Integrating Two-Level Reinforcement Learning Process for Enhancing Task Scheduling Efficiency in a Complex Problem-Solving Environment

Abstract

Task scheduling scenarios require the system designers to have complete information about the resources and their capabilities, along with the tasks and their application-specific requirements. An effective task-to-resource mapping strategy will maximize resource utilization under constraints, while minimizing the task waiting time, which will in-turn maximize the task execution efficiency. In this work, a two-level reinforcement learning algorithm for task scheduling is proposed. The algorithm utilizes a deep-intensive learning stage to generate a deployable strategy for task-to-resource mapping. This mapping is re-evaluated at specific execution breakpoints, and the strategy is re-evaluated based on the incremental learning from these breakpoints. In order to perform incremental learning, real-time parametric checking is done on the resources and the tasks; and a new strategy is devised during execution. The mean task waiting time is reduced by 20% when compared with standard algorithms like Dynamic and Integrated Resource Scheduling, Improved Differential Evolution, and Q-learning-based Improved Differential Evolution; while the resource utilization is improved by more than 15%. The algorithm is evaluated on datasets from different domains like Coronavirus disease (COVID-19) datasets of public domain, National Aeronautics and Space Administration (NASA) datasets and others. The proposed method performs consistently on all the datasets.

KEYWORDS:

• Deep learning
• Dynamic strategy
• Incremental learning
• Intensive learning

DISCLOSURE STATEMENT

No potential conflict of interest was reported by the author(s).

Additional information

Notes on contributors

Shantanu Lohi

Shantanu A Lohi, currently working as an assistant professor (Senior Grade) in the Department of Information Technology, Government College of Engineering, Amravati, Maharashtra. He has over 16 years of teaching experience. He has published various articles in national and international journals and conferences. His areas of interest are machine learning implementation in human cognition, metaheuristics, societal computational sciences and ICT for agricultural development.Email: [email protected]

Shailendra S. Aote

Shailendra S Aote is working as an assistant professor in the Department of Computer Science and Engineering at Shri Ramdeobaba College of Engineering and Management, Nagpur. He has 15 years of teaching and industrial experience. He pursued his PhD in the area of particle swarm optimization. Corresponding author. Email: [email protected]

Ravindra N. Jogekar

Ravindra Namdeorao Jogekar working as assistant professor, Department of Computer Science and Engineering in Priyadarshini J L College of Engineering, Nagpur, Maharashtra, India. He had 18 years of experience. He has done his PhD in computer science and engineering and his areas of interest are artificial intelligence, computer vision, metaheuristics, computer network, and graphics.Email: [email protected]

Harish V. Gorewar

Harish Vasantrao Gorewar was born in 1980. He is currently pursuing PhD from Sarvepalli RadhaKrishnan University, Bhopal, MP, India. His research areas include artificial intelligence, machine learning, deep learning, blockchain, IoT, data mining and text mining, metaheuristics and software engineering.Email: [email protected]

Ajay A. Jaiswal

Ajay A Jaiswal is working as a professor, Department of Computer Science and Engineering in KDK College of Engineering, Nagpur, Maharashtra, India, having 30 years of experience. He has done his PhD in computer science and engineering and his areas of interest are cloud computing, artificial intelligence, metaheuristics, computer network, graphics. He has widely published in international and national journals and conferences.Email: [email protected]

Sandeep S. Ganorkar

Sandeep Ganorkar is working as an assistant professor, Department of Information Technology in KDK College of Engineering, Nagpur, Maharashtra, India, having 20 years of experience. He has done his post-graduation in computer science and engineering and his areas of interests are cloud computing, artificial intelligence, computer network, graphics. He has widely published in international and national journals and conferences.Email: [email protected]

Snehal A. Lohi-Bode

Snehal A Lohi-Bode is currently pursuing PhD from Sarvepalli RadhaKrishnan University, Bhopal, MP, India in computer science and engineering. Her research areas include artificial intelligence, machine learning, ICT for agricultural development, agricultural yield prediction.Email: [email protected]

Rajesh M. Metkar

Rajesh Metkar is currently working as an associate professor in the Department of Mechanical Engineering, Government College of Engineering, Amravati, Maharashtra. He has over 17 years of teaching and 4 years of industrial experience. He has published various articles in the national and international journals. His area of interest is additive manufacturing, CAD and machine design.Email: [email protected]

Shwetambari Chiwhane

Shwetambari Chiwhane, currently associated with Symbiosis Institute of Technology, Symbiosis International (Deemed University), Pune, India, as Sr assistant professor in CS/IT Department. Enriched with 18 years of experience in the same field. Her areas of interest are image processing, computer vision, machine learning, artificial intelligence and deep learning. She has widely published her work in national and international journals and conferences.Email: [email protected]