A comprehensive study and performance analysis of deep neural network-based approaches in wind time-series forecasting

Rahman, Mijanur; Shakeri, Mohammad Taghi; Khatun, Fatema; Tiong, Sieh Kiong; Alkahtani, Ammar Ahmed; Samsudin, Nurul Asma; Amin, Nowshad; Pasupuleti, Jagadeesh; Hasan, Mohammad Kamrul

doi:10.1007/s40860-021-00166-x

Cited by 25 publications

(12 citation statements)

References 68 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A latest study shows that ANN-based controllers offer quicker dynamic reaction and enhanced the constancy of converter structures over a vast range of operating situations. The advantages of ANN comprise learnability, error tolerance, adaptability, generalizability, contextual data processing, less power utilization, traceability, robustness and fast convergence [45], [46]. The main ANN design consists of three layers and is presented in (7) V-fold cross validation was used to select the optimal subtree; (8) The optimal decision tree is selected to determine the conditions of the new test samples, and the corresponding classification results are output.…”

Section: ) Artificial Neural Networkmentioning

confidence: 99%

Performance Analysis of Renewable Energy Based Distributed Generation System Using ANN Tuned UPQC

Zanib

Batool²,

Riaz

et al. 2022

IEEE Access

View full text Add to dashboard Cite

Emerging trends and advances in techniques in power electronics, Unified Power Quality Conditioner (UPQC) has a superior performance compared to other methods. The paper proposes the application of a ANN based UPQC to enhance the power quality of a three-phase Low-voltage network connected to a hybrid distribution generation (DG) system. The proposed work emphases the detailed performance analysis of a distributed generation system that integrates a solar PV and wind energy system by utilizing Unified Power Quality Conditioner (UPQC) with an artificial neural network (ANN) controller with respect to proportional-integral (PI) controller. The core objective of the proposed ANN is to offer good steady and dynamic state performance compared to the PID controller. The system called UPQC-ANN-RE feeds energy generated by a photovoltaic array and a wind turbine into the electrical grid and loads attached to a system of 3-phase 4-wire electrical distribution. In addition to inserting active/real power in the utility grid, the system of UPQC-ANN-RE functions as a UPQC, improving power quality signs e.g., voltage and current harmonics and power factor. A detailed analysis of the active-real power flow by converters is carried out to allow a good understanding of the operation of the UPQC-ANN-RE. The simulation outcomes are presented to assess the dynamic and steady state performance of the system of UPQC-ANN-RE connected to an electrical distribution system and to compare the consequences with the PI controller.

show abstract

Section: ) Artificial Neural Networkmentioning

confidence: 99%

Performance Analysis of Renewable Energy Based Distributed Generation System Using ANN Tuned UPQC

Zanib

Batool²,

Riaz

et al. 2022

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Likewise, this lack of transparency also limits cross-TSO comparisons, since it is unclear whether several TSOs utilize the same methodology and input data streams, or if they implement their own. Furthermore, cross-comparisons over different forecasting techniques have remained limited and are often restricted to theoretical settings ( [30,31]). This is mainly due to the fact that the performance of forecasting techniques is highly context-dependent.…”

Section: Contributionsmentioning

confidence: 99%

How good are TSO load and renewable generation forecasts: Learning curves, challenges, and the road ahead

Kazmi

Tao

2022

Applied Energy

View full text Add to dashboard Cite

“…At this stage at which energy needs are globally advancing, greenhouse gasses capture for higher feasting of energy produced by red-hot fossil fuels; those sources should be reduced by renewable energy sources. Wind energy WE are a plentiful energy source for the environment (Rahman et al, 2022).…”

Section: Introductionmentioning

confidence: 99%

Machine Learning-Based Wind Speed Estimation for Renewable Energy Optimization in Urban Environments: A Case Study in Kano State, Nigeria

A. M.,

J. M.,

J. K.

et al. 2024

Advanced Journal of Science, Technology and Engineering

View full text Add to dashboard Cite

Climate change always had a massive effect on worldwide cities. which can only be decreased through considering renewable energy sources (wind energy, solar energy). However, the need to focus on wind energy prediction will be the best solution to the world electricity petition. Wind power (WP) estimating techniques have been used for diverse literature studies for many decades. The hardest way to improve WP is its nature of differences that make it a tough undertaking to forecast. In line with the outdated ways of predicting wind speed (WS), employing machine learning methods (ML) has become an essential tool for studying such a problem. The methodology used for this study focuses on sanitizing efficient models to precisely predict WP regimens. Two ML models were employed “Gaussian Process Regression (GPR), and Feed Forward Neural Network (FFNN)” for WS estimation. The experimental methods were used to focus the WS prediction. The prophecy models were trained using a 24-hour’ time-series data driven from Kano state Region, one of the biggest cities in Nigeria. Thus, investigating the (ML) forecast performance was done in terms of coefficient of determination (R²), linear correlation coefficient (R), Mean Square Error (MSE), and Root Mean square error (RMSE). Were. The predicted result shows that the FFNN produces superior outcomes compared to GPR. With R²= 1, R = 1, MSE = 6.62E-20, and RMSE = 2.57E-10

show abstract

A comprehensive study and performance analysis of deep neural network-based approaches in wind time-series forecasting

Cited by 25 publications

References 68 publications

Performance Analysis of Renewable Energy Based Distributed Generation System Using ANN Tuned UPQC

Performance Analysis of Renewable Energy Based Distributed Generation System Using ANN Tuned UPQC

How good are TSO load and renewable generation forecasts: Learning curves, challenges, and the road ahead

Machine Learning-Based Wind Speed Estimation for Renewable Energy Optimization in Urban Environments: A Case Study in Kano State, Nigeria

Contact Info

Product

Resources

About