一种适用于单/多光伏电站的迁移超短期光伏预测建模框架

任密蜂; 王家辉; 叶泽甫; 朱竹军; 阎高伟

doi:10.19912/j.0254-0096.tynxb.2023-0330

PDF(3301 KB)

太阳能学报 ›› 2024, Vol. 45 ›› Issue (6) : 359-367. DOI: 10.19912/j.0254-0096.tynxb.2023-0330

一种适用于单/多光伏电站的迁移超短期光伏预测建模框架

任密蜂¹, 王家辉¹, 叶泽甫², 朱竹军², 阎高伟¹

作者信息 +

TRANSFER ULTRA-SHORT TERM PHOTOVOLTAIC PREDICTION MODELING FRAMEWORK FOR SINGLE/MULTIPLE PHOTOVOLTAIC POWER STATIONS

Ren Mifeng¹, Wang Jiahui¹, Ye Zefu², Zhu Zhujun², Yan Gaowei¹

Author information +

文章历史 +

摘要

针对新建电站的历史数据量有限,且不同时段光伏数据的分布存在较大差异的问题,构建一种适用于单/多光伏电站的迁移超短期光伏预测建模框架。首先,为充分考量光伏序列的不确定性及数值天气预报的固有偏差,提出一种基于加权滚动时间窗聚类方法,同时为避免维度过高问题并强化天气类型与光伏发电功率之间的映射关系,提出类内外特征加权结构保持降维算法;其次,通过采用测地线流式核积分完成数据分布对齐,减小样本分布差异对单/多电站模型鲁棒性的影响;最后,采用梯度增强决策树建立光伏功率预测模型,实现光伏功率预测精度的提升。采用公开数据集PVOD验证了所提算法的有效性。

Abstract

To solve the problem that the historical data of new photovoltaic power stations are limited and the distribution of photovoltaic data in different periods of time is quite different, a transfer ultra-short-term photovoltaic prediction modeling framework for single/multiple photovoltaic power stations is presented. First, a weighted rolling time window clustering method based on a weighted structure preserving dimensionality reduction algorithm with inside and outside features is presented to fully consider the uncertainty of photovoltaic series and the inherent bias of numerical weather prediction. Secondly, geodesic flow kernel is used to integrate infinite subspaces to simulate the gradient process of the distribution of photovoltaic data, thus completing the data distribution alignment. Finally, a photovoltaic power prediction model is built using gradient boosting decision tree. The validity of the proposed algorithm is verified by using the public dataset PVOD.

导出引用

任密蜂, 王家辉, 叶泽甫, 朱竹军, 阎高伟. 一种适用于单/多光伏电站的迁移超短期光伏预测建模框架[J]. 太阳能学报. 2024, 45(6): 359-367 https://doi.org/10.19912/j.0254-0096.tynxb.2023-0330

Ren Mifeng, Wang Jiahui, Ye Zefu, Zhu Zhujun, Yan Gaowei. TRANSFER ULTRA-SHORT TERM PHOTOVOLTAIC PREDICTION MODELING FRAMEWORK FOR SINGLE/MULTIPLE PHOTOVOLTAIC POWER STATIONS[J]. Acta Energiae Solaris Sinica. 2024, 45(6): 359-367 https://doi.org/10.19912/j.0254-0096.tynxb.2023-0330

中图分类号： TM615

参考文献

[1] PRĂVĂLIE R, PATRICHE C, BANDOC G. Spatial assessment of solar energy potential at global scale. A geographical approach[J]. Journal of cleaner production, 2019, 209: 692-721.
[2] 张家安, 郝峰, 董存, 等. 基于两阶段不确定性量化的光伏发电超短期功率预测[J]. 太阳能学报, 2023, 44(01): 69-77.
ZHANG J A, HAO F, DONG C, et al.Ultra-short-term power forecasting of photovoltaic power generation based on two-stage uncertainty quantization[J]. Acta energiae solaris sinica, 2023, 44(1): 69-77.
[3] 张成, 白建波, 兰康, 等. 基于数据挖掘和遗传小波神经网络的光伏电站发电量预测[J]. 太阳能学报, 2021, 42(3): 375-382.
ZHANG C, BAI J B, LAN K, et al.Photovoltaic power generation prediction based on data mining and genetic wavelet neural network[J]. Acta energiae solaris sinica, 2021, 42(3): 375-382.
[4] VAN D W, WIDÉN J, MUNKHAMMAR J. Review on probabilistic forecasting of photovoltaic power production and electricity consumption[J]. Renewable and sustainable energy reviews, 2018, 81: 1484-1512.
[5] GANGER D, ZHANG J S, VITTAL V.Forecast-based anticipatory frequency control in power systems[J]. IEEE transactions on power systems, 2018, 33(1): 1004-1012.
[6] LI K P, WANG F, MI Z Q, et al.Capacity and output power estimation approach of individual behind-the-meter distributed photovoltaic system for demand response baseline estimation[J]. Applied energy, 2019, 253: 113595.
[7] LI K P, LIU L M, WANG F, et al. Impact factors analysis on the probability characterized effects of time of use demand response tariffs using association rule mining method[J]. Energy conversion and management, 2019, 197: 111891.1-111891.15.
[8] ANGENENDT G, ZURMÜHLEN S, FIGGENER J, et al. Providing frequency control reserve with photovoltaic battery energy storage systems and power-to-heat coupling[J]. Energy, 2020, 194: 116923.
[9] BOLAND J, DAVID M, LAURET P.Short term solar radiation forecasting: island versus continental sites[J]. Energy, 2016, 113: 186-192.
[10] 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: 1958-1971.
[11] JIANG Y M, YANG Y, WU Q X, et al.Research on predicting the short-term output of photovoltaic (PV) based on extreme learning machine model and improved similar day[C]// 2019 IEEE Innovative Smart Grid Technologies-Asia (ISGT Asia). Chengdu, China, 2019.
[12] 黄雨薇, 彭道刚, 姚峻, 等.基于SSA和K均值的TD-BP神经网络超短期光伏功率预测[J]. 太阳能学报, 2021, 42(4): 229-238.
HUANG Y W,PENG D G, YAO J, et al.Ultra-short-term photovoltaic power forecast of TD-BP neural network based on SSA and K-means[J]. Acta energiae solaris sinica, 2021, 42(4): 229-238.
[13] YANG D Z.Validation of the 5-min irradiance from the National Solar Radiation Database(NSRDB)[J]. Journal of renewable and sustainable energy, 2021, 13(1): 016101.
[14] BENJAMIN S G, WEYGANDT S S, BROWN J M, et al.A North American hourly assimilation and model forecast cycle: the rapid refresh[J]. Monthly weather review, 2016, 144(4): 1669-1694.
[15] ZHANG R, MA H, HUA W, et al.Data-driven photovoltaic generation forecasting based on a Bayesian network with spatial-temporal correlation analysis[J]. IEEE transactions on industrial informatics, 2020, 16(3): 1635-1644.
[16] LUO X, ZHANG D X, ZHU X.Combining transfer learning and constrained long short-term memory for power generation forecasting of newly-constructed photovoltaic plants[J]. Renewable energy, 2022, 185: 1062-1077.
[17] YANG M, HUANG X.Ultra-short-term prediction of photovoltaic power based on periodic extraction of PV energy and LSH algorithm[J]. IEEE access, 2018, 6: 51200-51205.
[18] 王福忠, 王帅峰, 张丽. 基于VMD-LSTM与误差补偿的光伏发电超短期功率预测[J]. 太阳能学报, 2022, 43(8): 96-103.
WANG F Z, WANG S F, ZHANG L.Ultra short term power prediction of photovoltaic power generation based on VMD-LSTM and error compensation[J]. Acta energiae solaris sinica, 2022, 43(8): 96-103.
[19] PHILLIPS P J, ZHENG J, CHELLAPPA R.Sparse embedding-based domain adaptation for object recognition |NIST[C]//The 1st International Workshop on Visual Domain Adaptation and Dataset Bias. 2013.
[20] BEN-DAVID S, BLITZER J, CRAMMER K, et al.Analysis of representations for domain adaptation[C]//Proceedings of the 19th International Conference on Neural Information Processing Systems. Canada, 2006: 137-144.
[21] GONG B Q, SHI Y, SHA F, et al.Geodesic flow kernel for unsupervised domain adaptation[C]//2012 IEEE Conference on Computer Vision and Pattern Recognition. Providence, RI, USA, 2012.
[22] GOPALAN R, LI R N, CHELLAPPA R.Domain adaptation for object recognition: an unsupervised approach[C]//IEEE International Conference on Computer Vision. Barcelona, Spain, 2011: 999-1006.
[23] KAKIMOTO M, SHIGA Y, SHIN H, et al.Quantile mapping correction of analog ensemble forecast for solar irradiance[J]. Solar energy, 2022, 237: 253-263.
[24] KUMAR K M, REDDY A R M. A fast DBSCAN clustering algorithm by accelerating neighbor searching using groups method[J]. Pattern recognition, 2016, 58(C): 39-48.
[25] ZHU P, KNYAZEV A V.Angles between subspaces and their tangents[J]. Journal of numerical mathematics, 2013, 21(4): 325-340.
[26] 米增强, 王飞, 杨光, 等. 光伏电站辐照度ANN预测及其两维变尺度修正方法[J]. 太阳能学报, 2013, 34(2): 251-259.
MI Z Q, WANG F, YANG G, et al.ANN based irradiance forecast of photovoltaic power plant and two dimensions variable scale modification method for the forecast value[J]. Acta energiae solaris sinica, 2013, 34(2): 251-259.
[27] 张娜, 葛磊蛟. 基于SOA优化的光伏短期出力区间组合预测[J]. 太阳能学报, 2021, 42(5): 252-259.
ZHANG N, GE L J.Photovoltaic system short-term power interval hybrid forecasting method based on seeker optimization algorithm[J]. Acta energiae solaris sinica, 2021, 42(5): 252-259.
[28] 谢从珍, 王江储, 谢心昊, 等. 基于细粒度特征的BOA-GBDT光伏出力预测[J]. 电网技术, 2020, 44(2): 689-696.
XIE C Z, WANG J C, XIE X H, et al.PV output prediction based on gradient boosting decision tree model with Bayesian optimization algorithm and fine-grained features[J]. Power system technology, 2020, 44(2): 689-696.
[29] 王琦, 季顺祥, 钱子伟, 等. 基于熵理论和改进ELM的光伏发电功率预测[J]. 太阳能学报, 2020, 41(10): 151-158.
WANG Q, JI S X, QIAN Z W, et al.Photovoltaic power prediction based on entropy theory and improved ELM[J]. Acta energiae solaris sinica, 2020, 41(10): 151-158.
[30] MOHAMED A, BADRUL C.Solar power forecasting using artificial neural networks[C]// 2015 North American Power Symposium(NAPS). Charlotte, NC, USA, 2015.