Learning and Energy Efficient Edge Intelligence: Data Partition and Rate Control

Xiaoyang Li1; Shuai Wang1; Guangxu Zhu2; Ziqin Zhou1; Kaibin Huang3; Yi Gong1

10.1109/ICC45855.2022.9838801

2022

IEEE International Conference on Communications (ICC)

1550-3607

978-1-5386-8348-4

ICC 2022 - IEEE International Conference on Communications

2022-May

5353-5358

16-20 May 2022

Seoul, Korea, Republic of

345 E 47TH ST, NEW YORK, NY 10017 USA

IEEE

The rapid development of artificial intelligence together with the powerful computation capabilities of the advanced edge servers make it possible to deploy learning tasks at the wireless network edge, which is dubbed as edge intelligence (EI). The communication bottleneck between the data resource and the server results in deteriorated learning performance as well as tremendous energy consumption. To tackle this challenge, we explore a new paradigm called learning-and-energy-efficient (LEE) EI, which simultaneously maximizes the learning accuracies and energy efficiencies of multiple tasks via data partition and rate control. Mathematically, this results in a multi-objective optimization problem. Moreover, the continuous varying rates introduce infinite variables, which further complicates the problem. To solve this complex problem, the number of variables is reduced to a finite level by exploiting the optimality of constant-rate transmission in each epoch, based on which a string-pulling (SP) algorithm is proposed to obtain the numerical values. The performance of the proposed joint data partition and rate control design is examined by experiments based on public datasets.

Edge intelligence learning efficiency energy efficiency data partition rate control

第一

英语

EI ; CPCI-S

National Key R&D Program of China[2019YFB1802800]

Telecommunications

Telecommunications

WOS:000864709905091

20223712710811

Data handling ; Energy utilization ; Multiobjective optimization

Energy Conservation:525.2 ; Energy Utilization:525.3 ; Data Processing and Image Processing:723.2 ; Optimization Techniques:921.5

IEEE

1.Southern University of Science and Technology, Shenzhen, China
2.Shenzhen Research Institute of Big Data, Shenzhen, China
3.The University of Hong Kong, Hong Kong

Xiaoyang Li,Shuai Wang,Guangxu Zhu,et al. Learning and Energy Efficient Edge Intelligence: Data Partition and Rate Control[C]. 345 E 47TH ST, NEW YORK, NY 10017 USA:IEEE,2022:5353-5358.