Accuracy of wind speed predictability with heights using Recurrent Neural networks

Mohandes, M.; Rehman, Shafiqur; Nuha, Hilal Hudan; Islam, Md. Saiful; Schulze, F.H.

doi:10.5937/fme2104908m

Cited by 20 publications

(8 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the development and gradual maturity of AI theory and technology, an increasing amount of researchers have applied deep neural networks (DNN), such as convolutional neural networks (CNN), 19 deep belief networks (DBN), 20 and recurrent neural networks (RNN) 21 to predict wind speed and wind power. Ehsan et al 22 used an LSTM network to predict wind speed in a wind farm, which improved the accuracy of the prediction.…”

Section: Introductionmentioning

confidence: 99%

An ultra‐short‐term wind speed prediction model using LSTM based on modified tuna swarm optimization and successive variational mode decomposition

Tuerxun

Guo

et al. 2022

Energy Science & Engineering

View full text Add to dashboard Cite

Accurate ultra-short-term wind speed prediction is extremely important for the power control of wind farms, the safe dispatch of power systems, and the stable operation of power grids. At present, most wind farms mainly rely on supervisory control and data acquisition systems to obtain operation and maintenance data which includes operating characteristics of wind turbines. In the ultra-short-term wind speed prediction, a long short-term memory network is one of the commonly used deep learning methods. To address the problem that improper selection of long short-term memory network's hyperparameters may affect the prediction results, In the present study, a hybrid prediction model based on the long short-term memory and the modified tuna swarm optimization algorithm was established, and was used to predict after the wind speed sample data had been decomposed by successive variational mode decomposition method. The experimental results reveal that the proposed model effectively improved the accuracy of wind speed prediction for wind farms compared with the support vector regression, deep belief networks, and long short-term memory models optimized by particle swarm optimization algorithm.

show abstract

Section: Introductionmentioning

confidence: 99%

An ultra‐short‐term wind speed prediction model using LSTM based on modified tuna swarm optimization and successive variational mode decomposition

Tuerxun

Guo

et al. 2022

Energy Science & Engineering

View full text Add to dashboard Cite

show abstract

“…ML techniques have been utilized for temporal predictions of WS. 5,6 However, the utilization of ML methods to predict WS at the hub height based on measured WS at lower heights is limited. Islam et al 7 proposed hybrid neural networks to predict WS at 100 m using 10-40 m heights measurements.…”

Section: Introductionmentioning

confidence: 99%

“…Bañuelos‐Ruedas et al 4 studied the Hellman logarithmic method to estimate WS at certain heights. ML techniques have been utilized for temporal predictions of WS 5,6 . However, the utilization of ML methods to predict WS at the hub height based on measured WS at lower heights is limited.…”

Section: Introductionmentioning

confidence: 99%

Vertical wind speed extrapolation model using long short‐term memory and particle swarm optimization

Al‐Shaikhi

Nuha

Mohandes

et al. 2022

Energy Science & Engineering

View full text Add to dashboard Cite

Investigating the potential for deploying a wind farm requires accurate knowledge of the vertical profile of wind speed (WS), both temporal and with height. Commonly, WS estimations at different heights involves calculating sitedependent parameters such as roughness length, atmospheric conditions, and wind shear coefficient. This study proposes a hybrid model to estimate WS at different heights based on measurements at lower heights using particle swarm optimization and long short-term memory (PSO-LSTM). The training procedure consists of two steps, namely the Levenberg-Marquardt (LM) and the PSO, to minimize the mean squared error. To perform vertical extrapolation, the PSO-LSTM utilizes the measured WS at 10-40 m heights to predict WS at 50 m. The predicted results at 50 m are then utilized along with the measured WS at 10-40 to extrapolate WS to 60 m. This process continues until the extrapolation of WS at 120 m is made. The PSO is compared with other optimization methods like genetic algorithm (GA), tuna swarm optimization (TSO), grey wolf optimization (GWO), sparrow search algorithm (SSA), and bald eagle search (BES) on improving the LSTM accuracy. The performance of the PSO-LSTM is compared with the standard LSTM, feedforward neural network and the logarithmic law (LogLaw) based estimation. The extrapolated values obtained using these methods are compared with LiDAR system-based measurements. The proposed method outperformed the other methods.

show abstract

“…It can be noticed that Indonesian tourism app has been thoroughly explored. More enhancement using machine learning methods can be seen in [7,8] using standard machine learning and in [9] using recurrent architecture. The main contribution of this paper is to present the development of the application "ICT Nusantara" which is one of the earliest applications on the Android mobile platform that can help find tourism spots.…”

Section: Introductionmentioning

confidence: 99%

Ict Nusantara: An Android Based Tourism Supporting and Advertising Application Using Google Maps

Mugitama¹,

Rakhatsyah²,

Ghozali³

2022

jipi. jurnal. ilmiah. penelitian. dan. pembelajaran. informatik

View full text Add to dashboard Cite

Aplikasi penunjang wisata perlu untuk dikembangkan pada platform mobile untuk membantug mobilitas wisatawan. Sesuai dengan data statistik dari Gartner dan IDC (International Data Corporation), Android adalah system operasi untuk smartphone yang paling banyak digunakan di dunia tahun 2011, dan Gartner memprediksi jumlah pengguna Android akan meningkat hingga 48,8%. Oleh karena itu, maka platform mobile yang paling sesuai untuk dikembangkan untuk memenuhi kebutuhan pengguna tersebut adalah Android. Aplikasi “ICT Nusantara” adalah aplikasi berbasis Android yang bisa ditujukan membantu wisatawan menemukan tempat-tempat tujuan wisata. Makalah ini juga menyajikan proses pengembangan aplikasi ICT Nusantara Mulai dari Bahasa pemrograman hingga database. Pada pembahasan Bahasa pemrograman, beberapa teori dasar dalam pembuatan aplikasi termasuk Bahasa pemrograman yang dipakai seperti java, javascript, dan HTML untuk layout dibahas secara ringkas. Selain itu, teori dasar tentang basis data seperti mySQL, Sqlite dan jQuery juga dibahas secara ringkas. Kebutuhan perangkat lunak dan keras juga disajikan untuk bisa dikembangkan lebih lanjut. Pengujian terkait wisatawan dan tujuan wisatanya, pemilik tujuan wisata, pemasangan iklan, dan fasilitas public juga dibahas pada makalah ini. Aplikasi baik dari sisi user dan admin sebagai back-end juga dibahas secara rinci namun ringkas. Aplikasi user menggunakan android sebagai platform yang mempunyai fungsi utama untuk melihat peta wisata, mencari lokasi, memberikan petunjuk arah, dan menampilkan gambar-gambar terkait. Sedangkan aplikasi admin menggunakan server berbasis XAMPP yang mempunyai fungsionalitas untuk melakukan operasi perubahan data. Aplikasi admin bisa melakukan operasi penambahan dan perubahan lokasi wisata, operasi terhadap data iklan, dan melakukan verifikasi data lokasi. Karena fungsionalitas tersebut jugalah, aplikasi ini juga bisa digunakan sebagai sebagai sarana advertising. Aplikasi ini juga menyediakan rekomendasi tempat tujuan wisata terdekat dengan sesuai dengan lokasi pengguna

show abstract

Accuracy of wind speed predictability with heights using Recurrent Neural networks

Cited by 20 publications

References 50 publications

An ultra‐short‐term wind speed prediction model using LSTM based on modified tuna swarm optimization and successive variational mode decomposition

An ultra‐short‐term wind speed prediction model using LSTM based on modified tuna swarm optimization and successive variational mode decomposition

Vertical wind speed extrapolation model using long short‐term memory and particle swarm optimization

Ict Nusantara: An Android Based Tourism Supporting and Advertising Application Using Google Maps

Contact Info

Product

Resources

About