摘要
空调负荷在居民用电中占据高比例,监测其运行情况具有重要意义,可以引导居民合理用电,保证电网的稳定运行,同时可为需求响应提供决策支持,缓解供需矛盾。目前空调负荷监测工作相对较少,大多作为非侵入式负荷监测的一部分来开展,选取的输入数据主要考虑通用性,较少关注空调的运行规律以及气象因素的影响,导致空调监测的准确率仍有不足。针对该问题,该文提出了基于专家知识与双分支网络的空调监测方法,基于长短时记忆神经网络(long short term memory,LSTM)构建时序分支以深度挖掘空调运行的时序特征,基于反向传播神经网络(Back Propagation,BP)构建专家知识电气特征分支以捕捉空调的运行规律。对20名用户一年真实数据的实验结果表明,与传统LSTM模型相比,该模型能实现对空调负荷的精准辨识,为空调负荷的需求响应潜力评估提供支撑。
Air conditioning load occupies a large proportion of residential electricity consumption,and monitoring its operation is of great significance,which can guide residents to use electricity reasonably,ensure the stable operation of the power grid,and at the same time provide decision-making support for demand response to alleviate the contradiction between supply and demand.At present,there are relatively few air conditioning load monitoring works,most of which are carried out as a part of nonintrusive load monitoring.The selected input data mainly consider the universality,and pay little attention to the operation rules of air conditioning and the influence of meteorological factors,resulting in the accuracy of air conditioning monitoring is still insufficient.To address this problem,this paper proposes an air conditioning monitoring method based on expert knowledge and twin branch network,a time sequence branch is constructed based on long short term memory neural network(LSTM)to deeply mine the time sequence characteristics of air conditioner operation,and an expert knowledge electrical feature branch is constructed based on back propagation neural network(BP)to capture the operation law of the air conditioner.The experimental results of one-year real data from 20 users show that compared with the traditional LSTM model,the proposed model can realize accurate identification of air conditioning loads,whick provides support for the assessment of demand response potential of air conditioning loads.
作者
高勇
张俊玮
吕菁
谈竹奎
高吉普
GAO Yong;ZHANG Junwei;LYU Jing;TAN Zhukui;GAO Jipu(Electric Power Research Institute of Guizhou Power Grid Co.,Ltd.,Guiyang 550002,Guizhou,China;Tongren Power Supply Bureau of Guizhou Power Grid Co.,Ltd.,Tongren 554300,Guizhou,China)
出处
《电力大数据》
2025年第1期50-57,共8页
Power Systems and Big Data
基金
中国南方电网有限责任公司科技项目(GZKJXM20222137,GZKJXM20222141)。
关键词
负荷辨识
空调监测
专家知识
LSTM神经网络
BP神经网络
load identification
air conditioning monitoring
expert knowledge
LSTM neural network
BP neural network
作者简介
高勇(1993),男,硕士,工程师,主要从事智能用电技术研究工作。
