Correlation aware multi-step ahead wind speed forecasting with heteroscedastic multi-kernel learning

Abstract For the management of wind energy, wind speed forecasting is often required. Accurate multi-step ahead wind speed forecasts make the power system be adjusted timely and properly to ensure the stable and efficient operation of power system. Currently, various techniques have been developed for multi-step ahead wind speed forecasting. However, the correlation among different forecasting steps is often neglected in current multi-step ahead wind speed forecasting approaches, and the characteristic of heteroscedasticity in wind speed forecasting errors is usually not taken into consideration. In this work, a novel multi-step ahead forecasting method based on multi-kernel learning is developed. This method considers the task correlation, which represented by the covariance of multi-step ahead forecasting tasks, as well as the heteroscedasticity of forecasting errors. The optimization is solved within the framework of variational Bayesian. Thus, a correlation aware multi-step ahead wind speed forecasting technique with heteroscedastic multi-kernel learning is designed. In this paper, the experimental results in different wind farms and different seasons prove that the regression model considering the characteristics of multi-step ahead wind speed forecasting, task correlation and heteroscedasticity, will produce more accurate forecasts than the other models as for two to six-ahead wind speed forecasting. However, it is difficult to tell which characteristic is more important from the forecasting results. So, the regression model considering both of them will be more reasonable. Moreover, the training time of the proposed model is more than 10 min but less than 20 min. Thus, two to six-step ahead wind speed forecasts can be used in some practical applications, such as the load dispatch planning and the load increment/decrement decisions.

[1]  Michael E. Tipping.  Sparse Bayesian Learning and the Relevance Vector Machine , 2001, J. Mach. Learn. Res..

[2]  Qinghua Hu,et al.  Deterministic and probabilistic wind power forecasting using a variational Bayesian-based adaptive robust multi-kernel regression model , 2017 .

[3]  Liang Xiao,et al.  Variational Bayesian learning for robust AR modeling with the presence of sparse impulse noise , 2016, Digit. Signal Process..

[4]  Lei Wu,et al.  Wind speed forecasting based on the hybrid ensemble empirical mode decomposition and GA-BP neural network method , 2016 .

[5]  Qinghua Hu,et al.  Kernel ridge regression for general noise model with its application , 2015, Neurocomputing.

[6]  Feng Qian,et al.  Multi-step wind speed forecasting based on a hybrid forecasting architecture and an improved bat algorithm , 2017 .

[7]  Yun Wang,et al.  A hybrid wind speed forecasting model based on phase space reconstruction theory and Markov model: A case study of wind farms in northwest China , 2015 .

[8]  Peng Kou,et al.  Probabilistic wind power forecasting with online model selection and warped gaussian process , 2014 .

[9]  A. Immanuel Selvakumar,et al.  Linear and non-linear autoregressive models for short-term wind speed forecasting , 2016 .

[10]  Peng Kou,et al.  Probabilistic electricity price forecasting with variational heteroscedastic Gaussian process and active learning , 2015 .

[11]  Dai Hui.  CALCULATION OF WIND FARM PENETRATION BASED ON POWER SYSTEM TRANSIENT STABILITY ANALYSIS , 2002 .

[12]  Ainuddin Wahid Abdul Wahab,et al.  An appraisal of wind speed distribution prediction by soft computing methodologies: A comparative study , 2014 .

[13]  Zhongyi Hu,et al.  Multi-step-ahead time series prediction using multiple-output support vector regression , 2014, Neurocomputing.

[14]  R. Kavasseri,et al.  Day-ahead wind speed forecasting using f-ARIMA models , 2009 .

[15]  Chu Zhang,et al.  A compound structure of ELM based on feature selection and parameter optimization using hybrid backtracking search algorithm for wind speed forecasting , 2017 .

[16]  Ajit Achuthan,et al.  Recursive wind speed forecasting based on Hammerstein Auto-Regressive model , 2015 .

[17]  Athanasios Sfetsos,et al.  A novel approach for the forecasting of mean hourly wind speed time series , 2002 .

[18]  Haikun Wei,et al.  A Gaussian process regression based hybrid approach for short-term wind speed prediction , 2016 .

[19]  Antti Sorjamaa,et al.  Multiple-output modeling for multi-step-ahead time series forecasting , 2010, Neurocomputing.

[20]  Yitao Liu,et al.  Deep learning based ensemble approach for probabilistic wind power forecasting , 2017 .

[21]  Cinzia Viroli,et al.  Finite mixtures of matrix normal distributions for classifying three-way data , 2011, Stat. Comput..

[22]  Eric M. Aldrich,et al.  Calibrated Probabilistic Forecasting at the Stateline Wind Energy Center , 2006 .

[23]  Henrik Madsen,et al.  Spatio‐temporal analysis and modeling of short‐term wind power forecast errors , 2011 .

[24]  Jianzhou Wang,et al.  Analysis and application of forecasting models in wind power integration: A review of multi-step-ahead wind speed forecasting models , 2016 .

[25]  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 .

[26]  Yitao Liu,et al.  Deep belief network based deterministic and probabilistic wind speed forecasting approach , 2016 .

[27]  Jian Wang,et al.  Maximum likelihood estimation for compound-gaussian clutter with inverse gamma texture , 2007, IEEE Transactions on Aerospace and Electronic Systems.

[28]  Jianzhou Wang,et al.  Short-term wind speed forecasting using a hybrid model , 2017 .

[29]  Qinghua Hu,et al.  Short-Term Wind Speed or Power Forecasting With Heteroscedastic Support Vector Regression , 2016, IEEE Transactions on Sustainable Energy.

[30]  F.E. Turkheimer,et al.  A Variational Bayesian inference method for parametric imaging of PET data , 2017, NeuroImage.

[31]  H. C. S. Thom,et al.  a Note on the Gamma Distribution , 1958 .

[32]  S. T. Boris Choy,et al.  SCALE MIXTURES DISTRIBUTIONS IN STATISTICAL MODELLING , 2008 .

[33]  P. Ramasamy,et al.  Wind speed prediction in the mountainous region of India using an artificial neural network model , 2015 .

[34]  A. Roverato.  Hyper Inverse Wishart Distribution for Non-decomposable Graphs and its Application to Bayesian Inference for Gaussian Graphical Models , 2002 .

[35]  Karl J. Friston,et al.  Variational Bayesian inference for fMRI time series , 2003, NeuroImage.

[36]  Mehmet Gönen,et al.  A Bayesian Multiple Kernel Learning Framework for Single and Multiple Output Regression , 2012, ECAI.

[37]  Jing Shi,et al.  Fine tuning support vector machines for short-term wind speed forecasting , 2011 .

[38]  Fulei Chu,et al.  Non-parametric hybrid models for wind speed forecasting , 2017 .

[39]  Jie Zhang,et al.  A data-driven multi-model methodology with deep feature selection for short-term wind forecasting , 2017 .

[40]  Mohammad Arashi,et al.  On Conditional Applications of Matrix Variate Normal Distribution , 2010 .

[41]  Jiayu Zhou,et al.  Modeling disease progression via multi-task learning , 2013, NeuroImage.

[42]  Qinghua Hu,et al.  Noise model based v-support vector regression with its application to short-term wind speed forecasting , 2014, Neural Networks.

[43]  Hui Liu,et al.  Four wind speed multi-step forecasting models using extreme learning machines and signal decomposing algorithms , 2015 .

[44]  Yanfei Li,et al.  Comparison of two new intelligent wind speed forecasting approaches based on Wavelet Packet Decomposition, Complete Ensemble Empirical Mode Decomposition with Adaptive Noise and Artificial Neural Networks , 2018 .