{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T01:39:40Z","timestamp":1783561180179,"version":"3.55.0"},"reference-count":28,"publisher":"MDPI AG","issue":"13","license":[{"start":{"date-parts":[[2024,6,27]],"date-time":"2024-06-27T00:00:00Z","timestamp":1719446400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Special Fund for Forestry Scientific Research in the Public Interest","award":["201104037"],"award-info":[{"award-number":["201104037"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Convolutional Neural Networks (CNNs) have been widely applied in various edge computing devices based on intelligent sensors. However, due to the high computational demands of CNN tasks, the limited computing resources of edge intelligent terminal devices, and significant architectural differences among these devices, it is challenging for edge devices to independently execute inference tasks locally. Collaborative inference among edge terminal devices can effectively utilize idle computing and storage resources and optimize latency characteristics, thus significantly addressing the challenges posed by the computational intensity of CNNs. This paper targets efficient collaborative execution of CNN inference tasks among heterogeneous and resource-constrained edge terminal devices. We propose a pre-partitioning deployment method for CNNs based on critical operator layers, and optimize the system bottleneck latency during pipeline parallelism using data compression, queuing, and \u201cmicro-shifting\u201d techniques. Experimental results demonstrate that our method achieves significant acceleration in CNN inference within heterogeneous environments, improving performance by 71.6% compared to existing popular frameworks.<\/jats:p>","DOI":"10.3390\/s24134176","type":"journal-article","created":{"date-parts":[[2024,6,27]],"date-time":"2024-06-27T08:57:50Z","timestamp":1719478670000},"page":"4176","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Researching the CNN Collaborative Inference Mechanism for Heterogeneous Edge Devices"],"prefix":"10.3390","volume":"24","author":[{"given":"Jian","family":"Wang","sequence":"first","affiliation":[{"name":"College of Computer and Control Engineering, Northeast Forestry University, Harbin 150040, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9611-7990","authenticated-orcid":false,"given":"Chong","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Computer and Control Engineering, Northeast Forestry University, Harbin 150040, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shiwei","family":"Li","sequence":"additional","affiliation":[{"name":"College of Computer and Control Engineering, Northeast Forestry University, Harbin 150040, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4616-2515","authenticated-orcid":false,"given":"Chaoyong","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Computer and Control Engineering, Northeast Forestry University, Harbin 150040, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xianzhi","family":"Cao","sequence":"additional","affiliation":[{"name":"College of Computer and Control Engineering, Northeast Forestry University, Harbin 150040, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liusong","family":"Yang","sequence":"additional","affiliation":[{"name":"College of Computer and Control Engineering, Northeast Forestry University, Harbin 150040, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2024,6,27]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"12486","DOI":"10.1007\/s11227-021-03781-w","article-title":"Performance evaluation and optimization of a task offloading strategy on the mobile edge computing with edge heterogeneity","volume":"77","author":"Li","year":"2021","journal-title":"J. Supercomput."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Ren, W., Qu, Y., Dong, C., Jing, Y., Sun, H., Wu, Q., and Guo, S. (2022). A Survey on Collaborative DNN Inference for Edge Intelligence. arXiv.","DOI":"10.1007\/s11633-022-1391-7"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1145\/1866739.1866751","article-title":"Cloud computing privacy concerns on our doorstep","volume":"54","author":"Ryan","year":"2011","journal-title":"Commun. ACM"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"110","DOI":"10.1109\/MWC.014.2200283","article-title":"Collaboration of heterogeneous edge computing paradigms: How to fill the gap between theory and practice","volume":"31","author":"Cai","year":"2023","journal-title":"IEEE Wirel. Commun."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"160607","DOI":"10.1109\/ACCESS.2021.3131396","article-title":"Low latency deep learning inference model for distributed intelligent IoT edge clusters","volume":"9","author":"Naveen","year":"2021","journal-title":"IEEE Access"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Han, P., Zhuang, X., Zuo, H., Lou, P., and Chen, X. (2023). The Lightweight Anchor Dynamic Assignment Algorithm for Object Detection. Sensors, 23.","DOI":"10.3390\/s23146306"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Manessi, F., Rozza, A., Bianco, S., Napoletano, P., and Schettini, R. (2018, January 20\u201324). Automated pruning for deep neural network compression. Proceedings of the 2018 24th International Conference on Pattern Recognition (ICPR), Beijing, China.","DOI":"10.1109\/ICPR.2018.8546129"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Wu, J., Leng, C., Wang, Y., Hu, Q., and Cheng, J. (2016, January 27\u201330). Quantized convolutional neural networks for mobile devices. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.521"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"957","DOI":"10.1109\/TETCI.2023.3251404","article-title":"Edge-native intelligence for 6G communications driven by federated learning: A survey of trends and challenges","volume":"7","author":"Mohjazi","year":"2023","journal-title":"IEEE Trans. Emerg. Top. Comput. Intell."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Gomes, B., Soares, C., Torres, J.M., Karmali, K., Karmali, S., Moreira, R.S., and Sobral, P. (2024). An Efficient Edge Computing-Enabled Network for Used Cooking Oil Collection. Sensors, 24.","DOI":"10.3390\/s24072236"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Mao, J., Chen, X., Nixon, K.W., Krieger, C., and Chen, Y. (2017, January 27\u201331). Modnn: Local distributed mobile computing system for deep neural network. Proceedings of the Design, Automation & Test in Europe Conference & Exhibition (DATE), Lausanne, Switzerland.","DOI":"10.23919\/DATE.2017.7927211"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"2175","DOI":"10.1109\/TPDS.2021.3058532","article-title":"Deepslicing: Collaborative and adaptive cnn inference with low latency","volume":"32","author":"Zhang","year":"2021","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Hu, B., Gao, Y., Zhang, W., Jia, D., and Liu, H. (2023, January 25\u201327). Computation Offloading and Resource Allocation in IoT-Based Mobile Edge Computing Systems. Proceedings of the 2023 IEEE International Conference on Smart Internet of Things (SmartIoT), Xining, China.","DOI":"10.1109\/SmartIoT58732.2023.00024"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"28832","DOI":"10.1007\/s10489-023-05065-7","article-title":"A dynamic queuing model based distributed task offloading algorithm using deep reinforcement learning in mobile edge computing","volume":"53","author":"Chai","year":"2023","journal-title":"Appl. Intell."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Liu, X., Zheng, J., Zhang, M., Li, Y., Wang, R., and He, Y. (2024). Multi-User Computation Offloading and Resource Allocation Algorithm in a Vehicular Edge Network. Sensors, 24.","DOI":"10.3390\/s24072205"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Zhou, L., Samavatian, M.H., Bacha, A., Majumdar, S., and Teodorescu, R. (2019, January 7\u20139). Adaptive parallel execution of deep neural networks on heterogeneous edge devices. Proceedings of the 4th ACM\/IEEE Symposium on Edge Computing, Arlington, VA, USA.","DOI":"10.1145\/3318216.3363312"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"2348","DOI":"10.1109\/TCAD.2018.2858384","article-title":"Deepthings: Distributed adaptive deep learning inference on resource-constrained iot edge clusters","volume":"37","author":"Zhao","year":"2018","journal-title":"IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1180","DOI":"10.1007\/s10489-022-03482-8","article-title":"DeepMECagent: Multi-agent computing resource allocation for UAV-assisted mobile edge computing in distributed IoT system","volume":"53","author":"Zhang","year":"2023","journal-title":"Appl. Intell."},{"key":"ref_19","unstructured":"Hu, Y., Imes, C., Zhao, X., Kundu, S., Beerel, P.A., Crago, S.P., and Walters, J.P.N. (2021). Pipeline parallelism for inference on heterogeneous edge computing. arXiv."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Hu, C., and Li, B. (2022, January 2\u20135). Distributed inference with deep learning models across heterogeneous edge devices. Proceedings of the IEEE INFOCOM 2022-IEEE Conference on Computer Communications, Virtual Conference.","DOI":"10.1109\/INFOCOM48880.2022.9796896"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"595","DOI":"10.1109\/TNET.2020.3042320","article-title":"Coedge: Cooperative dnn inference with adaptive workload partitioning over heterogeneous edge devices","volume":"29","author":"Zeng","year":"2020","journal-title":"IEEE\/ACM Trans. Netw."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Yang, C.-Y., Kuo, J.-J., Sheu, J.-P., and Zheng, K.-J. (2021, January 14\u201323). Cooperative distributed deep neural network deployment with edge computing. Proceedings of the ICC 2021-IEEE International Conference on Communications, Virtual Event.","DOI":"10.1109\/ICC42927.2021.9500668"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1186\/s13638-023-02284-x","article-title":"Partitioning multi-layer edge network for neural network collaborative computing","volume":"2023","author":"Li","year":"2023","journal-title":"EURASIP J. Wirel. Commun. Netw."},{"key":"ref_24","unstructured":"Guo, X., Pimentel, A.D., and Stefanov, T. (2022). AutoDiCE: Fully Automated Distributed CNN Inference at the Edge. arXiv."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"8831341","DOI":"10.1155\/2020\/8831341","article-title":"Collaborative intelligence: Accelerating deep neural network inference via device-edge synergy","volume":"2020","author":"Shan","year":"2020","journal-title":"Secur. Commun. Netw."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Li, N., Iosifidis, A., and Zhang, Q. (June, January 28). Attention-based feature compression for cnn inference offloading in edge computing. Proceedings of the ICC 2023-IEEE International Conference on Communications, Rome, Italy.","DOI":"10.1109\/ICC45041.2023.10279110"},{"key":"ref_27","unstructured":"Molchanov, P., Tyree, S., Karras, T., Aila, T., and Kautz, J. (2016). Pruning convolutional neural networks for resource efficient inference. arXiv."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Parthasarathy, A., and Krishnamachari, B. (2022, January 4\u20138). Defer: Distributed edge inference for deep neural networks. Proceedings of the 2022 14th International Conference on COMmunication Systems & NETworkS (COMSNETS), Bangalore, India.","DOI":"10.1109\/COMSNETS53615.2022.9668515"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/13\/4176\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T15:06:09Z","timestamp":1760108769000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/13\/4176"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,27]]},"references-count":28,"journal-issue":{"issue":"13","published-online":{"date-parts":[[2024,7]]}},"alternative-id":["s24134176"],"URL":"https:\/\/doi.org\/10.3390\/s24134176","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6,27]]}}}