Authors:
S. Balaji, S. Silvia Priscila, B. M. Praveen

Addresses:
Department of Information Technology, Institute of Computer Science and Information Science, Srinivas University, Dakshina Kannada, Karnataka, India. Department of Information Technology, Al Zahara College for Women, Madinat Al-I'rfan, Muscat, Oman. Department of Computer Science, Bharath Institute of Higher Education and Research, Chennai, Tamil Nadu, India. Institute of Engineering and Technology, Srinivas University, Dakshina Kannada, Karnataka, India.

Abstract:

The booming growth of cloud computing has made efficient and adaptive load-balancing mechanisms required to handle the highly dynamic and heterogeneous workload. Traditional static and monolithic optimisation methods struggle to maintain service quality under fluctuating demand, leading to performance degradation and increased energy consumption. This study addresses dynamic load imbalance in virtualised cloud environments by proposing an autonomous hybrid swarm evolutionary load-balancing model that combines global exploration, local refinement, and adaptive decision control. The proposed framework combines swarm intelligence for efficient search, evolutionary optimisation for solution improvement, and a dynamically weighted fitness mechanism for autonomous adaptation to changing system conditions. Extensive experimental evaluation shows that the proposed model can achieve an average response time of 152ms, reduce the load imbalance to 4.3%, reduce SLA violations to 1.5%, and reduce energy consumption to 9.8kWh, which is better than various state-of-the-art methods. Statistical validation using k-fold cross-validation and paired t-tests is used to assess the robustness and significance of the results. The results show that the proposed hybrid strategy provides a scalable, reliable, and energy-efficient solution for real-time load balancing in modern cloud infrastructures.

Keywords: Cloud Computing; Resource Management; Evolutionary Optimisation; Swarm Intelligence; Dynamic Load Balancing; Virtualised Environments; Optimisation Methods.

Received on: 19/03/2025, Revised on: 10/06/2025, Accepted on: 17/07/2025, Published on: 03/01/2026

DOI: 10.69888/FTSCL.2026.000599

FMDB Transactions on Sustainable Computer Letters, 2026 Vol. 4 No. 1, Pages: 38–54

• Views : 48
• Downloads : 10

Download PDF