BiLSTM-PINN-based wind turbine power prediction architecture and anomaly data identification

With the accelerated transformation of the global energy structure, wind power, as a clean and renewable energy source, has attracted increasing attention. Its efficient utilization and sustainable development heavily rely on accurate power prediction. However, traditional forecasting methods face significant challenges due to factors such as turbine health conditions, environmental fluctuations, and data anomalies. To address these issues, this paper proposes a physics-informed bidirectional long short-term memory network (BiLSTM-PINN) based prediction framework. First, a method combining the Anisotropic Local Outlier Factor (A-LOF) with a Multilayer Perceptron (MLP), termed A-LOF-MLP, is employed to clean the raw data, effectively identifying and removing outliers and anomalous clustered data. Subsequently, based on the cleaned data, a Grey Relational Analysis-Long Short-Term Memory (GRA-LSTM) algorithm is used to assess the health status of the wind turbine. Finally, incorporating both health assessment results and physical constraints, the BiLSTM-PINN model is applied to achieve accurate wind power prediction. Experimental results demonstrate that the proposed A-LOF-MLP data cleaning method significantly improves data quality, and compared to existing approaches, the proposed framework exhibits superior performance in both prediction accuracy and robustness against disturbances.