Energy-Efficient Dynamic Workflow Scheduling in Cloud Environments Using Deep Learning

Dynamic workflow scheduling in cloud environments is a challenging task due to task dependencies, fluctuating workloads, resource variability, and the need to balance makespan and energy consumption. This study presents a novel scheduling framework that integrates Graph Neural Networks (GNNs) with Deep Reinforcement Learning (DRL) using the Proximal Policy Optimization (PPO) algorithm to achieve multi-objective optimization, focusing on minimizing makespan and reducing energy consumption. By leveraging GNNs to model task dependencies within workflows, the framework enables adaptive and informed resource allocation. The agent was evaluated within a CloudSim-based simulation environment using synthetic datasets. Experimental results across benchmark datasets demonstrate the proposed framework's effectiveness, achieving consistent improvements in makespan and energy consumption over traditional heuristic methods. The framework achieved a minimum makespan of 689.22 s against the second best of 800.72 s in moderate-sized datasets, reducing makespan significantly with improvements up to 13.92% over baseline methods such as HEFT, Min-Min, and Max-Min, while maintaining competitive energy consumption of 10,964.45 J. These findings highlight the potential of combining GNNs and DRL for dynamic task scheduling in cloud environments, effectively balancing multiple objectives.