Workflow scheduling strategy based on deep reinforcement learning

Abstract

Abstract With the increase of Internet of Things devices, the data intensive workflow has emerged. Because the data-intensive workflow has the characteristics of scattered data sources, large data scale and collaborative distributed execution at the cloud edge. It brings many challenges to the execution of workflow, such as data flow control management, data transmission scheduling, etc. Aiming at the execution constraints and data transmission optimization of data-intensive workflow, this paper proposes a workflow scheduling method based on deep reinforcement learning. First, the execution constraints, edge node load and data transmission volume of IoT data workflow are modeled; Then the data - intensive workflow is segmented with the optimization goal of data transmission; Besides, taking the workflow execution time and average load balancing as the optimization goal, the improved DQN algorithm is used to schedule the workflow. Based on the DQN algorithm, the model reward function and action selection are redesigned and improved. The simulation results based on WorkflowSim show that, compared with MOPSO, NSGA-II and GTBGA, the algorithm proposed in this paper can effectively reduce the execution time of IoT data workflow under the condition of ensuring the execution constraints and load balancing of edge nodes.