基于压缩感知的短期风电功率预测相似数据分析方法
|
摘要
准确及时的短期风电功率预测对包含大规模风电的电力系统运行调度、检修计划、备用安排有着重要意义。引入温度、风速、风向及其各自的最大变化范围等对风电功率影响较大的因素作为风电模式特征,利用其时段周期性,提出一种基于压缩感知的相似数据分析方法,用以为预测模型提取历史基础数据。文中提出的基于压缩感知的相似数据分析方法以风电模式特征为数据类别,预测目标时间段数据为原始信息,利用时段周期性历史样本数据构造冗余字典,通过匹配追踪,求得观测值作为相似数据。实验结果表明,相对于一般的相似数据分析方法,本方法提取的相似数据更为切合实际情况,进而可以提高短期风电功率预测的精度,为风电场运行和调度提供更优的数据参考。
Accurate and timely short-term wind power forecasting is of great significance to the operation dispatch,turnaround plan and spare planning of electrical power system with large-scale wind power. This paper introduced temperature,wind speed,wind direction and the maximum range of them that have great influence of wind power as wind power pattern features,and put forward a similar data analysis method based on compressive sensing through using the periodicity,to extract history sample data for forecasting model. In this paper,the similar data analysis method based on compressive sensing takes wind power pattern features as data category,the data of forecast period as the original data,and the periodic history sample data are adopted to redundant dictionary,and matching pursuit to get observation as similar data.Simulation results show that,compared with the general similar data analysis methods,the method proposed in this paper is more accurate,furthermore,it can improve the accuracy of short-term wind power forecasting,and provide optimization data for the wind farm operation dispatch.
Accurate and timely short-term wind power forecasting is of great significance to the operation dispatch,turnaround plan and spare planning of electrical power system with large-scale wind power. This paper introduced temperature,wind speed,wind direction and the maximum range of them that have great influence of wind power as wind power pattern features,and put forward a similar data analysis method based on compressive sensing through using the periodicity,to extract history sample data for forecasting model. In this paper,the similar data analysis method based on compressive sensing takes wind power pattern features as data category,the data of forecast period as the original data,and the periodic history sample data are adopted to redundant dictionary,and matching pursuit to get observation as similar data.Simulation results show that,compared with the general similar data analysis methods,the method proposed in this paper is more accurate,furthermore,it can improve the accuracy of short-term wind power forecasting,and provide optimization data for the wind farm operation dispatch.
引文
[1]张庆阳,郭家康.世界风能强国发展风电的经验与对策[J].中外能源,2015,20(6):25-34.Zhang Qingyang,Guo Jiakang. Major Wind Power Using Countries’Experience and Countermeasures in Developing Wind Energy[J]. SinoGlobal Energy,2015,20(6):25-34.
[2] Yao Z,Jianxue W,Xifan W. Review on Probabilistic Forecasting of Wind Power Generation[J]. Renewable and Sustainable Energy Reviews,2014(32):255-270.
[3] Soman S S,Zareipour H,Malij O,et al. A Review of Wind Power and Wind Speed Forecasting Methods with Different Time Horizons[C]//2010 North American Power Symposium(NAPS),Sept. 26-28,2010,Arlington,TX,USA:IEEE,2010:1-8.
[4]于大洋,韩学山,梁军,等.基于NASA地球观测数据库的区域风电功率波动特性分析[J].电力系统自动化,2011,35(5):77-81.Yu Dayang,Han Xueshan,Liang Jun,et al. Study on the Profiling of China’s Regional Wind Power Fluctuation Using GEOS-5 Data Assimilation System of National Aeronautics and Space Administration of America[J]. Automation of Electric Power System,2011,35(5):77-81.
[5] Henrik A N,Henrik M,Torben S N. Using Quantile Regression to Extend an Existing Wind Power Forecasting System with Probabilistic Forecasts[J]. Wind Energy,2006,9:95-108.
[6]王丽婕,廖晓钟,高阳,等.风电场发电功率的建模和预测研究综述[J].电力系统保护与控制,2009,37(13):118-121.Wang Lijie,Liao Xiaozhong,Gao Yang,et al. Summarization of Modeling and Prediction of Wind Power Generation[J]. Power System Protection and Control,2009,37(13):118-121.
[7] Yan J,Li K,Bai E,et al. Special condition wind power forecasting based on Gaussian Process and similar historical data[C]//Power&Energy Society General Meeting,2015 IEEE. IEEE,2015:1-5.
[8] Zhu Z,Zhou D,Fan Z. Short term forecast of wind power generation based on SVM with pattern matching[C]//Energy Conference(ENERGYCON),2016 IEEE International. IEEE,2016:1-6.
[9] Mu Q,Wu Y,Pan X,et al. Short-term load forecasting using improved similar days method[C]//Power and Energy Engineering Conference(APPEEC),2010 Asia-Pacific. IEEE,2010:1-4.
[10]车远宏,贾雍,汤卓,等.皮尔逊相关系数在风电功率组合预测中的应用[J].广西电力,2016,39(3):50-53.Che Yuanhong,Jia Yong,Tang Zhuo,et al. Application of Pearson Correlation Coefficient in Wind Power Combination Prediction[J]. Guangxi Electric Power,2016,39(3):50-53.
[11]Shenzhe W,Shan G,Xin Z,et al. A multi-timescale wind power forecasting method based on selection of similar days[C]//Electricity Distribution(CICED),2016 China International Conference on. IEEE,2016:1-5.
[12]Duan Q,Shi L,Hu B,et al. Power forecasting approach of PV plant based on similar time periods and Elman neural network[C]//Chinese Automation Congress(CAC),2015. IEEE,2015:1258-1262.
[13]史宇伟,潘学萍.计及历史气象数据的短期风速预测[J].电力自动化设备,2014,34(10):75-80.Shi Yuwei,Pan Xueping. Short-term wind speed forecasting considering historical meteorological data[J]. Electric Power Automation Equipment,2014,34(10):75-80.
[14]邢婷,郑有飞,朱勇,等.云南风能资源及其开发利用研究进展[J].气象与环境科学,2013,36(4):55-61.Xing Ting,Zheng Youfei,Zhu Yong,et al. Research on the Development and Exploitation of Wind Energy Resources in Yunnan Province[J]. Meteorological and Environmental Sciences,2013,36(4):55-61.
[15]杨茂,王东,严干贵,等.风电功率波动特性中的周期性研究[J].太阳能学报,2013,34(11):2020-2026.Yang Mao,Wang Dong,Yan Gangui,et al. Study on periodicity for wind power fluctuations characteristics[J]. Acta Energiae Solaris Sinica,2013,34(11):2020-2026.
[16]王贺,胡志坚,陈珍,等.基于集合经验模态分解和小波神经网络的短期风功率组合预测[J].电工技术学报,2013,28(9):138-144.Wang He,Hu Zhijian,Chen Zhen,et al. A Hybrid Model for Wind Power Forecasting Based on Ensemble Empirical Mode Decomposition and Wavelet Neural Networks[J]. Transactions Of China Electrotechnical Society,2013,28(9):138-144.
[2] Yao Z,Jianxue W,Xifan W. Review on Probabilistic Forecasting of Wind Power Generation[J]. Renewable and Sustainable Energy Reviews,2014(32):255-270.
[3] Soman S S,Zareipour H,Malij O,et al. A Review of Wind Power and Wind Speed Forecasting Methods with Different Time Horizons[C]//2010 North American Power Symposium(NAPS),Sept. 26-28,2010,Arlington,TX,USA:IEEE,2010:1-8.
[4]于大洋,韩学山,梁军,等.基于NASA地球观测数据库的区域风电功率波动特性分析[J].电力系统自动化,2011,35(5):77-81.Yu Dayang,Han Xueshan,Liang Jun,et al. Study on the Profiling of China’s Regional Wind Power Fluctuation Using GEOS-5 Data Assimilation System of National Aeronautics and Space Administration of America[J]. Automation of Electric Power System,2011,35(5):77-81.
[5] Henrik A N,Henrik M,Torben S N. Using Quantile Regression to Extend an Existing Wind Power Forecasting System with Probabilistic Forecasts[J]. Wind Energy,2006,9:95-108.
[6]王丽婕,廖晓钟,高阳,等.风电场发电功率的建模和预测研究综述[J].电力系统保护与控制,2009,37(13):118-121.Wang Lijie,Liao Xiaozhong,Gao Yang,et al. Summarization of Modeling and Prediction of Wind Power Generation[J]. Power System Protection and Control,2009,37(13):118-121.
[7] Yan J,Li K,Bai E,et al. Special condition wind power forecasting based on Gaussian Process and similar historical data[C]//Power&Energy Society General Meeting,2015 IEEE. IEEE,2015:1-5.
[8] Zhu Z,Zhou D,Fan Z. Short term forecast of wind power generation based on SVM with pattern matching[C]//Energy Conference(ENERGYCON),2016 IEEE International. IEEE,2016:1-6.
[9] Mu Q,Wu Y,Pan X,et al. Short-term load forecasting using improved similar days method[C]//Power and Energy Engineering Conference(APPEEC),2010 Asia-Pacific. IEEE,2010:1-4.
[10]车远宏,贾雍,汤卓,等.皮尔逊相关系数在风电功率组合预测中的应用[J].广西电力,2016,39(3):50-53.Che Yuanhong,Jia Yong,Tang Zhuo,et al. Application of Pearson Correlation Coefficient in Wind Power Combination Prediction[J]. Guangxi Electric Power,2016,39(3):50-53.
[11]Shenzhe W,Shan G,Xin Z,et al. A multi-timescale wind power forecasting method based on selection of similar days[C]//Electricity Distribution(CICED),2016 China International Conference on. IEEE,2016:1-5.
[12]Duan Q,Shi L,Hu B,et al. Power forecasting approach of PV plant based on similar time periods and Elman neural network[C]//Chinese Automation Congress(CAC),2015. IEEE,2015:1258-1262.
[13]史宇伟,潘学萍.计及历史气象数据的短期风速预测[J].电力自动化设备,2014,34(10):75-80.Shi Yuwei,Pan Xueping. Short-term wind speed forecasting considering historical meteorological data[J]. Electric Power Automation Equipment,2014,34(10):75-80.
[14]邢婷,郑有飞,朱勇,等.云南风能资源及其开发利用研究进展[J].气象与环境科学,2013,36(4):55-61.Xing Ting,Zheng Youfei,Zhu Yong,et al. Research on the Development and Exploitation of Wind Energy Resources in Yunnan Province[J]. Meteorological and Environmental Sciences,2013,36(4):55-61.
[15]杨茂,王东,严干贵,等.风电功率波动特性中的周期性研究[J].太阳能学报,2013,34(11):2020-2026.Yang Mao,Wang Dong,Yan Gangui,et al. Study on periodicity for wind power fluctuations characteristics[J]. Acta Energiae Solaris Sinica,2013,34(11):2020-2026.
[16]王贺,胡志坚,陈珍,等.基于集合经验模态分解和小波神经网络的短期风功率组合预测[J].电工技术学报,2013,28(9):138-144.Wang He,Hu Zhijian,Chen Zhen,et al. A Hybrid Model for Wind Power Forecasting Based on Ensemble Empirical Mode Decomposition and Wavelet Neural Networks[J]. Transactions Of China Electrotechnical Society,2013,28(9):138-144.