Empowering cloud providers: optimised locust-inspired algorithm for SLA violation mitigation in green cloud computing
Cloud computing has become integral to modern technology, offering scalable and on-demand access to computational resources. However, cloud data centres face persistent challenges such as high Service Level Agreement (SLA) violations, excessive energy consumption, and frequent Virtual Machine (VM) m...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | en |
| Published: |
Springer
2025
|
| Online Access: | http://psasir.upm.edu.my/id/eprint/120822/1/120822.pdf http://psasir.upm.edu.my/id/eprint/120822/ https://link.springer.com/article/10.1007/s00607-025-01527-7?error=cookies_not_supported&code=4e58ff9f-ac23-4c99-8f30-e0144b112547 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Cloud computing has become integral to modern technology, offering scalable and on-demand access to computational resources. However, cloud data centres face persistent challenges such as high Service Level Agreement (SLA) violations, excessive energy consumption, and frequent Virtual Machine (VM) migrations, particularly under dynamic workloads. To address these issues, we propose an optimised bio-inspired algorithm, based on locust swarm behaviour, that tackles the multi-objective problem of VM mapping and server consolidation. The algorithm explicitly considers SLA compliance, energy efficiency, resource utilisation, and migration overhead. It enhances the locust-inspired algorithm by integrating SLA-awareness and adaptive host classification and is evaluated using real workload traces in the CloudSim toolkit. Experimental results show that the proposed algorithm reduces SLA violations by approximately 40%, energy consumption by 32%, and VM migrations by 68% on average, while improving resource utilisation by around 45%, compared to state-of-the-art heuristic and meta-heuristic algorithms. The algorithm also demonstrates strong scalability in large-scale data centre environments, making it a promising solution for sustainable and efficient cloud infrastructure management. |
|---|