Photovoltaic power prediction method of deep neural network model fused with attention mechanism

Abstract

The invention discloses a photovoltaic power prediction method of a deep neural network model fused with an attention mechanism, and belongs to the technical field of renewable energy photovoltaic power. According to the method, firstly, a hybrid neural network based on a long-term and short-term memory neural network and a convolutional neural network is selected as a prediction model according to photovoltaic data characteristics, and an optimal connection mode is considered; and secondly, in order to shorten the calculation time of the model and more accurately extract high-quality featureinformation capable of being used for photovoltaic prediction, an attention mechanism model is added in the aspect of model feature extraction. Through comparison of different prediction models, the advantages of the proposed hybrid deep learning model are proved, and possibility is provided for selection of high-quality features through application of an attention mechanism model. The reasonablehybrid model mode can realize dual pursuits of high prediction precision and low calculation cost.

Description

technical field [0001] The invention belongs to the technical field of photovoltaic power forecasting of renewable energy sources, and in particular relates to a photovoltaic power forecasting method of a deep neural network model integrating an attention mechanism. Background technique [0002] Photovoltaic power generation is growing at a faster rate every year. Due to the randomness of light and the periodicity of day and night, photovoltaic power generation is naturally uncontrollable and is a typical fluctuating and intermittent power source. The output of photovoltaic power generation system is largely affected by factors such as weather and climate. These characteristics have brought new challenges to the power system after large-capacity / high-proportion photovoltaics are connected to the grid, such as increasing the difficulty and complexity of grid scheduling. Forecasting photovoltaic power generation has become one of the key basic technologies to improve the qua...

AI Technical Summary

Problems solved by technology

However, for traditional neural networks, too much input data, the number of hidden layers, and the number of nodes in each hidden layer are likely to cause problems such as over-fitting, gradient disappearance, and explosion in network training.

Images