Wind Speed Prediction Based on Seasonal ARIMA model

Tyass, Ilham; Bellat, Abdelouahad; Raihani, Abdelhadi; Mansouri, Khalifa; Khalili, Tajeddine

doi:10.1051/e3sconf/202233600034

Cited by 16 publications

(7 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Based on information from Western Australia, Eddie Yatiyana et al projected wind speed and direction using ARIMA independently. Ilham Tyass et al obtained a forecast error of about 16% on an hour ahead forecast, based on the Seasonal ARIMA model for the Morocco region [14]. Similarly, Bri-Mathias Hodge et al [15], Jing Shi et al [16], and Pei Du et al [17] used statistical models to anticipate short-term wind power, finding comparable results with roughly 10% error percentage.…”

Section: Literature Surveymentioning

confidence: 94%

Comparative Study of Time-Series Forecasting Models for Wind Power Generation in Gujarat, India

Mahata,

Harsh,

Shekher

2023

Preprint

View full text Add to dashboard Cite

<p>The rapid rate of transformation in the power sector of India has placed a significant emphasis on robust grids and distributed generation units. The observable shift in the energy sector, especially in wind and solar energy, also requires smooth integration of Distributed Generation units with the existing power grid. Precise wind power generation forecast, therefore, becomes an important and complex task for the strategic planning and management of the systems. We, thus, aim towards a system that can actually provide precise wind power forecasts by applying machine learning techniques. This work proposes a comparative and comprehensive analysis of Artificial Neural Network (ANN), Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and Autoregressive Integrated Moving Average (ARIMA) model. The experimentations and modelling are performed considering meteorological and historical power generation data. The study is concentrated in Kutch, Gujarat and is validated on the data collected from the Central Electricity Authority (CEA), India for power generation data and weather data collected from regional weather centres. The findings show that ARIMA outperforms the other models for non-linear data in multivariate analysis, with a MAPE score of 5.87 on the prediction dataset.</p>

show abstract

Section: Literature Surveymentioning

confidence: 94%

Comparative Study of Time-Series Forecasting Models for Wind Power Generation in Gujarat, India

Mahata,

Harsh,

Shekher

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…In this experiment, we compared the Dst Transformer (DSTT) with six closely related machine learning methods including linear regression (LR), random forests (RF), support vector regression (SVR), auto regressive integrated moving average (ARIMA) (Tyass et al 2022), long shortterm memory (LSTM), and the method developed by Gruet et al (2018), which combines LSTM with Gaussian processes (GP) and is denoted by LSTMGP. Because the six related methods do not have the ability to quantify both data and model uncertainties, we turned off the uncertainty quantification mechanism in our DSTT model when performing this experiment.…”

Section: Comparison With Related Methodsmentioning

confidence: 99%

“…Combining Conv1D and LSTM layers has shown significant improvement in performance when dealing with sequential data such as time series (Abduallah et al 2021;Faghihi and Kalantarpour 2021). LSTM hands the learned patterns down to a multi-head attention layer (Vaswani et al 2017). The multi-head attention layer provides transformation on the sequential input of values to obtain distinct metrics of size h. Here, h is the number of attention heads that is set to 3 and the size of each attention head is also set to 3 because a number greater than 3 caused overhead and less than 3 caused performance degradation.…”

Section: Architecture Of the Dstt Modelmentioning

confidence: 99%

Forecasting the Disturbance Storm Time Index with Bayesian Deep Learning

Abduallah¹,

Wang

Bose

et al. 2022

FLAIRS

View full text Add to dashboard Cite

The disturbance storm time (Dst) index is an important and useful measurement in space weather research. It has been used to characterize the size and intensity of a geomagnetic storm. A negative Dst value means that the Earth's magnetic field is weakened, which happens during storms. In this paper, we present a novel deep learning method, called the Dst Transformer, to perform short-term, 1-6 hour ahead, forecasting of the Dst index based on the solar wind parameters provided by the NASA Space Science Data Coordinated Archive. The Dst Transformer combines a multi-head attention layer with Bayesian inference, which is capable of quantifying both aleatoric uncertainty and epistemic uncertainty when making Dst predictions. Experimental results show that the proposed Dst Transformer outperforms related machine learning methods in terms of the root mean square error and R-squared. Furthermore, the Dst Transformer can produce both data and model uncertainty quantification results, which can not be done by the existing methods. To our knowledge, this is the first time that Bayesian deep learning has been used for Dst index forecasting.

show abstract

“…Time series forecasting consists of determining the future values of a variable in time on the basis of a model and the values of this quantity measured in the past [41]. In their first forecasting attempts dedicated to various RES installations, the authors of various studies in the literature [41][42][43][44][45] used various forecasting models, e.g., those based on econometric models (creeping trend models, exponential smoothing models, etc.) [46] or autoregressive and moving averages [47].…”

Section: Forecasting Time Series Using Regressive Machine Learning Mo...mentioning

confidence: 99%

Forecasting of Energy Balance in Prosumer Micro-Installations Using Machine Learning Models

Popławski,

Dudzik,

Szeląg

2023

Energies

View full text Add to dashboard Cite

It is indisputable that power systems are being transformed around the world to increase the use of RES and reduce the use of fossil fuels in overall electricity production. This year, the EU Parliament adopted the Fit for 55 package, which should significantly reduce the use of fossil fuels in the energy balance of EU countries while increasing the use of RES. At the end of 2022, the total number of prosumer installations in Poland amounted to about one million two hundred thousand. Such a high saturation of prosumer micro-installations in the power system causes many threats resulting from their operation. These threats result, among others, from the fact that photovoltaics are classified as unstable sources and the expected production of electricity from such installations is primarily associated with highly variable weather conditions and is only dependent on people to a minor extent. Currently, there is a rapid development of topics related to forecasting the volume of energy production from unstable sources such as wind and photovoltaic power plants. This issue is being actively developed by research units around the world. Scientists use a whole range of tools and models related to forecasting techniques, from physical models to artificial intelligence. According to our findings, the use of machine learning models has the greatest chance of obtaining positive prognostic effects for small, widely distributed prosumer installations. The present paper presents the research results of two energy balance prediction algorithms based on machine learning models. For forecasting, we proposed two regression models, i.e., regularized LASSO regression and random forests. The work analyzed scenarios taking into account both endogenous and exogenous variables as well as direct multi-step forecasting and recursive multi-step forecasting. The training was carried out on real data obtained from a prosumer micro-installation. Finally, it was found that the best forecasting results are obtained with the use of a random forest model trained using a recursive multi-step method and an exogenous scenario.

show abstract

Wind Speed Prediction Based on Seasonal ARIMA model

Cited by 16 publications

References 16 publications

Comparative Study of Time-Series Forecasting Models for Wind Power Generation in Gujarat, India

Comparative Study of Time-Series Forecasting Models for Wind Power Generation in Gujarat, India

Forecasting the Disturbance Storm Time Index with Bayesian Deep Learning

Forecasting of Energy Balance in Prosumer Micro-Installations Using Machine Learning Models

Contact Info

Product

Resources

About