智能协同计算：技术演进、前沿挑战与未来图景

Intelligent collaborative computing: Technical evolution, frontier challenges and future prospects

摘要

面向无人化、智能化现场业务环境中的智能无人体系协同作业，针对异构算力分散、模型协同困难、信息保障低效等问题，梳理了智能协同计算领域的研究进展与技术体系。着眼智能协同计算技术从单元到体系的多层内涵，该文构建了一个包含“核心技术体系−多目标优化−领域应用与价值”的三维综述框架。通过分析，归纳出智能算力效能增强、智能模型计算协同、信息智能融合编织三大核心技术方向，系统阐述了各方向的技术内涵、研究范畴与关键挑战；分析了面向时延、能耗、精度、可靠性等维度的多目标优化策略；同时从军事作战、应急管理、城市治理、工业生产等典型领域分析其应用与价值。利用该三维分析框架，阐述了智能协同计算技术的演进规律，指出了其在核心方法、多目标优化、领域应用与价值释放方面面临的技术挑战和未来研究方向，为解决现有方法的问题提供参考，有助于智能协同计算技术的进一步发展。

Abstract

Focusing on intelligent unmanned system collaborations in unmanned and intelligent on-site business environments, this paper addresses dispersed heterogeneous computing power, difficult model collaboration, and inefficient information support, and reviews research progress and the technical system of intelligent collaborative computing. A three-dimensional review framework of “core technology system, multi-objective optimization, and domain applications and value” is constructed. Three core technical directions are summarized: intelligent computing power efficiency enhancement, intelligent model computing collaboration, and intelligent information fusion and weaving. The technical connotations, research scope, and key challenges of each direction are systematically elaborated. Multi-objective optimization strategies targeting latency, energy consumption, accuracy, and reliability are analyzed. Domain applications and value are further examined in military operations, emergency management, urban governance, and industrial production. This framework describes the evolutionary patterns of intelligent collaborative computing and identifies technical challenges and future directions in core methods, multi-objective optimization, and domain applications and value, providing a reference for its further development.

关键词

智能协同计算 / 异构算力 / 模型协同 / 智能信息融合编织 / 边缘智能 / 多目标优化

Key words

intelligent collaborative computing / heterogeneous computing / model collaboration / intelligent information fusion and weaving / edge intelligence / multi-objective optimization

参考文献

[1] Shi Weisong, Cao Jie, Zhang Quan, et al. Edge computing: Vision and challenges[J].IEEE Internet of Things Journal, 2016, 3(5):637-646.

[2] 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.

[3] Shi Weisong, Zhang Xingzhou, Wang Yifan, et al. Edge computing: State-of-the-art and future directions[J].Journal of Computer Research and Development, 2019, 56(1):69-89. (in Chinese)

[4] Satyanarayanan M. The emergence of edge computing[J].Computer, 2017, 50(1):30-39.

[5] Ren Ju, Zhang Deyu, He Shiwen, et al. A survey on end-edge-cloud orchestrated network computing paradigms: Transparent computing, mobile edge computing, fog computing, and cloudlet[J].ACM Computing Surveys, 2020, 52(6):125.

[6] Bonomi F, Milito R, Zhu Jiang, et al. Fog computing and its role in the internet of things[C]//Proceedings of the First Edition of the MCC Workshop on Mobile Cloud Computing. Helsinki: ACM, 2012:13-16.

[7] He Kaiming, Zhang Xiangyu, Ren Shaoqing, et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016:770-778.

[8] Howard A G, Zhu Menglong, Chen Bo, et al. MobileNets: Efficient convolutional neural networks for mobile vision applications[PP/OL]. V1.arXiv (2017-04-17)[2026-03-01].https://arxiv.org/abs/1704.04861.

[9] McMahan B, Moore E, Ramage D, et al. Communication-efficient learning of deep networks from decentralized data[C]//Proceedings of the 20th International Conference on Artificial Intelligence and Statistics. Fort Lauderdale: PMLR, 2017:1273-1282.

[10] Vepakomma P, Gupta O, Swedish T, et al. Split learning for health: Distributed deep learning without sharing raw patient data[PP/OL]. V1.arXiv (2018-12-03)[2026-03-01].https://arxiv.org/abs/1812.00564.

[11] Konečný J, McMahan H B, Yu F X, et al. Federated learning: Strategies for improving communication efficiency[PP/OL]. V1.arXiv (2016-10-18)[2026-03-01].https://arxiv.org/abs/1610.05492.

[12] 夏元清, 王晁, 高润泽, 等. 云网边端协同云控制研究进展及挑战[J].信息与控制, 2024, 53(3):273-286.

[13] Xia Yuanqing, Wang Chao, Gao Runze, et al. Progress and challenges of cloud-network-edge-end collaborative cloud control[J].Information and Control, 2024, 53(3):273-286. (in Chinese)

[14] 唐卓, 蒋冰婷, 张嘉鹏, 等. 算力网络调度基础理论与关键技术现状及展望[J].中国科学基金, 2025, 39(2):240-249.

[15] Tang Zhuo, Jiang Bingting, Zhang Jiapeng, et al. The foundation theory and key technologies of computing first network scheduling: Present situation and prospects[J].Bulletin of National Natural Science Foundation of China, 2025, 39(2):240-249. (in Chinese)

[16] 周俊龙, 侯祥鹏, 兰兰, 等. 云边端协同计算与智能[J].嵌入式技术与智能系统, 2025, 2(4):261-267.

[17] Zhou Junlong, Hou Xiangpeng, Lan Lan , et al. Cloud-edge-end collaborative computing and intelligence[J].Embedded Technology and Intelligent Systems, 2025, 2(4):261-267. (in Chinese)

[18] 王睿, 齐建鹏, 陈亮, 等. 面向边缘智能的协同推理综述[J].计算机研究与发展, 2023, 60(2):398-414.

[19] Wang Rui, Qi Jianpeng, Chen Liang, et al. Survey of collaborative inference for edge intelligence[J].Journal of Computer Research and Development, 2023, 60(2):398-414. (in Chinese)

[20] 赵婵婵, 吕飞, 石宝, 等. 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.

[21] Zhao Chanchan, Lyu Fei, Shi Bao, et al. Review of collaborative inference methods for edge intelligence[J].Computer Engineering and Applications, 2025, 61(3):1-20. (in Chinese)

[22] Han Song, Pool J, Tran J, et al. Learning both weights and connections for efficient neural networks[C]//Proceedings of the 29th International Conference on Neural Information Processing Systems. Montreal: MIT Press, 2015:1135-1143.

[23] Liu Hanxiao, Simonyan K, Yang Yiming. DARTS: Differentiable architecture search[C]//7th International Conference on Learning Representations. New Orleans: OpenReview.net, 2019:1-13.

[24] Pham H, Guan M Y, Zoph B, et al. Efficient neural architecture search via parameters sharing[C]//Proceedings of the 35th International Conference on Machine Learning. Stockholm: PMLR, 2018:4095-4104.

[25] Mao Yuyi, Zhang Jun, Song S H, et al. Stochastic joint radio and computational resource management for multi-user mobile-edge computing systems[J].IEEE Transactions on Wireless Communications, 2017, 16(9):5994-6009.

[26] You C S, Huang K B, Chae H J, et al. Energy-efficient resource allocation for mobile-edge computation offloading[J].IEEE Transactions on Wireless Communications, 2017, 16(3):1397-1411.

[27] Kang Yiping, Hauswald J, Gao Cao, et al. Neurosurgeon: Collaborative intelligence between the cloud and mobile edge[J].ACM SIGARCH Computer Architecture News, 2017, 45(1):615-629.

[28] Hu C, Bao W, Wang D, et al. Dynamic adaptive DNN surgery for inference acceleration on the edge[C]//IEEE INFOCOM 2019-IEEE Conference on Computer Communications. Paris: IEEE, 2019:1423-1431.

[29] 罗宇哲, 李玲, 侯朋朋, 等. 面向 AIoT 的协同智能综述[J].计算机研究与发展, 2025, 62(1):179-206.

[30] Luo Yuzhe, Li Ling, Hou Pengpeng, et al. Survey of AIoT-oriented collaborative intelligence[J].Journal of Computer Research and Development, 2025, 62(1):179-206. (in Chinese)

[31] Wang Yingchao, Yang Chen, Lan Shulin, et al. End-edge-cloud collaborative computing for deep learning: A comprehensive survey[J].IEEE Communications Surveys & Tutorials, 2024, 26(4):2647-2683.

[32] Park J, Samarakoon S, Bennis M, et al. Wireless network intelligence at the edge[J].Proceedings of the IEEE, 2019, 107(11):2204-2239.

[33] Ji Shaoxiong, Pan Shirui, Cambria E, et al. A survey on knowledge graphs: Representation, acquisition, and applications[J].IEEE Transactions on Neural Networks and Learning Systems, 2022, 33(2):494-514.

[34] Hogan A, Blomqvist E, Cochez M, et al. Knowledge graphs[J].ACM Computing Surveys, 2022, 54(4):71.

[35] 徐伟华, 黄旭东, 蔡可. 基于粒计算的多源信息融合方法综述[J].数据采集与处理, 2023, 38(2):245-261.

[36] Xu Weihua, Huang Xudong, Cai Ke. Review of multi-source information fusion methods based on granular computing[J].Journal of Data Acquisition and Processing, 2023, 38(2):245-261. (in Chinese)

[37] Khaleghi B, Khamis A, Karray F O, et al. Multisensor data fusion: A review of the state-of-the-art[J].Information Fusion, 2013, 14(1):28-44.

[38] Hall D L, Llinas J. Handbook of multisensor data fusion[M]. Boca Raton: CRC Press,2001.

[39] Lim W Y B, Luong N C, Hoang D T, et al. Federated learning in mobile edge networks: A comprehensive survey[J].IEEE Communications Surveys & Tutorials, 2020, 22(3):2031-2063.

[40] Li Tian, Sahu A K, Talwalkar A, et al. Federated learning: Challenges, methods, and future directions[J].IEEE Signal Processing Magazine, 2020, 37(3):50-60.

[41] Cheng Yu, Wang Duo, Zhou Pan, et al. Model compression and acceleration for deep neural networks: The principles, progress, and challenges[J].IEEE Signal Processing Magazine, 2018, 35(1):126-136.

[42] Jacob B, Kligys S, Chen Bo, et al. Quantization and training of neural networks for efficient integer-arithmetic-only inference[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018:2704-2713.

[43] Hinton G, Vinyals O, Dean J. Distilling the knowledge in a neural network[PP/OL]. V1.arXiv (2015-03-09)[2026-03-01].https://arxiv.org/abs/1503.02531.

[44] Zhou Zhi, Chen Xu, Li En, et al. Edge intelligence: paving the last mile of artificial intelligence with edge computing[J].Proceedings of the IEEE, 2019, 107(8):1738-1762.

[45] Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems. Long Beach: Curran Associates Inc., 2017:6000-6010.

[46] Abbas N, Zhang Yan, Taherkordi A, et al. Mobile edge computing: A survey[J].IEEE Internet of Things Journal, 2018, 5(1):450-465.

[47] Deb K, Pratap A, Agarwal S, et al. A fast and elitist multiobjective genetic algorithm: NSGA-II[J].IEEE Transactions on Evolutionary Computation, 2002, 6(2):182-197.

[48] Zhang Qingfu, Li Hui. MOEA/D: A multiobjective evolutionary algorithm based on decomposition[J].IEEE Transactions on Evolutionary Computation, 2007, 11(6):712-731.

[49] Liu Songbai, Lin Qiuzhen, Li Jianqiang, et al. A survey on learnable evolutionary algorithms for scalable multiobjective optimization[J].IEEE Transactions on Evolutionary Computation, 2023, 27(6):1941-1961.

[50] Shi Yuanming, Yang Kai, Jiang Tao, et al. Communication-efficient edge AI: Algorithms and systems[J].IEEE Communications Surveys & Tutorials, 2020, 22(4):2167-2191.

[51] Jia Ninghui, Qu Zhihao, Ye Baoliu, et al. A comprehensive survey on communication-efficient federated learning in mobile edge environments[J].IEEE Communications Surveys & Tutorials, 2025, 27(6):3710-3741.

[52] Kim S W. Cooperative federated learning-based task offloading scheme for tactical edge networks[J].IEEE Access, 2021, 9:145739-145747.

[53] Chen L, Englund C. Every second counts: Integrating edge computing and service oriented architecture for automatic emergency management[J].Journal of Advanced Transportation, 2018, 2018:1-13.

[54] Mach P, Becvar Z. Mobile edge computing: A survey on architecture and computation offloading[J].IEEE Communications Surveys & Tutorials, 2017, 19(3):1628-1656.

[55] Nain G, Pattanaik K K, Sharma G K. Towards edge computing in intelligent manufacturing: past, present and future[J].Journal of Manufacturing Systems, 2022, 62:588-611.

[56] Shafiee A, Nag A, Muralimanohar N, et al. ISAAC: A convolutional neural network accelerator with in-situ analog arithmetic in crossbars[J].ACM SIGARCH Computer Architecture News, 2016, 44(3):14-26.

[57] Touvron H, Lavril T, Izacard G, et al. LLaMA: Open and efficient foundation language models[PP/OL]. V1.arXiv (2023-02-27)[2026-03-01].https://arxiv.org/abs/2302.13971.

[58] Tao Fei, Zhang He, Liu Ang, et al. Digital twin in industry: State-of-the-art[J].IEEE Transactions on Industrial Informatics, 2019, 15(4):2405-2415.

[59] Khan L U, Saad W, Niyato D, et al. Digital-twin-enabled 6G: Vision, architectural trends, and future directions[J].IEEE Communications Magazine, 2022, 60(1):74-80.

[60] Kairouz P, McMahan H B, Avent B. Advances and open problems in federated learning[J].Foundations and Trends in Machine Learning, 2021, 14(1/2):1-210.

[61] Sabt M, Achemlal M, Bouabdallah A. Trusted execution environment: What it is, and what it is not[C]//2015 IEEE Trustcom/BigDataSE/ISPA. Helsinki: IEEE, 2015:57-64.

基金资助

国家自然科学基金(92582204, 62501116)