Deep convolution IT2 fuzzy system with adaptive variable selection method for ultra-short-term wind speed prediction.

Changes in wind speed directly affect the output of wind turbines, so in power system planning, accurate prediction of future wind speed can help adjust the stability and reliability of power networks. In order to solve the problem that unknown wind speed prediction systems are unable to select features autonomously and to alleviate the insufficient prediction accuracy of single interval type 2 fuzzy models, this paper proposes a new deep convolutional interval type 2 fuzzy system (DCIT2FS) based on adaptive feature selection. First off, type 2 fuzzy sets are employed in the construction of two stage interval type 2 fuzzy curves and surfaces to address the issue of dimensionality explosion brought on by complex system modelling. By removing inaccurate and redundant information, this strategy achieves automated screening of key input aspects of an unknown system. Second, the model's interpretability is improved by the addition of the interval type 2 fuzzy system to the deep convolutional structure, which also addresses the issue that a single interval type 2 fuzzy model cannot achieve the required level of prediction accuracy. Thirdly, the incorporation of the feature pyramid structure boosts the mining of underlying data to increase the model's capacity to predict outcomes accurately while simultaneously strengthening its resistance to interference. Finally, model prediction performance tests are completed using meteorological feature data for both time periods, and generalisability tests are conducted using the benchmark dataset. The experimental results show that the prediction accuracy of the model proposed in this paper is improved by at least 7.70% and 1.23% in two wind speed prediction experiments compared to other models. • A new deep convolutional interval type 2 fuzzy prediction model is designed. • The feature pyramid structure is added to DCIT2FS in an innovative way. • A method TSIT2FCS is designed to realise the automatic selection of input features. • The hybrid model TSIT2FCS-DCIT2FS is successfully applied in wind speed prediction. [ABSTRACT FROM AUTHOR]