边缘智能(Edge Intelligence) Cloud data center 。云-边-端协同处理框架 Deep learning ●将人工智能算法（当前主要是 Internet Deep 深度学习)推向边缘 learning 九 Edge Edge ●加速AI的发展 server server ·驱动力有四个方面：算法、硬件、 Edge devices 数据和应用场景 End devices ● 边缘端丰富的应用场景和多样化 Deep learning 的数据促进了AI进一步发展 [1]JIASI CHEN AND XUKAN RAN,Deep Learning With Edge Computing:A Review,Proceedings of the IEEE,May 2019
ƊŐûŘ(Edge Intelligence) [1] JIASI CHEN AND XUKAN RAN, Deep Learning With Edge Computing: A Review, Proceedings of the IEEE, May 2019. l ,-Ɗ-ŀm}ĥĊĆ l «1²ûŘŃĕÉa&ťø ęÁ)è~ƊŐ l dƗAIīw¯ l ưfcþ"ôƬŃĕĵ; ðå¿ħú l ƊŐŀ$¨ī¿ħúĈj īðåLƐ*AIƐĐw¯
深度学习的训练和推理 Cloud ● 经典模式：云端训练+边缘推理 Cloud Training (Takes hours,Days) Forward ·选配模式：边缘训练，基于本 地的数据特性来进行定制化的 Cloud Data 训练 Edge ● 通过Pruning、Dropout等方 Edge Data Generation Edge Inference (Takes ms.seconds) 法降低训练参数量 ●通过迁移学习快速训练 Edge Local Training ·通过强化学习迭代训练
ęÁ)īŭʼnèĥ l ŊUčÄ,ŀŭʼnƊŐèĥ l ƕƜčÄƊŐŭʼn+ÿ īðåĞÓĂƐŢ¢`jī ŭʼn l ƖƍPruningDropoutŁô ĕƦDŭʼnuðƞ l Ɩƍƌļ)ÏƗŭʼn l ƖƍÈj)ƒ8ŭʼn
边缘训练模型 Edge server DNN to be Gradient update trained Gradient can be compressed or sen infrequently Gradient update End device End device (b)Decentralized training. (a)Centralized training. ·集中式训练：Each worker computes local data set,which are then collected by a central parameter server,and the updates sent back to the workers.代表性模型：联邦学习 ·分布式训练：Each device computes its own gradient updates based on its training data and then communicates its updates to some of the other devices. ·两种模型比较：DNN模型一致性、带宽限制等
ƊŐŭʼnč • Ʃ#Äŭʼn: Each worker computes local data set, which are then collected by a central parameter server, and the updates sent back to the workers. 8ţÓčŖƚ) • Z·Äŭʼn: Each device computes its own gradient updates based on its training data and then communicates its updates to some of the other devices. • !ĻčĒƆDNNčśÓ¹§Ƨ`Ł
边缘推理模型 Edge Edge Server Server (a)Edge-based mode Device A Device B (b)Device-based mode (a)Edge-based mode. (b)Device-based mode. (c)Edge-device mode Edge Edge Server Server (d)Edge-cloud mode Cloud Data Center Device Device D (c)Edge-device mode. (d)Edge-cloud mode
ƊŐèĥč aEdge-based mode bDevice-based mode cEdge-device mode dEdge-cloud mode
边缘智能的6个等级 Level 6 All on-device 根据数据卸载的数量和路 Level 5 All in-adge 径长度，我们将边缘智能 Reduced amount or shorten path of data offloading Levol 4 分成6个等级 Cloud-edge co-training Level3 On-device inference 层级越高，数据卸载的数 量和路径长度越少，从而 Lovel 2 Training In-edge co-inference on the cloud 时延、带宽、安全有优势， Level 1 但会增加计算延迟和能耗 Cloud-edge co-inference 代价 Cloud Intelligence Training and inference on the cloud [2]Zhi Zhou,Xu Chen,En Li,Liekang Zeng,Ke Luo,and Junshan Zhang,Edge Intelligence:Paving the Last Mile of Artificial Intelligence with Edge Computing,Proceedings of the IEEE,May 2019
ƊŐûŘī "ŁŇ [2] Zhi Zhou, Xu Chen, En Li, Liekang Zeng, Ke Luo, and Junshan Zhang, Edge Intelligence: Paving the Last Mile of Artificial Intelligence with Edge Computing, Proceedings of the IEEE, May 2019. • ĉåðåsƅīðƞſ ÍơÁØ:«ƊŐûŘ Z× "ŁŇ • ®ŇżƳðåsƅīð ƞſÍơÁż6Ŕ ÷¹§ Rþ>h B?dūŃÂƑŘŕ 8<