Abstract
The burgeoning field of Artificial Intelligence for the Internet of Things (AIoT) is rapidly transforming smart transportation, posing the formidable challenge of efficiently processing voluminous traffic data. Addressing this, our study presents a novel three-tiered device-edge-cloud video stream scheduling framework, DECS-DRL, underpinned by deep reinforcement learning. The DECS-DRL framework enables efficient video stream processing through multi-layer collaboration: key frame extraction, using lightweight models for fast task processing, and using more complex models for high-precision task processing. Central to navigating the intricate balance between detection accuracy and latency minimization in task scheduling, we introduce an innovative deep reinforcement learning algorithm enhanced by a hybrid state encoder. Our empirical evaluations underscore the DECS-DRL framework’s efficacy, showcasing significant advancements in video streaming task scheduling and optimizing deep reinforcement learning model training within intelligent transportation systems.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Chen, H.T., Jiang, B., Ding, S.X., Huang, B.A.: Data-driven fault diagnosis for traction systems in high-speed trains: a survey, challenges, and perspectives. IEEE Trans. Intell. Transp. Syst. 23(3), 1700–1716 (2022)
Huang, Q.Y., Jia, H.F., Xu, Y.B., Yang, Y.J., Xiao, G.X.: Limi-TFP: citywide traffic flow prediction with limited road status information. IEEE Trans. Veh. Technol. 72(3), 2947–2959 (2023)
Karagiannis, G., et al.: Vehicular networking: a survey and tutorial on requirements, architectures, challenges, standards and solutions. IEEE Commun. Surv. Tutorials 13(4), 584–616 (2011)
Lee, D., Lee, C., Jang, G., Na, W., Cho, S.: Energy-efficient directional charging strategy for wireless rechargeable sensor networks. IEEE Internet Things J. 9(19), 19034–19048 (2022)
Liang, W., Xie, W.Q., Zhou, X.K., Wang, K.I.K., Ma, J.H., Jin, Q.: Bi-dueling DQN enhanced two-stage scheduling for augmented surveillance in smart ems. IEEE Trans. Industr. Inf. 19(7), 8218–8228 (2023)
Long, S.Q., Zhang, Y., Deng, Q.Y., Pei, T.R., Ouyang, J.Z., Xia, Z.H.: An efficient task offloading approach based on multi-objective evolutionary algorithm in cloud-edge collaborative environment. IEEE Trans. Netw. Sci. Eng. 10(2), 645–657 (2023)
Malekloo, M.H., Kara, N., Barachi, M.: An energy efficient and SLA compliant approach for resource allocation and consolidation in cloud computing environments. Sustainable Comput. Infor. Syst. 17, 9–24 (2018)
Mu, J.S., Jin, J., Jing, X.J., Zhang, R.H., Zhang, P.Y., Zhu, H.L.: Machine learning assisted video stream offloading for 5G MBMS mobile edge computing. IEEE Trans. Broadcast. (2023)
Qiu, J., Wang, R., Chakrabarti, A., Guerin, R., Lu, C.: Adaptive edge offloading for image classification under rate limit. IEEE Trans. Comput. Aided Des. Integr. Circuits Syst. 41(11), 3886–3897 (2022)
Sarkar, A., Murray, J., Dasari, M., Zink, M., Nahrstedt, K., Soc, I.C.: L3bou: low latency, low bandwidth, optimized super-resolution backhaul for 360-degree video streaming. In: 23rd IEEE International Symposium on Multimedia (ISM), pp. 138–147. IEEE International Symposium on Multimedia-ISM (2021)
Song, M.C., et al.: In-situ AI: towards autonomous and incremental deep learning for IoT systems. In: 24th IEEE International Symposium on High Performance Computer Architecture (HPCA), pp. 92–103. International Symposium on High-Performance Computer Architecture-Proceedings (2018)
Wang, L.F., Zhang, Z.Y., Di, X., Tian, J.: IEEE: a roadside camera-radar sensing fusion system for intelligent transportation. In: 17th European Radar Conference (EuRAD), pp. 282–285. European Radar Conference EuRAD (2021)
Wen, L.Y., et al.: Ua-detrac: a new benchmark and protocol for multi-object detection and tracking. Comput. Vision Image Underst. 193 (2020)
Xiao, K.L., Gao, Z.P., Wang, Q., Yang, Y.: IEEE: a heuristic algorithm based on resource requirements forecasting for server placement in edge computing. In: 3rd IEEE/ACM Symposium on Edge Computing (SEC), pp. 354–355 (2018)
Xing, P.Y., Wang, Y.W., Peng, P.X., Tian, Y.H., Huang, T.J.: IEEE: end-edge-cloud collaborative system: a video big data processing and analysis architecture. In: IEEE 3rd International Conference on Multimedia Information Processing and Retrieval (IEEE MIPR), pp. 233–236 (2020)
Acknowledgment
This work was supported in part by Formal analysis and optimization research on production capacity of large-scale personalized customization system, National Key Laboratory of Large-Scale Personalized Customization Systems and Technology, H&C-MPC-2023–02-03.Innovation Fund Project for Graduate Student of China University of Petroleum (East China) and the Fundamental Research Funds for the Central Universities (No.24CX04030A)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2025 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Wang, N., Pang, S., Ji, X., Gui, H., He, X. (2025). Device-Edge-Cloud Collaborative Video Stream Processing and Scheduling Strategy Based on Deep Reinforcement Learning. In: Cai, Z., Takabi, D., Guo, S., Zou, Y. (eds) Wireless Artificial Intelligent Computing Systems and Applications. WASA 2024. Lecture Notes in Computer Science, vol 14999. Springer, Cham. https://doi.org/10.1007/978-3-031-71470-2_8
Download citation
DOI: https://doi.org/10.1007/978-3-031-71470-2_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-71469-6
Online ISBN: 978-3-031-71470-2
eBook Packages: Computer ScienceComputer Science (R0)