Heuristic Adaptive Weighted Decision untuk Task Offloading pada Edge–Fog IoT

Ata Amrullah; Toga Aldila Cinderatama; Mohammad Rifqi Dwi Ardiansyah

doi:10.31004/riggs.v5i1.6460

Authors

Ata Amrullah Universitas Islam Darul Ulum Lamongan
Toga Aldila Cinderatama PSDKU Politeknik Negeri Malang
Mohammad Rifqi Dwi Ardiansyah Universitas Islam Darul Ulum

DOI:

https://doi.org/10.31004/riggs.v5i1.6460

Keywords:

Internet of Things, Edge Computing, Fog Computing, Task Offloading, Heuristic Decision

Abstract

Pertumbuhan pesat Internet of Things (IoT) mendorong peningkatan jumlah perangkat dan volume data yang harus diproses secara real-time dengan batasan latensi yang ketat. Ketergantungan penuh pada cloud computing sering kali kurang efisien akibat keterbatasan bandwidth, jarak geografis, dan fluktuasi kondisi jaringan. Untuk mengatasi permasalahan tersebut, paradigma edge–fog computing diperkenalkan dengan mendekatkan sumber daya komputasi ke pengguna akhir. Namun, keterbatasan kapasitas komputasi dan panjang antrean pada node edge dan fog menjadikan penentuan strategi task offloading sebagai isu krusial dalam menjaga kualitas layanan IoT, khususnya pada aplikasi yang sensitif terhadap keterlambatan respons. Penelitian ini mengusulkan metode Heuristic Adaptive Weighted Decision (HAWD) untuk task offloading pada arsitektur edge–fog IoT. Metode yang diusulkan menentukan node tujuan eksekusi task berdasarkan kombinasi beberapa parameter sistem, yaitu latensi end-to-end, utilisasi CPU, dan panjang antrean, dengan bobot keputusan yang disesuaikan secara adaptif mengikuti kondisi beban sistem. Pendekatan ini dirancang bersifat ringan dan tidak memerlukan proses pelatihan model, sehingga sesuai untuk lingkungan edge–fog dengan sumber daya terbatas. Evaluasi kinerja metode HAWD dilakukan melalui simulasi pada skenario smart healthcare dan dibandingkan dengan pendekatan baseline static latency-only. Hasil simulasi menunjukkan bahwa metode HAWD mampu menurunkan latensi end-to-end rata-rata sebesar 18–25% serta menghasilkan distribusi beban yang lebih stabil pada node edge–fog, terutama pada kondisi beban sistem tinggi. Temuan ini menunjukkan bahwa pendekatan offloading berbasis multi-kriteria adaptif lebih efektif dalam mendukung layanan IoT real-time dibandingkan strategi statis konvensional.

Downloads

Download data is not yet available.

References

S. Yang, G. Lee, and L. Huang, “Deep Learning-Based Dynamic Computation Task Offloading for Mobile Edge Computing Networks,” Sensors, vol. 22, no. 11, 2022, doi: 10.3390/s22114088.

X. Shen, Z. Chang, and S. Niu, “Mobile Edge Computing Task Offloading Strategy Based on Parking Cooperation in the Internet of Vehicles,” Sensors, vol. 22, no. 13, 2022, doi: 10.3390/s22134959.

Md. D. Hossain et al., “Dynamic Task Offloading for Cloud-Assisted Vehicular Edge Computing Networks: A Non-Cooperative Game Theoretic Approach,” Sensors, vol. 22, no. 10, 2022, doi: 10.3390/s22103678.

X. Liu, X. Zhao, G. Liu, F. Huang, T. Huang, and Y. Wu, “Collaborative Task Offloading and Service Caching Strategy for Mobile Edge Computing,” Sensors, vol. 22, no. 18, 2022, doi: 10.3390/s22186760.

B. Kopras, F. Idzikowski, B. Bossy, P. Kryszkiewicz, and H. Bogucka, “Communication and Computing Task Allocation for Energy-Efficient Fog Networks,” Sensors, vol. 23, no. 2, 2023, doi: 10.3390/s23020997.

A. Markus, A. Al-Haboobi, G. Kecskemeti, and A. Kertesz, “Simulating IoT Workflows in DISSECT-CF-Fog,” Sensors, vol. 23, no. 3, 2023, doi: 10.3390/s23031294.

A. Amrullah, “Optimization of AI-Powered Edge-IoT Architecture for Real-Time Response in Distributed Smart City Systems,” Intellithings Journal, vol. 1, no. 1, Feb. 2024, [Online]. Available: https://e-jurnal.unisda.ac.id/index.php/intellithings/article/view/10651

A. Acheampong, Y. Zhang, X. Xu, and D. A. Kumah, “A Review of the Current Task Offloading Algorithms, Strategies and Approach in Edge Computing Systems,” CMES - Computer Modeling in Engineering and Sciences, vol. 134, no. 1, pp. 35–88, 2022, doi: https://doi.org/10.32604/cmes.2022.021394.

S. Tong, Y. Liu, X. Chang, J. Mišić, and Z. Zhang, “Joint Task Offloading and Resource Allocation: A Historical Cumulative Contribution Based Collaborative Fog Computing Model,” IEEE Trans. Veh. Technol., vol. 72, no. 2, pp. 2202–2215, 2023, doi: 10.1109/TVT.2022.3213084.

T. Du, C. Li, and Y. Luo, “Latency-aware Computation Offloading and DQN-based Resource Allocation Approaches in SDN-enabled MEC,” 2022. [Online]. Available: https://www.elsevier.com/open-access/userlicense/1.0/

M. K. Alasmari, S. S. Alwakeel, and Y. A. Alohali, “A Multi-Classifiers Based Algorithm for Energy Efficient Tasks Offloading in Fog Computing,” Sensors, vol. 23, no. 16, 2023, doi: 10.3390/s23167209.

W. Shi, L. Chen, and X. Zhu, “Task Offloading Decision-Making Algorithm for Vehicular Edge Computing: A Deep-Reinforcement-Learning-Based Approach,” Sensors, vol. 23, no. 17, 2023, doi: 10.3390/s23177595.

X. Bi and L. Zhao, “Two-Layer Edge Intelligence for Task Offloading and Computing Capacity Allocation with UAV Assistance in Vehicular Networks,” Sensors, vol. 24, no. 6, 2024, doi: 10.3390/s24061863.

X. Dang, L. Su, Z. Hao, and X. Shang, “Dynamic Offloading Method for Mobile Edge Computing of Internet of Vehicles Based on Multi-Vehicle Users and Multi-MEC Servers,” Electronics (Basel)., vol. 11, no. 15, 2022, doi: 10.3390/electronics11152326.

C. Duo, P. Dong, Q. Gao, B. Li, and Y. Li, “MEC Computation Offloading-Based Learning Strategy in Ultra-Dense Networks,” Information, vol. 13, no. 6, 2022, doi: 10.3390/info13060271.

L. C. Keat, A. T. Fong, C. Y. Chong, and T. Yiqi, “(Offloading) QoE-Aware Application Mapping and Energy-Aware Module Placement in Fog Computing + Offloading,” International Journal of Web Services Research, vol. 19, no. 1, 2022, doi: https://doi.org/10.4018/IJWSR.299017.