2.STC-Abstract

The document presents a seminar abstract by Sankalp Sandeep Indish on automating AI service deployment in Multi-Access Edge Computing (MEC) scenarios. It introduces the VEF Edge Framework, which addresses the diverse requirements of AI applications while optimizing resource management and minimizing latency. Experimental results demonstrate the framework's effectiveness in enhancing performance for AI services in MEC environments.

Uploaded by

sankalp.indish23

We take content rights seriously. If you suspect this is your content, claim it here.

Available Formats

Download as DOCX, PDF, TXT or read online on Scribd

0% found this document useful (0 votes)

3 views

2.STC-Abstract

Uploaded by

sankalp.indish23

We take content rights seriously. If you suspect this is your content, claim it here.

Available Formats

Download as DOCX, PDF, TXT or read online on Scribd

You are on page 1/ 1

“Techno-Social Excellence”

Marathwada Mitra Mandal’s

INSTITUTE OF TECHNOLOGY
Lohgaon, Pune-47

“Towards Ubiquitous Computing Technology”

Department of Computer Engineering
TE Seminar (Abstract)
(A.Y. 2024-25)

Name of Student:- Sankalp Sandeep Indish

Class:- TE COMP Roll No.:- TEB75
Guide Name:- Mr. Sanjay. A. Agrawal
Domain Name:- Multiaccess Edge Computing(MEC) + AI
Seminar Topic Automating the Deployment of Artificial Intelligence Services in Multi-
Name:- access Edge Computing Scenarios.
Abstract:-
The rise of edge computing, particularly Multi-Access Edge Computing (MEC), has spurred
significant interest due to its benefits over traditional cloud computing, such as reduced latency and
lower energy consumption. This has made MEC an ideal platform for deploying artificial intelligence
(AI) services. However, these AI services come with diverse requirements, including varying
computational resources, data formats, and communication protocols. To address these challenges,
we introduce the VEF Edge Framework. This framework is designed to facilitate the development
and deployment of AI services in MEC environments, focusing on minimizing latency and
optimizing CPU and memory usage.
The VEF Edge Framework stands out by providing a robust solution that addresses the complex
needs of AI applications, ensuring they can operate efficiently in edge computing scenarios. We have
meticulously detailed the VEF architecture to highlight its innovative approach to resource
management and service deployment. Additionally, our experimental results underscore the
framework's effectiveness. Specifically, we implemented an object detection inference service using
VEF to benchmark its performance. Our experiments assessed CPU and memory consumption for
VEF's key components and evaluated processing times for inference and video stream handling.
These findings demonstrate the practical advantages of the VEF Edge Framework, paving the way
for more efficient and scalable AI service deployments in MEC settings. By leveraging VEF,
developers can ensure their AI applications meet stringent performance requirements, ultimately
enhancing the overall user experience.