为提高光伏功率预测的准确性和稳定性,提出一种基于双层分解和改进多目标浣熊优化算法（AMOCOA）的BiLSTM超短期光伏功率预测模型。其中,双层分解将改进自适应白噪声的完全集合经验模态分解（ICCEMDAN）与变分模态分解（VMD）结合,可充分挖掘高频信号中的信息。改进多目标浣熊优化算法（AMOCOA）通过引入自适应区域搜索策略与多项式变异算子提升了算法收敛性与多样性。首先,利用ICEEMDAN将历史光伏功率序列分解为多个分量,其次将高频分量利用变分模态进一步分解,得到周期性分量。然后通过AMOCOA对BiLSTM参数进行优化并建立各子序列最优AMOCOA-BiLSTM模型。最后对子序列进行重构得到最终预测结果。通过实际数据对模型进行验证,结果表明,阴天天气下相比BiLSTM,所提模型的均方根误差下降了51.56%,平均绝对误差下降了68.75%,稳定指标下降了50.74%,表现出更好的预测准确性与稳定性。
Abstract
To improve the accuracy and stability of ultra-short-term photovoltaic （PV） power prediction, the BiLSTM model based on dual-layer decomposition and an improved multi-objective coati optimization algorithm （AMOCOA） is proposed. The dual-layer decomposition combines improved complete ensemble empirical mode decomposition with adaptive noise （ICEEMDAN） and variational mode decomposition （VMD） to fully extract information from high-frequency signals. AMOCOA enhances algorithm convergence and diversity by introducing an adaptive region search strategy and polynomial mutation operator. First, ICEEMDAN is used to decompose the historical PV power series into multiple components, and the high-frequency components are further decomposed using VMD to extract periodic components. Then, AMOCOA is applied to optimize the BiLSTM parameters, building the optimal AMOCOA-BiLSTM model for each subseries. Finally, the subseries are reconstructed to obtain the final prediction results. The experimental results show that, under cloudy weather scenarios, compared to the BiLSTM, the root-mean-square error of the proposed model decreased by 51.56%, the average absolute error decreased by 68.75%, and the stability index decreased by 50.74%, showing better prediction accuracy and stability.
关键词
多目标优化 /
光伏功率 /
预测模型 /
浣熊优化算法 /
双层分解
Key words
multiobjective optimization /
photovoltaic power /
prediction models /
coati optimization algorithm /
dual-layer decomposition
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] PILLOT B, MUSELLI M, POGGI P, et al.Historical trends in global energy policy and renewable power system issues in Sub-Saharan Africa: the case of solar PV[J]. Energy policy, 2019, 127: 113-124.
[2] WANG H Z, LEI Z X, ZHANG X, et al.A review of deep learning for renewable energy forecasting[J]. Energy conversion and management, 2019, 198: 111799.
[3] 贾凌云, 云斯宁, 赵泽妮, 等. 神经网络短期光伏发电预测的应用研究进展[J]. 太阳能学报, 2022, 43(12): 88-97.
JIA L Y., YUN S N, ZHAO Z N, et al.Recent progress of short-term forecasting of photovoltaic generation based on artificial neural networks[J]. Acta energiae solaris sinica, 2022, 43(12): 88-97.
[4] BARBIERI F, RAJAKARUNA S, GHOSH A.Very short-term photovoltaic power forecasting with cloud modeling: a review[J]. Renewable and sustainable energy reviews, 2017, 75: 242-263.
[5] LORENZ E, SCHEIDSTEGER T, HURKA J, et al.Regional PV power prediction for improved grid integration[J]. Progress in Photovoltaics: Research and Applications, 2011, 19(7): 757-771.
[6] 董存, 王铮, 白捷予, 等. 光伏发电功率超短期预测方法综述[J]. 高电压技术, 2023, 49(7): 2938-2951.
DONG C, WANG Z, BAI J Y, et al.Review of ultra-short-term forecasting methods for photovoltaic power generation[J]. High voltage engineering, 2023, 49(7): 2938-2951.
[7] ZHANG M Y, HAN Y, WANG C Y, et al.Ultra-short-term photovoltaic power prediction based on similar day clustering and temporal convolutional network with bidirectional long short-term memory model: a case study using DKASC data[J]. Applied energy, 2024, 375: 124085.
[8] SU Z Y, GU S Y, WANG J, et al.Improving ultra-short-term photovoltaic power forecasting using advanced deep-learning approach[J]. Measurement, 2025, 239: 115405.
[9] HU K Y, CAO S H, WANG L D, et al.A new ultra-short-term photovoltaic power prediction model based on ground-based cloud images[J]. Journal of cleaner production, 2018, 200: 731-745.
[10] ZHOU H X, WANG J, OUYANG F L, et al.A two-stage method for ultra-short-term PV power forecasting based on data-driven[J]. IEEE access, 2023, 11: 41175-41189.
[11] 姜建国, 杨效岩, 毕洪波. 基于VMD-FE-CNN-BiLSTM的短期光伏发电功率预测[J].太阳能学报, 2024, 45(7): 462-473.
JIANG J G, YANG X Y, BI H B.Photovoltaic power forecasting method based on VMD-FE-CNN-BiLSTM[J]. Acta energiae solaris sinica, 2024, 45(7): 462-473.
[12] 郭威, 孙胜博, 陶鹏, 等. 基于多元变分模态分解和混合深度神经网络的短期光伏功率预测[J]. 太阳能学报, 2024, 45(4): 489-499.
GUO W, SUN S B, TAO P, et al.Short-term photovoltaic power forecasting based on multivariate variational mode decomposition and hybrid deep neural network[J]. Acta energiae solaris sinica, 2024, 45(4): 489-499.
[13] 张程, 林谷青, 匡宇. 基于MEEMD-QUATRE-BILSTM的短期光伏出力区间预测[J]. 太阳能学报, 2023, 44(11): 40-54.
ZHANG C, LIN GU Q, KUANG Y, et al.Short-term PV power output interval prediction based on MEEMD-QUATRE-BILSTM[J]. Acta energiae solaris sinica, 2023, 44(11): 40-54.
[14] 臧海祥, 张越, 程礼临, 等. 基于ICEEMDAN-LSTM和残差注意力的短期太阳辐照度预测[J]. 太阳能学报, 2023, 44(12): 175-181.
ZANG H X, ZHANG Y, CHENG L L, et al.Short-term solar radiation forcasting based on ICEEMDAN-LSTM and residual attention[J]. Acta energiae solaris sinica, 2023, 44(12): 175-181.
[15] HUANG N E, SHEN Z, LONG S R, et al.The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis[J]. Proceedings of the Royal Society of London Series A: mathematical, physical and engineering Sciences, 1998, 454(1971): 903-995.
[16] DEHGHANI M, MONTAZERI Z, TROJOVSKÁ E, et al.Coati Optimization Algorithm: a new bio-inspired metaheuristic algorithm for solving optimization problems[J]. Knowledge-based systems, 2023, 259: 110011.
[17] ABED-ALGUNI B H, PAUL D. Island-based cuckoo search with elite opposition-based learning and multiple mutation methods for solving optimization problems[J]. Soft computing, 2022, 26(7): 3293-3312.
[18] ZHANG D D, CHEN B A, ZHU H Y, et al.Short-term wind power prediction based on two-layer decomposition and BiTCN-BiLSTM-attention model[J]. Energy, 2023, 285: 128762.
[19] YE J H, XIE L R, MA L, et al.A novel hybrid model based on Laguerre polynomial and multi-objective Runge-Kutta algorithm for wind power forecasting[J]. International journal of electrical power & energy systems, 2023, 146: 108726.
[20] XIA Y R, WANG J Z, ZHANG Z Y, et al.Short-term PV power forecasting based on time series expansion and high-order fuzzy cognitive maps[J]. Applied soft computing, 2023, 135: 110037.
[21] SEDGWICK P.Pearson’s correlation coefficient[J]. BMJ, 2012, 345: e4483.
[22] SIBTAIN M, LI X S, SALEEM S, et al.A multistage hybrid model ICEEMDAN-SE-VMD-RDPG for a multivariate solar irradiance forecasting[J]. IEEE access, 2021, 9: 37334-37363.
[23] DEB K, JAIN H.An evolutionary many-objective optimization algorithm using reference-point-based nondominated sorting approach, part I: solving problems with box constraints[J]. IEEE transactions on evolutionary computation, 2014, 18(4): 577-601.
[24] MIRJALILI S, SAREMI S, MIRJALILI S M, et al.Multi-objective grey wolf optimizer: a novel algorithm for multi-criterion optimization[J]. Expert systems with applications, 2016, 47: 106-119.
[25] WANG J Z, DU P, NIU T, et al.A novel hybrid system based on a new proposed algorithm: multi-objective whale optimization algorithm for wind speed forecasting[J]. Applied energy, 2017, 208: 344-360.
基金
新疆重点研发计划（2022B01020-4); 国家自然科学基金（52266017）; 新疆天山英才科技创新团队项（2023TSYCTD0009）; 新疆自治区研究生教育创新计划（XJ2024G099; XJ2023G052）
PDF(1556 KB)
