A Review on Machine Learning Techniques Used in VANET and FANET Networks

Year 2022, Volume: 9 Issue: 2, 1150 - 1165, 31.12.2022

Sumeyra Muti Eyüp Emre Ülkü

https://doi.org/10.35193/bseufbd.1102897

Abstract

The widespread use of the Internet and the increase in the number and variety of devices connected to the internet have led to the emergence of new methods in wireless communication. Dynamic and temporary Ad-Hoc networks, which do not require a fixed infrastructure as in traditional wireless network communication, are one of these new methods. The fact that Ad-Hoc networks do not need a fixed infrastructure has revealed a network structure with a lower cost and less configuration. Mobile Ad-Hoc networks play an important role, especially in the communication of nodes on the move. FANET (Flying Ad-Hoc Networks) networks, which are called flying ad hoc networks, are mobile Ad-Hoc networks used for communication of unmanned aerial vehicles (UAV), and VANET (Vehicular Ad-Hoc Networks) networks, which are called vehicular ad hoc networks, are mobile Ad-Hoc networks used for communication of road vehicles. The development and dissemination of these networks make a significant contribution to the development of autonomous vehicles and UAVs. The increase in the use of FANET and VANET networks, which are specialized subnets of mobile Ad-Hoc networks, and the increase in the number of nodes in these networks have caused problems related to security, efficiency, and sustainability in these networks. Machine learning methods, one of today' s effective and common approaches, are one of the ways that are frequently used in solving the problems specified in FANET and VANET networks. The rapid topology change, which is one of the most important features of these networks, makes it difficult to provide traffic management, trust management, routing, and data transmission. In this direction, machine learning approaches play an active role. In this study, it is presented by examining which machine learning techniques are used in the literature to perform important tasks such as traffic management, trust management, routing, and data transfer. Thus, it is aimed for those who will work in these fields to acquire information about machine learning approaches that can be used. Since the FANET network type is a new approach, it has been observed that there are few studies using machine learning. In VANET systems, studies using machine learning methods are especially intense in 2021. This study was carried out to give the reader an idea about which machine learning methods can be used in which problems in FANET and VANET networks.

Keywords

Ad Hoc, Wireless Communication, VANET, FANET, Machine Learning

VANET ve FANET Ağlarda Kullanılan Makine Öğrenimi Teknikleri Üzerine İnceleme

Abstract

İnternetin yaygınlaşması ve internete bağlı cihaz sayısı ve çeşitliliğinin artması kablosuz iletişimde yeni yöntemlerin ortaya çıkmasını sağlamıştır. Geleneksel kablosuz ağ iletişiminde olduğu gibi sabit bir alt yapı gereksinimi olmayan dinamik ve geçici Ad-Hoc ağlar bu yeni yöntemlerden bir tanesidir. Ad-Hoc ağların sabit bir altyapıya ihtiyaç duymamaları daha düşük maliyetli ve daha az konfigürasyona ihtiyaç duyan bir ağ yapısını ortaya koymuştur. Özellikle hareket halindeki düğümlerin haberleşmesinde mobil Ad-Hoc ağlar önemli rol oynamaktadır. Uçan tasarsız ağlar olarak adlandırılan FANET (Flying Ad-Hoc Networks) ağlar insansız hava araçlarının (İHA) haberleşmesini, araçsal tasarsız ağlar olarak adlandırılan VANET (Vehicular Ad-Hoc Networks) ağlar ise karayolu araçlarının haberleşmesini sağlamada kullanılan mobil Ad-Hoc ağlardır. Bu ağların gelişimi ve yaygınlaşması otonom araçların ve İHA’ ların gelişimine önemli katkı sağlamaktadır. Mobil Ad-Hoc ağların özelleşmiş alt ağları olan FANET ve VANET ağlarının kullanımının artması ve bu ağlar içerisinde yer alan düğüm sayılarındaki artış bu ağlarda güvenlik, verimlilik ve sürdürülebilirlik ile ilgili problemlerin ortaya çıkmasına neden olmuştur. Günümüzün etkin ve yaygın yaklaşımlarından biri olan makine öğrenmesi yöntemleri FANET ve VANET ağlarda belirtilen problemlerin çözümünde sıklıkla başvurulan yollardan bir tanesidir. Bu ağların en önemli özelliklerinin başında gelen hızlı topoloji değişimi trafik yönetiminin, güven yönetiminin, yönlendirmelerin ve veri iletiminin sağlanmasını zorlaştırmaktadır. Bu doğrultuda makine öğrenmesi yaklaşımları etkin rol oynamaktadır. Bu çalışmada, literatürde trafik yönetimi, güven yönetimi, yönlendirme ve veri transferi gibi önemli görevleri gerçekleştirmede hangi makine öğrenmesi tekniklerinin kullanıldığı incelenerek sunulmuştur. Böylelikle bu alanlarda çalışacakların kullanılabilecek makine öğrenimi yaklaşımları ile ilgili bilgileri edinmeleri hedeflenmiştir. FANET ağ türünün yeni bir yaklaşım olması nedeniyle makine öğrenimi yaklaşımlarının kullanıldığı az sayıda çalışma olduğu gözlemlenmiştir. VANET sistemlerde ise makine öğrenmesi yöntemlerinin kullanıldığı çalışmalar özellikle 2021 yılında yoğunluk göstermektedir. Bu çalışma, FANET ve VANET ağlarda hangi problemlerde hangi makine öğrenmesi yöntemlerinin kullanılabileceği hakkında okuyucuya fikir vermek amacıyla gerçekleştirilmiştir.

Keywords

Tasarsız Ağlar, Kablosuz Haberleşme, VANET, FANET, Makine Öğrenmesi

References

• Ayyash, M., Alsbou Y., &Anan M. (2015). Wireless Sensor and Mobile Ad-Hoc Networks. Introduction to Mobile Ad-Hoc and Vehicular Networks. Springer, New York, 33-46.
• Benek, Ö., (2019). Vanet sistemlerinde kullanilan iletişim protokollerinin analizi.Yüksek Lisans Tezi, İstanbul Üniversitesi, Cerrahpaşa Lisansüstü Eğitim Enstitüsü, İstanbul.
• Bekmezci, İ. &Ülkü, E. E., (2015) Location information sharing with multi token circulation in Flying Ad Hoc Networks. 7th International Conference on Recent Advances in Space Technologies (RAST).16-19 June, İstanbul, 669-673.
• Ulku, E. E., Dogan, B., Demir, O., & Bekmezci, I. (2019). Sharing Location Information in Multi-UAV Systems by Common Channel Multi-Token Circulation Method in FANETs. ElektronikaIrElektrotechnika, 25(1), 66-71.
• Ulku, E. E., & Bekmezci, I. (2016). Multi token based locations haring for multi UAV systems. International Journal of Computer and Electrical Engineering, 8(3), 197.
• Zhang, S., Lagutkina, M., Ovaz Akpinar, K. & Akpinar, M. (2021). Improving performance and data transmission security in VANETs. Computer Communications, 180, 126-133.
• Costa, L. A. L. d., Kunst, R., & Freitas, E. P. d. (2021). Q-FANET: Improved Q-learning based routing protocol for FANETs. Computer Networks, 198, 108379.
• Acharya, A., & Oluoch, J. (2021). A Dual Approach for Preventing Blackhole Attacks in Vehicular Ad Hoc Networks Using Statistical Techniques and Supervised Machine Learning. IEEE International Conference on Electro Information Technology (EIT). 14-15 May, USA, 230-235.
• Arafat, M. Y., & Moh, S. (2021). A Q-Learning-Based Topology-Aware Routing Protocol for Flying Ad Hoc Networks. IEEE Internet of Things Journal, 9, 1985-2000.
• Kadam, N., & Sekhar, K. R. (2021). Machine Learning Approach of Hybrid KSVN Algorithm to Detect DDoS Attack in VANET. International Journal of Advanced Computer Science and Applications, 12.
• Tong, J., Gu, X., Zhang, M., Wan, J., & Wang, J. (2021). Traffic flow prediction based on improved SVR for VANET. 4th International Conference on Advanced Electronic Materials, Computers and Software Engineering (AEMCSE). 26-28 March, China, 402-405.
• Sharma, A., & Jaekel, A. (2021). Machine Learning Approach for Detecting Location Spoofing in VANET. International Conference on Computer Communications and Networks (ICCCN).19-22 July, Greece, 1-6.
• Guerber, C., Royer, M., & Larrieu, N. (2021). Machine Learning and Software Defined Network to secure communications in a swarm of drones. Journal of Information Security and Applications, 61, 102940.
• Krishna, M. V. B. M., Ananth, C. A., & Raj, N. K. (2021). Intrusion Detection System for Energy Efficient Cluster based Vehicular Adhoc Networks. International Journal of Advanced Computer Science and Applications, 12.
• Gonçalves, F., Macedo, J., & Santos, A. (2021). An intelligent hierachical security framework for vanets. Information, 12, 455.
• Cárdenas, L. L., Mezher, A. M., Bautista, P. A. B., León, J. P. A., & Igartua, M. A. (2021). A Multimetric Predictive ANN-Based Routing Protocol for Vehicular Ad Hoc Networks. IEEE access, 9, 86037 – 86053.
• Mankodiya, H., Obaidat, M. S., Gupta, R., & Tanwar, S. (2021). XAI-AV: Explainable Artificial Intelligence for Trust Management in Autonomous Vehicles. International Conference on Communications, Computing, Cybersecurity, and Informatics (CCCI). 15-17 October, Beijing, China, 1-5,
• Nadarajan, J., & Kaliyaperumal, J. (2021). QOS aware and secured routing algorithm using machine intelligence in next generation VANET. International Journal of System Assurance Engineering and Management, 1-12.
• Gad, A. R., Nashat, A. A., & Barkat, T. M. (2021). Intrusion Detection System Using Machine Learning for Vehicular Ad Hoc Networks Based on ToN-IoT Dataset. IEEE Access, 9, 142206-142217.
• Ashtaiwi, A. (2021). ML-Based Localizing and Driving Direction Estimation System for Vehicular Networks. International Conference on Artificial Intelligence in Information and Communication (ICAIIC). 13-16 April, Jeju Island, South Korea, 465-470.
• Alsarhan, A., Alauthman, M., Alshdaifat, E., Al Ghuwairi, A., & Al Dubai, A. (2021). Machine Learning driven optimization for SVM based intrusion detection system in vehicular ad hoc networks. Journal of Ambient Intelligence and Humanized Computing, 1-10.
• Uprety, A., Rawat, D. B., & Li, J. (2021). Privacy Preserving Misbehavior Detection in IoV using Federated Machine Learning. 18th Annual Consumer Communications Networking Conference (CCNC). 9-12 January, Las Vegas, NV, USA, 1-6.
• Ercan, S., Ayaida, M., & Messai, N. (2021). New Features for Position Falsification Detection in VANETs using Machine Learning. ICC 2021 - IEEE International Conference on Communications. 14-23 June, Montreal, QC, Canada, 1-6.
• Cabelin, J. D., Alpano, P. V., & Pedrasa, J. R. (2021). SVM-based Detection of False Data Injection in Intelligent Transportation System. International Conference on Information Networking (ICOIN). 13-16 January, Jeju Island, South Korea, 279-284.
• Kumbhar, F. H., & Shin, S. Y. (2021). DT-VAR: Decision Tree Predicted Compatibility-Based Vehicular Ad-Hoc Reliable Routing. Ieee Wireless Communications Letters, 10, 87-91.
• Bolodurina, I., Parfenov, D., & Grishina, L. (2021). Investigation of Feature Engineering Methods for Identifying Attacks in the VANET. International Russian Automation Conference (RusAutoCon). 5-11 September, Sochi, Russian Federation, 1031-1035.
• Raja, G., Anbalagan, S., & Vijayaraghavan, G. (2021). SP-CIDS: Secure and Private Collaborative IDS for VANETs. IEEE Transactions On Intelligent Transportation Systems, 22, 4385-4393.
• Zang, M., & Yan, Y. (2021). Machine Learning-Based Intrusion Detection System for Big Data Analytics in VANET. 3rd Vehicular Technology Conference (VTC2021-Spring). 25-28 April, Helsinki, Finland, 1-5.
• R, D. K., Chavhan, S., Gupta, D., Khanna, A., & Rodrigues, J. J. P. C. (2021). An Intelligent Self-learning Drone Assistance Approach towards V2V Communication in Smart City. Proceedings of the 4th ACM MobiCom Workshop on Drone Assisted Wireless Communications for 5G and Beyond (DroneCom '21). 29 October, New York, NY, United States, 19-24.
• Goncçalves, F., Macedo, J., & Santos, A. (2021). Evaluation of VANET Datasets in Context of an Intrusion Detection System. 2021 International Conference on Software, Telecommunications and Computer Networks (SoftCOM). 23-25 September, Split, Hvar, Croatia, 1-6.
• Hossain, M. A., Noor, R. M., Yau, K.-L. A., Azzuhri, S. R., Z’aba, M. R., Ahmedy, I., & Jabbarpour, M. R. (2021). Machine Learning-Based Cooperative Spectrum Sensing in Dynamic Segmentation Enabled Cognitive Radio Vehicular Network. Energies, 14, 1169.
• Lee, S.-W., Ali, S., Yousefpoor, M. S., Yousefpoor, E., Lalbakhsh, P., Javaheri, D., Rahmani, A. M., & Hosseinzadeh, M. (2021). An Energy-Aware and Predictive Fuzzy Logic-Based Routing Scheme in Flying Ad Hoc Networks (FANETs). IEEE Access, 9, 129977-130005.
• Yu, J., Vandanapu, A., Qu, C., Wang, S., & Calyam, P. (2020). Energy-aware Dynamic Computation Offloading for Video Analytics in Multi-UAV Systems. 2020 International Conference on Computing, Networking and Communications (ICNC). 17-20 February, Big Island, HI, USA, 641-647.
• Quevedo, C. H. O. O., Quevedo, A. M. B. C., Campos, G. A., Gomes, R. L., Celestino, J., & Serhrouchni, A. (2020). An Intelligent Mechanism for Sybil Attacks Detection in VANETs. IEEE International Conference on Communications (ICC). 7-11 June, Dublin, Ireland, 1-6.
• Haddaji, A., Ayed, S., & Fourati, L. C. (2020). Blockchain-based Multi-Levels Trust Mechanism Against Sybil Attacks for Vehicular Networks. IEEE 14th International Conference on Big Data Science and Engineering (BigDataSE). 31 December - 1 January, Guangzhou, China, 155-163.
• Koshimizu, T., Gengtian, S., Wang, H., Pan, Z., Liu, J., & Shimamoto, S. (2020). Multi-Dimensional Affinity Propagation Clustering Applying a Machine Learning in 5G-Cellular V2X. IEEE Access, 8, 94560-94574.
• Adhikary, K., Bhushan, S., Kumar, S., & Dutta, K. (2020). Hybrid Algorithm to Detect DDoS Attacks in VANETs. Wireless Personal Communications, 114, 3613-3634.
• Liu, X. (2020). Deep Learning for Resource Allocation of a Marine Vehicular Ad-Hoc Network. 2020 IEEE Latin-American Conference on Communications (LATINCOM). 18-20 November, Santo Domingo, Dominican Republic, 1-6.
• Mamatha, G., Sharan, H. S.., Prathik, R., Priya, D. S., & Prajwal, U. (2020). Smart Vehicular communication for Road status analysis and Vehicle trajectory prediction. Third International Conference on Smart Systems and Inventive Technology (ICSSIT 2020). 20-22 August, Tirunelveli, India, 1081-1087.
• Garip, M. T., Lin, J., Reiher, P., & Gerla, M. (2019). SHIELDNET: An Adaptive Detection Mechanism against Vehicular Botnets in VANETs. 2019 IEEE Vehicular Networking Conference (VNC). 4-6 December, Los Angeles, California, 1-7.
• Pressas, A., Sheng, Z., Ali, F., & Tian, D. (2019). A Q-Learning Approach With Collective Contention Estimation for Bandwidth-Efficient and Fair Access Control in IEEE 802.11p Vehicular Networks. IEEE Transactions On Vehicular Technology, 68, 9136-9150.
• Kamble, S. J.,& Kounte, M. R. (2019). On Road Intelligent Vehicle Path Predication and Clustering using Machine Learning Approach. Third International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC 2019). 12-14 December, Palladam, India, 501-505.
• Zhao, H., Cheng, H., Mao, T., & He, C. (2019). Research on Traffic Accident Prediction Model Based on Convolutional Neural Networks in VANET. 2019 2nd International Conference on Artificial Intelligence and Big Data (ICAIBD). 25-28 May, Chengdu, China, 79-84.
• Aljeri, N., & Boukerche, A. (2019). A Novel Online Machine Learning Based RSU Prediction Scheme for Intelligent Vehicular Networks. 2019 IEEE/ACS 16th International Conference on Computer Systems and Applications (AICCSA). 3-7 November, Abu Dhabi, United Arab Emirates, 1-8.
• Li, J., Xing, Z., Wei, S., Qian, Y., & Zhang, W. (2019). Dynamic Vehicle Data Gathering via Deep Reinforcement Learning Approach. 2019 IEEE 5th International Conference on Computer and Communications (ICCC). 6-9 December, Chengdu, China, 1916-1920.
• Das, R., & Khilar, P. M. (2019). Driver Behaviour Profiling in VANETs : Comparison of Ensemble Machine Learning Techniques. 2019 IEEE 1st International Conference on Energy, Systems and Information Processing (ICESIP). 4-6 July, Chennai, India, 1-5.
• Alsuhli, G. H., Khattab, A., Fahmy, Y. A., & Massoud, Y. (2019). Enhanced urban clustering in VANETs using online machine learning. IEEE International conference on vehicular electronics and safety (ICVES). 4-6 September, Egypt, 1-6.
• Kandali, K., Bennis, L., & Bennis, H. (2021). A New Hybrid Routing Protocol Using a Modified K-Means Clustering Algorithm and Continuous Hopfield Network for VANET. IEEE Access, 9, 47169-47183.