Performance Comparison of Deep Reinforcement Learning and Genetic Algorithm for Workflow Scheduling

Traditionally, heuristic-based methods and guided random search are two major categories of workflow scheduling algorithms. Genetic Algorithm (GA) is a well-known guided random search method and has demonstrated effectiveness in previous research. In our previous work, the recently emerging Deep Reinforcement Learning (DRL) approach outperformed the state-of-the-art heuristic-based method, IPPTS. In this paper, we aim to further explore the advantages and effectiveness of DRL, and compare its performance in workflow scheduling to the well-known GA approach.