{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T02:34:00Z","timestamp":1778726040224,"version":"3.51.4"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,8,19]],"date-time":"2023-08-19T00:00:00Z","timestamp":1692403200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,8,19]],"date-time":"2023-08-19T00:00:00Z","timestamp":1692403200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"the National Key Research and Development Program of China","award":["2020YFB2104500"],"award-info":[{"award-number":["2020YFB2104500"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Wireless Com Network"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>There is a trend to deploy neural network on edge devices in recent years. While the mainstream of research often concerns with single edge device processing and edge-cloud two-layer neural network collaborative computing, in this paper, we propose partitioning multi-layer edge network for neural network collaborative computing. With the proposed method, sub-models of neural network are deployed on multi-layer edge devices along the communication path from end users to cloud. Firstly, we propose an optimal path selection method to form a neural network collaborative computing path with lowest communication overhead. Secondly, we establish a time-delay optimization mathematical model to evaluate the effects of different partitioning solutions. To find the optimal partition solution, an ordered elitist genetic algorithm (OEGA) is proposed. The experimental results show that, compared with traditional cloud computing, single-device edge computing and edge-cloud collaborative computing, the proposed multi-layer edge network collaborative computing has a smaller runtime delay with limited bandwidth resources, and because of the pipeline computing characteristics, the proposed method has a better response speed when processing large number of requests. Meanwhile, the OEGA algorithm has better performance than conventional methods, and the optimized partitioning method outperforms other methods like random and evenly partition.<\/jats:p>","DOI":"10.1186\/s13638-023-02284-x","type":"journal-article","created":{"date-parts":[[2023,8,19]],"date-time":"2023-08-19T18:01:54Z","timestamp":1692468114000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Partitioning multi-layer edge network for neural network collaborative computing"],"prefix":"10.1186","volume":"2023","author":[{"given":"Qiang","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1952-5574","authenticated-orcid":false,"given":"Ming-Tuo","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tian-Feng","family":"Ren","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cheng-Bin","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,8,19]]},"reference":[{"issue":"6","key":"2284_CR1","doi-asserted-by":"publisher","first-page":"854","DOI":"10.1109\/JIOT.2016.2584538","volume":"3","author":"M Chiang","year":"2017","unstructured":"M. Chiang, Z. Tao, Fog and iot: an overview of research opportunities. IEEE Internet Things J. 3(6), 854\u2013864 (2017)","journal-title":"IEEE Internet Things J."},{"issue":"5","key":"2284_CR2","doi-asserted-by":"publisher","first-page":"637","DOI":"10.1109\/JIOT.2016.2579198","volume":"3","author":"W Shi","year":"2016","unstructured":"W. Shi, C. Jie, Z. Quan, Y. Li, L. Xu, Edge computing: vision and challenges. Internet Things J. IEEE 3(5), 637\u2013646 (2016)","journal-title":"Internet Things J. IEEE"},{"issue":"4","key":"2284_CR3","doi-asserted-by":"publisher","first-page":"2322","DOI":"10.1109\/COMST.2017.2745201","volume":"19","author":"Y Mao","year":"2017","unstructured":"Y. Mao, C. You, J. Zhang, K. Huang, K.B. Letaief, A survey on mobile edge computing: the communication perspective. IEEE Commun. Surv. Tutor. 19(4), 2322\u20132358 (2017)","journal-title":"IEEE Commun. Surv. Tutor."},{"key":"2284_CR4","doi-asserted-by":"crossref","unstructured":"L.A. Hai, B. Sz, A. Zc, C. Hl, D. Lw, A survey on computation offloading modeling for edge computing\u2014sciencedirect. J. Netw. Comput. Appl. 2020, 169.","DOI":"10.1016\/j.jnca.2020.102781"},{"issue":"99","key":"2284_CR5","doi-asserted-by":"publisher","first-page":"869","DOI":"10.1109\/COMST.2020.2970550","volume":"22","author":"X Wang","year":"2020","unstructured":"X. Wang, Y. Han, V. Leung, D. Niyato, X. Chen, Convergence of edge computing and deep learning: a comprehensive survey. IEEE Commun. Surv. Tutorials 22(99), 869\u2013904 (2020)","journal-title":"IEEE Commun. Surv. Tutorials"},{"issue":"1","key":"2284_CR6","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1109\/MNET.2018.1700145","volume":"32","author":"X Chen","year":"2018","unstructured":"X. Chen, Q. Shi, L. Yang, J. Xu, Thrifty edge: resource-efficient edge computing for intelligent iot applications. IEEE Netw. 32(1), 61\u201365 (2018)","journal-title":"IEEE Netw."},{"issue":"9","key":"2284_CR7","doi-asserted-by":"publisher","first-page":"8769","DOI":"10.1109\/TVT.2018.2846232","volume":"67","author":"X Chen","year":"2018","unstructured":"X. Chen, W. Li, S. Lu, Z. Zhi, X. Fu, Efficient resource allocation for on-demand mobile-edge cloud computing. IEEE Trans. Veh. Technol. 67(9), 8769\u20138780 (2018)","journal-title":"IEEE Trans. Veh. Technol."},{"issue":"8","key":"2284_CR8","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1109\/MCOM.2018.1701080","volume":"56","author":"C Xu","year":"2018","unstructured":"C. Xu, R. Ju, D. Zhang, Y. Zhang, Distilling at the edge: a local differential privacy obfuscation framework for iot data analytics. IEEE Commun. Mag. 56(8), 20\u201325 (2018)","journal-title":"IEEE Commun. Mag."},{"issue":"1","key":"2284_CR9","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1109\/JSTSP.2022.3222910","volume":"17","author":"Y Ding","year":"2023","unstructured":"Y. Ding, Y. Feng, W. Lu et al., Online edge learning offloading and resource management for UAV-assisted MEC secure communications. IEEE J. Select. Topics Signal Process. 17(1), 54\u201365 (2023). https:\/\/doi.org\/10.1109\/JSTSP.2022.3222910","journal-title":"IEEE J. Select. Topics Signal Process."},{"issue":"3","key":"2284_CR10","doi-asserted-by":"publisher","first-page":"1270","DOI":"10.1109\/TNSE.2022.3185130","volume":"10","author":"W Lu","year":"2023","unstructured":"W. Lu, Y. Mo, Y. Feng et al., Secure transmission for multi-UAV-assisted mobile edge computing based on reinforcement learning. IEEE Trans. Netw. Sci. Eng. 10(3), 1270\u20131282 (2023). https:\/\/doi.org\/10.1109\/TNSE.2022.3185130","journal-title":"IEEE Trans. Netw. Sci. Eng."},{"issue":"8","key":"2284_CR11","doi-asserted-by":"publisher","first-page":"1738","DOI":"10.1109\/JPROC.2019.2918951","volume":"107","author":"Z Zhou","year":"2019","unstructured":"Z. Zhou, X. Chen, E. Li, L. Zeng, K. Luo, J. Zhang, Edge intelligence: paving the last mile of artificial intelligence with edge computing. Proc. IEEE 107(8), 1738\u20131762 (2019)","journal-title":"Proc. IEEE"},{"issue":"4","key":"2284_CR12","first-page":"3","volume":"56","author":"S Han","year":"2015","unstructured":"S. Han, H. Mao, W.J. Dally, Deep compression: compressing deep neural networks with pruning, trained quantization and huffman coding. Fiber 56(4), 3\u20137 (2015)","journal-title":"Fiber"},{"issue":"2","key":"2284_CR13","first-page":"576","volume":"71","author":"YD Kim","year":"2015","unstructured":"Y.D. Kim, E. Park, S. Yoo, T. Choi, L. Yang, D. Shin, Compression of deep convolutional neural networks for fast and low power mobile applications. Computer Science 71(2), 576\u2013584 (2015)","journal-title":"Computer Science"},{"key":"2284_CR14","doi-asserted-by":"crossref","unstructured":"N. Lane, S. Bhattacharya, A. Mathur, C. Forlivesi, F. Kawsar,DXTK: Enabling Resource-efficient Deep Learning on Mobile and Embedded Devices with the DeepX Toolkit. Eai International Conference on Mobile Computing. ICST (Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering). 2016.","DOI":"10.4108\/eai.30-11-2016.2267463"},{"key":"2284_CR15","doi-asserted-by":"crossref","unstructured":"S. Liu, Y. Lin, Z. Zhou, K. Nan, J. Du. On-Demand Deep Model Compression for Mobile Devices: A Usage-Driven Model Selection Framework. MobiSys '18: Proceedings of the 16th Annual International Conference on Mobile Systems, Applications, and Services, 2018, 389\u2013400.","DOI":"10.1145\/3210240.3210337"},{"key":"2284_CR16","doi-asserted-by":"crossref","unstructured":"Oh, Y. H., Quan, Q., Kim, D., Kim, S., & Lee, J. W., A Portable, Automatic Data Qantizer For Deep Neural Networks, PACT '18: Proceedings of the 27th International Conference on Parallel Architectures and Compilation Techniques,November 2018, 1\u201314.","DOI":"10.1145\/3243176.3243180"},{"issue":"1","key":"2284_CR17","doi-asserted-by":"publisher","first-page":"615","DOI":"10.1145\/3093336.3037698","volume":"52","author":"Y Kang","year":"2017","unstructured":"Y. Kang, J. Hauswald, G. Cao, A. Rovinski, T. Mudge, J. Mars et al., Neurosurgeon: collaborative intelligence between the cloud and mobile edge. Acm Sigplan Notices 52(1), 615\u2013629 (2017)","journal-title":"Acm Sigplan Notices"},{"issue":"1","key":"2284_CR18","doi-asserted-by":"publisher","first-page":"447","DOI":"10.1109\/TWC.2019.2946140","volume":"19","author":"E Li","year":"2020","unstructured":"E. Li, L. Zeng, Z. Zhou, X. Chen, Edge ai: on-demand accelerating deep neural network inference via edge computing. IEEE Trans. Wireless Commun. 19(1), 447\u2013457 (2020)","journal-title":"IEEE Trans. Wireless Commun."},{"key":"2284_CR19","doi-asserted-by":"crossref","unstructured":"C. Hu, W. Bao, D. Wang and F. Liu, in Dynamic Adaptive DNN Surgery for Inference Acceleration on the Edge, IEEE INFOCOM 2019 - IEEE Conference on Computer Communications, 2019, pp. 1423\u20131431.","DOI":"10.1109\/INFOCOM.2019.8737614"},{"key":"2284_CR20","first-page":"1","volume":"2020","author":"M Liu","year":"2020","unstructured":"M. Liu, Y. Li, Y. Zhao, H. Yang, J. Zhang, Adaptive DNN model partition and deployment in edge computing-enabled metro optical interconnection network. Optic Fiber Commun Conf Exhibit 2020, 1\u20133 (2020)","journal-title":"Optic Fiber Commun Conf Exhibit"},{"key":"2284_CR21","doi-asserted-by":"crossref","unstructured":"H. Li, C. Hu, J. Jiang, Z. Wang, Y. Wen and W. Zhu, JALAD: Joint accuracy-and latency-aware deep structure decoupling for edge-cloud execution, 2018 IEEE 24th international conference on parallel and distributed systems (ICPADS), 2018, pp 671\u2013678","DOI":"10.1109\/PADSW.2018.8645013"},{"issue":"2","key":"2284_CR22","doi-asserted-by":"publisher","first-page":"314","DOI":"10.1109\/TMC.2019.2893250","volume":"19","author":"M Xu","year":"2020","unstructured":"M. Xu, F. Qian, M. Zhu, F. Huang, S. Pushp, X. Liu, DeepWear: adaptive local offloading for on-wearable deep learning. IEEE Trans. Mob. Comput. 19(2), 314\u2013330 (2020)","journal-title":"IEEE Trans. Mob. Comput."},{"issue":"5","key":"2284_CR23","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1109\/MNET.001.1800506","volume":"33","author":"L Zeng","year":"2019","unstructured":"L. Zeng, E. Li, Z. Zhou, X. Chen, Boomerang: on-demand cooperative deep neural network inference for edge intelligence on the industrial internet of things. IEEE Network 33(5), 96\u2013103 (2019)","journal-title":"IEEE Network"},{"key":"2284_CR24","doi-asserted-by":"crossref","unstructured":"H. J. Jeong, H. J. Lee, C. H. Shin, S. M. Moon. IONN: Incremental Offloading of Neural Network Computations from Mobile Devices to Edge Servers, in the ACM Symposium. ACM. 2018.","DOI":"10.1145\/3267809.3267828"},{"key":"2284_CR25","doi-asserted-by":"crossref","unstructured":"G. Li, L. Liu, X. Wang, X. Dong, P. Zhao, X. Feng. Auto-tuning neural network quantization framework for collaborative inference between the cloud and edge, in ICANN 2018:\u00a0Artificial Neural Networks and Machine Learning, 2018, pp. 402\u2013411.","DOI":"10.1007\/978-3-030-01418-6_40"},{"key":"2284_CR26","doi-asserted-by":"crossref","unstructured":"S. Teerapittayanon, B. McDanel and H.T. Kung, BranchyNet: Fast inference via early exiting from deep neural networks, 2016 23rd International Conference on Pattern Recognition (ICPR), 2016, pp. 2464\u20132469.","DOI":"10.1109\/ICPR.2016.7900006"},{"key":"2284_CR27","doi-asserted-by":"crossref","unstructured":"C. Lo, Y.-Y. Su, C.-Y. Lee and S.-C. Chang, A Dynamic Deep Neural Network Design for Efficient Workload Allocation in Edge Computing, in 2017 IEEE International Conference on Computer Design (ICCD), 2017, pp. 273\u2013280","DOI":"10.1109\/ICCD.2017.49"},{"key":"2284_CR28","unstructured":"Rapp, J. W., Jackson, L., Jones, M., & Cherasaro, T., Pipeline accelerator for improved computing architecture and related system and method. 2004, CA, US-2004136241-A1"},{"key":"2284_CR29","doi-asserted-by":"crossref","unstructured":"Harlap, A., Narayanan, D., Phanishayee, A., Seshadri, V., Devanur, N., & Ganger, G., et al,. Pipedream: fast and efficient pipeline parallel dnn training, 2018, eprint arXiv:1806.03377.","DOI":"10.1145\/3341301.3359646"},{"key":"2284_CR30","unstructured":"Seyedzadegan, M., Othman, M., Ali, B. M., & Subramaniam, S, Wireless Mesh Networks: WMN Overview, 2011, WMN Architecture."},{"key":"2284_CR31","doi-asserted-by":"crossref","unstructured":"Ranjini, A., & Zoraida, B., Preemptive appliances scheduling in smart home using genetic algorithm. Adv. Intell. Syst. Comput. 2015, 387\u2013393.","DOI":"10.1007\/978-81-322-2126-5_43"},{"issue":"06","key":"2284_CR32","doi-asserted-by":"publisher","first-page":"731","DOI":"10.1142\/S0218001496000438","volume":"10","author":"D Bhandari","year":"1996","unstructured":"D. Bhandari, C.A. Murthy, Pal SK (1996) Genetic algorithm with elitist model and its convergence. Int J Pattern Recogn Artific Intell 10(06), 731\u2013747 (1996)","journal-title":"Int J Pattern Recogn Artific Intell"},{"key":"2284_CR33","doi-asserted-by":"crossref","unstructured":"Koonce, B., VGG Network, in Convolutional Neural Networks with Swift for Tensorflow (Apress, Berkeley, CA, 2021).","DOI":"10.1007\/978-1-4842-6168-2"},{"key":"2284_CR34","unstructured":"Alom, M. Z., Taha, T. M., Yakopcic, C., Westberg, S., & Asari, V. K., The history began from alexnet: a comprehensive survey on deep learning approaches, 2018, eprint arXiv:1803.01164."},{"key":"2284_CR35","doi-asserted-by":"publisher","unstructured":"P. Wiener, P. Zehnder and D. Riemer, in Towards Context-Aware and Dynamic Management of Stream Processing Pipelines for Fog Computing. 2019 IEEE 3rd International Conference on Fog and Edge Computing (ICFEC), Larnaca, Cyprus, 2019, pp. 1\u20136, doi: https:\/\/doi.org\/10.1109\/CFEC.2019.8733145.","DOI":"10.1109\/CFEC.2019.8733145"},{"key":"2284_CR36","doi-asserted-by":"publisher","unstructured":"M.-T. Zhou, F.-G. Shen, T.-F. Ren and X.-Y. Feng, Blockchain-based Volunteer Edge Cloud for IoT Applications. In: 2021 IEEE 93rd Vehicular Technology Conference (VTC2021-Spring), Helsinki, Finland, 2021, pp 1\u20136, https:\/\/doi.org\/10.1109\/VTC2021-Spring51267.2021.9449041","DOI":"10.1109\/VTC2021-Spring51267.2021.9449041"},{"key":"2284_CR37","doi-asserted-by":"publisher","first-page":"133520","DOI":"10.1109\/ACCESS.2021.3112202","volume":"9","author":"K Suzaki","year":"2021","unstructured":"K. Suzaki, K. Nakajima, T. Oi, A. Tsukamoto, TS-Perf: general performance measurement of trusted execution environment and rich execution environment on intel SGX, Arm TrustZone, and RISC-V Keystone. IEEE Access 9, 133520\u2013133530 (2021). https:\/\/doi.org\/10.1109\/ACCESS.2021.3112202","journal-title":"IEEE Access"},{"key":"2284_CR38","doi-asserted-by":"crossref","unstructured":"Q. Li, M.-T. Zhou, T.-F. Ren, et al., Optimized Edge-Network Collaborative Computing for Artificial Intelligence, submitted, May 2023","DOI":"10.1186\/s13638-023-02284-x"}],"container-title":["EURASIP Journal on Wireless Communications and Networking"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13638-023-02284-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13638-023-02284-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13638-023-02284-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T16:21:27Z","timestamp":1700497287000},"score":1,"resource":{"primary":{"URL":"https:\/\/jwcn-eurasipjournals.springeropen.com\/articles\/10.1186\/s13638-023-02284-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,19]]},"references-count":38,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["2284"],"URL":"https:\/\/doi.org\/10.1186\/s13638-023-02284-x","relation":{},"ISSN":["1687-1499"],"issn-type":[{"value":"1687-1499","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8,19]]},"assertion":[{"value":"16 January 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 August 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 August 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest. The funders had no role in the design of the study; in the collection, analyses, or interpretation of data; in the writing of the manuscript; or in the decision to publish the results.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"80"}}