Different normalization techniques as data preprocessing for one step ahead forecasting of solar global horizontal irradiance

Singla, Pradeep; Duhan, Manoj; Saroha, Sumit

doi:10.1016/b978-0-323-90396-7.00004-3

Cited by 16 publications

(5 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The values near zero represent the model stably tracing the observed value of measurement. On the other hand, larger RMSE values represent poor model performance (Singla et al. , 2022): Tables 5–7 display velocity changes with depth from numerical study and measurements.…”

Section: Resultsmentioning

confidence: 99%

Analysis of open channel flow with various layered vegetation using CFD, considering different near-wall treatment methods

Şibil

2024

HFF

View full text Add to dashboard Cite

Purpose The purpose of this paper is to investigate the impact of near-wall treatment approaches, which are crucial parameters in predicting the flow characteristics of open channels, and the influence of different vegetation covers in different layers. Design/methodology/approach Ansys Fluent, a computational fluid dynamics software, was used to calculate the flow and turbulence characteristics using a three-dimensional, turbulent (k-e realizable), incompressible and steady-flow assumption, along with various near-wall treatment approaches (standard, scalable, non-equilibrium and enhanced) in the vegetated channel. The numerical study was validated concerning an experimental study conducted in the existing literature. Findings The numerical model successfully predicted experimental results with relative error rates below 10%. It was determined that nonequilibrium wall functions exhibited the highest predictive success in experiment Run 1, standard wall functions in experiment Run 2 and enhanced wall treatments in experiment Run 3. This study has found that plant growth significantly alters open channel flow. In the contact zones, the velocities and the eddy viscosity are low, while in the free zones they are high. On the other hand, the turbulence kinetic energy and turbulence eddy dissipation are maximum at the solid–liquid interface, while they are minimum at free zones. Originality/value This is the first study, to the best of the author’s knowledge, concerning the performance of different near-wall treatment approaches on the prediction of vegetation-covered open channel flow characteristics. And this study provides valuable insights to improve the hydraulic performance of open-channel systems.

show abstract

Section: Resultsmentioning

confidence: 99%

Analysis of open channel flow with various layered vegetation using CFD, considering different near-wall treatment methods

Şibil

2024

HFF

View full text Add to dashboard Cite

show abstract

“…Many researchers have used wavelet transform (WT) to pre-process the input time series into different constituents, while EMD further dissects the input series into various constituent parts. This combined use of WT and EMD algorithms allows for a more comprehensive decomposition of the input series, aiding in the improvement of model accuracy [28].…”

Section: Preprocessing Techniquesmentioning

confidence: 99%

Wind power forecasting technologies: A review

Kumar,

Prabhakar,

Verma

2024

Energ. Stor. Conv.

View full text Add to dashboard Cite

This study addresses the critical role of wind power forecasting in ensuring stable and reliable power system operations. Wind Power Forecasting is critical for the efficient operation of plant, time scheduling, and it’s balancing of power generation with grid integration systems. Due to its dependency on dynamic climatic conditions and associated factors, accurate wind power forecasting is challenging. The research delves into various aspects, including input data, input selection techniques, data pre-processing, and forecasting methods, with the aim of motivating researchers to design highly efficient online/offline models on weather-based data. The overarching goal is to enhance the reliability and stability of power systems while optimizing energy resource utilization. The analysis reveals that hybrid models offer more accurate results, highlighting their significance in the current era. This study investigates different Wind Power Forecasting (WPF) models from existing literature, focusing on input variables, time horizons, climatic conditions, pre-processing techniques, and sample sizes that affect model accuracy. It covers statistical models like ARMA and ARIMA, along with AI techniques including Deep Learning (DL), Machine Learning (ML), and neural networks, to estimate wind power.

show abstract

“…Di mana 𝑛 adalah jumlah observasi, 𝑦 𝑖 adalah nilai aktual, dan 𝑦 ̂𝑖 adalah nilai prediksi untuk observasi ke-𝑖. Nilai RMSE yang lebih rendah menunjukkan prediksi yang lebih akurat, dengan nilai 0 mewakili prediksi yang sempurna [14].…”

Section: Evaluasi Modelunclassified

Perbandingan Algoritma Simple Linear Regression Dan Support Vector Regression Dalam Prediksi Jumlah Penduduk Di Sulawesi Tenggara

Chaidir,

Ramadhan,

Zaria

et al. 2024

methodika

View full text Add to dashboard Cite

Pertumbuhan penduduk di Sulawesi Tenggara terus meningkat, mencapai kenaikan sekitar 8% dari tahun 2014 hingga 2023, seperti yang tercatat dalam data Badan Pusat Statistika (BPS). Dampak potensial dari fenomena ini pada kehidupan masyarakat dan pembangunan wilayah perlu menjadi perhatian. Dengan memprediksi jumlah penduduk, dapat membantu dalam perencanaan pembangunan jangka panjang, pengembangan infrastruktur, dan pengelolaan dan alokasi sumber daya. Penelitian ini bertujuan untuk menciptakan model yang efektif untuk meramalkan pertumbuhan penduduk dengan akurasi yang baik. Data yang digunakan adalah data jumlah penduduk Sulawesi Tenggara dari tahun 2014 hingga 2023 menurut kabupaten/kota oleh BPS. Prediksi dilakukan menggunakan metode Support Vector Regression (SVR) dan Simple Linear Regression (SLR). Hasil perbandingan menunjukkan bahwa SLR menunjukkan performa yang lebih baik secara umum dibandingkan dengan SVR pada sebagian besar model, dengan memiliki rata-rata MAPE sebesar 1.89% dan RMSE sebesar 0.51%. Temuan ini mengonfirmasi bahwa SLR merupakan algoritma yang lebih akurat dalam meramalkan pertumbuhan penduduk di Sulawesi Tenggara.

show abstract

Different normalization techniques as data preprocessing for one step ahead forecasting of solar global horizontal irradiance

Cited by 16 publications

References 34 publications

Analysis of open channel flow with various layered vegetation using CFD, considering different near-wall treatment methods

Analysis of open channel flow with various layered vegetation using CFD, considering different near-wall treatment methods

Wind power forecasting technologies: A review

Perbandingan Algoritma Simple Linear Regression Dan Support Vector Regression Dalam Prediksi Jumlah Penduduk Di Sulawesi Tenggara

Contact Info

Product

Resources

About