Retracted: Lightweight deep learning model for task scheduling in Resource Constrained Internet of Things

Regarding the trade in computation time and optimisation in each task scheduling, it is challenging for a single scheduling method to achieve the optimal scheduler optimisation while minimizing the very worst computational complexity in a resource-constrained Internet of Things (IoT) systems. Moreover, it is challenging to use Big-O complexity as a benchmark because hardware configurations specifications have varying effects on the scheduler computing time. The scheduling approach that has a shorter computation time and better task completion sequence optimization is switched to in this research in order to meet the computation deadline. In the worst-case time-complexity scenario, the fixed task scheduler is unable to satisfy the computing constraint because the amount of jobs and the types of resources used would affect the scheduler’s calculation time. The optimum scheduling approach to address the issue is predicted by our machine learning implementation, and the results demonstrate that it can enhance the precision of reaching the calculation limit by an average of 85.11 percent.