基于SGMD-Transformer-BiLSTM组合模型的 超短期风电功率预测

打开文本图片集

中图分类号：TM614 文献标志码：A

SGMD-Transformer-BiLSTM hybrid model for ultra-short-term wind power forecasting

TANG Jie，DUAN Zhu'ao ， SHAO Wu

（1.Hunan Provincial Key Laboratory of Grids Operation and Control on Multi-Power Sources Area，Shaoyang 422OoO，China;2. School of Electrical Engineering，Shaoyang University， Shaoyang 422000，China）

Abstract： To address low forecasting accuracy caused by fluctuations and non-stationarity in wind power sequences，this study proposes a hybrid forecasting model integrating symplectic geometry mode decomposition （SGMD），Transformer architecture，and bidirectional long short-term memory （BiLSTM） networks. SGMD adaptively decomposes raw wind power data into distinct components，efectively separating high-frequency noise from low-frequency trends as model inputs.The Transformer-BiLSTM framework leverages multi-head attention to capture global interdependencies among components while utilizing bidirectional temporal modeling for local feature extraction.Final forecastsare reconstructed through component integration.Simulations demonstrate significantly enhanced accuracyand stability in ultra-short-term forecasting，providing reliable technical support for the secure operation of wind-dominant power systems.

Key words： wind power forecasting； symplectic geometry mode decomposition; Transformer; bidirectional long short-term memory

为实现“双碳”目标，推动煤炭清洁高效利用，我国现在大力发展风电、光伏等可再生能源。（剩余8831字）