分时电价下任务调度–人员排班组合问题的代理模型求解研究

doi:10.3969/j.issn.1007-7375.220235

工业工程 ›› 2024, Vol. 27 ›› Issue (1): 65-77.doi: 10.3969/j.issn.1007-7375.220235

分时电价下任务调度–人员排班组合问题的代理模型求解研究

赖信君¹, 黄金晓¹, 刘艺涵¹, 张恪², 毛宁¹, 陈庆新¹

1. 广东工业大学机电工程学院，广东广州 510006;
2. 广汽埃安新能源汽车有限公司，广东广州 511434

收稿日期:2022-11-21 发布日期:2024-03-05
通讯作者: 毛宁 (1962—)，女，江苏省人，教授，主要研究方向为敏捷制造、并行工程及cims下的质量控制。Email: maoning@gdut.edu.cn E-mail:maoning@gdut.edu.cn
作者简介:赖信君 (1986—)，女，广东省人，副教授，博士，主要研究方向为机器学习、需求分析等
基金资助:
国家自然科学基金资助项目 (61973089)；广东省自然科学基金资助项目 (2114050003127)

A Surrogate Model of the Task-Personnel Scheduling Combinatorial Problem Considering Time-of-Use Electricity Tariffs

LAI Xinjun¹, HUANG Jinxiao¹, LIU Yihan¹, ZHANG Ke², MAO Ning¹, CHEN Qingxin¹

1. School of Electromechanical Engineering, Guangdong University of Technology, Guangzhou 510006, China;
2. GAC AION New Energy Automobile Co. Ltd, Guangzhou 511434, China

Received:2022-11-21 Published:2024-03-05

摘要/Abstract

摘要： 在分时电价背景下，制造成本和人力成本往往难以取得平衡：晚上电价较低但人员加班费较高，白天人员时薪较低而电价却较高。若将两个问题联合建模，则规模较大，不易求解。在实际应用中，较多采用先进行任务调度，再对人员排班的分阶段建模求解方法，但该求解思路难以保证得到较低成本的解。针对这一问题，提出一种代理模型的方法，以GA算法生成两个子问题的多组较优可行解作为训练样本，利用BP神经网络、深度学习及宽度学习系统分别拟合组合问题的代理模型，并采用BFGS法寻优。随着工件与工序数目的增加，本文所提供的自适应采样算法能有效解决维数灾问题。算例结果表明，新方法能得到明显优于利用遗传算法分阶段求解得到的结果，能为企业节省高达11.91%的电费与人力总成本。

关键词: 代理模型, 基于仿真的优化, 宽度学习系统, 变尺度法, 自适应采样

Abstract: Task and personnel scheduling problems are critical to production management. In the condition of time-of-use electricity tariffs, it is difficult to strike a balance between manufacturing and labor costs: electricity prices are lower at night but the salary for working-at-night is higher, while hourly wages are lower during the day but electricity prices are higher. If the two problems are jointly modeled, the resulting large-scale model is not easy to solve. In applications, it is usually addressed in the way that the task scheduling is firstly solved, and then the personnel scheduling is determined afterwards; however, it is difficult to guarantee a low-cost solution. To resolve this issue, this paper proposes a surrogate model method, which uses: 1) multiple sets of relatively optimal feasible solutions of the two sub-problems generated by genetic algorithm, as training samples; and 2) BP neural network, deep learning and broad learning systems to respectively fit the surrogate model for the combination problem. Then, BFGS algorithm is used to search for optima. The proposed adaptive sampling algorithm can effectively simplify the problem in terms of dimensions as the number of jobs and processes increases. Results show that the new method can obtain significantly better results than those obtained by genetic algorithm. In addition, it can save up to 11.9 % of the total cost of electricity and manpower for enterprises.

Key words: surrogate model, simulation-based optimization, broad learning system, variable metric method, adaptive sampling

中图分类号:

F406.2
TP301

赖信君, 黄金晓, 刘艺涵, 张恪, 毛宁, 陈庆新. 分时电价下任务调度–人员排班组合问题的代理模型求解研究[J]. 工业工程, 2024, 27(1): 65-77.

LAI Xinjun, HUANG Jinxiao, LIU Yihan, ZHANG Ke, MAO Ning, CHEN Qingxin. A Surrogate Model of the Task-Personnel Scheduling Combinatorial Problem Considering Time-of-Use Electricity Tariffs[J]. Industrial Engineering Journal, 2024, 27(1): 65-77.

参考文献

[1] 王丰, 刘昊翔. 基于双层规划的老城区自行车专用道网络设计[J]. 交通运输工程与信息学报, 2022, 20(4): 72-87
WANG Feng, LIU Haoxiang. Design of bicycle lane network in China's old city based on bi-level programming[J]. Journal of Transportation Engineering and Information, 2022, 20(4): 72-87
[2] CHE A, ZHANG S, WU X. Energy-conscious unrelated parallel machine scheduling under time-of-use electricity tariffs[J]. Journal of Cleaner Production, 2017, 156: 688-697
[3] REGO M F, PINTO J C E, COTA L P, et al. A mathematical formulation and an NSGA-II algorithm for minimizing the makespan and energy cost under time-of-use electricity price in an unrelated parallel machine scheduling[J/OL]. PeerJ Computer Science, 2022 (2022-02-03). https://peerj.com/articles/cs-844/.
[4] 樊小毛, 熊红林, 赵淦森. 带约束的清洁排班问题模型及其求解[J]. 计算机应用, 2021, 41(2): 577-582
FAN Xiaomao, XIONG Honglin, ZHAO Gansen. Cleaning scheduling model with constraints and its solution[J]. Journal of Computer Applications, 2021, 41(2): 577-582
[5] ARAMON B, TAVAKKOLI-MOGHADDAM R. A new branch-and-bound algorithm for the unrelated parallel machine scheduling problem with sequence-dependent setup times[J]. IFAC Proceedings Volumes, 2009, 42(4): 792-797
[6] 于军琪, 杨思远, 赵安军, 等. 基于神经网络的建筑能耗混合预测模型[J]. 浙江大学学报 (工学版) , 2022, 56(6): 1220-1231
YU Junqi, YANG Siyuan, ZHAO Anjun, et al. Hybrid prediction model of building energy consumption based on neural network[J]. Journal of Zhejiang University (Engineering Science) , 2022, 56(6): 1220-1231
[7] 张国辉, 胡一凡, 孙靖贺. 改进遗传算法求解多时间约束的柔性作业车间调度问题[J]. 工业工程, 2020, 23(2): 19-25
ZHANG Guohui, HU Yifan, SUN Jinhe. An improved genetic algorithm for flexible job shop scheduling problem with multiple time constraints[J]. Industrial Engineering Journal, 2020, 23(2): 19-25
[8] WANG Y, LI L. Manufacturing profit maximization under time-varying electricity and labor pricing[J]. Computers & Industrial Engineering, 2016, 104: 23-34
[9] 王玖河, 高辉, 刘欢. 基于遗传算法的共享助力车调度问题研究[J]. 工业工程, 2021, 24(1): 90-96
WANG Jiuhe, GAO Hui, LIU Huan. A research on shared motorcycle scheduling problem based on genetic algorithms[J]. Industrial Engineering Journal, 2021, 24(1): 90-96
[10] DU G, ZHANG Y, LIU X, et al. A review of leader-follower joint optimization problems and mathematical models for product design and development[J]. The International Journal of Advanced Manufacturing Technology, 2019, 103(9-12): 3405-3424
[11] LAI X, ZHANG K, LI Z, et al. Scheduling air conditioner testing tasks under time-of-use electricity tariff: a predictin and for optimization approach[J]. Computers & Industrial Engineering, 2023, 175: 108850
[12] 韩忠华. Kriging模型及代理优化算法研究进展[J]. 航空学报, 2016, 37(11): 3197-3225
HAN Zhonghua. Research progress of Kriging model and surrogate optimization algorithm[J]. Acta Aeronautica et Astronautica Sinica, 2016, 37(11): 3197-3225
[13] CHEN C, LIU Z. Broad learning system: an effective and efficient incremental learning system without the need for deep architecture[J]. IEEE Transactions on Neural Networks & Learning Systems, 2018, 29(99): 10-24
[14] ZHAO F, LIU Y, LIU H, et al. Broad learning approach to surrogate-assisted multi-objective evolutionary fuzzy clustering algorithm based on reference points for color image segmentation[J]. Expert Systems with Applications, 2022, 200: 117015
[15] 郭述臻, 昂海松, 蔡红明. 一种自适应抽样的代理模型构建及其在复材结构优化中的应用[J]. 复合材料学报, 2018, 35(8): 2084-2094
GUO Shuzhen, ANG Haisong, CAI Hongming. Construction of an adaptive sampling surrogate model and application in composite material structure optimization[J]. Acta Materiae Compositae Sinica, 2018, 35(8): 2084-2094
[16] 户佐安, 邹正丰, 包天雯. 基于BP神经网络的交通信息量预测方法[J]. 交通运输工程与信息学报, 2018, 16(4): 81-87
HU Zuoan, ZOU Zhengfeng, BAO Tianwen. Approach for prediction of traffic information volume based on BP neural network[J]. Journal of Transportation Engineering and Information, 2018, 16(4): 81-87
[17] 季长清, 高志勇, 秦静, 等. 基于卷积神经网络的图像分类算法综述[J]. 计算机应用, 2022, 42(4): 1044-1049
JI Changqing, GAO Zhiyong, QIN Jing, et al. Review of image classification algorithms based on convolutional neural network[J]. Journal of Computer Applications, 2022, 42(4): 1044-1049
[18] LIEU Q X, NGUYEN K T, DANG K D, et al. An adaptive surrogate model to structural reliability analysis using deep neural network[J]. Expert Systems with Applications, 2022, 189: 116104
[19] 任长娥, 袁超, 孙彦丽, 等. 宽度学习系统研究进展[J]. 计算机应用研究, 2021, 38(8): 2258-2267
REN Chang'e, YUAN Chao, SUN Yanli, et al. Research of broad learning system[J]. Application Research of Computers, 2021, 38(8): 2258-2267

分时电价下任务调度–人员排班组合问题的代理模型求解研究

A Surrogate Model of the Task-Personnel Scheduling Combinatorial Problem Considering Time-of-Use Electricity Tariffs

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 4

编辑推荐

Metrics

本文评价

[1]	陈光林, 于丽娅, 张成龙, 周鹏, 李笑瑜. 基于麻雀算法优化宽度学习系统的轴承故障诊断[J]. 工业工程, 2023, 26(3): 151-158.
[2]	田永杰. 经销商公平偏好的供应链合作广告策略研究[J]. 工业工程, 2021, 24(4): 67-75.
[3]	王虹森，贾素玲，闫志华. 基于仿真的三级供应链成本优化[J]. 工业工程, 2015, 18(2): 51-58.
[4]	辛玉红，李小莉. 基于SCF的多任务委托代理激励机制[J]. 工业工程, 2013, 16(5): 39-44.