区域尺度住宅建筑日用电负荷模型构建方法研究

doi:10.11930/j.issn.1004-9649.202002019

摘要/Abstract

摘要： 面对新时代能源发展形势，有效整合电力用户、电网企业及供应商信息，全面深度分析“源网荷储”特性是推进能源互联网发展的重要举措，模拟建筑用电这一典型负荷已尤为重要。关注区域规模居民用电负荷，提出用电负荷数据预处理分析方法和区域尺度住宅建筑日用电负荷模拟方法。区域尺度的用电数据在空间规模和时间跨度上均具有高维特征，分析大量数据并再现区域规模用电负荷是其主要难点。为此，提出结合自编码和k近邻算法的数据异常值剔除方法。在数据预处理的基础上，提出基于聚类分析的区域尺度住宅日用电负荷模型和模型检验方法，以单个住户的日均用电和全年最大日负荷为指标聚类，基于聚类分析结果提出随机用电模型，模拟区域尺度住宅建筑逐户逐日用电负荷。应用华东某重点城市智能电表采集的整年居民用电数据开展研究分析案例，实现区域住宅建筑居民日用电负荷的模拟再现。提出“数据异常值预处理、聚类分析、模型构建和检验”系列研究分析方法，可有效满足能源互联网建设对大量末端用户用电负荷的模拟分析需求。

关键词: 能源互联网, 住宅建筑, 日用电负荷, 自编码, 聚类, 随机用电模型

Abstract: Faced with the energy development situation in the new epoch, it is key measures for promoting the development of power energy Internet to effectively integrate the information of power users, grid companies and suppliers, and to comprehensively analyze the source network load and storage characteristics. Therefore, it is crucial to simulate the typical electricity load in buildings. This study focuses on the electricity consumption of different households in district scale and proposes a preprocessing method of electricity load of district-scale users, and a residential daily electricity load simulation method. The electricity consumption data of urban scale has high-dimensional characteristics in both spatial scale and temporal span. Characterizing the district-scale electricity consumption is the principal difficulty. To this end, this study proposes a method integrating auto-encoding and neighbor clustering algorithms for data outlier detection for data with high-dimensional characteristics at the spatial and temporal scales. Based on the results of preprocessing, the study proposes a district-scale residential electricity load simulation model based on clustering analysis, and the evaluation method. Clustering analysis was performed on the average daily electricity consumption and the daily maximum load of the whole year of single household. Based on the clustering analysis, a random electricity model is proposed to simulate the daily electricity consumption of residential buildings on the district scale. In this study, part of the household in one key city in East China is used as a case study to demonstrate the proposed method. The raw data comes from the daily electricity consumption measurement of multi-family smart meters, lasting for one year. To conclude, this study builds a complete research method of data outlier preprocessing, clustering analysis, model construction and model verification, it can effectively solve the needs of power energy Internet construction for the end use energy consumption analysis of a large amount.

Key words: energy internet, residential building, daily electricity load, auto-encoder, clustering, stochastic electricity use model

徐杰彦, 许雯旸, 褚渊, 晋远, 康旭源, 陈征. 区域尺度住宅建筑日用电负荷模型构建方法研究[J]. 中国电力, 2020, 53(8): 29-39.

XU Jieyan, XU Wenyang, CHU Yuan, JIN Yuan, KANG Xuyuan, CHEN Zheng. Residential Electricity Load Model Construction in District Scale[J]. Electric Power, 2020, 53(8): 29-39.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202002019

https://www.electricpower.com.cn/CN/Y2020/V53/I8/29

参考文献

[1] 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.
[2] PONOĆKO J, MILANOVIĆ J V. Application of data analytics for advanced demand profiling of residential load using smart meter data[C]//2017 IEEE Manchester PowerTech. Manchester, UK: IEEE, 2017: 1-6.
[3] WEN L L, ZHOU K L, YANG S L. A shape-based clustering method for pattern recognition of residential electricity consumption[J]. Journal of Cleaner Production, 2019, 212: 475-488.
[4] ZHOU K L, YANG S L, SHAO Z. Household monthly electricity consumption pattern mining: a fuzzy clustering-based model and a case study[J]. Journal of Cleaner Production, 2017, 141: 900-908.
[5] 赵莉, 候兴哲, 胡君, 等. 基于改进k-means算法的海量智能用电数据分析[J]. 电网技术, 2014, 38(10): 2715-2720
ZHAO Li, HOU Xingzhe, HU Jun, et al. Improved k-means algorithm based analysis on massive data of intelligent power utilization[J]. Power System Technology, 2014, 38(10): 2715-2720
[6] 朱文俊, 王毅, 罗敏, 等. 面向海量用户用电特性感知的分布式聚类算法[J]. 电力系统自动化, 2016, 40(12): 21-27
ZHU Wenjun, WANG Yi, LUO Min, et al. Distributed clustering algorithm for awareness of electricity consumption characteristics of massive consumers[J]. Automation of Electric Power Systems, 2016, 40(12): 21-27
[7] 康旭源, 燕达, 孙红三, 等. 居住建筑用电数据分析与随机模型构建[J]. 建筑科学, 2019, 35(12): 1-11
KANG Xuyuan, YAN Da, SUN Hongsan, et al. Analysis and stochastic modelling of electricity consumption in urban residential buildings[J]. Building Science, 2019, 35(12): 1-11
[8] ZHAO Q, LI H, WANG X, et al. Analysis of users’ electricity consumption behavior based on ensemble clustering[J]. Global Energy Interconnection, 2019, 2(6): 480-489.
[9] VALOR E, MENEU V, CASELLES V. Daily air temperature and electricity load in Spain[J]. Journal of Applied Meteorology, 2001, 40(8): 1413-1421.
[10] BECCALI M, CELLURA M, LO BRANO V, et al. Forecasting daily urban electric load profiles using artificial neural networks[J]. Energy Conversion and Management, 2004, 45(18/19): 2879-2900.
[11] LÓPEZ J M G, POURESMAEIL E, CAÑIZARES C A, et al. Smart residential load simulator for energy management in smart grids[J]. IEEE Transactions on Industrial Electronics, 2019, 66(2): 1443-1452.
[12] LI R R, JIANG P, YANG H F, et al. A novel hybrid forecasting scheme for electricity demand time series[J]. Sustainable Cities and Society, 2020, 55: 102036.
[13] JIANG P, LI R R, LIU N N, et al. A novel composite electricity demand forecasting framework by data processing and optimized support vector machine[J]. Applied Energy, 2020, 260: 114243.
[14] MASOUMI A, JABARI F, GHASSEM ZADEH S, et al. Long-term load forecasting approach using dynamic feed-forward back-propagation artificial neural network[M]//Studies in Systems, Decision and Control. Cham: Springer International Publishing, 2020: 233-257.
[15] BAETENS R, SAELENS D. Modelling uncertainty in district energy simulations by stochastic residential occupant behaviour[J]. Journal of Building Performance Simulation, 2016, 9(4): 431-447.
[16] 陈智锴. 基于系统动力学的工业园区电力需求分析与预测[D]. 北京: 北京交通大学, 2019.
CHEN Zhikai. Analysis of power demand for industrial park based on system dynamics and its forecast[D]. Beijing: Beijing Jiaotong University, 2019.
[17] 李琛, 郭文利, 吴进, 等. 基于BP神经网络的北京夏季日最大电力负荷预测方法[J]. 气候与环境研究, 2019, 24(1): 135-142
LI Chen, GUO Wenli, WU Jin, et al. A method for prediction of daily maximum electric loads in the summer in Beijing based on the BP neural network[J]. Climatic and Environmental Research, 2019, 24(1): 135-142
[18] 闫重熙, 陈皓. 基于改进天牛须搜索算法优化LSSVM短期电力负荷预测方法研究[J]. 电测与仪表, 2020, 57(6): 6-11, 18
YAN Chongxi, CHEN Hao. Research of LSSVM short-term load forecasting method based on the improved beetle antennae search algorithm[J]. Electrical Measurement & Instrumentation, 2020, 57(6): 6-11, 18
[19] 罗澍忻, 陆秋瑜, 靳冰洁, 等. 考虑相关因素的长短时记忆网络短期负荷预测方法[J]. 机电工程技术, 2019, 48(12): 126-129
LUO Shuxin, LU Qiuyu, JIN Bingjie, et al. Short-term load forecasting based on long short-term memory network considering related factors[J]. Mechanical & Electrical Engineering Technology, 2019, 48(12): 126-129
[20] 陈振宇, 刘金波, 李晨, 等. 基于LSTM与XGBoost组合模型的超短期电力负荷预测[J]. 电网技术, 2020, 44(2): 614-620
CHEN Zhenyu, LIU Jinbo, LI Chen, et al. Ultra short-term power load forecasting based on combined LSTM-XGBoost model[J]. Power System Technology, 2020, 44(2): 614-620
[21] 黄一楠. 探讨支持向量机在电力负荷预测中的运用[J]. 科技风, 2017(20): 145
[22] SINGH M, GUPTA S. Application of neural networks to power systems for electrical load forecasting[J]. CSVTU Research Journal on Engineering and Technology, 2020, 8(2): 152-159.
[23] TAN Y, CHEN H, LIU W, et al. Repulsive firefly algorithm-based optimal switching device placement in power distribution systems[J]. Global Energy Interconnection, 2019, 2(6): 490-496.
[24] LIU H W, LI X L, LI J Y, et al. Efficient outlier detection for high-dimensional data[J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2018, 48(12): 2451-2461.
[25] LI C D, DING Z X, ZHAO D B, et al. Building energy consumption prediction: an extreme deep learning approach[J]. Energies, 2017, 10(10): 1525.
[26] RUMMELHART D E. Parallel Distributed Processing[M]. US: MIT Press, 1986: 318-62.
[27] COVER T, HART P. Nearest neighbor pattern classification[J]. IEEE Transactions on Information Theory, 1967, 13(1): 21-27.
[28] ENGLAND R, BEYNON D. A remark on as 136: a K-means clustering algorithm[J]. Journal of the Royal Statistical Society: Series C (Applied Statistics), 1981, 30(3): 355-356.
[29] CALIŃSKI T, HARABASZ J. A dendrite method for cluster analysis[J]. Communications in Statistics, 1974, 3(1): 1-27.
[30] 刘鑫. 通化地区电网规划设计与分析[D]. 北京: 华北电力大学(北京), 2016.
LIU Xin. Tonghua district power grid planning design and analysis[D]. Beijing: North China Electric Power University, 2016
[31] SHAYEGHI H, GHASEMI A, MORADZADEH M, et al. Simultaneous day-ahead forecasting of electricity price and load in smart grids[J]. Energy Conversion and Management, 2015, 95: 371-384.