| 533 | 5 | 4 |
| 下载次数 | 被引频次 | 阅读次数 |
为解决现有算网融合方案存在的完整业务建模缺失、算网资源与业务需求失配、系统多性能指标折中关系不清的问题，提出了基于服务化架构的算网融合关键技术。通过建模微服务与业务性能相关性业务模型，设计适配业务需求的算网融合资源调度方案，并研究面向系统多种性能联合优化的算网融合一体化编排策略，满足新一代移动通信网络建设中业务高性能、系统高效能、算网深融合的综合发展需求。
Abstract：The current schemes of computing and network convergence(CNC) resource allocation face three challenges: the lack of a general profile and model of service, the mismatching between computing-network resource allocation and service needs, and the missing analysis of the tradeoff relation among various system key performance indicators(KPIs). To solve these problems, the combination between service-based architecture and CNC is studied, and the service-aware CNC technology is introduced. By leveraging the orchestration strategy of computing and network for the system-level optimization on multiple KPIs, the service-aware CNC can greatly enhance the performance of applications, improve the efficiency of the system and strengthen the convergence of computing and network.
[1] IMT-2030(6G)推进组. 6G典型场景和关键能力白皮书[R]. 2022
[2]中国信息通信研究院.中国算力发展指数白皮书[EB/OL].[2022-09-05]. http://www.caict.ac.cn/kxyj/qwfb/bps/202109/t20210918_390058.htm
[3] China Mobile, China Telecom, China Unicom, et al. 5G-advanced technology evolution from a network perspective(2021)[EB/OL].[2022-09-05]. https://www. huawei. com/en/events/5g-advanced-technologyevolution-network-perspective
[4] IMT-2030(6G)推进组. 6G网络架构愿景与关键技术展望白皮书[R]. 2021
[5] PELTONEN E, BENNIS M, CAPOBIANCO M, et al. 6G white paper on edge intelligence[EB/OL].(2020-04-30)[2022-09-07]. https://arxiv. org/abs/2004.14850
[6] WIKSTROM G, PERSSON P, PARKVALL S, et al. 6G-connecting a cyberphysical world[EB/OL].[2022-09-06]. https://www. ericsson. com/en/reports-and-papers/white-papers/a-research-outlook-towards-6g
[7]国家发展改革委,中央网信办,工业和信息化部,等.全国一体化大数据中心协同创新体系算力枢纽实施方案[EB/OL].[2022-09-06]. https://www.ndrc.gov.cn/xwdt/tzgg/202105/t20210526_1280839.html?code=&state=123
[8] IMT-2030(6G)推进组. 6G网络架构愿景与关键技术展望白皮书[EB/OL].[2022-09-06]. https://mp.weixin.qq.com/s/JXq Jb VTvb Pv JE_Tl5jRXKA
[9]中国移动通信有限公司研究院. 6G服务化RAN白皮书[EB/OL].[2022-09-06]. http://cmri.chinamobile.com/insight/technology/7319.html
[10] WANG M, CHENG B, FENG W D, et al. An efficient service function chain placement algorithm in a MEC-NFV environment[C]//Proceedings of 2019IEEE Global Communications Conference. IEEE, 2019:1-6. DOI:10.1109/GLOBECOM38437.2019.9013235
[11] CAO Z, ZHANG H G, CAO Y, et al. A deep reinforcement learning approach to multi-component job scheduling in edge computing[C]//Proceedings of 2019 15th International Conference on Mobile Ad-Hoc and Sensor Networks(MSN). IEEE, 2019:19-24. DOI:10.1109/MSN48538.2019.00018
[12] CHEN L L, XU Y C, LU Z H, et al. IoT microservice deployment in edgecloud hybrid environment using reinforcement learning[J]. IEEE Internet of Things journal, 2021, 8(16):12610-12622. DOI:10.1109/JIOT.2020.3014970
[13] WANG S Q, ZAFER M, LEUNG K K. Online placement of multicomponent applications in edge computing environments[J]. IEEE access,2017, 5:2514-2533. DOI:10.1109/ACCESS.2017.2665971
[14] CHEN J W, YANG Y J, WANG C Y, et al. Multitask offloading strategy optimization based on directed acyclic graphs for edge computing[J]. IEEE Internet of Things journal, 2022, 9(12):9367-9378. DOI:10.1109/JIOT.2021.3110412
[15] GHOLAMI A, BARAS J S. Collaborative cloud-edge-local computation offloading for multi-component applications[C]//2021 IEEE/ACM Symposium on Edge Computing(SEC). IEEE, 2021:361-365. DOI:10.1145/3453142.3493515
[16] SEDGHANI H, FILIPPINI F, ARDAGNA D. A randomized greedy method for AI applications component placement and resource selection in computing continua[C]//Proceedings of 2021 IEEE International Conference on Joint Cloud Computing. IEEE,2021:65-70. DOI:10.1109/JCC53141.2021.00022
[17] CHEN X W, TANG S T, LU Z H, et al. iDiSC:a new approach to IoT-dataintensive service components deployment in edge-cloud-hybrid system[J]. IEEE access, 7:59172-59184. DOI:10.1109/ACCESS.2019.2915020
[18] FATICANTI F, DE PELLEGRINI F, SIRACUSA D, et al. Throughput-aware partitioning and placement of applications in fog computing[J]. IEEE transactions on network and service management, 2020, 17(4):2436-2450. DOI:10.1109/TNSM.2020.3023011
基本信息:
DOI：
中图分类号:TN929.5
引用信息:
[1]周吉喆,杨思远,王志勤.面向业务感知的算网融合关键技术研究[J].中兴通讯技术,2022,28(05):2-6.
基金信息:
国家重点研发计划（2021YFB2900200）; 中国博士后科学基金（2022M713475）