Abstract
Omnidirectional virtual reality video streaming requires high data rate and low latency to provide immersive experiences. Caching video contents at collaborative wireless edge servers is a promising approach to enable omnidirectional video streaming. Given limited storage at edges and ultra-high rate of omnidirectional video streaming, collaborative caching is challenging. Although restricting caching to parts of field of views (FoVs) of omnidirectional videos can alleviate the problem, the FoV based collaborative caching is still difficult considering multiple video encoding versions, long-term benefits for multiple end users and possible FoV prediction error. In this paper, we propose a deep reinforcement learning (DRL) based scheme to learn a collaborative caching policy adaptively for tile-based omnidirectional video streaming, where watched tiles are cached with abundant storage space, and either discarded or replacing existing content when edge storages are full. The collaborative cache replacement is modeled as a Markov decision process (MDP). To address the problem of searching a large-scale action space in DRL, we designed an adaptive action-selection scheme utilizing FoV prediction results. Simulation results demonstrate the effectiveness of the proposed scheme.
This work is supported by National Natural Science Foundation of China under Grant No. 61801167, and the Fundamental Research Funds for the Central Universities under Grant No. B200202189.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Khurana, T.: Retail and AR and VR: 5G brings it home! (2019). https://blogs.cisco.com/sp/retail-and-ar-and-vr-5g-brings-it-home?dtid=osscdc000283
Dai, J., Zhang, Z., Mao, S., Liu, D.: A view synthesis-based 360\(^{\circ }\) VR caching system over MEC-enabled C-RAN. IEEE Trans. Circuits Syst. Video Technol. 30, 3843–3855 (2019)
Sukhmani, S., Sadeghi, M., Erol-Kantarci, M., El Saddik, A.: Edge caching and computing in 5G for mobile AR/VR and tactile internet. IEEE Multimedia 26(1), 21–30 (2019)
Han, S., Su, H., Yang, C., Molisch, A.F.: Proactive edge caching for video on demand with quality adaptation. IEEE Trans. Wireless Commun. 19(1), 218–234 (2020)
Wang, D., et al.: Adaptive wireless video streaming based on edge computing: opportunities and approaches. IEEE Trans. Serv. Comput. 12(5), 685–697 (2019). https://doi.org/10.1109/TSC.2018.2828426
Tran, T.X., Hajisami, A., Pandey, P., Pompili, D.: Collaborative mobile edge computing in 5G networks: new paradigms, scenarios, and challenges. IEEE Commun. Mag. 55(4), 54–61 (2017). https://doi.org/10.1109/MCOM.2017.1600863
Chakareski, J.: VR/AR immersive communication: caching, edge computing, and transmission trade-offs. In: Proceedings of the Workshop on Virtual Reality and Augmented Reality Network. VR/AR Network 2017, pp. 36–41 (2017). https://doi.org/10.1145/3097895.3097902
Song, Y., Zhao, Y., Li, C.: A user behavior aware immersive video caching algorithm. In: Proceedings of the 11th International Conference on Wireless Communications and Signal Processing. WCSP 2019, pp. 1–6 (2019). https://doi.org/10.1109/WCSP.2019.8927955
Sullivan, G.J., Ohm, J., Han, W., Wiegand, T.: Overview of the high efficiency video coding (HEVC) standard. IEEE Trans. Circuits Syst. Video Technol. 22(12), 1649–1668 (2012)
Chakareski, J.: Viewport-adaptive scalable multi-user virtual reality mobile-edge streaming. IEEE Trans. Image Process. 29, 6330–6342 (2020). https://doi.org/10.1109/TIP.2020.2986547
Maniotis, P., Bourtsoulatze, E., Thomos, N.: Tile-based joint caching and delivery of 360\(^{\circ }\) videos in heterogeneous networks. In: Proceedings of the 21st International Workshop on Multimedia Signal Processing. MMSP 2019, pp. 1–6 (2019)
He, D., Jiang, J., Westphal, C., Yang, G.: Efficient edge caching for high-quality 360-degree video delivery. In: Ro, Y.M., et al. (eds.) MMM 2020. LNCS, vol. 11962, pp. 39–51. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-37734-2_4
Yang, Y., Lee, J., Kim, N., Kim, K.: Social-viewport adaptive caching scheme with clustering for virtual reality streaming in an edge computing platform. Future Gener. Comput. Syst. 108, 424–431 (2020). https://doi.org/10.1016/j.future.2020.02.078
Sun, L., Mao, Y., Zong, T., Liu, Y., Wang, Y.: Flocking-based live streaming of 360-degree video. In: Proceedings of the 11th ACM Multimedia Systems Conference. MMSys 2020, pp. 26–37 (2020). https://doi.org/10.1145/3339825.3391856
Mahzari, A., Taghavi Nasrabadi, A., Samiei, A., Prakash, R.: FoV-aware edge caching for adaptive 360\(^{\circ }\) video streaming. In: Proceedings of the 26th ACM International Conference on Multimedia. MM 2018, pp. 173–181 (2018). https://doi.org/10.1145/3240508.3240680
Li, D., et al.: Deep reinforcement learning for cooperative edge caching in future mobile networks. In: Proceedings of the 2019 IEEE Wireless Communications and Networking Conference, pp. 1–6 (2019). https://doi.org/10.1109/WCNC.2019.8885516
Yang, Z., Liu, Y., Chen, Y., Tyson, G.: Deep reinforcement learning in cache-aided MEC networks. In: Proceedings of the 2019 IEEE International Conference on Communications. ICC 2019, pp. 1–6 (2019). https://doi.org/10.1109/ICC.2019.8761349
Wang, F., Wang, F., Liu, J., Shea, R., Sun, L.: Intelligent video caching at network edge: a multi-agent deep reinforcement learning approach. In: Proceedings of the IEEE Conference on Computer Communications. INFOCOM 2020, pp. 2499–2508 (2020). https://doi.org/10.1109/INFOCOM41043.2020.9155373
Qu, Z., Ye, B., Tang, B., Guo, S., Lu, S., Zhuang, W.: Cooperative caching for multiple bitrate videos in small cell edges. IEEE Trans. Mob. Comput. 19(2), 288–299 (2020). https://doi.org/10.1109/TMC.2019.2893917
Amazon Web Services, Inc.: Amazon EC2 pricing (2021). https://aws.amazon.com/cn/ec2/pricing/on-demand/
Tran, T.X., Pandey, P., Hajisami, A., Pompili, D.: Collaborative multi-bitrate video caching and processing in Mobile-Edge Computing networks. In: Proceedings of the 13th Annual Conference on Wireless On-demand Network Systems and Services. WONS 2017, pp. 165–172 (2017). https://doi.org/10.1109/WONS.2017.7888772
Lo, W.C., Fan, C.L., Lee, J., Huang, C.Y., Chen, K.T., Hsu, C.H.: 360\(^{\circ }\) video viewing dataset in head-mounted virtual reality. In: Proceedings of the 8th ACM on Multimedia Systems Conference. MMSys 2017, pp. 211–216 (2017). https://doi.org/10.1145/3083187.3083219
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Tan, Z., Xu, Y. (2021). Deep Reinforcement Learning Based Collaborative Mobile Edge Caching for Omnidirectional Video Streaming. In: Liu, Z., Wu, F., Das, S.K. (eds) Wireless Algorithms, Systems, and Applications. WASA 2021. Lecture Notes in Computer Science(), vol 12937. Springer, Cham. https://doi.org/10.1007/978-3-030-85928-2_36
Download citation
DOI: https://doi.org/10.1007/978-3-030-85928-2_36
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-85927-5
Online ISBN: 978-3-030-85928-2
eBook Packages: Computer ScienceComputer Science (R0)