Resource-efficient Continuous Learning Framework for Edge Real-time Video Analytics

Authors

Shuxia Wu, College of Computer and Data Science, Fuzhou University, Fuzhou 350116, China; Engineering Research Center of Big Data Intelligence, Ministry of Education, Fuzhou 350002, China; Fujian Key Laboratory of Network Computing and Intelligent Information Processing (Fuzhou University), Fuzhou 350116, China
Junjie Zhang, College of Computer and Data Science, Fuzhou University, Fuzhou 350116, China; Engineering Research Center of Big Data Intelligence, Ministry of Education, Fuzhou 350002, China; Fujian Key Laboratory of Network Computing and Intelligent Information Processing (Fuzhou University), Fuzhou 350116, China
Delong Chen, College of Computer and Data Science, Fuzhou University, Fuzhou 350116, China; Engineering Research Center of Big Data Intelligence, Ministry of Education, Fuzhou 350002, China; Fujian Key Laboratory of Network Computing and Intelligent Information Processing (Fuzhou University), Fuzhou 350116, China
Zheyi Chen, College of Computer and Data Science, Fuzhou University, Fuzhou 350116, China; Engineering Research Center of Big Data Intelligence, Ministry of Education, Fuzhou 350002, China; Fujian Key Laboratory of Network Computing and Intelligent Information Processing (Fuzhou University), Fuzhou 350116, China

Abstract

Abstract: By deploying lightweight models at the network edge, edge systems can provide services of real-time video analytics. However, due to the data drift caused by the discrepancy between model training and actual deployment, it is challenging to construct lightweight models that match real-world environments. To address this challenge, a resource-efficient continuous learning framework for edge real-time video analytics (CL4VA) was proposed. A region of interest-granularity predictor for accuracy degradation was introduced to efficiently select key samples from real-time video streams. A two-layer mixed sample pool was constructed to adaptively trigger the model's continuous learning and avoid the issue of catastrophic forgetting. A DRL-based controller was designed to determine the appropriate time to complete model re-training. The simulation results show that compared to the baseline method, CL4VA can reduce the average latency by 8.65% and increase the accuracy by up to 5.57%. Moreover, the core components of CL4VA require extremely low online overhead.

Recommended Citation

Wu, Shuxia; Zhang, Junjie; Chen, Delong; and Chen, Zheyi (2026) "Resource-efficient Continuous Learning Framework for Edge Real-time Video Analytics," Journal of System Simulation: Vol. 38: Iss. 2, Article 4.
DOI: 10.16182/j.issn1004731x.joss.25-0590
Available at: https://dc-china-simulation.researchcommons.org/journal/vol38/iss2/4

First Page

294

Last Page

306

CLC

TP393

Recommended Citation

Wu Shuxia, Zhang Junjie, Chen Delong, et al. Resource-efficient Continuous Learning Framework for Edge Real-time Video Analytics[J]. Journal of System Simulation, 2026, 38(2): 294-306.

Corresponding Author

Chen Zheyi

DOI

10.16182/j.issn1004731x.joss.25-0590