In order to improve the accuracy of PV power forecast
a short-term PV power forecast model is proposed
which takes into account the multivariate meteorological information from nearby power stations and improves the combined neural network. Firstly
considering the correlation between geographical factors and climatic conditions among adjacent distributed photovoltaic power stations
the grey correlation method is used to determine the main influencing factors of the power stations to be predicted
and the key features of multivariate meteorological information are constituted as the input sequence of the prediction model. Secondly
combining the advantages of the temporal convolutional network (TCN) for efficient extraction of input sequence information and bidirectional gated recurrent unit (BiGRU) for bidirectional data learning
a combined prediction model of TCN-BiGRU is built
and the improved Grey Wolf optimization algorithm (IGWO) is used to optimize the hyperparameters of BiGRU
so as to achieve high-precision prediction of photovoltaic power generation. Finally
the proposed model is verified by the measured data and compared with the similar methods. The results show that combined with multivariate meteorological information
the prediction model can effectively improve the prediction accuracy of power generation in different types of weather throughout the year
and compared with other prediction models
the proposed method can also show good prediction accuracy even when the climate conditions change drastically or randomly.
ZHOU Y, ZHOU N R, GONG L H, et al.Prediction of photovoltaic power output based on similar day analysis, genetic algorithm and extreme learning machine[J]. Energy, 2020, 204: 117894.
STUL M, STUL K, LEENDERS R, et al.Development of a SVM prediction model to optimize the energy consumption of industrial installations by detecting and classifying errors at an early S[J]. International journal of mechanical engineering and robotics research, 2017, 62(2): 108-113.
YANG T T, SUN X W, YANG H R, et al.Integrated thermal error modeling and compensation of machine tool feed system using subtraction-average-based optimizer-based CNN-GRU neural network[J]. The international journal of advanced manufacturing technology, 2024, 131(12): 6075-6089.