返回
Enhancing long short-term memory for electric load forecasting with multi-batch Bayesian optimization
DOI:10.1016/j.epsr.2025.112436.png)
摘要
En 中文
• 提出了一种通过多批次贝叶斯优化方法优化的增强型长短期记忆(Long Short-Term Memory)模型,旨在提高复杂特征融合场景下的短期电力负荷预测精度。
• 通过结合历史负荷和气象数据形成多变量时间序列输入,以捕捉实际运行条件。
• 模型架构得到改进,以更好地捕捉长期依赖关系,同时结合学习率衰减和早停机制的混合训练方案,以及优化后的超参数,提升了模型的稳定性、效率和鲁棒性。
• 来自不同季节的真实数据验证了模型性能。
Keyword:
Short-term load forecasting
Long short-term memory network
Bayesian optimization
Meteorological feature modelling
期刊
IF:
4.2
论文数:
1.2W
被引数:
2.2W
机构
引用论文
P. Cheng, X. Li, H. Sun, A LSTM prediction method optimized by improved sine and cosine algorithm, in: Y. Jia, W. Zhang, Y. Fu, Z. Yu, S. Zheng (Eds.) Proceedings of 2021 Chinese Intelligent Systems Conference, Springer Singapore, Singapore, 2022, pp. 413–422.P. Cheng, X. Li, H. Sun, 一种基于改进正弦余弦算法优化的LSTM预测方法,载于:Y. Jia, W. Zhang, Y. Fu, Z. Yu, S. Zheng 主编,《2021年中国智能系统会议论文集》,Springer Singapore出版,新加坡,2022年,第413-422页。
V. Bhogade, B. Nithya, Time series forecasting using transformer neural network, Int. J. Comput. Applicat., 46 (2024) 880–888.V. Bhogade, B. Nithya, 基于Transformer神经网络的时序预测,国际计算机应用杂志,46(2024)880–888。
M. Salami, M.R. Niakan, M. Hasani, Electricity load forecasting: a new hybrid model combining wavelet transform, genetic algorithm and LSTM models, in: 2021 International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME), 2021, pp. 1–6.M. Salami, M.R. Niakan, M. Hasani, 电力负荷预测:一种结合小波变换、遗传算法和LSTM模型的新型混合模型,发表于:2021年电气、计算机、通信和机电一体化工程国际会议(ICECCME),2021,第1-6页。
M. Li, D. Zhang, Y. Wang, Z. Li, Research on electricity load forecasting based on the GWO-LSTM algorithm, in: 2024 39th Youth Academic Annual Conference of Chinese Association of Automation (YAC), 2024, pp. 2041–2044.M. Li, D. Zhang, Y. Wang, Z. Li, 基于GWO-LSTM算法的电力负荷预测研究, 见: 2024年第39届中国自动化学会青年学术年会(YAC), 2024, 第2041–2044页。
A Novel Temporal Feature Selection Based LSTM Model for Electrical Short-Term Load Forecasting基于时序特征选择的LSTM短期电力负荷预测模型
IEEE ACCESS
IF3.6
Short-Term Electricity Load Forecasting Based on NeuralProphet and CNN-LSTM基于NeuralProphet和cnn-lstm的短期电力负荷预测
IEEE ACCESS
IF3.6
Social, environmental, and economic consequences of integrating renewable energies in the electricity sector: a review将可再生能源纳入电力部门的社会、环境和经济后果: 综述
M.R. Kabootarkhani, S.G. Kermani, A. Aldallal, M. Zounemat-Kermani, Forecasting river daily discharge using decision tree and time series methods, Proceed. Institut. Civil Engineers - Water Manag., 177 (2024) 294–307.M.R. Kabootarkhani, S.G. Kermani, A. Aldallal, M. Zounemat-Kermani, 使用决策树和时间序列方法预测河流日流量, Proceed. Institut. Civil Engineers - Water Manag., 177 (2024) 294–307.

