Discrete wavelet transforms based hybrid approach to forecast windspeed time series

2021 ◽  
pp. 0309524X2199826
Author(s):  
Anil Kumar Kushwah ◽  
Rajesh Wadhvani
Keyword(s):  
Time Series ◽  
Wind Speed ◽  
Wind Power ◽  
Statistical Models ◽  
Wavelet Transforms ◽  
Hybrid Approach ◽  
Hybrid Models ◽  
Superior Performance ◽  
Discrete Wavelet ◽  
Power Calculation

The wind resources have been estimated by using physical models, statistical models, and artificial intelligence models. Wind power calculation helps us measure the annual energy that will sustain the balance between electricity generation and electricity consumption. Wind speed plays a significant role in calculating wind power, due to which here we focus on wind speed prediction. In this paper, hybrid models for wind speed forecasting have been proposed. The hybrid models are formed by combining the time series decomposition technique, that is, discrete wavelet transform (DWT), with statistical models, that is, autoregressive integrated moving average (ARIMA) and generalized autoregressive score (GAS), respectively. These hybrid models are referred to as DWT-ARIMA and DWT-GAS. DWT decomposes the original series into sub-series. After that, statistical models are applied to each sub-series for prediction. In the end, aggregate the prediction results of each sub-series to get the final forecasted series. For experimentation purposes, statistical and hybrid models are applied to various datasets that are taken from the NREL repository. In our studies, the hybrid version demonstrates better results in terms of accuracy and complexity, which indicates superior performance in most cases compared to the existing statistical models.

scholarly journals Enhancing Wind Turbine Power Forecast via Convolutional Neural Network

Electronics ◽  
2021 ◽  
Vol 10 (3) ◽  
pp. 261
Author(s):  
Tianyang Liu ◽  
Zunkai Huang ◽  
Li Tian ◽  
Yongxin Zhu ◽  
Hui Wang ◽  
...  
Keyword(s):  
Time Series ◽  
Wind Speed ◽  
Wind Turbine ◽  
Wind Power ◽  
Rapid Development ◽  
Superior Performance ◽  
Learning Platform ◽  
Novel Approach ◽  
Wind Power Forecast ◽  
Transformation Methods

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.

A Probabilistic Model for Simulating Long-Term Wind-Power Output

2003 ◽  
Vol 27 (3) ◽  
pp. 167-181 ◽  
Author(s):  
Scott Kennedy ◽  
Peter Rogers
Keyword(s):  
Time Series ◽  
Wind Speed ◽  
Wind Power ◽  
Power Output ◽  
Energy Resource ◽  
Autoregressive Process ◽  
Resource Planning ◽  
Offshore Wind ◽  
Arbitrary Length

This paper describes a chronological wind-plant simulation model for use in long-term energy resource planning. The model generates wind-power time series of arbitrary length that accurately reproduce short-term (hourly) to long-term (yearly) statistical behaviour. The modelling objective and methodology differ from forecasting models, which focus on minimizing prediction error. In the present analysis, periodic cycles are isolated from historical wind-speed data from a known local site and combined with a first-order autoregressive process to produce a wind-speed time series model. Corrections for negative wind-speed values and spatial smoothing for geographically disperse wind turbines are discussed. The resulting model is used to simulate the output from a hypothetical offshore wind-plant south of Long Island, New York. Modelled differences of power output between individual turbines result from wind speed variability; wake effects are not considered in this analysis.

scholarly journals A Short-Term Ensemble Wind Speed Forecasting System for Wind Power Applications

2012 ◽  
Vol 51 (10) ◽  
pp. 1763-1774 ◽  
Author(s):  
Justin J. Traiteur ◽  
David J. Callicutt ◽  
Maxwell Smith ◽  
Somnath Baidya Roy
Keyword(s):  
Wind Speed ◽  
Wind Power ◽  
Statistical Models ◽  
Bayesian Model Averaging ◽  
Numerical Models ◽  
Weather Prediction ◽  
Environmental Stability ◽  
Short Term ◽  
Wind Speed Forecasting ◽  
Forecasting System

AbstractThis study develops an adaptive, blended forecasting system to provide accurate wind speed forecasts 1 h ahead of time for wind power applications. The system consists of an ensemble of 21 forecasts with different configurations of the Weather Research and Forecasting Single Column Model and persistence, autoregressive, and autoregressive moving-average models. The ensemble is calibrated against observations for a 6-month period (January–June 2006) at a potential wind-farm site in Illinois using the Bayesian model averaging technique. The forecasting system is evaluated against observations for the July 2006–December 2007 period at the same site. The calibrated ensemble forecasts significantly outperform the forecasts from the uncalibrated ensemble as well the time series models under all environmental stability conditions. This forecasting system is computationally more efficient than traditional numerical weather prediction models and can generate a calibrated forecast, including model runs and calibration, in approximately 1 min. Currently, hour-ahead wind speed forecasts are almost exclusively produced using statistical models. However, numerical models have several distinct advantages over statistical models including the potential to provide turbulence forecasts. Hence, there is an urgent need to explore the role of numerical models in short-term wind speed forecasting. This work is a step in that direction and is likely to trigger a debate within the wind speed forecasting community.

scholarly journals Time Series Classification with Discrete Wavelet Transformed Data

2016 ◽  
Vol 26 (09n10) ◽  
pp. 1361-1377 ◽  
Author(s):  
Daoyuan Li ◽  
Tegawende F. Bissyande ◽  
Jacques Klein ◽  
Yves Le Traon
Keyword(s):  
Time Series ◽  
Classification Accuracy ◽  
Wavelet Transforms ◽  
Time Series Data ◽  
Knowledge Engineering ◽  
Series Data ◽  
Discrete Wavelet ◽  
Time Series Classification ◽  
Time Series Mining ◽  
Compressed Data

Time series mining has become essential for extracting knowledge from the abundant data that flows out from many application domains. To overcome storage and processing challenges in time series mining, compression techniques are being used. In this paper, we investigate the loss/gain of performance of time series classification approaches when fed with lossy-compressed data. This extended empirical study is essential for reassuring practitioners, but also for providing more insights on how compression techniques can even be effective in smoothing and reducing noise in time series data. From a knowledge engineering perspective, we show that time series may be compressed by 90% using discrete wavelet transforms and still achieve remarkable classification accuracy, and that residual details left by popular wavelet compression techniques can sometimes even help to achieve higher classification accuracy than the raw time series data, as they better capture essential local features.

scholarly journals A New Strategy of Hybrid Models using ARIMA, ANN, and DWT in Time Series Modelling

2021 ◽  
Vol 25 (1) ◽  
pp. 27-50
Author(s):  
Tsung-Lin Li ◽  
◽  
Chen-An Tsai ◽  
Keyword(s):  
Time Series ◽  
Moving Average ◽  
Arima Model ◽  
Real Data ◽  
Hybrid Models ◽  
Discrete Wavelet ◽  
Data Sets ◽  
Model Combining ◽  
Time Series Modelling ◽  
Significant Difference

Time series forecasting is a challenging task of interest in many disciplines. A variety of techniques have been developed to deal with the problem through a combination of different disciplines. Although various researches have proved successful for hybrid models, none of them carried out the comparisons with solid statistical test. This paper proposes a new stepwise model determination method for artificial neural network (ANN) and a novel hybrid model combining autoregressive integrated moving average (ARIMA) model, ANN and discrete wavelet transformation (DWT). Simulation studies are conducted to compare the performance of different models, including ARIMA, ANN, ARIMA-ANN, DWT-ARIMA-ANN and the proposed method, ARIMA-DWT-ANN. Also, two real data sets, Lynx data and cabbage data, are used to demonstrate the applications. Our proposed method, ARIMA-DWT-ANN, outperforms other methods in both simulated datasets and Lynx data, while ANN shows a better performance in the cabbage data. We conducted a two-way ANOVA test to compare the performances of methods. The results showed a significant difference between methods. As a brief conclusion, it is suggested to try on ANN and ARIMA-DWT-ANN due to their robustness and high accuracy. Since the performance of hybrid models may vary across data sets based on their ARIMA alike or ANN alike natures, they should all be considered when encountering a new data to reach an optimal performance.

scholarly journals Intelligent security system detects the hidden objects in the smart grid

2020 ◽  
Vol 19 (1) ◽  
pp. 188
Author(s):  
Ammar Wisam Altaher ◽  
Abdullah Hasan Hussein
Keyword(s):  
Image Fusion ◽  
Search Algorithm ◽  
Detection System ◽  
Harmony Search ◽  
Hybrid Approach ◽  
Human Vision ◽  
Superior Performance ◽  
Support Vector ◽  
Accurate Information ◽  
Discrete Wavelet

<p>Monitoring the general public gathered in large numbers is one of the most challenging tasks faced by the law and order enforcement team. There is swiftly demand to that have inbuilt sensors which can detect the concealed weapon, from a standoff distance the system can locate the weapon with very high accuracy. Objects that are obscure and invisible from human vision can be seen vividly from enhanced artificial vision systems. Image Fusion is a computer vision technique that fuses images from multiple sensors to give accurate information. Image fusion using visual and infrared images has been employed for a safe, non-invasive standoff threat detection system. The fused imagery is further processed for specific identification of weapons. The unique approach to discover concealed weapon based on DWT in conjunction with Meta heuristic algorithm Harmony Search Algorithm and SVM classification is presented. It firstly uses the traditional discrete wavelet transform along with the hybrid Hoteling transform to obtain a fused imagery. Then a heuristic search algorithm is applied to search the best optimal harmony to generate the new principal components of the registered input images which is later classified using the K means support vector machines to build better classifiers for concealed weapon detection. Experimental results demonstrate the hybrid approach which shows the superior performance.</p>

Sign in / Sign up

Export Citation Format

Share Document