BIPHASIC EFFICIENCY MODELING FOR STABLE
OFFLOADING IN RESOURCE CONSTRAINED
EDGE NETWORKS USING PUREEDGESIM
Amit Malik1, Amita Rani2
1Department of Computer Science and Engineering,
SRM University, Delhi-NCR, Sonepat, Haryana, India.
Email: amit.m@srmuniversity.ac.in,
ORCID: 0009-0008-0407-7183
2Department of Computer Science and Engineering,
DCRUST, Murthal, Sonepat, Haryana, India.
Email: amitamalik.cse@dcrustm.org,
ORCID: 0000-0002-7385-4045
Abstract. Current edge computing research strongly favors complex deep learning for managing resources. However, these data-heavy models often clash with the physical needs of edge devices, such as low latency, low energy, and total predictability. This study examines the trade-offs between unpredictable learning methods and the proposed deterministic approach, Biphasic Efficiency Model (BEM). Performance evaluation in PureEdgeSim shows that BEM maintains a stable completion rate between 38% and 44%, while traditional methods collapse to nearly 7% under high workload.
How
to cite this paper?
Source: International Journal of Applied Mathematics
ISSN printed version: 1311-1728
ISSN on-line version: 1314-8060
Year: 2025
Volume: 38
Issue: 3
References
[1] S. R. Das, K. Sinha, N. Mukherjee, and B. P. Sinha, “Delay and Disruption Tolerant Networks: A Brief Survey,” 2021. doi: 10.1007/978-981-15-5971-6_32.
[2] E. P. van Horssen, J. A. A. van Hooijdonk, D. Antunes, and W. M. Heemels, “Event- and Deadline-Driven Control of a Self-Localizing Robot With Vision-Induced Delays,” IEEE Transactions on Industrial Electronics, Feb. 2020, doi: 10.1109/TIE.2019.2899553.
[3] R. Yu and G. Xue, “Principles and Practices for Application-Network Co-Design in Edge Computing,” IEEE Network, Jan. 2022, doi: 10.1109/mnet.128.2200430.
[4] M. B. F. Sanjetha, Y. Kanagaraj, V. Herath, and S. Lokuliyana, “Deep Learning for Edge Computing Applications: A Comprehensive Survey,” Asian journal of computer science and technology, Dec. 2022, doi: 10.51983/ajcst-2022.11.2.3456.
[5] “Challenges and opportunities in edge computing architecture using machine learning approaches,” 2022. doi: 10.1016/b978-0-12-824054-0.00002-2.
[6] C. Comte and C. Comte, “Dynamic Load Balancing with Tokens,” May 2018. doi: 10.23919/IFIPNETWORKING.2018.8697018.
[7] D. Dice and A. Kogan, “Avoiding Scalability Collapse by Restricting Concurrency,” 2019.
[8] T. Kontogiannis and S. Malakis, “A system dynamics approach to the efficiency thoroughness tradeoff,” Safety Science, Oct. 2019, doi: 10.1016/J.SSCI.2019.06.011.
[9] C.-H. Hong and B. Varghese, “Resource Management in Fog/Edge Computing: A Survey on Architectures, Infrastructure, and Algorithms,” ACM Computing Surveys, Sep. 2019, doi: 10.1145/3326066.
[10] X. Liu, S. Jiang, and Y. Wu, “A Novel Deep Reinforcement Learning Approach for Task Offloading in MEC Systems,” Applied Sciences, Nov. 2022.
[11] I. Akturk and U. R. Karpuzcu, “Trading Computation for Communication: A Taxonomy of Data Recomputation Techniques,” IEEE Transactions on Emerging Topics in Computing, Jan. 2021, doi: 10.1109/TETC.2018.2883286.
[12] M. H. Najafi and D. J. Lilja, “High Quality Down-Sampling for Deterministic Approaches to Stochastic Computing,” IEEE Transactions on Emerging Topics in Computing, vol. 9, no. 1, pp. 7–14, Jan. 2021, doi: 10.1109/TETC.2017.2789243.
[13] R. Shi, Y. Gan, and Y. Wang, “Evaluating Scalability Bottlenecks by Workload Extrapolation,” Modeling, Analysis, and Simulation On Computer and Telecommunication Systems, pp. 333–347, Sep. 2018, doi: 10.1109/MASCOTS.2018.00039.
[14] M. Jin and J. Lavaei, “Stability-Certified Reinforcement Learning: A Control-Theoretic Perspective,” IEEE Access, vol. 8, pp. 229086–229100, Dec. 2020.
[15] C. Mechalikh, H. Taktak, and F. Moussa, “PureEdgeSim: A simulation framework for performance evaluation of cloud, edge and mist computing environments,” Computer Science and Information Systems, vol. 18, no. 1, pp. 43–66, Jan. 2021, doi: 10.2298/CSIS200301042M.
IJAM
o Home
o Contents