基于可解释性AI的6G O-RAN研究综述

廖勇; 杨善云

doi:10.11959/j.issn.1000-0801.DXKX260181

您当前的位置：

首页 >

文章列表页 >

基于可解释性AI的6G O-RAN研究综述

更新时间：2026-06-24

- 基于可解释性AI的6G O-RAN研究综述
- A Survey on 6G O-RAN Based on Explainable AI
- 电信科学 2026年
- 作者机构：
  
  重庆大学微电子与通信工程学院，重庆 400044
- 作者简介：
  
  廖勇（1982-），男，四川自贡人，博士，副研究员，CCF杰出会员，主研6G通信、人工智能技术及其应用
  杨善云（2005-），男，重庆合川人，本科生，电子信息工程专业。
- 基金信息：
  
  重庆市自然科学基金(CSTB2023NSCQ-MSX0025)
- DOI：10.11959/j.issn.1000-0801.DXKX260181
  中图分类号： A
- 收稿：2026-03-19，
  
  修回：2026-05-20，
  
  录用：2026-06-01，
- 稿件说明：
移动端阅览
廖勇, 杨善云. 基于可解释性AI的6G O-RAN研究综述[J/OL]. 电信科学, 2026.

LIAO Yong, YANG Shanyun. A Survey on 6G O-RAN Based on Explainable AI[J/OL]. Telecommunications Science, 2026.
廖勇, 杨善云. 基于可解释性AI的6G O-RAN研究综述[J/OL]. 电信科学, 2026. DOI： 10.11959/j.issn.1000-0801.DXKX260181.

LIAO Yong, YANG Shanyun. A Survey on 6G O-RAN Based on Explainable AI[J/OL]. Telecommunications Science, 2026. DOI： 10.11959/j.issn.1000-0801.DXKX260181.

摘要

面向第六代移动通信技术（Sixth Generation Mobile Communication，6G）的开放式无线接入网络（Open Radio Access Network，O-RAN）智能自治演进中，高度依赖的人工智能（Artificial Intelligence，AI）黑盒特性与透明决策需求存在矛盾。可解释人工智能（eXplainable AI，XAI）深度融合是打破黑盒、实现透明决策及构建可信自治网络的核心。本文综述XAI在6G O-RAN中的研究，提出多层级融合部署框架与应用路径：阐述O-RAN架构与XAI部署逻辑；围绕无线资源管理、网络切片运维、网络安全增强、智能协作与零接触运维，分析XAI实现路径与典型应用；探讨解释计算开销与实时性矛盾、评估标准匮乏、接口协同限制及隐私风险等技术挑战；展望轻量化XAI算法、神经符号因果推理模型、闭环自治机制及跨学科方法融合等趋势，为构建智能、透明、安全的6G可信自治网络提供参考。

Abstract

As the Open Radio Access Network (O-RAN) for Sixth Generation mobile communication technology (6G) evolves toward intelligent autonomy

the "black-box" nature of highly relied-upon Artificial Intelligence (AI) models conflicts with the requirement for transparent and trustworthy decision-making. The deep integration of eXplainable AI (XAI) is essential to demystify this black-box

achieve transparent decision-making

and construct a trustworthy autonomous network. This paper provides a comprehensive review of XAI research in 6G O-RAN and proposes a multi-layer integrated deployment framework and roadmap: we expound on the O-RAN architecture and XAI deployment logic; analyze implementation paths and typical applications across radio resource management

network slicing

network security enhancement

intelligent collaboration

and zero-touch operation; discuss technical challenges

including the trade-off between explanation computational overhead and real-time requirements

the lack of unified evaluation standards

interface-induced coordination constraints

and data privacy risks; and explore future trends

such as lightweight XAI algorithms

neuro-symbolic causal reasoning models

closed-loop autonomous mechanisms

and interdisciplinary integration

offering insights for constructing intelligent

transparent

and secure 6G trustworthy autonomous networks.

关键词

Keywords

references

BRIK B , BOUTIBA K , DAHMANI A , et al . Explainable AI in 6G O-RAN: A tutorial and survey on architecture, use cases, challenges, and future research [J ] . IEEE Communications Surveys & Tutorials , 2025 , 27 ( 5 ): 2826 - 2859 .

WANG C X . On the road to 6G: Visions, requirements, key technologies and testbeds [J ] . IEEE Communications Surveys & Tutorials , 2023 , 25 ( 2 ): 905 - 974 .

ZHOU D , SHENG M , LI J , et al . Aerospace integrated networks innovation for empowering 6G: A survey and future challenges [J ] . IEEE Communications Surveys & Tutorials , 2023 , 25 ( 2 ): 975 - 1019 .

MAO B , LIU J , WU Y , et al . Security and privacy on 6G network edge: A survey [J ] . IEEE Communications Surveys & Tutorials , 2023 , 25 ( 2 ): 1095 - 1127 .

CORONADO E , et al . Zero touch management: A survey of network automation solutions for 5G and 6G networks [J ] . IEEE Communications Surveys & Tutorials , 2022 , 24 ( 4 ): 2535 - 2578 .

王思野 , 高荦雨 , 赵中原 , 等 . 6G与XAI的融合 [J ] . 移动通信 , 2024 , 48 ( 8 ): 111 - 117 .

杨志航 . 算法透明实现的另一种可能: 可解释人工智能 [J ] . 行政法学研究 , 2024 ( 3 ): 154 - 163 .

杜人淮 , 马会君 . 人工智能的一体化发展及其水平评价研究 [J ] . 贵州大学学报(自然科学版) , 2025 , 42 ( 6 ): 1 - 11 .

包义明 , 林阳 , 屠要峰 . 人工智能技术与应用前沿 [J ] . 中兴通讯技术 , 2025 , 31 ( 4 ): 64 - 74 .

BASARAN T , DRESSLER F . XAInomaly: Explainable, interpretable and trustworthy AI for xURLLC in 6G Open-RAN [C ] // 2024 3rd International Conference on 6G Networking (6GNet) . Paris, France : IEEE , 2024 : 93 - 101 .

FIANDRINO C , BONATI L , D'ORO S , et al . EXPLORA: AI/ML EXPLainability for the open RAN [J ] . Proceedings of the ACM on Networking , 2023 , 1(CoNEXT3): 19.

解宇瑄 , 李响 , 李婷 , 等 . 6G无线接入网通算智融合关键技术与标准化思考 [J/OL ] . 中兴通讯技术 , 1 - 13 [ 2026-04-15 ] .

索士强 , 许盛浩 , 曾婷 , 等 . 面向6G的通感空口融合无线电接入网方案 [J ] . 电信科学 , 2022 , 38 ( 9 ): 71 - 76 .

王晴天 , 刘洋 , 刘海涛 , 等 . 面向6G的网络智能化研究 [J ] . 电信科学 , 2022 , 38 ( 9 ): 151 - 160 .

FIANDRINO C , ATTANASIO G , FIORE M , et al . Toward native explainable and robust AI in 6G networks: Current state, challenges and road ahead [J ] . Computer Communications , 2022 , 193 : 47 - 52 .

JUNEJO S , SHAIKH F K , CHOWDHRY B S , et al . Role of AI and Open RAN in 6G networks: Performance impact and key technologies [C ] // 2024 IEEE International Conference on Advanced Telecommunication and Networking Technologies (ATNT) . Johor Bahru, Malaysia : IEEE , 2024 : 1 - 4 .

AL KASSIR H , MASOOD A , KAZMI S H A , et al . Automated end-to-end AI/ML lifecycles for radio management in 6G networks [C ] // 2024 IEEE Future Networks World Forum (FNWF) . Dubai, United Arab Emirates : IEEE , 2024 : 365 - 371 .

KHAN N , COLERI S , ABDALLAH A , et al . Explainable and robust artificial intelligence for trustworthy resource management in 6G networks [J ] . IEEE Communications Magazine , 2024 , 62 ( 4 ): 50 - 56 .

LIATSAS L , KIBALYA G M , ANTONOPOULOS A . XAI-driven model design for resource utilization forecasting in cloud-native 6G networks [C ] // 2024 IEEE International Mediterranean Conference on Communications and Networking (MeditCom) . Madrid, Spain : IEEE , 2024 : 566 - 571 .

O-RAN Alliance . O-RAN: Towards an open and smart RAN [R ] . Alfter, Germany : O-RAN Alliance , 2018 .

ABETA S , KAWAHARA T , UMESH A , et al . O-RAN alliance standardization trends [J ] . NTT DOCOMO Technical Journal , 2019 , 15 ( 1 ): 38 - 45 .

QIN P , FU Y , ZHANG J , et al . DRL-based resource allocation and trajectory planning for NOMA-enabled multiUAV collaborative caching 6G network [J ] . IEEE Transactions on Vehicular Technology , 2024 , 73 ( 6 ): 8750 - 8764 .

WU M , GUO K , LI X , et al . Optimization design in RIS-assisted integrated satellite-UAV-served 6G IoT: A deep reinforcement learning approach [J ] . IEEE Internet Things Magazine , 2024 , 7 ( 1 ): 12 - 18 .

REZAZADEH F , ROY S , CHERGUI H , et al . Toward explainable reasoning in 6G: A proof of concept study on radio resource allocation [J ] . IEEE Open Journal of the Communications Society , 2024 , 5 : 6239 - 6260 .

KHAN M , ABDALLAH A , CELIK A , et al . Explainable and robust millimeter wave beam alignment for AI-native 6G networks [C ] // ICC 2025 - IEEE International Conference on Communications . Montreal, QC, Canada : IEEE , 2025 : 753 - 758 .

GIZZINI A K , MEDJAHDI Y , MABROUK M B . GRACE: Gradient-based XAI scheme for channel estimation in wireless communications [C ] // 2024 IEEE International Mediterranean Conference on Communications and Networking (MeditCom) . Madrid, Spain : IEEE , 2024 : 572 - 577 .

PHYU H P , NABOULSI D , STANICA R . Machine learning in network slicing—A survey [J ] . IEEE Access , 2023 , 11 : 39123 - 39153 .

RAHMAN M H , KARIM F , ZULKARNAIN , et al . Leveraging O-RAN SC AI/ML framework & non-RT RIC for AI-driven network slice QoS optimization [C ] // 2024 IEEE Globecom Workshops (GC Wkshps) . Cape Town, South Africa : IEEE , 2024 : 1 - 6 .

ROY S , CHERGUI H , VERIKOUKIS C . Toward bridging the FL performance-explainability tradeoff: A trustworthy 6G RAN slicing use-case [J ] . IEEE Transactions on Vehicular Technology , 2024 , 73 ( 7 ): 10529 - 10538 .

ROY S , REZAZADEH F , CHERGUI H , et al . Joint explainability and sensitivity-aware federated deep learning for transparent 6G RAN slicing [C ] // ICC 2023 - IEEE International Conference on Communications . Rome, Italy : IEEE , 2023 : 1238 - 1243 .

刘杨 , 彭木根 . 6G内生安全：体系结构与关键技术 [J ] . 电信科学 , 2020 , 36 ( 1 ): 11 - 20 .

CHATZIMILTIS S , SHOJAFAR M , MASHHADI M B , et al . AI-on-RAN for cyber defense: An XAI-LLM framework for interpretable anomaly detection [J ] . IEEE Transactions on Network Science and Engineering , 2025 .

PORAMBAGE P , PINOLA J , RUMESH Y , et al . XcARet: XAI based green security architecture for resilient open radio access networks in 6G [C ] // 2023 Joint European Conference on Networks and Communications & 6G Summit (EuCNC/6G Summit) . Gothenburg, Sweden : IEEE , 2023 : 699 - 704 .

KAUR N , GUPTA L . Enhancing IoT security in 6G environment with transparent AI: Leveraging XGBoost, SHAP and LIME [C ] // 2024 IEEE 10th International Conference on Network Softwarization (NetSoft) . Saint Louis, MO, USA : IEEE , 2024 : 180 - 184 .

MEHTA D , JAMEEL F , ALI A , et al . Quantum-assisted XAI-driven DL framework for FDI detection in connected autonomous electric vehicles underlying 6G [C ] // 2025 5th Intelligent Cybersecurity Conference (ICSC) . Tampa, FL, USA : IEEE , 2025 : 349 - 354 .

SHAH S D A , HAFEEZ M , SALAMA A , et al . Proactive AI-and-RAN workload orchestration in O-RAN architectures for 6G networks [J ] . IEEE Open Journal of the Communications Society , 2025 , 6 : 7939 - 7954 .

GUO J , WANG S . xTL: Reducing communication overhead with XAI-guided, semantic-aware DRL for urban traffic light control [C ] // 2025 IEEE Intelligent Vehicles Symposium (IV) . Cluj-Napoca, Romania : IEEE , 2025 : 2033 - 2038 .

MHATRE S , ADELANTADO F , RAMANTAS K , et al . Enhancing AI transparency: XRL-based resource management and RAN slicing for 6G O-RAN architecture [C ] // ICC 2025 - IEEE International Conference on Communications . Montreal, QC, Canada : IEEE , 2025 : 5755 - 5760 .

ŞENGÖZ N , YIĞIT T . Towards third generation AI: Explainable and interpretable AI [C ] // 2022 7th International Conference on Computer Science and Engineering (UBMK) . Diyarbakir, Turkey : IEEE , 2022 : 523 - 526 .

SUN H , ZHANG P , WANG Y , et al . Advancing 6G: Survey for explainable AI on communications and network slicing [J ] . IEEE Open Journal of the Communications Society , 2025 , 6 : 1372 - 1412 .

耿光磊 , 高博 , 熊轲 , 等 . 联邦学习赋能6G网络综述 [J ] . 物联网学报 , 2023 , 7 ( 2 ): 50 - 66 .

王首峰 , 郭建超 , 边森 . 原生AI融合网络数字孪生赋能下一代无线网络自治 [J ] . 中兴通讯技术 , 2025 , 31 ( 5 ): 30 - 36 .

张彤 , 任奕璟 , 闫实 , 等 . 人工智能驱动的6G网络：智慧内生 [J ] . 电信科学 , 2020 , 36 ( 9 ): 14 - 22 .

ABOUELMAATI D , ESFAHANI A , GOUDAZI S , et al . Empowering Next-Gen Networks: AI-Driven Autonomy in O-RAN and SON Architectures [J ] . IEEE Access , 2025 , 13 : 186903 - 186936 .

ANTWARG L , MILLER R M , SHAPIRA B , et al . Explaining Anomalies Detected by Autoencoders using Shapley Additive Explanations [J ] . Expert Systems with Applications , 2021 , 186 : 115736 .

BLANCO L , OVIEDO J A , GARCÍA-AVILÉS D , et al . UNITY-6G: UNified archITecture for Open RAN enabled distributed, scalable and sustainabilitYenhanced 6G networks [C ] // 2025 Joint European Conference on Networks and Communications & 6G Summit (EuCNC/6G Summit) . Poznan, Poland : IEEE , 2025 : 440 - 445 .

CORONA J , RODRIGUES P , ALMEIDA L , et al . From black box to transparency: Consistency and cost within XAI [C ] // 2024 IEEE Globecom Workshops (GC Wkshps) . Cape Town, South Africa : IEEE , 2024 : 1 - 6 .

LIANG X , WANG Q , AL-TAHMEESSCHI A , et al . Energy consumption of machine learning enhanced Open RAN: A comprehensive review [J ] . IEEE Access , 2024 , 12 : 81889 - 81910 .

RAGO A , FASCISTA A , PIRO G , et al . 6GxAID: Integrating 6G networks and eXplainable artificial intelligence for drone-based assistance in emergency situations [C ] // 2025 25th Anniversary International Conference on Transparent Optical Networks (ICTON) . Barcelona, Spain : IEEE , 2025 : 1 - 4 .

RENDA A , DUCANGE P , GALLO G , et al . XAI models for quality of experience prediction in wireless networks [C ] // 2021 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE) . Luxembourg, Luxembourg : IEEE , 2021 : 1 - 6 .

黄海松 , 朱云伟 , 张国章 . 人机协作技术的发展与应用研究综述 [J ] . 贵州大学学报(自然科学版) , 2025 , 42 ( 4 ): 1 - 8 .

姚丽菡 , 陈建辉 , 车艳 , 等 . 基于区块链和5G网络的物联网云联健康管理系统研究 [J ] . 贵州大学学报(自然科学版) , 2022 , 39 ( 3 ): 85 - 92 .

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

基于可信网格DSTM的6G分布式自治网络安全机制研究

面向5G-Advanced与6G的智能无线电接入网：关键标准技术与未来演进

面向6G空天地一体化系统的OTA测试方法与关键技术展望

基于标准空间光传送网协议的天地一体化网络构建研究

基于BYOL与实复域融合的动态噪声自动调制识别