为提高光伏发电功率预测的精确度,保障电网能可持续稳定运行,将长短时记忆网络（LSTM）与淘金优化算法（GRO）改进后的麻雀搜索算法（SSA）结合起来,用于实现短期光伏发电功率的预测。首先,利用皮尔逊相关系数提取影响光伏功率的关键因素;然后,利用麻雀搜索算法对长短时记忆网络进行优化,得到网络中最优的隐含层节点数量、训练次数、学习率等超参数;其次,引入Tent混沌映射优化麻雀种群的初始分布,使得种群初始位置分布更加均匀;最后,为避免算法陷入局部最优,引入GRO对SSA进行优化,使得麻雀种群搜索范围更加广泛,结果更加精确。实验结果表明,与LSTM、SSA-LSTM相比,GRO-SSA-LSTM在短期光伏发电功率预测中具有更高的预测精度,且具有至关重要的现实意义。
Abstract
In order to improve the accuracy of photovoltaic power generation prediction and ensure the sustainable and stable operation of the power grid, this article combines long short term memory （LSTM） network with sparrow search algorithm （SSA） improved by gold rush optimizer （GRO） algorithm to achieve short-term photovoltaic power generation prediction. Firstly, the Pearson correlation coefficient is used to extract key factors that affect photovoltaic power; Secondly, the sparrow search algorithm is used to optimize the long and short term memory network, obtaining the optimal hyperparameters such as the number of hidden layer nodes, training times, and learning rate in the network. Then, introducing Tent chaotic mapping to optimize the initial distribution of sparrow population, making the initial position distribution of the population more uniform. Finally, to avoid the algorithm falling into local optima, GRO is introduced to optimize SSA, making the search range of sparrow population more extensive and the results more accurate. The experimental results indicate that compared with LSTM and SSA-LSTM, GRO-SSA-LSTM has higher prediction accuracy in short-term photovoltaic power generation prediction and has crucial practical significance.
关键词
光伏发电 /
预测模型 /
长短时记忆网络 /
麻雀搜索算法 /
淘金优化算法
Key words
photovoltaic power /
prediction model /
long short-term memory network /
sparrow search algorithm /
gold rushing optimization algorithm
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 李春鹏, 张廷元, 周封. 太阳能光伏发电综述[J]. 电工材料, 2006(3): 45-48.
LI C P, ZHANG T Y, ZHOU F.Summarization of solar energy PV generation[J]. Electrical engineering materials, 2006(3): 45-48.
[2] 张程, 林谷青, 黄靖, 等. 基于AMBOA-DBN结合相似日的短期光伏功率预测[J]. 太阳能学报, 2023, 44(6): 290-299.
ZHANG C, LIN G Q, HUANG J, et al.Short-term PV power prediction based on AMBOA-DBN combined with similar days[J]. Acta energiae solaris sinica, 2023, 44(6): 290-299.
[3] 王晓霞, 俞敏, 冀明, 等. 基于气候相似性与SSA-CNN-LSTM的光伏功率组合预测[J]. 太阳能学报, 2023, 44(6): 275-283.
WANG X X, YU M, JI M, et al.Photovoltaic power combination forecasting based on climate similarity and SSA-CNN-LSTM[J]. Acta energiae solaris sinica, 2023, 44(6): 275-283.
[4] 李争, 罗晓瑞, 张杰, 等. 基于改进麻雀搜索算法的光伏功率短期预测[J]. 太阳能学报, 2023, 44(6): 284-289.
LI Z, LUO X R, ZHANG J, et al.Short term prediction of photovoltaic power based on improved sparrow search algorithm[J]. Acta energiae solaris sinica, 2023, 44(6): 284-289.
[5] 武宇翔, 韩肖清, 牛哲文, 等. 融合多注意力深度神经网络的可解释光伏功率区间预测[J]. 电网技术, 2024, 48(7): 2928-2939.
WU Y X, HAN X Q, NIU Z W, et al.Interpretable photovoltaic power interval prediction using multi-attention deep neural networks[J]. Power system technology, 2024, 48(7): 2928-2939.
[6] 乔楠. 基于SSA-FNN的光伏功率超短期预测研究[J]. 光源与照明, 2022(10): 98-100.
QIAO N.Research on ultra-short-term prediction of photovoltaic power based on SSA-FNN[J]. Lamps & lighting, 2022(10): 98-100.
[7] 薛阳, 燕宇铖, 贾巍, 等. 基于改进灰狼算法优化长短期记忆网络的光伏功率预测[J]. 太阳能学报, 2023, 44(7): 207-213.
XUE Y, YAN Y C, JIA W, et al.Photovoltaic power prediction model based on IGWO-LSTM[J]. Acta energiae solaris sinica, 2023, 44(7): 207-213.
[8] 李多, 董海鹰, 杨立霞. 基于EMD与ELM的光伏电站短期功率预测[J]. 可再生能源, 2016, 34(2): 173-177.
LI D, DONG H Y, YANG L X.The short-term power forecasting of photovoltaic plant based on EMD-ELM[J]. Renewable energy resources, 2016, 34(2): 173-177.
[9] 刘春芳, 王攀攀, 曹菲. 基于PSO-DE-BP的光伏发电功率短期预测[J]. 计算机测量与控制, 2023, 31(5): 180-186.
LIU C F, WANG P P, CAO F.Short term prediction of photovoltaic power generation based on PSO-DE-BP[J]. Computer measurement & control, 2023, 31(5): 180-186.
[10] 文爽, 马逸骋, 孙志强. 基于GWO-EEMD-BP神经网络的光伏发电功率短期预测[J]. 中南大学学报(自然科学版), 2022, 53(12): 4799-4808.
WEN S, MA Y C, SUN Z Q.Short-term prediction of photovoltaic power based on GWO-EEMD-BP[J]. Journal of Central South University (science and technology), 2022, 53(12): 4799-4808.
[11] 辛航. 基于BA-LSTM的短期光伏输出功率预测研究[D]. 沈阳: 沈阳农业大学, 2022.
XIN H.Research on short-term photovoltaic output power prediction based on BA-LSTM[D]. Shenyang: Shenyang Agricultural University, 2022.
[12] 李森文, 张伟, 李纯宇, 等. 基于SSA-LSTM的海上风电功率预测[J]. 机械与电子, 2022, 40(6): 22-25, 30.
LI S W, ZHANG W, LI C Y, et al.Power prediction of offshore wind farm based on SSA-LSTM[J]. Machinery & electronics, 2022, 40(6): 22-25, 30.
[13] XUE J K, SHEN B.A novel swarm intelligence optimization approach: sparrow search algorithm[J]. Systems science & control engineering, 2020, 8(1): 22-34.
[14] 肖海飞, 曾国辉, 杜涛, 等. 基于麻雀搜索算法的PMSM智能控制器设计[J]. 电力电子技术, 2022, 56(1): 5-8, 34.
XIAO H F, ZENG G H, DU T, et al.Design of intelligent controller of PMSM based on sparrow search algorithm[J]. Power electronics, 2022, 56(1): 5-8, 34.
[15] ZOLFI K.Gold rush optimizer: a new population-based metaheuristic algorithm[J]. Operations research and decisions, 2023, 33(1): 113-150.
[16] 郭雯博. 基于相似日和Tent-SSA-BP光伏发电功率预测研究[J]. 信息技术与信息化, 2023(5): 173-177.
GUO W B.Research on photovoltaic power prediction based on similar day and Tent-SSA-BP[J]. Information technology and informatization, 2023(5): 173-177.
[17] 回立川, 陈雪莲, 孟嗣博. 多策略混合的改进麻雀搜索算法[J]. 计算机工程与应用, 2022, 58(16): 71-83.
HUI L C, CHEN X L, MENG S B.Improved sparrow search algorithm based on multi-strategy mixing[J]. Computer engineering and applications, 2022, 58(16): 71-83.
[18] 吴丁杰, 周庆兴, 温立书. 基于Logistic混沌映射的改进麻雀算法[J]. 高师理科学刊, 2021, 41(6): 10-15.
WU D J, ZHOU Q X, WEN L S.Improved sparrow algorithm based on Logistic chaos mapping[J]. Journal of Science of Teachers’ College and University, 2021, 41(6): 10-15.
[19] 黄敬宇. 融合t分布和Tent混沌映射的麻雀搜索算法研究[D]. 兰州: 兰州大学, 2021.
HUANG J Y.Research on sparrow search algorithm combining t distribution and Tent chaotic mapping[D]. Lanzhou: Lanzhou University, 2021.
[20] 孟学尧, 郭倩倩, 郭海儒. 一种改进萤火虫算法的模糊聚类方法[J]. 小型微型计算机系统, 2021, 42(6): 1165-1170.
MENG X Y, GUO Q Q, GUO H R.Fuzzy clustering method based on improved firefly algorithm[J]. Journal of Chinese computer systems, 2021, 42(6): 1165-1170.
[21] 楼泽霖, 郑军红, 何利力. 基于改进SSA-LSTM的销量预测研究[J]. 计算机时代, 2023(10): 50-53, 58.
LOU Z L, ZHENG J H, HE L L.Research on sales forecasting based on improved SSA-LSTM[J]. Computer era, 2023(10): 50-53, 58.
[22] MIRJALILI S, LEWIS A.The whale optimization algorithm[J]. Advances in engineering software, 2016, 95: 51-67.
[23] XUE J K, SHEN B.Dung beetle optimizer: a new meta-heuristic algorithm for global optimization[J]. The journal of supercomputing, 2023, 79(7): 7305-7336.
[24] HASHIM F A, HUSSIEN A G.Snake Optimizer: a novel meta-heuristic optimization algorithm[J]. Knowledge-based systems, 2022, 242: 108320.
基金
国家自然科学基金（62073259; 52177194）
PDF(1803 KB)
