基于时间窗延迟的资源约束项目调度双层优化研究

ABi-level Programming Problem Based on Time-window Delay for Resource-Constrained Project Scheduling

本研究从业主—承包商交互的视角构建了一种RCPSP(resource-constrained project scheduling problem)双层优化模型,即在可更新资源约束条件下,项目双方如何进行交互决策达到双方NPV(Net present value)最大化的目标。首先对研究问题进行界定,构建资源约束下的max-NPV项目调度双层优化模型;然后利用延迟优先规则设计了一种基于时间窗延迟的嵌套式自适应遗传算法来求解该模型,以达到双方NPV最大化;最后用一个算例验证算法的有效性,同时通过PSPLIB数值实验说明算法的稳定性,并分析关键参数对项目双方收益的影响。研究结果为项目进程的安排以及奖励机制的设计提供依据,以提高双方利益。

In this paper,a bi-level programming problem of RCPSP(resource-constrained project scheduling problem)is proposed from the perspective of owner-contractor interaction,that is,how to make interactive decision to maximize NPV(Net present value)under renewable resource constraints.Firstly,we establish the programming model for client and contractor as a leader-follower game that is enacted through bi-level hierarchical programming mechanism.The client is modeled as an upper-level problem for optimal selection of unit incentive ratio while the contractor is modeled as a lower-level problem which responds to decisions of upper level in order to schedule the activities.Secondly,in order to solve the problem,a nested adaptive genetic algorithm based on time window delay program is designed.Finally,a case study is implemented to illustrate the stability and efficiency of the algorithm,the proposed program has been tested on the PSPLIB dataset,and managerial insights are provided with respect to the impact of key parameters.The results can provide a basis for the arrangement of the project process and the formulation of the incentive mechanism between the two parties,so as to improve the interests of both parties.