

浏览全部资源
扫码关注微信
1.河海大学人工智能与自动化学院,江苏省南京市 210098
2.南京工程学院应用技术学院,江苏省南京市211100
Received:29 November 2024,
Revised:2025-03-29,
Published Online:05 June 2025,
Published:10 August 2025
移动端阅览
李加文,孙永辉,王森等.计及异常场景数据缺失的负荷超短期预测[J].电力系统自动化,2025,49(15):133-143.
LI Jiawen,SUN Yonghui,WANG Sen,et al.Ultra-short-term Load Forecasting Considering Missing Data in Anomalous Scenarios[J].Automation of Electric Power Systems,2025,49(15):133-143.
李加文,孙永辉,王森等.计及异常场景数据缺失的负荷超短期预测[J].电力系统自动化,2025,49(15):133-143. DOI: 10.7500/AEPS20241129006.
LI Jiawen,SUN Yonghui,WANG Sen,et al.Ultra-short-term Load Forecasting Considering Missing Data in Anomalous Scenarios[J].Automation of Electric Power Systems,2025,49(15):133-143. DOI: 10.7500/AEPS20241129006.
受能源转型和极端天气频发等因素影响,包含特殊模式的异常场景对电力系统的稳定性影响日益严重。为此,文中提出一种计及异常场景数据缺失的负荷超短期预测方法。该方法首先通过基于局部差异和全局差异的多尺度框架提取异常场景,根据异常场景日期信息引入缺失值,并使用二元掩码矩阵控制缺失率,仿真异常场景数据缺失;然后,结合时序相关性,通过改进后的截断反距离权重(CIDW)插补方法自动识别缺失数据进行插补;最后,针对插补后数据,构建基于时域卷积网络(TCN)与标量长短期记忆(sLSTM)网络的模型进行特征提取和预测,并设置数据随机缺失场景下不同缺失率来验证模型泛化能力。通过不同场景和不同模型对比分析,验证了所提模型部分指标相较于对比模型均有所提升。
Due to the influence by factors such as energy transition and frequent occurrence of extreme weather events
the impact of anomalous scenarios with special patterns on power system stability has become increasingly severe. To this end
this paper proposes an ultra-short-term load forecasting method considering the missing data in anomalous scenarios. Firstly
this method is applied to extract anomalous scenarios using a multi-scale extraction framework based on local and global differences
introduce missing values based on the date information of anomalous scenarios
control the missing rate using a binary mask matrix
and make simulation where data in anomalous scenarios are missing. Secondly
combining temporal correlation
the improved cutoff inverse distance weighting (CIDW) imputation method is used to automatically identify the missing data for imputation. Finally
a model based on temporal convolutional network (TCN) and scalar long short-term memory (sLSTM) network is constructed to perform feature extraction and forecasting for the imputed data
and the model generalization ability is verified under different missing rates in scenarios with random missing data. Through comparative analysis of different scenarios and models
it is verified that some indicators of the proposed model are all improved compared to the comparative model.
刘文霞 , 刘佳怡 , 万海洋 , 等 . 面向多类型极端天气的新型电力系统规划方案全场景风险评估 [J]. 电力系统自动化 , 2025 , 49 ( 4 ): 65 - 78 .
LIU Wenxia , LIU Jiayi , WAN Haiyang , et al . Full-scenario risk assessment of new power system planning scheme for multiple types of extreme weather [J]. Automation of Electric Power Systems , 2025 , 49 ( 4 ): 65 - 78 .
XU J , WANG B , SUN Y Z , et al . A day-ahead economic dispatch method considering extreme scenarios based on wind power uncertainty [J]. CSEE Journal of Power and Energy Systems , 2019 , 5 ( 2 ): 224 - 233 .
邢晓萱 , 巩敦卫 , 孙晓燕 , 等 . 基于重构误差和极端模式识别的综合能源系统短期负荷预测 [J]. 中国电机工程学报 , 2024 , 44 ( 9 ): 3476 - 3489 .
XING Xiaoxuan , GONG Dunwei , SUN Xiaoyan , et al . Short-term load forecasting of integrated energy system based on reconstruction error and extreme patterns recognition [J]. Proceedings of the CSEE , 2024 , 44 ( 9 ): 3476 - 3489 .
YANG S C , WANG X , ZHOU S D , et al . Multi-scenario failure diagnosis for lithium-ion battery based on coupling PSO-SA-DBSCAN algorithm [J]. Journal of Energy Storage , 2024 , 99 : 113393 .
DU N C , TANG F , LIAO Q F , et al . Hosting capacity assessment in distribution networks considering wind-photovoltaic-load temporal characteristics [J]. Frontiers in Energy Research , 2021 , 9 : 767610 .
ZATTI M , GABBA M , FRESCHINI M , et al . K-MILP: a novel clustering approach to select typical and extreme days for multi-energy systems design optimization [J]. Energy , 2019 , 181 : 1051 - 1063 .
ZHU X , YU Z C , LIU X . Security constrained unit commitment with extreme wind scenarios [J]. Journal of Modern Power Systems and Clean Energy , 2020 , 8 ( 3 ): 464 - 472 .
许彦平 , 白婕 , 施浩波 , 等 . 基于凸包算法的极端运行方式提取方法 [J]. 中国电力 , 2024 , 57 ( 7 ): 30 - 39 .
XU Yanping , BAI Jie , SHI Haobo , et al . Extreme operation mode extraction method based on convex hull algorithm [J]. Electric Power , 2024 , 57 ( 7 ): 30 - 39 .
SCOTT I J , CARVALHO P M S , BOTTERUD A , et al . Clustering representative days for power systems generation expansion planning: Capturing the effects of variable renewables and energy storage [J]. Applied Energy , 2019 , 253 : 113603 .
李滨 , 黄佳 , 吴茵 , 等 . 基于分形特性修正气象相似日的节假日短期负荷预测方法 [J]. 电网技术 , 2017 , 41 ( 6 ): 1949 - 1955 .
LI Bin , HUANG Jia , WU Yin , et al . Holiday short-term load forecasting based on fractal characteristic modified meteorological similar day [J]. Power System Technology , 2017 , 41 ( 6 ): 1949 - 1955 .
MIAO X Y , WU Y Y , CHEN L , et al . An experimental survey of missing data imputation algorithms [J]. IEEE Transactions on Knowledge and Data Engineering , 2023 , 35 ( 7 ): 6630 - 6650 .
KONG X J , ZHOU W F , SHEN G J , et al . Dynamic graph convolutional recurrent imputation network for spatiotemporal traffic missing data [J]. Knowledge-Based Systems , 2023 , 261 : 110188 .
TWALA B , CARTWRIGHT M , SHEPPERD M . Comparison of various methods for handling incomplete data in software engineering databases [C]// 2005 International Symposium on Empirical Software Engineering , November 17-18 , 2005 , Noosa Heads, Australia : 10p .
ROYSTON P , WHITE I . Multiple imputation by chained equations (MICE): implementation in Stata [J]. Journal of Statistical Software , 2011 , 45 ( 4 ): 1 - 20 .
REN L J , SEKLOULI A S , ZHANG H Q , et al . An adaptive Laplacian weight random forest imputation for imbalance and mixed-type data [J]. Information Systems , 2023 , 111 : 102122 .
YOON J , JORDON J , VAN DER SCHAAR M . GAIN: missing data imputation using generative adversarial nets [EB/OL]. [ 2024-08-30 ]. https://arxiv.org/abs/1806.02920v1 https://arxiv.org/abs/1806.02920v1 .
朱凌建 , 荀子涵 , 王裕鑫 , 等 . 基于CNN-Bi LSTM的短期电力负荷预测 [J]. 电网技术 , 2021 , 45 ( 11 ): 4532 - 4539 .
ZHU Lingjian , XUN Zihan , WANG Yuxin , et al . Short-term power load forecasting based on CNN-BiLSTM [J]. Power System Technology , 2021 , 45 ( 11 ): 4532 - 4539 .
张哲 , 秦博宇 , 高鑫 , 等 . 基于CNN-LSTM网络的电网电压稳定紧急控制策略 [J]. 电力系统自动化 , 2023 , 47 ( 11 ): 60 - 68 .
ZHANG Zhe , QIN Boyu , GAO Xin , et al . Emergency control strategy of power grid voltage stability based on convolutional neural network and long short-term memory network [J]. Automation of Electric Power Systems , 2023 , 47 ( 11 ): 60 - 68 .
SHAKEEL A , CHONG D T , WANG J S . District heating load forecasting with a hybrid model based on LightGBM and FB-prophet [J]. Journal of Cleaner Production , 2023 , 409 : 137130 .
DENG X Z , YE A S , ZHONG J S , et al . Bagging-XGBoost algorithm based extreme weather identification and short-term load forecasting model [J]. Energy Reports , 2022 , 8 : 8661 - 8674 .
WANG S , ZHANG W J , SUN Y H , et al . Wind power forecasting in the presence of data scarcity: a very short-term conditional probabilistic modeling framework [J]. Energy , 2024 , 291 : 130305 .
张延宇 , 张智铭 , 刘春阳 , 等 . 基于动态自适应图神经网络的电动汽车充电负荷预测 [J]. 电力系统自动化 , 2024 , 48 ( 7 ): 86 - 93 .
ZHANG Yanyu , ZHANG Zhiming , LIU Chunyang , et al . Electric vehicle charging load prediction based on dynamic adaptive graph neural network [J]. Automation of Electric Power Systems , 2024 , 48 ( 7 ): 86 - 93 .
SUN Y H , ZHOU Y , WANG S , et al . Nonparametric probabilistic prediction of regional PV outputs based on Granule-based clustering and direct optimization programming [J]. Journal of Modern Power Systems and Clean Energy , 2023 , 11 ( 5 ): 1450 - 1461 .
袁畅 , 王森 , 孙永辉 , 等 . 基于混合特征双重衍生和误差修正的风电功率超短期预测 [J]. 电力系统自动化 , 2024 , 48 ( 5 ): 68 - 76 .
YUAN Chang , WANG Sen , SUN Yonghui , et al . Ultra-short-term forecasting of wind power based on dual derivation of hybrid features and error correction [J]. Automation of Electric Power Systems , 2024 , 48 ( 5 ): 68 - 76 .
ZHANG L J , JÁNOŠÍK D . Enhanced short-term load forecasting with hybrid machine learning models: CatBoost and XGBoost approaches [J]. Expert Systems with Applications , 2024 , 241 : 122686 .
胡俊杰 , 赖信辉 , 郭伟 , 等 . 考虑电动汽车灵活性与风电消纳的区域电网多时间尺度调度 [J]. 电力系统自动化 , 2022 , 46 ( 16 ): 52 - 60 .
HU Junjie , LAI Xinhui , GUO Wei , et al . Multi-time-scale scheduling for regional power grid considering flexibility of electric vehicle and wind power accommodation [J]. Automation of Electric Power Systems , 2022 , 46 ( 16 ): 52 - 60 .
MORAIS L B S , AQUILA G , DE FARIA V A D , et al . Short-term load forecasting using neural networks and global climate models: an application to a large-scale electrical power system [J]. Applied Energy , 2023 , 348 : 121439 .
BECK M , PÖPPEL K , SPANRING M , et al . xLSTM: extended long short-term memory [EB/OL]. [ 2024-08-30 ]. https://arxiv.org/abs/2405.04517v2 https://arxiv.org/abs/2405.04517v2 .
GRANELL R , AXON C J , WALLOM D C H . Impacts of raw data temporal resolution using selected clustering methods on residential electricity load profiles [J]. IEEE Transactions on Power Systems , 2015 , 30 ( 6 ): 3217 - 3224 .
YILMAZ S , CHAMBERS J , PATEL M K . Comparison of clustering approaches for domestic electricity load profile characterisation—implications for demand side management [J]. Energy , 2019 , 180 : 665 - 677 .
刘志坚 , 陶韵旭 , 刘航 , 等 . 基于双通道生成对抗网络的城市用电负荷缺失数据补全方法 [J]. 电力系统自动化 , 2024 , 48 ( 17 ): 161 - 170 .
LIU Zhijian , TAO Yunxu , LIU Hang , et al . Completion method for missing urban power load data based on double-channel generative adversarial networks [J]. Automation of Electric Power Systems , 2024 , 48 ( 17 ): 161 - 170 .
PARK K , JEONG J , KIM D , et al . Missing-insensitive short-term load forecasting leveraging autoencoder and LSTM [J]. IEEE Access , 2020 , 8 : 206039 - 206048 .
AZEEM A , ISMAIL I , MOHANI S S , et al . Mitigating concept drift challenges in evolving smart grids: an adaptive ensemble LSTM for enhanced load forecasting [J]. Energy Reports , 2025 , 13 : 1369 - 1383 .
RAN P , DONG K , LIU X , et al . Short-term load forecasting based on CEEMDAN and transformer [J]. Electric Power Systems Research , 2023 , 214 : 108885 .
0
Views
0
下载量
0
CSCD
Publicity Resources
Related Articles
Related Author
Related Institution
京公网安备11010802024621