Federated Learning and Proactive Computation Reuse at the Edge of Smart Homes

被引:17
作者
Nour, Boubakr [1 ]
Cherkaoui, Soumaya [1 ]
Mlika, Zoubeir [1 ]
机构
[1] Univ Sherbrooke, Fac Engn, Dept Elect & Comp Sci Engn, INTERLAB Res Lab, Sherbrooke, PQ J1K 2R1, Canada
来源
IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING | 2022年 / 9卷 / 05期
基金
加拿大自然科学与工程研究理事会;
关键词
Servers; Task analysis; Data privacy; Smart homes; Computational modeling; Data models; Training; Edge Computing; Computation Reuse; Federated Learning; Internet of Things; Collaborative Learning; CHALLENGES; IOT;
D O I
10.1109/TNSE.2021.3131246
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
Edge-based technologies have emerged as a key enabler to empower low-latency services and incorporate machine learning techniques for learning/inference. However, transferring user data to the edge server to conduct learning could violate data privacy and overburden the network. In addition, the server could receive multiple redundant tasks for inference which leads to redundant computations. In this article, we study both communication and computation issues in edge networks by emphasizing data privacy in a smart home scenario. We design an architecture that incorporates federated edge learning to promote data privacy and a node weighting and dropping scheme to select the appropriate participating devices with quality data and therefore improve the training and reduce communication cost. We further apply Long Short-Term Memory to predict future tasks and proactively store them locally at the edge device. We adopt the computation reuse concept to satisfy incoming tasks with less-to-no computation and thus eliminating redundant computation and further decreasing the computation cost. Simulation results based on real-world dataset show the effectiveness and efficiency of the proposed architecture. The training phase is reached with few iterations, while computation and communication are reduced by up to 80% and 70%, respectively, compared with existing schemes while data privacy is promoted.
引用
收藏
页码:3045 / 3056
页数:12
相关论文
共 42 条
[11]   FedHealth: A Federated Transfer Learning Framework for Wearable Healthcare [J].
Chen, Yiqiang ;
Qin, Xin ;
Wang, Jindong ;
Yu, Chaohui ;
Gao, Wen .
IEEE INTELLIGENT SYSTEMS, 2020, 35 (04) :83-93
[12]   Industrial Edge Computing Enabling Embedded Intelligence [J].
Dai, Wenbin ;
Nishi, Hiroaki ;
Vyatkin, Valeriy ;
Huang, Victor ;
Shi, Yang ;
Guan, Xinping .
IEEE INDUSTRIAL ELECTRONICS MAGAZINE, 2019, 13 (04) :48-56
[13]   Cachier: Edge-caching for recognition applications [J].
Drolia, Utsav ;
Guo, Katherine ;
Tan, Jiaqi ;
Gandhi, Rajeev ;
Narasimhan, Priya .
2017 IEEE 37TH INTERNATIONAL CONFERENCE ON DISTRIBUTED COMPUTING SYSTEMS (ICDCS 2017), 2017, :276-286
[14]   AutoMEC: LSTM-based User Mobility Prediction for Service Management in Distributed MEC Resources [J].
Fattore, Umberto ;
Liebsch, Marco ;
Brik, Bouziane ;
Ksentini, Adlen .
PROCEEDINGS OF THE 23RD INTERNATIONAL ACM CONFERENCE ON MODELING, ANALYSIS AND SIMULATION OF WIRELESS AND MOBILE SYSTEMS, MSWIM 2020, 2020, :155-159
[15]   Game Theoretical Analysis on Acceptance of a Cloud Data Access Control System Based on Reputation [J].
Gao, Lijun ;
Yan, Zheng ;
Yang, Laurence T. .
IEEE TRANSACTIONS ON CLOUD COMPUTING, 2020, 8 (04) :1003-1017
[16]   Diversity in Machine Learning [J].
Gong, Zhiqiang ;
Zhong, Ping ;
Hu, Weidong .
IEEE ACCESS, 2019, 7 :64323-64350
[17]   Privacy on the Edge: Customizable Privacy-Preserving Context Sharing in Hierarchical Edge Computing [J].
Gu, Bruce ;
Gao, Longxiang ;
Wang, Xiaodong ;
Qu, Youyang ;
Jin, Jiong ;
Yu, Shui .
IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING, 2020, 7 (04) :2298-2309
[18]   FoggyCache: Cross-Device Approximate Computation Reuse [J].
Guo, Peizhen ;
Hu, Bo ;
Li, Rui ;
Hu, Wenjun .
MOBICOM'18: PROCEEDINGS OF THE 24TH ANNUAL INTERNATIONAL CONFERENCE ON MOBILE COMPUTING AND NETWORKING, 2018, :19-34
[19]  
Guo PZ, 2018, ACM SIGPLAN NOTICES, V53, P271, DOI [10.1145/3173162.3173185, 10.1145/3296957.3173185]
[20]   Deep Residual Learning for Image Recognition [J].
He, Kaiming ;
Zhang, Xiangyu ;
Ren, Shaoqing ;
Sun, Jian .
2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :770-778