Title: Workflow scheduling optimisation for distributed environment using artificial neural networks and reinforcement learning

Authors: K. Jairam Naik; Mounish Pedagandam; Amrita Mishra

Addresses: Department of Computer Science and Engineering, National Institute of Technology Raipur, Raipur, Chhattisgarh, India ' Department of Computer Science and Engineering, National Institute of Technology Raipur, Raipur, Chhattisgarh, India ' Department of Computer Science and Engineering, National Institute of Technology Raipur, Raipur, Chhattisgarh, India

Abstract: The growing volumes of information and multifaceted nature of information processing, workflow scheduling in distributed environment are a prominent component for computing operations to diminish the amount of information transferring, computation load allocation to resources, reducing the task's waiting time and execution time. The basic objective of this article is to find an optimal schedule (Sopt) which can reduce the makespan of workflow. Artificial intelligence and neural network (NN) systems are the main-stream, but they were not effectively employed nevertheless for workflow scheduling. Hence, we enhance the scheduling by realising artificial neural networks and reinforcement Q-learning standards. An optimised NN-based scheduling algorithm (WfSo_ANRL) that represents an agent which can effectively schedule the tasks among computational nodes was provided in this article. The agent interacts with the external environment, i.e., the computing environment and collects the current status of load encoded in the form of a state vector. The agent then predicts an action and efficiently allocates the tasks on to the attainable resources. The external computing environment then awards incentives to the agent. The agent then learns to produce optimal schedules for reducing the makespan. In this way, the WfSo_ANRL produces optimal solution for workload.

Keywords: workflow; scheduling; tasks; workload; optimisation; distributed environment; ANN; makespan time; Q-learning; resources.

DOI: 10.1504/IJCSE.2021.119984

International Journal of Computational Science and Engineering, 2021 Vol.24 No.6, pp.653 - 670

Received: 10 Nov 2020
Accepted: 23 Feb 2021
Published online: 04 Jan 2022 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article