Task Scheduling Optimization with Direct Constraints from a Tensor Network Perspective
This work addresses the problem of efficient task scheduling in industrial plants, offering a novel exact solution approach, though the improvements appear incremental.
The paper introduces a quantum-inspired tensor network method for task scheduling optimization with directed constraints, minimizing total execution cost. The algorithm achieves exact solutions with reduced computational complexity through preprocessing and constraint condensation, and its performance is validated on implemented versions.
This work presents a novel method for task optimization in industrial plants using quantum-inspired tensor network technology. This method obtains the best possible combination of tasks on a set of machines with directed constraints while minimizing the total execution cost. With this method, an exact and explicit solution of the problem is provided. This algorithm constructs a tensor network representation of the tensor which provides the solution of the problem. This method is improved in order to reduce the computational complexity of the solution computation, using problem preprocessing, new techniques of condensation of logical constraints, optimization of the value determination technique with previously calculated results, reuse of intermediate computations, and iterative relations for constraints. Three algorithms for computation are presented: the main algorithm, the iterative algorithm which adds only the minimal amount of necessary constraints, and the genetic algorithm which combines the iterative algorithm with basic genetic algorithms. Finally, a simple version of both algorithms was implemented, and their performance was tested, all publicly available.