Edge Intelligence Paradigm Shift on Optimizing the Edge Intelligence Using Artificial Intelligence State-of-the-Art Models

Author:

Chandrasekaran Saravanan1ORCID,Athinarayanan S.2ORCID,Masthan M.3,Kakkar Anmol1,Bhatnagar Pranav4,Samad Abdul1

Affiliation:

1. Department of Computer Science and Engineering, SRM Institute of Science and Technology, Ramapuram, India

2. Department of CSE, School of Computing, Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology (Deemed), Avadi, India

3. Arffy Technologies Private Limited, Bengaluru, India

4. Department of Computer Science and Business Systems, SRM Institute of Science and Technology, Ramapuram, India

Abstract

Edge AI changes data processing (EI) strategy incorporating powerful AI capabilities directly at the network's edge, where devices and sensors gather data. This convergence solves cloud-centric AI's latency and bandwidth challenges by enabling real-time analysis and decision-making. Three paradigm-shifting effects of edge intelligence include localized processing allowing real-time data analysis and quick responses. Second, minimizing large-scale data transfers to centralized cloud services greatly minimizes latency. Third, edge intelligence's distributed architecture reduces centralized system demand, boosting infrastructure resilience and scalability and enabling new developments. Imagine smart cities using edge-based analysis to enhance traffic flow or autonomous cars making quick sensor-based choices. Data at the network edge needs security. AI algorithms must work on low-resource edge devices. Edge intelligence can solve these issues and enable near-instantaneous network decision-making, changing numerous industries. Edge computing (EC) solved this problem by moving processing closer to data sources, but edge intelligence introduced AI at the network edge. This unique solution uses AI to increase edge device capabilities beyond data processing. A network edge device can learn, decide, and infer in real-time with EI. Integration reduces latency, boosts efficiency, and empowers intelligent devices. This chapter covers the need for solid EI infrastructure and cutting-edge AI models to optimize the edge device (ED). AI's astounding results in numerous fields have inspired EC researchers to investigate its potential, particularly in machine learning (ML), a fast-growing discipline of AI. This chapter defines EC and explains its popularity. EC's fundamental issues and flaws in traditional methods are then examined. This chapter shows research on optimizing EC and applying AI within the EC framework for different areas to stimulate new research lines that exploit AI and EC's synergy.

Publisher

IGI Global

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