面向边缘智能的协同推理方法研究综述

doi:10.3778/j.issn.1002-8331.2406-0040

摘要/Abstract

摘要： 随着边缘智能的兴起，协同推理技术通过云、边缘和终端设备之间的协作在提升智能应用的效率和性能方面取得了明显的进展。阐述了边缘智能的性能指标和应用场景及挑战，并以边缘智能的评级架构引出协同推理技术下的四种推理范式：端端协同、边端协同、边边协同和云边端协同推理。根据协同推理技术应用场景的局限性和差异性，对不同推理范式中协同推理技术的优势、局限性、原理及优化目标进行了全面分析对比。详细探讨了协同推理技术在不同应用场景下所解决的计算资源分配、推理时延优化和吞吐量优化等问题，指出了边缘智能中协同推理技术在隐私安全、通信服务资源管理、协同训练方面的挑战，并对其未来的发展趋势和研究方向进行了讨论，为该领域的研究提供参考和借鉴。

关键词: 边缘计算, 边缘智能, 协同推理, 机器学习

Abstract: With the development of edge intelligence, collaborative inference technology has made significant progress in enhancing the efficiency and performance of intelligent applications through collaboration among cloud, edge, and terminal devices. The performance metrics, application scenarios, and challenges of edge intelligence are outlined, introducing four inference paradigms under collaborative inference technology through the rating architecture of edge intelligence: end-to-end collaboration, edge-to-end collaboration, edge-to-edge collaboration, and cloud-edge-end collaboration. Based on the limitations and differences of application scenarios for collaborative inference technology, the advantages, limitations, principles, and optimization goals of collaborative inference technology in different inference paradigms are comprehensively analyzed and compared. The discussion delves into issues such as computational resource allocation, inference latency optimization, and throughput optimization solved by collaborative inference technology in different application scenarios. It also points out challenges in privacy security, communication service resource management, and collaborative training within edge intelligence. Future development trends and research directions are discussed, providing references and insights for research in this field.

Key words: edge computing, edge intelligence, collaborative inference, machine learning

赵婵婵, 吕飞, 石宝, 尉晓敏, 杨星辰, 岳效灿. 面向边缘智能的协同推理方法研究综述[J]. 计算机工程与应用, 2025, 61(3): 1-20.

ZHAO Chanchan, LYU Fei, SHI Bao, YU Xiaomin, YANG Xingchen, YUE Xiaocan. Review of Collaborative Inference Methods for Edge Intelligence[J]. Computer Engineering and Applications, 2025, 61(3): 1-20.

参考文献

[1] KHANG A, ABDULLAYEV V, SHAH V H A V. Advanced IoT technologies and applications in the industry 4.0 digital economy[M]. Boca Raton, FL: CRC Press, 2024.
[2] Cisco. Cisco annual internet report (2018?2023) white paper[R]. San Jose: Cisco, 2020.
[3] CARRIE M, DAVID R, MICHAEL S. The growth in connected IoT devicesis expected to generate 79.4?ZB of data in 2025, according to a new IDC forecast[EB/OL]. (2019-06-18) [2022-02-15]. https://www.businesswire.com/news/home/20190618005012/en/The-Growth-in-Connected-IoT-Devices-is-Expected-to-Generate-79.4ZB-of-Data-in-2025-According-to-a-New-IDC-Forecast.
[4] JIN H, JIA L, ZHOU Z. Boosting edge intelligence with collaborative cross-edge analytics[J]. IEEE Internet of Things Journal, 2021, 8(4): 2444-2458.
[5] 施巍松, 孙辉, 曹杰, 等. 边缘计算: 万物互联时代新型计算模型[J]. 计算机研究与发展, 2017, 54(5): 907-924.
SHI W S, SUN H, CAO J, et al. Edge computing—an emerging computing model for the Internet of everything era[J]. Journal of Computer Research and Development, 2017, 54(5): 907-924.
[6] BELKADI F, DHUIEB M A, AGUADO J V, et al. Intelligent assistant system as a context-aware decision-making support for the workers of the future[J]. Computers & Industrial Engineering, 2020, 139: 105732.
[7] 王睿, 王岩, 尹朴, 等. 面向边缘智能的协同训练研究进展[J]. 工程科学学报, 2023, 45(8): 1400-1416.
WANG R, WANG Y, YIN P, et al. Survey of edge-edge collaborative training for edge intelligence[J]. Chinese Journal of Engineering, 2023, 45(8): 1400-1416.
[8] 施巍松, 张星洲, 王一帆, 等. 边缘计算: 现状与展望[J]. 计算机研究与发展, 2019, 56(1): 69-89.
SHI W S, ZHANG X Z, WANG Y F, et al. Edge computing: state-of-the-art and future directions[J]. Journal of Computer Research and Development, 2019, 56(1): 69-89.
[9] PATEL M, NAUGHTON B, CHAN C, et al. Mobile-edge computing[R]. Mobile-Edge Computing (MEC) Industry Initiative, 2014.
[10] ZHANG X Z, LU S D, SHI W S. Research on collaborative computing technology in edge intelligence[J]. AI-View, 2019, 5: 55-67.
[11] ASIM M, WANG Y, WANG K Z, et al. A review on computational intelligence techniques in cloud and edge computing[J]. IEEE Transactions on Emerging Topics in Computational Intelligence, 2020, 4(6): 742-763.
[12] 莫梓嘉, 高志鹏, 苗东. 边缘智能: 人工智能向边缘分布式拓展的新触角[J]. 数据与计算发展前沿, 2020, 2(4): 16-27.
MO Z J, GAO Z P, MIAO D. Edge intelligence: a new exploration for artificial intelligence expanding to edge[J]. Frontiers of Data & Computing, 2020, 2(4): 16-27.
[13] WANG H, ZHANG Y, XIE J F, et al. Key technologies and applications of industrial Internet edge intelligence[C]//Proceedings of the 2023 IEEE Smart World Congress. Piscataway: IEEE, 2023: 1-6.
[14] NKENYEREYE L, BAEG K J, CHUNG W Y. Deep reinforcement learning for containerized edge intelligence inference request processing in IoT edge computing[J]. IEEE Transactions on Services Computing, 2023, 16(6): 4328-4344.
[15] SATYANARAYANAN M, BAHL P, CACERES R, et al. The case for VM-based cloudlets in mobile computing[J]. IEEE Pervasive Computing, 2009, 8(4): 14-23.
[16] JIANG K, SUN C, ZHOU H, et al. Intelligence-empowered mobile edge computing: framework, issues, implementation, and outlook[J]. IEEE Network, 2021, 35(5): 74-82.
[17] 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.
[18] 莫梓嘉. 面向边缘智能的深度卷积神经网络训练与推理优化方法研究[D]. 北京: 北京邮电大学, 2023.
MO Z J. Research on training and reasoning optimization method of deep convolution neural network oriented to edge intelligence[D]. Beijing: Beijing University of Posts and Telecommunications, 2023.
[19] SANKAR H, SUBRAMANIYASWAMY V, VIJAYAKUMAR V, et al. Intelligent sentiment analysis approach using edge computing-based deep learning technique[J]. Software: Practice and Experience, 2020, 50(5): 645-657.
[20] AGGARWAL S, GOSWAMI D, HOODA M, et al. Recommendation systems for interactive multimedia entertainment[M]//Data visualization and knowledge engineering. Cham: Springer, 2019: 23-48.
[21] NASIR M, MUHAMMAD K, ULLAH A, et al. Enabling automation and edge intelligence over resource constraint IoT devices for smart home[J]. Neurocomputing, 2022, 491: 494-506.
[22] ZHU S, OTA K, DONG M X. Energy-efficient artificial intelligence of things with intelligent edge[J]. IEEE Internet of Things Journal, 2022, 9(10): 7525-7532.
[23] ZHANG J L, ZHAO Y C, WANG J Y, et al. FedMEC: improving efficiency of differentially private federated learning via mobile edge computing[J]. Mobile Networks and Applications, 2020, 25(6): 2421-2433.
[24] DONG W, YANG Q, LI W, et al. Machine-learning-based real-time economic dispatch in islanding microgrids in a cloud-edge computing environment[J]. IEEE Internet of Things Journal, 2021, 8(17): 13703-13711.
[25] PELTONEN E, BENNIS M, CAPOBIANCO M, et al. 6G white paper on edge intelligence[J]. arXiv:2004.14850, 2020.
[26] BUI K N, JUNG J J. Computational negotiation-based edge analytics for smart objects[J]. Information Sciences, 2019, 480: 222-236.
[27] WANG X D, GARG S, LIN H, et al. Toward accurate anomaly detection in industrial Internet of Things using hierarchical federated learning[J]. IEEE Internet of Things Journal, 2022, 9(10): 7110-7119.
[28] BIBRI S E, KROGSTIE J, KABOLI A, et al. Smarter eco-cities and their leading-edge artificial intelligence of things solutions for environmental sustainability: a comprehensive systematic review[J]. Environmental Science and Ecotechnology, 2024, 19: 100330.
[29] GONG T Y, ZHU L, YU F R, et al. Edge intelligence in intelligent transportation systems: a survey[J]. IEEE Transactions on Intelligent Transportation Systems, 2023, 24(9): 8919-8944.
[30] AAZAM M, ZEADALLY S, FLUSHING E F. Task offloading in edge computing for machine learning-based smart healthcare[J]. Computer Networks, 2021, 191: 108019.
[31] SIVABALAN S, MINU R. Edge AI for industrial IoT applications[M]//Applied edge AI. Boca Raton: Auerbach Publications, 2022: 147-170.
[32] LV Z H, CHEN D L, LOU R R, et al. RETRACTED: intelligent edge computing based on machine learning for smart city[J]. Future Generation Computer Systems, 2021, 115: 90-99.
[33] HOSSEINZADEH M, HEMMATI A, RAHMANI A M. Clustering for smart cities in the Internet of things: a review[J]. Cluster Computing, 2022, 25(6): 4097-4127.
[34] LIAN Y X, QIAN L, DING L H, et al. Semantic fusion infrastructure for unmanned vehicle system based on cooperative 5G MEC[C]//Proceedings of the 2020 IEEE/CIC International Conference on Communications in China. Piscataway: IEEE, 2020: 202-207.
[35] HEMMATI A, RAHMANI A M. Internet of medical things in the COVID-19 era: a systematic literature review[J]. Sustainability, 2022, 14(19): 12637.
[36] MISRA S, KUMAR TYAGI A, PIURI V, et al. Artificial intelligence for cloud and edge computing[M]. Cham: Springer, 2022.
[37] LABBA C, BEN ATITALLAH R, BOYER A. Combining artificial intelligence and edge computing to reshape distance education (case study: K-12 learners)[M]//Artificial intelligence in education. Cham: Springer, 2022: 218-230.
[38] LALAPURA V S, AMUDHA J, SATHEESH H S. Recurrent neural networks for edge intelligence: a survey[J]. ACM Computing Surveys, 2021, 54(4): 91.
[39] DEBAUCHE O, MAHMOUDI S, MAHMOUDI S A, et al. Edge computing and artificial intelligence for real-time poultry monitoring[J]. Procedia Computer Science, 2020, 175: 534-541.
[40] MAKKAR A, GHOSH U, RAWAT D B, et al. FedLearnSP: preserving privacy and security using federated learning and edge computing[J]. IEEE Consumer Electronics Magazine, 2022, 11(2): 21-27.
[41] LETAIEF K B, SHI Y M, LU J M, et al. Edge artificial intelligence for 6G: vision, enabling technologies, and applications[J]. IEEE Journal on Selected Areas in Communications, 2022, 40(1): 5-36.
[42] REN W Q, QU Y B, DONG C, et al. A survey on collaborative DNN inference for edge intelligence[J]. Machine Intelligence Research, 2023, 20(3): 370-395.
[43] LIU A, SWAYAMDIPTA S, SMITH N A, et al. WANLI: worker and AI collaboration for natural language inference dataset creation[J]. arXiv:2201.05955, 2022.
[44] ZENG L K, CHEN X, ZHOU Z, et al. CoEdge: cooperative DNN inference with adaptive workload partitioning over heterogeneous edge devices[J]. IEEE/ACM Transactions on Networking, 2021, 29(2): 595-608.
[45] ECCLES B J, RODGERS P, KILPATRICK P, et al. DNNShifter: an efficient DNN pruning system for edge computing[J]. Future Generation Computer Systems, 2024, 152: 43-54.
[46] SHLEZINGER N, FARHAN E, MORGENSTERN H, et al. Collaborative inference via ensembles on the edge[C]//Proceedings of the 2021 IEEE International Conference on Acoustics, Speech and Signal Processing. Piscataway: IEEE, 2021: 8478-8482.
[47] RONG G P, XU Y C, TONG X X, et al. An edge-cloud collaborative computing platform for building AIoT applications efficiently[J]. Journal of Cloud Computing, 2021, 10(1): 36.
[48] HADIDI R, CAO J S, RYOO M S, et al. Toward collaborative inferencing of deep neural networks on Internet-of-things devices[J]. IEEE Internet of Things Journal, 2020, 7(6): 4950-4960.
[49] HUANG Y K, QIAO X Q, DUSTDAR S, et al. Toward decentralized and collaborative deep learning inference for intelligent IoT devices[J]. IEEE Network, 2022, 36(1): 59-68.
[50] FENG X Y, LI L J, WANG T L, et al. CoBC: a blockchain-based collaborative inference system for Internet of Things[J]. IEEE Internet of Things Journal, 2023, 10: 21389-21400.
[51] LI J N, WU J, LI J H, et al. Blockchain-based trust edge knowledge inference of multi-robot systems for collaborative tasks[J]. IEEE Communications Magazine, 2021, 59(7): 94-100.
[52] CHEN Y F, YU Z Q, MWASE C, et al. Self-aware collaborative edge inference with embedded devices for task-oriented IIoT[C]//Proceedings of the 2023 IEEE 98th Vehicular Technology Conference. Piscataway: IEEE, 2023: 1-5.
[53] XIAO Y L, XIAO L, WAN K P, et al. Reinforcement learning based energy-efficient collaborative inference for mobile edge computing[J]. IEEE Transactions on Communications, 2023, 71(2): 864-876.
[54] LIU K, XIAO K, DAI P L, et al. Fog computing empowered data dissemination in software defined heterogeneous VANETs[J]. IEEE Transactions on Mobile Computing, 2021, 20(11): 3181-3193.
[55] LIU K, LIU C H, YAN G Z, et al. Accelerating DNN inference with reliability guarantee in vehicular edge computing[J]. IEEE/ACM Transactions on Networking, 2023, 31(6): 3238-3253.
[56] 林峰, 李华, 罗铖文, 等. 车联网中面向依赖任务的联合计算卸载及资源分配算法[J]. 重庆邮电大学学报(自然科学版), 2023, 35(5): 826-837.
LIN F, LI H, LUO C W, et al. Joint computing offloading and resource allocation algorithm for dependent tasks in Internet of vehicles[J]. Journal of Chongqing University of Posts and Telecommunications (Natural Science Edition), 2023, 35(5): 826-837.
[57] QU Y B, DAI H P, WANG H C, et al. Service provisioning for UAV-enabled mobile edge computing[J]. IEEE Journal on Selected Areas in Communications, 2021, 39(11): 3287-3305.
[58] LI Y, QU Y B, DONG C, et al. Dynamic DNN model switching for collaborative edge intelligence in UAV swarm[C]//Proceedings of the 2023 International Conference on Wireless Communications and Signal Processing. Piscataway: IEEE, 2023: 923-929.
[59] REN W Q, QU Y B, QIN Z, et al. Energy-efficient collaborative DNN inference in UAV swarm[C]//Proceedings of the 2023 9th International Conference on Big Data Computing and Communications. Piscataway: IEEE, 2023: 195-202.
[60] YAO S C, LI J Y, LIU D X, et al. Deep compressive offloading: speeding up neural network inference by trading edge computation for network latency[C]//Proceedings of the 18th Conference on Embedded Networked Sensor Systems. New York: ACM, 2020: 476-488.
[61] MATSUBARA Y, CALLEGARO D, SINGH S, et al. BottleFit: learning compressed representations in deep neural networks for effective and efficient split computing[C]//Proceedings of the 2022 IEEE 23rd International Symposium on a World of Wireless, Mobile and Multimedia Networks. Piscataway: IEEE, 2022: 337-346.
[62] HU D Y, KRISHNAMACHARI B. Fast and accurate streaming CNN inference via communication compression on the edge[C]//Proceedings of the 2020 IEEE/ACM Fifth International Conference on Internet-of-Things Design and Implementation. Piscataway: IEEE, 2020: 157-163.
[63] HUANG X F, ZHOU S. Dynamic compression ratio selection for edge inference systems with hard deadlines[J]. IEEE Internet of Things Journal, 2020, 7(9): 8800-8810.
[64] YANG Y B, MANDT S, THEIS L. An introduction to neural data compression[J]. Foundations and Trends? in Computer Graphics and Vision, 2023, 15(2): 113-200.
[65] CHOI J, HAN B. Task-aware quantization network for JPEG image compression[C]//Proceedings of 2020 European Conference on Computer Vision. Cham: Springer, 2020: 309-324.
[66] MATSUBARA Y, YANG R H, LEVORATO M, et al. SC2 benchmark: supervised compression for split computing[J]. arXiv:2203.08875, 2022.
[67] MATSUBARA Y, YANG R H, LEVORATO M, et al. Supervised compression for resource-constrained edge computing systems[C]//Proceedings of the 2022 IEEE/CVF Winter Conference on Applications of Computer Vision. Piscataway: IEEE, 2022: 923-933.
[68] LI N, IOSIFIDIS A, ZHANG Q. Attention-based feature compression for CNN inference offloading in edge computing[C]//Proceedings of the IEEE International Conference on Communications. Piscataway: IEEE, 2023: 967-972.
[69] 郭永安, 周金粮, 王宇翱. 基于边端协同的CNN推理加速框架[J]. 南京邮电大学学报 (自然科学版), 2023, 43(3): 68-77.
GUO Y A, ZHOU J L, WANG Y A. A CNN inference acceleration framework based on edge-end collaboration[J]. Journal of Nanjing University of Posts and Telecommunications (Natural Science Edition), 2023, 43(3): 68-77.
[70] 钟李翔. 边缘智能中基于模型分割的推理任务调度策略研究[D]. 合肥: 合肥工业大学, 2022.
ZHONG L X. Research on reasoning task scheduling strategy based on model segmentation in edge intelligence[D]. Hefei: Hefei University of Technology, 2022.
[71] SHAO J W, ZHANG H W, MAO Y Y, et al. Branchy-GNN: a device-edge co-inference framework for efficient point cloud processing[C]//Proceedings of the 2021 IEEE International Conference on Acoustics, Speech and Signal Processing. Piscataway: IEEE, 2021: 8488-8492.
[72] LIU Z Y, LAN Q, HUANG K B. Resource allocation for multiuser edge inference with batching and early exiting[J]. IEEE Journal on Selected Areas in Communications, 2023, 41(4): 1186-1200.
[73] YANG X, CHEN D Z, QI Q, et al. Adaptive DNN surgery for selfish inference acceleration with on-demand edge resource[J]. arXiv:2306.12185, 2023.
[74] FRESA A, CHAMPATI J P V, FRESA A, et al. An offloading algorithm for maximizing inference accuracy on edge device in an edge intelligence system[C]//Proceedings of the 25th International ACM Conference on Modeling Analysis and Simulation of Wireless and Mobile Systems. New York: ACM, 2022: 15-23.
[75] WANG Q, LI Z Y, NAI K, et al. Dynamic resource allocation for jointing vehicle-edge deep neural network inference[J]. Journal of Systems Architecture, 2021, 117: 102133.
[76] YANG C Y, KUO J J, SHEU J P, et al. Cooperative distributed deep neural network deployment with edge computing[C]//Proceedings of the IEEE International Conference on Communications. Piscataway: IEEE, 2021: 1-6.
[77] MOHAMMED T, JOE-WONG C, BABBAR R, et al. Distributed inference acceleration with adaptive DNN partitioning and offloading[C]//Proceedings of the IEEE Conference on Computer Communications. Piscataway: IEEE, 2020: 854-863.
[78] LI P Z, KOYUNCU E, SEFEROGLU H. Adaptive and resilient model-distributed inference in edge computing systems[J]. IEEE Open Journal of the Communications Society, 2023, 4: 1263-1273.
[79] HU C H, LI B C. Distributed inference with deep learning models across heterogeneous edge devices[C]//Proceedings of the IEEE Conference on Computer Communications. Piscataway: IEEE, 2022: 330-339.
[80] WU L T, GAO G L, YU J, et al. PDD: partitioning DAG-topology DNNs for streaming tasks[J]. IEEE Internet of Things Journal, 2024, 11(6): 9258-9268.
[81] FELTIN T, MARCHó L, CORDERO-FUERTES J A, et al. DNN partitioning for inference throughput acceleration at the edge[J]. IEEE Access, 2023, 11: 52236-52249.
[82] XU Y Z, MOHAMMED T, DI FRANCESCO M, et al. Distributed assignment with load balancing for DNN inference at the edge[J]. IEEE Internet of Things Journal, 2023, 10(2): 1053-1065.
[83] LI N, IOSIFIDIS A, ZHANG Q. Collaborative edge computing for distributed CNN inference acceleration using receptive field-based segmentation[J]. Computer Networks, 2022, 214: 109150.
[84] GUO X T, PIMENTEL A D, STEFANOV T. Automated exploration and implementation of distributed CNN inference at the edge[J]. IEEE Internet of Things Journal, 2023, 10(7): 5843-5858.
[85] WAN X L, JI T X, GUAN X J, et al. Optimal DNN inference delay minimization for chain-structured roadside edge networks[J]. IEEE Transactions on Vehicular Technology, 2023, 72(12): 16731-16736.
[86] 蒋伟进, 孙永霞, 朱昊冉, 等. 边云协同计算下基于ST-GCN的监控视频行为识别机制[J]. 南京大学学报(自然科学), 2022, 58(1): 163-174.
JIANG W J, SUN Y X, ZHU H R, et al. Surveillance video behavior recognition mechanism based on ST-GCN under edge-cloud collaborative computing[J]. Journal of Nanjing University (Natural Science), 2022, 58(1): 163-174.
[87] CUI K, ZHANG G T, ZHANG F, et al. Facial expression recognition system on a distributed edge-cloud infrastructure[C]//Proceedings of the 2022 IEEE Cloud Summit. Piscataway: IEEE, 2022: 51-56.
[88] CHEN C, LIU B, WAN S H, et al. An edge traffic flow detection scheme based on deep learning in an intelligent transportation system[J]. IEEE Transactions on Intelligent Transportation Systems, 2021, 22(3): 1840-1852.
[89] ZHANG W T, YANG D, PENG H X, et al. Deep reinforcement learning based resource management for DNN inference in industrial IoT[J]. IEEE Transactions on Vehicular Technology, 2021, 70(8): 7605-7618.
[90] HAO Z W, XU G Y, LUO Y, et al. Multi-agent collaborative inference via DNN decoupling: intermediate feature compression and edge learning[J]. IEEE Transactions on Mobile Computing, 2023, 22(10): 6041-6055.
[91] XUE M, WU H M, PENG G, et al. DDPQN: an efficient DNN offloading strategy in local-edge-cloud collaborative environments[J]. IEEE Transactions on Services Computing, 2022, 15(2): 640-655.
[92] QI H M, REN F, WANG L L, et al. Multi-compression scale DNN inference acceleration based on cloud-edge-end collaboration[J]. ACM Transactions on Embedded Computing Systems, 2024, 23(1): 1-25.
[93] YANG L, SHEN X Y, ZHONG C Y, et al. On-demand inference acceleration for directed acyclic graph neural networks over edge-cloud collaboration[J]. Journal of Parallel and Distributed Computing, 2023, 171: 79-87.
[94] ZHAO P, YU J, ZHANG H L, et al. How to securely outsource finding the min-cut of undirected edge-weighted graphs[J]. IEEE Transactions on Information Forensics and Security, 2019, 15: 315-328.
[95] NAIK S， PATIL S. Brain tumor classification using SLIC segmentation with superpixel fusion, GoogleNet, and linear neighborhood semantic segmentation[J]. Journal of Scientific & Industrial Research, 2023, 82(2): 255.
[96] LIU G Z, DAI F, XU X L, et al. An adaptive DNN inference acceleration framework with end-edge-cloud collaborative computing[J]. Future Generation Computer Systems, 2023, 140: 422-435.
[97] XUE M, WU H M, LI R D, et al. EosDNN: an efficient offloading scheme for DNN inference acceleration in local-edge-cloud collaborative environments[J]. IEEE Transactions on Green Communications and Networking, 2022, 6(1): 248-264.
[98] YANG S S, ZHANG Z H, ZHAO C, et al. CNNPC: end-edge-cloud collaborative CNN inference with joint model partition and compression[J]. IEEE Transactions on Parallel and Distributed Systems, 2022, 33(12): 4039-4056.
[99] CHEHREHZAD M, KECIBAS G, BESIROVA C, et al. Tool wear prediction through AI-assisted digital shadow using industrial edge device[J]. Journal of Manufacturing Processes, 2024, 113: 117-130.
[100] PAGLIARI D J, CHIARO R, MACII E, et al. CRIME: input-dependent collaborative inference for recurrent neural networks[J]. IEEE Transactions on Computers, 2021, 70(10): 1626-1639.
[101] QIU T, CHI J C, ZHOU X B, et al. Edge computing in industrial Internet of Things: architecture, advances and challenges[J]. IEEE Communications Surveys & Tutorials, 2020, 22(4): 2462-2488.
[102] JIANG M Z, WU T H, WANG Z, et al. A multi-intersection vehicular cooperative control based on end-edge-cloud computing[J]. IEEE Transactions on Vehicular Technology, 2022, 71(3): 2459-2471.
[103] ZHANG Y K, CHEN D K, KUNDU S, et al. C2PI: an efficient crypto-clear two-party neural network private inference[C]//Proceedings of the 2023 60th ACM/IEEE Design Automation Conference. Piscataway: IEEE, 2023: 1-6.
[104] LI J Y, LIAO G C, CHEN L, et al. Roulette: a semantic privacy-preserving device-edge collaborative inference framework for deep learning classification tasks[J]. IEEE Transactions on Mobile Computing, 2024, 23(5): 5494-5510.
[105] YANG R K, MA J F, ZHANG J Y, et al. Practical feature inference attack in vertical federated learning during prediction in artificial Internet of Things[J]. IEEE Internet of Things Journal, 2024, 11(1): 5-16.
[106] SHUVO M M H, ISLAM S K, CHENG J L, et al. Efficient acceleration of deep learning inference on resource-constrained edge devices: a review[J]. Proceedings of the IEEE, 2023, 111(1): 42-91.
[107] XU D, LI T, LI Y, et al. Edge intelligence: empowering inteli-gence to the edge of network[J]. Proceedings of the IEEE, 2021, 109(11): 1778-1837.
[108] 司强毅, 陈祎鹏, 杨哲. 基于缓存优化的移动边缘计算资源分配策略[J]. 计算机应用研究, 2024, 41(3): 818-823.
SI Q Y, CHEN Y P, YANG Z. Resource allocation strategy for mobile edge computing based on cache optimization[J]. Application Research of Computers, 2024, 41(3): 818-823.
[109] 王云迪. 用于端-边协同推理的DNN动态快速划分策略研究[D]. 长春: 吉林大学, 2023.
WANG Y D. Research on dynamic fast partition strategy of DNN for end-edge collaborative reasoning[D]. Chang-chun: Jilin University, 2023.
[110] 路松峰, 屠向阳, 周军龙, 等. 云边端协同的增量联邦学习算法[J]. 华中科技大学学报 (自然科学版), 2023, 51(10): 12-18.
LU S F, TU X Y, ZHOU J L, et al. Incremental federated learning algorithm for cloud-edge-device collaboration[J]. Journal of Huazhong University of Science and Technology (Natural Science Edition), 2023, 51(10): 12-18.