A Hybrid Resource Allocation for Robust Scheduling Through Combination of Neural Networks, Critical Path Method and NSGA-II

A Hybrid Resource Allocation for Robust Scheduling Through Combination of Neural Networks, Critical Path Method and NSGA-II

Mostafa Khanzadi1 Amirhossein Movahedian Attar2 Morteza Bagherpour3

1) professor, Department of civil engineering, iran university of science and technology
2) phD candidate, Department of civil engineering, iran university of science and technology
3) professor, Department of industrial engineering, iran university of science and technology

IOI Code : XYZH-ZAFDA
Publication : 2nd International Conference on Management and Humanities(2icmhconf.com)
Abstract :
    In many scheduling problems with controllable processing times, commonly two general resource consumption function is used, linear and convex, and the effect of the starting time of activity not considered. However, both of these functions have some assumption fails such as the effect of the environmental condition from starting time of activity and quality of assigned resources. Inspired by these perceptions, we provide a hybrid model for robust project scheduling in which each activity’s processing time is a function of its starting time and quality and quantity of its allocated resource. The objective is optimizing sequence of activities respect to time and cost of project with considering limits of available resources. To achieve this goal, in the proposed method, Neural Networks is combined with Critical Path Method for calculation of activity’s processing time, then NSGA-II is used for optimization. For evaluation of model capability, a problem is optimized with proposed method. The objective function is to minimize the makespan and total completion cost of project. The results show that the model has factors of robust scheduling.

Keywords : scheduling resource allocation artificial neural networks nsga ii