

浏览全部资源
扫码关注微信
1.杭州电子科技大学自动化学院,浙江省杭州市 310018
2.杭州电子科技大学圣光机联合学院,浙江省杭州市 310018
3.杭州电子科技大学信息工程学院,浙江省杭州市 310018
Received:17 March 2023,
Revised:2023-08-20,
Published Online:26 October 2023,
Published:25 January 2024
移动端阅览
罗平,朱振宇,樊星驰等.基于时序生成对抗网络的居民用户非侵入式负荷分解[J].电力系统自动化,2024,48(2):71-81.
LUO Ping,ZHU Zhenyu,FAN Xingchi,et al.Non-intrusive Load Decomposition for Residential Users Based on Time-series Generative Adversarial Network[J].Automation of Electric Power Systems,2024,48(2):71-81.
罗平,朱振宇,樊星驰等.基于时序生成对抗网络的居民用户非侵入式负荷分解[J].电力系统自动化,2024,48(2):71-81. DOI: 10.7500/AEPS20230317003.
LUO Ping,ZHU Zhenyu,FAN Xingchi,et al.Non-intrusive Load Decomposition for Residential Users Based on Time-series Generative Adversarial Network[J].Automation of Electric Power Systems,2024,48(2):71-81. DOI: 10.7500/AEPS20230317003.
现有的非侵入式负荷分解算法往往需要大量电器设备级的负荷数据才能保证分解精度,但由于用户对隐私性的考虑以及安装成本过高等问题
很难获取这些数据。因此,构建一种能深度挖掘电力负荷数据时序特性和电器相关性的时序生成对抗网络。利用降维网络对所有电器有功功率序列组成的高维向量进行降维以降低计算的复杂度,通过复原网络将结果还原为高维向量。基于电器运行状态和深度学习的非侵入式分解方法,运用卷积神经网络-双向门控循环单元构建状态复杂电器的负荷分解回归模型,对状态简单电器利用深度神经网络构建负荷识别分类模型。通过对比其他数据生成方法,以及改变典型公开数据集中生成数据比例所得的负荷分解结果验证了所提方法的有效性。
The existing non-intrusive load decomposition algorithms often require a large number of electrical load data at equipment level to ensure the decomposition accuracy
but it is difficult to obtain these data due to the user's consideration of privacy and high installation cost. Therefore
a time-series generative adversarial network which can deeply explore the time-series characteristics of power load data and the correlation of electrical appliances is constructed. The dimensionality reduction network is used to reduce the dimensionality of the high-dimensional vector composed of the active power sequence of all electrical appliances to reduce the computational complexity
and the result is restored to the high-dimensional vector through the restoration network. Based on the non-intrusive decomposition method of electrical appliance operation status and deep learning
the load decomposition regression model of complex-state electrical appliances is built by using the convolutional neural network-bidirectional gated recurrent unit
and the load identification and classification model of simple-state electrical appliances is constructed by using the deep neural network. The effectiveness of the proposed method is verified by comparing other data generation methods and the load decomposition results obtained by changing the proportion of the generated data in typical public datasets.
国家能源局 . 2022年全社会用电量同比增长3.6% [J]. 电力勘测设计 , 2023 ( 1 ): 48 .
National Energy Administration . In 2022, the electricity consumption of the whole society increased by 3.6% year on year [J]. Electric Power Survey & Design , 2023 ( 1 ): 48 .
KORNATKA M , POPŁAWSKI T . Advanced metering infrastructure—towards a reliable network [J]. Energies , 2021 , 14 ( 18 ): 5986 .
DASH S , SAHOO N C . Electric energy disaggregation via non-intrusive load monitoring: a state-of-the-art systematic review [J]. Electric Power Systems Research , 2022 , 213 : 108673 .
燕续峰 , 翟少鹏 , 王治华 , 等 . 深度神经网络在非侵入式负荷分解中的应用 [J]. 电力系统自动化 , 2019 , 43 ( 1 ): 126 - 132 .
YAN Xufeng , ZHAI Shaopeng , WANG Zhihua , et al . Application of deep neural network in non-intrusive load disaggregation [J]. Automation of Electric Power Systems , 2019 , 43 ( 1 ): 126 - 132 .
QUY T L , ZERR S , NTOUTSI E , et al . Data augmentation for dealing with low sampling rates in NILM [EB/OL]. [ 2023-01-28 ]. https://ui.adsabs.harvard.edu/abs/2021arXiv210402055L https://ui.adsabs.harvard.edu/abs/2021arXiv210402055L .
WU H P , LIU H . Non-intrusive load transient identification based on multivariate LSTM neural network and time series data augmentation [J]. Sustainable Energy, Grids and Networks , 2021 , 27 : 100490 .
LIM S K , LOO Y , TRAN N T , et al . DOPING: generative data augmentation for unsupervised anomaly detection with GAN [C]// IEEE International Conference on Data Mining (ICDM) , November 17-20 , 2018 , Singapore : 1122 - 1127 .
HARELL A , JONES R , MAKONIN S , et al . TraceGAN: synthesizing appliance power signatures using generative adversarial networks [J]. IEEE Transactions on Smart Grid , 2021 , 12 ( 5 ): 4553 - 4563 .
LI J B , CHEN Z Q , CHENG L , et al . Energy data generation with Wasserstein deep convolutional generative adversarial networks [J]. Energy , 2022 , 257 : 124694 .
DONNAL J . NILM-synth: synthetic dataset generation for non-intrusive load monitoring algorithms [C]// IEEE Power & Energy Society Innovative Smart Grid Technologies Conference (ISGT) , April 24-28 , 2022 , New Orleans, USA .
杨建平 , 向月 , 刘俊勇 . 面向配电网投资决策的小样本关联规则自适应迁移学习方法 [J]. 中国电机工程学报 , 2022 , 42 ( 16 ): 5823 - 5834 .
YANG Jianping , XIANG Yue , LIU Junyong . Adaptive transfer learning of small sample correlation rules for distribution network investment decision [J]. Proceedings of the CSEE , 2022 , 42 ( 16 ): 5823 - 5834 .
鲍光海 , 黄逸欣 . 基于ResNeXt网络和迁移学习的非侵入式负荷监测 [J]. 电力系统自动化 , 2023 , 47 ( 13 ): 110 - 120 .
BAO Guanghai , HUANG Yixin . Non-intrusive load monitoring based on ResNeXt network and transfer learning [J]. Automation of Electric Power Systems , 2023 , 47 ( 13 ): 110 - 120 .
刘航 , 刘春阳 , 赵浩然 , 等 . 基于深度学习的公共楼宇电-气负荷非侵入式分解 [J]. 电网技术 , 2023 , 47 ( 3 ): 1188 - 1197 .
LIU Hang , LIU Chunyang , ZHAO Haoran , et al . Non-invasive decomposition of electric-gas load in public buildings based on deep learning [J]. Power System Technology , 2023 , 47 ( 3 ): 1188 - 1197 .
武昕 , 于金莹 , 彭林 , 等 . 基于用户边缘侧事件解析的工业电力负荷非侵入式感知辨识 [J]. 电力系统自动化 , 2021 , 45 ( 4 ): 29 - 37 .
WU Xin , YU Jinying , PENG Lin , et al . Non-intrusive perception and identification of industrial power load based on analysis of event on user edge [J]. Automation of Electric Power Systems , 2021 , 45 ( 4 ): 29 - 37 .
鲍海波 , 杨舒惠 , 陈子民 , 等 . 事件检测类非侵入式负荷监测算法综述 [J]. 电力系统自动化 , 2023 , 47 ( 13 ): 94 - 109 .
BAO Haibo , YANG Shuhui , CHEN Zimin , et al . Review on event-inspection based non-intrusive load monitoring algorithms [J]. Automation of Electric Power Systems , 2023 , 47 ( 13 ): 94 - 109 .
REHMAN A U , LIE T T , VALLÈS B , et al . Event-detection algorithms for low sampling nonintrusive load monitoring systems based on low complexity statistical features [J]. IEEE Transactions on Instrumentation and Measurement , 2020 , 69 ( 3 ): 751 - 759 .
LUAN W P , LIU Z S , LIU B , et al . An adaptive two-stage load event detection method for nonintrusive load monitoring [J]. IEEE Transactions on Instrumentation and Measurement , 2022 , 71 : 1 - 14 .
YAN L , TIAN W , WANG H , et al . Robust event detection for residential load disaggregation [J]. Applied Energy , 2023 , 331 : 120339 .
邓晓平 , 张桂青 , 魏庆来 , 等 . 非侵入式负荷监测综述 [J]. 自动化学报 , 2022 , 48 ( 3 ): 644 - 663 .
DENG Xiaoping , ZHANG Guiqing , WEI Qinglai , et al . A survey on the non-intrusive load monitoring [J]. Acta Automatica Sinica , 2022 , 48 ( 3 ): 644 - 663 .
魏广芬 , 赵航 , 胡春华 , 等 . 基于香农熵加权投票算法的集成式非侵入式负荷识别方法 [J]. 中国电机工程学报 , 2022 , 42 ( 24 ): 8876 - 8888 .
WEI Guangfen , ZHAO Hang , HU Chunhua , et al . An ensemble non-intrusive load identification method based on Shannon entropy weighted voting algorithm [J]. Proceedings of the CSEE , 2022 , 42 ( 24 ): 8876 - 8888 .
WU Z , WANG C , PENG W X , et al . Non-intrusive load monitoring using factorial hidden Markov model based on adaptive density peak clustering [J]. Energy and Buildings , 2021 , 244 : 111025 .
冯人海 , 袁万琦 , 葛磊蛟 . 基于图信号交替优化的居民用户非侵入式负荷监测方法 [J]. 中国电机工程学报 , 2022 , 42 ( 4 ): 1355 - 1365 .
FENG Renhai , YUAN Wanqi , GE Leijiao . Non-intrusive load monitoring method for resident users based on alternating optimization in graph signal [J]. Proceedings of the CSEE , 2022 , 42 ( 4 ): 1355 - 1365 .
JINSUNG Y , DANIEL J . Time-series generative adversarial nets [C]// Neural Information Processing Systems , December 8 , 2019, Vancouver , Canada : 5508 - 5518 .
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 .
马愿谦 , 李启源 , 陈汉忠 , 等 . 基于BLAP聚类和多粒度犹豫模糊集的售电套餐推荐方法 [J]. 电力系统自动化 , 2023 , 47 ( 1 ): 96 - 104 .
MA Yuanqian , LI Qiyuan , CHEN Hanzhong , et al . Recommendation method of electricity sales package based on BLAP clustering and multi-granularity hesitation fuzzy set [J]. Automation of Electric Power Systems , 2023 , 47 ( 1 ): 96 - 104 .
任智仁 , 汤博 , 周弼 , 等 . 基于CNN-BiGRU-Attention的非侵入式负荷分解 [J]. 电机与控制应用 , 2022 , 49 ( 8 ): 41 - 46 .
REN Zhiren , TANG Bo , ZHOU Bi , et al . Non-invasive load decomposition based on CNN-BiGRU-Attention [J]. Electric Machines & Control Application , 2022 , 49 ( 8 ): 41 - 46 .
ROCHEFORT-BEAUDOIN T , VADEAN A , GAMACHE J F , et al . Supervised deep learning for the moving morphable components topology optimization framework [J]. Engineering Applications of Artificial Intelligence , 2023 , 123 : 106436 .
KONG W C , DONG Z Y , MA J , et al . An extensible approach for non-intrusive load disaggregation with smart meter data [J]. IEEE Transactions on Smart Grid , 2018 , 9 ( 4 ): 3362 - 3372 .
魏书荣 , 闫梦飞 , 任子旭 , 等 . 考虑运行环境影响的海上双馈风电机组状态判别 [J]. 电力系统自动化 , 2022 , 46 ( 20 ): 181 - 189 .
WEI Shurong , YAN Mengfei , REN Zixu , et al . Condition discrimination of offshore doubly-fed wind turbine considering the influence of operating environment [J]. Automation of Electric Power Systems , 2022 , 46 ( 20 ): 181 - 189 .
KELLY J , KNOTTENBELT W . Neural NILM: deep neural networks applied to energy disaggregation [C]// ACM International Conference on Embedded Systems for Energy Efficient Built Environments , November 4-5 , 2015 , Seoul, South Korea : 55 - 64 .
0
Views
0
下载量
0
CSCD
Publicity Resources
Related Articles
Related Author
Related Institution
京公网安备11010802024621