Publication Date

Fall 2021

Degree Type

Master's Project

Degree Name

Master of Science (MS)

Department

Computer Science

First Advisor

Teng Moh

Second Advisor

Melody Moh

Third Advisor

Kong Li

Keywords

Privacy-preserving, Federated Learning, Dual User-Adaptation, FedAvg, FedProx

Abstract

The internet of things (IoT) is an integrated part of contemporary life. It includes wearable devices, such as smart watches and cell phones, as well as sensors for Smart City. Fog computing can improve the efficiency and battery life of IoT devices by offloading tasks to fog cloud. It is important to have fog clusters near the IoT device for faster data offload. The goal of this project is to develop dynamic resource allocation for on-demand fog computing cluster to efficiently deploy tasks from IoT. This report studies the different research papers about the current state of resource management in cloud environment. It overviews the main mechanisms, objectives, and the evaluation criteria of the state-of-the art solutions. This report discusses the results of different modifications of memetic algorithm. In our project, we try to minimize the task completion delay, number of requests failed by deadline for all services and services with the high priority by finding the closest to a user fog node that has enough available resource. In this project we will use Yet Another Fog Simulator (YAFS) for simulating and testing the effectiveness of proposed memetic algorithms modifications.

Available for download on Saturday, December 17, 2022

Share

COinS