一种求解资源受限项目调度问题的蚁群算法  

ACO for Solving Resource-constrained Project Scheduling Problem

作　　者：彭武良[1] 王成恩[2] 

机构地区：[1]沈阳理工大学经济管理学院,沈阳110168 [2]教育部流程工业综合自动化重点实验室,沈阳110004

出　　处：《系统仿真学报》2009年第7期1974-1978,共5页Journal of System Simulation

基　　金：国家自然科学基金(60604025)

摘　　要：针对资源受限项目调度问题的特点,开发了一种基于蚁群算法的项目调度新方法。在该方法中,采用基于优先权排列的编码方式进行编码,利用组合评估的形式指导蚂蚁移动。提出能使用大量优先级规则的规则池方法,为不同的蚂蚁设置不同的优先级规则。充分利用蚁群算法的优点,为每个蚂蚁设计单独的线程,采用多线程结构实现了本算法。利用被普遍应用的PSPLIB标准问题对该算法进行了大量的仿真测试,并与既有智能优化算法进行了比较,取得了令人满意的结果。A modified ant colony optimization （ACO） algorithm for solving resource-constrained project scheduling problem （RCPSP） based on the characteristics of the problem was developed. In the algorithm, a new permutation of priorities-based coding scheme was employed and the summation evaluation was applied to direct the movement of ants. The priority rules pool in which lots of priority rules could be managed, was proposed to provide ants with different priority rules. Taking full advantage of ACO, each ant owned a single thread and the algorithm was implemented in the multithreading architecture. A full factorial computational experiment was set up using the well-known standard instances in PSPLIB, and the algorithm was compared to the existing intelligence optimization algorithms. The results reveal that the algorithm is effective for the RCPSP.

关 键 词：项目管理 项目调度 蚁群算法 群智能 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]