Optimal parameters selection for BP neural network based on particle swarm optimization: A case study of wind speed forecasting

Ren, Chao; An, Ning; Wang, Jianzhou; Li, Lian; Hu, Bin; Shang, Duo

doi:10.1016/j.knosys.2013.11.015

Cited by 455 publications

(193 citation statements)

References 31 publications

Supporting

Mentioning

192

Contrasting

Unclassified

Order By: Relevance

“…The best improvements (r = 45) in this paper are measured by the following two criteria: MAE with 0.0535 m/s and RMSE with 0.0789 m/s. In [32], the new proposed model IS-PSO-BP obtained good wind prediction performance based on different training numbers and data sources, whose MAE is 0.16 m/s and RMSE with 0.4123 m/s. In [34] its authors adopted All the above statistics and analysis suggest that we have proposed a valid and feasible wind disturbance model based on a BP neural network.…”

Section: Discussionmentioning

confidence: 95%

See 1 more Smart Citation

Lorenz Wind Disturbance Model Based on Grey Generated Components

et al. 2014

View full text Add to dashboard Cite

Abstract:In order to meet the needs of wind speed prediction in wind farms, we consider the influence of random atmospheric disturbances on wind variations. Considering a simplified fluid convection mode, a Lorenz system can be employed as an atmospheric disturbance model. Here Lorenz disturbance is defined as the European norm of the solutions of the Lorenz equation. Grey generating and accumulated generating models are employed to explore the relationship between wind speed and its related disturbance series. We conclude that a linear or quadric polynomial generating model are optimal through the verification of short-term wind speed prediction in the Sotavento wind farm. The new proposed model not only greatly improves the precision of short-term wind speed prediction, but also has great significance for the maintenance and stability of wind power system operation.

show abstract

Section: Discussionmentioning

confidence: 95%

“…BP Neural Network BP neural network is widely used in wind forecasting and does well in dealing with nonlinear problems [31][32][33]. Thus, it is adopted as the basic forecasting model in this study.…”

Section: Wind Disturbance Model When Rayleigh Number Equals To 45mentioning

confidence: 99%

Lorenz Wind Disturbance Model Based on Grey Generated Components

et al. 2014

View full text Add to dashboard Cite

show abstract

“…The second is the use of the principle of connection, such as the proposed artificial neural network algorithm. The third kind is the classification of some specific rules, such as rough set theory, association rules and decision tree [6].…”

Section: Introductionmentioning

confidence: 99%

A Data Classification Algorithm of Internet of Things Based on Neural Network

2017

Int. J. Onl. Eng.

View full text Add to dashboard Cite

Abstract-To alleviate the pressure of data size, data transmission and data processing in the huge data dimension of the Internet of things., data classification is realized based on back propagation (BP) neural network algorithm. The working principle is deduced in detail. For the shortcomings of slow convergence and easy to fall into the local minimum, the combination of variable learning and momentum factors is used to improve the traditional back propagation algorithm. The results show that the optimized algorithm improves the convergence speed of the network to a certain extent. Therefore, it is concluded that the back propagation neural network has higher classification success rate when classifying multidimensional data in Internet of things.

show abstract

“…Wind power has many advantages [1][2] ; we all know that it's clean, economical and renewable, and the development scale of wind power is constantly expanding, however, wind power also has some disadvantages, such as the characteristic of its randomness, intermittency, non-scheduling and partial predictability, as a result, it brings severe challenges to the large-scale wind power gird for electricity dispatching operation. Compared with our country, many foreign countries carried out the research of wind power prediction error distribution earlier, the normal distribution, beta distribution, Cauchy distribution and Laplace distribution and several traditional empirical distribution models were proposed [3][4][5][6] .…”

Section: Introductionmentioning

confidence: 99%

Error Analysis of Ultra Short Term Wind Power Prediction Model

Zhu¹,

Zha²,

Qin³

2017

Proceedings of the 2016 International Forum on Mechanical, Control and Automation (IFMCA 2016)

View full text Add to dashboard Cite

Abstract. In this paper, we use a piecewise exponential distribution model to predict the ultra short term wind power error and then estimate the parameters. The case we used is from Northern Ireland, we forecast the probability and precision of wind power on the basis of Normal distribution model, Laplace distribution model, Cauchy distribution model, Beta distribution model and the proposed piecewise exponential distribution model. The prediction error distribution model of the sub index wind power forecasting error can be used to mine the relative information of the actual error distribution, in addition, it's convenient to implement and easy to be used in calculus, it can be applied to describe the error distribution of the multiple time scale prediction, so it has more advantages in the error analysis.

show abstract

Optimal parameters selection for BP neural network based on particle swarm optimization: A case study of wind speed forecasting

Cited by 455 publications

References 31 publications

Lorenz Wind Disturbance Model Based on Grey Generated Components

Lorenz Wind Disturbance Model Based on Grey Generated Components

A Data Classification Algorithm of Internet of Things Based on Neural Network

Error Analysis of Ultra Short Term Wind Power Prediction Model

Contact Info

Product

Resources

About