{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,8,11]],"date-time":"2024-08-11T00:13:49Z","timestamp":1723335229253},"reference-count":39,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2022,11,29]],"date-time":"2022-11-29T00:00:00Z","timestamp":1669680000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Key-Area Research and Development Program of Guangdong Province","award":["2019B010155003"]},{"name":"National Natural Science and Foundation of China","award":["NSFC 61902355"]},{"name":"Guangdong Basic and Applied Basic Research Foundation","award":["2020B1515120044"]},{"name":"joint fund of Science & Technology Department of Liaoning Province and State Key Laboratory of Robotics","award":["2021-KF-22-12"]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Symmetry"],"abstract":"Recurrent neural networks (RNNs) are widely used to process sequence-related tasks such as natural language processing. Edge cloud computing systems are in an asymmetric structure, where task managers allocate tasks to the asymmetric edge and cloud computing systems based on computation requirements. In such a computing system, cloud servers have no energy limitations, since they have unlimited energy resources. Edge computing systems, however, are resource-constrained, and the energy consumption is thus expensive, which requires an energy-efficient method for RNN job processing. In this paper, we propose a low-overhead, energy-aware runtime manager to process tasks in edge cloud computing. The RNN task latency is defined as the quality of service (QoS) requirement. Based on the QoS requirements, the runtime manager dynamically assigns RNN inference tasks to edge and cloud computing systems and performs energy optimization on edge systems using dynamic voltage and frequency scaling (DVFS) techniques. Experimental results on a real edge cloud system indicate that in edge systems, our method can reduce the energy up to 45% compared with the state-of-the-art approach.<\/jats:p>","DOI":"10.3390\/sym14122524","type":"journal-article","created":{"date-parts":[[2022,11,30]],"date-time":"2022-11-30T09:05:24Z","timestamp":1669799124000},"page":"2524","source":"Crossref","is-referenced-by-count":1,"title":["An Energy-Efficient Method for Recurrent Neural Network Inference in Edge Cloud Computing"],"prefix":"10.3390","volume":"14","author":[{"given":"Chao","family":"Chen","sequence":"first","affiliation":[{"name":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, China"}]},{"given":"Weiyu","family":"Guo","sequence":"additional","affiliation":[{"name":"Artificial Intelligence Thrust, Information Hub, Hong Kong University of Science and Technology, Guangzhou 511458, China"}]},{"ORCID":"http:\/\/orcid.org\/0000-0003-2855-9570","authenticated-orcid":false,"given":"Zheng","family":"Wang","sequence":"additional","affiliation":[{"name":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, China"}]},{"ORCID":"http:\/\/orcid.org\/0000-0003-1159-3115","authenticated-orcid":false,"given":"Yongkui","family":"Yang","sequence":"additional","affiliation":[{"name":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, China"}]},{"given":"Zhuoyu","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Engineering, Durham University, Lower Mountjoy, South Rd., Durham DH1 3LE, UK"}]},{"given":"Guannan","family":"Li","sequence":"additional","affiliation":[{"name":"Marine Robot Engineering Research Center, Huzhou Institute of Zhejiang University, Huzhou 313000, China"},{"name":"State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences (CAS), Shenyang 110016, China"},{"name":"Hangzhou Innovation Institute, Beihang University, Hangzhou 310051, China"}]}],"member":"1968","published-online":{"date-parts":[[2022,11,29]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"2295","DOI":"10.1109\/JPROC.2017.2761740","article-title":"Efficient Processing of Deep Neural Networks: A Tutorial and Survey","volume":"105","author":"Sze","year":"2017","journal-title":"Proc. IEEE"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Sahlol, A.T., Abd Elaziz, M., Tariq Jamal, A., Dama\u0161evi\u010dius, R., and Farouk Hassan, O. (2020). A Novel Method for Detection of Tuberculosis in Chest Radiographs Using Artificial Ecosystem-Based Optimisation of Deep Neural Network Features. Symmetry, 12.","DOI":"10.3390\/sym12071146"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Maxwell, A.E., Warner, T.A., and Guill\u00e9n, L.A. (2021). Accuracy assessment in convolutional neural network-based deep learning remote sensing studies\u2014part 1: Literature review. Remote Sens., 13.","DOI":"10.3390\/rs13132450"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Dhaka, V.S., Meena, S.V., Rani, G., Sinwar, D., Ijaz, M.F., and Wo\u017aniak, M. (2021). A survey of deep convolutional neural networks applied for prediction of plant leaf diseases. Sensors, 21.","DOI":"10.3390\/s21144749"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"272","DOI":"10.3390\/info12070272","article-title":"Applications of recurrent neural network for biometric authentication & anomaly detection","volume":"12","author":"Ackerson","year":"2021","journal-title":"Information"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"106548","DOI":"10.1016\/j.knosys.2020.106548","article-title":"ASRNN: A recurrent neural network with an attention model for sequence labeling","volume":"212","author":"Lin","year":"2021","journal-title":"Knowl. Based Syst."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Anagnostis, A., Benos, L., Tsaopoulos, D., Tagarakis, A., Tsolakis, N., and Bochtis, D. (2021). Human activity recognition through recurrent neural networks for human\u2013robot interaction in agriculture. Appl. Sci., 11.","DOI":"10.3390\/app11052188"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Rahman, M.M., Watanobe, Y., and Nakamura, K. (2021). A Bidirectional LSTM Language Model for Code Evaluation and Repair. Symmetry, 13.","DOI":"10.3390\/sym13020247"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"198","DOI":"10.1109\/TCSI.2017.2735490","article-title":"A reconfigurable streaming deep convolutional neural network accelerator for Internet of Things","volume":"65","author":"Du","year":"2017","journal-title":"IEEE Trans. Circuits Syst. I Regul. Pap."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"264","DOI":"10.1016\/j.eng.2020.01.007","article-title":"A survey of accelerator architectures for deep neural networks","volume":"6","author":"Chen","year":"2020","journal-title":"Engineering"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"260","DOI":"10.1109\/TMSCS.2018.2821154","article-title":"A hierarchical inference model for Internet-of-Things","volume":"4","author":"Yin","year":"2018","journal-title":"IEEE Trans. Multi-Scale Comput. Syst."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Thomas, A., Guo, Y., Kim, Y., Aksanli, B., Kumar, A., and Rosing, T.S. (2019, January 9\u201311). Hierarchical and distributed machine learning inference beyond the edge. Proceedings of the 2019 IEEE 16th International Conference on Networking, Sensing and Control (ICNSC), Banff, AB, Canada.","DOI":"10.1109\/ICNSC.2019.8743164"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"615","DOI":"10.1145\/3093337.3037698","article-title":"Neurosurgeon: Collaborative intelligence between the cloud and mobile edge","volume":"45","author":"Kang","year":"2017","journal-title":"ACM SIGARCH Comput. Archit. News"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Eshratifar, A.E., Esmaili, A., and Pedram, M. (2019, January 29\u201331). Bottlenet: A deep learning architecture for intelligent mobile cloud computing services. Proceedings of the 2019 IEEE\/ACM International Symposium on Low Power Electronics and Design (ISLPED), Lausanne, Switzerland.","DOI":"10.1109\/ISLPED.2019.8824955"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Pagliari, D.J., Chiaro, R., Chen, Y., Vinco, S., Macii, E., and Poncino, M. (2020, January 20\u201324). Input-dependent edge-cloud mapping of recurrent neural networks inference. Proceedings of the 2020 57th ACM\/IEEE Design Automation Conference (DAC), San Francisco, CA, USA.","DOI":"10.1109\/DAC18072.2020.9218595"},{"key":"ref_16","first-page":"1626","article-title":"CRIME: Input-Dependent Collaborative Inference for Recurrent Neural Networks","volume":"70","author":"Pagliari","year":"2020","journal-title":"IEEE Trans. Comput."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Tann, H., Hashemi, S., Bahar, R.I., and Reda, S. (2016, January 2\u20137). Runtime configurable deep neural networks for energy-accuracy trade-off. Proceedings of the 2016 International Conference on Hardware\/Software Codesign and System Synthesis (CODES+ISSS), Pittsburgh, PA, USA.","DOI":"10.1145\/2968456.2968458"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Jahier Pagliari, D., Panini, F., Macii, E., and Poncino, M. (2019, January 9\u201311). Dynamic Beam Width Tuning for Energy-Efficient Recurrent Neural Networks. Proceedings of the GLSVLSI \u201919, 2019 on Great Lakes Symposium on VLSI, Tysons Corner, VA, USA.","DOI":"10.1145\/3299874.3317974"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1738","DOI":"10.1109\/JPROC.2019.2918951","article-title":"Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing","volume":"107","author":"Zhou","year":"2019","journal-title":"Proc. IEEE"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1655","DOI":"10.1109\/JPROC.2019.2921977","article-title":"Deep Learning With Edge Computing: A Review","volume":"107","author":"Chen","year":"2019","journal-title":"Proc. IEEE"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1537","DOI":"10.1109\/JPROC.2019.2920341","article-title":"A Survey on Edge Computing Systems and Tools","volume":"107","author":"Liu","year":"2019","journal-title":"Proc. IEEE"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"869","DOI":"10.1109\/COMST.2020.2970550","article-title":"Convergence of Edge Computing and Deep Learning: A Comprehensive Survey","volume":"22","author":"Wang","year":"2020","journal-title":"IEEE Commun. Surv. Tutor."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"268","DOI":"10.1109\/JETCAS.2020.3022920","article-title":"An Overview of Efficient Interconnection Networks for Deep Neural Network Accelerators","volume":"10","author":"Nabavinejad","year":"2020","journal-title":"IEEE J. Emerg. Sel. Top. Circuits Syst."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Belabed, T., Coutinho, M.G.F., Fernandes, M.A.C., Carlos, V., and Souani, C. (2020, January 2\u20135). Low Cost and Low Power Stacked Sparse Autoencoder Hardware Acceleration for Deep Learning Edge Computing Applications. Proceedings of the 2020 5th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP), Sousse, Tunisia.","DOI":"10.1109\/ATSIP49331.2020.9231748"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"101991","DOI":"10.1016\/j.sysarc.2021.101991","article-title":"SparkNoC: An energy-efficiency FPGA-based accelerator using optimized lightweight CNN for edge computing","volume":"115","author":"Xia","year":"2021","journal-title":"J. Syst. Archit."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"252","DOI":"10.1109\/TCSS.2021.3059318","article-title":"Collaborative Edge Computing With FPGA-Based CNN Accelerators for Energy-Efficient and Time-Aware Face Tracking System","volume":"9","author":"Liu","year":"2022","journal-title":"IEEE Trans. Comput. Soc. Syst."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"2610","DOI":"10.1109\/TMC.2020.3041781","article-title":"The Case for FPGA-Based Edge Computing","volume":"21","author":"Xu","year":"2022","journal-title":"IEEE Trans. Mob. Comput."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1145\/3339308","article-title":"Lightweight Convolution Neural Networks for Mobile Edge Computing in Transportation Cyber Physical Systems","volume":"10","author":"Zhou","year":"2019","journal-title":"ACM Trans. Intell. Syst. Technol."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Kim, R., Kim, G., Kim, H., Yoon, G., and Yoo, H. (2020, January 21\u201323). A Method for Optimizing Deep Learning Object Detection in Edge Computing. Proceedings of the 2020 International Conference on Information and Communication Technology Convergence (ICTC), Jeju, Republic of Korea.","DOI":"10.1109\/ICTC49870.2020.9289529"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"3614","DOI":"10.1109\/TCAD.2020.3013050","article-title":"Fusion-Catalyzed Pruning for Optimizing Deep Learning on Intelligent Edge Devices","volume":"39","author":"Li","year":"2020","journal-title":"IEEE Trans. Comput. Aided Des. Integr. Circuits Syst."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"212177","DOI":"10.1109\/ACCESS.2020.3039714","article-title":"Head Network Distillation: Splitting Distilled Deep Neural Networks for Resource-Constrained Edge Computing Systems","volume":"8","author":"Matsubara","year":"2020","journal-title":"IEEE Access"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1016\/bs.adcom.2020.10.003","article-title":"Chapter Nine\u2014\u201cLast mile\u201d optimization of edge computing ecosystem with deep learning models and specialized tensor processing architectures","volume":"Volume 122","author":"Kim","year":"2021","journal-title":"Hardware Accelerator Systems for Artificial Intelligence and Machine Learning"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"102431","DOI":"10.1016\/j.sysarc.2022.102431","article-title":"Optimizing deep neural networks on intelligent edge accelerators via flexible-rate filter pruning","volume":"124","author":"Li","year":"2022","journal-title":"J. Syst. Archit."},{"key":"ref_34","unstructured":"Zhou, X., Canady, R., Bao, S., and Gokhale, A. (2020, January 25\u201326). Cost-effective hardware accelerator recommendation for edge computing. Proceedings of the 3rd USENIX Workshop on Hot Topics in Edge Computing (HotEdge 20), Virtual Event."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"9372","DOI":"10.1109\/JIOT.2020.2986015","article-title":"Intelligent Cooperative Edge Computing in Internet of Things","volume":"7","author":"Gong","year":"2020","journal-title":"IEEE Internet Things J."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"6214","DOI":"10.1109\/JIOT.2019.2961707","article-title":"Cooperative Computation Offloading and Resource Allocation for Blockchain-Enabled Mobile-Edge Computing: A Deep Reinforcement Learning Approach","volume":"7","author":"Feng","year":"2020","journal-title":"IEEE Internet Things J."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"12229","DOI":"10.1109\/TVT.2020.3016840","article-title":"Cooperative Offloading and Resource Management for UAV-Enabled Mobile Edge Computing in Power IoT System","volume":"69","author":"Liu","year":"2020","journal-title":"IEEE Trans. Veh. Technol."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Kennedy, J., Varghese, B., and Rea\u00f1o, C. (2021, January 10\u201313). AVEC: Accelerator Virtualization in Cloud-Edge Computing for Deep Learning Libraries. Proceedings of the 2021 IEEE 5th International Conference on Fog and Edge Computing (ICFEC), Melbourne, VIC, Australia.","DOI":"10.1109\/ICFEC51620.2021.00013"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"102167","DOI":"10.1016\/j.sysarc.2021.102167","article-title":"Cooperative computation offloading and resource allocation for delay minimization in mobile edge computing","volume":"118","author":"Kuang","year":"2021","journal-title":"J. Syst. Archit."}],"container-title":["Symmetry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-8994\/14\/12\/2524\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,10]],"date-time":"2024-08-10T10:37:54Z","timestamp":1723286274000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-8994\/14\/12\/2524"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,29]]},"references-count":39,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2022,12]]}},"alternative-id":["sym14122524"],"URL":"http:\/\/dx.doi.org\/10.3390\/sym14122524","relation":{},"ISSN":["2073-8994"],"issn-type":[{"type":"electronic","value":"2073-8994"}],"subject":[],"published":{"date-parts":[[2022,11,29]]}}}
