中国电信股份有限公司上海分公司,上海 200041
龚勃(1969- ),男,中国电信股份有限公司上海分公司高级工程师,主要研究方向为云网融合、固移融合、物联网及智算网络。
曾莹(1977- ),女,中国电信股份有限公司上海分公司总工程师室高级工程师,集团公司高级专家,主要研究方向为新型城域网、融合边缘、云化网关、vDPI、网络安全、数据安全及应用安全。
朱姝(1981- ),女,中国电信股份有限公司上海分公司总工程师室副总工程师,主要研究方向为新型城域网、云网融合、云化网关、人工智能。
张慷(1968- ),男,中国电信股份有限公司上海分公司副总工程师,主要研究方向为云网融合、算力网络、人工智能。
许燕萍(1980- ),女,中国电信股份有限公司上海分公司智能云网操作维护中心高级工程师,上海公司一级专家,主要研究方向为云化网关、智慧家庭终端、政企智能终端及终端运营支撑系统实现。
收稿:2025-11-06,
修回:2026-04-14,
纸质出版:2026-05-20
移动端阅览
龚勃,曾莹,朱姝等.基于云网关的边缘智能体架构方案[J].电信科学,2026,42(05):212-221.
Gong Bo,Zeng Ying,Zhu Shu,et al.Architecture scheme for edge AI agents based on cloud gateway[J].Telecommunications Science,2026,42(05):212-221.
龚勃,曾莹,朱姝等.基于云网关的边缘智能体架构方案[J].电信科学,2026,42(05):212-221. DOI: 10.11959/j.issn.1000-0801.DXKX250650.
Gong Bo,Zeng Ying,Zhu Shu,et al.Architecture scheme for edge AI agents based on cloud gateway[J].Telecommunications Science,2026,42(05):212-221. DOI: 10.11959/j.issn.1000-0801.DXKX250650.
基于云网关的边缘智能体是融合了边缘计算与人工智能(AI)技术,部署在边缘设备与边缘云网关的智能程序或系统。该边缘智能体具有基于云网关的应用识别能力,具备边端策略自适应、可扩展性强等优势,具有很广泛的应用前景,同时其对架构也提出了一定的要求。主要分析了基于云网关的边缘智能体架构方案如何在运营商级城域网上部署,以实现边缘智能体自适应、可扩展的优势,该架构可为后续在新型城域网部署智能体服务提供参考。
The edge AI agent based on the cloud gateway is an intelligent program or system which integrates edge computing and artificial intelligence technologies. This agent is deployed on edge devices and edge cloud gateways. It possesses the capability of identifying applications based on the cloud gateway
supports adaptive edge strategies
offers high scalability
and has broad application prospects. At the same time
it also can impose certain requirements on its architecture. The architectural solution of the edge AI agent based on the cloud gateway was primarily analyzed
which could be deployed and implemented on a carrier network to realize the adaptive and scalable advantages of the edge AI agent
serving as a reference for providing intelligent agent services in the deployment of next-generation metropolitan area networks.
张晓东 , 张朝昆 , 赵继军 . 边缘智能研究进展 [J ] . 计算机研究与发展 , 2023 , 60 ( 12 ): 2749 - 2769 .
Zhang X D , Zhang C K , Zhao J J . State-of-the-art survey on edge intelligence [J ] . Journal of Computer Research and Development , 2023 , 60 ( 12 ): 2749 - 2769 .
田睿 , 张雅勤 , 董伟 , 等 . 机器学习在恶意加密流量检测中的应用及研究 [J ] . 电子技术应用 , 2025 , 51 ( 4 ): 1 - 11 .
Tian R , Zhang Y Q , Dong W , et al . The application and research of machine learning in malicious encrypted traffic detection [J ] . Application of Electronic Technique , 2025 , 51 ( 4 ): 1 - 11 .
Lu C W , Cao Y X , Wang Z B . Research on intrusion detection based on an enhanced random forest algorithm [J ] . Applied Sciences , 2024 , 14 ( 2 ): 714 .
赵馨 , 李文博 . 基于ASPP-Swin Transformer模型的加密流量识别方法 [J ] . 通信世界 , 2025 ( 20 ): 29 - 35 .
Zhao X , Li W B . Encrypted traffic identification method based on ASPP-Swin Transformer model [J ] . Communications World , 2025 ( 20 ): 29 - 35 .
Binbusayyis A . Hybrid VGG19 and 2D-CNN for intrusion detection in the FOG-cloud environment [J ] . Expert Systems with Applications , 2024 , 238 : 121758 .
何明枢 . 基于机器学习的网络流威胁行为认知分析与研究 [D ] . 北京 : 北京邮电大学 , 2022 .
He M S . Research on network flow threat behavior cognition based on machine learning [D ] . Beijing : Beijing University of Posts and Telecommunications , 2022 .
Ahmed M J , Mozo A , Karamchandani A . A survey on graph neural networks, machine learning and deep learning techniques for time series applications in industry [J ] . PeerJ Computer Science , 2025 , 11 : e3097 .
李孟想 , 彭闯 , 王浩 , 等 . 基于图神经网络的鲁棒加密流量识别 [J ] . 电信科学 , 2024 , 40 ( 6 ): 89 - 99 .
Li M X , Peng C , Wang H , et al . A robust encrypted traffic identification scheme based on graph neural network [J ] . Telecommunications Science , 2024 , 40 ( 6 ): 89 - 99 .
王志宏 , 刘昇然 , 池泽桂 , 等 . 基于多层级图表征增强的加密应用流量识别方法 [J ] . 计算机科学 , 2025 , 52 ( S2 ): 871 - 877 .
Wang Z H , Liu S R , Chi Z G , et al . Classification of encrypted application traffic enhanced by multi-level graph representation [J ] . Computer Science , 2025 , 52 ( S2 ): 871 - 877 .
Cui T , Lin X , Li S , et al . TrafficLLM: enhancing large language models for network traffic analysis with generic traffic representation [PP ] . ( 2025-04-15 )[ 2025-10-11 ] . arXiv: 2504.04222 .
Wang X , Han Y , Leung V C M , et al . Edge intelligence: on-demand deep learning model co-inference with mobile edge computing for smart city applications [J ] . IEEE Communications Magazine , 2023 , 61 ( 4 ): 28 - 34 .
ITU-T Recommendation G . 107: The E-model: a computational model for use in transmission planning [S ] . 2022
Sandler M , Howard A , Zhu M L , et al . MobileNetV2: inverted residuals and linear bottlenecks [C ] // Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE Press , 2018 : 4510 - 4520 .
Zhang K , Li M , Liu Z , et al . Federated QoE prediction in telecom networks using lightweight LSTM models [C ] // Proceedings of the IEEE International Conference on Communications (ICC) . Piscataway : IEEE Press, Seoul , 2024 : 1 - 6 .
Chen X , Shi W , Liang W , et al . AI agents in edge computing: architectures, challenges, and opportunities [J ] . ACM Computing Surveys , 2025 , 57 ( 3 ): 1 - 36 .
0
浏览量
0
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621