Container load prediction algorithm based on convolution neural network and self-attention

Xin Xie; Chen Wang; Dongcheng Zhang; Liyuan Zheng; Pengxiang Gao

doi:10.1117/12.2690009

7 September 2023 Container load prediction algorithm based on convolution neural network and self-attention

Xin Xie, Chen Wang, Dongcheng Zhang, Liyuan Zheng, Pengxiang Gao

Proceedings Volume 12790, Eighth International Conference on Electromechanical Control Technology and Transportation (ICECTT 2023); 127904Z (2023) https://doi.org/10.1117/12.2690009
Event: 8th International Conference on Electromechanical Control Technology and Transportation (ICECTT 2023), 2023, Hangzhou, China

Abstract

Containers are currently the core technology of cloud computing, which has attracted wide attention from industry and academia. However, dynamically allocating resources to use containers reasonably is a huge challenge. This article proposes a container load prediction algorithm based on convolutional neural networks and attention (CAA-Net) to provide reference for container resource scheduling. CAA-Net obtains global information by global convolution and local information by local convolution, and fuses the two kinds of information to predict the load. Finally, this article verifies the accuracy of the algorithm through experiments.

Citation Download Citation

Xin Xie, Chen Wang, Dongcheng Zhang, Liyuan Zheng, and Pengxiang Gao "Container load prediction algorithm based on convolution neural network and self-attention", Proc. SPIE 12790, Eighth International Conference on Electromechanical Control Technology and Transportation (ICECTT 2023), 127904Z (7 September 2023); https://doi.org/10.1117/12.2690009

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available