Feasibility Study of Edge Computing Empowered by Artificial Intelligence—A Quantitative Analysis Based on Large Models

Author:

Chen Yan1,Wu Chaonan1,Sui Runqi2ORCID,Zhang Jingjia3

Affiliation:

1. School of Economics and Management, Beijing University of Posts and Communications, Beijing 100876, China

2. School of Cyberspace Security, Beijing University of Posts and Communications, Beijing 100876, China

3. APEC Study Center of Nankai University, Nankai University, Tianjin 300071, China

Abstract

The advancement of artificial intelligence (AI) demands significant data and computational resources that have an adverse impact on the environment. To address this issue, a novel computing architecture that is both energy efficient and eco-friendly is urgently required. Edge computing has emerged as an increasingly popular solution to this problem. In this study, we explore the development history of edge computing and AI and analyze the potential of model quantization to link AI and edge computing. Our comparative analysis demonstrates that the quantization approach can effectively reduce the model’s size and accelerate model inference while maintaining its functionality, thereby enabling its deployment on edge devices. This research serves as a valuable guide and reference for future advancements in edge AI.

Funder

Chinese Academy of Engineering Strategic Research and Consulting Program

Major Project of the Key Research Institutions for Humanities and Social Sciences of the Ministry of Education of China

Publisher

MDPI AG

Reference44 articles.

1. Zhou, Y., Guo, C., Wang, X., Chang, Y., and Wu, Y. (2024). A survey on data augmentation in large model era. arXiv.

2. Kaddour, J., Harris, J., Mozes, M., Bradley, H., Raileanu, R., and McHardy, R. (2023). Challenges and applications of large language models. arXiv.

3. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A., and Polosukhin, I. (2017, December 04). Attention Is All You Need. Advances in Neural Information Processing Systems. Available online: https://proceedings.neurips.cc/paper_files/paper/2017/file/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf.

4. China Academy of Information and Communications Technology (CAICT) (2024). The Whitepaper on the Global Digital Economy, CAICT.

5. Chinanews (2024, July 09). The Number of Large Models with Scale of Over 1 Billion Parameters in China Has Exceeded 100. Available online: https://www.chinanews.com.cn/gn/2024/03-25/10186743.shtml.

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3