Efficient Edge Resource Management and Enhancing Quality of Services QoS in IOT Through Edge Intelligence
Loading...
Date
item.page.authors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
The rapid expansion of the Internet of Things (IoT) and the development with
newlinepowerful services in the cloud contributed to the advancement on edge computing, which
newlineallows for data processing at edge nodes inside the cloud network. This research proposes
newlinea machine learning-based approach leveraging edge intelligence to enhance efficient edge
newlineresource management and Quality of Service (QoS) for end-users within IoT platforms.
newlineChallenges in edge resource management include low latency, low energy consumption,
newlinehigh accuracy, and throughput across various applications. Efficient Edge Resource
newlineManagement through Intelligent Edge Gateway Architecture has been proposed to
newlineaddress these challenges. Lightweight Unified Collaborated Relinquish (LUCR) Edge
newlineIntelligent Gateway Architecture with Joint Optimization model was introduced to utilize
newlinelimited edge resources efficiently. There are challenges to providing QoS in real-time
newlineprocessing, such as efficiency and accuracy concerning quality in video, and prediction
newlinein data management. The real-time video monitoring model and real-time data
newlinemanagement model have been proposed to address these challenges. The QoS in realtime
newlinevideo monitoring by incorporating a Greedy-based genetic algorithm (GGA) for
newlinefeature selection and Deep Convolutional Neural Networks (CNN) for classification,
newlineachieving significant improvements in accuracy and performance efficiency
newline