浙江大学学报(工学版)  2022, Vol. 56 Issue (2): 338-346    DOI: 10.3785/j.issn.1008-973X.2022.02.015
 计算机与控制工程

1. 六盘水师范学院 物理与电气工程学院，贵州 六盘水 553004
2. 云南大学 信息学院，云南 昆明 650091
New energy ramp event prediction based on time series decomposition and error correction
Lin TONG1(),Zheng GUAN2,*(),Li-wei WANG1,Wen-tao YANG1,Yang YAO1
1. School of Physics and Electrical Engineering, Liupanshui Normal University, Liupanshui 553004, China
2. School of Information Engineering, Yunnan University, Kunming 650091, China
 全文: PDF(1331 KB)   HTML

Abstract:

A ramp prediction model based on principal component analysis, time series decomposition and correction of long short-term memory (LSTM) network was proposed, in order to improve the accuracy of ramp prediction of new energy represented by wind power and photovoltaic power. In order to fully consider the time series characteristics of power, the power was decomposed into period, trend and residual by the time series decomposition method, and the trend and residual prediction model based on LSTM was established by combining the principal components of several characteristic factors, to realize the mapping relationship between the time characteristics of power and the principal components of influencing factors. Based on the preliminary prediction of trend and residual terms by LSTM, an error correction algorithm was introduced to calculate the dynamic error of the fitting prediction model and construct a new non-stationary time series to obtain the trend and residual predicted values with better accuracy. The final power prediction was obtained by fusing the trend, residual terms and the period value obtained by using the naive method. Combined with the definition of wind power and photovoltaic ramp event, the proposed model was used to predict the wind power and photovoltaic ramp event respectively. Experimental results show that the proposed model has better accuracy than other forecasting methods in direct power prediction and indirect ramp event prediction, and it can provide a more reliable basis for power grid dispatching.

Key words: principal component analysis    long short-term memory network    error correction    new energy ramp    time series decomposition

 CLC: TP 391

 服务 把本文推荐给朋友 加入引用管理器 E-mail Alert 作者相关文章 童林 官铮 王立威 杨文韬 姚洋

#### 引用本文:

Lin TONG,Zheng GUAN,Li-wei WANG,Wen-tao YANG,Yang YAO. New energy ramp event prediction based on time series decomposition and error correction. Journal of ZheJiang University (Engineering Science), 2022, 56(2): 338-346.

#### 链接本文:

 图 1  新能源爬坡示意图 图 2  新能源功率爬坡事件预测模型 图 3  基于PCA与STL的风电分解结果 表 1  功率爬坡事件预测结果 图 4  5种方法的风电功率预测结果与真实值的对比 表 2  5种方法的风电功率预测性能 图 5  5种方法的风电功率爬坡预测结果 表 3  5种方法的风电爬坡预测准确性 图 6  5种方法的光伏功率预测结果与真实值的对比 表 4  5种方法的光伏功率预测性能 图 7  5种方法的光伏功率爬坡预测结果 表 5  5种方法的光伏爬坡预测准确性
 1 SANCHEZ-SUTIL F, CANO O, HERNANDEZ J C, et al Development and calibration of an open source, low-cost power smart meter prototype for PV household-prosumers[J]. Electronics, 2019, (8): 878 2 王铮, 王伟胜, 刘纯, 等 基于风过程方法的风电功率预测结果不确定性估计[J]. 电网技术, 2013, 37 (1): 242- 247WANG Zheng, WANG Wei-sheng, LIU Chun, et al Uncertainty estimation of wind power prediction result based on wind process method[J]. Power System Technology, 2013, 37 (1): 242- 247 3 GALLEGO-CASTILLO C, GARCIA-BUSTAMANTE E, CUERVA A, et al Identifying wind power ramp causes from multivariate datasets: a methodological proposal and its application to reanalysis data[J]. IET Renewable Power Generation, 2015, 9 (8): 867- 875 doi: 10.1049/iet-rpg.2014.0457 4 HURTT J, BAKER K Sensitivity analysis of photovoltaic system design parameters to passively mitigate ramp rates[J]. IEEE Journal of Photovoltaics, 2021, 11 (2): 545- 551 doi: 10.1109/JPHOTOV.2020.3045679 5 KARABACAK M, FERNÁNDEZ-RAMÍREZ L M, KAMAL T, et al A new hill climbing maximum power tracking control for wind turbines with inertial effect compensation[J]. IEEE Transactions on Industrial Electronics, 2019, 66 (11): 8545- 8556 doi: 10.1109/TIE.2019.2907510 6 OUYANG T, ZHA X, QIN L, et al Prediction of wind power ramp events based on residual correction[J]. Renewable Energy, 2019, 136: 781- 792 doi: 10.1016/j.renene.2019.01.049 7 ARIAS-CASTRO E, KLEISSL J, LAVE M A poisson model for anisotropic solar ramp rate correlations[J]. Solar Energy, 2014, 101: 192- 202 doi: 10.1016/j.solener.2013.12.028 8 ZHENG H Y, KUSIAK A Prediction of wind farm power ramp rates: a data-mining approach[J]. Journal of Solar Energy Engineering, 2009, 131 (3): 031011 doi: 10.1115/1.3142727 9 ZHANG G, LIU H, ZHANG J, et al Wind power prediction based on variational mode decomposition multi-frequency combinations[J]. Journal of Modern Power Systems and Clean Energy, 2019, 7 (2): 281- 288 doi: 10.1007/s40565-018-0471-8 10 吴振威, 蒋小平, 马会萌, 等 多时间尺度的光伏出力波动特性研究[J]. 现代电力, 2014, 31 (1): 58- 61 WU Zhen-wei, JIANG Xiao-ping, MA Hui-meng, et al Study on fluctuations characteristics of photovoltaic power output in different time scales[J]. Modern Electric Power, 2014, 31 (1): 58- 61 doi: 10.3969/j.issn.1007-2322.2014.01.011 11 HABIB A, ABBASSI R, ARISTIZÁBAL A J, et al Forecasting model for wind power integrating least squares support vector machine, singular spectrum analysis, deep belief network, and locality-sensitive hashing[J]. Wind Energy, 2020, 23 (2): 235- 257 doi: 10.1002/we.2425 12 朱乔木, 李弘毅, 王子琪, 等 基于长短期记忆网络的风电场发电功率超短期预测[J]. 电网技术, 2017, 41 (12): 3797- 3802ZHU Qiao-mu, LI Hong-yi, WANG Zi-qi, et al Short-term wind power forecasting based on LSTM[J]. Power System Technology, 2017, 41 (12): 3797- 3802 13 CHU Y H, PEDRO H T C, LI M Y, et al Real-time forecasting of solar irradiance ramps with smart image processing[J]. Solar Energy, 2015, 114: 91- 104 doi: 10.1016/j.solener.2015.01.024 14 刘芳, 汪震, 刘睿迪, 等 基于组合损失函数的BP神经网络风力发电短期预测方法[J]. 浙江大学学报:工学版, 2021, 55 (3): 594- 600LIU Fang, WANG Zhen, LIU Rui-di, et al Short-term forecasting method of wind power generation based on BP neural network with combined loss function[J]. Journal of Zhejiang University: Engineering Science, 2021, 55 (3): 594- 600 15 LIU Z F, LI L L, TSENG M L, et al Prediction short-term photovoltaic power using improved chicken swarm optimizer-extreme learning machine model[J]. Journal of Cleaner Production, 2020, 248: 119272 doi: 10.1016/j.jclepro.2019.119272 16 ZHU W L, ZHANG L, YANG M, et al Solar power ramp event forewarning with limited historical observations[J]. IEEE Transactions on Industry Applications, 2019, 55 (6): 5621- 5630 doi: 10.1109/TIA.2019.2934935 17 TRUEWIND A. AWS Truewind’s final report for the Alberta forecasting pilot project [R]. New York: Wind Power Forecasting PILOT Project, 2008. 18 FERREIRA C, GAMA J, MATIAS L, et al. A survey on wind power ramp forecasting [R]. Chicago: Argonne National Laboratory (ANL), 2011. 19 韩学山, 王心仪, 杨明, 等 新能源爬坡事件综述及展望[J]. 山东大学学报:工学版, 2021, 51 (5): 53- 62+75HAN Xue-shan, WANG Xin-yi, YANG Ming, et al Review and prospect of renewable energy ramp events[J]. Journal of Shandong University: Engineering Science, 2021, 51 (5): 53- 62+75 20 李文书, 邹涛涛, 王洪雁, 等 基于双尺度长短期记忆网络的交通事故量预测模型[J]. 浙江大学学报:工学版, 2020, 54 (8): 1613- 1619LI Wen-shu, ZOU Tao-tao, WANG Hong-yan, et al Traffic accident quantity prediction model based on dual-scale long short-term memory network[J]. Journal of Zhejiang University: Engineering Science, 2020, 54 (8): 1613- 1619 21 CLEVELAND R, CLEVELAND W, MCRAE J STL: a seasonal-trend decomposition procedure based on loess[J]. Journal of Official Statistics, 1990, 6 (1): 3- 33 22 刘雪, 刘锦涛, 李佳利, 等 基于季节分解和长短期记忆的北京市鸡蛋价格预测[J]. 农业工程学报, 2020, 36 (9): 331- 340 LIU Xue, LIU Jin-tao, LI Jia-li, et al Egg price forecasting in Beijing market using seasonal-trend decomposition procedures based on seasonal decomposition and long-short term memory[J]. Transactions of the Chinese Society of Agricultural Engineering, 2020, 36 (9): 331- 340 doi: 10.11975/j.issn.1002-6819.2020.09.038 23 张东英, 代悦, 张旭, 等 风电爬坡事件研究综述及展望[J]. 电网技术, 2018, 42 (6): 1783- 1792ZHANG Dong-ying, DAI Yue, ZHANG Xu, et al Review and prospect of research on wind power ramp events[J]. Power System Technology, 2018, 42 (6): 1783- 1792
 [1] 陈伟航,罗强,王腾飞,蒋良潍,张良. 基于Bi-LSTM的非等时距路基工后沉降滚动预测[J]. 浙江大学学报(工学版), 2022, 56(4): 683-691. [2] 黄炜,陈田,吴入军. 基于门控循环单元与误差修正的短期负荷预测[J]. 浙江大学学报(工学版), 2021, 55(9): 1625-1633. [3] 李文书,邹涛涛,王洪雁,黄海. 基于双尺度长短期记忆网络的交通事故量预测模型[J]. 浙江大学学报(工学版), 2020, 54(8): 1613-1619. [4] 周金海,王依川,佟京鲆,周世镒,吴翔飞. 基于慢时间分割的超宽带雷达步态识别[J]. 浙江大学学报(工学版), 2020, 54(2): 283-290. [5] 李研彪,郑航,徐梦茹,罗怡沁,孙鹏. 5-PSS/UPU并联机构的多目标性能参数优化[J]. 浙江大学学报(工学版), 2019, 53(4): 654-663. [6] 王文浩,张筱,万永菁. 改进深度信念网络在语音转换中的应用[J]. 浙江大学学报(工学版), 2019, 53(12): 2372-2380. [7] 胡天中,余建波. 基于多尺度分解和深度学习的锂电池寿命预测[J]. 浙江大学学报(工学版), 2019, 53(10): 1852-1864. [8] 孙颖,胡艳香,张雪英,段淑斐. 面向情感语音识别的情感维度PAD预测[J]. 浙江大学学报(工学版), 2019, 53(10): 2041-2048. [9] 吴平, 陈亮, 周伟, 郭玲玲. 基于主成分分析和噪声估计的在线子空间辨识[J]. 浙江大学学报(工学版), 2018, 52(9): 1694-1701. [10] 刘大龙, 冯冬芹. 采用多尺度主成分分析的控制系统欺骗攻击检测[J]. 浙江大学学报(工学版), 2018, 52(9): 1738-1746. [11] 孟濬, 邓晓雨, 虞捷舟. 基于变量聚类的BP神经网络术后生存期预测模型[J]. 浙江大学学报(工学版), 2018, 52(12): 2365-2371. [12] 刘磊,杨鹏,刘作军. 基于多源信息和粒子群优化算法的下肢运动模式识别[J]. 浙江大学学报(工学版), 2015, 49(3): 439-447. [13] 徐锋,纪杨建,顾新建,祁国宁. 基于主成分分析的产品低碳包装概念设计方法[J]. 浙江大学学报(工学版), 2014, 48(11): 2009-2016. [14] 丁宽,仲兆平,张波,刘志超. 纯化凹凸棒土催化废轮胎热解制取高值液态产物[J]. 浙江大学学报(工学版), 2014, 48(11): 2053-2060. [15] 李懿, 陆光明, 金帅, 罗建勋, 陈卫东, 郑筱祥. 手部精细运动获取缺损数据修复方法[J]. J4, 2013, 47(6): 925-933.