Energy Management Method for Integrated Energy Driven by Users’ Social Attributes

doi:10.16182/j.issn1004731x.joss.26-0057

Abstract

Abstract:

To explore a new interaction mechanism between an energy service provider (ESP) and multiple users, this paper proposes a complex modeling and energy management method for integrated energy systems driven by users' social attributes. A multi-agent interaction framework comprising an ESP and user clusters is established. To maximize the ESP's operational benefit and minimize users' energy costs, a leader-follower game-based energy management model is established within a reinforcement learning framework, and a distributed collaborative solution algorithm combining Q-learning and quadratic programming is proposed. Simulation results show that, compared with the traditional integrated demand response method, consideration of users' social attributes increases the ESP's operational benefit by 10.79%, reduces the total operating costs of user clusters I and II by 6.98% and 0.36%, respectively, and decreases system carbon emissions by 5.05%. The algorithm also achieves a good balance between convergence accuracy and computational efficiency.

Key words: integrated energy system, energy service provider, user, energy management, social attribute

CLC Number:

TP391

Zhu Yankai, Huang Yujing, Wang Qinghua, Zhang Xiaoning, Fang Fang, Niu Yuguang. Energy Management Method for Integrated Energy Driven by Users’ Social Attributes[J]. Journal of System Simulation, 2026, 38(8): 2152-2166.

Figures/Tables 23

Fig. 1

Fig. 2

Fig. 3

Table 1

Table 2

Table 3

Fig. 4

Fig. 5

Fig. 6

Fig. 7

Fig. 8

Fig. 9

Fig. 10

Fig. 11

Fig. 12

Table 4

Fig. 13

Table 5

Table 6

Table 7

Table 8

Fig. 14

Table 9

References 35

[1]	龙传煜, 张靖, 何宇, 等. 基于绿证-碳交易等价交互的综合能源系统低碳优化调度[J]. 电力自动化设备, 2026, 46(4): 149-156.
	Long Chuanyu, Zhang Jing, He Yu, et al. Low-carbon Optimal Dispatch of Integrated Energy Systems Considering Green Certificate-carbon Trading Equivalent Interactions[J]. Electric Power Automation Equipment, 2026, 46(4): 149-156.
[2]	Wang Ziren, Zhang Yuanan, Li Wei. A Bi-level Optimization Operation Method for Hydrogen-enriched Integrated Energy Systems Incorporating Dynamic Carbon Emission Factors[J]. Renewable Energy, 2026, 256: 124168.
[3]	谢晗烁. 基于博弈论的区域综合能源系统服务商运行策略研究[D]. 北京: 华北电力大学(北京), 2024.
	Xie Hanshuo. Research on Operational Strategies of Regional Integrated Energy System Service Providers Based on Game Theory[D]. Beijing: North China Electric Power University(Beijing), 2024.
[4]	李振坤, 王茹楠, 徐琛, 等. 基于混合博弈的社区综合能源服务商与微网群二阶段协同运行策略[J]. 现代电力, 2025, 42(2): 302-313.
	Li Zhenkun, Wang Runan, Xu Chen, et al. A Two-stage Collaborative Operation Strategy for Community Integrated Energy Service Provider and Microgrid Group Based on Mixed Game[J]. Modern Electric Power, 2025, 42(2): 302-313.
[5]	杨欣怡, 陈涛, 高赐威, 等. 虚拟电厂调节能力评估与典型运行模式用户画像方法[J]. 电网技术, 2026, 50(5): 1801-1811.
	Yang Xinyi, Chen Tao, Gao Ciwei, et al. Regulation Capability Assessment and User Profiling Methods for Typical Operational Modes of Virtual Power Plant[J]. Power System Technology, 2026, 50(5): 1801-1811.
[6]	李鹏, 吴迪凡, 李雨薇, 等. 基于综合需求响应和主从博弈的多微网综合能源系统优化调度策略[J]. 中国电机工程学报, 2021, 41(4): 1307-1321.
	Li Peng, Wu Difan, Li Yuwei, et al. Optimal Dispatch of Multi-microgrids Integrated Energy System Based on Integrated Demand Response and Stackelberg Game[J]. Proceedings of the CSEE, 2021, 41(4): 1307-1321.
[7]	王珂, 吴峰, 曹若琳, 等. 市场环境下需求响应行为特性及模型研究综述[J]. 电力系统自动化, 2024, 48(15): 1-14.
	Wang Ke, Wu Feng, Cao Ruolin, et al. Review on Characteristics and Models of Demand Response Behavior in Market Environment[J]. Automation of Electric Power Systems, 2024, 48(15): 1-14.
[8]	王仕炬, 刘天琪, 何川, 等. 基于舒适度的需求响应与碳交易的园区综合能源经济调度[J]. 电测与仪表, 2022, 59(11): 1-7.
	Wang Shiju, Liu Tianqi, He Chuan, et al. Comfort Demand Response and Carbon Trading Based Comprehensive Energy Economic Dispatching in Industrial Parks[J]. Electrical Measurement & Instrumentation, 2022, 59(11): 1-7.
[9]	陈钱蓁, 高红均, 王晓辉, 等. 面向产消用户的售电公司发-用电多元电力套餐优化[J]. 电力自动化设备, 2023, 43(5): 154-162.
	Chen Qianzhen, Gao Hongjun, Wang Xiaohui, et al. Prosumer Oriented Multiple Generation-consumption Electricity Package Optimization for Electricity Retailers[J]. Electric Power Automation Equipment, 2023, 43(5): 154-162.
[10]	段新会, 程泽龙, 张东超, 等. 考虑需求响应与两阶段P2G的综合能源系统优化调度[J]. 系统仿真学报, 2025, 37(8): 2139-2151.
	Duan Xinhui, Cheng Zelong, Zhang Dongchao, et al. Optimal Scheduling of an Integrated Energy System Considering Demand Response and Two-stage P2G[J]. Journal of System Simulation, 2025, 37(8): 2139-2151.
[11]	王玉东, 胡俊杰. 考虑多主体交互策略的综合能源系统P2P能-碳管理方法[J]. 系统仿真学报, 2024, 36(10): 2488-2502.
	Wang Yudong, Hu Junjie. Peer-to-peer Energy-carbon Management Method of Multiple Integrated Energy Systems Considering Multi-agent Interaction Strategy[J]. Journal of System Simulation, 2024, 36(10): 2488-2502.
[12]	Zhang Bowen, Baligen Talihati, Fan Hongtao, et al. A Dynamic Carbon Flow Traceability Framework for Integrated Energy Systems[J]. Journal of Cleaner Production, 2025, 518: 145878.
[13]	An Na, Liu Tingxiang, Yang Libin, et al. Low Carbon Economic Dispatch of Integrated Energy Systems with Multiple Types of Energy Storage Considering Uncertainty[J]. Renewable Energy, 2025, 43(9): 1529-1671.
[14]	钟华平, 范钰波, 税纪钧, 等. 考虑源荷不确定性和线性碳交易的综合能源系统优化调度[J]. 系统仿真学报, 2025, 37(10): 2485-2499.
	Zhong Huaping, Fan Yubo, Shui Jijun, et al. Optimal Scheduling of Integrated Energy Systems Considering Source-load Uncertainty and Linear Carbon Trading[J]. Journal of System Simulation, 2025, 37(10): 2485-2499.
[15]	Wang Fulin, Wang Bozhao, Tang Wentao. Reinforcement Learning Optimization Scheduling of Micro-integrated Energy Systems Under Uncertain Factors[J]. Journal of Physics: Conference Series, 2025, 3012(1): 012089.
[16]	Araújo David, Santos Gabriel, Teixeira Brígida, et al. Reinforcement Learning for Real-time Price Prediction in Energy Systems[C]//Progress in Artificial Intelligence. Cham: Springer Nature Switzerland, 2026: 451-463.
[17]	庞超, 霍现旭, 王智爽, 等. 面向用户隐私保护的综合能源系统博弈与强化学习协同调度方法[J/OL]. 电力系统及其自动化学报. (2025-12-23) [2026-01-06]. .
	Pang Chao, Huo Xianxu, Wang Zhishuang, et al. A Game-theoretic and Reinforcement Learning-based Cooperative Scheduling Method for Integrated Energy Systems with User Privacy Preservation[J/OL]. Proceedings of the CSU-EPSA. (2025-12-23) [2026-01-06]. .
[18]	李玉璟, 李泽宁, 郝军强. 基于多智能体深度强化学习的充电站实时协调定价方法[J]. 电力系统自动化, 2026, 50(3): 125-134.
	Li Yujing, Li Zening, Hao Junqiang. Real-time Coordinated Pricing Method for Charging Stations Based on Multi-agent Deep Reinforcement Learning[J]. Automation of Electric Power Systems, 2026, 50(3): 125-134.
[19]	郑颖颖, 缪新义, 王晖, 等. 支持时变需求响应激励价格的电动汽车优化充电策略[J]. 电力系统自动化, 2025, 49(9): 96-106.
	Zheng Yingying, Miao Xinyi, Wang Hui, et al. Optimal Charging Strategies for Electric Vehicles Supporting Time-varying Demand Response Incentive Price[J]. Automation of Electric Power Systems, 2025, 49(9): 96-106.
[20]	Khorramdel Hossein, Gitizadeh Mohsen, Siano Pierluigi, et al. Evaluating the Economic Impact of Users' Personality on Selection of Demand Response Programs[J]. CSEE Journal of Power and Energy Systems, 2023, 9(3): 1036-1050.
[21]	Edomah Norbert. Who Triggers Change? Social Network Mapping, Stakeholder Analysis and Energy Systems Interventions in Nigeria's Electricity Sector[J]. International Journal of Sustainable Energy Planning and Management, 2023, 37: 5-20.
[22]	Peralta Jaime, Velar Victor, Quintana Eugenio, et al. Dynamic Behavior of Grid-forming Inverters in Large-scale Low-strength Power Grids[C]//2024 IEEE/PES Transmission and Distribution Conference and Exposition (T&D). Piscataway: IEEE, 2024: 1-5.
[23]	Talab Odia A, Avci Isa. Energy Management in Microgrids Using Model-free Deep Reinforcement Learning Approach[J]. IEEE Access, 2025, 13: 5871-5891.
[24]	Siti Nuraishah Agos Jawaddi, Ismail Azlan, Mohd Suffian Sulaiman, et al. Analyzing Energy-efficient and Kubernetes-based Autoscaling of Microservices Using Probabilistic Model Checking[J]. Journal of Grid Computing, 2025, 23(1): 3.
[25]	Fernandez S. Energy and Memory: A New Neural Network Paradigm[EB/OL]. (2025-05-14) [2026-01-06]. .
[26]	Uralde Jokin, Barambones Oscar, Calvo Isidro, et al. Neural Network Approach for the Energy Management and Gear Selection of a Fuel Cell Electric Vehicle[J]. International Journal of Hydrogen Energy, 2025, 171: 151196.
[27]	马苗苗, 董利鹏, 刘向杰. 基于Q-learning算法的多智能体微电网能量管理策略[J]. 系统仿真学报, 2023, 35(7): 1487-1496.
	Ma Miaomiao, Dong Lipeng, Liu Xiangjie. Energy Management Strategy of Multi-agent Microgrid Based on Q-learning Algorithm[J]. Journal of System Simulation, 2023, 35(7): 1487-1496.
[28]	王海洋, 李珂, 张承慧, 等. 基于主从博弈的社区综合能源系统分布式协同优化运行策略[J]. 中国电机工程学报, 2020, 40(17): 5435-5444.
	Wang Haiyang, Li Ke, Zhang Chenghui, et al. Distributed Coordinative Optimal Operation of Community Integrated Energy System Based on Stackelberg Game[J]. Proceedings of the CSEE, 2020, 40(17): 5435-5444.
[29]	Niromandfam Amir, Saeid Pashaei Choboghloo. Modeling Electricity Demand, Welfare Function and Elasticity of Electricity Demand Based on the Customers Risk Aversion Behavior[EB/OL]. (2020-10-15) [2026-01-06]. .
[30]	Eric John Wilczynski, Chambers Jonathan, Patel Martin K, et al. Assessment of the Thermal Energy Flexibility of Residential Buildings with Heat Pumps Under Various Electric Tariff Designs[J]. Energy and Buildings, 2023, 294: 113257.
[31]	Yang Yang, Raman Gurupraanesh, Chih-Hsien Peng Jimmy. Shaping Residential Electricity Demand with Negative Pricing[J]. Nature Energy, 2026, 11(1): 58-65.
[32]	Cassidy A, Strube M, Nehorai A. A Framework for Exploring Social Network and Personality-based Predictors of Smart Grid Diffusion[J]. IEEE Transactions on Smart Grid, 2015, 6(3): 1314-1322.
[33]	Chen Weilong, Liu Xinru, Zhang Xinran, et al. SocioDiff: A Socio-aware Diffusion Model for Residential Electricity Consumption Data Generation[J]. IEEE Transactions on Smart Grid, 2025, 16(5): 3786-3800.
[34]	Marrero Lester, Sbárbaro Daniel, García-Santander Luis. Online Demand Response Characterization Based on Variability in Customer Behavior[J]. Journal of Modern Power Systems and Clean Energy, 2024, 12(3): 936-946.
[35]	Chen Liudong, Liu Nian, Li Chenchen, et al. Peer-to-peer Energy Sharing with Social Attributes: A Stochastic Leader-follower Game Approach[J]. IEEE Transactions on Industrial Informatics, 2021, 17(4): 2545-2556.

时段	售电价/(元/kW·h)
01:00-8:00	0.45
09:00-11:00; 16:00-17:00; 23:00-24:00	0.86
12:00-15:00; 20:00-22:00	1.35

参数	参数名称	用户1	用户2
价格敏感与偏好	电价敏感系数	0.8	0.6
	热价敏感系数	0.9	0.7
	热价容忍度	0.05	0.03
	心理热价参考阈值	0.4	0.4
社会网络影响	电能选择社会影响依赖度	0.3	0.3
	热能选择社会影响依赖度	0.3	0.3
	信息传播延迟系数	0.8	0.3
	异质性信任系数	0.7~0.9	0.4~0.6
	网络节点度均值	15	8
	社会影响权重矩阵	权重和为1
不确定性扰动	随机扰动方差	高峰段：0.05 平时段：0.03 低谷时段：0.01
负荷弹性与满意度	电负荷价格弹性系数	0.5	0.5
	热负荷价格弹性系数	0.4	0.4
	电能满意度损失系数	0.02	0.02
	热能满意度损失系数	0.03	0.03

设备	参数	ESP	用户1	用户2
CHP	机组容量/kW	1 500	—	—
	运维系数/(元/kW)	0.05	—	—
	热电比	1.35	—	—
HP	机组容量/kW	—	1 500	1 000
	运维系数/(元/kW)	—	0.026	0.026
	制热系数	—	0.90	0.86
GB	机组容量/kW	1 500	—	—
	运维系数/(元/kW)	0.15	—	—
	制热系数	0.85	—	—
PV	机组容量/kW	—	1 000	2 500
PV	运维系数/(元/kW)	—	0.025	0.025
ES	机组容量/kW	1 000	—	2 000
ES	运维系数/(元/kW)	0.02	—	0.02
HS	机组容量/kW	1 000	—	—
HS	运维系数/(元/kW)	0.02	—	—

性能指标	场景I	场景II
收敛迭代次数	35	48
总求解时间/s	24.15	27.68
最终系统Q值/元	48 229.79	47 913.14
相对理论最优误差/%	0.24	0.05

性能指标	本文方法	DRL方法
收敛迭代次数	48	152
总求解时间/s	27.68	68.42
最终系统Q值/元	47 913.14	48 120.56
相对理论最优误差/%	0.05	0.18