Page 186 - 《中国电力》2026年第5期

2026 年 第 59 卷

modeling[J]. Shandong Electric Power, 2025, 52(2): 32–45. power based on long short-term memory network and light gradient
[22] BARAN S, LERCH S. Mixture EMOS model for calibrating boosting machine[J]. Hunan Electric Power, 2023, 43(6): 68–75.
ensemble forecasts of wind speed[J]. Environmetrics, 2016, 27(2): [31] ANGELIS D, SOFOS F, KARAKASIDIS T E. Artificial intelligence
116–130. in physical sciences: symbolic regression trends and perspectives[J].
[23] WANG C, ZHANG S H, LIAO P, et al. Wind speed forecasting Archives of Computational Methods in Engineering, 2023, 30(6):
based on hybrid model with model selection and wind energy 3845–3865.
conversion[J]. Renewable Energy, 2022, 196: 763–781. [32] 张伟伟, 王旭, 寇家庆. 面向流体力学的多范式融合研究展望 [J].
[24] FAN H, ZHANG X M, MEI S W, et al. A Markov regime switching 力学进展, 2023, 53(2): 433–467.
ZHANG Weiwei, WANG Xu, KOU Jiaqing. Prospects of multi-
model for ultra-short-term wind power prediction based on toeplitz
paradigm fusion methods for fluid mechanics research[J]. Advances
inverse covariance clustering[J]. Frontiers in Energy Research, 2021,
in Mechanics, 2023, 53(2): 433–467.
9: 638797.
[33] WANG S, LI B, LI G Z, et al. Short-term wind power prediction
[25] RAISSI M, PERDIKARIS P, KARNIADAKIS G E. Physics-
based on multidimensional data cleaning and feature
informed neural networks: a deep learning framework for solving
reconfiguration[J]. Applied Energy, 2021, 292: 116851.
forward and inverse problems involving nonlinear partial differential
[34] CAMAL S, GIRARD R, FORTIN M, et al. A conditional and
equations[J]. Journal of Computational Physics, 2019, 378: 686–707.
regularized approach for large-scale spatiotemporal wind power
[26] KARNIADAKIS G E, KEVREKIDIS I G, LU L, et al. Physics-
forecasting[J]. Sustainable Energy Technologies and Assessments,
informed machine learning[J]. Nature Reviews Physics, 2021, 3(6):
2024, 65: 103743.
422–440.
[35] BARJASTEH A, GHAFOURI S H, HASHEMI M. A hybrid model
[27] 袁飞, 夏德喜, 汪正军. 基于 SCADA 数据的风电机组群尾流效应
based on discrete wavelet transform (DWT) and bidirectional
计算与验证研究 [J]. 智慧电力, 2023, 51(7): 23–30.
recurrent neural networks for wind speed prediction[J]. Engineering
YUAN Fei, XIA Dexi, WANG Zhengjun. Calculation and
Applications of Artificial Intelligence, 2024, 127: 107340.
verification of wake effect on wind turbine based on SCADA data[J].
作者简介：
Smart Power, 2023, 51(7): 23–30.
赵军（1991），男，工程师，通
[28] YANG X Y, ZHANG Y F, YANG Y W, et al. Deterministic and
信作者，从事新能源功率预测、储能
probabilistic wind power forecasting based on bi-level convolutional
运行研究，E-mail：18246153625@163.
neural network and particle swarm optimization[J]. Applied Sciences,
com；
2019, 9(9): 1794.
张世锋（1989），男，高级工程
[29] KENNEDY J, EBERHART R. Particle swarm optimization[C]//
师，从事新能源并网运行分析研究，
Proceedings of ICNN'95 - International Conference on Neural
E-mail：zhangshifeng4696@163.com；
Networks. Perth, WA, Australia. IEEE, 2002: 1942-1948.
宋金鸽（1996），女，助理工程师，从事新能源功率
[30] 李振海, 李钰炎, 易志高, 等. 基于长短时记忆网络和轻梯度增强机
预测研究，E-mail：songjinge0121@163.com。
的风电功率多步预测 [J]. 湖南电力, 2023, 43(6): 68–75.
LI Zhenhai, LI Yuyan, YI Zhigao, et al. Multi-step prediction of wind （责任编辑 杨彪）

182