DEThresh: A Hybrid Evolutionary and Threshold Algorithm for Cloud Optimization
Abstract
Cloud computing’s growth has necessitated advanced approaches to enhance service delivery, particularly in datacenter selection and load balancing, to meet users’ demands efficiently. Our research introduces DEThresh, a novel dual-method approach combining differential evolution-based datacenter selection with a threshold-based load-balancing strategy. DEThresh optimizes cloud resource management by selecting suitable datacenters and balancing load distribution to maximize resource utilization and minimize response time and costs. Results show that DEThresh outperforms established algorithms, demonstrating improved data processing efficiency and response times, particularly under dynamic user and datacenter conditions. By achieving optimal performance with fewer datacenters, DEThresh offers a cost-effective solution for robust and reliable cloud service provisioning.
Department(s)
Computer Science
Document Type
Conference Proceeding
DOI
10.1109/Cloud-Summit64795.2025.00018
Keywords
Cloud, Datacenter Selection, Differential Evolution, Load Balancing, Overload, Threshold, Underload
Publication Date
1-1-2025
Recommended Citation
Chowdhury, Shusmoy; Katangur, Ajay K.; Liu, Siming; and Iqbal, Razib, "DEThresh: A Hybrid Evolutionary and Threshold Algorithm for Cloud Optimization" (2025). Faculty Scholarship. 219.
https://bearworks.missouristate.edu/articles00/219
Journal Title
Proceedings 2025 IEEE Cloud Summit Cloud Summit 2025
