计算机科学 ›› 2022, Vol. 49 ›› Issue (9): 249-259.doi: 10.11896/jsjkx.220500222
胡玉姣1, 贾庆民1, 孙庆爽2, 谢人超1,3, 黄韬1,3
HU Yu-jiao1, JIA Qing-min1, SUN Qing-shuang2, XIE Ren-chao1,3, HUANG Tao1,3
摘要: 面向算力网络新兴研究领域,针对其迫切需要提升智能性与精准服务能力的问题,提出了云边端算力资源、网络资源、智能模型及算法协同共生的融智算力网络建设理念,引入了内生智能和业务智能两个层面的智能性。内生智能指算力网络为保障系统准确运行所具备的自感知、自适应、自决策、自学习能力,业务智能指算力网络为增强对行业/应用的适应性所具备的智能资源封装及自主部署能力、业务编排与认知能力。进一步地,设计了层次化功能架构,从基础资源、资源管理、业务编排、运营服务以及系统优化5个层面明确了AI赋能融智算力网络内生智能与业务智能的具体表现。最后,将智能制造及智慧安防两类应用中的3个场景(车间物流、基于机器视觉的质检品控、社区及道路监测)作为仿真实验原型场景,并设计了对比实验组。实验结果表明,应用融智算力网络至车间物流场景中,性能提升幅度与场景规模有关,规划用时提升了约2~50倍,规划结果提升了约2~5倍;基于机器视觉的质检品控场景中,算力设备部署成本下降为原来的1/5、检测准确率提升约4.5%;社区及道路监测场景中,系统的算力部署成本可降低为原来的1/10。
中图分类号:
[1]新型数据中心发展三年行动计划(2021-2023年)解读[OL].2021-07-16.http://www.gov.cn/zhengce/2021-07/16/content_5625389.htm. [2]关于印发《全国一体化大数据中心协同创新体系算力枢纽实施方案》的通知[OL].2021-05-24.http://www.gov.cn/zhengce/zhengceku/2021-05/26/content_5612405.htm. [3]中华人民共和国国家发展和改革委员会.东数西算[OL].https://www.ndrc.gov.cn/xwdt/ztzl/dsxs/?code=&state=123. [4]“东数西算”让数字化“脚步”更快更稳[OL].2022-02-28.http://www.gov.cn/zhengce/2022-02/28/content_5675995.htm. [5]工业和信息化部关于印发《新型数据中心发展三年行动计划(2021-2023年)》的通知[OL].2021-07-04.http://www.gov.cn/zhengce/zhengceku/2021-07/14/content_5624964.htm. [6]China Mobile.Computing Force Network WhitePaper[M/OL].https://www.vzkoo.com/document/568a222bc5892fb727aa400ea6c8e828.html?keyword=%E7%AE%97%E5%8A%9B%E7%BD%91%E7%BB%9C. [7]China Academy of Information and Communications Technology.White Paper on China's Computing Power Development Index[M/OL].http://www.caict.ac.cn/kxyj/qwfb/bps/202109/t20210918_390058.htm. [8]China Mobile.Diversity Computing Technology Vision WhitePaper[M/OL].https://www.vzkoo.com/document/b2d9baf73ecc3e9e5448dd10df64b321.html?keyword=%E5%A4%9A%E6%A0%B7%E6%80%A7%E7%AE%97%E5%8A%9B. [9]China Unicom.Computer Power Network WhitePaper[M/OL].https://wenku.baidu.com/view/5817c423b868a98271fe910ef12d2af90342a844.html. [10]China Mobile,HuaWei.Computing-awareNetworking WhitePaper[M/OL].https://www.vzkoo.com/document/297a189187b473cd9132bf706651c333.html?keyword=%E7%AE%97%E5%8A%9B%E7%BD%91%E7%BB%9C%E7%99%BD%E7%9A%AE%E4%B9%A6. [11]China Institute of Communications.Computing Network Frontier Report[R/OL].https://www.vzkoo.com/document/a9255c0ed9e4db735d93e42b1f3ab839.html?keyword=%E7%AE%97%E5%8A%9B%E5%89%8D%E6%B2%BF. [12]LEI B,LIU Z Y,WANG X L,et al.Computing network:a new multi-access edge computing[J].Telecommunications Science,2019,35(9):44-51. [13]DUAN X D,YAO H J,FU Y X,et al.Computing force network technologies for computing and network integration evolution[J].Telecommunications Science,2021,37(10):76-85. [14]ZHANG S,CAO C,TANG X Y.Computing Power NetworkTechnology Architecture Based on SRv6[J/OL].ZTE Communications,2022.https://www.cnki.com.cn/Article/CJFDTotal-ZXTX202201005.htm. [15]DI Z,CAO Y F,QIU C,et al.New computing power network architecture and its application case analysis [J/OL].Computer Application.https://d.wanfangdata.com.cn/periodical/jsjyy202206002. [16]HUANG G P,SHI W Q,TAN B.Computing Power NetworkResources Based on SRv6 and Its Service Arrangement and Scheduling[J/OL].ZTE Communications.https://www.zte.com.cn/china/about/magazine/zte-communications/2021/cn202103/specialtopic/cn202103006.html. [17]LI J F,CAO C,LI A,et al.Computing Power Modeling for Business Experience in Computing Power Network[J/OL].ZTE Communications.https://s.wanfangdata.com.cn/periodical?q=Mixed%20supervision%20for%20surface-defect%20detec-tion%3A%20From%20weakly%20to%20fully%20super-vised%20learning. [18]GONG C Y,SHU H F,ZHANG X.Multi-level computing po-wer network centralized indivisible task scheduling algorithm[J/OL].ZTE Communications.https://www.zte.com.cn/china/about/magazine/zte-communications/2021/cn202103/specialtopic/cn202103008. [19]LIU Z N,LI K,WU L T,et al.CATS:Cost Aware Task Sche-duling in Multi-Tier Computing Networks[J].Journal of Computer Research and Development,2020,57(9):1810-1822. [20]SUN Y K,ZHANG X,LEI B.Research on intelligent computing power-aware routing allocation strategy in edge computing po-wer network[J].Radio Communications Technology,2022,48(1):60-67. [21]JIA Q M,DING R,LIU H,et al.Survey on research progress for compute first networking[J].Chinese Journal of Network and Information Security,2021,7(5):1-12. [22]HU Y J,YAO Y,LEE W S.A reinforcement learning approachfor optimizing multiple traveling salesman problems over graphs[J].Knowledge-Based Systems,2020,204:106244.1-106244.14. [23]KAEMPFER Y,WOLF L.Learning the multiple travelingsalesmen problem with permutation invariant pooling networks[J].arXiv:1803.09621,2018. [24]BOŽIČ J,TABERNIK D,SKOČAJ D.Mixed supervision for surface-defect detection:From weakly to fully supervised lear-ning[J].Computers in Industry,2021,129:103459. [25]BOŽIČ J,TABERNIK D,SKOČAJ D.End-to-end training of a two-stage neural network for defect detection[C]//2020 25th International Conference on Pattern Recognition (ICPR).IEEE,2021:5619-5626. [26]TABERNIK D,ŠELA S,SKVARČ J,et al.Segmentation-based deep-learning approach for surface-defect detection[J].Journal of Intelligent Manufacturing,2020,31(3):759-776. [27]LOPES V,ALEXANDRE L A.Auto-classifier:A robust defect detector based on an automl head[C]//International Conference on Neural Information Processing.Cham:Springer,2020:137-149. [28]RUDOLPH M,WANDT B,ROSENHAHN B.Same same butdiffernet:Semi-supervised defect detection with normalizing flows[C]//Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision.2021:1907-1916. [29]ZAMIR S W,ARORA A,KHAN S,et al.Restormer:Efficient transformer for high-resolution image restoration[C]//Procee-dings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2022:5728-5739. [30]DAI Z,LIU H,LE Q V,et al.Coatnet:Marrying convolution and attention for all data sizes[J].Advances in Neural Information Processing Systems,2021,34:3965-3977. [31]XU Q,ZHOU Y,WANG W,et al.Spg:Unsupervised domain adaptation for 3d object detection via semantic point generation[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision.2021:15446-15456. [32]REDDY N D,GUIGUES L,PISHCHULIN L,et al.Tessetrack:End-to-end learnable multi-person articulated 3d pose tracking[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2021:15190-15200. |
[1] | 李梦菲, 毛莺池, 屠子健, 王瑄, 徐淑芳. 基于深度确定性策略梯度的服务器可靠性任务卸载策略 Server-reliability Task Offloading Strategy Based on Deep Deterministic Policy Gradient 计算机科学, 2022, 49(7): 271-279. https://doi.org/10.11896/jsjkx.210600040 |
[2] | 魏鹏, 马玉亮, 袁野, 吴安彪. 用户行为驱动的时序影响力最大化问题研究 Study on Temporal Influence Maximization Driven by User Behavior 计算机科学, 2022, 49(6): 119-126. https://doi.org/10.11896/jsjkx.210700145 |
[3] | 刘丽, 李仁发. 医疗CPS协作网络控制策略优化 Control Strategy Optimization of Medical CPS Cooperative Network 计算机科学, 2022, 49(6A): 39-43. https://doi.org/10.11896/jsjkx.210300230 |
[4] | 沈超, 何希平. 基于纹理特征增强和轻量级网络的人脸防伪算法 Face Anti-spoofing Algorithm Based on Texture Feature Enhancement and Light Neural Network 计算机科学, 2022, 49(6A): 390-396. https://doi.org/10.11896/jsjkx.210600217 |
[5] | 刘云, 董守杰. 基于CUDA核函数的多路视频图像拼接加速算法 Acceleration Algorithm of Multi-channel Video Image Stitching Based on CUDA Kernel Function 计算机科学, 2022, 49(6A): 441-446. https://doi.org/10.11896/jsjkx.210600043 |
[6] | 朱旭辉, 沈国娇, 夏平凡, 倪志伟. 基于螺旋进化萤火虫算法和BP神经网络的模型及其在PPP融资风险预测中的应用 Model Based on Spirally Evolution Glowworm Swarm Optimization and Back Propagation Neural Network and Its Application in PPP Financing Risk Prediction 计算机科学, 2022, 49(6A): 667-674. https://doi.org/10.11896/jsjkx.210800088 |
[7] | 杨晓宇, 殷康宁, 候少麒, 杜文仪, 殷光强. 基于特征定位与融合的行人重识别算法 Person Re-identification Based on Feature Location and Fusion 计算机科学, 2022, 49(3): 170-178. https://doi.org/10.11896/jsjkx.210100132 |
[8] | 陈贵强, 何军. 自然场景下遥感图像超分辨率重建算法研究 Study on Super-resolution Reconstruction Algorithm of Remote Sensing Images in Natural Scene 计算机科学, 2022, 49(2): 116-122. https://doi.org/10.11896/jsjkx.210700095 |
[9] | 李玉, 段宏岳, 殷昱煜, 高洪皓. 基于区块链的去中心化众包技术综述 Survey of Crowdsourcing Applications in Blockchain Systems 计算机科学, 2021, 48(11): 12-27. https://doi.org/10.11896/jsjkx.210600152 |
[10] | 廉文娟, 赵朵朵, 范修斌, 耿玉年, 范新桐. 基于认证及区块链的CFL_BLP_BC模型 CFL_BLP_BC Model Based on Authentication and Blockchain 计算机科学, 2021, 48(11): 36-45. https://doi.org/10.11896/jsjkx.201000002 |
[11] | 杨青, 张亚文, 朱丽, 吴涛. 基于注意力机制和BiGRU融合的文本情感分析 Text Sentiment Analysis Based on Fusion of Attention Mechanism and BiGRU 计算机科学, 2021, 48(11): 307-311. https://doi.org/10.11896/jsjkx.201000075 |
[12] | 高熙, 孙未未. 集装箱码头岸桥最优调度理论研究和高效算法 Theoretical Research and Efficient Algorithm of Container Terminal Quay Crane Optimal Scheduling 计算机科学, 2021, 48(11A): 22-29. https://doi.org/10.11896/jsjkx.201200167 |
[13] | 代闯闯, 栾海晶, 杨雪莹, 过晓冰, 陆忠华, 牛北方. 区块链技术研究综述 Overview of Blockchain Technology 计算机科学, 2021, 48(11A): 500-508. https://doi.org/10.11896/jsjkx.201200163 |
[14] | 刘彤彤, 杨环, 西永明, 郭建伟, 潘振宽, 黄宝香. 机器学习在脊柱疾病智能诊治中的应用综述 Review on Intelligent Diagnosis of Spine Disease Based on Machine Learning 计算机科学, 2021, 48(11A): 597-607. https://doi.org/10.11896/jsjkx.201100006 |
[15] | 穆聪聪, 王一舒, 袁野, 乔百友, 马玉亮. 时序图中Top-k稠密子图查询算法研究 Top-k Densest Subgraphs Search in Temporal Graphs 计算机科学, 2021, 48(10): 152-159. https://doi.org/10.11896/jsjkx.201100005 |
|