意图驱动的物联网双时间尺度资源分配方法

宋航; 才建; 袁运栋; 张宇; 刘锐; 王见素; 刘刚; 张敏; 王敬宇

doi:10.11959/j.issn.2096-3750.2026.00501

您当前的位置：

首页 >

文章列表页 >

意图驱动的物联网双时间尺度资源分配方法

理论与技术 | 更新时间：2026-04-16

- 意图驱动的物联网双时间尺度资源分配方法
- Intent-driven dual-time-scale resource allocation approach for Internet of things
- 物联网学报 2026年10卷第1期页码：216-225
- 作者机构：
  
  1.中油国际管道公司，北京 102200
  2.北京邮电大学网络与交换技术全国重点实验室，北京 100876
- 作者简介：
  
  [ "宋航（1989‒ ），男，中油国际管道公司工程师，主要研究方向为石油通信。" ]
  [ "才建（1980‒ ），男，博士，中油国际管道公司高级工程师，主要研究方向为油气管道建设及运行管理。" ]
  [ "袁运栋（1971‒ ），男，中油国际管道公司高级工程师，主要研究方向为油气管道运行管理。" ]
  [ "张宇（1983‒ ），男，博士，中油国际管道公司高级工程师，主要研究方向为油气储运。" ]
  [ "刘锐（1974.10‒ ），男，中油国际管道公司高级工程师，主要研究方向为长输油气管道自动化和通信。" ]
  [ "王见素（1987‒ ），女，中油国际管道公司会计师，主要研究方向为网络信息。" ]
  [ "刘刚（1982‒ ），男，中油国际管道公司高级工程师，主要研究方向为自动化与无线通信。" ]
  [ "张敏（2002‒ ），女，北京邮电大学网络与交换技术全国重点实验室硕士生，主要研究方向为意图网络。" ]
  [ "王敬宇（1978‒ ），男，博士，北京邮电大学网络与交换技术全国重点实验室长聘教授，国家级高层次人才，国家自然科学基金重点项目负责人，中国通信学会高级会员，主要研究方向为智能网络、机器学习、边缘计算。" ]
- 基金信息：
  
  国家自然科学基金项目(62471055;U23B2001;62071067);教育部-中国移动科研基金项目(MCM20200202;MCM20180101)
- DOI：10.11959/j.issn.2096-3750.2026.00501
  中图分类号： TP393
- 收稿：2025-04-09，
  
  修回：2025-06-26，
  
  录用：2025-06-30，
  
  纸质出版：2026-03-30
- 稿件说明：
移动端阅览
宋航,才建,袁运栋等.意图驱动的物联网双时间尺度资源分配方法[J].物联网学报,2026,10(01):216-225.

Song Hang,Cai Jian,Yuan Yundong,et al.Intent-driven dual-time-scale resource allocation approach for Internet of things[J].Chinese Journal on Internet of Things,2026,10(01):216-225.
宋航,才建,袁运栋等.意图驱动的物联网双时间尺度资源分配方法[J].物联网学报,2026,10(01):216-225. DOI： 10.11959/j.issn.2096-3750.2026.00501.

Song Hang,Cai Jian,Yuan Yundong,et al.Intent-driven dual-time-scale resource allocation approach for Internet of things[J].Chinese Journal on Internet of Things,2026,10(01):216-225. DOI： 10.11959/j.issn.2096-3750.2026.00501.

摘要

随着物联网技术的发展，不同业务场景对服务质量的需求日趋多样化。当前，如何精准解析物联网业务需求、有效保障差异化业务场景的服务质量，仍是行业面临的巨大挑战。针对这一挑战，亟待深入研究意图驱动的物联网资源分配机制。物联网环境具有动态复杂性，且业务需求存在显著差异，传统需求解析方式难以实现用户意图到物联网策略的精准映射。为此，提出一种意图驱动的双时间尺度资源分配方法。首先，根据业务服务质量需求对场景进行分类，并设计基于大规模语言模型与检索增强的意图转译算法，结合设备及业务信息，将用户意图转译为可执行的物联网策略。其次，面向资源分配效率与物联网动态状态变化，构建以最大化系统整体收益为优化目标的双时间尺度资源分配框架。该框架包括：在长时间尺度下，采用竞争双深度Q网络算法对切片间资源进行全局分配；在短时间尺度下，通过混合整数线性规划算法对切片内业务细粒度资源进行调配。实验结果表明，所提方法通过融合意图转译算法实现了上层策略精准生成，并结合资源分配算法实现下层资源的弹性调度。相较于单一时间尺度的算法，该方法能够进行更高效且贴合下游物联网状态的资源分配，进而保障同一物联网中不同业务场景的差异化服务质量。

Abstract

With the development of IoT technologies

the demand for quality of service across different business scenarios has become increasingly diverse. Currently

how to accurately interpret IoT service requirements and effectively guarantee quality of service (QoS) for differentiated business scenarios remains a significant challenge in the industry. To address this challenge

in-depth research on intent-driven IoT resource allocation mechanisms is urgently needed. Given the dynamic and complex nature of IoT environments

along with the notable differences in service requirements

traditional demand interpretation methods are found to be inadequate for achieving accurate mapping from user intents to IoT policies. Therefore

an intent-driven dual-time-scale resource allocation method was proposed. Firstly

scenarios were categorized based on their QoS requirements

and an intent translation algorithm based on a large language model with retrieval enhancement was designed. By integrating device and service information

user intents were translated into executable IoT policies. Secondly

focusing on both resource allocation efficiency and the dynamic state changes in IoT environments

a dual-time-scale resource allocation framework was constructed with the optimization objective of maximizing the overall system revenue. This framework included: at the long time scale

the dueling double deep Q-network (D3QN) algorithm was adopted for global resource allocation among slices; at the short time scale

the mixed-integer linear programming (MILP) algorithm was employed for fine-grained resource scheduling within slices. Experimental results demonstrated that the proposed method enabled accurate generation of upper-level policies through intent translation and achieved elastic scheduling of lower-level resources via the resource allocation algorithms. Compared with single-time-scale algorithms

the proposed approach allowed for more efficient resource allocation that better adapted to the state of downstream IoT systems

thereby ensuring differentiated QoS for various business scenarios within the same IoT environment.

关键词

Keywords

references

Cheng N , Lyu F , Quan W , et al . Space/aerial-assisted computing offloading for IoT applications: a learning-based approach [J ] . IEEE Journal on Selected Areas in Communications , 2019 , 37 ( 5 ): 1117 - 1129 .

Maule M , Vardakas J , Verikoukis C . 5G RAN slicing: dynamic single tenant radio resource orchestration for eMBB traffic within a multi-slice scenario [J ] . IEEE Communications Magazine , 2021 , 59 ( 3 ): 110 - 116 .

Wang C X , You X H , Gao X Q , et al . On the road to 6G: visions, requirements, key technologies, and testbeds [J ] . IEEE Communications Surveys & Tutorials , 2023 , 25 ( 2 ): 905 - 974 .

Latva-Aho M , Leppänen K . Key drivers and research challenges for 6G ubiquitous wireless intelligence [R ] . 2019 .

TM Forum . Autonomous networks: empowering digital transformation for telecoms industry [R ] . 2019 .

De Alwis C , Kumar P , Pham Q V , et al . Towards 6G: key technological directions [J ] . ICT Express , 2023 , 9 ( 4 ): 525 - 533 .

Boasman-Patel A R E , Sun D , Wang Y , et al . Autonomous networks: empowering digital transformation for the telecoms industry [R ] . 2019 .

Beshley M , Kryvinska N , Beshley H . Quality of service management method in a heterogeneous wireless network using big data technology and mobile QoE application [J ] . Simulation Modelling Practice and Theory , 2023 , 127 : 102771 .

Khurana D , Koli A , Khatter K , et al . Natural language processing: state of the art, current trends and challenges [J ] . Multimedia tools and applications , 2023 , 82 ( 3 ): 3713 - 3744 .

Achiam J , Adler S , Agarwal S , et al . Gpt-4 technical report [PP ] . V4 , arXiv ( 2023-11-19 )[ 2025-06-09 ] . arXiv: 2303.08774 .

Min B , Ross H , Sulem E , et al . Recent advances in natural language processing via large pre-trained language models: a survey [J ] . ACM Computing Surveys , 2023 , 56 ( 2 ): 1 - 40 .

Chen L J , Zaharia M , Zou J . How is ChatGPT's behavior changing over time [J ] . Harvard Data Science Review·Special Issue 5: Grappling With the Generative AI Revolution , 2024 , 6 ( 2 ): 1 - 26 .

Hu L M , Liu Z Y , Zhao Z W , et al . A survey of knowledge enhanced pre-trained language models [PP ] . V4. arXiv ( 2023-8-30 )[ 2025-06-09 ] . arXiv: 2211.05994 .

Clemm A , Ciavaglia L , Granville L Z , et al . Intent-based networking-concepts and definitions:RFC 9315 [EB ] . 2022 .

Velasco L , Signorelli M , De Dios O G , et al . End-to-end intent-based networking [J ] . IEEE communications Magazine , 2021 , 59 ( 10 ): 106 - 112 .

Leivadeas A , Falkner M . VNF placement problem: a multi-tenant intent-based networking approach [C ] // Proceedings of the 2021 24th Conference on innovation in clouds, internet and networks and workshops (ICIN) . Piscataway : IEEE Press , 2021 : 143 - 150 .

Leivadeas A , Falkner M . A survey on Intent-based networking [J ] . IEEE Communications Surveys & Tutorials , 2023 , 25 ( 1 ): 625 - 655 .

Mcnamara J , Camps-Mur D , Goodarzi M , et al . Nlp powered Intent based network management for private 5G networks [J ] . IEEE Access , 2023 , 11 : 36642 - 36657 .

李凤凯 , 张亚丽 , 夏寅贲 . NEMO:一种声明式网络编程与业务定制语言 [J ] . 信息通信技术 , 2016 , 10 ( 4 ): 65 - 74 .

LI F K , Zhang Y L , XIA Y B . NEMO：a declarative network programming and service customization language [J ] . Information and Communications Technologies , 2016 , 10 ( 4 ): 65 - 74 .

Van Deursen A , Klint P . Domain-specific language design requires feature descriptions [J ] . Journal of Computing and Information Technology , 2002 , 10 ( 1 ): 1 - 17 .

Tian B C , Zhang X Y , Zhai E N , et al . Safely and automatically updating in-network ACL configurations with Intent language [C ] // Proceedings of the ACM Special Interest Group on Data Communication . New York : ACM Press , 2019 : 214 - 226 .

Jacobs A S , Pfitscher R J , Ribeiro R H , et al . Hey, Lumi! Using natural language for Intent-based network management [C ] // Proceedings of the 2021 USENIX Annual Technical Conference . 2021 : 625 - 639 .

Zhao J Y , Sun H F , Wang J Y , et al . CONFPILOT: a pilot for faster configuration by learning from device manuals [C ] // Proceedings of the 2023 IEEE 43rd International Conference on Distributed Computing Systems (ICDCS) . Piscataway : IEEE Press , 2023 : 108 - 119 .

Khan T A , Abbas K , Muhammad A , et al . GAN and DRL based Intent translation and deep fake configuration generation for optimization [C ] // Proceedings of the 2020 International Conference on Information and Communication Technology Convergence (ICTC) . Piscataway : IEEE Press , 2020 : 347 - 352 .

Ji Z W , Lee N , Frieske R , et al . Survey of hallucination in natural language generation [J ] . ACM Computing Surveys , 2023 , 55 ( 12 ): 1 - 38 .

Lin B H , Bouneffouf D , Cecchi G , et al . Towards healthy AI: large language models need therapists too [C ] // Proceedings of the 4th Workshop on Trustworthy Natural Language Processing (TrustNLP 2024) . ACL Press , 2024 : 61 - 70 .

NGMN . Description of network slicing concept [EB ] . 2016 .

Trivisonno R , An X L , Wei Q . Network slicing for 5G systems: a review from an architecture and standardization perspective [C ] // Proceedings of the 2017 IEEE Conference on Standards for Communications and Networking (CSCN) . Piscataway : IEEE Press , 2017 : 36 - 41 .

Chergui H , Verikoukis C . Big data for 5G intelligent network slicing management [J ] . IEEE Network , 2020 , 34 ( 4 ): 56 - 61 .

Hurtado Sánchez J A , Casilimas K , Rendon O M C . Deep reinforcement learning for resource management on network slicing: a survey [J ] . Sensors , 2022 , 22 ( 8 ): 3031 .

Su R Y , Zhang D Y , Venkatesan R , et al . Resource allocation for network slicing in 5G telecommunication networks: a survey of principles and models [J ] . IEEE Network , 2019 , 33 ( 6 ): 172 - 179 .

Han B , Schotten H D . Machine learning for network slicing resource management: a comprehensive survey [J ] . ZTE Communications , 2019 , 17 ( 4 ): 27 - 32 .

Dong T J , Zhuang Z R , Qi Q , et al . Intelligent joint network slicing and routing via GCN-powered multi-task deep reinforcement learning [J ] . IEEE Transactions on Cognitive Communications and Networking , 2021 , 8 ( 2 ): 1269 - 1286 .

Leconte M , Paschos G S , Mertikopoulos P , et al . A resource allocation framework for network slicing [C ] // Proceedings of the IEEE INFOCOM 2018-IEEE Conference on Computer Communications . Piscataway : IEEE Press , 2018 : 2177 - 2185 .

亓伟敬 , 宋清洋 , 郭磊 . 面向软件定义多模态车联网的双时间尺度 RAN 切片资源分配 [J ] . 通信学报 , 2022 , 43 ( 4 ): 60 - 70 .

QI W J , S Q Y , GUO L . Dual time scale resource allocation for RAN slicing in software-defined oriented polymorphic IoV [J ] . Journal on Communications , 2022 , 43 ( 4 ): 60 - 70 .

陈赓 , 齐书虎 , 沈斐 , 等 . 面向 B5G 多业务场景基于 D3QN 的双时间尺度网络切片算法 [J ] . 通信学报 , 2022 , 43 ( 11 ): 213 - 224 .

Chen G , Qi S H , Shen Fei , et al . Dual time scale network slicing algorithm based on D3QN for B5G multi-service scenarios [J ] . Journal on Communication , 2022 , 43 ( 11 ): 213 - 224 .

郭令奇 , 张蕾 , 杨红伟 , 等 . 知识定义的意图网络策略生成技术 [J ] . 北京邮电大学学报 , 2024 , 47 ( 3 ): 36 - 41 .

Guo L Q , Zhang L , Yang H W , et al . Intent-based network policy generation for knowledge definition [J ] . Journal of Beijing University of Posts and Telecommunications , 2024 , 47 ( 3 ): 36 - 41 .

Winata G I , Madotto A , Lin Z J , et al . Language models are few-shot learners [C ] // Proceedings of the 1st Workshop on Multilingual Representation Learning . ACL Press , 2021 , 1 - 15 .

Tay Y , Tran V , Dehghani M , et al . Transformer memory as a differentiable search index [C ] // Proceedings of the 36th International Conference on Neural Information Processing System . New York : Curran Associates Inc. , 2022 : 21831 - 21843 .

Han R X , Wang J Y , Qi Q , et al . NetRen: service migration-driven network renascence with synthesizing updated configuration [C ] // Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems , New York : ACM Press , 2024 : 708 - 721 .

Guo D K , Li C l , Wu J , et al . DCube: a family of network structures for containerized data centers using dual-port servers [J ] . Computer communications , 2014 , 53 : 13 - 25 .

Singla A , Hong C Y , Popa L , et al . Jellyfish: networking data centers randomly [C ] // Proceedings of the 9th USENIX conference on Networked Systems Design and Implementation . 2012 : 225 - 238 .

Bega D , Gramaglia M ， Fiore M , et al . AZTEC: Anticipatory capacity allocation for zero-touch network slicing [C ] // Proceedings of the IEEE INFOCOM 2020 - IEEE Conference on Computer Communications . Piscataway : IEEE Press , 2020 : 794 - 803 .

Bega D , Gramaglia M , Bernardos Cano C J , et al . Toward the network of the future: from enabling technologies to 5G concepts [J ] . Transactions on Emerging Telecommunications Technologies , 2017 , 28 ( 8 ): e3205 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于深度强化学习的图约简方法

面向非可信节点的联合频谱感知与资源分配机制设计

星地协同中基于多智能体的时敏任务调度优化策略