FramCo: Frame corrupted detection for the Open RAN intelligent controller to assist UAV-based mission-critical operations
DOI:
https://doi.org/10.5753/jisa.2024.4036Keywords:
Communication networks, Artificial Intelligence, UAV, Mission-critical operationsAbstract
Unmanned Aerial Vehicles (UAVs) and communication systems are fundamental elements in Mission Critical services, such as Search and Rescue (SAR) operations. UAVs can fly over an area, collect high-resolution video information, and transmit it back to a ground base station to identify victims through a Deep Neural Network object detection model. However, instabilities in the communication infrastructure can compromise SAR operations. For example, if one or more transmitted data packets fail to arrive at their destination, the high-resolution video frames can be distorted, degrading the application performance. In this article, we explore the relevance of computer vision application information, complementing the functionalities of Radio Access Network Intelligent Controllers for managing and orchestrating network components, through FramCo - a frame corrupted detection based on EfficientNet. Another contribution from this article is an architectural element that explores the components of the Open Radio Access Network (O-RAN) standard specification, with an assessment of a complex use case that explores new market trends, such as SAR operations assisted by UAV-based computer vision. The experimental results indicate that the proposed architectural element can act as an external trigger, integrated into the O-RAN cognitive control loop, significantly improving the performance of applications with sensitive Key Performance Indicators (KPIs).
Downloads
References
GPP-TR22.125 (2021-09). Unmanned Aerial System (UAS) support in 3GPP. Technical report, 3rd Generation Partnership Project (3GPP). Available online [link] Version 17.0.4.
Alawada et al. (2023). An unmanned aerial vehicle (uav) system for disaster and crisis management in smart cities. Electronics, 12(4):1051. DOI: 10.3390/electronics12041051.
Bertizzolo et al. (2021). Streaming from the air: Enabling drone-sourced video streaming applications on 5g open-ran architectures. IEEE Transactions on Mobile Computing, 22(5):3004-3016. DOI: 10.1109/TMC.2021.3129094.
Both et al. (2022). System Intelligence for UAV-Based Mission Critical with Challenging 5G/B5G Connectivity. ITU Journal on Future and Evolving Technologies, 2. DOI: 10.48550/arXiv.2102.02318.
Buchner, J. (2022). Image Hashing library. Available at [link]. Accessed: Oct-19-2022.
Da Jiang Innovations (2024). DJI Mavic 3. Available at: [link]. Accessed: Jul-13-2024.
Everingham et al. (2015). The Pascal Visual Object Classes Challenge: A Retrospective. International Journal of Computer Vision, 111(1):98-136. DOI: 10.1007/s11263-014-0733-5.
Hellaoui et al. (2023). On supporting multi-services in uav-enabled aerial communication for the internet of things. IEEE Internet of Things Journal, pages 1-1. DOI: 10.1109/JIOT.2023.3262920.
Kulkarni, S., Chaphekar, V., Uddin Chowdhury, M. M., Erden, F., and Guvenc, I. (2020). Uav aided search and rescue operation using reinforcement learning. In 2020 SoutheastCon, volume 2, pages 1-8. DOI: 10.1109/SoutheastCon44009.2020.9368285.
Li, J. et al. (2022a). 5G New Radio for Public Safety Mission Critical Communications. IEEE Communications Standards Magazine, 6(4):48-55. DOI: 10.1109/MCOMSTD.0002.2100036.
Li, J. et al. (2022b). Toward Providing Connectivity When and Where It Counts: An Overview of Deployable 5G Networks. IEEE Communications Standards Magazine, 6(4):56-64. DOI: 10.1109/MCOMSTD.0003.2100094.
Liang et al. (2023). Model-driven cluster resource management for ai workloads in edge clouds. ACM Trans. Auton. Adapt. Syst., 18(1). DOI: 10.1145/3582080.
Linux Foundation (2024). Traffic Control in the Linux kernel. Available at: [link]. Accessed: Jul-13-2024.
Macedo et al. (2022a). Improved support for UAV-based computer vision applications in Search and Rescue operations via RAN Intelligent Controllers. XL Brazilian Symposium on Telecommunications and Signal Processing, XL. DOI: 10.14209/sbrt.2022.1570817420.
Macedo et al. (2022b). UAV images packet loss distortions. Available at: [link]. Accessed: Jul-12-2024.
Nishio et al. (2021). When wireless communications meet computer vision in beyond 5g. IEEE Communications Standards Magazine, 5(2):76-83. DOI: 10.1109/MCOMSTD.001.2000047.
O-RAN Working Group 1 (2021-02). O-RAN Operations and Maintenance Interface 4.0. Technical specification, O-RAN.WG1.O1-Interface.0-v04.00. Available at: [link].
O-RAN Working Group 1 (2022-03). O-RAN Architecture-Description 6.0. Technical specification, O-RAN.WG1.O-RAN-Architecture-Description-v06.00. Available at: [link].
O-RAN Working Group 2 (2021-07). A1 interface: General aspects and principles 2.03. Technical specification, ORAN-WG2.A1.GAP-v02.03. Available at: [link].
O-RAN Working Group 2 (2021-10). O-RAN AI/ML workflow description and requirements 1.03. Technical specification, O-RAN.WG2.AIML-v01.03. Available at: [link].
O-RAN Working Group 3 (2022-03). O-RAN Near-Real-time RAN Intelligent Controller Architecture & E2 General Aspects and Principles 2.01. Technical specification, O-RAN.WG3.E2GAP-v02.01. Available at: [link].
Our World in Data (2024). Economic damage by natural disaster type, 1900 to 2023. Available at: [link]. Accessed: Jul-13-2024.
Polese, M. et al. (2022). Understanding O-RAN: Architecture, Interfaces, Algorithms, Security, and Research Challenges. CoRR, abs/2202.01032. DOI: 10.48550/arXiv.2202.01032.
Redmon, J. and Farhadi, A. (2018). YOLOv3: An Incremental Improvement. CoRR, abs/1804.02767. DOI: 10.48550/arXiv.1804.02767.
Rezatofighi et al. (2019). Generalized Intersection Over Union: A Metric and a Loss for Bounding Box Regression. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 658-666. DOI: 10.1109/CVPR.2019.00075.
Roldan et al. (2019). ITU Guidelines for national emergency telecommunication plans; ITU-D Emergency Telecommunications Disaster Response. Technical report, International Telecommunication Union (ITU). Available online [link].
Saif et al. (2023). Skyward bound: Empowering disaster resilience with multi-UAV-assisted B5G networks for enhanced connectivity and energy efficiency. Internet of Things, 23:100885. DOI: 10.1016/j.iot.2023.100885.
Shule, W. et al. (2020). UWB-Based Localization for Multi-UAV Systems and Collaborative Heterogeneous Multi-Robot Systems. Procedia Computer Science, 175:357-364. DOI: 10.1016/j.procs.2020.07.051.
Tan, M. and Le, Q. V. (2020). EfficientNet: Rethinking model scaling for convolutional neural networks. CoRR, abs/1905.11946. DOI: 10.48550/arXiv.1905.11946.
Testbeds, N. R. (2024). Open-Access Research Testbed for Next-Generation Wireless Networks. Available at [link]. Accessed: Jul-13-2024.
Wang, Y. et al. (2020). From Design to Practice: ETSI ENI Reference Architecture and Instantiation for Network Management and Orchestration Using Artificial Intelligence. IEEE Communications Standards Magazine, 4(3):38-45. DOI: 10.1109/MCOMSTD.001.1900039.
Wu, X. et al. (2021). Deep Learning for Unmanned Aerial Vehicle-Based Object Detection and Tracking: A Survey. IEEE Geoscience and Remote Sensing Magazine, pages 2-35. DOI: 10.1109/MGRS.2021.3115137.
Xu, D. et al. (2020). Edge Intelligence: Architectures, Challenges, and Applications. CoRR, abs/2003.12172. DOI: 10.48550/arXiv.2003.12172.
Zeng, Y. et al. (2016). Wireless communications with unmanned aerial vehicles: opportunities and challenges. IEEE Communications Magazine, 54(5):36-42. DOI: 10.1109/MCOM.2016.7470933.
Zhang, H. et al. (2021). An empirical study of multi-scale object detection in high resolution UAV images. Neurocomputing, 421:173-182. DOI: 10.1016/j.neucom.2020.08.074.
Zhou et al. (2019). Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing. Proceedings of the IEEE, 107(8):1738-1762. DOI: 10.1109/JPROC.2019.2918951.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 Journal of Internet Services and Applications
This work is licensed under a Creative Commons Attribution 4.0 International License.