Answers are grounded in this paper and cite their sources.
With the continuous progress of people's living standard, electricity has been applied to every aspect of people's daily life, and people's demand for electricity is also growing. Photovoltaic power generation, as a kind of power generation method, has been developing rapidly in recent years both domestically and internationally, and has made great breakthroughs. However, PV power generation is subject to fluctuations due to weather and other factors, and how to accurately forecast PV power generation is an issue that needs to be considered. In this study, BiTCN-DCMA model based on bidirectional temporal convolutional neural network is proposed for the prediction of photovoltaic power generation. BiTCN-DCMA uses dynamic convolution for forward and backward optimization to achieve features that can adapt to different scales; the bi-directional fused feature information enters the attention layer, which consists of a bi-directional long and short-term memory network and a multi-head attention mechanism, and the attention layer is able to carry out the contextual data that captures the complex interactions between different locations in the sequence, and these optimization methods strengthen the linear layer's prediction of power generation Accuracy. The results show that the root mean square error (RMSE) of BiTCN-DCMA is reduced by 75.81% and the correlation coefficient R2 is improved by 12.50% compared to the Transformer model, showing good prediction accuracy and stability.
No takes yet. Share an insight, caveat, or question.
A 2024 study studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: