Abstract
Recently, Docker Container as a Service (CaaS) has been provided for multi-user services in the 5G Multi-Access Edge Computing (MEC) environment, and servers that support accelerators such as GPUs, not conventional CPU servers, are being considered. In addition, as the number of AI services is increasing and the computation power required by deep neural network model increases, offloading to edge servers is required due to insufficient computational capacity and heat problem of user devices (UE). However, there is a resource scheduling problem because all users’ packets cannot be offloaded to the edge server due to resource limitations. To address this problem, we suggest deep reinforcement learning-based GPU CaaS Packet scheduling named as Delcas for stabilizing quality of AI experience. First, we design the architecture using containerized target AI application on MEC GPUs and multiple users send video stream to MEC server. We evaluate video stream to identify the dynamic amount of resource requirement among each users using optical flow and adjust user task queue. To satisfy equal latency quality of experience, we apply lower quality first serve approach and respond hand pose estimation results to each user. Finally, we evaluate our approach and compare to conventional scheduling method in the aspect of both accuracy and latency quality.
Supported by Samsung Network (SNIC) and BK21.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Cheng, R., Wu, N., Chen, S., Han, B.: Will metaverse be NextG internet? Vision, hype, and reality. IEEE Netw. 36(5), 197–204 (2022)
Huang, Z., Xiong, C., Ni, H., Wang, D., Tao, Y., Sun, T.: Standard evolution of 5G-advanced and future mobile network for extended reality and metaverse. IEEE Internet Things Mag. 6(1), 20–25 (2023)
Kozinets, R.V.: Immersive netnography: a novel method for service experience research in virtual reality, augmented reality and metaverse contexts. J. Serv. Manag. 34(1), 100–125 (2023)
Park, S.M., Kim, Y.G.: A metaverse: taxonomy, components, applications, and open challenges. IEEE Access 10, 4209–4251 (2022)
Chakraborty, B.K., Sarma, D., Bhuyan, M.K., MacDorman, K.F.: Review of constraints on vision-based gesture recognition for human-computer interaction. IET Comput. Vis. 12(1), 3–15 (2018)
O’Hagan, R., Zelinsky, A., Rougeaux, S.: Visual gesture interfaces for virtual environments. Interact. Comput. 14(3), 231–250 (2002)
Oprea, S., Martinez-Gonzalez, P., Garcia-Garcia, A., Castro-Vargas, J.A., Orts-Escolano, S., Garcia-Rodriguez, J.: A visually realistic grasping system for object manipulation and interaction in virtual reality environments. Comput. Graph. 83, 77–86 (2019)
Yin, R., Wang, D., Zhao, S., Lou, Z., Shen, G.: Wearable sensors-enabled human-machine interaction systems: from design to application. Adv. Funct. Mater. 31(11), 2008936 (2021)
Raj, P., Saini, K., Surianarayanan, C.: Edge/Fog Computing Paradigm: The Concept, Platforms and Applications. Academic Press, Cambridge (2022)
Attaran, M.: The impact of 5G on the evolution of intelligent automation and industry digitization. J. Ambient Intell. Humaniz. Comput. 1–17 (2021)
Sukhmani, S., Sadeghi, M., Erol-Kantarci, M., El Saddik, A.: Edge caching and computing in 5G for mobile AR/VR and tactile internet. IEEE Multimed. 26(1), 21–30 (2018)
Premsankar, G., Di Francesco, M., Taleb, T.: Edge computing for the internet of things: a case study. IEEE Internet Things J. 5(2), 1275–1284 (2018)
Marjanović, M., Antonić, A., Žarko, I.P.: Edge computing architecture for mobile crowdsensing. IEEE Access 6, 10662–10674 (2018)
Gavrilovska, L., Rakovic, V., Denkovski, D.: From cloud ran to open ran. Wirel. Pers. Commun. 113, 1523–1539 (2020)
Bonati, L., Polese, M., DOro, S., Basagni, S., Melodia, T.: Open, programmable, and virtualized 5G networks: state-of-the-art and the road ahead. Comput. Netw. 182, 107516 (2020)
Iqbal, S., Hamamreh, J.M.: A comprehensive tutorial on how to practically build and deploy 5G networks using open-source software and general-purpose, off-the-shelf hardware. RS Open J. Innov. Commun. Tech 2(6), 1–28 (2021)
Gallipeau, D., Kudrle, S.: Microservices: building blocks to new workflows and virtualization. SMPTE Motion Imaging J. 127(4), 21–31 (2018)
Goniwada, S.R., Goniwada, S.R.: Containerization and virtualization. Cloud Native Architecture and Design: A Handbook for Modern Day Architecture and Design with Enterprise-Grade Examples, pp. 573–617 (2022)
Horn, B.K., Schunck, B.G.: Determining optical flow. Artif. Intell. 17(1–3), 185–203 (1981)
Lucas, B.D., Kanade, T.: An iterative image registration technique with an application to stereo vision. In: IJCAI’81: 7th International Joint Conference on Artificial Intelligence, vol. 2, pp. 674–679 (1981)
Xue, F., Hai, Q., Dong, T., Cui, Z., Gong, Y.: A deep reinforcement learning based hybrid algorithm for efficient resource scheduling in edge computing environment. Inf. Sci. 608, 362–374 (2022)
Yang, T., Hu, Y., Gursoy, M.C., Schmeink, A., Mathar, R.: Deep reinforcement learning based resource allocation in low latency edge computing networks. In: 2018 15th International Symposium on Wireless Communication Systems (ISWCS), pp. 1–5. IEEE (2018)
Zhou, Y., Habermann, M., Xu, W., Habibie, I., Theobalt, C., Xu, F.: Monocular real-time hand shape and motion capture using multi-modal data. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5346–5355 (2020)
Farnebäck, G.: Two-frame motion estimation based on polynomial expansion. In: Bigun, J., Gustavsson, T. (eds.) Image Analysis. SCIA 2003. LNCS, vol. 2749, pp. 363–370. Springer, Berlin, Heidelberg (2003). https://doi.org/10.1007/3-540-45103-X_50
Lee, K., Youn, C.H.: Reinforcement learning based adaptive resource allocation scheme for multi-user augmented reality service. In: 2022 13th International Conference on Information and Communication Technology Convergence (ICTC), pp. 1989–1994 (2022). https://doi.org/10.1109/ICTC55196.2022.9952934
Lee, K., Youn, C.H.: Reindear: reinforcement learning agent for dynamic system control in edge-assisted augmented reality service. In: 2020 International Conference on Information and Communication Technology Convergence (ICTC), pp. 949–954. IEEE (2020)
Merkel, D., et al.: Docker: lightweight Linux containers for consistent development and deployment. Linux j 239(2), 2 (2014)
Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. Adv. Neural Inf. Process. Syst. 32 (2019)
Zhang, C., Zhou, G., Li, J., Chang, F., Ding, K., Ma, D.: A multi-access edge computing enabled framework for the construction of a knowledge-sharing intelligent machine tool swarm in industry 4.0. J. Manuf. Syst. 66, 56–70 (2023)
Acknowledgements
This work is supported in part by Samsung Electronics Co., Ltd and in part by BK21.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Lee, C., Lee, K., Cho, G., Youn, CH. (2024). DELCAS: Deep Reinforcement Learning Based GPU CaaS Packet Scheduling for Stabilizing QoE in 5G Multi-Access Edge Computing. In: Casteleyn, S., Mikkonen, T., García Simón, A., Ko, IY., Loseto, G. (eds) Current Trends in Web Engineering. ICWE 2023. Communications in Computer and Information Science, vol 1898. Springer, Cham. https://doi.org/10.1007/978-3-031-50385-6_5
Download citation
DOI: https://doi.org/10.1007/978-3-031-50385-6_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-50384-9
Online ISBN: 978-3-031-50385-6
eBook Packages: Computer ScienceComputer Science (R0)