首页|NeurstrucEnergy:A bi-directional GNN model for energy prediction of neural networks in IoT

NeurstrucEnergy:A bi-directional GNN model for energy prediction of neural networks in IoT

扫码查看
原文链接
  • NETL
  • NSTL
  • 万方数据
A significant demand rises for energy-efficient deep neural networks to support power-limited embedding devices with successful deep learning applications in IoT and edge computing fields.An accurate energy prediction approach is critical to provide measurement and lead optimization direction.However,the current energy pre-diction approaches lack accuracy and generalization ability due to the lack of research on the neural network structure and the excessive reliance on customized training dataset.This paper presents a novel energy prediction model,NeurstrucEnergy.NeurstrucEnergy treats neural networks as directed graphs and applies a bi-directional graph neural network training on a randomly generated dataset to extract structural features for energy predic-tion.NeurstrucEnergy has advantages over linear approaches because the bi-directional graph neural network collects structural features from each layer's parents and children.Experimental results show that Neu-rstrucEnergy establishes state-of-the-art results with mean absolute percentage error of 2.60％.We also evaluate NeurstrucEnergy in a randomly generated dataset,achieving the mean absolute percentage error of 4.83％over 10 typical convolutional neural networks in recent years and 7 efficient convolutional neural networks created by neural architecture search.Our code is available at https://github.com/NEUSoftGreenAI/NeurstrucEnergy.git.

Internet of thingsNeural network energy predictionGraph neural networksGraph structure embeddingMulti-head attention

Chaopeng Guo、Zhaojin Zhong、Zexin Zhang、Jie Song

展开 >

Software Campus,Northeastern University,Shenyang,110000,Liaoning,China

Natural Science Foundation of Liaoning ProvinceFundamental Research Funds for the Central UniversitiesNational Natural Science Foundation of China

2020-BS-054N201700562162050

2024

10.1016/j.dcan.2022.09.006

数字通信与网络(英文)

数字通信与网络(英文)

ISSN：
年,卷(期)：2024.10(2)
  • 58