Year: 2025
Type: article
Abstract: The Internet of Things (IoT) has increased data generation and processing requirements, leading to increased energy consumption and resource allocation in data centers.This research proposes an advanced energy-efficient resource optimization framework for fog computing data centers, integrating Q-Learning with threshold-based virtual machine migration for real-time resource management.This dual strategy enhances energy efficiency, reduces resource contention, and improves system scalability.The proposed method outperforms traditional methods, achieving 30.3% energy savings, 20% throughput improvement, and 15% reduction in response time.The sensitivity analysis on Q-learning hyperparameters provides theoretical justification for their selection.The findings highlight the scalability, adaptability, and real-world applicability of the proposed framework.
Language: English
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W4410250038