Araç kenar bilişim için 5G milimetre dalga tabanlı görev boşaltma yaklaşımı

Öz

Araç Kenar Bilişim (VEC), düşük gecikme süresi, verimli bant genişliği kullanımı ve azaltılmış enerji tüketimi sağlarken, hesaplama açısından yoğun araç uygulamalarının yürütülmesini desteklemek için özel olarak tasarlanmış bir bilişim paradigmasıdır. Modern araç ortamlarında, araçların çeşitli uygulamalar tarafından üretilen büyük miktarda veriyi işlemesi gerekir ve yerel araç içi kaynaklar genellikle bu talepleri karşılamak için yetersiz kalır. Bu nedenle, araçlar, özellikle dinamik ve değişken ağ koşullarında optimum hesaplama performansını korumak için, hesaplama görevlerini daha yüksek işlem kapasitesi sunan harici hesaplama sistemlerine verimli bir şekilde aktarmalıdır. Bu makale, araçların genel hesaplama süresini optimize etmek ve başarılı görev aktarım oranını artırmak amacıyla hesaplama görevlerini dış kaynaklara aktardığı bir VEC senaryosunu incelemektedir. Bu tür senaryolarda, heterojen görev gereksinimleri ve araçların doğasında bulunan hareketlilik gibi çeşitli faktörler hesaplama verimliliğini etkiler. Görev boyutundaki, gecikme duyarlılığındaki ve işleme taleplerindeki değişiklikler, araç konumundaki sık değişikliklerle birleştiğinde, görev aktarım mekanizmalarının performansını ve kaynak kullanımını önemli ölçüde etkileyebilir. Bu zorlukları ele almak için, çalışma, görev aktarım kararlarını ve hesaplama kaynaklarını etkili bir şekilde yönetmek için beşinci nesil (5G) radyo ağını dahil eder ve kullanır. Hareketliliği dikkate alan bir şekilde hesaplama kaynaklarını yönetmeyi amaçlayan 5G tabanlı bir görev aktarma şeması önerilmektedir. Önerilen şema, araç hareketliliğini dikkate alarak görev aktarma kararlarını değişen ağ koşullarına uyarlar ve böylece sistemin sağlamlığını ve verimliliğini artırır. Şema, ağ genelinde görev aktarma ve kaynak tahsisini koordine ederek neredeyse optimal çözümler sağlayan dağıtık bir iletişim modeli ile daha da desteklenmektedir. Ayrıca, önerilen yaklaşım, sistem performansını artırmak için beşinci nesil yeni radyo (NR) iletişim modelini entegre eder. Bu model, hem hücresel bağlantıyı hem de milimetre dalga (mmWave) iletişimini içerir ve sistemin her bir iletişim modunun güçlü yönlerinden yararlanmasını sağlar. Simülasyon sonuçları, önerilen modelin, özellikle başarılı görev devri ve Deneyim Kalitesi (QoE) açısından hesaplama verimliliğini önemli ölçüde artırdığını göstermektedir. QoE, kullanıcılar tarafından algılanan genel hizmet performansını temsil eder ve gecikme, verim ve hata oranları gibi temel faktörlerden etkilenir. Genel olarak, önerilen yaklaşım, mmWave ve 5G NR iletişim modellerinin etkili entegrasyonu yoluyla görev aktarım verimliliğini artırır, görev başarısızlık oranlarını azaltır ve QoE'yi geliştirir.

Anahtar Kelimeler

• Araç kenarı bilgi işlem
• 5G iletişim
• mmWave
• Görev aktarımı.

A 5G mmWave-based task offloading approach for vehicular edge computing

Öz

Context—Vehicular Edge Computing (VEC) has evolved into a critical for supporting computationally intensive vehicular applications by enabling low-latency processing, efficient bandwidth utilization, and reduced energy consumption. In contemporary vehicular environments, vehicles continuously generate substantial data volumes originating from heterogeneous sources such as sensors, cameras, and connected vehicles. However, the limited onboard computational capacity of vehicles often makes it impractical to process these data-intensive tasks locally. Consequently, task offloading to external edge computing infrastructures becomes an essential mechanism for maintaining system performance. This challenge is further complicated by highly dynamic network conditions caused by vehicle mobility, frequent topology changes, and heterogeneous task characteristics, all of which significantly affect task execution and transmission reliability.

Objective—The primary objective of this research is to propose a task offloading technique that dynamically determines whether a task should be processed locally or offloaded to an edge server, while adaptively selecting the most suitable edge server with the aim of minimizing the energy consumption of mobile devices. The study particularly emphasizes mobility-aware decision-making and the handling of heterogeneous vehicular tasks under dynamic network conditions. By addressing these aspects, the proposed framework aims to improve the efficiency and enhance the reliability of 5G-enabled road safety systems.

Method—To tackle these challenges, a 5G-based task offloading scheme is proposed to manage computational and communication resources in a mobility-aware approach. The proposed approach dynamically adapts task offloading decisions based on changing network conditions by taking vehicle mobility patterns into account. Furthermore, a distributed communication model is utilized to coordinate task offloading processes and resource allocation across the network, enabling near-optimal decision-making without relying on centralized control. The system also incorporates a fifth generation (5G) New Radio (NR) communication model that integrates conventional cellular connectivity with millimeter-wave (mmWave) communication. This hybrid communication structure is designed to exploit the complementary advantages of both transmission modes, such as high data rates and improved coverage.

Results—Simulationresults indicate that the proposed model substantially improves computational efficiency, particularly in terms of successful task handover and overall task offloading performance. The combined use of mmWave and 5G NR communication effectively reduces task failure rates and improves Quality of Experience (QoE). These improvements are reflected in key performance metrics, including reduced latency, increased throughput, and lower error rates under varying mobility conditions.

Conclusion—The results indicate that mobility-aware task offloading supported by integrated 5G NR and mmWave communication substantially improves VEC system performance. With a failure rate of merely 0.0042% compared to 21.90% for MAB, 0.351% for ML-BASED, and 0.0151% for DT-ECS, the proposed method achieves 93.53% QoE and zero network-related failures while maintaining competitive service time. These findings validate that the proposed approach offers a robust and efficient solution for vehicular task offloading and provides a solid foundation for future research on adaptive and large-scale vehicular edge computing environments.

Anahtar Kelimeler

• Vehicular edge computing
• 5g communication
• mmWave
• Task offloading.

Kaynakça

1. [1] A. Gupta, R. K. Jha, “A Survey of 5G Network: Architecture and Emerging Technologies”, IEEE Access, 3, 1206–1232, 2015. https://doi.org/10.1109/ACCESS.2015.2461602.
2. [2] W. Shi, J. Cao, Q. Zhang, Y. H. Z. Li, L. Y. Xu, “Edge Computing: Vision and Challenges”, IEEE Internet Things Journal, 3(5), 637–646, 2016. https://doi.org/10.1109/JIOT.2016.2579198.
3. [3] A. Botta, W. de Donato, V. Persico, A. Pescapé, “Integration of Cloud computing and Internet of Things: A survey”, Future Generation Computer Systems-The International Journal of Escience, 56, 684–700, 2016. https://doi.org/10.1016/j.future.2015.09.021.
4. [4] K. Georgiou, S. Xavier-De-Souza, K. Eder, “The IoT Energy Challenge: A Software Perspective”, IEEE Embedded Systems Letters, 10(3), 53–56, 2018. https://doi.org/10.1109/LES.2017.2741419.
5. [5] F. Jalali, O. J. Smith, T. Lynar, F. Suits, “Cognitive IoT gateways: Automatic task sharing and switching between cloud and Edge/Fog computing”, Proceedings of the 2017 SIGCOMM Posters and Demos, Los Angeles, CA, USA, 22–24 August 2017, 121–123. https://doi.org/10.1145/3123878.3132008.
6. [6] L. Tong, Y. Li, W. Gao, “A hierarchical edge cloud architecture for mobile computing”, 35th IEEE Annual International Conference on Computer Communications (IEEE INFOCOM), San Francisco, CA, USA, 10-14 April 2016. https://doi.org/10.1109/INFOCOM.2016.7524340.
7. [7] S. N. M. Savani and A. Buchade, "Priority Based Resource Allocation in Cloud Computing," International Journal of Engineering Research & Technology (IJERT), vol. 3, no. 5, pp. 855–857, May 2014.
8. [8] S. Raza, M. Ahmed, H. Ahmad, M. A. Mirza, M. A. Habib, S. Wang, “Task offloading in mmWave based 5G vehicular cloud computing”, Journal of Ambient Intelligence Humanized Computing., 14, 12595–12607, 2023. https://doi.org/10.1007/s12652-022-04320-y.

9. [9] A. B. De Souza, P. A. L. Rego, P. H. G. Rocha, T. Carneiro, J. N. De Souza, “A Task Offloading Scheme for WAVE Vehicular Clouds and 5G Mobile Edge Computing”, IEEE Global Communications Conference (GLOBECOM) on Advanced Technology for 5G Plus, Taipei, Taiwan, 07-11 December 2020. https://doi.org/10.1109/GLOBECOM42002.2020.9348130.
10. [10] S. Raza, S. G. Wang, M. Ahmed, M. R. Anwar, M. A. Mirza, W. U. Khan, “Task Offloading and Resource Allocation for IoV Using 5G NR-V2X Communication”, IEEE Internet of Things Journal, 9(13), 10397–10410, 2022. https://doi.org/10.1109/JIOT.2021.3121796.
11. [11] M. S. Bute, P. Z. Fan, G. Liu, F. Abbas, Z. G. Ding, “A Collaborative Task Offloading Scheme in Vehicular Edge Computing”, IEEE 93rd Vehicular Technology Conference (VTC-Spring), Helsinki, Finland, 25-28 April 2021. https://doi.org/10.1109/VTC2021-Spring51267.2021.9448975.
12. [12] J. Zhang, H. Z. Guo, J. J. Liu, Y. N. Zhang, “Task Offloading in Vehicular Edge Computing Networks: A Load-Balancing Solution”, IEEE Transactions on Vehicular Technology, 69(2), 2092–2104, 2020. https://doi.org/10.1109/TVT.2019.2959410.
13. [13] M. A. Mirza, J. S. Yu, S. Raza, M. Ahmed, M. Asif, A. Irshad, N. Kumar, “MCLA Task Offloading Framework for 5G-NR-V2X-Based Heterogeneous VECNs”, IEEE Transactions on Intelligent Transportation Systems, 24(12), 14329–14346, 2023. https://doi.org/10.1109/TITS.2023.3292140.
14. [14] S. Yang, “A joint optimization scheme for task offloading and resource allocation based on edge computing in 5G communication networks”, Computer Communications, 160, 759–768, 2020. https://doi.org/10.1016/j.comcom.2020.07.008.
15. [15] X. L. Xu, X. Zhang, X. H. Liu, J. L. Jiang, L. Y. Qi, M. Z. A. Bhuiyan, “Adaptive Computation Offloading with Edge for 5G-Envisioned Internet of Connected Vehicles”, IEEE Transactions on Intelligent Transportation Systems, 22(8), 5213–5222, 2021. https://doi.org/10.1109/TITS.2020.2982186.
16. [16] Z. Y. Wu, D. F. Yan, “Deep reinforcement learning-based computation offloading for 5G vehicle-aware multi-access edge computing network”, China Communications, 18(11), 26–41, 2021. https://doi.org/10.23919/JCC.2021.11.003.
17. [17] A. B. De Souza, P. A. L. Rego, T. Carneiro, P. H. G. Rocha, J. N. De Souza, “A context-oriented framework for computation offloading in vehicular edge computing using WAVE and 5G networks”, Vehicular Communications, 32, 100389, 2021. https://doi.org/10.1016/j.vehcom.2021.100389.
18. [18] A. B. De Souza, P. A. L. Rego, V. Chamola, T. Carneiro, P. H. G. Rocha, J. N. De Souza, “A Bee Colony-Based Algorithm for Task Offloading in Vehicular Edge Computing”, IEEE Systems Journal, 17(3), 4165–4176, 2023. https://doi.org/10.1109/JSYST.2023.3237363.
19. [19] N. Hassan, K. L. A. Yau, C. Wu, “Edge computing in 5G: A review”, IEEE Access, 7, 127276-127289, 2019. https://doi.org/10.1109/ACCESS.2019.2938534.
20. [20] H. Z. Xiao, Q. Q. Pei, X. F. Song, W. S. Shi, “Authentication Security Level and Resource Optimization of Computation Offloading in Edge Computing Systems”, IEEE Internet of Things Journal, 9(15), 13010–13023, 2022. https://doi.org/10.1109/JIOT.2021.3139222.
21. [21] R. Zhang, L. B. Wu, S. Q. Cao, D. Wu, J. X. Li, “A Vehicular Task Offloading Method With Eliminating Redundant Tasks in 5G HetNets”, IEEE Transactions on Network and Service Management, 20(1), 456–470, 2023. https://doi.org/10.1109/TNSM.2022.3201953.
22. [22] A. Goldsmith, Wireless Communications, Cambridge University Press, 2005. https://doi.org/10.1017/CBO9780511841224.
23. [23] X. W. Hou, Z. Y. Ren, J. J. Wang, W. C. Cheng, Y. Ren, W. C. Chen, H. L. Zhang, “Reliable Computation Offloading for Edge-Computing-Enabled Software-Defined IoV”, IEEE Internet of Things Journal, 7(8), 7097–7111, 2020. https://doi.org/10.1109/JIOT.2020.2982292.
24. [24] R. Shahzadi, A. Niaz, M. Ali, M. Naeem, J. J. P. C. Rodrigues, F. Qamar, S. M. Anwar, “Three tier fog networks: Enabling IoT/5G for latency sensitive applications”, China Communications, 16(3), 1–11, 2019.
25. [25] H. Santos, D. Alencar, R. Meneguette, D. Rosário, J. Nobre, C. Both, E. Cerqueira, T. Braun, “A multi-tier fog content orchestrator mechanism with quality of experience support”, Computer Networks, 177, 107288, 2020. https://doi.org/10.1016/j.comnet.2020.107288.
26. [26] S. C. Chen, Q. J. Li, M. C. Zhou, A. Abusorrah, “Recent Advances in Collaborative Scheduling of Computing Tasks in an Edge Computing Paradigm”, Sensors, 21(3), 779, 2021. https://doi.org/10.3390/s21030779.
27. [27] C. Sonmez, A. Ozgovde, C. Ersoy, “EdgeCloudSim: An environment for performance evaluation of edge computing systems”, Transactions on Emerging Telecommunications Technologies, 29(11), e3493, 2018. https://doi.org/10.1002/ett.3493.
28. [28] C. Sonmez, C. Tunca, A. Ozgovde, C. Ersoy, “Machine Learning-Based Workload Orchestrator for Vehicular Edge Computing”, IEEE Transactions on Intelligent Transportation Systems, 22(4), 2239–2251, 2021. https://doi.org/10.1109/TITS.2020.3024233.
29. [29] F. Zeng, C. Liu, J. Tangjiang, W. Li, “Deep Learning-Based Task Offloading for Vehicular Edge Computing”, 16th International Conference on Wireless Algorithms, Systems, and Applications (WASA), Nanjing Univ Aeronaut & Astronaut, Nanjing, PRC, 25-27 June 2021, 291–298. https://doi.org/10.1007/978-3-030-86137-7_32.
30. [30] Y. X. Sun, X. Y. Guo, J. H. Song, S. Zhou, Z. Y. Jiang, X. Liu, Z. S. Niu, “Adaptive Learning-Based Task Offloading for Vehicular Edge Computing Systems”, IEEE Transactions on Vehicular Technology, 68(4), 3061–3074, 2019. https://doi.org/10.1109/TVT.2019.2895593.
31. [31] M. Tay, A. Şentürk, “Decision tree‐based task offloading in vehicle edge computing”, Concurrency and Computation-Practice & Experience, 36(12), 2024. https://doi.org/10.1002/cpe.8026.