A Decomposition-Based Approach for Multitask Scheduling With Execution Uncertainty in Industrial Internet of Things

Industrial Internet of Things (IIoT) is changing the way in which factories operate with the help of various industrial applications. However, the execution uncertainty of computing tasks has always been ignored in IIoT applications. In this article, we define a novel conditional task graph to describe the execution uncertainty and present a generation algorithm to obtain all task scenario graphs and corresponding occurrence probabilities. Then, a new IIoT-oriented multitask scheduling model under execution uncertainty is built. This model is simplified by reformulating the nonlinear constraints and subsequently decomposed into several small-scale models using the Lagrange multipliers, from which a decomposition-based algorithm is derived to solve the decomposed small-scale models and progressively acquire a well-optimized solution of the initial model. Furthermore, a patching algorithm is constructed to improve the obtained solution. Finally, many test cases are generated, and four selected algorithms are taken for comparison to evaluate the performance of our algorithms. The results demonstrate that our algorithms remarkably outperform the others. Besides, the solutions of the proposed algorithms can completely satisfy the execution deadline constraints of different task scenarios.