智能网联环境下面向语义通信的资源分配

doi:10.11959/j.issn.2096-3750.2022.00279

物联网学报 ›› 2022, Vol. 6 ›› Issue (3): 47-57.doi: 10.11959/j.issn.2096-3750.2022.00279

智能网联环境下面向语义通信的资源分配

陈九九¹, 郭彩丽¹^,², 冯春燕¹, 刘传宏¹

¹ 北京邮电大学先进信息网络北京实验室，北京 100876
² 北京邮电大学网络体系构建与融合北京市重点实验室，北京 100876

修回日期:2022-06-15 出版日期:2022-08-05 发布日期:2022-08-08
作者简介:陈九九（1994- ），男，北京邮电大学博士生，主要研究方向为车联网资源分配、语义通信、强化学习算法等
郭彩丽（1977- ），女，博士，北京邮电大学教授、博士生导师，主要研究方向为语义通信、无线移动通信技术、认知无线电、信号检测与估值、车联网、可见光通信、视觉智能计算、社交跨媒体数据挖掘与分析等
冯春燕（1963- ），女，博士，北京邮电大学教授、博士生导师，主要研究方向为无线通信信息传输与处理、宽带通信网络理论与技术、社交网络分析和信息检索、电信大数据分析与挖掘等
刘传宏（1998- ），男，北京邮电大学博士生，主要研究方向为深度学习、语义通信、资源分配等
基金资助:
北京市自然科学基金资助项目(4202049);中央高校基本科研业务费专项资金资助项目(2021XD-A01-1)

Resource allocation for the semantic communication in the intelligent networked environment

Jiujiu CHEN¹, Caili GUO¹^,², Chunyan FENG¹, Chuanhong LIU¹

¹ Beijing Laboratory of Advanced Information Networks, Beijing University of Posts and Telecommunications, Beijing 100876, China
² Beijing Key Laboratory of Network System Construction and Integration, Beijing University of Posts and Telecommunications, Beijing 100876, China

Revised:2022-06-15 Online:2022-08-05 Published:2022-08-08
Supported by:
The Natural Science Foundation of Beijing(4202049);The Fundamental Research Funds for the Central Universities(2021XD-A01-1)

摘要/Abstract

摘要：

传统的资源分配方法难以满足智能网联环境下各种业务准确理解大量多媒体数据语义的需求。针对该挑战，以智能任务导向的车联网场景为例，首先，提出了两种面向语义通信的资源分配优化准则；然后，针对不同维度的资源，综述了面向语义通信的资源分配模型与算法；构建了面向语义通信的图像数据集，在车联网仿真场景下分析了所研究资源分配方法的性能优势；最后，给出了语义通信资源分配的未来挑战。

关键词: 语义通信, 资源分配, 智能网联, 优化准则, 强化学习

Abstract:

Traditional resource allocation methods are difficult to meet the needs of various services to accurately understand the semantics of a large amount of multimedia data in the intelligent networked environment.Facing with this challenge, taking intelligent task-oriented internet of vehicles scenarios as an example, two resource allocation optimization criteria for the semantic communication were firstly proposed.Then, according to different dimensions of resources, the models and algorithms of the resource allocation for the semantic communication were described.Then, a semantic communication-oriented image dataset was constructed, and the performance advantages of the proposed resource allocation methods in the simulation scenario of the internet of vehicles were analyzed.Finally, the future challenges of the resource allocation for the semantic communication were presented.

Key words: semantic communication, resources allocation, intelligent networked connection, optimization criteria, reinforcement learning

中图分类号:

TN929.5

陈九九, 郭彩丽, 冯春燕, 刘传宏. 智能网联环境下面向语义通信的资源分配[J]. 物联网学报, 2022, 6(3): 47-57.

Jiujiu CHEN, Caili GUO, Chunyan FENG, Chuanhong LIU. Resource allocation for the semantic communication in the intelligent networked environment[J]. Chinese Journal on Internet of Things, 2022, 6(3): 47-57.

图/表 9

图1

表1

表2

表3

表4

表5

图2

图3

图4

参考文献 47

[1]	GYAWALI S , XU S J , QIAN Y ,et al. Challenges and solutions for cellular based V2X communications[J]. IEEE Communications Surveys ＆ Tutorials, 2021,23(1): 222-255.
[2]	李克强 . 中国智能网联汽车产业化过程中的挑战及发展对策[J]. 机器人产业, 2019(6): 54-57.
	LI K Q . Challenges and development countermeasures in the industrialization of China's intelligent connected vehicles[J]. Robot Industry, 2019(6): 54-57.
[3]	DENG S G , ZHAO H L , FANG W J ,et al. Edge intelligence,the confluence of edge computing and artificial intelligence[J]. IEEE Internet of Things Journal, 2020,7(8): 7457-7469.
[4]	CALVANESE STRINATI E , BARBAROSSA S . 6G networks,beyond Shannon towards semantic and goal-oriented communications[J]. Computer Networks,(190), 2021(90): 107930.
[5]	SHANNON C E , WEAVER W , WIENER N . The mathematical theory of communication[J]. Physics Today, 1950,3(9): 31-32.
[6]	SHI G M , XIAO Y , LI Y Y ,et al. From semantic communication to semantic-aware networking,model,architecture,and open problems[J]. IEEE Communications Magazine, 2021,59(8): 44-50.
[7]	LI G Y , BOUKHATEM L , WU J S . Adaptive quality-of-service-based routing for vehicular ad hoc networks with ant colony optimization[J]. IEEE Transactions on Vehicular Technology, 2017,66(4): 3249-3264.
[8]	KIM J W , KIM J W , JEON D K . A cooperative communication protocol for QoS provisioning in IEEE 802.11p/wave vehicular networks[J]. Sensors (Basel,Switzerland), 2018,18(11): 3622.
[9]	WU Z Y , LU Z H , HUNG P C K ,et al. QaMeC,a QoS-driven IoVs application optimizing deployment scheme in multimedia edge clouds[J]. Future Generation Computer Systems, 2019(92): 17-28.
[10]	SUN L , SHAN H G , HUANG A P ,et al. Channel allocation for adaptive video streaming in vehicular networks[J]. IEEE Transactions on Vehicular Technology, 2017,66(1): 734-747.
[11]	ZHANG H X , MA Y B , YUAN D F ,et al. Quality-of-service driven power and sub-carrier allocation policy for vehicular communication networks[J]. IEEE Journal on Selected Areas in Communications, 2011,29(1): 197-206.
[12]	LIANG H B , ZHANG X H , HONG X T ,et al. Reinforcement learning enabled dynamic resource allocation in the Internet of vehicles[J]. IEEE Transactions on Industrial Informatics, 2021,17(7): 4957-4967.
[13]	TAO X M , DUAN Y P , XU M ,et al. Learning QoE of mobile video transmission with deep neural network,a data-driven approach[J]. IEEE Journal on Selected Areas in Communications, 2019,37(6): 1337-1348.
[14]	BAIRAGI A K , ABEDIN S F , TRAN N H ,et al. QoE-enabled unlicensed spectrum sharing in 5G,a game-theoretic approach[J]. IEEE Access, 2018,6: 50538-50554.
[15]	JALIL PIRAN M , TRAN N H , SUH D Y ,et al. QoE-driven channel allocation and handoff management for seamless multimedia in cognitive 5G cellular networks[J]. IEEE Transactions on Vehicular Technology, 2017,66(7): 6569-6585.
[16]	ZHU H , CAO Y , WANG W ,et al. QoE-aware resource allocation for adaptive device-to-device video streaming[J]. IEEE Network, 2015,29(6): 6-12.
[17]	CHEN X , HWANG J N , DE MENG ,et al. A quality-of-content-based joint source and channel coding for human detections in a mobile surveillance cloud[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2017,27(1): 19-31.
[18]	ZHU L , YU F R , WANG Y G ,et al. Big data analytics in intelligent transportation systems,a survey[J]. IEEE Transactions on Intelligent Transportation Systems, 2019,20(1): 383-398.
[19]	ZHOU Z , CHEN X , LI E ,et al. Edge intelligence,paving the last Mile of artificial intelligence with edge computing[J]. Proceedings of the IEEE, 2019,107(8): 1738-1762.
[20]	FLORIDI L . Outline of a theory of strongly semantic information[J]. Minds and Machines, 2004,14(2): 197-221.
[21]	BAO J , BASU P , DEAN M K ,et al. Towards a theory of semantic communication[C]// Proceedings of 2011 IEEE Network Science Workshop. Piscataway,IEEE Press, 2011: 110-117.
[22]	SHANNON C E . Communication in the presence of noise[J]. Proceedings of the IRE, 1949,37(1): 10-21.
[23]	徐文伟, 张弓, 白铂 ,等. 后香农时代ICT领域的十大挑战问题[J]. 中国科学,数学, 2021,51(7): 1095-1138.
	XU W W , ZHANG G , BAI B ,et al. Ten key ICT challenges in the post-Shannon era[J]. Scientia Sinica (Mathematica), 2021,51(7): 1095-1138.
[24]	ZHONG Y X . A theory of semantic information[J]. China Communications, 2017,14(1): 1-17.
[25]	ZHU M Y , FENG C Y , CHEN J J ,et al. Video semantics based resource allocation algorithm for spectrum multiplexing scenarios in vehicular networks[C]// Proceedings of 2021 IEEE/CIC International Conference on Communications in China (ICCC Workshops). Piscataway,IEEE Press, 2021: 31-36.
[26]	陈九九, 冯春燕, 郭彩丽 ,等. 车联网中视频语义驱动的资源分配算法[J]. 通信学报, 2021,42(7): 1-11.
	CHEN J J , FENG C Y , GUO C L ,et al. Video semantics-driven resource allocation algorithm in Internet of vehicles[J]. Journal on Communications, 2021,42(7): 1-11.
[27]	CHEN J J , GUO C L , FENG C Y ,et al. Content driven and reinforcement learning based resource allocation scheme in vehicular network[C]// Proceedings of ICC 2021 - IEEE International Conference on Communications. Piscataway,IEEE Press, 2021: 1-6.
[28]	BOYD S , VANDENBERGHE L . Convex optimization[M]. Cambridge,Cambridge University Press, 2004.
[29]	ZANDAVI S M , CHUNG V Y Y , ANAISSI A . Stochastic dual simplex algorithm,a novel heuristic optimization algorithm[J]. IEEE Transactions on Cybernetics, 2021,51(5): 2725-2734.
[30]	HUSSAIN F , HASSAN S A , HUSSAIN R ,et al. Machine learning for resource management in cellular and IoT networks,potentials,current solutions,and open challenges[J]. IEEE Communications Surveys ＆Tutorials, 2020,22(2): 1251-1275.
[31]	XIE H Q , QIN Z J , LI G Y ,et al. Deep learning enabled semantic communication systems[J]. IEEE Transactions on Signal Processing, 2021,69: 2663-2675.
[32]	SHARMA S , KAUSHIK B . A survey on Internet of vehicles,applications,security issues ＆ solutions[J]. Vehicular Communications, 2019(20),100182
[33]	ZHANG K , MAO Y M , LENG S P ,et al. Predictive offloading in cloud-driven vehicles,using mobile-edge computing for a promising network paradigm[J]. IEEE Vehicular Technology Magazine, 2017(99),1.
[34]	HAN X , TIAN D X , SHENG Z G ,et al. Reliability-aware joint optimization for cooperative vehicular communication and computing[J]. IEEE Transactions on Intelligent Transportation Systems, 2021,22(8): 5437-5446.
[35]	CAO X W , WANG F , XU J ,et al. Joint computation and communication cooperation for energy-efficient mobile edge computing[J]. IEEE Internet of Things Journal, 2019,6(3): 4188-4200.
[36]	LI E , ZENG L K , ZHOU Z ,et al. Edge AI,on-demand accelerating deep neural network inference via edge computing[J]. IEEE Transactions on Wireless Communications, 2020,19(1): 447-457.
[37]	LEE M Y , YU G D , LI G Y . Learning to branch,accelerating resource allocation in wireless networks[J]. IEEE Transactions on Vehicular Technology, 2020,69(1): 958-970.
[38]	LUO S Q , CHEN X , ZHOU Z ,et al. Fog-enabled joint computation,communication and caching resource sharing for energy-efficient IoT data stream processing[J]. IEEE Transactions on Vehicular Technology, 2021,70(4): 3715-3730.
[39]	XU L M , YANG Z X , WU H Q ,et al. Socially driven joint optimization of communication,caching,and computing resources in vehicular networks[J]. IEEE Transactions on Wireless Communications, 2022,21(1): 461-476.
[40]	WANG G , WANG L , CHUAN J B ,et al. LRA-3C,learning based resource allocation for communication-computing-caching systems[C]// Proceedings of 2019 International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber,Physical and Social Computing (CPSCom) and IEEE Smart Data. Piscataway,IEEE Press, 2019: 828-833.
[41]	贺颖 . 基于深度强化学习的无线网络多维资源分配技术研究[D]. 大连,大连理工大学, 2018.
	HE Y . Research on multi-dimensional resource allocation of wireless networks based on deep reinforcement learning[D]. Dalian,Dalian University of Technology, 2018.
[42]	LI Z , GUO C L . Multi-agent deep reinforcement learning based spectrum allocation for D2D underlay communications[J]. IEEE Transactions on Vehicular Technology, 2020,69(2): 1828-1840.
[43]	DOLLáR P , WOJEK C , SCHIELE B ,et al. Pedestrian detection:anevaluation of the state of the art[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012,34(4): 743-761.
[44]	SUN P , KRETZSCHMAR H , DOTIWALLA X ,et al. Scalability in perception for autonomous driving,waymo open dataset[C]// Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway,IEEE Press, 2020: 2443-2451.
[45]	CHEN J , GUO C , WEI S ,et al. SCO-Dataset[EB]. 2022.
[46]	REN S Q , HE K M , GIRSHICK R ,et al. Faster R-CNN,towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017,39(6): 1137-1149.
[47]	SULLIVAN G J , OHM J R , HAN W J ,et al. Overview of the high efficiency video coding (HEVC) standard[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2012,22(12): 1649-1668.

优化准则	优点	缺点	适用任务类型	适用场景
模型驱动	可解释性强，不需要额外计算开销	计算精度不够，模型中的概率难计算	一般语义理解任务	所有场景
数据驱动	计算精度高，方法可迁移性强	可解释性差，需要数据和算力支撑	特定语义理解任务	智能场景

算法类别	代表算法	优点	缺点适用场景
精确算法	凸优化、动态规划等	能得到精确解，不依赖数据	复杂度高，不适合大规模问题小规模求解，高可靠需求场景
启发式算法	遗传算法、粒子群算法等	通用性较强，收敛速度快	次优解，易陷入局部最优局部开发，低时延需求场景
机器学习算法	强化学习等	无模型，与环境交互	对智能程度，计算能力要求较高决策优化，高动态变化场景

计算场景	定义	优点	缺点
计算卸载	DNN模型的训练和推理主要在边缘计算服务器上实现	适用于所有任务，实现简单	准确率较低，算力资源利用率较低
协同计算	服务器和车辆协同完成DNN模型的训练和推理	算力资源利用率高，准确率较高	实现复杂，不同任务间的兼容性差

资源分配模型	目标函数	耦合关系	面向场景
通信资源分配	P3、P4	通信资源和语义理解准确率之间的关系	面向语义通信的无线传输
通信和计算资源联合分配	P5、P6	通信和计算相互制约，共同影响语义理解准确率	无线传输和智能计算融合场景
多维资源联合分配	P7	不同资源之间存在相互转化和制约，不同资源对语义理解准确率的影响不同	通信、计算和存储等一体化场景

参数类别	参数数值
边缘服务器覆盖范围	0.5 km
车辆数目M	3～18
车辆行驶速度v_m	0～120 km/h
车辆发射功率	23 dBm
噪声功率谱密度	-174 dBm/Hz
中心载波频率	2 GHz

智能网联环境下面向语义通信的资源分配

Resource allocation for the semantic communication in the intelligent networked environment

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 9

参考文献 47

相关文章 15

Metrics

推荐阅读 0

[1]	王志宏, 冷甦鹏, 熊凯. 面向无人机集群协同感知的多智能体资源分配策略[J]. 物联网学报, 2023, 7(1): 18-26.
[2]	廖岑卉珊, 陈俊彦, 梁观平, 谢小兰, 卢小烨. 基于深度强化学习的SDN服务质量智能优化算法[J]. 物联网学报, 2023, 7(1): 73-82.
[3]	汤蓓, 王倩, 陈思光. 融合射频能量采集的协同节能计算迁移研究[J]. 物联网学报, 2023, 7(1): 83-92.
[4]	刘耀, 何岳园, 周红静, 李超良, 李闯. 移动边缘计算中基于资源联合分配的部分计算卸载方法[J]. 物联网学报, 2023, 7(1): 140-148.
[5]	张彪, 汪西明, 徐逸凡, 李文, 韩昊, 刘松仪, 陈学强. 基于多智能体深度强化学习的多域协同抗干扰方法研究[J]. 物联网学报, 2022, 6(4): 104-116.
[6]	张欢欢, 周安福, 马华东. 基于强化学习的实时视频流控与移动终端训练方法研究[J]. 物联网学报, 2022, 6(4): 1-13.
[7]	孙君, 赵尚维康. 工业物联网中基于Sarsa算法的节能计算卸载方案[J]. 物联网学报, 2022, 6(3): 82-90.
[8]	俞汉清, 林艳, 贾林琼, 李强, 张一晋. 面向多目标救援的通信受限无人机集群分布式策略[J]. 物联网学报, 2022, 6(3): 103-112.
[9]	罗梓珲, 江呈羚, 刘亮, 郑霄龙, 马华东. 基于深度强化学习的智能车间调度方法研究[J]. 物联网学报, 2022, 6(1): 53-64.
[10]	徐勇军, 杨浩克, 叶迎晖, 陈前斌, 卢光跃. 反向散射通信网络资源分配综述[J]. 物联网学报, 2021, 5(3): 56-69.
[11]	石光明, 肖泳, 李莹玉, 高大化, 谢雪梅. 面向万物智联的语义通信网络[J]. 物联网学报, 2021, 5(2): 26-36.
[12]	张琪, 蒋宇娜, 葛晓虎, 李永会. 基于最优运输理论的物联网边缘计算资源优化机制[J]. 物联网学报, 2021, 5(2): 60-70.
[13]	林椿珉, 曾烈康, 陈旭. 边缘智能驱动的高能效无人机自主导航算法研究[J]. 物联网学报, 2021, 5(2): 87-96.
[14]	沈学民,承楠,周海波,吕丰,权伟,时伟森,吴华清,周淙浩. 空天地一体化网络技术：探索与展望[J]. 物联网学报, 2020, 4(3): 3-19.
[15]	周鹏,徐金城,杨博. 工业物联网中基于边缘计算的跨域计算资源分配与任务卸载[J]. 物联网学报, 2020, 4(2): 96-104.