为提高光伏输出功率预测精度、保证电网的优化调度和稳定运行,提出一种改进麻雀搜索算法（SSA）的光伏输出功率预测模型。首先,对实验平台收集到的历史数据进行分析,得到关键气候影响因素;然后,用经验模态分解和主成分分析法对数据进行维稳和降维处理;并建立改进麻雀搜索算法的BP神经网络预测模型;最后,进行实例验证。结果表明,该预测模型在敛散精度方面有所提升。
Abstract
In order to improve the prediction accuracy of photovoltaic output power and ensure the optimal dispatching and stable operation of power grid, a photovoltaic output power prediction model based on improved sparrow search algorithm（SSA） is proposed. Firstly, the historical data collected by the experimental platform are analyzed to obtain the key climate influencing factors. Then, the empirical mode decomposition（EMD） and principal component analysis（PCA） are used to maintain the stability and reduce the dimension of the data. Thirdly, the BP neural network prediction model of improved sparrow search algorithm is established. Finally, an example is given to verify the model. The results show that the prediction model improves the convergence and divergence accuracy.
关键词
经验模态分解 /
主成分分析 /
改进麻雀搜索算法 /
光伏输出功率短期预测
Key words
empirical mode decomposition /
principal component analysis /
improved sparrow search algorithm /
short term prediction of photovoltaic output power
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] MA T, YANG H X, LU L.Solar photovoltaic system modeling and performance prediction[J]. Renewable and sustainable energy reviews, 2014, 36: 304-315.
[2] SAREMI S, MIRJALILI S, LEWIS A.Grasshopper optimisation algorithm: theory and application[J]. Advances in engineering software, 2017, 105: 30-47.
[3] XUE J K,SHEN B.A novel swarm intelligence optimization approach: sparrow search algorithm[J]. Systems science & control engineering, 2020, 8(1): 22-34.
[4] ZHOU Y, ZHOU N R, GONG L H, et al.Prediction of photovoltaic power output based on similar day analysis, genetic algorithm and extreme learning machine[J]. Energy, 2020, 204: 117894.
[5] PAN M Z, LI C, GAO R, et al.Photovoltaic power forecasting based on a support vector machine with improved ant colony optimization[J]. Journal of cleaner production, 2020, 277: 123948.
[6] CHEN X, DING K, ZHANG J W, et al.Online prediction of ultra-short-term photovoltaic power using chaotic characteristic analysis, improved PSO and KELM[J]. Energy, 2022, 248: 123574.
[7] SANG K W, WANG K, GAO W G.Power prediction of short-term photovoltaic power generation system based on EMD-RVM[J]. Journal of Sichuan University of Science & Engineering(natural science edition), 2019.
[8] 张雲钦. 基于深度学习的光伏功率预测模型研究[D]. 太原: 太原理工大学, 2020.
ZHANG Y Q.Research on photovoltaic power prediction model based on deep learning[D]. Taiyuan: Taiyuan University of Technology, 2020.
[9] WANG X, HUANG K, ZHENG Y H, et al.Short-term forecasting method of photovoltaic output power based on PNN/PCA/SS-SVR[J]. Automation of electric power systems, 2016, 40(17): 156-162.
[10] 魏小辉. 基于灰色模型与机器学习的短期光伏功率预测[D]. 兰州: 兰州大学, 2019.
WEI X H.Short term photovoltaic power prediction based on grey model and machine learning[D]. Lanzhou: Lanzhou University, 2019.
[11] 刘卫健. 面向二次调频的储能电池优化配置及高效性研究[D]. 长沙: 湖南大学, 2018.
LIU W J.Research on optimal configuration and efficiency of energy storage battery for secondary frequency modulation[D]. Changsha: Hunan University, 2018.
[12] 张雲钦, 程起泽, 蒋文杰, 等. 基于EMD-PCA-LSTM的光伏功率预测模型[J]. 太阳能学报, 2021, 42(9): 62-69.
ZHANG Y Q, CHENG Q Z, JIANG W J, et al.Photovoltaic power prediction model based on EMD-PCA-LSTM[J]. Acta energiae solaris sinica, 2021, 42(9): 62-69.
[13] 徐一伦, 张彬桥, 黄婧, 等. 考虑天气类型和相似日的IWPA-LSSVM光伏发电功率预测[J]. 中国电力, 2023, 56(2): 143-149.
XU Y L, ZHANG B Q, HUANG J, et al.IWPA-LSSVM photovoltaic power prediction considering weather types and similar days[J]. Electric power, 2023, 56(2): 143-149.
[14] 魏书荣, 张鑫, 符杨, 等. 基于GRA-LSTM-Stacking模型的海上双馈风力发电机早期故障预警与诊断[J]. 中国电机工程学报, 2021, 41(7): 2373-2382.
WEI S R, ZHANG X, FU Y, et al.Early fault warning and diagnosis of offshore doubly fed wind turbine based on GRA-LSTM-Stacking model[J]. Proceedings of the CSEE, 2021, 41(7): 2373-2382.
[15] 王秋雯, 陈彦如, 刘媛春. 基于卷积长短时记忆神经网络的城市轨道交通短时客流预测[J]. 控制与决策, 2021, 36(11): 2760-2770.
ZHANG Q W, CHEN Y R, LIU Y C.Metro short-term traffic flow prediction with ConvLSTM[J]. Control and decision, 2021, 36(11): 2760-2770.
基金
国家自然科学基金（51877070）; 河北省重点研发计划（19214501D）; 河北省自然科学基金（E2021208008）; 河北省高层次人才项目 （A201905008）
PDF(2035 KB)
