Predictive Deep Boltzmann Machine for Multiperiod Wind Speed Forecasting

Zhang, Chun-Yang; Chen, C. L. Philip; Gan, Min; Chen, Long

doi:10.1109/tste.2015.2434387

Cited by 197 publications

(60 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Frequently used features include historical meteorological data [23], [24], [53], spatial information [54], real time mea-3 surements performed using wind farm sensors [55], and NWP [25] data.…”

Section: Related Workmentioning

confidence: 99%

A Decision Support System for Wind Power Production

Labati

Genovese

Piuri

et al. 2020

IEEE Trans. Syst. Man Cybern, Syst.

View full text Add to dashboard Cite

Abstract-Renewable energy production is constantly growing worldwide, and some countries produce a relevant percentage of their daily electricity consumption through wind energy. Therefore, decision support systems that can make accurate predictions of wind-based power production are of paramount importance for traders operating in the energy market and for managers in charge of planning the non-renewable energy production. In this paper, we present a decision support system that can predict electric power production, estimate a variability index for the prediction, and analyze wind farm production characteristics. The main contribution of this paper is a novel system for long-term electric power prediction based solely on weather forecasts; thus, it is suitable for wind farms that cannot collect or manage real-time data acquired by sensors. Our system is based on neural networks and on novel techniques for calibrating and thresholding the weather forecasts based on the distinctive characteristics of wind farm orography. We tuned and evaluated the proposed system using data collected from two wind farms over a two-year period and achieved satisfactory results. We studied different feature sets, training strategies, and system configurations before implementing this system for a player in the energy market. This company evaluated the power production prediction performance and impact of our system at ten different wind farms under real-world conditions and achieved a significant improvement with respect to their previous approach.

show abstract

Section: Related Workmentioning

confidence: 99%

A Decision Support System for Wind Power Production

Labati

Genovese

Piuri

et al. 2020

IEEE Trans. Syst. Man Cybern, Syst.

View full text Add to dashboard Cite

show abstract

“…However, it has not been actively utilized in the wind power or wind speed forecasting fields. Deep belief network, due to its strong ability of learning, has been performed in short-term WSP [26]. The stacked denoising autoencoder combined with rough set was applied to extract features from wind speed series [20].…”

Section: Mathematical Problems In Engineeringmentioning

confidence: 99%

Multistep Wind Speed and Wind Power Prediction Based on a Predictive Deep Belief Network and an Optimized Random Forest

Sun

Zhang

2018

Mathematical Problems in Engineering

View full text Add to dashboard Cite

A variety of supervised learning methods using numerical weather prediction (NWP) data have been exploited for short-term wind power forecasting (WPF). However, the NWP data may not be available enough due to its uncertainties on initial atmospheric conditions. Thus, this study proposes a novel hybrid intelligent method to improve existing forecasting models such as random forest (RF) and artificial neural networks, for higher accuracy. First, the proposed method develops the predictive deep belief network (DBN) to perform short-term wind speed prediction (WSP). Then, the WSP data are transformed into supplementary input features in the prediction process of WPF. Second, owing to its ensemble learning and parallelization, the random forest is used as supervised forecasting model. In addition, a data driven dimension reduction procedure and a weighted voting method are utilized to optimize the random forest algorithm in the training process and the prediction process, respectively. The increasing number of training samples would cause the overfitting problem. Therefore, the k-fold cross validation (CV) technique is adopted to address this issue. Numerical experiments are performed at 15-min, 30-min, 45-min, and 24-h to indicate the superiority and signal advantages compared with existing methods in terms of forecasting accuracy and scalability.

show abstract

“…There are varieties of ultra-short term wind speed forecast, such as continuous method, machine learning method and time series method [4,5,6]. When considering hysteresis and correlation of wind speed's time sequence, it can be used directly to predict wind speed.…”

Section: Introductionmentioning

confidence: 99%

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

Qiao¹,

Hu²,

Yang³

et al. 2018

Proceedings of the 2018 International Conference on Mechanical, Electrical, Electronic Engineering &Amp; Science (MEEES 2018)

View full text Add to dashboard Cite

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.

show abstract

Predictive Deep Boltzmann Machine for Multiperiod Wind Speed Forecasting

Cited by 197 publications

References 36 publications

A Decision Support System for Wind Power Production

A Decision Support System for Wind Power Production

Multistep Wind Speed and Wind Power Prediction Based on a Predictive Deep Belief Network and an Optimized Random Forest

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

Contact Info

Product

Resources

About