Multi-enterprise Dynamic Task Scheduling Approach for Industrial Internet-of-things

In the context of the Industrial Internet-of-Things, as part of the informatization process in industrial manufacturing enterprises, most manufacturing companies are inclined to transition from large-scale mass production to flexible manufacturing modes. This shift involves adopting a new manufacturing paradigm that focuses on personalized customization, consumer orientation, and demand-driven production. In this background, faced with complex manufacturing tasks, collaborative manufacturing among multiple enterprises becomes the norm, which places higher demands on decision-making for inter-enterprise task scheduling. To address the high dynamics of the manufacturing process and the uncertainties present in industrial environments under the current Industrial Internet of Things context, this paper proposes a dynamic scheduling algorithm based on the genetic algorithm. When there are changes in manufacturing information, the algorithm efficiently utilizes the effective information from previous decision-making stages by employing chromosome-directed modification to quickly determine the optimal scheduling solution. Through numerical simulations and a comparison with traditional static scheduling algorithms, the effectiveness and superiority of the proposed algorithm are validated.