计算机科学 ›› 2020, Vol. 47 ›› Issue (10): 256-262.doi: 10.11896/jsjkx.190800159
王瑄, 毛莺池, 谢在鹏, 黄倩
WANG Xuan, MAO Ying-chi, XIE Zai-peng, HUANG Qian
摘要: 卷积神经网络(Convolutional Neural Network,CNN)作为深度学习的重要技术,已被广泛应用在移动智能应用中。针对CNN推断任务高内存、高计算量的需求,现有解决方案多将任务卸载到云上执行,难以适应时延敏感的移动应用程序。为解决上述问题,提出了一种基于改进差分进化算法的CNN推断任务卸载策略,它采用端云协作模式将计算任务部署在云和边缘设备之间。该策略研究了成本约束下最小化时延的任务卸载方案,将CNN推断过程转化为任务图并将其构建为0-1整数规划问题,利用改进二进制差分进化算法高效求解最佳卸载决策。实验结果表明,在给定费用约束下,与移动端推断和云推断方案相比,所提策略将任务响应时间平均缩短了33.60%和6.06%。
中图分类号:
[1]ZHOU F Y,JIN L P,DONG J.Review of Convolutional Neural Network[J].Chinese Journal of Computers,2017,40(6):1229-1251. [2]PLASTIRAS G,TERZI M,KYRKOU C,et al.Edge Intelli-gence:Challenges and Opportunities of Near-Sensor Machine Learning Applications[C]//2018 IEEE 29th International Conference on Application-specific Systems,Architectures and Processors (ASAP).IEEE,2018:1-7. [3]GUO T.Cloud-based or On-device:An Empirical Study of Mobile Deep Inference[C]//2018 IEEE International Conference on Cloud Engineering (IC2E).IEEE,2018:184-190. [4]KANG Y,HAUSWALD J,GAO C,et al.Neurosurgeon:Collaborative intelligence between the cloud and mobile edge[J].ACM SIGplan Notices,2017,52(4):615-629. [5]HUANG Y T,MA Y Q,FAN X Y,et al.When Deep Learning Meets Edge Computing[C]//2017 IEEE 25th International Conference on Network Protocols (ICNP).IEEE Computer Society,2017:1-2. [6]LI E,ZHOU Z,CHEN X.Edge intelligence:On-demand deeplearning model co-inference with device-edge synergy[C]//Proceedings of the 2018 Workshop on Mobile Edge Communications.ACM,2018:31-36. [7]ZHANG Q,ZHANG H L.Research progress of task offloading technologies in mobile cloud computing[J].Intelligent Computer and Applications,2016,6(6):1-4. [8]GOYAL S,CARTER J.A lightweight secure cyber foraging infrastructure for resource-constrained devices[C]//Sixth IEEE Workshop on Mobile Computing Systems and Applications.IEEE,2004:186-195. [9]HUANG D,WANG P,NIYATO D.A dynamic offloading algorithm for mobile computing[J].IEEE Transactions on Wireless Communications,2012,11(6):1991-1995. [10]BARRAMEDA J,SAMAAN N.A novel application model and an offloading mechanism for efficient mobile computing[C]//2014 IEEE 10th International Conference on Wireless and Mobile Computing,Networking and Communications (WiMob).IEEE,2014:419-426. [11]ESHRATIFAR A E,PEDRAM M.Energy and performance efficient computation offloading for deep neural networks in a mobile cloud computing environment[C]//Proceedings of the 2018 on Great Lakes Symposium on VLSI.ACM,2018:111-116. [12]ZANNAT H,HOSSAIN M S.A hybrid framework using Markov decision process for mobile code offloading[C]//2016 19th International Conference on Computer and Information Technology (ICCIT).IEEE,2016:31-35. [13]ENZAI N I M,TANG M.A heuristic algorithm for multi-site computation offloading in mobile cloud computing[J].Procedia Computer Science,2016,80:1232-1241. [14]JEONG H J,JEONG I C,LEE H J,et al.Computation Offloading for Machine Learning Web Apps in the Edge Server Envi- ronment[C]//2018 IEEE 38th International Conference on Distributed Computing Systems (ICDCS).IEEE Computer Society,2018:1492-1499. [15]GUO K,YANG M,ZHANG Y,et al.An Efficient Dynamic Offloading Approach based on Optimization Technique for Mobile Edge Computing[C]//2018 6th IEEE International Conference on Mobile Cloud Computing,Services,and Engineering (MobileCloud).IEEE,2018:29-36. [16]QIAN H,ANDREAEN D.Reducing mobile device energy consumption with computation offloading[C]//2015 IEEE/ACIS 16th International Conference on Software Engineering,Artificial Intelligence,Networking and Parallel/Distributed Computing (SNPD).IEEE,2015:1-8. [17]ESHRATIFAR A E,ABRISHAMI M S,PEDRAM M.JointDNN:An Efficient Training and Inference Engine for Intelligent Mobile Cloud Computing Services[J/OL].https://arxiv.org/pdf/1801.08618. [18]HE K,ZHANG X,REN S,et al.Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2016:770-778. [19]SZEGEDY C,LIU W,JIA Y,et al.Going deeper with convolutions[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2015:1-9. [20]ZHANG W,WEN Y,WU D O.Energy-efficient scheduling policy for collaborative execution in mobile cloud computing[C]//2013 Proceedings Ieee Infocom.IEEE,2013:190-194. [21]CHU C A,LIN W,XIAO H.An adaptive genetic algorithmbased on weighted hamming distance[J].Journal of South Normal University (Natural Science Edition),2015,47(6):121-127. [22]CHEN H,FAN Y R,DENG S G.Adaptive differential evolution algorithm based on logistic model[J].Control and Decision,2011,26(7):1105-1108. [23]WU L H,WANG Y N,YUAN X F,et al.Differential Evolution Algorithm with Adaptive Second Mutation[J].Control and Decision,2006,21(8):898-902. [24]KRIZHEVSKY A,SUTSKEVER I,HINTON G E.Imagenet classification with deep convolutional neural networks[J].Communications of the ACM,2017,60(6):84-90. |
[1] | 孙慧婷, 范艳芳, 马孟晓, 陈若愚, 蔡英. VEC中基于动态定价的车辆协同计算卸载方案 Dynamic Pricing-based Vehicle Collaborative Computation Offloading Scheme in VEC 计算机科学, 2022, 49(9): 242-248. https://doi.org/10.11896/jsjkx.210700166 |
[2] | 周乐员, 张剑华, 袁甜甜, 陈胜勇. 多层注意力机制融合的序列到序列中国连续手语识别和翻译 Sequence-to-Sequence Chinese Continuous Sign Language Recognition and Translation with Multi- layer Attention Mechanism Fusion 计算机科学, 2022, 49(9): 155-161. https://doi.org/10.11896/jsjkx.210800026 |
[3] | 李宗民, 张玉鹏, 刘玉杰, 李华. 基于可变形图卷积的点云表征学习 Deformable Graph Convolutional Networks Based Point Cloud Representation Learning 计算机科学, 2022, 49(8): 273-278. https://doi.org/10.11896/jsjkx.210900023 |
[4] | 陈泳全, 姜瑛. 基于卷积神经网络的APP用户行为分析方法 Analysis Method of APP User Behavior Based on Convolutional Neural Network 计算机科学, 2022, 49(8): 78-85. https://doi.org/10.11896/jsjkx.210700121 |
[5] | 朱承璋, 黄嘉儿, 肖亚龙, 王晗, 邹北骥. 基于注意力机制的医学影像深度哈希检索算法 Deep Hash Retrieval Algorithm for Medical Images Based on Attention Mechanism 计算机科学, 2022, 49(8): 113-119. https://doi.org/10.11896/jsjkx.210700153 |
[6] | 檀莹莹, 王俊丽, 张超波. 基于图卷积神经网络的文本分类方法研究综述 Review of Text Classification Methods Based on Graph Convolutional Network 计算机科学, 2022, 49(8): 205-216. https://doi.org/10.11896/jsjkx.210800064 |
[7] | 金方焱, 王秀利. 融合RACNN和BiLSTM的金融领域事件隐式因果关系抽取 Implicit Causality Extraction of Financial Events Integrating RACNN and BiLSTM 计算机科学, 2022, 49(7): 179-186. https://doi.org/10.11896/jsjkx.210500190 |
[8] | 张翀宇, 陈彦明, 李炜. 边缘计算中面向数据流的实时任务调度算法 Task Offloading Online Algorithm for Data Stream Edge Computing 计算机科学, 2022, 49(7): 263-270. https://doi.org/10.11896/jsjkx.210300195 |
[9] | 张颖涛, 张杰, 张睿, 张文强. 全局信息引导的真实图像风格迁移 Photorealistic Style Transfer Guided by Global Information 计算机科学, 2022, 49(7): 100-105. https://doi.org/10.11896/jsjkx.210600036 |
[10] | 戴朝霞, 李锦欣, 张向东, 徐旭, 梅林, 张亮. 基于DNGAN的磁共振图像超分辨率重建算法 Super-resolution Reconstruction of MRI Based on DNGAN 计算机科学, 2022, 49(7): 113-119. https://doi.org/10.11896/jsjkx.210600105 |
[11] | 刘月红, 牛少华, 神显豪. 基于卷积神经网络的虚拟现实视频帧内预测编码 Virtual Reality Video Intraframe Prediction Coding Based on Convolutional Neural Network 计算机科学, 2022, 49(7): 127-131. https://doi.org/10.11896/jsjkx.211100179 |
[12] | 徐鸣珂, 张帆. Head Fusion:一种提高语音情绪识别的准确性和鲁棒性的方法 Head Fusion:A Method to Improve Accuracy and Robustness of Speech Emotion Recognition 计算机科学, 2022, 49(7): 132-141. https://doi.org/10.11896/jsjkx.210100085 |
[13] | 张嘉淏, 刘峰, 齐佳音. 一种基于Bottleneck Transformer的轻量级微表情识别架构 Lightweight Micro-expression Recognition Architecture Based on Bottleneck Transformer 计算机科学, 2022, 49(6A): 370-377. https://doi.org/10.11896/jsjkx.210500023 |
[14] | 王建明, 陈响育, 杨自忠, 史晨阳, 张宇航, 钱正坤. 不同数据增强方法对模型识别精度的影响 Influence of Different Data Augmentation Methods on Model Recognition Accuracy 计算机科学, 2022, 49(6A): 418-423. https://doi.org/10.11896/jsjkx.210700210 |
[15] | 孙洁琪, 李亚峰, 张文博, 刘鹏辉. 基于离散小波变换的双域特征融合深度卷积神经网络 Dual-field Feature Fusion Deep Convolutional Neural Network Based on Discrete Wavelet Transformation 计算机科学, 2022, 49(6A): 434-440. https://doi.org/10.11896/jsjkx.210900199 |
|