Research on a federated learning ADMM-based hierarchical distributed demand response strategy for industrial parks

LIU Mohan; CUI Mingjian; GU Liting; WANG Yishen

doi:10.19783/j.cnki.pspc.251247

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

Research on a federated learning ADMM-based hierarchical distributed demand response strategy for industrial parks

更新时间：2026-07-27

- Research on a federated learning ADMM-based hierarchical distributed demand response strategy for industrial parks
- Power System Protection and Control Vol. 54, Issue 12, (2026)
- 作者机构：
- 作者简介：
- 基金信息：
- DOI：10.19783/j.cnki.pspc.251247
  CLC：
- Published：2026
- 稿件说明：
移动端阅览
LIU Mohan, CUI Mingjian, GU Liting, et al. Research on a federated learning ADMM-based hierarchical distributed demand response strategy for industrial parks[J]. Power System Protection and Control, 2026, 54(12).
DOI：

LIU Mohan, CUI Mingjian, GU Liting, et al. Research on a federated learning ADMM-based hierarchical distributed demand response strategy for industrial parks[J]. Power System Protection and Control, 2026, 54(12). DOI： 10.19783/j.cnki.pspc.251247.

摘要

工业用户是激励型需求响应的主要参与者。然而，集中式求解其响应策略难以兼顾多主体利益，易引发隐私泄露风险。为此，提出了一种基于联邦学习交替方向乘子法 (federated learning alternating direction method of multipliers

FedADMM) 的工业园区分层分布式需求响应策略，在考虑聚合商和用户双方利益的同时，有效保护敏感数据。首先，建立兼顾多主体利益的分层响应模型。聚合商层以响应收益最大为目标优化用户级响应策略，用户层以额外收益最大为目标优化设备级响应策略。随后，提出改进的联邦学习交替方向乘子法 (improved FedADMM

IFedADMM)，通过对全局参数更新、传输信息加密、客户端迭代规则方面进行改进，实现了迭代过程隐私保护和计算效率的提高。接着，采用该方法分布式求解优化模型，双方动态更新补偿价格直至收敛至最优解。最后，通过某工业园区算例验证了所提方法在提高隐私保护和计算效率等方面的有效性。

Abstract

Industrial customers are the primary participants in incentive-based demand response programs. However

centralized optimization of their response strategies struggles to balance the interests of multiple stakeholders and is prone to privacy leakage risks. To address these issues

this paper proposes a hierarchical distributed demand response strategy for industrial parks utilizing the federated learning alternating direction method of multipliers (FedADMM). This approach simultaneously considers the interests of both aggregators and customers while effectively protecting sensitive data. First

a hierarchical response model is established

accounting for the benefits of multiple stakeholders. The aggregator layer optimizes customer-level response strategies to maximize demand response profits

while the customer layer optimizes device-level strategies to maximize additional revenues. Second

an improved FedADMM (IFedADMM) is proposed. By improving global parameter updating

information transmission encryption

and client-side iteration rules

the proposed method achieves privacy protection during the iterative process and enhances computational efficiency. The optimization model is then solved in a distributed manner

where both parties dynamically update compensation prices until convergence to the optimal solution. Finally

a case study of an industrial park is conducted to verify the effectiveness of the proposed method in improving privacy protection and computational efficiency.

关键词

Keywords

references

ZANG Haixiang, ZHAO Yongkai, SUN Kang, et al. Distribution network optimization based on topology security-constrained integrated reinforcement learning[J]. Protection and Control of Modern Power Systems, 2026, 11(2): 48-61.

WANG Fei, ZHOU Lidong, REN Hui, et al. Multi- objective optimization model of source-load-storage synergetic dispatch for a building energy management system based on TOU price demand response[J]. IEEE Transactions on Industry Applications, 2018, 54(2): 1017-1028.

CAI Xinlei, PAN Tingzhe, YU Zhenfan, et al. Active potential mining of day-ahead invitation demand response for industrial conveying loads[J]. Journal of Computational Methods in Sciences and Engineering, 2025, 25(5): 4231-4245.

GERAMI N, GHASEMI A, LOTFI A, et al. Energy consumption modeling of production process for industrial factories in a day ahead scheduling with demand response[J]. Sustainable Energy, Grids and Networks, 2021, 25.

LÜ R, GUO Hongye, TANG Qinghu, et al. Production scheduling identification: an inverse optimization approach for industrial load modeling using smart meter data[J]. IEEE Transactions on Smart Grid, 2025, 16(2): 1207-1220.

JAGANA J S, AMARAN S, ZHANG Q. Multistage robust mixed-integer optimization for industrial demand response with interruptible load[J]. Computers and Chemical Engineering, 2025, 194.

LI Mingxuan, HE Dawei. Dispatch method of industrial demand response considering uncertainty[J]. IEEE Internet of Things Journal, 2024, 11(24): 39195-39205.

XU Xiaofeng, WANG Boyu, SHI Mengshu, et al. Research on hydrogen storage system configuration and optimization in regional integrated energy systems considering electric-gas-heat-hydrogen integrated demand response[J]. International Journal of Hydrogen Energy, 2025, 135: 86-103.

ZHAO Wenna, MA Kai, YANG Jie, et al. A multi-time scale demand response scheme based on noncooperative game for economic operation of industrial park[J]. Energy, 2024, 302.

PARVIZI S, MONTAZERI M, KEBRIAEI H. Contract- based demand response mechanism for commercial and industrial customers[J]. IEEE Transactions on Automation Science and Engineering, 2025, 22: 3135-3146.

WEI Jingdong, ZHANG Yao, WANG Jianxuan, et al. Decentralized demand management based on alternating direction method of multipliers algorithm for industrial park with CHP units and thermal storage[J]. Journal of Modern Power Systems and Clean Energy, 2022, 10(1): 120-130.

ALLMAN A, ZHANG Qi. Distributed cooperative industrial demand response[J]. Journal of Process Control, 2020, 86: 81-93.

ZHANG Xiaoyan, WANG Cenfeng, XIAO Jiangwen, et al. A transactive energy cooperation scheduling for hydrogen-based community microgrid with refueling preferences of hydrogen vehicles[J]. Applied Energy, 2025, 377.

WANG Dongxia, LIN Yanli, PENG Xin, et al. Differential-privacy-preserving distributed ADMM using load-balanced sparse all reduce communication[J]. IEEE Transactions on Cognitive Communications and Networking, 2026, 12: 4361-4375.

GONG Yonghai, LI Yichuan, FRERIS N M. FedADMM: a robust federated deep learning framework via primal-dual optimization[J]. arXiv: 2204.03529, 2026.

GABAY D, MERCIER B. A dual algorithm for the solution of nonlinear variational problems via finite element approximation[J]. Computers Mathematics with Applications, 1976, 2(1): 17-40.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Market-oriented dual-type demand response operation strategy for electric vehicle aggregators considering temperature effects

计及多维紧急负荷调控目标的智能用电开关设备优化配置

基于多主体博弈的配电网-多综合能源系统分布式优化调度

考虑动态碳势和需求响应的配电网低碳调度策略

Voltage control of single-phase grid-forming inverters based on a model-assisted extended state observer with a quasi-proportional resonant controller

Related Author

LI Xianshan

LI Jiahui

LI Danning

QIU Chenglong

ZHANG Yuanhang

LIU Songkai

LI Fei

YAN Pengfei

Related Institution

State Grid Chongqing Electric Power Company

ZHU Rui(1. State Key Laboratory of Power Transmission Equipment Technology (Chongqing University)

State Grid Changshou Power Supply Company

CHENG Ying(1. Hubei Engineering Research Center of New Energy Microgrid (China Three Gorges University)

Research Center of Smart Energy Technology, School of Electric Power Engineering, South China University of Technology

AI问答

⁰