Adaptive Mirage Search Optimization for Educational Workload Scheduling in Multi-Cloud Environments

AI-driven educational platforms increasingly rely on heterogeneous cloud workloads, including real-time tutoring, adaptive assessments, and large-scale learning analytics, which impose diverse and conflicting quality-of-service (QoS) requirements. Conventional cloud scheduling approaches fail to address such heterogeneity, often leading to service-level agreement (SLA) violations, increased execution cost, and poor resource utilization. This study proposes QoS-aware Adaptive Mirage Search Optimization Framework (QoS-AMSO), a QoS-aware multi-objective task scheduling framework based on an enhanced Mirage Search Optimization algorithm for intelligent workload management in multi-cloud environments. The proposed approach integrates four key innovations: adaptive refraction-based step sizing for improved convergence, QoS-feedback-driven dynamic weight adjustment, Lévy flight-based diversity preservation, and Pareto-based elite solution selection. Additionally, a task classification model categorizes workloads into latency-critical, throughput-intensive, deadline-soft, and batch-deferred classes, enabling context-aware scheduling decisions. The framework is evaluated using CloudSim 3.0 simulations with three cloud providers, 60 virtual machines, and workload sizes ranging from 100 to 1000 educational tasks under multiple workload scenarios. The QoS-AMSO achieves the best overall performance, reducing makespan to 798 s, execution cost to USD 292.8, SLA violation rate to 3.9%, and improving resource utilization to 97.2%. These results demonstrate the effectiveness and scalability of QoS-AMSO for QoS-aware scheduling in AI-powered educational multi-cloud environments.

@article{Mosleh2026,
  title     = {Adaptive Mirage Search Optimization for Educational Workload Scheduling in Multi-Cloud Environments},
  journal   = {International Journal of Advanced Computer Science and Applications},
  volume    = {17},
  number    = {7},
  year      = {2026},
  publisher = {The Science and Information Organization},
  author    = {Mohammed A.S. Mosleh and Elham Alzain and Hesham M.A. Abdullah and Ali Alshebami},
  doi       = {10.14569/IJACSA.2026.0170723},
  url       = {https://doi.org/10.14569/IJACSA.2026.0170723}
}