Enhanced Fault Tolerance and Load Balancing using Adaptive Tuning in a Hierarchical Dragonfly Algorithm Framework

Abstract

In the evolving landscape of cloud computing, ensuring high availability and optimal resource utilization are critical challenges. This paper introduces a novel approach to fault tolerance and load balancing by employing a Hierarchical Dragonfly Algorithm (DA) with Adaptive Tuning. The proposed method leverages a hierarchical structure to efficiently manage resources and maintain system stability under varying loads and fault conditions. By dynamically adjusting DA parameters through adaptive tuning, the system can respond effectively to real-time changes in workload and node availability. Extensive simulations demonstrate that the proposed approach significantly improves fault tolerance, enhances load distribution, and reduces response time, leading to increased system throughput and overall cloud service efficiency. This study aims to develop an efficient fault-tolerant and load-balancing mechanism in cloud computing using a Hierarchical Dragonfly Algorithm with Adaptive Tuning. The primary objectives include: Enhancing fault tolerance to maintain system stability under varying load conditions, Improving load distribution for optimal resource utilization and Minimizing response time while increasing system throughput. The proposed approach integrates a Hierarchical Dragonfly Algorithm (DA) with Adaptive Tuning to manage cloud resources dynamically. The methodology includes (i) Implementing a hierarchical structure to enhance fault tolerance and optimize load balancing. (ii) Employing adaptive tuning to adjust DA parameters in real time based on workload and node availability. (iii) Conducting extensive simulations to evaluate the performance of the proposed method in comparison with existing techniques. Simulation results indicate that the Hierarchical DA with Adaptive Tuning significantly improves cloud system performance.