移动边缘网络中基于QoE的网络媒体流卸载算法

doi:10.11959/j.issn.1000-436x.2024035

摘要/Abstract

摘要：

针对移动边缘计算中新兴网络媒体流业务面临的高时延、高能耗、高带宽、低用户体验质量（QoE）等问题，提出一种基于QoE反馈配置卸载（QFCO）算法。首先，联合考虑预处理和优先级划分，从而最大化网络资源利用率，并为计算任务赋予不同的权重建立资源分配关系；然后，综合考虑截止时间、计算资源、功率和带宽等约束，以任务时延、能耗和精确度加权和为优化目标建立QoE模型，利用拉格朗日乘数法求解。仿真结果表明，相比深度增强学习在线卸载（DROO）算法，所提算法可有效实现资源的整体优化配置，更好地提升用户体验质量。

关键词: 移动边缘计算, 用户体验质量, 拉格朗日乘数法, 网络媒体流, 计算卸载

Abstract:

Aiming at the problems of high-latency, high energy consumption, high bandwidth, and poor quality of experience (QoE) caused by emerging network media streaming business in mobile edge computing, a computing offloading algorithm based on QoE feedback configuration was proposed.Firstly, both preprocessing and priority were comprehensively considered to maximize network resource utilization.Meanwhile, different weights were assigned to the computation tasks for establishing a resource allocation relationship.Secondly, after comprehensively taking into account deadline, computing resource, power and bandwidth constraint, an QoE model was established where the optimization objective was the weighted sum of task delay, energy consumption and precision, and the method of Lagrange multipliers was utilized to solve the established model.Simulation results indicate that, compared with the deep reinforcement learning-based online offloading algorithm, the proposed algorithm can effectively optimize the resource allocation and better improve the QoE.

Key words: mobile edge computing, quality of experience, Lagrange multiplier method, network media streaming, com-puting offloading

中图分类号:

TN393

王再见, 程浩. 移动边缘网络中基于QoE的网络媒体流卸载算法[J]. 通信学报, 2024, 45(2): 201-212.

Zaijian WANG, Hao CHENG. Network media streaming offloading algorithm based on QoE in mobile edge network[J]. Journal on Communications, 2024, 45(2): 201-212.

图/表 11

表1

系统参数"

参数	含义
N	终端数量
M	中继边缘节点数量
D_{n ,i}	数据大小
C_{n ,i}	计算复杂度
T^max	最大容忍时延
O_ni	识别目标数目
$h_{n, i}^{j}$	终端和边缘服务器之间的信道增益
$δ^{2}$	噪声功率
$I_{n, i}^{j}$	信道上终端设备引起的信噪比
B	传输带宽
P^T	传输功率
$f_{n, i}^{j}$	分配给任务的计算资源
r_{k ,t}	分辨率对应的精确度函数
f_{k ,t}	帧率对应的精确度函数

表1

图1

图2

表2

图3

图4

图5

图6

图7

图8

图9

参考文献 29

[1]	XU W , YANG Z H , NG D W K ,et al. Edge learning for B5G networks with distributed signal processing:semantic communication,edge computing,and wireless sensing[J]. IEEE Journal of Selected Topics in Signal Processing, 2023,17(1): 9-39.
[2]	KHAN M A , BACCOUR E , CHKIRBENE Z ,et al. A survey on mobile edge computing for video streaming:opportunities and challenges[J]. IEEE Access, 2022,10: 120514-120550.
[3]	HU Y C , PATEL M , SABELLA D ,et al. Mobile edge computing—a key technology towards 5G[R]. ETSI White Paper, 2015.
[4]	DU J B , YU F R , LU G Y ,et al. MEC-assisted immersive VR video streaming over terahertz wireless networks:a deep reinforcement learning approach[J]. IEEE Internet of Things Journal, 2020,7(10): 9517-9529.
[5]	HOU Y Z , WANG C R , ZHU M ,et al. Joint allocation of wireless resource and computing capability in MEC-enabled vehicular network[J]. China Communications, 2021,18(6): 64-76.
[6]	NGUYEN T H , PARK L . A survey on deep reinforcement learning-driven task offloading in aerial access networks[C]// Proceedings of 13th International Conference on Information and Communication Technology Convergence (ICTC). Piscataway:IEEE Press, 2022: 822-827.
[7]	ABBAS N , ZHANG Y , TAHERKORDI A ,et al. Mobile edge computing:a survey[J]. IEEE Internet of Things Journal, 2018,5(1): 450-465.
[8]	HU H J , SHAN H G , WANG C K ,et al. Video surveillance on mobile edge networks—a reinforcement-learning-based approach[J]. IEEE Internet of Things Journal, 2020,7(6): 4746-4760.
[9]	JAIN S , ZHANG X , ZHOU Y H ,et al. Spatula:efficient cross-camera video analytics on large camera networks[C]// Proceedings of IEEE/ACM Symposium on Edge Computing (SEC). Piscataway:IEEE Press, 2020: 110-124.
[10]	DAI X X , YANG P , ZHANG X Y ,et al. RESPIRE:reducing spatial-temporal redundancy for efficient edge-based industrial video analytics[J]. IEEE Transactions on Industrial Informatics, 2022,18(12): 9324-9334.
[11]	DOU W C , ZHAO X , YIN X C ,et al. Edge computing-enabled deep learning for real-time video optimization in IIoT[J]. IEEE Transactions on Industrial Informatics, 2021,17(4): 2842-2851.
[12]	HUNG C C , ANANTHANARAYANAN G , BODIK P ,et al. VideoEdge:processing camera streams using hierarchical clusters[C]// Proceedings of IEEE/ACM Symposium on Edge Computing (SEC). Piscataway:IEEE Press, 2018: 115-131.
[13]	LIU Q , HAN T . DARE:dynamic adaptive mobile augmented reality with edge computing[C]// Proceedings of IEEE 26th International Conference on Network Protocols (ICNP). Piscataway:IEEE Press, 2018: 1-11.
[14]	WU K , JIN Y B , MIAO W W ,et al. Soudain:online adaptive profile configuration for real-time video analytics[C]// Proceedings of IEEE/ACM 29th International Symposium on Quality of Service (IWQOS). Piscataway:IEEE Press, 2021: 1-10.
[15]	ZHANG S , WANG C , JIN Y B ,et al. Adaptive configuration selection and bandwidth allocation for edge-based video analytics[J]. IEEE/ACM Transactions on Networking, 2022,30(2): 285-298.
[16]	YUAN X M , ZHANG Z D , FENG C J ,et al. A DQN-based frame aggregation and task offloading approach for edge-enabled IoMT[J]. IEEE Transactions on Network Science and Engineering, 2023,10(3): 1339-1351.
[17]	QIAO G H , LENG S P , MAHARJAN S ,et al. Deep reinforcement learning for cooperative content caching in vehicular edge computing and networks[J]. IEEE Internet of Things Journal, 2020,7(1): 247-257.
[18]	HUANG L , BI S Z , ZHANG Y J A . Deep reinforcement learning for online computation offloading in wireless powered mobile-edge computing networks[J]. IEEE Transactions on Mobile Computing, 2020,19(11): 2581-2593.
[19]	朱思峰, 蔡江昊, 柴争义 ,等. 车联网云边协同计算场景下的多目标优化卸载决策[J]. 通信学报, 2022,43(6): 223-234.
	ZHU S F , CAI J H , CHAI Z Y ,et al. Multi-objective optimal offloading decision for cloud-edge collaborative computing scenario in Internet of vehicles[J]. Journal on Communications, 2022,43(6): 223-234.
[20]	XU X L , WU Q , QI L Y ,et al. Trust-aware service offloading for video surveillance in edge computing enabled Internet of vehicles[J]. IEEE Transactions on Intelligent Transportation Systems, 2021,22(3): 1787-1796.
[21]	龙隆, 刘子辰, 陆在旺 ,等. 移动边缘网络下服务缓存与资源分配联合优化策略[J]. 通信学报, 2023,44(1): 64-74.
	LONG L , LIU Z C , LU Z W ,et al. Joint optimization strategy of service cache and resource allocation in mobile edge network[J]. Journal on Communications, 2023,44(1): 64-74.
[22]	MA X T , LI Q , JIANG Y ,et al. Learning-based joint QoE optimization for adaptive video streaming based on smart edge[J]. IEEE Transactions on Network and Service Management, 2022,19(2): 1789-1806.
[23]	孙国林, 欧睿杰, 刘贵松 . 基于深度强化学习的应急物联网切片资源预留算法[J]. 通信学报, 2020,41(9): 8-20.
	SUN G L , OU R J , LIU G S . Deep reinforcement learning-based resource reservation algorithm for emergency Internet-of-things slice[J]. Journal on Communications, 2020,41(9): 8-20.
[24]	WANG C M , YU F R , LIANG C C ,et al. Joint computation offloading and interference management in wireless cellular networks with mobile edge computing[J]. IEEE Transactions on Vehicular Technology, 2017,66(8): 7432-7445.
[25]	ZHANG G L , ZHANG S , ZHANG W Q ,et al. Joint service caching,computation offloading and resource allocation in mobile edge computing systems[J]. IEEE Transactions on Wireless Communications, 2021,20(8): 5288-5300.
[26]	邝祝芳, 陈清林, 李林峰 ,等. 基于深度强化学习的多用户边缘计算任务卸载调度与资源分配算法[J]. 计算机学报, 2022,45(4): 812-824.
	KUANG Z F , CHEN Q L , LI L F ,et al. Multi-user edge computing task offloading scheduling and resource allocation based on deep reinforcement learning[J]. Chinese Journal of Computers, 2022,45(4): 812-824.
[27]	YANG B , CAO X L , BASSEY J ,et al. Computation offloading in multi-access edge computing:a multi-task learning approach[J]. IEEE Transactions on Mobile Computing, 2021,20(9): 2745-2762.
[28]	GOODFELLOW I , BENGIO Y , COURVILLE A ,et al. Deep learning[M]. Cambridge: MIT Press, 2016.
[29]	KANG Z Y , YOU C S , ZHANG R . 3D placement for multi-UAV relaying:an iterative Gibbs-sampling and block coordinate descent optimization approach[J]. IEEE Transactions on Communications, 2021,69(3): 2047-2062.

参数	数值
视频帧帧率/FPS	30
本地终端计算能力/GHz	[0.5,1.0]
服务器计算能力/GHz	[2,14]
通信带宽/MHz	5
任务数据大小/KB	[100,400]
传输功率/mW	100
信道增益	10^-6