A Multi-Contractor Approach for MLRCPSP with the Graph Structure Optimization

Resource-constrained project scheduling problem (RCPSP) is one of the most challenging combinatorial optimization problems. This task contains different variations and is the object of attention of many researchers. However, the existing formulation of practical optimization tasks in industrial production processes significantly exceeds the limits of classical RSPCP formulation, academic frameworks like PSPLib and datasets like RG300. It is expressed in the presence of additional parameters (degrees of freedom), uncertainty in the actual data of parameters of the solving task and the dimensionality of the problems themselves. A striking example of such production processes is the capital construction of complex facilities, such as capital projects (construction of capital assets) or airport operation, where activities can exceed tens of thousands, have fuzzy connections, form sub-sets of tasks, and be performed by complex teams that have different types of resources in their disposal. The formulation of such problems not only opens up the opportunities to develop new modifications of existing algorithms but also allows us to evaluate the practical feasibility of using such algorithms on dimensions orders of times higher than the generally accepted test sets. In the current research, we introduce problem extension MLRCPSP - multi-resource-constrained project scheduling problem and a new generalized algorithm that can take into account the features of actual production processes and demonstrates how effective it could be in application to synthetically generated data from real practical applications, using an extended state-of-the-art implementation of the genetic algorithm.