Construction Method for Autonomous Agents of Electrical Appliances Based on Functional States and Its Application

LIU Weifeng; SHEN Yu; WANG Zhihua; MENG Yuhang; WU Qing; HE Guangyu

doi:10.7500/AEPS20250109001

您当前的位置：

首页 >

文章列表页 >

Construction Method for Autonomous Agents of Electrical Appliances Based on Functional States and Its Application

Application Research | 更新时间：2025-09-25

- Construction Method for Autonomous Agents of Electrical Appliances Based on Functional States and Its Application
- Automation of Electric Power Systems Vol. 49, Issue 18, Pages: 195-207(2025)
- 作者机构：
  
  1.电力传输与功率变换教育部重点实验室（上海交通大学），上海市 200240
  2.清华大学电机工程与应用电子技术系，北京市 100084
  3.清华长三角研究院能源互联网研究中心，浙江省嘉兴市 314006
  4.国网上海市电力公司电力调度控制中心，上海市 200122
  5.华北电力大学海南热带新型电力系统研究院，海南省海口市 570311
- 作者简介：
- 基金信息：
  
  National Key R&D Program of China(2024YFE0110900)
- DOI：10.7500/AEPS20250109001
  CLC：
- Received：09 January 2025，
  
  Revised：2025-03-28，
  
  Published Online：16 May 2025，
  
  Published：25 September 2025
- 稿件说明：
移动端阅览
刘伟峰,沈瑜,王治华等.基于工作状态的电器自主智能体构建方法及应用[J].电力系统自动化,2025,49(18):195-207.

LIU Weifeng,SHEN Yu,WANG Zhihua,et al.Construction Method for Autonomous Agents of Electrical Appliances Based on Functional States and Its Application[J].Automation of Electric Power Systems,2025,49(18):195-207.
刘伟峰,沈瑜,王治华等.基于工作状态的电器自主智能体构建方法及应用[J].电力系统自动化,2025,49(18):195-207. DOI： 10.7500/AEPS20250109001.

LIU Weifeng,SHEN Yu,WANG Zhihua,et al.Construction Method for Autonomous Agents of Electrical Appliances Based on Functional States and Its Application[J].Automation of Electric Power Systems,2025,49(18):195-207. DOI： 10.7500/AEPS20250109001.

摘要

为使生活电器能像智能机器人一样主动适应用电需求和运行环境，提出了状态切换技术路线下的电器自主智能体构建方法，使得智能体可在智能用电场景和需求响应场景中提供恰当的电力服务。首先，从生活电器视角提出了相容性概念及评估方法，以量化生活电器提供的电力服务与用电需求、运行环境间的匹配程度。其次，根据电力服务提供的价值，定义并划分了一系列工作状态，这些状态构成了电器自主智能体在不同用电场景中自主优化性能的基础。然后，设计了工作状态驱动的自趋优运行方法，通过工作状态自识别和自切换方法，确保电器自主智能体始终处于趋向最优状态的过程。最后，基于自律分散理论，设计了电器自主智能体的仿真框架，并对1万个灯和变频空调的自主智能体进行了仿真。通过分析这些电器自主智能体的性能表现和不同驱动方法的效果，验证了所提方法的优越性。同时，探讨了电器自主智能体在智能用电和需求响应场景中的应用效果，部分结果可作为工程实施和政策制定的参考。

Abstract

To enable residential electrical appliances to actively adapt to electricity demand and operation environment like intelligent robots

a construction method for autonomous agents of electrical appliances is proposed utilizing a technology roadmap based on state transitions. These agents are capable of providing appropriate electrical services in scenarios of intelligent electricity consumption and demand response. Firstly

the concept of compatibility and its evaluation method are proposed from the perspective of residential electrical appliances to quantify the alignment between the power services provided by residential electrical appliances and the electricity demand and operation environment. Secondly

a series of functional states are defined and divided according to the values provided by these electricity services. These states form the foundation for autonomously optimizing the performance of the autonomous agents of electrical appliances in various electricity consumption scenarios. Then

a self-approaching optimization operation method driven by these functional states is designed

which ensures that the autonomous agents of electrical appliances perpetually strive towards an optimal state through self-recognition and self-transition methods of functional states. Finally

based on the autonomous decentralized system theory

a simulation framework for these autonomous agents of electrical appliances is designed and implemented on autonomous agents including 10 000 lights and inverter air conditioners. The performance of these autonomous agents of electrical appliances and the effects of various driving methods are analyzed to verify the superiority of the proposed method. Meanwhile

the application effects of these autonomous agents of electrical appliances in the intelligent electricity consumption and demand response scenarios is discussed. Some of the results can serve as references for engineering implementation and policy formulation.

关键词

Keywords

references

MarketsandMarkets . AI Agents market by Agent role， offering， Agent system—global forecast to 2030 ［EB/OL］. ［ 2025-01-01 ］. https：//www.marketsandmarkets.com/Market-Reports/ai-agents-market-15761548.html https://www.marketsandmarkets.com/Market-Reports/ai-agents-market-15761548.html .

周奇，马瑞，王铁强，等 . 基于多智能体的主动配电网空调负荷聚合及其降压调温削减方法［J］. 中国电机工程学报， 2022 ， 42 （ 18 ）： 6668 - 6681 .

ZHOU Qi ， MA Rui ， WANG Tieqiang ， et al . Multi-agent-system based air-conditioning load aggregation method and its shedding by voltage reduction and temperature adjustment of active distribution network ［J］. Proceedings of the CSEE ， 2022 ， 42 （ 18 ）： 6668 - 6681 .

ALROBAIAN A A ， ALSAGRI A S . Multi-agent-based energy management for a fully electrified residential consumption ［J］. Energy ， 2023 ， 282 ： 128852 .

姚期智 . 人工智能的科学视角［EB/OL］.［ 2024-09-28 ］. https：//mp.weixin.qq.com/s/zNkF90-ZsK1Ec70OShYVdQ https://mp.weixin.qq.com/s/zNkF90-ZsK1Ec70OShYVdQ .

YAO Qizhi . The scientific perspective of artificial intelligence ［EB/OL］. ［ 2024-09-28 ］. https：//mp.weixin.qq.com/s/zNkF90-ZsK1Ec70OShYVdQ https://mp.weixin.qq.com/s/zNkF90-ZsK1Ec70OShYVdQ .

周欢，王芬，李志勇，等 . 虚拟电厂自趋优负荷跟踪控制策略［J］. 中国电机工程学报， 2021 ， 41 （ 24 ）： 8334 - 8349 .

ZHOU Huan ， WANG Fen ， LI Zhiyong ， et al . Load tracking control strategy for virtual power plant via self-approaching optimization ［J］. Proceedings of the CSEE ， 2021 ， 41 （ 24 ）： 8334 - 8349 .

ARYAL A ， BECERIK-GERBER B ， LUCAS G M ， et al . Intelligent agents to improve thermal satisfaction by controlling personal comfort systems under different levels of automation ［J］. IEEE Internet of Things Journal ， 2021 ， 8 （ 8 ）： 7089 - 7100 .

刘伟峰，范帅，田济源，等 . 面向需求响应的空调智能体：概念、构建和应用［J］. 电力系统自动化， 2024 ， 48 （ 22 ）： 70 - 83 .

LIU Weifeng ， FAN Shuai ， TIAN Jiyuan ， et al . Air conditioner intelligent agent for demand response： concept， construction， and application ［J］. Automation of Electric Power Systems ， 2024 ， 48 （ 22 ）： 70 - 83 .

王闯 . 有关建筑用能的人行为模拟研究［D］. 北京：清华大学， 2014 .

WANG Chuang . Research on human behavior simulation of building energy consumption ［D］. Beijing ： Tsinghua University ， 2014 .

陈星，黄志明，叶心舒，等 . 智能家居情境感知服务的运行时建模与执行方法［J］. 软件学报， 2019 ， 30 （ 11 ）： 3297 - 3312 .

CHEN Xing ， HUANG Zhiming ， YE Xinshu ， et al . Approach to modeling and executing context-aware services of smart home at runtime ［J］. Journal of Software ， 2019 ， 30 （ 11 ）： 3297 - 3312 .

JIANG Y L ， ANDREW EJENAKEVWE K ， WANG J K ， et al . Development， implementation， and impact analysis of model predictive control-based optimal precooling using smart home thermostats ［J］. Energy and Buildings ， 2024 ， 303 ： 113790 .

包顺，周礼刚 . 加型Pythagorean模糊偏好关系的多属性决策方法［J］. 计算机工程与应用， 2021 ， 57 （ 17 ）： 61 - 67 .

BAO Shun ， ZHOU Ligang . Multiple attribute decision making method based on additive consistent Pythagorean fuzzy preference relations ［J］. Computer Engineering and Applications ， 2021 ， 57 （ 17 ）： 61 - 67 .

ALıÇ O ， FILIK Ü B . A multi-objective home energy management system for explicit cost-comfort analysis considering appliance category-based discomfort models and demand response programs ［J］. Energy and Buildings ， 2021 ， 240 ： 110868 .

PAMULAPATI T ， MALLIPEDDI R ， LEE M . Multi-objective home appliance scheduling with implicit and interactive user satisfaction modelling ［J］. Applied Energy ， 2020 ， 267 ： 114690 .

傅质馨，李潇逸，朱俊澎，等 . 基于马尔科夫决策过程的家庭能量管理智能优化策略［J］. 电力自动化设备， 2020 ， 40 （ 7 ）： 141 - 152 .

FU Zhixin ， LI Xiaoyi ， ZHU Junpeng ， et al . Intelligent optimization strategy of home energy management based on Markov decision process ［J］. Electric Power Automation Equipment ， 2020 ， 40 （ 7 ）： 141 - 152 .

张甜，赵奇，陈中，等 . 基于深度强化学习的家庭能量管理分层优化策略［J］. 电力系统自动化， 2021 ， 45 （ 21 ）： 149 - 158 .

ZHANG Tian ， ZHAO Qi ， CHEN Zhong ， et al . Hierarchical optimization strategy for home energy management based on deep reinforcement learning ［J］. Automation of Electric Power Systems ， 2021 ， 45 （ 21 ）： 149 - 158 .

LÜ X Q ， ZHAI X R ， ZHANG Y Y ， et al . Energy management and distribution of fuel cell hybrid power system based on efficient and stable movement of mobile robot ［J］. International Journal of Hydrogen Energy ， 2024 ， 94 ： 1064 - 1083 .

AZAZA M ， WALLIN F . Finite state machine household’s appliances models for non-intrusive energy estimation ［J］. Energy Procedia ， 2017 ， 105 ： 2157 - 2162 .

周汉斌，杨建，黄连生，等 . 基于有限状态机的三电平逆变器双矢量模型预测控制策略［J］. 电力系统自动化， 2023 ， 47 （ 11 ）： 155 - 164 .

ZHOU Hanbin ， YANG Jian ， HUANG Liansheng ， et al . Double-vector model predictive control strategy of three-level inverter based on finite state machine ［J］. Automation of Electric Power Systems ， 2023 ， 47 （ 11 ）： 155 - 164 .

罗平，樊星驰，章坚民，等 . 基于电器运行状态和深度学习的非侵入式负荷分解［J］. 电力系统自动化， 2021 ， 45 （ 12 ）： 49 - 56 .

LUO Ping ， FAN Xingchi ， ZHANG Jianmin ， et al . Non-intrusive load decomposition based on operation state of electrical appliances and deep learning ［J］. Automation of Electric Power Systems ， 2021 ， 45 （ 12 ）： 49 - 56 .

燕续峰，翟少鹏，何光宇 . 基于时间概率分布与电器组合超状态的非侵入式负荷分解［J］. 电力系统自动化， 2018 ， 42 （ 24 ）： 53 - 58 .

YAN Xufeng ， ZHAI Shaopeng ， HE Guangyu . Non-intrusive load disaggregation based on time probability distribution and super state of appliances ［J］. Automation of Electric Power Systems ， 2018 ， 42 （ 24 ）： 53 - 58 .

CASTILLA M ， ÁLVAREZ J D ， BERENGUEL M ， et al . A comparison of thermal comfort predictive control strategies ［J］. Energy and Buildings ， 2011 ， 43 （ 10 ）： 2737 - 2746 .

吴承鑫，沈海军，王治华，等 . 数据驱动的变频空调负荷模型参数在线辨识方法［J］. 电力系统自动化， 2022 ， 46 （ 1 ）： 120 - 129 .

WU Chengxin ， SHEN Haijun ， WANG Zhihua ， et al . Data-driven online identification method for parameters of inverter air-conditioning load model ［J］. Automation of Electric Power Systems ， 2022 ， 46 （ 1 ）： 120 - 129 .

COLLEDANCHISE M ， GREN P . Behavior trees in robotics and AI： an introduction ［M］. Boca Raton， USA ： CRC Press ， 2017 .

何光宇，孙英云，梅生伟，等 . 多指标自趋优的智能电网［J］. 电力系统自动化， 2009 ， 33 （ 17 ）： 1 - 5 .

HE Guangyu ， SUN Yingyun ， MEI Shengwei ， et al . Multi-indices self-approximate-optimal smart grid ［J］. Automation of Electric Power Systems ， 2009 ， 33 （ 17 ）： 1 - 5 .

谭永东 . 自律分散系统动态进化问题研究［D］. 成都：西南交通大学， 2007 .

TAN Yongdong . Research on dynamic evolution of autonomous decentralized systems ［D］. Chengdu ： Southwest Jiaotong University ， 2007 .

上海市发改委 . 2024年版上海市市民价格信息指南［EB/OL］.［ 2024-02-29 ］. https：//www.shanghai.gov.cn/nw17239/20240229/1fcafdb2cfd14f1694d804a4bd0bf2ae.html https://www.shanghai.gov.cn/nw17239/20240229/1fcafdb2cfd14f1694d804a4bd0bf2ae.html .

Shanghai Development and Reform Commission . 2024 Shanghai citizen price information guide ［EB/OL］. ［ 2024-02-29 ］. https：//www.shanghai.gov.cn/nw17239/20240229/1fcafdb2cfd14f1694d804a4bd0bf2ae.html https://www.shanghai.gov.cn/nw17239/20240229/1fcafdb2cfd14f1694d804a4bd0bf2ae.html .

江苏省发展改革委 . 江苏省电力需求响应实施细则（修订征求意见稿）［EB/OL］.［ 2024-04-23 ］. https：//fzggw.jiangsu.gov.cn/art/2024/4/23/art_296_11225170.html https://fzggw.jiangsu.gov.cn/art/2024/4/23/art_296_11225170.html .

Jiangsu Provincial Development and Reform Commission . Implementation rules for electricity demand response in Jiangsu Province （revised draft for comments）［EB/OL］. ［ 2024-04-23 ］. https：//fzggw.jiangsu.gov.cn/art/2024/4/23/art_296_11225170.html https://fzggw.jiangsu.gov.cn/art/2024/4/23/art_296_11225170.html .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Adaptive Control Method for Smart Homes in Dynamic Application Scenarios

Marginal Carbon Emission Factors in Multiple Time Periods and Analysis of Their Uncertainties

Related Author

SHEN YU

WU Qing

LIU Weifeng

SHEN YU

WANG Zhihua

MENG Yuhang

WU Qing

HE Guangyu

Related Institution

Energy Internet Research Center, Yangtze Delta Region Institute of Tsinghua University

Tropical New-type Power System Research Institute, North China Electric Power University

State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources (North China Electric Power University)

State Grid Electric Power Research Institute (NARI Group Corporation)

⁰