Hybrid CF-CNN-BiLSTM hypertuned by Bayesian optimization for thermal power generation and decarbonization forecasting

Accurate thermal power generation forecasting is essential for grid stability, operational cost reduction, and decarbonization (via CO 2 emission management), but is challenged by noisy, non-linear, temporally dependent data. In this paper, a novel hybrid model integrates a Christiano–Fitzgerald (CF) random walk filter to decompose time series into trend, cyclical, and irregular components for denoising. A convolutional neural network (CNN)-bidirectional long short-term memory (BiLSTM) architecture extracts spatial features and captures temporal dependencies. Bayesian Optimization automates hyperparameter tuning. The model is evaluated on real data from Brazil’s Candiota III coal-fired power plant. The proposed hypertuned CF-CNN-BiLSTM significantly outperformed 16 benchmarks. For 6-hour-ahead forecasting, the proposed model achieved root mean squared error (RMSE) of 1.42 × 1 0 − 3 , mean absolute percentage error (MAPE) of 0.207%, and mean squared logarithmic error (MSLE) of 1.11 × 1 0 − 6 . Statistical analysis over 50 runs confirmed robustness (low mean errors, narrow interquartile ranges), though occasional outliers occurred. The integration of CF filtering, CNN-BiLSTM, and Bayesian optimization delivers high-precision thermal generation forecasts, directly supporting emission reduction strategies. Future work should incorporate exogenous variables like weather and fuel prices. • CF filter enhances input data by reducing noise and isolating key trends. • CNN-BiLSTM captures both spatial patterns and temporal dependencies. • Bayesian optimization tunes hyperparameters for better model performance. • Achieved the lowest error among all evaluated forecasting models. • Forecasting thermal output also enables indirect CO 2 emissions estimation.