基于综合能源计量大数据的中长期用电量预测

doi:10.11930/j.issn.1004-9649.202103108

摘要/Abstract

摘要： 用电量预测对智能电网的管理和安全有重要意义。传统方法一般基于历史用电数据本身，而“多表融合”的推广使得多表数据的分析更为便捷。针对用电量预测场景，利用集成智能表采集的水、电、气数据，将用水量与用气量作为特征，提出结合多表数据的中长期用电量预测模型：高斯过程回归（Gaussian process regression，GPR）与相关向量回归（relevance vector regression，RVR）。通过实验结果仿真，验证了所提模型的优势以及综合能源计量数据对用电量预测问题的重要价值。

关键词: 用电量预测, 多表融合, 概率模型, 时间序列

Abstract: Load forecasting is critical for management and security of smart grid system. Traditional methods are usually on the basis of historical power consumption data, and the popularization of multi-meter integration technology makes analysis of integrated energy consumption data more efficient. Towards the issue of load forecasting, with water/power/gas consumption data collected by integrated smart meter as features, two mid-and-long term power consumption forecasting methods are proposed: gaussian process regression (GPR) and relevance vector regression (RVR). Experimental results show the superiority of the proposed method and the significance of integrated energy consumption data for load forecasting problem.

Key words: power consumption forecasting, multi-meter integration, probabilistic model, time series

王新刚, 朱彬若, 顾臻. 基于综合能源计量大数据的中长期用电量预测[J]. 中国电力, 2021, 54(10): 211-216.

WANG Xingang, ZHU Binruo, GU Zhen. Mid-and-Long Term Load Forecasting Based on Integrated Power Consumption Data[J]. Electric Power, 2021, 54(10): 211-216.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202103108

https://www.electricpower.com.cn/CN/Y2021/V54/I10/211

参考文献

[1] 夏水斌, 余鹤, 何行, 等. 水电气多表合一数据自动采集系统设计[J]. 计算机测量与控制, 2018, 26(3): 141–144, 149
XIA Shuibin, YU He, HE Xing, et al. Design of automatic data acquisition system for water and electrical multimeter data[J]. Computer Measurement & Control, 2018, 26(3): 141–144, 149
[2] 李然, 刘宣, 唐悦, 等. "多表合一"采集终端功能检测系统设计与应用[J]. 电测与仪表, 2019, 56(15): 148–152
LI Ran, LIU Xuan, TANG Yue, et al. Design and application of multi-meter unification acquisition terminal function detection system[J]. Electrical Measurement & Instrumentation, 2019, 56(15): 148–152
[3] 刘南艳, 贺敏, 赵建文. 基于大数据平台的电力负荷预测[J]. 现代电子技术, 2018, 41(20): 153–156
LIU Nanyan, HE Min, ZHAO Jianwen. Power load prediction based on big data platform[J]. Modern Electronics Technique, 2018, 41(20): 153–156
[4] 李俊楠, 李伟, 李会君, 等. 基于大数据云平台的电力能源大数据采集与应用研究[J]. 电测与仪表, 2019, 56(12): 104–109
LI Junnan, LI Wei, LI Huijun, et al. Research on big data acquisition and application of power energy based on big data cloud platform[J]. Electrical Measurement & Instrumentation, 2019, 56(12): 104–109
[5] 郭泽宇, 陈玲俐. 城市用水量组合预测模型及其应用[J]. 水电能源科学, 2018, 36(1): 40–43
GUO Zeyu, CHEN Lingli. Combination prediction model of urban water supply and its application[J]. Water Resources and Power, 2018, 36(1): 40–43
[6] 史佳琪, 谭涛, 郭经, 等. 基于深度结构多任务学习的园区型综合能源系统多元负荷预测[J]. 电网技术, 2018, 42(3): 698–707
SHI Jiaqi, TAN Tao, GUO Jing, et al. Multi-task learning based on deep architecture for various types of load forecasting in regional energy system integration[J]. Power System Technology, 2018, 42(3): 698–707
[7] 董雪梅, 王洁微. 基于多尺度高斯核的分布式正则化回归学习算法[J]. 模式识别与人工智能, 2019, 32(7): 589–599
DONG Xuemei, WANG Jiewei. Distributed regularized regression learning algorithm based on multi-scale Gaussian kernels[J]. Pattern Recognition and Artificial Intelligence, 2019, 32(7): 589–599
[8] 夏成希, 李泽, 刘畅, 等. 随机子空间集成下的GPR光伏发电预测方法[J]. 计算机仿真, 2019, 36(11): 79–84
XIA Chengxi, LI Ze, LIU Chang, et al. GPR photovoltaic power generation forecasting method based on stochastic subspace integration[J]. Computer Simulation, 2019, 36(11): 79–84
[9] SAHOO D, HOI S C H, LI B. Large scale online multiple kernel regression with application to time-series prediction[J]. ACM Transactions on Knowledge Discovery from Data, 2019, 13(1): 1–33.
[10] 顾熹, 廖志伟. 基于相空间重构和高斯过程回归的短期负荷预测[J]. 电力系统保护与控制, 2017, 45(5): 73–79
GU Xi, LIAO Zhiwei. Short-term load forecasting based on phase space reconstruction and Gaussian process regression[J]. Power System Protection and Control, 2017, 45(5): 73–79
[11] 涂智福, 丁坚勇, 周凯. 基于VMD和GP的短期风电功率置信区间预测[J]. 电测与仪表, 2020, 57(1): 84–88
TU Zhifu, DING Jianyong, ZHOU Kai. Confidence interval prediction of short-term wind power based on VMD and GP[J]. Electrical Measurement & Instrumentation, 2020, 57(1): 84–88
[12] 刘升伟, 王星华, 鲁迪, 等. 基于改进高斯过程回归的短期负荷概率区间预测方法[J]. 电力系统保护与控制, 2020, 48(1): 18–25
LIU Shengwei, WANG Xinghua, LU Di, et al. Electric load probabilistic interval prediction method based on improved Gaussian process regression[J]. Power System Protection and Control, 2020, 48(1): 18–25
[13] 任利强, 张立民, 王海鹏, 等. 基于IPSO-GPR的短期负荷区间预测[J]. 计算机工程与设计, 2019, 40(10): 3002–3008
REN Liqiang, ZHANG Limin, WANG Haipeng, et al. Short-term power load interval forecasting based on improved particle swarm optimization and Gaussian process regression[J]. Computer Engineering and Design, 2019, 40(10): 3002–3008
[14] WU A, ROY N A, KEELEY S, et al. Gaussian process based nonlinear latent structure discovery in multivariate spike train data[J]. Advances in Neural Information Processing Systems, 2017, 30: 3496–3505.
[15] 何奇峰. 考虑季节性和趋势性影响的时空数据异常值检测研究[D]. 北京: 北京邮电大学, 2018.
HE Qifeng. A study on outlier detection of seasonal and trendy spatial-temporal data[D]. Beijing: Beijing University of Posts and Telecommunications, 2018.
[16] 范兴明, 王超, 张鑫, 等. 基于增量学习相关向量机的锂离子电池SOC预测方法[J]. 电工技术学报, 2019, 34(13): 2700–2708
FAN Xingming, WANG Chao, ZHANG Xin, et al. A prediction method of Li-ion batteries SOC based on incremental learning relevance vector machine[J]. Transactions of China Electrotechnical Society, 2019, 34(13): 2700–2708
[17] 燕彩蓉, 张青龙, 赵雪, 等. 基于广义高斯分布的贝叶斯概率矩阵分解方法[J]. 计算机研究与发展, 2016, 53(12): 2793–2800
YAN Cairong, ZHANG Qinglong, ZHAO Xue, et al. A method of Bayesian probabilistic matrix factorization based on generalized Gaussian distribution[J]. Journal of Computer Research and Development, 2016, 53(12): 2793–2800
[18] 邴其春, 龚勃文, 杨兆升, 等. 一种组合核相关向量机的短时交通流局域预测方法[J]. 哈尔滨工业大学学报, 2017, 49(3): 144–149
BING Qichun, GONG Bowen, YANG Zhaosheng, et al. A short-term traffic flow local prediction method of combined kernel function relevance vector machine[J]. Journal of Harbin Institute of Technology, 2017, 49(3): 144–149
[19] 高国强, 杨飞豹, 尹豪杰, 等. 基于代价敏感组合核相关向量机的电力变压器故障诊断[J]. 电测与仪表, 2017, 54(16): 7–13
GAO Guoqiang, YANG Feibao, YIN Haojie, et al. Transformer fault diagnosis based on cost-sensitive multi-kernel learning relevance vector machine[J]. Electrical Measurement & Instrumentation, 2017, 54(16): 7–13
[20] 田壁源, 刘琪, 张新燕, 等. 基于APSO-GSA和相关向量机的短期风电功率预测[J]. 电力系统保护与控制, 2020, 48(2): 107–114
TIAN Biyuan, LIU Qi, ZHANG Xinyan, et al. Short-term wind power prediction based on APSO-GSA and correlation vector machine[J]. Power System Protection and Control, 2020, 48(2): 107–114
[21] MALLASTO A, FERAGEN A. Wrapped Gaussian process regression on Riemannian manifolds[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, UT, USA. IEEE, 2018: 5580–5588.
[22] 张旭东, 李飞, 刘迪, 等. 基于CNN的产消群需求响应滚动优化策略[J]. 中国电力, 2021, 54(2): 78–89
ZHANG Xudong, LI Fei, LIU Di, et al. CNN-based rolling optimization strategy for prosumer group in demand response[J]. Electric Power, 2021, 54(2): 78–89
[23] ZHOU H Y, ZHANG S H, PENG J Q, et al. Informer: beyond efficient transformer for long sequence time-series forecasting[EB/OL]. (2020-07-05) [2020-10-26]. https://www.researchgate.net/publication/347125466_Informer_Beyond_Efficient_Transformer_for_Long_Sequence_Time-Series_Forecasting.
[24] 张志, 杜延菱, 崔慧军, 等. 考虑关联因素的智能化中长期电力负荷预测方法[J]. 电力系统保护与控制, 2019, 47(2): 24–30
ZHANG Zhi, DU Yanling, CUI Huijun, et al. Intelligent mid-long electricity load forecast method considering associated factors[J]. Power System Protection and Control, 2019, 47(2): 24–30
[25] 雷铮, 田书欣, 闫大威, 等. 基于ARIMA-TARCH-BP神经网络模型的中长期负荷预测方法[J]. 电子器件, 2020, 43(1): 175–179
LEI Zheng, TIAN Shuxin, YAN Dawei, et al. Mid-long term load forecasting based on ARIMA-TARCH-BP neural network model[J]. Chinese Journal of Electron Devices, 2020, 43(1): 175–179
[26] 孙兴鲁. 主动配电网鲁棒运行优化技术研究[D]. 广州: 华南理工大学, 2018.
SUN Xinglu. Research on robust operational optimization technology of active distribution network[D]. Guangzhou: South China University of Technology, 2018.
[27] 欧阳森, 杨家豪, 安晓华, 等. 基于时段解耦的含特殊负荷的配电网动态无功优化[J]. 华南理工大学学报(自然科学版), 2016, 44(2): 97–106
OUYANG Sen, YANG Jiahao, AN Xiaohua, et al. Dynamic reactive power optimization of distribution network containing special load based on time decoupling[J]. Journal of South China University of Technology (Natural Science Edition), 2016, 44(2): 97–106