J. Zhang , R. Rajashekar, R. Maunder, Z. Wang and L. Hanzo, "Adaptive Coherent/Non-Coherent Spatial Modulation Aided Unmanned Aircraft Systems,"  IEEE Wireless Communications, vol. 26, no. 4, pp. 170-177, 2019. [Full paper]

[2]  B. Chen, D. Liu, and L. Hanzo, "Decentralized Trajectory and Power Control Based on Multi-Agent Deep Reinforcement Learning in UAV Networks," in IEEE ICC, 16-20 May 2022. [Full paper]

[More publications]

[1] Adaptive Coherent/Non-Coherent Spatial Modulation Aided Unmanned Aircraft Systems

UAVs are envisioned to be an important part of the device-centric IoT. These bespoke Unmanned Aircraft Systems (UASs) that support UAVs significantly differ from traditional terrestrial and aeronautical networks, both of which are evolving toward their next-generation forms. The major challenges of the UAS include augmented interference due to strong LoS, the dynamic shadowing effects owing to 3-D aerial maneuvering, the excessive Doppler shift owing to high UAV mobility, and the SWAP constraints. Against this background, we propose to invoke the recently developed coherent/non-coherent SM and its diversity-oriented counterpart of STBC-ISK. These arrangements employ multiple TAs in order to improve the network's QoS, but they only use a single RF chain. Furthermore, based on the throughput, delay and power-efficiency, we conceive a novel three-fold adaptivity design, where the UAS may adaptively switch between coherent and non-coherent schemes, switch between single- and multiple-TA based arrangements, as well as switch between high-diversity and high-spectral-efficiency multiple-TA based schemes.

[2] Decentralized Trajectory and Power Control Based on Multi-Agent Deep Reinforcement Learning in UAV Networks

Unmanned aerial vehicles (UAVs) are capable of enhancing the coverage of existing cellular networks by acting as aerial base stations (ABSs). Due to the limited on-board battery capacity and dynamic topology of UAV networks, trajectory planning and interference coordination are crucial for providing satisfactory service, especially in emergency scenarios, where it is unrealistic to control all UAVs in a centralized manner by gathering global user information. Hence, we solve the decentralized joint trajectory and transmit power control problem of multi-UAV ABS networks. Our goal is to maximize the number of satisfied users, while minimizing the overall energy consumption of UAVs. To allow each UAV to adjust its position and transmit power solely based on local- rather the global-observations, a multi-agent reinforcement learning (MARL) framework is conceived. In order to overcome the non-stationarity issue of MARL and to endow the UAVs with distributed decision making capability, we resort to the centralized training in conjunction with decentralized execution paradigm. By judiciously designing the reward, we propose a decentralized joint trajectory and power control (DTPC) algorithm with significantly reduced complexity. Our simulation results show that the proposed DTPC algorithm outperforms the state-of-the-art deep reinforcement learning based methods, despite its low complexity.

[top]