Beyond 5G for digital twins of UAVs

doi:10.1016/j.comnet.2021.108366

Computer Networks

Volume 197, 9 October 2021, 108366

https://doi.org/10.1016/j.comnet.2021.108366 Get rights and content

Abstract

The purpose is to explore the application effects and limitations of Unmanned Aerial Vehicle (UAV) in 5G/B5G (Beyond 5G) mobile and wireless communication. Based on 5Gcommunication, the deep learning (DL) algorithm is introduced to construct the UAV Digital Twins (DTs) communication channel model based on DL. The Coordinated Multi-point Transmission (COMP) technology is adopted to study the interference suppression of UAVs. The key algorithm in the physical layer security is employed to ensure information communication security. Finally, the model constructed is simulated and analyzed. The transmission error rates and transmission estimation accuracy of several algorithms, including the proposed algorithm and ordinary Deep Neural Networks (DNNs), are compared under different Signal-to-Noise Ratios (SNRs). Results find that the convergence speed and convergence effect of the proposed algorithm has prominent advantages, presenting strong robustness; the proposed algorithm's estimation accuracy is about 150 times higher than the traditional algorithms. Further analysis reveals that the proposed algorithm's accuracy reaches 82.39%, which increases by at least 3.2% than other classic machine algorithms. The indicators of Precision, Recall, and F1 are compared as well. Apparently, the Precision, Recall, and F1 values of the proposed algorithm are the highest, while the transmission delay is the smallest. Therefore, the constructed UAV DTs wireless communication channel model has strong robustness and further reduces UAV limitations, providing a reference for improving UAV system performance in the later stage.

Introduction

As science and technology advances quickly, the Unmanned Aerial Vehicle (UAV) has become increasingly accepted in various fields. UAV applications in the military field include land security, air defense, border-coastal defense patrols, police security, anti-terrorism, and arrests; those in the civil field include agriculture, forestry protection, pest control, traffic monitoring, electricity, environmental climate assessment, and geological prospecting [1,2]. While UAVs are universally applied, operations in high-risk environments place higher requirements, such as collisions with civil aircraft and accidents that cause injuries after UAV operation errors. Hence, as communication technology develops rapidly, using Digital Twins (DT) to map the physical space during UAV flight into the virtual space in real-time has become a hot topic.

The UAV communication system has the characteristics of mobility, flexibility, and adaptability, making it widely employed in the wireless communication field. Challenges are posed to the existing communication networks to cope with UAV's rapidly growing application fields and business needs. UAV networking and the combination of the Fifth-Generation (5G) communication technology have become an inevitable trend of future development. 5G base stations support flexible 3D beamforming and large-scale antenna technologies, providing UAVs with more 3D and comprehensive coverage and better transmission performance. Simultaneously, 5G networks’ ultra-low latency will provide strong support for UAV Command and Control (C&C) signaling. The next stage of the 5G can be referred to as “Beyond 5G (B5G).” Furthermore, the 5G technology can be optimized from two aspects: Ultra-Reliability Low Latency Communication (URLLC) and massive Machine type of Communication (mMTC). The air interface characteristic supports 52.6∼114.25GHz Millimeter-Wave (MMW) frequency band can be designed, thereby optimizing the 5G technology [3,4]. With the emergence of B5G communication technology, data flow and equipment will expand, and the number of mobile connections will keep growing, even exceeding 100 billion. This result is inseparable from the rapid development of artificial intelligence (AI) and deep learning (DL) algorithms [5]. The accelerated development of high-tech approaches, such as AI, the Internet of Things (IoT), and big data, has promoted the digital development of industrial production exceedingly. The virtual world corresponding to the physical world develops at an unprecedented speed; in turn, the physical world is driven by the digital world for efficient and orderly production. Under this background, DTs applications are born. Moreover, DTs innovation and development in the intelligent manufacturing industry has brought new guiding concepts to solve UAV intelligent control driven by DTs [6]. Therefore, the 5G communication is further optimized by combining the UAV and wireless networks and enabling the flexible coverage of wireless communication signals, in an effort to increase the channel capacity, channel link stability, and transfer rate.

In summary, although the application ranges of UAVs become extensive and the number further increases, there are major problems in the flexible coverage of UAV communication signals. The innovative points are using DTs to remotely control UAVs in high-risk environments and introducing deep learning algorithms based on 5G communication to build a UAV DTs communication channel model. The Coordinated Multi-point Transmission (COMP) technology is applied to UAV interference suppression, and the key algorithm in the physical layer security is applied to ensure information communication security. Finally, the constructed algorithm's performance is simulated and analyzed, providing an important contribution to improving the UAV system performance in the future.

Section snippets

Development trend of UAV communication

Today, when UAVs are widely used in various fields, there are also many accidents linked to UAVs. Wireless communication, a fundamental technology for controlling UAVs, has been studied by many researchers. Fawaz et al. (2018) relaxed these two highly restrictive assumptions by integrating UAV as a buffer auxiliary mobile relay into the traditional relay auxiliary File System Object (FSO) system, thereby improving the performance of the existing relay auxiliary FSO system [7]. Ye et al. (2018)

UAV Application and challenge analysis

With UAV as the subject, the Unmanned Aircraft System (UAS), an integrated system, connects the ground station via the communication data link and assists various elements such as the mission load and personnel. The current UAV communication schemes often depend on simple point-to-point communication on the unlicensed frequency band (ISM, 2.4GHz). Its data rate is low, unreliable, unsafe, susceptible to interference, hard to legally monitor and manage, and can only operate within a minimal

Transmission error rate of each algorithm under different SNRs

The transmission error rate of each algorithm is compared under different SNR, as shown in Fig. 6.

According to Fig. 6a, among the four channel estimation schemes, under the condition of low SNR, the traditional LMMSE channel estimation performs the best, and the scheme of learning network (DNN and RoemNet) cannot achieve the desired effect. However, as the SNR increases, the relationship between the data and the label becomes increasingly apparent. At about 25dB, the performance of RoemNet

Conclusion

To sum up, based on 5G communication, deep learning algorithms are introduced to construct a UAV DTs communication channel model; moreover, the COMP technology is applied to study further and simulate the interference suppression of UAV. Finally, results demonstrate that the constructed wireless communication channel model has strong robustness. The accuracy rate can reach 82.39%, which provides a reference for improving UAV system performance in the future. However, there are some weaknesses

Author statement

Zhihan Lv: Conceptualization, Methodology, Supervision

Dongliang Chen: Software, Investigation, Writing- Original draft preparation

Hailing Feng: Supervision

Ranran Lou: Software, Investigation, Writing- Reviewing and Editing

Huihui Wang: Conceptualization

Declaration of Competing Interest

None.

Acknowledgments

This work was supported by the National Natural Science Foundation of China (No. 61902203) and the Key Research and Development Plan - Major Scientific and Technological Innovation Projects of ShanDong Province (2019JZZY020101).

References (30)

S. Yang et al.
Cost-efficient FPGA implementation of a biologically plausible dopamine neural network and its application[J]
Neurocomputing
(2018)
S. Yang et al.
Efficient spike-driven learning with dendritic event-based processing[J]
Front. Neurosci.
(2021)
W. Yuan et al.
Learning-based predictive beamforming for UAV communications with jittering[J]
IEEE Wirel. Commun.
(2020)
C. Zhong et al.
Secure UAV communication with cooperative jamming and trajectory control[J]
IEEE Commun. Lett.
(2018)
H. Wang et al.
Network-connected UAV communications: potentials and challenges[J]
China Commun.
(2018)
S. Li et al.
Reconfigurable intelligent surface assisted UAV communication: joint trajectory design and passive beamforming[J]
IEEE Wirel. Commun. Lett.
(2020)
M. Bacco et al.
IEEE 802.15. 4 air-ground UAV communications in smart farming scenarios[J]
IEEE Commun. Lett.
(2018)
H. Darvishi et al.
Sensor-fault detection, isolation and accommodation for digital twins via modular data-driven architecture
IEEE Sens. J.
(2020)
W. Fawaz et al.
UAV-aided cooperation for FSO communication systems[J]
IEEE Commun. Mag.
(2018)
J. Ye et al.
Secure UAV-to-UAV systems with spatially random UAVs[J]
IEEE Wirel. Commun. Lett.
(2018)

C. Zhang et al.

Research challenges and opportunities of UAV millimeter-wave communications[J]

IEEE Wirel. Commun.

(2019)

L. Yang et al.

On the performance of RIS-assisted dual-hop UAV communication systems[J]

IEEE Trans. Veh. Technol.

(2020)

R. Li et al.

Intelligent 5G: when cellular networks meet artificial intelligence[J]

IEEE Wirel. Commun.

(2017)

W. Feng et al.

UAV-aided MIMO communications for 5G Internet of Things[J]

IEEE Internet of Things J.

(2018)

B. Li et al.

Secure UAV communication networks over 5G[J]

IEEE Wirel. Commun.

(2019)

Cited by (19)

CoTwin: Collaborative improvement of digital twins enabled by blockchain
2024, Future Generation Computer Systems
Integrating digital twin technology in Cyber–Physical Systems and Internet of Things can boost their intelligence. Given the current maturity of digital twin technology (yet in progress), improving the models that these systems use is typically achieved off-line, requiring the system to stop and reconfigure to run each new model version. In fact, most works use cloud back-ends to run heavy machine learning algorithms, imposing strict requirements on the data exchange between the physical system and the cloud.
We address the online improvement of digital twin models in cyber–physical systems by supporting model refinement without disrupting nor stopping the normal operation of the system. This improves the dynamicity of the system that may turn into a major competitive advantage in a number of industrial scenarios. Precisely, we exploit the collaborative expectation of next generation cyber–physical systems based on highly-connected cells enabled by 5G and 6G networking; and on top of these, we design a shared space properly managed to deliver the needed temporal behaviour required by cyber–physical systems.
For this, we present the design of CoTwin framework as a middleware that allows cells to collectively improve digital twin models seamlessly. CoTwin manages the interaction of cells with a blockchain-based collaborative space offering a built-in trusted storage model. We integrate neural network algorithms as they provide fast execution that meet the time-sensitivity requirements of cyber–physical systems. Our contribution is validated by means of its implementation and deployment on an actual blockchain network, and an exhaustive set of experiments to analyse the resulting overhead and temporal behaviour. Results show that CoTwin achieves stable execution times across all its functional pieces; and it exhibits stable service time for large sets of cells.
How to build a Digital Twin for operating PEM-Electrolyser system – A reference approach
2024, Annual Reviews in Control
Operating electrolyzers for producing green hydrogen is a critical emerging issue because of either the broader use of hydrogen for several scopes or the short life span and efficiency of these components. Digital Twin offers a new opportunity to effectively face these problems by improving online control and providing fault detection, diagnosis, and prediction services. Since the Digital Twin is, in fact, a virtual mirror of a real system continuously updated by information received from the field, it allows it to swiftly react to small signals of departure from standard or optimal conditions. Although Digital Twins are widely applied in different fields, comprehensive guidance on developing and designing a Digital Twin in the literature is still lacking. This manuscript aims to provide a comprehensive guide on how to build the Digital Twin of a PEM-Electrolyzer. In particular, the architecture of the Digital Twin is initially presented, then all its components are analyzed, showing the steps to be performed to build a Digital Twin for operating PEM-Electrolyser system.
Unlocking information technology infrastructure for promoting climate resilience and environmental quality
2024, Technological Forecasting and Social Change
We examine the role of Information Technological Infrastructure (ITI) in promoting climate resilience and environmental quality in OECD countries. Our empirical strategy is framed in the advanced econometrics methodology. Our analysis begins with standard specification, which controls for unobserved factors in the panel data. We then explore the variables' long and short-run relationships using the Generalised Method of Moment dynamic family specifications. We also evaluate the heterogeneity drivers of environmental quality using Quantile via Moment. The analysis is also extended using alternative and complementary statistical procedures by Hausman–Taylor and Feasible Generalised Least Squares as robustness checks. Our findings indicate that ITI and renewable energy significantly mitigates carbon emissions and can be helpful in achieving a net-zero target. In contrast, the empirical evidence reveals that economic growth and non-renewable energy usage are harmful to the environment. The finding also suggests a significant degree of heterogeneity exists in the covariates on the conditional distribution of environmental quality and its driven factors. While the findings reaffirm the significance of ITI in ensuring careful planning and monitoring of critical infrastructure, they also show that ITI can be used to balance the entire system by creating resilience. We strongly suggest that policymakers should use ITI to spur innovation and drive better solutions for energy transition and environmental improvement.
Guest Editorial: Recent Advances in Connected and Autonomous Unmanned Aerial/Ground Vehicles
2022, Computer Networks
A buffer-aware dynamic UAV trajectory design for data collection in resource-constrained IoT frameworks
2022, Computers and Electrical Engineering
Citation Excerpt :
Unmanned aerial vehicle (UAV) communication is likely to become more reliable, robust, and efficient as technologies like smart cities, 5G, Internet of Things (IoT), and artificial intelligence continue to advance [1–3].
The emergence of unmanned aerial vehicle (UAV)-enabled technology in the Internet of Things (IoT) era leads to a significant reduction in data collection delays when accumulating sensory data from ground IoT nodes (INs). As a flying data collector, the UAV hovers at a limited number of Access Points (APs) to collect data, outperforming ground data collectors in terms of transmission energy consumption, data delivery reliability, and timeliness. However, the INs have a finite amount of buffer capacity to store the data that must be collected before they overflow. As a result, the data gathering route for UAVs should be adaptable to INs’ buffer deadline in order to minimize data loss. In this paper, a buffer-aware dynamic UAV trajectory design protocol is proposed for data collection from resource-constrained INs. A distributed AP nomination strategy is proposed in order to reduce UAV hovering latency. Furthermore, using machine learning approaches, a modified ant colony optimization algorithm is constructed to minimize the data loss penalty due to buffer overflow. Finally, the performance of the proposed scheme is evaluated against several state-of-the-art protocols with regards to parameters such as data loss penalty, packet delivery ratio, and network lifetime.
Energy efficiency in 5G systems: A systematic literature review
2024, International Journal of Knowledge-Based and Intelligent Engineering Systems

View all citing articles on Scopus

Zhihan Lv is IEEE Senior Member, British Computer Society Fellow and ACM Distinguished Speaker. He is currently a Professor of Qingdao University, China. He has been an Assistant Professor at Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences from 2012 to 2016. He received his Ph.D. from Paris7 University and Ocean University of China in 2012. He worked in CNRS (France) as Research Engineer, Umea University/KTH Royal Institute of Technology (Sweden) as Postdoc Research Fellow, Fundacion FIVAN (Spain) as Experienced Researcher, University College London (UK) as Research Associate, University of Barcelona (Spain) as Postdoc. He was a Marie Curie Fellow in European Union's Seventh Framework Program LANPERCEPT. His research mainly focuses on Internet of Things, Multimedia, Virtual Reality, Serious Game, HCI, Big data. He has contributed 300+ papers in the related fields on journals such as IEEE TII, IEEE TITS, IEEE TFS, IEEE TSMC, IEEE TETC, IEEE TBD, IEEE/ACM TCBB, IEEE TNSE, IEEE TVT, IEEE TCSS, IEEE JSAC, IEEE JSTSP, IEEE COMMAG, IEEE Network, IEEE IOTJ, ACM TOMM, ACM TOIT, ACM TIST, and conferences such as ACM MM, ACM CHI, ACM Siggraph, ICCV, IEEE Virtual Reality. He has more than 20 ESI highly cited papers and 6 ESI hot papers.He is Editor-in-Chief of Internet of Things and Cyber-Physical Systems(KeAi), an Associate Editor of IEEE Transactions on Intelligent Transportation System, Computer Communications, Scientific Reports, Plos one, IEEE Access, Neurocomputing, IET Image Processing, PeerJ. He is the Leading Guest Editors for 40 special issues including IEEE Transactions on Industrial Informatics, IEEE Transactions on Intelligent Transportation Systems, IEEE Network, IEEE Sensors, IEEE Consumer Electronics Magazine, IEEE Communications Standards Magazine, IEEE Journal of Biomedical and Health Informatics, Future Generation Computer Systems, Neurocomputing, Neural Computing and Applications. He is Co-Chair or Program Committee member of ACM IUI2015-2021, IEEE CHASE Workshop on BIGDATA4HEALTH 2016, 2017, IEEE/CIC WIN Workshop 2016, IIKI2016-2021, WASA2016, 2017, IEEE PDGC2016, ACM SAC2017-WCN Track, IEEE CTS2016 Workshop on IoT2016, IEEE DASC2017,2020, ISAPE2017, IoTBDS2017, IEEE AIMS2017, IEEE iThings-2017, IEEE VTC2017-Fall, IEEE INFOCOM 2020-2021 workshop, ACM MobiCom 2020 workshop, ISAIR2021, ICC 2021 workshop. He has reviewed 300 papers as a reviewer for journals such as IEEE TMM, ACM TOMM, IEEE TII, IEEE TBD, IEEE TMC, IEEE TLL, IEEE TETC, IEEE TC, IEEE TVCG, IEEE TITS, IEEE/ACM TCBB, IEEE TDSC, ACM TOIT, IEEE Network, IEEE MultiMedia, IEEE IOTJ, IEEE COMMAG, and conference e.g. ACM MUM, ACM CHI, ACM DIS, IEEE EuroVis, ACM UIST, ACM MobileHCI, ACM CHIPLAY, ACM CSCW, ACM SUI, ACM ITS, IEEE VAST, IEEE VR, ACM IUI, IEEE 3DUI, ACM TVX, ACM Creativity & Cognition, ACM EICS, ACM IDC, IEEE ICSIPA, GI, IEEE ITSC, IEEE Sensors, ACM ACI, ACM VRST, ACM ISS, ACM HRI. He has received more than 20 awards from China, Europe, IEEE. He has received 1.5 million US dollars funding from government and industry as PI. He has been involved in many European and Chinese projects supported with funding of 25 million US dollars. He has given 30 invited talks for universities and companies in Europe and China, e.g., Aston University, University of Gothenburg, University of Geneva, Linkoping University, Aarhus University, Norwegian University of Science and Technology, Delft University of Technology, University of Electronic Science and Technology of China, Huawei, Alibaba, Tencent. He has given 14 keynote speech for International conferences.

Dongliang Chen is currently pursuing the M.S degree with the College of Computer Science and Technology, Qingdao University, China. Dongliang Chen's research direction include Deep Learning, Computer Vision, Serious Game, Cyber Security, Reinforcement Learning, Game Analysis. He has published 10 papers in IOTJ, FGCS, TOIT, SCS, IMAVIS journals.

Hailing Feng Received his PhD in computer science from the University of Science and Technology of China in June 2007. Since 2007, he worked in the school of information engineering of Zhejiang A&F University. From 2013 to 2014, he was a visiting professor at Forest Products Laboratory, USDA. He is currently a professor in the school of information engineering. His main interest areas include computer vision, intelligent information processing, Internet of Things.

Ranran Lou is currently a graduate student of software engineering in the College of Computer Science and Technology of Qingdao University, and his research direction is Deep Learning and Big Data. He received a bachelor's degree in engineering from Qingdao University in 2019. He has extensive experience in marine data processing.

Huihui Wang is an Associate Professor and the Director of Cybersecurity program at St. Bonaventure University. Dr. Wang's current interests are Cybersecurity of Cyber Physical Systems/Internet of Things, and the cyber/engineering education. She has been awarded about $1.8M from the external grant agencies including NSF, private foundations and industry. Dr. Wang has been actively serving as TPC Chairs, reviewers of various panels, journals and conferences. She is a senior member of IEEE, a member and the Program Chair of ASEE (2020-2021).

View full text

Beyond 5G for digital twins of UAVs

Abstract

Introduction

Section snippets

Development trend of UAV communication

UAV Application and challenge analysis

Transmission error rate of each algorithm under different SNRs

Conclusion

Author statement

Declaration of Competing Interest

Acknowledgments

Neurocomputing

Front. Neurosci.

Learning-based predictive beamforming for UAV communications with jittering[J]

IEEE Wirel. Commun.

Secure UAV communication with cooperative jamming and trajectory control[J]

IEEE Commun. Lett.

Network-connected UAV communications: potentials and challenges[J]

China Commun.

Reconfigurable intelligent surface assisted UAV communication: joint trajectory design and passive beamforming[J]

IEEE Wirel. Commun. Lett.

IEEE 802.15. 4 air-ground UAV communications in smart farming scenarios[J]

IEEE Commun. Lett.

Sensor-fault detection, isolation and accommodation for digital twins via modular data-driven architecture

IEEE Sens. J.

UAV-aided cooperation for FSO communication systems[J]

IEEE Commun. Mag.

Secure UAV-to-UAV systems with spatially random UAVs[J]

IEEE Wirel. Commun. Lett.

Research challenges and opportunities of UAV millimeter-wave communications[J]

IEEE Wirel. Commun.

On the performance of RIS-assisted dual-hop UAV communication systems[J]

IEEE Trans. Veh. Technol.

Intelligent 5G: when cellular networks meet artificial intelligence[J]

IEEE Wirel. Commun.

UAV-aided MIMO communications for 5G Internet of Things[J]

IEEE Internet of Things J.

Secure UAV communication networks over 5G[J]

IEEE Wirel. Commun.