基于Attention和残差网络的非侵入式负荷监测
TM714; 非侵入式负荷监测(non-intrusive load monitoring,NILM)可以从家庭电能表的总功率读数,估算出各用电器的功率.由于对于同一类用电器,其状态种类、各状态持续时长、各状态的功率波形都不同,这使得基于特征工程和聚类的模型的泛化能力不强;回归模型的分解功率难以迅速跟踪真实功率.针对这些问题,文中将回归问题转化为在序列每个时刻的多分类问题,并提出基于Attention和残差网络的非侵入式负荷监测模型.该模型基于具有编码器和解码器的seq2seq框架,首先通过嵌入矩阵将高维稀疏one-hot向量映射为低维稠密向量;在编码部分,通过双向GRU从前后两个方向提取序列...
Saved in:
| Published in | 电测与仪表 Vol. 61; no. 6; pp. 173 - 180 |
|---|---|
| Main Authors | , , , |
| Format | Journal Article |
| Language | Chinese |
| Published |
华南理工大学,广州 510006
15.06.2024
|
| Subjects | |
| Online Access | Get full text |
| ISSN | 1001-1390 |
| DOI | 10.19753/j.issn1001-1390.2024.06.023 |
Cover
| Abstract | TM714; 非侵入式负荷监测(non-intrusive load monitoring,NILM)可以从家庭电能表的总功率读数,估算出各用电器的功率.由于对于同一类用电器,其状态种类、各状态持续时长、各状态的功率波形都不同,这使得基于特征工程和聚类的模型的泛化能力不强;回归模型的分解功率难以迅速跟踪真实功率.针对这些问题,文中将回归问题转化为在序列每个时刻的多分类问题,并提出基于Attention和残差网络的非侵入式负荷监测模型.该模型基于具有编码器和解码器的seq2seq框架,首先通过嵌入矩阵将高维稀疏one-hot向量映射为低维稠密向量;在编码部分,通过双向GRU从前后两个方向提取序列信息,引入Attention机制计算序列中当前时刻最重要的信息,引入残差连接学习残差部分输入输出之间的差异;在解码部分,用回归层组合BiG-RU解码结果,取经过softmax函数处理的最大概率功率类别作为结果.该模型在选取REFIT数据集中表现良好,其中测试集与训练集完全独立,表明训练好的模型可以直接应用在新的住宅用户中. |
|---|---|
| AbstractList | TM714; 非侵入式负荷监测(non-intrusive load monitoring,NILM)可以从家庭电能表的总功率读数,估算出各用电器的功率.由于对于同一类用电器,其状态种类、各状态持续时长、各状态的功率波形都不同,这使得基于特征工程和聚类的模型的泛化能力不强;回归模型的分解功率难以迅速跟踪真实功率.针对这些问题,文中将回归问题转化为在序列每个时刻的多分类问题,并提出基于Attention和残差网络的非侵入式负荷监测模型.该模型基于具有编码器和解码器的seq2seq框架,首先通过嵌入矩阵将高维稀疏one-hot向量映射为低维稠密向量;在编码部分,通过双向GRU从前后两个方向提取序列信息,引入Attention机制计算序列中当前时刻最重要的信息,引入残差连接学习残差部分输入输出之间的差异;在解码部分,用回归层组合BiG-RU解码结果,取经过softmax函数处理的最大概率功率类别作为结果.该模型在选取REFIT数据集中表现良好,其中测试集与训练集完全独立,表明训练好的模型可以直接应用在新的住宅用户中. |
| Abstract_FL | Non-Intrusive load monitoring(NILM)is a technique to disaggregate the power consumption of the ap-pliances from the total power reading of the household electricity meter.Even for the same type of appliances,their state types,the duration of each state and the power waveform of each state are different,which requires high gen-eralization ability of the model based on feature engineering and clustering.Meanwhile,the disaggregate power of the regression model is difficult to quickly track the ground true power.To solve these problems,the regression problem is transformed into a multi-classification problem for each moment in the sequence,and a non-intrusive load monitoring model based on attention mechanism and residual networks is proposed in this paper.The proposed model is based on the seq2seq framework with encoder and decoder.Firstly,the high-dimensional sparse one-hot vector is mapped to the low-dimensional dense vector through the embedding matrix.In the encoder,BiGRU is used to extract the sequence information from the front and back directions,an attention mechanism is introduced to calculate the most important information at the current time in the sequence,and a residual connection is intro-duced to learn the difference between the input and output of the residual part.In the decoder,the regression layer is used to combine the BiGRU decoding results,and the maximum probability power category processed by a soft-max function is taken as the result.The model performs well in the REFIT dataset,and the testing dataset and training dataset are completely independent,which indicates that the trained model can be directly applied to new households. |
| Author | 季天瑶 何健明 李梦诗 张禄亮 |
| AuthorAffiliation | 华南理工大学,广州 510006 |
| AuthorAffiliation_xml | – name: 华南理工大学,广州 510006 |
| Author_FL | JI Tianyao HE Jianming ZHANG Luliang LI Mengshi |
| Author_FL_xml | – sequence: 1 fullname: HE Jianming – sequence: 2 fullname: LI Mengshi – sequence: 3 fullname: ZHANG Luliang – sequence: 4 fullname: JI Tianyao |
| Author_xml | – sequence: 1 fullname: 何健明 – sequence: 2 fullname: 李梦诗 – sequence: 3 fullname: 张禄亮 – sequence: 4 fullname: 季天瑶 |
| BookMark | eNo9j7tKA0EYRqeIYIx5C7Hb9Z_LzuyUIXiDgI3WYXackQ0yC86KpNcqXohlvKSyTWUIxMvTZLPxLYwoVge-4nycNVRxmTMIbWAIsRQR3eqEqfcOA-AAUwkhAcJC4CEQWkHV_30V1b1PE4gwFYwDqSJZDKez6W0jz43L08wV99fzUa-YjMqPfvn2WA4uv56eZ5_j4uqleL9bvA4XN5PyoT8f99bRilWn3tT_WENHO9uHzb2gdbC732y0Ao8B00CCUFYRYgUANdIqEzOMsZSSxFYzxYxKuOKR1ownWhMQ3FAhIFYUrJaG1tDmr_dCOavcSbuTnZ-55WP7WHe7yU8pLFMo_Qa7ml6Q |
| ClassificationCodes | TM714 |
| ContentType | Journal Article |
| Copyright | Copyright © Wanfang Data Co. Ltd. All Rights Reserved. |
| Copyright_xml | – notice: Copyright © Wanfang Data Co. Ltd. All Rights Reserved. |
| DBID | 2B. 4A8 92I 93N PSX TCJ |
| DOI | 10.19753/j.issn1001-1390.2024.06.023 |
| DatabaseName | Wanfang Data Journals - Hong Kong WANFANG Data Centre Wanfang Data Journals 万方数据期刊 - 香港版 China Online Journals (COJ) China Online Journals (COJ) |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| DocumentTitle_FL | Non-intrusive load monitoring algorithm based on attention and residual networks |
| EndPage | 180 |
| ExternalDocumentID | dcyyb202406023 |
| GrantInformation_xml | – fundername: (国家自然科学基金); (广州市基础与应用基础研究项目) funderid: (国家自然科学基金); (广州市基础与应用基础研究项目) |
| GroupedDBID | -03 2B. 4A8 5XA 5XD 92H 92I 93N ABJNI ACGFS ADMLS ALMA_UNASSIGNED_HOLDINGS CCEZO CEKLB CW9 GROUPED_DOAJ PSX TCJ TGT U1G U5M |
| ID | FETCH-LOGICAL-s1013-907afa22f7003e9fae8411199928fc4a4eab6a65cc46bcc2076e37708a30fc9e3 |
| ISSN | 1001-1390 |
| IngestDate | Thu May 29 03:55:45 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 6 |
| Keywords | BiGRU 注意力机制 deep learning non-intrusive load monitoring attention mechanism 深度学习 非侵入式负荷监测 residual network 残差网络 |
| Language | Chinese |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-s1013-907afa22f7003e9fae8411199928fc4a4eab6a65cc46bcc2076e37708a30fc9e3 |
| PageCount | 8 |
| ParticipantIDs | wanfang_journals_dcyyb202406023 |
| PublicationCentury | 2000 |
| PublicationDate | 2024-06-15 |
| PublicationDateYYYYMMDD | 2024-06-15 |
| PublicationDate_xml | – month: 06 year: 2024 text: 2024-06-15 day: 15 |
| PublicationDecade | 2020 |
| PublicationTitle | 电测与仪表 |
| PublicationTitle_FL | Electrical Measurement & Instrumentation |
| PublicationYear | 2024 |
| Publisher | 华南理工大学,广州 510006 |
| Publisher_xml | – name: 华南理工大学,广州 510006 |
| SSID | ssib051374602 ssj0039791 ssib001129792 |
| Score | 2.3570535 |
| Snippet | TM714; 非侵入式负荷监测(non-intrusive load... |
| SourceID | wanfang |
| SourceType | Aggregation Database |
| StartPage | 173 |
| Title | 基于Attention和残差网络的非侵入式负荷监测 |
| URI | https://d.wanfangdata.com.cn/periodical/dcyyb202406023 |
| Volume | 61 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnR27btRAcJWHhEiBeIpnSJGp0AU_1vsoKNZ3PkWI0JBI6aK1Y0N1SORSJHWowkOh5JWKNhVRpPD4mlwu_AUza9-dEYhXY409szOzO_bOeHd2l7FZ6fnKruaikeJPcoOHomigG87wNgpSa4PCWhqHXLgv5pf43eVoeWz8Ti1rab2bzmWbv1xX8j9WxWdoV1ol-w-WHTLFBwijffGKFsbrX9kYkgh0G2IDCaerSky3W-YvOlQAqgmJAJOAiulJLAlOJMQt0L4DYtBNAjQW55Bo0IhKHMME4ohKqQiMA-ImqDYkCmJOchFQLeJJxWPHUFARFddDXofljlWFdcyxbCklBmOIlfHBDPNqHQYVKeX7Tr4ATYVGJIJ0JS5YwwCMcFzaoOWIxOlsPNIB8VRB11AmqZOYFpjQARyMdvr6EIv6gEjAKXGrXBLqXmGnVyndAbpsBQ-UGDR0NGApB0IEvtAOqyFuV2Q6uRXR7IeouQdKQMOY2av7j3Iz-eo7qTsDvzykpYor_PLEqp9cFq1sdj6LJAwFzFHN3M6yQThy1cMEytVsYyMlEk8gwTibDKSkLIVJ01q492AUD2M0J0fT5pEfSi684f5qNKfrRiQGUk-x2YFKt3-jkFvg1ils52EtFls8y85UP1EzpvwizrGxzUfn2VRta80LTPd2D48OXwy_h96rZ8d7272Dvf6Xnf6nt_3XW9_evT_6ut97-qH3-eXJx92T5wf9NzvH-9sX2VI7WWzON6pjQhprPp1Noj1pCxsEhcQa5bqwueLowfHPJ1BFxi3PbSqsiLKMizTLAuyU8lBKT9nQKzKdh5fYROdxJ7_MZmxuw8L3ck8VAS94aDH4TXNJB7zJFPuxK-xmVfGVqhtYW_nRFFf_SHGNnR69tdfZRPfJen4DA9tuOl2Zb9oNDH0HYkp89A |
| linkProvider | EBSCOhost |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=%E5%9F%BA%E4%BA%8EAttention%E5%92%8C%E6%AE%8B%E5%B7%AE%E7%BD%91%E7%BB%9C%E7%9A%84%E9%9D%9E%E4%BE%B5%E5%85%A5%E5%BC%8F%E8%B4%9F%E8%8D%B7%E7%9B%91%E6%B5%8B&rft.jtitle=%E7%94%B5%E6%B5%8B%E4%B8%8E%E4%BB%AA%E8%A1%A8&rft.au=%E4%BD%95%E5%81%A5%E6%98%8E&rft.au=%E6%9D%8E%E6%A2%A6%E8%AF%97&rft.au=%E5%BC%A0%E7%A6%84%E4%BA%AE&rft.au=%E5%AD%A3%E5%A4%A9%E7%91%B6&rft.date=2024-06-15&rft.pub=%E5%8D%8E%E5%8D%97%E7%90%86%E5%B7%A5%E5%A4%A7%E5%AD%A6%2C%E5%B9%BF%E5%B7%9E+510006&rft.issn=1001-1390&rft.volume=61&rft.issue=6&rft.spage=173&rft.epage=180&rft_id=info:doi/10.19753%2Fj.issn1001-1390.2024.06.023&rft.externalDocID=dcyyb202406023 |
| thumbnail_s | http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=http%3A%2F%2Fwww.wanfangdata.com.cn%2Fimages%2FPeriodicalImages%2Fdcyyb%2Fdcyyb.jpg |