基于小样本数据差分扩容的微电网负荷预测方法

doi:10.11930/j.issn.1004-9649.202209035

摘要/Abstract

摘要： 面向新能源微电网负荷预测，针对中长期负荷预测中样本数据不足导致预测精度不高的问题，提出了一种新的数据扩容方法，将原始数据样本两两差分作为新数据样本，通过设置阈值进行数据筛选，在扩充数据样本的同时保证数据的准确性，分析了基于差分运算的数据扩容方法对于负荷数据不确定性的消除效果。考虑气象、人口等影响因素，利用多元回归分析拟合各种关联因素对负荷的影响，将原始数据负荷预测模型作为对照，通过比较预测结果与实际负荷之间的误差，验证了数据扩容方法的实用性和准确性。

关键词: 负荷预测, 小样本数据, 回归分析, 微电网

Abstract: For load forecasting in renewable energy microgrid, aiming at the problem that the prediction accuracy is not high because of the lack of sample data in mid- and long-term load forecasting. This paper proposes a new data expansion method. The original data sample is used as a new data sample, and the data is filtered by setting a threshold. The data sample is expanded while ensuring the accuracy of the data, and the data based on the difference operation is analyzed. The capacity expansion method can eliminate the uncertainty of load data. Considering the influencing factors such as meteorology and population, using multiple regression analysis to fit the impact of various related factors on the load, the original data load forecasting model was used as a control, and practicality and accuracy of the expansion method in this paper was verified by comparing the error between the predicted result and the actual load.

Key words: load forecasting, small-sample data, regression analysis, microgrid

贾巍, 黄裕春. 基于小样本数据差分扩容的微电网负荷预测方法[J]. 中国电力, 2023, 56(8): 151-156,165.

JIA Wei, HUANG Yuchun. Method of Load Forecasting in Microgrid Based on Differential Expansion of Small Sample Data[J]. Electric Power, 2023, 56(8): 151-156,165.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202209035

https://www.electricpower.com.cn/CN/Y2023/V56/I8/151

参考文献

[1] 袁小凯, 李果, 黄世平. 基于大数据技术的多变量短期电力需求预测研究[J]. 电网与清洁能源, 2020, 36(12): 30–34, 40
YUAN Xiaokai, LI Guo, HUANG Shiping. Multi-variable short-term power demand forecasting research based on big data technology[J]. Power System and Clean Energy, 2020, 36(12): 30–34, 40
[2] 李志敏. 基于数据挖掘的工业用户用电行为分析及辨识研究[D]. 沈阳: 沈阳工业大学, 2022.
LI Zhimin. Analysis and identification of industrial users' electricity consumption behavior based on data mining[D]. Shenyang: Shenyang University of Technology, 2022.
[3] 何宗泽. 基于数据挖掘的用户用电行为分析研究[D]. 长春: 吉林大学, 2022
HE Zongze. Analysis and research on user’s electricity consumption behavior based on data mining[D]. Changchun: Jilin University, 2022.
[4] 杨彪, 颜伟, 莫静山. 考虑源荷功率随机性和相关性的主导节点选择与无功分区方法[J]. 电力系统自动化, 2021, 45(11): 61–67
YANG Biao, YAN Wei, MO Jingshan. Pilot-bus selection and network partitioning method considering randomness and correlation of source-load power[J]. Automation of Electric Power Systems, 2021, 45(11): 61–67
[5] 王永伟, 李新龙, 田斐, 等. 基于人群搜索算法的电网短期用电负荷预测研究[J]. 电网与清洁能源, 2020, 36(12): 35–40
WANG Yongwei, LI Xinlong, TIAN Fei, et al. Research on short-term electric load forecasting of power grid based on crowd search algorithms[J]. Power System and Clean Energy, 2020, 36(12): 35–40
[6] 谭嘉, 李知艺, 杨欢, 等. 基于分布式优化思想的配电网用电负荷多层协同预测方法[J]. 上海交通大学学报, 2021, 55(12): 1544–1553
TAN Jia, LI Zhiyi, YANG Huan, et al. A multi-level collaborative load forecasting method for distribution networks based on distributed optimization[J]. Journal of Shanghai Jiao Tong University, 2021, 55(12): 1544–1553
[7] 张兴科, 魏朝阳, 李征, 等. 包含高渗透率分布式电源的母线负荷区间预测[J]. 电网与清洁能源, 2020, 36(12): 101–106
ZHANG Xingke, WEI Chaoyang, LI Zheng, et al. Bus load interval prediction of the distributed generation with high penetration[J]. Power System and Clean Energy, 2020, 36(12): 101–106
[8] 魏聪, 乔立, 赵红生, 等. 高新产业用户负荷接入关键要素辨识与预测[J]. 电网与清洁能源, 2020, 36(10): 6–13
WEI Cong, QIAO Li, ZHAO Hongsheng, et al. Identification and prediction of key elements of user load access in high-tech industry[J]. Power System and Clean Energy, 2020, 36(10): 6–13
[9] 刘辉, 凌宁青, 罗志强, 等. 基于TCN-LSTM和气象相似日集的电网短期负荷预测方法[J]. 智慧电力, 2022, 50(8): 30–37
LIU Hui, LING Ningqing, LUO Zhiqiang, et al. Power grid short-term load forecasting method based on TCN-LSTM and meteorological similar day sets[J]. Smart Power, 2022, 50(8): 30–37
[10] 李鑫, 李海明, 马健. 基于单步预测LSTM的短期负荷预测模型[J]. 计算机仿真, 2022, 39(6): 98–102, 117
LI Xin, LI Haiming, MA Jian. Short-term load forecasting model based on LSTM of single-step forecasting[J]. Computer Simulation, 2022, 39(6): 98–102, 117
[11] 陈杰尧, 黄炜斌, 马光文, 等. 基于相似性识别的短期负荷动态预测方法[J]. 电网与清洁能源, 2020, 36(4): 1–7, 13
CHEN Jieyao, HUANG Weibin, MA Guangwen, et al. A short-term load dynamic prediction method based on similarity recognition[J]. Power System and Clean Energy, 2020, 36(4): 1–7, 13
[12] 席雅雯. 融合历史数据和实时影响因素的精细化短期负荷预测[D]. 北京: 北京交通大学, 2019.
XI Yawen. Refined short-term load forecasting based on historical data and real-time influencing factors[D]. Beijing: Beijing Jiaotong University, 2019.
[13] 张素香, 赵丙镇, 王风雨, 等. 海量数据下的电力负荷短期预测[J]. 中国电机工程学报, 2015, 35(1): 37–42
ZHANG Suxiang, ZHAO Bingzhen, WANG Fengyu, et al. Short-term power load forecasting based on big data[J]. Proceedings of the CSEE, 2015, 35(1): 37–42
[14] 金鑫, 李龙威, 季佳男, 等. 基于大数据和优化神经网络短期电力负荷预测[J]. 通信学报, 2016, 37(增刊1): 36–42
JIN Xin, LI Longwei, JI Jianan, et al. Power short-term load forecasting based on big data and optimization neural network[J]. Journal on Communications, 2016, 37(S1): 36–42
[15] 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
[16] 王季, 李润清, 刘屾, 等. 基于改进长短期记忆网络的短期负荷预测[J]. 电气自动化, 2022, 44(4): 61–63
WANG Ji, LI Runqing, LIU Shen, et al. Short-term load forecasting based on improved long short-term memory network[J]. Electrical Automation, 2022, 44(4): 61–63
[17] 叶剑华, 曹旌, 杨理, 等. 基于变分模态分解和多模型融合的用户级综合能源系统超短期负荷预测[J]. 电网技术, 2022, 46(7): 2610–2622
YE Jianhua, CAO Jing, YANG Li, et al. Ultra short-term load forecasting of user level integrated energy system based on variational mode decomposition and multi-model fusion[J]. Power System Technology, 2022, 46(7): 2610–2622
[18] 胡威, 张新燕, 李振恩, 等. 基于优化的VMD-mRMR-LSTM模型的短期负荷预测[J]. 电力系统保护与控制, 2022, 50(1): 88–97
HU Wei, ZHANG Xinyan, LI Zhen'en, et al. Short-term load forecasting based on an optimized VMD-m RMR-LSTM model[J]. Power System Protection and Control, 2022, 50(1): 88–97
[19] 周凯, 丁坚勇, 田世明, 等. 基于小样本性能数据的电气设备可靠性评估与预测方法研究[J]. 电网技术, 2018, 42(6): 1967–1974
ZHOU Kai, DING Jianyong, TIAN Shiming, et al. Research on assessment and prediction of electrical equipment reliability based on small sample performance data[J]. Power System Technology, 2018, 42(6): 1967–1974
[20] 王景芹, 唐义良, 陆俭国. 小样本及无失效数据时电器产品可靠性特征量的估计[J]. 电工技术学报, 2000, 15(4): 27–31
WANG Jingqin, TANG Yiliang, LU Jianguo. Estimation method of reliability characteristic parameter of electrical apparatus products for a few of failure data and zero-failure data[J]. Transactions of China Electrotechnical Society, 2000, 15(4): 27–31
[21] 郝海风, 朱承治, 彭晶. 基于小样本数据的输变电工程造价估算的建模与仿真[J]. 自动化与仪器仪表, 2019(11): 157–160
HAO Haifeng, ZHU Chengzhi, PENG Jing. Modeling and simulation of cost estimation for transmission and distribution engineering based on small sample data[J]. Automation & Instrumentation, 2019(11): 157–160
[22] 于惠鸣, 张智晟, 龚文杰, 等. 基于深度递归神经网络的电力系统短期负荷预测模型[J]. 电力系统及其自动化学报, 2019, 31(1): 112–116
YU Huiming, ZHANG Zhisheng, GONG Wenjie, et al. Short-term load forecasting model of power system based on deep recurrent neural network[J]. Proceedings of the CSU-EPSA, 2019, 31(1): 112–116
[23] 郭祥富, 刘昊, 毛万登, 等. 面向云边协同的配变短期负荷集群预测[J]. 电力系统保护与控制, 2022, 50(9): 84–92
GUO Xiangfu, LIU Hao, MAO Wandeng, et al. Short-term load cluster forecast of distribution transformers for cloud edge collaboration[J]. Power System Protection and Control, 2022, 50(9): 84–92
[24] FAY D, RINGWOOD J V. On the influence of weather forecast errors in short-term load forecasting models[J]. IEEE Transactions on Power Systems, 2010, 25(3): 1751–1758.
[25] 肖晶, 陈晋, 李雪, 等. 基于行业用电特性的用户报装容量饱和度分析[J]. 电力需求侧管理, 2016, 18(1): 4–7, 17
XIAO Jing, CHEN Jin, LI Xue, et al. Saturability analysis of new user capacity based on industrial electricity characteristics[J]. Power Demand Side Management, 2016, 18(1): 4–7, 17