A Method to Generate the Simulated Time-series of Wind Turbine Output with Conversion of Wind Speed by Location and Height based on Weibull Distribution

The rapid development in wind power comes with new technical challenges. Reliable and accurate wind power forecast is of considerable significance to the electricity system’s daily dispatching and production. Traditional forecast methods usually utilize wind speed and turbine parameters as the model inputs. However, they are not sufficient to account for complex weather variability and the various wind turbine features in the real world. Inspired by the excellent performance of convolutional neural networks (CNN) in computer vision, we propose a novel approach to predicting short-term wind power by converting time series into images and exploit a CNN to analyze them. In our approach, we first propose two transformation methods to map wind speed and precipitation data time series into image matrices. After integrating multi-dimensional information and extracting features, we design a novel CNN framework to forecast 24-h wind turbine power. Our method is implemented on the Keras deep learning platform and tested on 10 sets of 3-year wind turbine data from Hangzhou, China. The superior performance of the proposed method is demonstrated through comparisons using state-of-the-art techniques in wind turbine power forecasting.

Download Full-text

Scale-dependent intrinsic entropies of complex time series

Philosophical Transactions of The Royal Society A Mathematical Physical and Engineering Sciences ◽

10.1098/rsta.2015.0204 ◽

2016 ◽

Vol 374 (2065) ◽

pp. 20150204 ◽

Cited By ~ 2

Author(s):

Jia-Rong Yeh ◽

Chung-Kang Peng ◽

Norden E. Huang

Keyword(s):

Time Series ◽

Time Scales ◽

Spatial Scales ◽

Multiple Time Scales ◽

Multiple Time ◽

Complex Time ◽

Multi Scale ◽

Mode Decomposition ◽

Simulated Time ◽

Simulated Time Series

Multi-scale entropy (MSE) was developed as a measure of complexity for complex time series, and it has been applied widely in recent years. The MSE algorithm is based on the assumption that biological systems possess the ability to adapt and function in an ever-changing environment, and these systems need to operate across multiple temporal and spatial scales, such that their complexity is also multi-scale and hierarchical. Here, we present a systematic approach to apply the empirical mode decomposition algorithm, which can detrend time series on various time scales, prior to analysing a signal’s complexity by measuring the irregularity of its dynamics on multiple time scales. Simulated time series of fractal Gaussian noise and human heartbeat time series were used to study the performance of this new approach. We show that our method can successfully quantify the fractal properties of the simulated time series and can accurately distinguish modulations in human heartbeat time series in health and disease.

Download Full-text

Student t-tests and compound tests to detect transients in simulated time series

European Journal of Operational Research ◽

10.1016/s0377-2217(98)00233-1 ◽

1999 ◽

Vol 116 (3) ◽

pp. 681-691 ◽

Cited By ~ 8

Author(s):

Daniel H. Ockerman ◽

David Goldsman

Keyword(s):

Time Series ◽

Simulated Time ◽

Simulated Time Series

Download Full-text

Estudio preliminar de caracterización de la velocidad del viento para instalar un aerogenerador de 400 W

ECORFAN Journal Republic of Paraguay ◽

10.35429/ejrop.2019.8.5.23.30 ◽

2019 ◽

pp. 23-30

Author(s):

Gustavo Adolfo Fajardo-Pulido ◽

Juan Carlos Juan Carlos ◽

Gerardo Fuster-Lopez

Keyword(s):

Wind Speed ◽

Wind Energy ◽

Weibull Distribution ◽

Wind Turbine ◽

Quintana Roo ◽

Wind Rose ◽

Scientific Advance ◽

Method Of Calculation ◽

Permissible Range

The characterization of wind speed in Cancun, Q. Roo Mexico, had as objectives: 1. To estimate the efficiency and energy produced by a 400W wind turbine at a height of 10 m; 2. To carry out the wind speed characterization. The methodology used was the Weibull distribution. In order to calculate the distribution of the wind speed, with the Wind Rose software we analyzed the energy in different directions and the calculation of potential wind energy based on Rayleigh's analysis. The results showed: that the power generated from the wind speed calculated in (PV) 2.8 m/s was 1.48 W, its capacity factor at 0.004 which does not reach the permissible range of 0.25 to 0.40; the energy produced annually was 14.02 kW/year, it is required to raise the wind turbine to 13.4 m, to reach 12 m/s speed and to be efficient to install a 400 W wind turbine. The paper identifies the preliminary activities and illustrates the method of calculation of wind characterization and energy produced to define the installation conditions of the wind turbine. It also contributes to the scientific advance by estimating the characterization of the wind in Cancun Quintana Roo, Mexico, for future wind turbine installations.

Download Full-text

Time series data mining for analysing the effects of wind speed on wind turbine reliability

Safety and Reliability – Theory and Applications ◽

10.1201/9781315210469-93 ◽

2017 ◽

Cited By ~ 2

Author(s):

Maik Reder ◽

Julio Melero

Keyword(s):

Data Mining ◽

Time Series ◽

Wind Speed ◽

Wind Turbine ◽

Time Series Data ◽

Series Data ◽

Time Series Data Mining

Download Full-text

Singular Spectrum Analysis Based on L1-Norm

Fluctuation and Noise Letters ◽

10.1142/s0219477516500097 ◽

2016 ◽

Vol 15 (01) ◽

pp. 1650009 ◽

Cited By ~ 11

Author(s):

Mahdi Kalantari ◽

Masoud Yarmohammadi ◽

Hossein Hassani

Keyword(s):

Time Series ◽

Spectrum Analysis ◽

Singular Spectrum Analysis ◽

Frobenius Norm ◽

L1 Norm ◽

Empirical Results ◽

Singular Spectrum ◽

Simulated Time ◽

Simulated Time Series ◽

Basic Version

In recent years, the singular spectrum analysis (SSA) technique has been further developed and increasingly applied to solve many practical problems. The aim of this research is to introduce a new version of SSA based on [Formula: see text]-norm. The performance of the proposed approach is assessed by applying it to various real and simulated time series, especially with outliers. The results are compared with those obtained using the basic version of SSA which is based on the Frobenius norm or [Formula: see text]-norm. Different criteria are also examined including reconstruction errors and forecasting performances. The theoretical and empirical results confirm that SSA based on [Formula: see text]-norm can provide better reconstruction and forecasts in comparison to basic SSA when faced with time series which are polluted by outliers.

Download Full-text