Ultra-short Term Wind Speed Prediction under Multi-model Structure and Uncertainty Analysis

DOI

10.2991/meees-18.2018.31How to use a DOI?

Keywords

wind speed prediction; ultra-short term; iterative multi-step prediction; uncertainty analysis; clustering; artificial neural network.

Abstract

In order to improve the forecasting accuracy and reliability of wind power, the precise prediction of wind speed plays a more and more important role. Thus, the ultra-short-term prediction of wind speed and its uncertainty analysis are studied in the paper. Firstly, based on the daily time series of wind speed and its distribution characteristics, the ADAP (adaptive affinity propagation) method is used to execute the clustering of similar days to extract data samples while the PCA (principal component analysis) algorithm is used for dimensionality reduction. Then, the KELM (kernel extreme learning machine) is used to establish prediction models for different wind speed clusters while the PSO (particle swarm optimization) algorithm is applied to optimize the parameters of KELM. To ensure the generalization ability of prediction model, the k-fold cross validation is brought in to obtain final prediction models with stable performance. Subsequently, the iterative multi-step prediction of wind speed is carried out and its uncertainty is analyzed. The minimum standard error model and the mean-square-root standard error model are achieved to describe the comprehensive uncertainty of the prediction methods. Finally, the operation data of wind turbine is used to evaluate effectiveness of the methods. The results show that the prediction accuracy of wind speed is improved by using the combination model with a certain generalization and stability. In addition, the uncertainty models of prediction error are verified to be effective.

Copyright

© 2018, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Yilin Qiao
AU  - Yang Hu
AU  - Qiong Yang
AU  - Dekun Lyu
PY  - 2018/05
DA  - 2018/05
TI  - Ultra-short Term Wind Speed Prediction under Multi-model Structure and Uncertainty Analysis
BT  - Proceedings of the 2018 International Conference on Mechanical, Electrical, Electronic Engineering & Science (MEEES 2018)
PB  - Atlantis Press
SP  - 167
EP  - 172
SN  - 2352-5401
UR  - https://doi.org/10.2991/meees-18.2018.31
DO  - 10.2991/meees-18.2018.31
ID  - Qiao2018/05
ER  -