Abstract :

IoT-based Fog Computing Environments Have Limited Energy Resources, Changing Workloads, And Diverse Devices, Effective Power Management Is A Crucial Concern. In Order To Overcome This Difficulty, The Current Approach Introduces A Framework For Adaptive Resource And Power Management Decision Making Based On Neural Networks. In Order To Record The Real-time Load And Energy Condition Of The Infrastructure, The System Continuously Checks Important Operational Data, Such As CPU Utilization, Power Consumption, And The Number Of Active Containers On Each Fog Node. To Produce Insightful Depictions Of System States, These Tracked Measurements Go Through A Feature Extraction Procedure. A Multilayer Perceptron (MLP) Model Is Trained Using The Retrived Characteristics To Understand The Intricate Connection Between Resource Usage Patterns And The Best Migration Choices. The Neural Network Dynamically Assesses If Container Movement Is Required Based On The Learnt Behaviour And Chooses A Suitable Destination, Like The Cloud Or Another Fog Node, To Balance Workloads. This Clever Migration Approach Seeks To Prolong The Battery Life Of IoT Devices, Avoid Node Overcrowding, And Minimize Excessive Power Usage. The Learning - Driven Framework Provides Better Adaptability To Varying Workloads And Shifting Network Conditions As Compared To Coventional Static And Rule - Based Techniques. The Approach Is Appropriate For Scalable And Sustainable Internet Of Things Applications Since It Improves Energy Efficiency And Resource Usage In Fog Computing Settings. Keywords—Internet Of Things; Energy Efficiency; Pareto Optimization; Neural Network Decision Making; Fog–Cloud Computing.

Published:

02-4-2026

Issue:

Vol. 26 No. 4 (2026)

Page Nos:

98-103

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite