Enhanced time-constraint aware tasks scheduling mechanism based on predictive optimization for efficient load balancing in smart manufacturing

Abstract

Smart manufacturing has great potential for developing customized products to meet the dynamic needs of customers and a collaborative network to enhance production efficiency. It is an emerging area with the revolution of business strategies, such as Industry 4.0 and Industrial Internet of the United States of America. IIoT and data-driven technologies, such as AI and ML, have leveraged the production environment by facilitating mass personalized customization of products and improving manufacturing processes collaboratively. However, these technologies are segregated and dispersed in the digitization of manufacturing products and automation of machines in existing manufacturing processes. Therefore, it is a leverage challenge to develop an integrated solution based on IIoT and data-driven technologies for an autonomous manufacturing environment. This research study presents an integrated solution using an enhanced TCA tasks scheduling mechanism based on a predictive optimization approach to improve smart manufacturing production efficiency. The proposed enhanced TCA tasks scheduling mechanism is an improved variant of FEF scheduling that considers accurate decision (prediction) measures and tasks’ minimal (optimal) time to schedule tasks efficiently. This study aims to efficiently plan task execution sequence to increase smart manufacturing productions and efficiency of resource utilization in real-time by maximizing utilization of smart machines, minimizing tasks idle time, and autonomously controlling the smart manufacturing environment through installed sensors and actuators. Furthermore, different evaluation methods are used to analyze the significance of the proposed PO-TCA scheduling mechanism, such as response time, tasks drop rate, tasks starvation rate, and machine utilization rate. The experimental analysis shows that the proposed enhanced PO-TCA scheduling mechanism reduces dropout and starvation rates by 21 % and 17 %, respectively. Our proposed mechanism also improves machine utilization by an average of 18 % compared to the baseline scheduling strategy. Moreover, experimental results signify that the proposed PO-TCA scheduling mechanism improves the utilization of smart machines and minimizes the task’s idle time to achieve a trade-off between tasks response and waiting time.