基于IWOA-SA-Elman神经网络的短期风电功率预测

刘吉成; 朱玺瑞; 于晶

doi:10.19912/j.0254-0096.tynxb.2022-1423

PDF(1835 KB)

太阳能学报 ›› 2024, Vol. 45 ›› Issue (1) : 143-150. DOI: 10.19912/j.0254-0096.tynxb.2022-1423

基于IWOA-SA-Elman神经网络的短期风电功率预测

刘吉成, 朱玺瑞, 于晶

作者信息 +

SHORT-TERM WIND POWER PREDICTION BASED ON IWOA-SA-ELMAN NEURAL NETWORK

Liu Jicheng, Zhu Xirui, Yu Jing

Author information +

文章历史 +

摘要

由于风力发电的随机性和不确定性使其短期功率的预测工作十分困难,而神经网络模型依靠其强大的自学习能力在风电功率预测领域有着广泛的应用。但神经网络预测精度受初始权重影响较大,且易出现过拟合的问题。为此构建一种基于改进鲸鱼算法和模拟退火组合优化的Elman神经网络短期风电功率预测模型,模型首先利用改进鲸鱼算法结合模拟退火策略获得高质量神经网络初始权值,接着引入正则化损失函数防止其过拟合,最后以西班牙瓦伦西亚某风电场陆上短期风电功率为研究对象,将该算法与BP、LSTM、Elman、WOA-Elman、IWOA-Elman 5种神经网络算法进行算法性能测试对比,结果表明IWOA-SA-Elman神经网络模型预测误差最小,验证了该算法的合理性和有效性。

Abstract

Due to the randomness and uncertainty of wind power generation, it is very difficult to predict its short-term power, and the neural network model has a wide range of applications in the field of wind power prediction relying on its powerful self-learning ability. However, the prediction accuracy of neural network is greatly affected by the initial weight, and prone to over-fitting problems. In this paper, an Elman neural network short-term wind power prediction model based on improved whale optimization algorithm （IWOA） and simulated annealing （SA） combined optimization is constructed. Firstly, the improved whale optimization algorithm combined with simulated annealing strategy is used to obtain the initial weights of high-quality neural network, and then the regularization loss function is introduced to prevent overfitting. Finally, the short-term wind power of a wind power plant in Valencia, Spain is taken as the research object. The algorithm is compared with back propagation （BP）, long short-term memory （LSTM）, Elman, WOA-Elman and IWOA-Elman neural network algorithms. The results show that the prediction error of IWOA-SA-Elman neural network model is the smallest, which verifies the rationality and effectiveness of the algorithm.

导出引用

刘吉成, 朱玺瑞, 于晶. 基于IWOA-SA-Elman神经网络的短期风电功率预测[J]. 太阳能学报. 2024, 45(1): 143-150 https://doi.org/10.19912/j.0254-0096.tynxb.2022-1423

Liu Jicheng, Zhu Xirui, Yu Jing. SHORT-TERM WIND POWER PREDICTION BASED ON IWOA-SA-ELMAN NEURAL NETWORK[J]. Acta Energiae Solaris Sinica. 2024, 45(1): 143-150 https://doi.org/10.19912/j.0254-0096.tynxb.2022-1423

中图分类号： TM614

参考文献

[1] 周孝信, 陈树勇, 鲁宗相, 等. 能源转型中我国新一代电力系统的技术特征[J]. 中国电机工程学报, 2018, 38(7): 1893-1904, 2205.
ZHOU X X, CHEN S Y, LU Z X, et al.Technology features of the new generation power system in China[J]. Proceedings of the CSEE, 2018, 38(7): 1893-1904, 2205.
[2] 程海花, 寇宇, 周琳, 等. 面向清洁能源消纳的流域型风光水多能互补基地协同优化调度模式与机制[J]. 电力自动化设备, 2019, 39(10): 61-70.
CHENG H H, KOU Y, ZHOU L, et al.Collaborative optimal dispatching mode and mechanism of watershed-type wind-solar-water multi-energy complementary bases for clean energy absorption[J]. Electric power automation equipment, 2019, 39(10): 61-70.
[3] 王钊, 王伟胜, 刘纯, 等. 风电功率的特征近邻搜索概率预测方法[J]. 电网技术, 2022, 46(3): 880-887.
WANG Z, WANG W S, LIU C, et al.Probabilistic forecast of wind power based on nearest neighbor feature searching[J]. Power system technology, 2022, 46(3): 880-887.
[4] 段学伟, 王瑞琪, 王昭鑫, 等. 风速及风电功率预测研究综述[J]. 山东电力技术, 2015, 42(7): 26-32.
DUAN X W, WANG R Q, WANG Z X, et al.Review of wind speed and wind power prediction methods[J]. Shandong electric power, 2015, 42(7): 26-32.
[5] TASCIKARAOGLU A, UZUNOGLU M.A review of combined approaches for prediction of short-term wind speed and power[J]. Renewable and sustainable energy reviews, 2014, 34: 243-254.
[6] 张翼飞, 皮子扬, 朱瑞琪, 等. 基于WOA-BiLSTM神经网络的风力发电预测[J]. 电工技术, 2022(10): 28-31.
ZHANG Y F, PI Z Y, ZHU R Q, et al.Wind power prediction based on WOA-BiLSTM neural network[J]. Electric engineering, 2022(10): 28-31.
[7] 刘辉, 凌宁青, 罗志强, 等. 基于TCN-LSTM和气象相似日集的电网短期负荷预测方法[J]. 智慧电力, 2022, 50(8): 30-37.
LIU H, LING N Q, LUO Z Q, et al.Power grid short-term load forecasting method based on TCN-LSTM and meteorological similar day sets[J]. Smart power, 2022, 50(8): 30-37.
[8] JALALI S M J, AHMADIAN S, KHODAYAR M, et al. An advanced short-term wind power forecasting framework based on the optimized deep neural network models[J]. International journal of electrical power & energy systems, 2022, 141: 108143.
[9] 高鹭, 孔繁苗, 张飞, 等. 基于IPSO-BiLSTM-AM模型的超短期风电功率预测方法[J]. 智慧电力, 2022, 50(4): 27-34.
GAO L, KONG F M, ZHANG F, et al.Ultra short-term wind power prediction method based on IPSO-BiLSTM-AM model[J]. Smart power, 2022, 50(4): 27-34.
[10] 盛四清, 金航, 刘长荣. 基于VMD-WSGRU的风电场发电功率中短期及短期预测[J]. 电网技术, 2022, 46(3): 897-904.
SHENG S Q, JIN H, LIU C R.Short-term and mid-short-term wind power forecasting based on VMD-WSGRU[J]. Power system technology, 2022, 46(3): 897-904.
[11] 郭杰, 苏路, 朱海浪, 等. 基于IBAS-BP神经网络的短期风电功率预测[J]. 信息技术, 2021, 45(10): 38-43.
GUO J, SU L, ZHU H L, et al.Short-term wind power prediction based on IBAS-BP neural network[J]. Information technology, 2021, 45(10): 38-43.
[12] FENG Q M, QIAN S P.Research on power load forecasting model of economic development zone based on neural network[J]. Energy reports, 2021, 7: 1447-1452.
[13] 孙子涵, 姜志海, 刘延龙, 等. 基于小波变换和优化的Elman神经网络的光伏功率预测[J]. 电网与清洁能源, 2022, 38(6): 98-103, 112.
SUN Z H, JIANG Z H, LIU Y L, et al.Photovoltaic power prediction based on wavelet transform and optimized Elman neural network[J]. Power system and clean energy, 2022, 38(6): 98-103, 112.
[14] 巩世兵, 沈海斌. 仿生策略优化的鲸鱼算法研究[J]. 传感器与微系统, 2017, 36(12): 10-12.
GONG S B, SHEN H B.Study of whale algorithm for biomimetic strategy optimization[J]. Transducer and microsystem technologies, 2017, 36(12): 10-12.
[15] 吴丁杰, 温立书. 基于鲸鱼算法优化Elman神经网络的房价预测[J]. 长江信息通信, 2021, 34(10): 12-14.
WU D J, WEN L S.House-price forecast optimization of Elman neural network based on whale optimization algorithm[J]. Changjiang information & communications, 2021, 34(10): 12-14.
[16] 郑光耀, 张慧华, 韩尚宇, 等. 裂纹反演分析的NMM-Elman神经网络协同方法[J]. 应用力学学报, 2022, 39(4): 673-682.
ZHENG G Y, ZHANG H H, HAN S Y, et al.Crack inverse analysis with the NMM-Elman neural network collaborative method[J]. Chinese journal of applied mechanics, 2022, 39(4): 673-682.
[17] 姜旭初, 许宇澄, 宋超. 短期风力发电负荷预测的新方法[J]. 北京师范大学学报(自然科学版), 2022, 58(1): 39-46.
JIANG X C, XU Y C, SONG C.A new method to predict short-term load of wind power[J]. Journal of Beijing Normal University (natural science), 2022, 58(1): 39-46.
[18] 何建强, 张玉萍, 滕志军. 基于K-means和改进KNN算法的风电功率短期预测系统[J]. 计算机测量与控制, 2022, 30(5): 156-162.
HE J Q, ZHANG Y P, TENG Z J.Wind power short-term forecasting system based on K-means and improved KNN algorithm[J]. Computer measurement & control, 2022, 30(5): 156-162.
[19] 吕国豪, 罗四维, 黄雅平, 等. 基于卷积神经网络的正则化方法[J]. 计算机研究与发展, 2014, 51(9): 1891-1900.
LYU G H, LUO S W, HUANG Y P, et al.A novel regularization method based on convolution neural network[J]. Journal of computer research and development, 2014, 51(9): 1891-1900.