Authors :
Gowrisankar Krishnamoorthy; Bhargav Kumar Konidena; Naveen Pakalapati
Volume/Issue :
Volume 9 - 2024, Issue 2 - February
Google Scholar :
https://tinyurl.com/udm9vu5d
Scribd :
https://tinyurl.com/3kn2nnh2
DOI :
https://doi.org/10.5281/zenodo.10776717
Abstract :
The integration of machine learning in edge
computing has emerged as a transformative paradigm,
offering unprecedented opportunities and challenges. This
review paper explores the consequences for network
architecture, privacy, security, and resource efficiency
while also delving into the dynamic environment of this
convergence. The article guides the reader through the
developments in artificial intelligence (AI) in edge
computing settings using current research findings. This
article covers important topics such as energy use
optimization and data processing efficiency, summarizing
important discoveries and offering a comprehensive
overview of the state of machine learning in edge
computing. A thorough analysis of AI methods, compute
offloading techniques, and security precautions clarifies
the way forward for utilizing edge computing and machine
learning in the future.
Keywords :
Machine Learning, Edge Computing, Opportunities and Challenges, Architectural Layout, Security, Resource Constraints, Real-time Data Processing, Edge Computing Platforms, AI Algorithms, Data Privacy, Computing Offloading Strategies.
The integration of machine learning in edge
computing has emerged as a transformative paradigm,
offering unprecedented opportunities and challenges. This
review paper explores the consequences for network
architecture, privacy, security, and resource efficiency
while also delving into the dynamic environment of this
convergence. The article guides the reader through the
developments in artificial intelligence (AI) in edge
computing settings using current research findings. This
article covers important topics such as energy use
optimization and data processing efficiency, summarizing
important discoveries and offering a comprehensive
overview of the state of machine learning in edge
computing. A thorough analysis of AI methods, compute
offloading techniques, and security precautions clarifies
the way forward for utilizing edge computing and machine
learning in the future.
Keywords :
Machine Learning, Edge Computing, Opportunities and Challenges, Architectural Layout, Security, Resource Constraints, Real-time Data Processing, Edge Computing Platforms, AI Algorithms, Data Privacy, Computing Offloading Strategies.
