车联网中视频内容理解任务的计算卸载决策研究

doi:10.19678/j.issn.1000-3428.0059963

摘要/Abstract

摘要： 视频数据能够为车辆的智能网联化提供丰富的信息，为了更好地提取视频内容并使卸载后的视频中包含更多的有效信息，在时延约束条件下，设计一种内容驱动的计算卸载指导方式并提出基于改进蒙特卡洛树搜索的计算卸载决策算法。在车辆端通过关键帧提取来对视频内容进行预处理，以有效分析视频内容理解任务的重要性，使得更重要的任务能够获得更多的计算资源。采用基于强化学习的启发式搜索算法完成计算卸载决策，并引入深度神经网络预训练先验转移概率，从而优化算法的收敛速度并降低计算复杂度。实验结果表明，该算法能够在时延约束下有效降低能耗并提升视频内容理解精度，相比基于Q-learning、基于模拟退火的算法，其收敛速度更快，计算复杂度更低，在700 ms时延约束下系统总效用达到37%。

关键词: 蒙特卡洛树搜索, 视频内容理解, 计算卸载决策, 边缘计算, 车联网

Abstract: Video data provides ample information for intelligent networking of vehicles.To improve the quality of video content extraction and keep more valid information in offloaded videos, this paper presents a content-driven method for instructing computation offloading, and a decision-making algorithm based on improved Monte Carlo Tree Search(MCTS) under delay constraints.The video content is pre-processed through key frame extraction at the vehicle end, which helps to analyze the importance of content analysis tasks, making important tasks obtain more computation resources.Then a heuristic search algorithm based on reinforcement learning is adopted for offloading decision making, and a DNN is adopted to pre-train the priori transition probability.So the convergence speed of the algorithm can be optimized and the computational complexity is reduced.Experimental results show that the proposed algorithm can effectively reduce energy consumption and improve the accuracy of video content understanding under the delay constraints.Compared with the algorithms based on Q-learning and simulated annealing, the proposed algorithm displays a higher convergence speed and lower computational complexity.Its overall system utility reaches 37% when constrained by a delay of 700 ms.

Key words: Monte Carlo Tree Search(MCTS), video content understanding, computing offloading decision, edge computing, Internet of vehicles

中图分类号:

TN992.52

冯浩, 郭彩丽. 车联网中视频内容理解任务的计算卸载决策研究[J]. 计算机工程, 2022, 48(1): 135-141,148.

FENG Hao, GUO Caili. Research on Computing Offloading Decision for Video Content Understanding Tasks in Internet of Vehicles[J]. Computer Engineering, 2022, 48(1): 135-141,148.

https://www.ecice06.com/CN/Y2022/V48/I1/135

图/表 8

20220108122340

20220108122343

20220108122347

20220108122350

20220108122354

20220108122357

20220108122400

20220108122406

参考文献

[1] RANFT B, STILLER C.The role of machine vision for intelligent vehicles[J].IEEE Transactions on Intelligent Vehicles, 2016, 9:8-19.
[2] 梁敏健.智能车行车环境视觉感知关键技术研究[D].西安:长安大学, 2017. LIANG M J.Research on key technologies of visual perception of intelligent vehicle driving environment[D].Xi'an:Chang'an University, 2017.(in Chinese)
[3] CAGLIERO L, CANALE L, FARINETTI L.VISA:a supervised approach to indexing video lectures with semantic annotations[C]//Proceedings of 2019 IEEE Annual Computer Software and Applications Conference.Washington D.C., USA:IEEE Press, 2019:226-235.
[4] LIU X.A geographic opportunistic forwarding strategy for vehicular named data networking[M].Berlin, Germany:Springer, 2016.
[5] SHANG L, WANG X, WANG P, et al.Computation offloading management in vehicular edge network under imperfect CSI[C]//Proceedings of 2019 IEEE International Conference on Information Communication and Signal Processing.Washington D.C., USA:IEEE Press, 2019:199-203.
[6] GU B, ZHOU Z.Task offloading in vehicular mobile edge computing:a matching-theoretic framework[J].Vehicular Technology Magazine, 2019, 14(3):100-106.
[7] ZHANG K, ZHU Y, LING S, et al.Deep learning embowered task off-roading for mobile edge computing in urban information[J].IEEE Internet of Things Journal, 2019, 6(5):7635-7647.
[8] CAO H, CAI J.Distributed multiuser computation offlooding for cludlet-based mobile computing:agame-theoretic machine leading approach[J].IEEE Transactions on Vehicular Technology, 2017, 67(1):752-764.
[9] 吕灵灵, 杨志鹏, 张磊.基于合约设计的移动边缘计算任务卸载策略研究[J].控制与决策, 2019, 34(11):97-105. LÜ L L, YANG Z P, ZHANG L.Control theory based task offlooding stratage of mobile edge computing[J].Control and Decision, 2019, 34(11):97-105.(in Chinese)
[10] HUANG X, XU K, LAI C, et al.Energy-efficient offloading decision-making for mobile edge computing in vehicular networks[J].EURASIP Journal on Wireless Communi-cations and Networking, 2020(1):35-39.
[11] 赵海涛, 朱银阳, 丁仪, 等.车联网中基于移动边缘计算的内容感知分类卸载算法研究[J].电子与信息学报, 2020, 42(1):20-27. ZHAO H T, ZHU Y Y, DING Y, et al.Research on content-aware classification offloading algorithm based on mobile edge calculation in the Internet of vehicles[J].Journal of Electronics and Information Technology, 2020, 42(1):20-27.(in Chinese)
[12] LUO G Y, YUAN Q, ZHOU H B, et al.Cooperative vehicular content distribution in edge computing assisted 5G-VANET[J].China Communications, 2018, 15(7):1-17.
[13] TAO X Y, OTA K, DONG M X, et al.Performance guaranteed computation offloading for mobile-edge cloud computing[J].IEEE Wireless Communications Letters, 2017, 6(6):774-777.
[14] MACHARDY Z, KHAN A, OBANA K, et al.V2X access technologies:regulation, research, and remaining challenges[J].IEEE Communications Surveys & Tutorials, 2018, 20(3):1858-1877.
[15] SZE V, CHEN Y H, YANG T J, et al.Efficient processing of deep neural networks:a tutorial and survey[J].Proceedings of the IEEE, 2017, 105(12):2295-2329.
[16] CHEN Y H, KRISHNA T, EMER J S, et al.Eyeriss:an energy-efficient reconfigurable accelerator for deep convolutional neural networks[EB/OL].[2020-10-05].https://www.rle.mit.edu/eems/wp-content/uploads/2016/02/eyeriss_isscc_2016.pdf.
[17] JU M, JUNG H, CHE H.A performance analysis methodology for multicore, multithreaded processors[J].IEEE Transactions on Computers, 2014, 63(2):276-289.
[18] 张海波, 栾秋季, 朱江, 等.车辆异构网中基于移动边缘计算的任务卸载与资源分配[J].物联网学报, 2018, 2(3):36-43. ZHANG H B, LUAN Q J, ZHU J, et al.Task unloading and resource allocation based on moving edge computing in heterogeneous vehicle networks[J].Journal of Internet of Things, 2018, 2(3):36-43.(in Chinese)
[19] MAO Y, ZHANG J, LETAIEF K B.Dynamic computation offloading for mobile-edge computing with energe harvesting procedures[J].IEEE Journal on Selected Areas in Communications, 2016, 34(12):3590-3605.
[20] HUANG X, XU K, LAI C, et al.Energy-efficient offloading decision-making for mobile edge computing in vehicular networks[EB/OL].[2020-10-05].https://jwcn-eurasipjournals.springeropen.com/track/pdf/10.1186/s13638-020-1652-5.pdf.
[21] HUANG W, RIBEIRO A R.Hierarchical clustering given confidence intervals of metric distances[J].IEEE Transactions on Signal Processing, 2018, 8:2600-2615.
[22] CHASLOT G M, WINANDS M H, HERIK H J.Parallel Monte-Carlo tree search[EB/OL].[2020-10-05].https://dke.maastrichtuniversity.nl/m.winands/documents/multithreadedMCTS2.pdf.
[23] LIM E J, AHN S Y, WAN C.Accelerating training of DNN in distributed machine learning system with shared memory[C]//Proceedings of 2017 International Conference on Information and Communication Technology.Washington D.C., USA:IEEE Press, 2017:1209-1212.
[24] HUANG Y, SONG R, XU K, et al.Deep learning based inverse scattering with structural similarity loss functions[J].IEEE Sensors Journal, 2021, 21(4):4900-4907.
[25] XUE X, YAN F, PAN B, et al.Performance assessment of OPSquare data center network with elastic allocation of WDM transceivers[C]//Proceedings of 2018 International Conference on Transparent Optical Networks.Washington D.C., USA:IEEE Press, 2018:1-4.
[26] GU H, DONG Y, CAO T.Data driven QoE-QoS association modeling of conversational video[C]//Proceedings of 2019 IEEE Global Conference on Signal and Information Processing.Washington D.C., USA:IEEE Press, 2019:1-4.
[27] MIETTINEN A P, NURMINEN J K.Energy efficiency of mobile clients in cloud computing[C]//Proceedings of USENIX Conference on Hot Topics in Cloud Computing.[S.l.]:USENIX Association, 2010:1-7.
[28] ZHANG S, XIE Y, WAN J, et al.WiderPerson:a diverse dataset for dense pedestrian detection in the wild[J].IEEE Transactions on Multimedia, 2019, 22(2):380-393.
[29] LIU Q, ZHOU S, HUI Y.Computation offloading scheme to improve QoE in vehicular networks with mobile edge computing[C]//Proceedings of 2018 International Conference on Wireless Communications and Signal Processing.Washington D.C., USA:IEEE Press, 2018:1-5.
[30] RAJA G, GANAPATHISUBRAMANIYAN A, ANBALAGAN S, et al.Intelligent reward-based data offloading in next-generation vehicular networks[J].IEEE Internet of Things Journal, 2020, 7(5):3747-3758.

选择文件类型/文献管理软件名称

选择包含的内容