Learning Evolution Modeling of Multi-cycle Nested Cloud Manufacturing Service Ecosystem

doi:10.16182/j.issn1004731x.joss.25-0993

Abstract

Abstract:

In view of the lack of comprehensive consideration of the individual adaptability changes of enterprises caused by the collaborative governance mechanism among multiple manufacturing units and the overall evolution trend of the system in existing learning evolution models, this proposed a learning evolution model of multi-cycle nested cloud manufacturing service ecosystem. At the micro level, the adaptive linkage decision-making among multiple manufacturing units within the enterprise was achieved in the individual layer through the nesting of planning-readiness-execution-assessment (PREA) loops and OODA loops; at the macro level, the closed-loop simulation of the individual layer, organizational layer, and social layer was achieved to provide an interpretable decision support tool for the development of digital and intelligent cloud manufacturing systems. The effectiveness of the model was verified by analyzing the survival quantity, aggregation degree, and overall capital of enterprises under different strategies and order allocation ratios in computational experiments.

Key words: agent-based modeling method, cloud-edge-end architecture, cloud manufacturing, computational experiment

CLC Number:

TP391.9

Li Fang, Zhou Deyu, Wang Gang, Liu Guangjun, Hu Qi. Learning Evolution Modeling of Multi-cycle Nested Cloud Manufacturing Service Ecosystem[J]. Journal of System Simulation, 2026, 38(8): 2265-2282.

Figures/Tables 15

Table 1

Fig. 1

Fig. 2

Fig. 3

Fig. 4

Fig. 5

Table 2

Table 3

Experimental parameter settings

参数	实验设置
环境大小	180×100
企业Agent的初始数量	50
企业Agent初始能量值	[100, 200]内随机取值
企业Agent视野范围	10
每步消耗能量值	2
每日消耗能量值	1
订单最大等待时间	30
单个订单收益能量值	[20, 50]内随机取值
订单1密集区域坐标和半径	(90, 62)和18
订单2密集区域坐标和半径	(41, 26)和18
订单3密集区域坐标和半径	(150, 50)和18
繁殖阈值	300
初始订单数 $N$	90
订单波动 $M$	20
工序总数 $J$	[5, 10]内随机取值
每个机器加工单个工件的时间/s	1
同一工厂内机器转移时间/s	0.5
不一工厂内机器转移时间/s	1
迭代次数 $T$	100
学习率	0.001
折扣因子	0.99
贪心因子	0.1
经验池大小	128
批次大小	16
种群大小	50
交叉概率	0.9
变异概率	0.1

Table 3

Fig. 6

Fig. 7

Fig. 8

Fig. 9

Fig. 11

Fig. 12

References 43

[1]	崔双双, 吴限, 王宏志, 等. 面向云边端协同的多模态数据建模技术及其应用[J]. 软件学报, 2024, 35(3): 1154-1172.
	Cui Shuangshuang, Wu Xian, Wang Hongzhi, et al. Multimodal Data Modeling Technology and Its Application for Cloud-edge-device Collaboration[J]. Journal of Software, 2024, 35(3): 1154-1172.
[2]	王飞跃. 计算实验方法与复杂系统行为分析和决策评估[J]. 系统仿真学报, 2004, 16(5): 893-897.
	Wang Feiyue. Computational Experiments for Behavior Analysis and Decision Evaluation of Complex Systems[J]. Journal of System Simulation, 2004, 16(5): 893-897.
[3]	刘永奎, 曾鸣, 张霖, 等. 基于微服务架构的云制造调度仿真系统设计与开发[J]. 系统仿真学报, 2022, 34(4): 700-711.
	Liu Yongkui, Zeng Ming, Zhang Lin, et al. Design and Development of a Simulation System for Scheduling in Cloud Manufacturing Based on Microservice Architecture[J]. Journal of System Simulation, 2022, 34(4): 700-711.
[4]	Xue Xiao, Li Guanding, Zhou Deyu, et al. Research Roadmap of Service Ecosystems: A Crowd Intelligence Perspective[J]. International Journal of Crowd Science, 2022, 6(4): 195-222.
[5]	Li Fang, Wang Gang, Liu Guangjun, et al. Integrity Verification Scheme for Distributed Dynamic Data in Service Ecosystems[J]. Computers & Security, 2025, 159: 104671.
[6]	Lee Tian-Shyug, Chen I-Fei. A Two-stage Hybrid Credit Scoring Model Using Artificial Neural Networks and Multivariate Adaptive Regression Splines[J]. Expert Systems with Applications, 2005, 28(4): 743-752.
[7]	Chen Jingfang, Wang Ling, Wang Shengyao, et al. An Effective Matching Algorithm with Adaptive Tie-breaking Strategy for Online Food Delivery Problem[J]. Complex & Intelligent Systems, 2022, 8(1): 107-128.
[8]	Zhong Yang, Fan Yushun, Huang Keman, et al. Time-aware Service Recommendation for Mashup Creation[J]. IEEE Transactions on Services Computing, 2015, 8(3): 356-368.
[9]	Huang Keman, Fan Yushun, Tan Wei. Recommendation in an Evolving Service Ecosystem Based on Network Prediction[J]. IEEE Transactions on Automation Science and Engineering, 2014, 11(3): 906-920.
[10]	Barros A P, Dumas M. The Rise of Web Service Ecosystems[J]. IT Professional, 2006, 8(5): 31-37.
[11]	Zhou Deyu, Hou Yugi, Xue Xiao, et al. Scenario Generator Design Method for Service Ecosystem Governance Driven by LLM-empowered Agents Simulation[C]//2025 IEEE International Conference on Web Services (ICWS). Piscataway: IEEE, 2025: 552-562.
[12]	佟兴, 张召, 金澈清, 等. 面向端边云协同架构的区块链技术综述[J]. 计算机学报, 2021, 44(12): 2345-2366.
	Tong Xing, Zhang Zhao, Jin Cheqing, et al. Blockchain for End-edge-cloud Architecture: A Survey[J]. Chinese Journal of Computers, 2021, 44(12): 2345-2366.
[13]	琚翔, 苏圣超, 徐超杰, 等. 边缘计算下基于深度强化学习的车联网任务调度[J]. 系统仿真学报, 2023, 35(12): 2550-2559.
	Ju Xiang, Su Shengchao, Xu Chaojie, et al. Task Scheduling for Internet of Vehicles Based on Deep Reinforcement Learning in Edge Computing[J]. Journal of System Simulation, 2023, 35(12): 2550-2559.
[14]	黄思进, 文佳, 陈哲毅. 面向边缘车联网系统的智能服务迁移方法[J]. 系统仿真学报, 2025, 37(2): 379-391.
	Huang Sijin, Wen Jia, Chen Zheyi. Intelligent Service Migration towards MEC-based IoV Systems[J]. Journal of System Simulation, 2025, 37(2): 379-391.
[15]	Xu Xiaolong, Wu Qi, Qi Lianyong, et al. Trust-aware Service Offloading for Video Surveillance in Edge Computing Enabled Internet of Vehicles[J]. IEEE Transactions on Intelligent Transportation Systems, 2021, 22(3): 1787-1796.
[16]	Li Xiaocui, Zhou Zhangbing, He Qiang, et al. Re-scheduling IoT Services in Edge Networks[J]. IEEE Transactions on Network and Service Management, 2023, 20(3): 3233-3246.
[17]	Tang Jine, Wei Lingxiao, Liu Weijing, et al. Correlation Anomaly Detection with Multiple Primary Attributes in Collaborative Device-edge-cloud Network[J]. IEEE Internet of Things Journal, 2023, 10(6): 4922-4936.
[18]	Zhang Junna, Chen Jiawei, Bao Xiang, et al. Dependent Task Offloading Mechanism for Cloud-edge-device Collaboration[J]. Journal of Network and Computer Applications, 2023, 216: 103656.
[19]	邸彦强, 李婷, 冯少冲, 等. 云边端架构的装备精确维修平行仿真系统[J]. 系统仿真学报, 2022, 34(9): 1909-1919.
	Di Yanqiang, Li Ting, Feng Shaochong, et al. Parallel Simulation System of Equipment Precision Maintenance Based on Cloud-edge-end Architecture[J]. Journal of System Simulation, 2022, 34(9): 1909-1919.
[20]	施建锋, 陈忻阳, 李宝龙. 面向物联网的云边端协同计算中任务卸载与资源分配算法研究[J]. 电子与信息学报, 2025, 47(2): 458-469.
	Shi Jianfeng, Chen Xinyang, Li Baolong. Research on Task Offloading and Resource Allocation Algorithms in Cloud-edge-end Collaborative Computing for the Internet of Things[J]. Journal of Electronics & Information Technology, 2025, 47(2): 458-469.
[21]	Malashenko Y E, Nazarova I A. Analysis of Critical Damage in the Communication Network: I. Model and Computational Experiment[J]. Journal of Computer and Systems Sciences International, 2020, 59(5): 745-754.
[22]	Xue Xiao, Wang Shufang, Zhang Lejun, et al. Social Learning Evolution (SLE): Computational Experiment-based Modeling Framework of Social Manufacturing[J]. IEEE Transactions on Industrial Informatics, 2019, 15(6): 3343-3355.
[23]	Zhou Deyu, Xue Xiao, Zhou Zhangbing. SLE2: The Improved Social Learning Evolution Model of Cloud Manufacturing Service Ecosystem[J]. IEEE Transactions on Industrial Informatics, 2022, 18(12): 9017-9026.
[24]	赵仕存, 周泓. 强化学习驱动进化的模因算法求解准时制分布式柔性作业车间调度问题[J]. 控制与决策, 2026, 41(4): 905-918.
	Zhao Shicun, Zhou Hong. Reinforcement Learning-driven Evolutionary Memetic Algorithm for Solving Just-in-time Distributed Flexible Job Shop Scheduling Problem[J]. Control and Decision, 2026, 41(4): 905-918.
[25]	张坤鹏, 王艳, 纪志成. 基于不完全信息博弈的云制造群智能优化方法[J]. 系统仿真学报, 2024, 36(4): 915-928.
	Zhang Kunpeng, Wang Yan, Ji Zhicheng. Intelligent Optimization Method of Cloud Manufacturing Swarm Based on Incomplete Information Game[J]. Journal of System Simulation, 2024, 36(4): 915-928.
[26]	李晓波, 郭银章. 基于语义相似度与改进PSO算法的云制造能力需求模型与匹配策略研究[J]. 现代制造工程, 2025(6): 30-44.
	Li Xiaobo, Guo Yinzhang. Research on Cloud Manufacturing Capability Demand Model and Matching Strategy Based on Semantic Similarity and Improved PSO Algorithm[J]. Modern Manufacturing Engineering, 2025(6): 30-44.
[27]	刘永奎, 张霖, 刘迎福, 等. 云制造环境下工业机器人远程监控系统设计与实现[J]. 系统仿真学报, 2023, 35(2): 318-329.
	Liu Yongkui, Zhang Lin, Liu Yingfu, et al. Design and Implementation of Industrial Robot Remote Monitoring System in Cloud Manufacturing[J]. Journal of System Simulation, 2023, 35(2): 318-329.
[28]	曹玉康, 刘全, 刘洪哲, 等. 基于图神经驱动自激励的协作多智能体强化学习方法[J]. 计算机学报, 2026, 49(1): 29-42.
	Cao Yukang, Liu Quan, Liu Hongzhe, et al. Graph Neural Network-driven Self-motivated Cooperative Multi-agent Reinforcement Learning Method[J]. Chinese Journal of Computers, 2026, 49(1): 29-42.
[29]	马思佳, 张舒宁, 王奕涵, 等. 联合退相位噪声下量子囚徒困境纳什均衡分析[J]. 复杂系统与复杂性科学, 2023, 20(2): 68-73, 80.
	Ma Sijia, Zhang Shuning, Wang Yihan, et al. Analysis of Nash Equilibrium of Quantum Prisoner's Dilemma with Collective-dephasing Noise Channel[J]. Complex Systems and Complexity Science, 2023, 20(2): 68-73, 80.
[30]	孙文娟, 刘鹏, 宫华. 基于合作博弈的批处理机生产与成批运输协调调度[J]. 运筹与管理, 2024, 33(12): 115-121.
	Sun Wenjuan, Liu Peng, Gong Hua. Coordinated Scheduling of Production and Batch Transportation with Batch-processing Machine Based on Cooperative Games[J]. Operations Research and Management Science, 2024, 33(12): 115-121.
[31]	王鹏, 王要玉, 王建才. 零售平台自有品牌与制造商渠道策略的竞合博弈分析[J]. 中国管理科学, 2024, 32(9): 214-224.
	Wang Peng, Wang Yaoyu, Wang Jiancai. Co-opetition Game Analysis Between Store Brand Strategy of Platform and Selling Channel Strategy of Manufacturer[J]. Chinese Journal of Management Science, 2024, 32(9): 214-224.
[32]	Gu Bilu, Yiming Lü, Zhu Jiyu, et al. Analyzing the Practice of Medical Humanistic Care Based on a Social Learning Model: Mapping the Trajectory of the Learning Dynamic Process from the Learner's Perspective[J]. Frontiers in Medicine, 2025, 12: 1601951.
[33]	Hung Chih-Chieh, Gao Xiaoyuan, Liu Zhen, et al. CECM: A Cognitive Emotional Contagion Model in Social Networks[J]. Multimedia Tools and Applications, 2024, 83(1): 1001-1023.
[34]	Shahabi-Nejad Fateme, Mohammad Mehdi Ebadzadeh. A Fast and Stable Framework for Generative Adversarial Imitation Learning[J]. Engineering Applications of Artificial Intelligence, 2025, 162: 112460.
[35]	徐智霞, 王蕊, 孙楠, 等. 基于改进遗传算法的协同干扰资源分配问题研究[J]. 系统仿真学报, 2025, 37(12): 3176-3188.
	Xu Zhixia, Wang Rui, Sun Nan, et al. Research on Cooperative Interference Allocation of Jamming Resources Based on Improved Genetic Algorithm[J]. Journal of System Simulation, 2025, 37(12): 3176-3188.
[36]	Li Yulin, He Deqiang, Jin Zhenzhen, et al. The Maintenance Optimization Strategy for Key Components of Train Bogies Based on DQN[J]. Engineering Research Express, 2025, 7(4): 045576.
[37]	Smith J M, Price G R. The Logic of Animal Conflict[J]. Nature, 1973, 246(5427): 15-18.
[38]	Murali Divya, Shaiju A J. Best-response Dynamics for Evolutionary Stochastic Games[J]. International Game Theory Review, 2023, 25(4): 1-31.
[39]	弗里德利希·冯·哈耶克. 法律、立法与自由: 第一卷-规则与秩序[M]. 邓正来, 译. 北京: 中国大百科全书出版社, 2000.Hayek F A. Law,
	Legislation and Liberty: Vol. 1: Rules and Order[M]. Translated by Deng Zhenglai. Beijing: Encyclopedia of China Publishing House, 2000.
[40]	Okasha S. Evolution and the Levels of Selection[M]. Oxford: Oxford University Press, 2006.
[41]	Szabó György, Tőke Csaba. Evolutionary Prisoner's Dilemma Game on a Square Lattice[J]. Physical Review E, 1998, 58(1): 69-73.
[42]	国家统计局. 中国统计年鉴2024[M]. 北京: 中国统计出版社, 2024.
	National Bureau of Statistics. China Statistical Yearbook 2024[M]. Beijing: China Statistics Press, 2024.
[43]	薛霄. 复杂系统的计算实验方法: 原理、模型与案例[M]. 北京: 科学出版社, 2020: 59-200.

项目	SLE^[22]	SLE2^[23]	本文模型
个体学习模式	OODA循环	OODA循环	PREA和OODA循环嵌套
个体学习技术	遗传算法	遗传算法、强化学习	遗传算法、深度强化学习
组织拓扑结构	随机分布	层级结构	层级结构
组织演化规则	邀请邻居并学习	群体智能的交互模式	基于战略定位、商业模式等策略的演化博弈
社会层面演化	学习精英经验	社会交流和分层机制	基于精英文化(例如策略)组织间演化博弈

属性	现实模型	计算模型
数量	不同类型企业的数量	不同类型企业Agent的数量
获取订单	企业的市场竞争力决定了获得订单的数量	企业Agent的视野
处理订单	企业竞争力决定了其处理订单的数量	企业Agent处理订单的时间
运营成本	企业的生产成本、管理成本等运营成本	企业Agent的移动能量消耗和日常消耗等
能量值	决定企业生存时间的资本	企业Agent的能量值(在消耗中减少同时处理完订单会增加)
繁殖	新企业涌入市场或者企业扩大规模	当企业Agent的能量值超过繁殖阈值时繁殖新子代企业Agent
死亡	企业在竞争中倒闭或缩小规模	企业Agent能量值为0时会死亡