Adaptive Deep Learning Architectures for Real-Time Data Streams in Edge Computing Environments
Article Sidebar
Main Article Content
Abstract
The increasing reliance on real-time analytics within edge computing environments has underscored the need for adaptive deep learning architectures capable of handling continuous data streams under limited computational and energy resources. Unlike traditional cloud-based frameworks, edge computing shifts computation closer to the data source, minimizing latency, preserving data privacy, and supporting responsive decision-making in dynamic contexts. This paper comprehensively examines adaptive deep learning models that autonomously adjust their structure and parameters in response to evolving data distributions and resource constraints. The study explores several key methodologies—such as master–surrogate deep neural networks, context–adaptive DNN atom partitioning, distributed inference with fused layer partitioning, and reinforcement learning–driven resource scheduling. Comparative analyses demonstrate that these adaptive frameworks achieve substantial performance gains, including up to 23.31% accuracy improvement, 62.14% latency reduction, and over 50% energy savings across diverse edge devices. Furthermore, the paper evaluates real-world deployments in smart cities, healthcare monitoring, Industry 4.0 automation, autonomous vehicles, and environmental sensing, illustrating the scalability and robustness of adaptive architectures in heterogeneous edge ecosystems. The discussion concludes by outlining current challenges—such as hardware diversity, continual learning, and energy constraints—and highlights future research directions including federated adaptation, neuromorphic hardware integration, and standardized benchmarking for edge AI.
Article Details
Issue
Section
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
How to Cite
References
H. Gao et al., “CuFSDAF: An Enhanced Flexible Spatiotemporal Data Fusion Algorithm Parallelized Using Graphics Processing Units,” IEEE Transactions on Geoscience and Remote Sensing, vol. 60, 2022, doi: 10.1109/TGRS.2021.3080384.
W. Jiang, D. Feng, Y. Sun, G. Feng, Z. Wang, and X. G. Xia, “Joint Computation Offloading and Resource Allocation for D2D-Assisted Mobile Edge Computing,” IEEE Trans Serv Comput, vol. 16, no. 3, 2023, doi: 10.1109/TSC.2022.3190276.
B. Guo, S. C. Liu, Y. Liu, Z. G. Li, Z. W. Yu, and X. S. Zhou, “AIoT: The Conceрt, Architecture and Key Techniques,” Jisuanji Xuebao/Chinese Journal of Computers, vol. 46, no. 11, 2023, doi: 10.11897/SP.J.1016.2023.02259.
B. Pang, E. Nijkamp, and Y. N. Wu, “Deep Learning With TensorFlow: A Review,” 2020. doi: 10.3102/1076998619872761.
K. Filus and J. Domańska, “Software vulnerabilities in TensorFlow-based deep learning applications,” Comput Secur, vol. 124, 2023, doi: 10.1016/j.cose.2022.102948.
P. Tam, S. Math, C. Nam, and S. Kim, “Adaptive Resource Optimized Edge Federated Learning in Real-Time Image Sensing Classifications,” IEEE J Sel Top Appl Earth Obs Remote Sens, vol. 14, 2021, doi: 10.1109/JSTARS.2021.3120724.
P. Dai, F. Song, K. Liu, Y. Dai, P. Zhou, and S. Guo, “Edge Intelligence for Adaptive Multimedia Streaming in Heterogeneous Internet of Vehicles,” IEEE Trans Mob Comput, vol. 22, no. 3, 2023, doi: 10.1109/TMC.2021.3106147.
N. Kumar and A. Ahmad, “Quality of service-aware adaptive radio resource management based on deep federated Q-learning for multi-access edge computing in beyond 5G cloud-radio access network,” Transactions on Emerging Telecommunications Technologies, vol. 34, no. 6, 2023, doi: 10.1002/ett.4762.
A. Sacco, M. Flocco, F. Esposito, and G. Marchetto, “An architecture for adaptive task planning in support of IoT-based machine learning applications for disaster scenarios,” Comput Commun, vol. 160, 2020, doi: 10.1016/j.comcom.2020.07.011.
L. Zang, X. Zhang, and B. Guo, “Federated Deep Reinforcement Learning for Online Task Offloading and Resource Allocation in WPC-MEC Networks,” IEEE Access, vol. 10, 2022, doi: 10.1109/ACCESS.2022.3144415.
R. Adamec, “Does long term potentiation in periacqueductal gray (PAG) mediate lasting changes in rodent anxiety-like behavior (ALB) produced by predator stress? - Effects of low frequency stimulation (LFS) of PAG on place preference and changes in ALB produced by predator stress,” Behavioural Brain Research, vol. 120, no. 2, 2001, doi: 10.1016/S0166-4328(00)00366-1.
X. Chen, D. Z. Chen, Y. Han, and X. S. Hu, “MoDNN: Memory Optimal Deep Neural Network Training on Graphics Processing Units,” IEEE Transactions on Parallel and Distributed Systems, vol. 30, no. 3, 2019, doi: 10.1109/TPDS.2018.2866582.
Z. Zhao, K. M. Barijough, and A. Gerstlauer, “DeepThings: Distributed adaptive deep learning inference on resource-constrained IoT edge clusters,” in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2018. doi: 10.1109/TCAD.2018.2858384.
L. Zhang, J. Wang, W. Wang, Z. Jin, Y. Su, and H. Chen, “Smart contract vulnerability detection combined with multi-objective detection,” Computer Networks, vol. 217, 2022, doi: 10.1016/j.comnet.2022.109289.
B. Pang et al., “AdaMEC: Towards a Context-adaptive and Dynamically Combinable DNN Deployment Framework for Mobile Edge Computing,” ACM Trans Sens Netw, vol. 20, no. 1, 2023, doi: 10.1145/3630098.
X. Zhu, T. Zhang, J. Zhang, B. Zhao, S. Zhang, and C. Wu, “Deep reinforcement learning-based edge computing offloading algorithm for software-defined IoT,” Computer Networks, vol. 235, 2023, doi: 10.1016/j.comnet.2023.110006.
D. Liu, H. Kong, X. Luo, W. Liu, and R. Subramaniam, “Bringing AI to edge: From deep learning’s perspective,” Neurocomputing, vol. 485, 2022, doi: 10.1016/j.neucom.2021.04.141.
S. Petrocchi, G. Giorgi, and M. G. C. A. Cimino, “A Real-Time Deep Learning Approach for Real-World Video Anomaly Detection,” in ACM International Conference Proceeding Series, 2021. doi: 10.1145/3465481.3470099.
Z. He and H. Sayadi, “Image-Based Zero-Day Malware Detection in IoMT Devices: A Hybrid AI-Enabled Method,” in Proceedings - International Symposium on Quality Electronic Design, ISQED, 2023. doi: 10.1109/ISQED57927.2023.10129348.
R. Vengaloor and R. Muralidhar, “Deep Learning Based Feature Discriminability Boosted Concurrent Metal Surface Defect Detection System Using YOLOv-5s-FRN,” International Arab Journal of Information Technology, vol. 21, no. 1, 2024, doi: 10.34028//iajit/21/1/9.
J. J. Chen et al., “How to do Deep Learning on Graphs with Graph Convolutional Networks,” IEEE Access, vol. 8, no. 1, 2019.
M. Peng, W. Zhang, F. Li, Q. Xue, J. Yuan, and P. An, “Weed detection with Improved Yolov 7,” EAI Endorsed Transactions on Internet of Things, vol. 9, no. 3, 2023, doi: 10.4108/eetiot.v9i3.3468.
S. Yin, Y. Jiao, C. You, M. Cai, T. Jin, and S. Huang, “Reliable adaptive edge-cloud collaborative DNN inference acceleration scheme combining computing and communication resources in optical networks,” Journal of Optical Communications and Networking, vol. 15, no. 10, 2023, doi: 10.1364/JOCN.495765.
M. Goudarzi, M. Palaniswami, and R. Buyya, “A Distributed Deep Reinforcement Learning Technique for Application Placement in Edge and Fog Computing Environments,” IEEE Trans Mob Comput, vol. 22, no. 5, 2023, doi: 10.1109/TMC.2021.3123165.
A. M. Alabdali, “A Novel Framework of an IOT-Blockchain-Based Intelligent System,” Wirel Commun Mob Comput, vol. 2022, 2022, doi: 10.1155/2022/4741923.
S. Garg, K. Kaur, G. Kaddoum, P. Garigipati, and G. S. Aujla, “Security in IoT-Driven Mobile Edge Computing: New Paradigms, Challenges, and Opportunities,” IEEE Netw, vol. 35, no. 5, 2021, doi: 10.1109/MNET.211.2000526.
P. Salva-Garcia, J. M. Alcaraz-Calero, Q. Wang, J. B. Bernabe, and A. Skarmeta, “5G NB-IoT: Efficient Network Traffic Filtering for Multitenant IoT Cellular Networks,” Security and Communication Networks, vol. 2018, 2018, doi: 10.1155/2018/9291506.
Muneera Altayeb and Amani Al-Ghraibah, “Arduino Based Real-Time Face Recognition And Tracking System,” International Journal of Advanced Trends in Computer Science and Engineering, vol. 12, no. 4, pp. 144–150, Aug. 2023, doi: 10.30534/ijatcse/2023/011242023.
H. B. Ahmad, R. R. Asaad, S. M. Almufti, A. A. Hani, A. B. Sallow, and S. R. M. Zeebaree, “SMART HOME ENERGY SAVING WITH BIG DATA AND MACHINE LEARNING,” Jurnal Ilmiah Ilmu Terapan Universitas Jambi, vol. 8, no. 1, pp. 11–20, May 2024, doi: 10.22437/jiituj.v8i1.32598.
S. M. Almufti, R. B. Marqas, Z. A. Nayef, and T. S. Mohamed, “Real Time Face-mask Detection with Arduino to Prevent COVID-19 Spreading,” Qubahan Academic Journal, vol. 1, no. 2, pp. 39–46, Apr. 2021, doi: 10.48161/qaj.v1n2a47.
R. Asaad, R. Ismail Ali, and S. Almufti, “Hybrid Big Data Analytics: Integrating Structured and Unstructured Data for Predictive Intelligence,” Qubahan Techno Journal, vol. 1, no. 2, Apr. 2022, doi: 10.48161/qtj.v1n2a14.
R. Rajab Asaad, R. Ismael Ali, A. Ahmad Shaban, and M. Shamal Salih, “Object Detection using the ImageAI Library in Python,” Polaris Global Journal of Scholarly Research and Trends, vol. 2, no. 2, pp. 1–9, Apr. 2023, doi: 10.58429/pgjsrt.v2n2a143.
R. Kumar, P. Kumar, R. Tripathi, G. P. Gupta, S. Garg, and M. M. Hassan, “BDTwin: An Integrated Framework for Enhancing Security and Privacy in Cybertwin-Driven Automotive Industrial Internet of Things,” IEEE Internet Things J, vol. 9, no. 18, 2022, doi: 10.1109/JIOT.2021.3122021.
S. Mukherjee, S. Gupta, O. Rawlley, and S. Jain, “Leveraging big data analytics in 5G-enabled IoT and industrial IoT for the development of sustainable smart cities,” Transactions on Emerging Telecommunications Technologies, vol. 33, no. 12, 2022, doi: 10.1002/ett.4618.
S. Agrawal, B. K. Patle, and S. Sanap, “A systematic review on metaheuristic approaches for autonomous path planning of unmanned aerial vehicles,” Jan. 01, 2024, Canadian Science Publishing. doi: 10.1139/dsa-2023-0093.
A. Ghasemi and M. Mirzavand, “Robot path planning using Big Bang–Big Crunch algorithm,” Rob Auton Syst, vol. 62, no. 3, pp. 390–399, 2014.
D. A. Majeed et al., “DATA ANALYSIS AND MACHINE LEARNING APPLICATIONS IN ENVIRONMENTAL MANAGEMENT,” Jurnal Ilmiah Ilmu Terapan Universitas Jambi, vol. 8, no. 2, pp. 398–408, Sep. 2024, doi: 10.22437/jiituj.v8i2.32769.
X. Wang, Y. Han, V. C. M. Leung, D. Niyato, X. Yan, and X. Chen, “Convergence of Edge Computing and Deep Learning: A Comprehensive Survey,” 2020. doi: 10.1109/COMST.2020.2970550.
D. A. Hasan, S. R. M. Zeebaree, M. A. M. Sadeeq, H. M. Shukur, R. R. Zebari, and A. H. Alkhayyat, “Machine Learning-based Diabetic Retinopathy Early Detection and Classification Systems - A Survey,” in 1st Babylon International Conference on Information Technology and Science 2021, BICITS 2021, Institute of Electrical and Electronics Engineers Inc., 2021, pp. 16–21. doi: 10.1109/BICITS51482.2021.9509920.
S. M. Almufti and A. M. Abdulazeez, “An Integrated Gesture Framework of Smart Entry Based on Arduino and Random Forest Classifier,” Indonesian Journal of Computer Science, vol. 13, no. 1, Feb. 2024, doi: 10.33022/ijcs.v13i1.3735.
M. Cao, Y. Li, X. Wen, Y. Zhao, and J. Zhu, “Energy-aware intelligent scheduling for deadline-constrained workflows in sustainable cloud computing,” Egyptian Informatics Journal, vol. 24, no. 2, 2023, doi: 10.1016/j.eij.2023.04.002.