Abstract
Abstract Practical problems in construction can be easily qualified as NP-hard (non-deterministic, polynomial-time hard) problems. The time needed for solving these problems grows exponentially with the increase of the problem’s size – this is why mathematical and heuristic methods do not enable finding solutions to complicated construction problems within an acceptable period of time. In the view of many authors, metaheuristic algorithms seem to be the most appropriate measures for scheduling and task sequencing. However even metaheuristic approach does not guarantee finding the optimal solution and algorithms tend to get stuck around local optima of objective functions. This is why authors considered improving the metaheuristic approach by the use of neural networks. In the article, authors analyse possible benefits of using a hybrid approach with the use of metaheuristics and neural networks for solving the multi-mode, resource-constrained, project-scheduling problem (MRCPSP). The suggested approach is described and tested on a model construction project schedule. The results are promising for construction practitioners, the hybrid approach improved results in 87% of tests. Based on the research outcomes, authors suggest future research ideas.
Highlights
The resource-constrained, project-scheduling problem (RCPSP) is commonly known in scienti c literature [1, 2]
The results are promising for construction practitioners, the hybrid approach improved results in 87% of tests
To test the e ciency of arti cial neural networks in terms of problem instance simpli cation authors carried out tests
Summary
The resource-constrained, project-scheduling problem (RCPSP) is commonly known in scienti c literature [1, 2]. The multi-mode, resource-constrained, projectscheduling problem (MRCPSP, sometimes known as MMRCPSP) is a generalized version of RCPSP. Each mode has a speci c duration and speci c resource requirements [2]. The computational time required for solving a MRCPS problem instance is longer than that of a similar RCPS problem instance without multiple modes. The problem can be even harder if one introduces probabilistic/fuzzy data [3, 4]. For this reason, it is of utmost importance to create e cient computational algorithms/ approaches for solving MRCPS class problems
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
