基于KNN-IDBO-LSTM的光伏短期发电预测方法研究

皮琳琳; 田立国

doi:10.19912/j.0254-0096.tynxb.2024-0099

PDF(1565 KB)

太阳能学报 ›› 2025, Vol. 46 ›› Issue (5) : 320-330. DOI: 10.19912/j.0254-0096.tynxb.2024-0099

基于KNN-IDBO-LSTM的光伏短期发电预测方法研究

皮琳琳^1,2, 田立国¹

作者信息 +

RESEARCH ON SHORT TERM PHOTOVOLTAIC POWER GENERATION PREDICTION METHOD BASED ON KNN-IDBO-LSTM

Pi Linlin^1,2, Tian Liguo¹

Author information +

文章历史 +

摘要

提出一种基于K-近邻（KNN）数据预处理和改进蜣螂算法（IDBO）优化的长短期记忆神经网络（LSTM）光伏出力预测模型。首先,采用KNN补全缺失数据并校正异常数据,并提取易于训练的时序特征;然后,提出一种基于IDBO的LSTM模型参数优化方法,在原始DBO的基础上,采用种群均匀初始化策略,融合Levy飞行进行蜣螂位置迭代,引入种群密度概念动态调整种群数量,在保证全局搜索能力的同时大幅降低搜索时间;最后,基于澳大利亚某光伏阵列数据评估优化后模型预测性能。结果表明：在晴天、多云和雨天3种情况下,相比于KNN-LSTM,KNN-IDBO-LSTM的决定系数（R²）最高提升2.67%、均方根误差（RMSE）最高降低71.2%、平均绝对误差（MAE）最高降低79.9%、运行时间减少33.6%。

Abstract

A long short-term memory neural network （LSTM） photovoltaic power prediction model based on K-nearest neighbor (KNN) data preprocessing and improved dung beetle algorithm （IDBO） optimization was proposed. Firstly, KNN is used to fill missing data and correct abnormal data, and easily trainable time-series features are extracted; Then, an IDBO-based parameter optimization method for LSTM model was proposed. Based on the original DBO, a uniform population initialization strategy was adopted,and Levy flight was integrated into the dung beetle position iteration. The concept of population density was introduced to dynamically adjust the population size, ensuring global search capability while significantly reducing search time. Finally, the optimized model’s predictive performance was evaluated using data from a photovoltaic array in Australia. The experimental results show that the optimized hyperparameters improved prediction accuracy of the prediction model, and IDBO algorithm achieves convergence faster than other optimization algorithms.

导出引用

皮琳琳, 田立国. 基于KNN-IDBO-LSTM的光伏短期发电预测方法研究[J]. 太阳能学报. 2025, 46(5): 320-330 https://doi.org/10.19912/j.0254-0096.tynxb.2024-0099

Pi Linlin, Tian Liguo. RESEARCH ON SHORT TERM PHOTOVOLTAIC POWER GENERATION PREDICTION METHOD BASED ON KNN-IDBO-LSTM[J]. Acta Energiae Solaris Sinica. 2025, 46(5): 320-330 https://doi.org/10.19912/j.0254-0096.tynxb.2024-0099

中图分类号： TM615

参考文献

[1] 韩肖清, 李廷钧, 张东霞, 等. 双碳目标下的新型电力系统规划新问题及关键技术[J]. 高电压技术, 2021, 47(9): 3036-3046.
HAN X Q, LI T J, ZHANG D X, et al.New issues and key technologies of new power system planning under double carbon goals[J]. High voltage engineering, 2021, 47(9): 3036-3046.
[2] 李美成, 高中亮, 王龙泽, 等. “双碳” 目标下我国太阳能利用技术的发展现状与展望[J]. 太阳能, 2021(11): 13-18.
LI M C, GAO Z L, WANG L Z, et al.Development status and prospect of solar energy utilization technology in China under goal of emission peak and carbon neutrality[J]. Solar energy, 2021(11): 13-18.
[3] 钱振, 蔡世波, 顾宇庆, 等. 光伏发电功率预测方法研究综述[J]. 机电工程, 2015, 32(5): 651-659.
QIAN Z, CAI S B, GU Y Q, et al.Review of PV power generation prediction[J]. Journal of mechanical & electrical engineering, 2015, 32(5): 651-659.
[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] 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.
[6] 徐恒山, 莫汝乔, 薛飞, 等. 基于时间戳特征提取和CatBoost-LSTM模型的光伏短期发电功率预测[J]. 太阳能学报, 2024, 45(5): 565-575.
XU H S, MO R Q, XUE F, et al.Short-term photovoltaic power prediction based on timestamp feature extration and CatBoost-LSTM model[J]. Acta energiae solaris sinica, 2024, 45(5): 565-575.
[7] DING S, LI R J, TAO Z.A novel adaptive discrete grey model with time-varying parameters for long-term photovoltaic power generation forecasting[J]. Energy conversion and management, 2021, 227: 113644.
[8] 林鹏, 于洋, 张昕, 等. 基于CRITIC加权和IMFO-LSSVM的光伏发电功率短期预测[J]. 电气自动化, 2021, 43(6): 13-16.
LIN P, YU Y, ZHANG X, et al.Short-term prediction of photovoltaic generation power basedon CRITIC weighting and IMFO-LSSVM[J]. Electrical automation, 2021, 43(6): 13-16.
[9] 丁明, 刘志, 毕锐, 等. 基于灰色系统校正-小波神经网络的光伏功率预测[J]. 电网技术, 2015, 39(9): 2438-2443.
DING M, LIU Z, BI R, et al.Photovoltaic output prediction based on grey system correction-wavelet neural network[J]. Power system technology, 2015, 39(9): 2438-2443.
[10] 魏鹏飞, 樊小朝, 史瑞静, 等. 基于改进麻雀搜索算法优化支持向量机的短期光伏发电功率预测[J]. 热力发电, 2021, 50(12): 74-79.
WEI P F, FAN X, SHI R J, et al.Short-term photovoltaic power generation forecast based on improved sparrow search algorithm optimized support vector machine[J]. Thermal power generation, 2021, 50(12): 74-79.
[11] 阳霜, 罗滇生, 何洪英, 等. 基于EMD-LSSVM的光伏发电系统功率预测方法研究[J]. 太阳能学报, 2016, 37(6): 1387-1395.
YANG S, LUO D S, HE H Y, et al.Output power forecast of PV power system based on EMD-LSSVM model[J]. Acta energiae solaris sinica, 2016, 37(6): 1387-1395.
[12] 王超, 蔺红, 庞晓虹. 基于HPO-VMD和MISMA-DHKELM的短期光伏功率组合预测[J]. 太阳能学报, 2023, 44(12): 65-73.
WANG C, LIN H, PANG X H.Short-term photovoltaic power combination prediction based on HPO-VMD and MISMA-DHKELM[J]. Acta energiae solaris sinica, 2023, 44(12): 65-73.
[13] CHEN B, LI J H.Combined probabilistic forecasting method for photovoltaic power using an improved Markov chain[J]. IET generation, transmission & distribution, 2019, 13(19): 4364-4373.
[14] 李一, 杨茂, 苏欣. 基于集成聚类及改进马尔科夫链模型的光伏功率短期预测[J]. 南方电网技术, 2023, 17(10): 113-122.
LI Y, YANG M, SU X.Short-term prediction of photovoltaic power based on integrated clustering and improved Markov chain model[J]. Southern power system technology, 2023, 17(10): 113-122.
[15] 王继拓, 王万成, 陈宏伟. 基于回归:马尔科夫链的光伏发电功率预测[J]. 电测与仪表, 2019, 56(1): 76-81.
WANG J T, WANG W C, CHEN H W.Photovoltaic power generation forecasting based on regression-Markov chain[J]. Electrical measurement & instrumentation, 2019, 56(1): 76-81.
[16] HE B, MA R Z, ZHANG W W, et al.An improved generating energy prediction method based on Bi-LSTM and attention mechanism[J]. Electronics, 2022, 11(12): 1885.
[17] 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.
[18] 袁建华, 谢斌斌, 何宝林, 等. 基于DTW-VMD-PSO-BP的光伏发电功率短期预测方法[J]. 太阳能学报, 2022, 43(8): 58-66.
YUAN J H, XIE B B, HE B L, et al.Short term forecasting method of photovoltaic output based on DTW-VMD-PSO-BP[J]. Acta energiae solaris sinica, 2022, 43(8): 58-66.
[19] 杨海柱, 李庆华, 张鹏. 基于tGSSA-DELM的短期光伏发电功率预测[J]. 智慧电力, 2023, 51(10): 70-77.
YANG H Z, LI Q H, ZHANG P.Short-term photovoltaic power generation prediction based on tGSSA-DELM[J]. Smart power, 2023, 51(10): 70-77.
[20] 薛阳, 李金星, 杨江天, 等. 基于相似日分析和改进鲸鱼算法优化LSTM网络模型的光伏功率短期预测[J]. 南方电网技术, 2024, 18(11): 97-105.
XUE Y, LI J X, YANG J T, et al.Short-term prediction of photovoltaic power based on similar day analysisand improved whale algorithm to optimize LSTM network model[J]. Southern power system technology, 2024, 18(11): 97-105.
[21] 李超然, 潘鹏程, 杨伟荣, 等. 基于改进相似日优化HBA-BiLSTM-KELM的光伏发电功率预测[J]. 太阳能学报, 2024, 45(5): 508-516.
LI C R, PAN P C, YANG W R, et al.Research on PV system power prediction based on improved similar day and HBA-BiLSTM-KELM neural network[J]. Acta energiae solaris sinica, 2024, 45(5): 508-516.
[22] 岳有军, 吴明沅, 王红君, 等. 基于CNN-GRU-ISSA-XGBoost的短期光伏功率预测[J]. 南京信息工程大学学报, 2024, 16(2): 231-238.
YUE Y J, WU M Y, WANG H J, et al.Short term photovoltaic power prediction based on CNN-GRU-ISSAXGBoost[J]. Journal of Nanjing University of Information Science & Technology, 2024, 16(2): 231-238.
[23] 赖昌伟, 黎静华, 陈博, 等. 光伏发电出力预测技术研究综述[J]. 电工技术学报, 2019, 34(6): 1201-1217.
LAI C W, LI J H, CHEN B, et al.Review of photovoltaic power output prediction technology[J]. Transactions of China Electrotechnical Society, 2019, 34(6): 1201-1217.
[24] 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.