Hybrid Kernel LSSVM Model for Prediction of Short-Term Wind Speed

In order to improve the prediction accuracy of short-term wind speed, a model based on Cuckoo Search (CS) optimized hybrid kernel Least Squares Support Vector Machine (LSSVM) is proposed. The algorithm first preprocesses the signal by Empirical Wavelet Transform (EWT), and filters out a part of noise interference. Then, combining advantages of the two kinds of LSSVM kernel functions, a hybrid kernel function LSSVM with comprehensive performance is constructed. Finally, with the help of CS algorithm, four parameters of the hybrid kernel LSSVM model are optimized, and performance of the algorithm is further improved. The validation of real wind speed data shows that the model can predict short-term wind speed effectively.

[1]  Xu Fan,et al.  A combined model based on CEEMDAN and modified flower pollination algorithm for wind speed forecasting , 2017 .

[2]  Oscar Castillo,et al.  Cuckoo Search via Lévy Flights and a Comparison with Genetic Algorithms , 2015, Fuzzy Logic Augmentation of Nature-Inspired Optimization Metaheuristics.

[3]  Jianzhou Wang,et al.  A hybrid technique for short-term wind speed prediction , 2015 .

[4]  Dhanraj Chitara,et al.  Cuckoo Search Optimization algorithm for designing of multimachine Power System Stabilizer , 2016, 2016 IEEE 1st International Conference on Power Electronics, Intelligent Control and Energy Systems (ICPEICES).

[5]  V. Sowmya,et al.  Empirical Wavelet Transform for Multifocus Image Fusion , 2016 .

[6]  Lin Cheng,et al.  Potential of trading wind power as regulation services in the California short-term electricity market , 2013 .

[7]  Wei Liu,et al.  Seismic Time–Frequency Analysis via Empirical Wavelet Transform , 2016, IEEE Geoscience and Remote Sensing Letters.

[8]  Yanfei Li,et al.  Wind speed forecasting method based on deep learning strategy using empirical wavelet transform, long short term memory neural network and Elman neural network , 2018 .

[9]  İnci Okumuş,et al.  Current status of wind energy forecasting and a hybrid method for hourly predictions , 2016 .

[10]  Akin Tascikaraoglu,et al.  A review of combined approaches for prediction of short-term wind speed and power , 2014 .

[11]  Dhanraj Chitara,et al.  Cuckoo Search Optimization Algorithm for Designing of a Multimachine Power System Stabilizer , 2018, IEEE Transactions on Industry Applications.

[12]  Yang Fu,et al.  Improvement on probabilistic small-signal stability of power system with large-scale wind farm integration , 2014 .