Jul 2026· International Journal of Computational Intelligence Systems· 0 citations
TL;DR
Results establish AMGSEA as a scalable, QoS-aware, and energy-efficient scheduling framework suitable for dynamic and heterogeneous cloud environments suitable for dynamic and heterogeneous cloud environments.
Abstract
This paper proposes the Adaptive Memetic-Guided Slime Evolution Algorithm (AMGSEA) for multi-objective task scheduling in large-scale Infrastructure-as-a-Service (IaaS) cloud environments. Unlike conventional hybrid metaheuristics that rely on static operator integration, AMGSEA introduces a feedback-driven adaptive framework that dynamically balances exploration and exploitation. The proposed method combines oscillatory global search from the Slime Mould Algorithm, Differential Evolution-based adaptive guidance, and a selective memetic local search applied only to elite non-dominated solutions. The key novelty lies in (i) adaptive activation of memetic refinement based on Pareto dominance, (ii) feedback-controlled evolutionary guidance to prevent premature convergence, and (iii) an elite re-injection strategy for diversity preservation. Extensive experiments using CloudSim with PlanetLab traces and synthetic workloads of up to 5,000 tasks demonstrate that AMGSEA achieves up to
14.6% reduction in makespan
,
11.2% reduction in execution cost
, and improved energy efficiency compared to seven state-of-the-art schedulers. Additionally, the method improves deadline satisfaction to
97% compliance
and increases hypervolume by an average of
8–12%
. Statistical validation using Wilcoxon signed-rank tests confirms the significance of the improvements. These results establish AMGSEA as a scalable, QoS-aware, and energy-efficient scheduling framework suitable for dynamic and heterogeneous cloud environments.
The imperative for Green AI has intensified the need for intelligent cloud schedulers that can minimize carbon emissions without violating business-critical Service Level Agreements (SLAs). While native discrete metaheuristics have been proposed, they often fail to leverage the full power of state-of-the-art continuous optimizers. This paper introduces a dual contribution. First, we propose a new continuous optimizer, the Self-adaptive memetic optimizer (SA-MO), designed for high performance with architectural principles from elite competition-winning algorithms. It integrates a hybridized global search engine, combining operators inspired by Differential Evolution and Particle Swarm Optimization, a memetic local search for intense exploitation, and a self-adaptive mechanism for dynamic parameter control. The core SA-MO engine is first validated against elite continuous optimizers, including L-SHADE and CMA-ES, on ten standard benchmark functions, where it demonstrates superior convergence and precision. Second, we introduce a novel cross-domain adaptation framework to apply this powerful continuous optimizer to the discrete, combinatorial domain of cloud scheduling. The framework utilizes a priority-based encoding and decoding scheme that serves as a high-fidelity bridge. The generality of this framework is verified by successfully adapting standard continuous optimizers to the discrete domain. The core SA-MO engine is first validated against elite continuous optimizers, including L-SHADE and CMA-ES, on ten standard benchmark functions, where it demonstrates competitive convergence and precision within the evaluation budget used in this study. The resulting scheduler, d-SA-MO, is then benchmarked against industry heuristics and state-of-the-art native discrete metaheuristics across six challenging operational scenarios on a bi-objective formulation (carbon emissions and SLA violations), with energy consumption reported as a secondary monitoring metric. Quantitative results are presented in a condensed table, and rigorous non-parametric statistical analysis confirms that d-SA-MO achieves statistically significant superiority in overall performance (p < 0.0001). A complete ablation study and parameter sensitivity analysis scientifically validates the necessity of each component of the novel SA-MO architecture. This work presents a complete, end-to-end contribution: a new continuous algorithm and a novel framework to apply it, demonstrating a highly effective new pathway for solving complex Green AI challenges.
Raza Hasan, Salman Mahmood, S. Palaniappan et al.· Discover Informatics· 0 citations
Cloud Drift Optimization (CDO) is a recent nature-inspired metaheuristic with a simple adaptive search framework. Despite its adaptive mechanisms, CDO does not explicitly regulate initial space coverage, population dispersion during evolution, or agent-specific local refinement. This study proposes a Multi-Strategy Enhanced Cloud Drift Optimizer, termed MSE-CDO. First, randomized multistart maximin Latin hypercube sampling is employed to improve the spatial distribution of the initial population. Second, adaptive Gaussian mutation is introduced after the original CDO update to generate controlled perturbations according to the population dispersion and search stage, while greedy selection retains better candidates. Third, a directional pattern search mechanism is incorporated to strengthen local refinement through individual search directions and adaptive step lengths. The proposed algorithm is evaluated on unimodal and multimodal benchmark functions and constrained engineering design problems and is compared with the original CDO and several established metaheuristic algorithms. The experimental results show that MSE-CDO improves the performance of the original CDO on most benchmark functions, achieves the best overall Friedman rank among the compared algorithms, and obtains competitive solutions for the considered engineering problems. These results indicate that the proposed strategies improve the search and convergence performance of CDO while preserving its original framework.
Aziz Ali, H. Bahamish, S. A. al-Shami· Jurnal Komputer Teknologi In...· 0 citations
The primary innovation of this research is the development of an adaptive switching framework that integrates Clouded Leopard Optimization for robust global exploration with Cock-hen-chicken Optimization for hierarchical local refinement.
Srinivasan Lingaraj, Purushothaman Annadurai· Proceedings of the Instituti...· 0 citations
The Narwhal Optimization Algorithm is a recent swarm metaheuristic that, like most population-based optimisers, is prone to premature convergence, is sensitive to random initialisation, and relies on a rigid, schedule-driven exploration–exploitation balance. This paper develops and rigorously evaluates two enhanced variants that address these weaknesses. NWOA-OBL adds opposition-based initialisation and a stagnation-triggered, dynamic-opposition restart that replenishes population diversity, while NWOA-RL replaces the fixed exploration ratio with a Q-learning controller that selects the search behaviour online from the observed progress of the optimisation. Both variants are made memetic through a shared elite local search that supplies the local-refinement drive the original wave-based moves lack. The variants are compared against the baseline algorithm and seven established and recent optimisers on the CEC2017 suite at dimension thirty and the CEC2022 suite at dimensions ten and twenty, on six constrained engineering-design problems, and through parameter-sensitivity and ablation studies, all under a common evaluation budget with thirty independent runs and full nonparametric statistical analysis. Pooled over the benchmark functions, NWOA-RL attains the joint-best mean rank, statistically indistinguishable from the strongest competitor and significantly ahead of the remaining baselines, and reaches near-optimal engineering designs. The ablation identifies the elite local search as the decisive component of the design.
A. Al Tawil, S. Z. Hashim, Hanaa Fathi et al.· Scientific Reports· 0 citations
A novel hybrid approach combining Bee Colony Optimization and Genetic Algorithm for efficient task scheduling in multi-core processor systems that leverages the global exploration capabilities of BCO and the exploitation strengths of GA to achieve optimal task-to-core assignments while minimizing makespan and balancing system load is proposed.
C. Igiri, Victor Peters, Igu Ajumoke Elizabeth· Journal of Artificial Intell...· 0 citations
Ensuring reliable and efficient task scheduling remains a critical challenge in multicore computing environments, particularly when system faults can significantly affect performance and interfere with execution. This paper presents a hybrid optimization strategy that combines Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) techniques to improve task allocation under fault-prone conditions. The proposed model considers task dependencies during scheduling and dynamically distributes workloads across available processing cores to achieve balanced utilization while maintaining reliability.To evaluate its effectiveness, the hybrid GA–PSO method was tested against standalone GA and PSO approaches. The experimental findings indicate that the combined strategy achieves shorter execution times, better scalability as workload increases, and a noticeable reduction in task failure rates. These results suggest that integrating evolutionary and swarm-based optimization mechanisms can provide a practical and robust solution for improving both performance and fault tolerance for modern multicore systems.
Folashade Christiana Adu, C. Igiri, Ogbolotuo Imumesen Solomon et al.· Journal of Artificial Intell...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
