Quantum-Inspired Adaptive Meta-Heuristic–Machine Learning framework for resilient and energy-efficient task scheduling in multi-cloud ecosystems

With the exponential growth of multi-cloud, spearheaded by latency-sensitive workloads, edge inclusion and heterogeneous resource pools; there is a dire need for scheduling methods which are energy neutral as well as robust against dynamic operational stress. In this work, a new bi-directional optimization–prediction system for intelligent task scheduling over federated cloud environments called Quantum-Inspired Adaptive Meta-Heuristic–Machine Learning (QI-AMHML) is proposed. Central to this is the Reinforced Quantum Whale Optimization Algorithm (RQWOA) which immerses quantum probability amplitudes and wavefunction-motivated search dynamics into classical whale optimization. Together with a federated gradient boosting scheduler, the framework establishes a continuous co-evolution between search and predictive guidance that allows proactive placement decisions under changing load and fault scenarios. The method combines resilience, energy models and load balancing constraints into a single multi-objective optimization. In evaluation based on a hybrid dataset, called MultiCloudSynth-2025, created by merging real-world traces from Google Cloud, Microsoft Azure, and Alibaba Cloud with synthetic burst (load) and fault events; QI-AMHML decreased energy consumption up to 38.2%, increased an average service delay by 33.5% and in clustered multi-fault scenarios maintained high resilience scores. We validated these results under large-scale simulations and live shadow deployments, showing that quantum-inspired search reinforced by federated predictive models can provide sustainable fault-tolerant schedule performance in real-world modern multiclustered hybrid clouds.