Page 48 - 《中国电力》2026年第5期
P. 48
2026 年 第 59 卷
theory[J]. Electric Power Construction, 2025, 46(4): 126–136. transform[J]. Smart Power, 2023, 51(7): 39–43, 50.
[6] 陈 景 文 , 黄 羽 倩 , 刘 耀 先 , 等 . 基 于 复 合 因 子 构 造 的 KAN- [14] TAN Z Q, ZHANG J, HE Y, et al. Short-term load forecasting based
BiLSTM 电力负荷预测方法 [J]. 中国电力, 2025, 58(12): 178–189, on integration of SVR and stacking[J]. IEEE Access, 2020, 8:
198. 227719–227728.
CHEN Jingwen, HUANG Yuqian, LIU Yaoxian, et al. A KAN- [15] 于润泽, 窦震海, 张志一, 等. 基于二次分解重构与多任务学习的综
BiLSTM-based power load forecasting method utilizing composite 合 能 源 系 统 多 元 负 荷 短 期 预 测 [J]. 电 力 建 设 , 2024, 45(12):
factor construction[J]. Electric Power, 2025, 58(12): 178–189, 198. 149–161.
[7] 于 多 , 曹 燚 , 王 海 荣 , 等 . 基 于 ICEEMDAN-PE 和 IDBO- YU Runze, DOU Zhenhai, ZHANG Zhiyi, et al. Multi-energy load
Informer 组合模型的短期负荷预测 [J]. 中国电力, 2025, 58(6): forecasting of integrated energy system based on secondary
19–32. decomposition-reconstruction and multi-task learning[J]. Electric
YU Duo, CAO Yi, WANG Hairong, et al. Short-term load Power Construction, 2024, 45(12): 149–161.
forecasting based on a combined ICEEMDAN-PE and IDBO- [16] 邵必林, 纪丹阳. 基于 VMD-SE 的电力负荷分量的多特征短期预
informer model[J]. Electric Power, 2025, 58(6): 19–32. 测 [J]. 中国电力, 2024, 57(4): 162–170.
[8] 杨佳泽, 王灿, 王增平. 新型电力系统背景下的智能负荷预测算法 SHAO Bilin, JI Danyang. Multi-feature short-term prediction of
研究综述 [J]. 华北电力大学学报 (自然科学版), 2025, 52(3): power load components based on VMD-SE[J]. Electric Power, 2024,
54–67. 57(4): 162–170.
YANG Jiaze, WANG Can, WANG Zengping. Review on intelligent [17] ZHANG M F, YU Z T, XU Z H. Short-term load forecasting using
load forecasting algorithms for the new-type power system[J]. recurrent neural networks with input attention mechanism and hidden
Journal of North China Electric Power University (Natural Science connection mechanism[J]. IEEE Access, 2020, 8: 186514–186529.
Edition), 2025, 52(3): 54–67. [18] TANG X L, DAI Y Y, LIU Q, et al. Application of bidirectional
[9] 梁宏涛, 刘红菊, 李静, 等. 基于机器学习的短期负荷预测算法综 recurrent neural network combined with deep belief network in short-
述 [J]. 计算机系统应用, 2022, 31(10): 25–35. term load forecasting[J]. IEEE Access, 2019, 7: 160660–160670.
LIANG Hongtao, LIU Hongju, LI Jing, et al. Survey on short-term [19] 陈媛, 段文献, 何怡刚, 等. 带降噪自编码器和门控递归混合神经网
load forecasting algorithm based on machine learning[J]. Computer 络的电池健康状态估算 [J]. 电工技术学报, 2024, 39(24): 7933–
Systems & Applications, 2022, 31(10): 25–35. 7949.
[10] 李志军, 徐博, 张家安, 等. 基于 TD3 可变长度时间窗口最优加权 CHEN Yuan, DUAN Wenxian, HE Yigang, et al. State of health
的短期负荷预测策略 [J]. 电力建设, 2024, 45(6): 140–148. estimation of lithium ion battery based on denoising autoencoder-
LI Zhijun, XU Bo, ZHANG Jia'an, et al. Short-term load optimal gated recurrent unit[J]. Transactions of China Electrotechnical
weighted forecasting strategy based on TD3 variable length time Society, 2024, 39(24): 7933–7949.
window[J]. Electric Power Construction, 2024, 45(6): 140–148. [20] AURANGZEB K, ALHUSSEIN M, JAVAID K, et al. A pyramid-
[11] CHEN S, LIN R H, ZENG W. Short-term load forecasting method CNN based deep learning model for power load forecasting of
based on ARIMA and LSTM[C]//2022 IEEE 22nd International similar-profile energy customers based on clustering[J]. IEEE
Conference on Communication Technology (ICCT). Nanjing, China. Access, 2021, 9: 14992–15003.
IEEE, 2023: 1913–1917. [21] RUBASINGHE O, ZHANG X N, CHAU T K, et al. A novel
[12] AL AMIN M A, HOQUE M A. Comparison of ARIMA and SVM sequence to sequence data modelling based CNN-LSTM algorithm
for short-term load forecasting[C]//2019 9th Annual Information for three years ahead monthly peak load forecasting[J]. IEEE
Technology, Electromechanical Engineering and Microelectronics Transactions on Power Systems, 2024, 39(1): 1932–1947.
Conference (IEMECON). Jaipur, India. IEEE, 2019: 1–6. [22] 葛众, 隆交凤, 李健, 等. 结合 CNN 与软共享机制的综合能源系统
[13] 田书欣, 韩雪. 基于正交小波变换的 LSTM-ARIMA 海上风速组合 多元负荷预测 [J]. 电力建设, 2024, 45(12): 162–173.
预测模型 [J]. 智慧电力, 2023, 51(7): 39–43, 50. GE Zhong, LONG Jiaofeng, LI Jian, et al. Multivariate load
TIAN Shuxin, HAN Xue. LSTM-ARIMA offshore wind speed forecasting of integrated energy systems based on convolutional
combined prediction model based on orthogonal wavelet neural network and soft sharing mechanism[J]. Electric Power
44

