Abstract: Accurate forecasting of wind power is crucial for ensuring the reliable operation of the electrical grid. Due to the impact of various factors, wind power forecasting presents a significant challenge. This paper presents the model that integrates Osprey and adaptive T-distribution dung beetle algorithm for optimizing a convolutional neural network. The CNN-BiLSTM-Attention model combines bidirectional long short-term memory neural networks with an attention mechanism, thereby improving the accuracy of wind power generation predictions. The original data is subjected to Variational Mode Decomposition (VMD) for analysis, taking into account the fluctuations in wind power across different periods. The BiLSTM network with short-term memory processes time-series wind power data, yielding an optimal predictive performance. The integration of the osprey algorithm and adaptive T-distribution within the Dung Beetle Optimization Algorithm was utilized to optimize the hyperparameters of the CNN-BiLSTM-Attention model, thereby enhancing its predictive performance. To assess the efficacy of the CNN-BiLSTM-Attention algorithm, enhanced by Ospreys and adaptive T-distributed dung beetle algorithm, we conducted experiments using the CEC2021 benchmark function. The integrated Osprey and adaptive T-distribution Dung Beetle algorithm has excellent global optimization performance when dealing with complex optimization problems. The fusion of Osprey and the adaptive T-distribution Dung beetle algorithm optimized the CNN-BiLSTM-Attention algorithm as well as other optimization algorithms for ablation experiments. The results show that the improved algorithm performs well in predicting wind power. The experimental findings suggest that the model’s predictive efficiency has enhanced by a minimum of 17.74%.

Key words: Convolutional neural network')">Convolutional neural network, Bidirectional long term memory, Dung beetle optimization, IntegratedOsprey and adaptive T-distribution