为有效提升光伏短期发电功率的预测精度和保障电网的稳定运行,在分别利用皮尔逊相关系数法（PCC）提取相关气象要素、传递闭包法确定相似日的基础上,结合ARIMA时间序列和BP神经网络,分别构建PCC-传递闭包-ARIMA和PCC-传递闭包-BP两类组合预测模型,用于解决云南宾川某光伏发电站的出力预测问题。对比结果显示：1）相较于单一模型,组合预测模型的预测精度明显提升,其中PCC-传递闭包-BP模型的预测效果最好,平均精度可达91.19%;2）在历史光伏出力普遍偏高的前提下,ARIMA模型在高光伏出力时段可较好地描述光伏出力的波动和变化特性,BP模型在低光伏出力时段具有更强的调整和纠正能力。
Abstract
In order to effectively improve the prediction accuracy of short-term photovoltaic power generation and ensure the stable operation of the power grid, this study uses the Pearson Correlation Coefficient （PCC） method to extract relevant meteorological elements and adopts the transitive closure method to determine the similar days. Combining ARIMA time series and BP neural network, two combined prediction models of PCC-transitive closure-ARIMA and PCC-transitive closure-BP are constructed, and used to solve the output prediction problem of a photovoltaic power station in Binchuan, Yunnan. The comparison results demonstrate that, （i） compared with single model, the prediction accuracy of two combination models is improved significantly, where the combined model based on BP neural network has the better performance, with an average prediction accuracy of 91.19%; （ii） ARIMA model is suitable to describe the fluctuation and variation characteristics of photovoltaic output in the period of high-level electricity output ; correspondingly, BP model owns more adjust and correct capability under unfavorable meteorological condition.
关键词
光伏发电 /
预测模型 /
因子分析 /
皮尔逊相关系数 /
传递闭包 /
ARIMA /
BP神经网络
Key words
photovoltaic power /
prediction model /
factor analysis /
Pearson correlation coefficient /
transitive closure /
ARIMA /
BP neural network
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] WAN C, ZHAO J, SONG Y H, et al.Photovoltaic and solar power forecasting for smart grid energy management[J]. CSEE journal of power and energy systems, 2015, 1(4): 38-46.
[2] 王育飞, 付玉超, 孙路, 等. 基于混沌-RBF神经网络的光伏发电功率超短期预测模型[J]. 电网技术, 2018, 42(4): 1110-1116.
WANG Y F, FU Y C, SUN L, et al.Ultra-short term prediction model of photovoltaic output power based on chaos-rbf neural network[J]. Power system technology, 2018, 42(4): 1110-1116.
[3] DAS U K, TEY K S, SEYEDMAHMOUDIAN M, et al.Forecasting of photovoltaic power generation and model optimization: a review[J]. Renewable and sustainable energy reviews, 2018, 81: 912-928.
[4] 吴硕. 光伏发电系统功率预测方法研究综述[J]. 热能动力工程, 2021, 36(8): 1-7.
WU S.Review of power forecasting methods of photovoltaic power generation system[J]. Thermal power engineering, 2021, 36(8): 1-7.
[5] NB/T 32031—2016, 光伏发电功率预测系统功能规范[S].
NB/T 32031—2016, Function specification of PV power forecasting system[S].
[6] 舒胜, 谢应明, 杨文宇, 等. 光伏发电预测方法研究进展[J]. 热能动力程, 2020, 35(11): 1-11.
SHU S, XIE Y M, YANG W Y, et al.A review of photovoltaic power generation forecasting methods[J]. Thermal power engineering, 2020, 35(11): 1-11.
[7] HAN S, QIAO Y H, YAN J, et al.Mid-to-long term wind and photovoltaic power generation prediction based on copula function and long short term memory network[J]. Applied energy, 2019, 239: 181-191.
[8] LI L L, WEN S Y, TSENG M L,et al.Renewable energy prediction:a novel short-term prediction model of photovoltaic output power[J] .Journal of cleaner production, 2019, 228: 359-375.
[9] 李秉晨, 于惠钧, 刘靖宇. 基于Kmeans和CEEMD-PE-LSTM的短期光伏发电功率预测[J]. 水电能源科学, 2021, 39(4): 204-208.
LI B C, YU H J, LIU J Y.Prediction of short-term photovoltaic power generation based on kmeans and CEEMD-PE-LSTM[J]. Water resources and power, 2021, 39(4): 204-208.
[10] 赵滨滨, 王莹, 王彬, 等. 基于ARIMA时间序列的分布式光伏系统输出功率预测方法研究[J]. 可再生能源, 2019, 37(6): 820-823.
ZHAO B B, WANG Y, WANG B, et al.Photovoltaic power prediction in distribution network based on ARIMA model time serie[J]. Renewable energy resources, 2019, 37(6): 820-823.
[11] 张晓宇. 模糊聚类在优化决策中的应用[D]. 成都: 西南交通大学, 2016.
ZHANG X Y.The appliccation of fuzzy clustering in the optimization decision[D]. Chengdu: Southwest Jiaotong University, 2016.
[12] 陈钉均, 孙运豪, 李俊捷, 等. 重大疫情下铁路应急救援能力评估指标体系构建[J]. 交通运输工程学报, 2020, 20(3): 129-138.
CHEN D J, SHUN Y H, LI J J, et al.Construction of evaluation index system for emergency rescue capacity of rail transit under serious epidemic situation[J]. Journal of traffic and transportation engineering, 2020, 20(3): 129-138.
[13] 王振东. 基于模糊聚类的铁路物流园区规划研究[D]. 北京: 中国铁道科学研究院, 2019.
WANG Z D.Research on railway logistics park planning based on fuzzy clustering[D]. Beijing: China Academy of Railway Sciences, 2019.
[14] 李文, 邓升, 段妍, 等. 时间序列预测与深度学习:文献综述与应用实例[J]. 计算机应用与软件, 2020, 37(10): 64-70, 84.
LI W, DENG S, DUAN Y, et al.Time series forecasting and deep learning:literature review and empirical example[J]. Computer applications and software, 2020, 37(10): 64-70, 84.
[15] 陈春俊, 杨露, 何智颖, 等. ARIMA-BP神经网络高速列车隧道压力波预测模型研究[J]. 中国测试, 2021, 47(10): 80-86.
CHEN C J, YANG L, HE Z Y, et al.Research on tunnel pressure wave prediction model of high-speed train based on ARIMA-BP neural network[J]. China measurement & testing technology, 2021, 47(10): 80-86.
[16] 张凌浩, 张明, 嵇文路, 等. 基于灰色关联理论和BP神经网络的分布式光伏电站运维数据虚拟采集方法[J]. 电力建设, 2021, 42(1): 125-131.
ZHANG L H, ZHANG M, JI W L, et al.Virtual acquisition method for operation data of distributed PV applying the mixture of grey relational theory and BP neural work[J]. Electric power construction, 2021, 42(1): 125-131.
[17] 高大启. 有教师的线性基本函数前向三层神经网络结构研究[J]. 计算机学报, 1998, 21(1): 80-86.
GAO D Q.On structures of supervised linear basis function feedforward three-layered neural networks[J]. Chinese journal of computers, 1998, 21(1): 80-86.
[18] 张雨金, 杨凌帆, 葛双冶, 等. 基于Kmeans-SVM的短期光伏发电功率预测[J]. 电力系统保护与控制, 2018, 46(21): 118-124.
ZHANG Y J, YNAG L F, GE S Z, et al.Short-term photovoltaic power forecasting based on Kmeans algorithm and support vector machine[J]. Power system protection and control, 2018, 46(21): 118-124.
[19] 张金金, 张倩, 马愿, 等. 模糊聚类-Elman神经网络短期光伏发电预测模型[J]. 电测与仪表, 2020, 57(12): 46-51.
ZHANG J J, ZHANG Q, MA Y, et al.Fuzzy clustering-Elman neural network model for short-term photovoltaic power generation prediction[J]. Electricity and instrumentation, 2020, 57(12): 46-51.
[20] HU W, ZHANG X Y, ZHU L J, et al.Short-term photovoltaic power prediction based on similar days and improved SOA-DBN model[J]. IEEE access, 2021, 9(1): 1958-1971.
基金
国家重点研发计划（2018YFE0208400）; 国家电网有限公司总部科技项目《面向跨境互联的多能互补新型能源系统关键技术研究》
PDF(1750 KB)
