Abstract
With the continuous optimization of energy structures, wind power generation has become the dominant new energy source. The strong random fluctuation of natural wind will bring challenges to power system dispatching, so it is necessary to predict wind power. In order to improve the short-term prediction accuracy of regional wind power, this paper proposes a new combination prediction model based on convolutional neural network (CNN) and similar days analysis. Firstly, the least square fitting and batch normalization (BN) are used to preprocess the data, and then the recent historical wind power data set for CNN is established. Secondly, the Pearson correlation coefficient and cosine similarity combination method are utilized to find similar days in the long-term data set, and the prediction model based on similar days is constructed by the weighting method. Finally, based on the particle swarm optimization (PSO) method, a combined forecasting model is established. The results show that the combined model can accurately predict the future short-term wind power curve, and the prediction accuracy is improved to different extents compared to a single method.
Highlights
In recent years, the new energy input, dominated by wind power generation, is increasing rapidly.The strong volatility and randomness of natural wind make it difficult to accurately predict wind power, which brings new problems for the safe and stable operation of power grids [1,2]
Two hidden layers in the Gated Recurrent Unit network were used in Reference [10] to forecast the wind power, and the results show that the proposed model has higher prediction accuracy than the Autoregressive moving average (ARMA) model and the Long short-term memory network (LSTM) model
This paper further studies the influence of combined weights on multi model prediction methods, and proposes a combined optimization prediction model of regional wind power based on convolutional neural network (CNN) and similar days
Summary
The new energy input, dominated by wind power generation, is increasing rapidly. The work in Reference [15] used CNN to extract information from input data and integrated the Light Gradient Boosting Machine (LightGBM) algorithm, and the combination model has better performance in terms of the accuracy and efficiency of the single model. The regional prediction method emphasizes the regularity of the total wind power in the prediction process, which effectively reduces the amount of information needed and the interference of local random factors of individual wind farms It is of great practical significance for the power sector to optimize the power system dispatching, and reduces the rotating reserve capacity and the operating cost of the power system. This paper further studies the influence of combined weights on multi model prediction methods, and proposes a combined optimization prediction model of regional wind power based on CNN and similar days. The optimal combination weight is selected by the PSO algorithm to obtain the predicted results, which are analyzed by examples
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
