改进TLBO算法求解绿色零等待流水线调度问题  

Modified Teaching-learning-based Optimization Algorithm for No-wait Flow-shop Green Scheduling Problem

作　　者：杜傲然 钱斌[1] 胡蓉[1] 张长胜[1] 王凌[2] DU Ao-Ran;QIAN Bin;HU Rong;ZHANG Chang-Sheng;WANG Ling(Faculty of Information Engineering and Automation,Kunming University of Science and Technology,Kunming 650500,China;Department of Automation,Tsinghua University,Beijing 100084,China)

机构地区：[1]昆明理工大学信息工程与自动化学院,云南昆明650500 [2]清华大学自动化系,北京100084

出　　处：《控制工程》2019年第12期2218-2224,共7页Control Engineering of China

基　　金：国家自然科学基金项目(51665025,61963022,60904081);云南省自然科学基金重点项目(2015FB136)

摘　　要：针对近年来严重的环境影响和越来越多的能量成本损耗所引发的绿色调度问题,提出了一种改进的基于"教"与"学"的优化算法,求解带序相关设置时间和释放时间的零等待流水线绿色调度问题,用于最小化能量成本。首先根据该调度问题的性质,设计了一种问题解的快速评价方法。其次在教师阶段,通过对成绩最差的学员或问题解进行Insert操作来提高种群的整体质量,同时提出一种自适应的教学因子,从而使算法的全局搜索能力得到改善。最后提出基于Insert邻域的策略来增强算法的局部搜索能力,有助于算法在全局和局部之间达到合理平衡。仿真实验和算法比较验证了该算法的有效性和鲁棒性。In this paper, a modified teaching-learning-based optimization algorithm, namely MTLBO, is proposed to minimize the energic power cost criterion of the no-wait flow-shop green scheduling problem with sequence-dependent setup times and release dates, which considers a serial of environmental impacts and the rising energy costs in recent years. Firstly, a speed-up evaluation method is developed according to the property of the algorithm. Secondly, in the teacher phase, the overall quality of the population can be improved by Insert operation for the learner with the worst grades or the problem solution. Meanwhile, a self-adapting teaching factor is put forward to improve the global search ability of MTLBO. Thirdly, the insert-neighborhood local search is proposed to strengthen the local search capability, which contributes to achieving a reasonable balance between global and local search of the algorithm. Simulation results and comparisons show that MTLBO is more robust and efficient than the other optimization methods.

关 键 词：基于“教”与“学”的优化算法 零等待流水线绿色调度 序相关设置时间 释放时间 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]