南方电网技术2026，Vol.20Issue(2)：39-52,14.DOI:10.13648/j.cnki.issn1674-0629.2026.02.005
基于BiLSTM多算法混合神经网络模型的季节性等效惯量短期预测
Short-Term Prediction of Seasonal Equivalent Inertia Based on BiLSTM Multi-Algorithm Hybrid Neural Network Model
摘要
Abstract
The grid inertia magnitude measures the frequency stability of the system,and accurate prediction of the system inertia level in advance can avoid the risk caused by low inertia.To this end,a multi-algorithm hybrid neural network model based on modal decomposition and feature fusion for short-term prediction of system equivalent inertia is proposed.Firstly,an improved complete ensemble empirical mode decomposition with adaptive noise is used to decompose the inertia of four seasons,and a new sequence is obtained by reconstructing the new inertia based on the fine composite multi-scale fuzzy entropy of each decomposed component.Secondly,the minimum redundancy maximum relevance method is used to measure the correlation between different decomposition components and different features,and a subset of highly correlated and low redundancy features is filtered out.Finally,a bidirectional long-short-term memory network model based on Bayesian optimization algorithm is used to predict different components of different seasonal inertias,and the final prediction results are accumulated.Typical examples at home and abroad are selected for testing,which verify that the proposed method can effectively balance the prediction accuracy and prediction time,and solves the problem of seasonal differences affecting the prediction results of system inertia.关键词
短期预测/季节性特征/精细复合多尺度模糊熵/最小冗余最大相关性/双向长短期记忆网络/超参数寻优Key words
short-term prediction/seasonal characteristics/RCMFE/mRMR/BiLSTM/hyperparameter optimization分类
信息技术与安全科学引用本文复制引用
李世春,刘佳昌,刘蒙恩,杨跳,刘璐,李振兴..基于BiLSTM多算法混合神经网络模型的季节性等效惯量短期预测[J].南方电网技术,2026,20(2):39-52,14.基金项目
国家自然科学基金资助项目(52077120). Supported by the National Natural Science Foundation of China(52077120). （52077120）
