O2O-PLB: A One-to-One-Based Optimizer With Priority and Load Balancing Mechanism for Resource Allocation in Fog-Cloud Environments
In the era of the Internet of Things (IoT), Fog and Cloud computing have become critical frameworks for managing large-scale, distributed systems. However, the challenge of optimizing resource allocation remains significant, especially in dynamic and diverse environments. This paper presents O2O-PLB...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10857275/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | In the era of the Internet of Things (IoT), Fog and Cloud computing have become critical frameworks for managing large-scale, distributed systems. However, the challenge of optimizing resource allocation remains significant, especially in dynamic and diverse environments. This paper presents O2O-PLB, a new One-to-One-Based Optimizer with Priority and Load Balancing mechanism aimed at improving resource allocation in Fog-Cloud settings. O2O-PLB adopts a priority-based approach, assigning tasks according to urgency, system limitations, and available resources, while its load balancing feature ensures an even distribution of tasks to prevent congestion and inefficiency. The method integrates Fog and Cloud resources effectively, boosting system performance and reducing latency. Simulation results show that O2O-PLB outperforms traditional resource allocation methods in resource usage, response times, and latency reduction. Based on the experimental results, the O2O-PLB algorithm significantly outperforms the benchmark algorithms across essential performance metrics at varying task loads. In terms of response time, O2O-PLB achieves an average reduction of 30% over Greedy-LC, 40% over GA, 45% over MOPSO, and 55% compared to EALB. For latency, O2O-PLB achieves an average decrease of 25% relative to Greedy-LC, 35% over GA, 40% compared to MOPSO, and 50% over EALB. When it comes to load imbalance, O2O-PLB consistently improves by approximately 60% over both MOPSO and EALB, 50% over GA, and 40% over Greedy-LC, indicating strong task distribution capabilities. In terms of task failure rate, O2O-PLB reduces failures by 65% compared to EALB, 50% over GA, 40% over MOPSO, and 35% over Greedy-LC. The findings suggest that O2O-PLB provides an effective solution for optimizing Fog-Cloud resource management, making it a promising tool for future IoT applications. |
|---|---|
| ISSN: | 2169-3536 |