View in EDS

A nature-inspired dual phased fuzzy hybrid algorithm for adaptive self-healing and dynamic energy-aware resource management in cloud computing.

Saved in:
Bibliographic Details
Title: A nature-inspired dual phased fuzzy hybrid algorithm for adaptive self-healing and dynamic energy-aware resource management in cloud computing.
Authors: Roberts, Michaelraj Kingston, Shanmugam, Sampath Kumar, Al-Razgan, Muna, Alfakih, Taha
Source: Journal of Cloud Computing (2192-113X); 11/5/2025, Vol. 14 Issue 1, p1-23, 23p
Abstract: In this work, an innovative bio-inspired approach to enhance the cloud ecosystem resilience through optimized workload management and fault tolerance frameworks is presented. We enhance the Modified Reptile Search Algorithm (MRSA) by integrating the adaptive optimization and novelty calculation features of the Black Mamba Optimization Algorithm (BMOA), yielding two specialized algorithms for cloud environments. The Workload Aware Autonomic Resource Management Algorithm (WARSA) employs BMOA's dynamic adaptive optimization to address fluctuating cloud workloads. By adjusting resource allocation in real time based on demand, WARSA maximizes utilization and mitigates risks of overloading or underutilization. By integrating BMOA's capabilities into Fault Tolerance and Energy Management (FTEM) framework, the proposed algorithm efficiently optimizes resource allocation by combining resilience metrics, probabilistic selection mechanism, and iterative feedback loops. Our approach is benchmarked against established cloud optimization algorithms to demonstrate its effectiveness. This integrated approach significantly enhances energy efficiency and fault management in cloud ecosystems. A self-healing layer, driven by a Fuzzy Inference System (FIS) parameterized with BMOA attributes, enables autonomous fault detection and resolution. The FIS monitors workload, energy consumption, and fault rates, triggering responses such as resource scaling or recovery when anomalies arise. Simulations validate our approach against five state-of-the-art algorithms including DCCWOA, HFSLM, MCT-AQNN, HWACO, IWHOLF-TSC, achieving 16.8% improved resource utilization, 19.8% higher throughput, and 10.67% lower energy consumption. Additionally, it reduces task failures by 33.3% and makespan by 10.7%. These results obtained using CloudSim framework with 10,000 tasks demonstrates the efficacy of our BMOA-enhanced framework in tackling contemporary cloud computing challenges. [ABSTRACT FROM AUTHOR]
Copyright of Journal of Cloud Computing (2192-113X) is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Complementary Index
Description
Abstract:In this work, an innovative bio-inspired approach to enhance the cloud ecosystem resilience through optimized workload management and fault tolerance frameworks is presented. We enhance the Modified Reptile Search Algorithm (MRSA) by integrating the adaptive optimization and novelty calculation features of the Black Mamba Optimization Algorithm (BMOA), yielding two specialized algorithms for cloud environments. The Workload Aware Autonomic Resource Management Algorithm (WARSA) employs BMOA's dynamic adaptive optimization to address fluctuating cloud workloads. By adjusting resource allocation in real time based on demand, WARSA maximizes utilization and mitigates risks of overloading or underutilization. By integrating BMOA's capabilities into Fault Tolerance and Energy Management (FTEM) framework, the proposed algorithm efficiently optimizes resource allocation by combining resilience metrics, probabilistic selection mechanism, and iterative feedback loops. Our approach is benchmarked against established cloud optimization algorithms to demonstrate its effectiveness. This integrated approach significantly enhances energy efficiency and fault management in cloud ecosystems. A self-healing layer, driven by a Fuzzy Inference System (FIS) parameterized with BMOA attributes, enables autonomous fault detection and resolution. The FIS monitors workload, energy consumption, and fault rates, triggering responses such as resource scaling or recovery when anomalies arise. Simulations validate our approach against five state-of-the-art algorithms including DCCWOA, HFSLM, MCT-AQNN, HWACO, IWHOLF-TSC, achieving 16.8% improved resource utilization, 19.8% higher throughput, and 10.67% lower energy consumption. Additionally, it reduces task failures by 33.3% and makespan by 10.7%. These results obtained using CloudSim framework with 10,000 tasks demonstrates the efficacy of our BMOA-enhanced framework in tackling contemporary cloud computing challenges. [ABSTRACT FROM AUTHOR]
ISSN:2192113X
DOI:10.1186/s13677-025-00788-z