PLoS ONE, Journal Year: 2025, Volume and Issue: 20(1), P. e0317619 - e0317619
Published: Jan. 23, 2025
This study presents a comprehensive comparative analysis of Machine Learning (ML) and Deep (DL) models for predicting Wind Turbine (WT) power output based on environmental variables such as temperature, humidity, wind speed, direction. Along with Artificial Neural Network (ANN), Long Short-Term Memory (LSTM), Recurrent (RNN), Convolutional (CNN), the following ML were looked at: Linear Regression (LR), Support Vector Regressor (SVR), Random Forest (RF), Extra Trees (ET), Adaptive Boosting (AdaBoost), Categorical (CatBoost), Extreme Gradient (XGBoost), Light (LightGBM). Using dataset 40,000 observations, assessed R-squared, Mean Absolute Error (MAE), Root Square (RMSE). ET achieved highest performance among models, an R-squared value 0.7231 RMSE 0.1512. Among DL ANN demonstrated best performance, achieving 0.7248 0.1516. The results show that especially ANN, did slightly better than models. means they are at modeling non-linear dependencies in multivariate data. Preprocessing techniques, including feature scaling parameter tuning, improved model by enhancing data consistency optimizing hyperparameters. When compared to previous benchmarks, both demonstrates significant predictive accuracy gains WT forecasting. study’s novelty lies directly comparing diverse range algorithms while highlighting potential advanced computational approaches renewable energy optimization.
Language: Английский
Citations
0Optimal Protection Coordination for Grid-Connected and Islanded Microgrids Assisted by the Crow Search Algorithm: Application of Dual-Setting Overcurrent Relays and Fault Current Limiters
Energies, Journal Year: 2025, Volume and Issue: 18(7), P. 1601 - 1601
Published: March 23, 2025
This paper introduces a two-stage protection coordination framework designed for grid-connected and islanded microgrids (MGs) that integrate distributed generations (DGs) energy storage systems (ESSs). The first stage focuses on determining the optimal location sizing of DGs ESSs within MG to ensure stable reliable operation. objective is minimize combined annual investment expected operational costs while adhering power flow equations governing MG, which incorporates both ESSs. To account inherent uncertainties in load DG generation, scenario-based stochastic programming (SBSP) used model these variations effectively. second develops strategy MGs, aiming achieve rapid efficient protective response. achieved by optimizing settings dual-setting overcurrent relays (DSORs) appropriate fault current limiters (FCLs), using data from MG’s daily performance. goal total operating time DSORs primary backup modes respecting critical constraints such as interval (CTI) limits FCLs. solve this complex optimization problem, Crow Search Algorithm (CSA) employed, ensuring derivation effective solutions. implemented 9-bus 32-bus demonstrating its practical applicability evaluating effectiveness real-world scenarios. proposed method achieves an relay operation 1041.36 s 1282 MG. Additionally, results indicate reduction maximum voltage deviation 0.0073 p.u. (grid-connected mode) 0.0038 (islanded decrease loss 1.0114 MWh 0.9435 MWh. CSA solver outperforms conventional methods, achieving standard 1.13% 1.21% two stages, high reliability computational efficiency. work not only provides valuable insights into but also contributes broader effort enhancing economic viability microgrid systems, are becoming increasingly vital sustainable solutions modern grids.
Language: Английский
Citations
0Enhancing Wind Energy Efficiency: A Study on the Power Output of Shrouded Wind Turbines for a Hydrogen Storage System
Results in Engineering, Journal Year: 2025, Volume and Issue: unknown, P. 104710 - 104710
Published: March 1, 2025
Language: Английский
Citations
0A Data Envelopment Analysis Model for Optimizing Transfer Time of Ischemic Stroke Patients Under Endovascular Thrombectomy
Healthcare Analytics, Journal Year: 2024, Volume and Issue: unknown, P. 100364 - 100364
Published: Sept. 1, 2024
Language: Английский
Citations
3Resiliency Planning of Distribution Network using of Active Distribution Network Partitioning
Heliyon, Journal Year: 2024, Volume and Issue: 10(16), P. e36422 - e36422
Published: Aug. 1, 2024
Today, micro-grids (MGs) include all kinds of energy storage systems (ESSs), wind turbines (WTs), photovoltaic (PV), combined heat and power (CHP), etc., also demand response are active on the side. In this paper, single-level robust methods for partitioning planning distribution network (ADN) into several MGs presented. According to desired purpose, objective function model is investment costs minimization installing capacity distributed generations (DGs) switches, activity responsive loads based forecast generation non- DG, losses risk load points costumers. On other hand, maximizing income from sales upstream grid technical constraints optimal flow (OPF) equations. The mentioned problem a complex nonlinear model, therefore, improved genetic algorithm (GA) used. order validate efficiency, method has been used 25-bus ADN including five switches. simulation results obtained case studies prove fact that use retrofitted increases MG, especially in an island operation, contrast presence significantly reduce costs.
Language: Английский
Citations
2Coordination of protection and operation in micro-grids with inverter based distributed generation using SAOA
PLoS ONE, Journal Year: 2024, Volume and Issue: 19(10), P. e0311584 - e0311584
Published: Oct. 10, 2024
In the proposed protection coordination scheme, depreciation of operation time entire relay in primary and backup modes for all possible fault locations is considered as objective function. The limitations this problem include equations calculating relays both forward reverse directions, limitation interval, setting parameters relays, restriction size reactance that limits current, standing distributed generation per small signal fault. depends on short circuit current passing through them, so it necessary to calculate network variables before occurs. For purpose, optimal daily power distribution should be used micro-grid, because micro-grids consist storage renewable resources. plan includes uncertainties consumption capacity Then, achieve a reliable answer with low standard deviation, refrigeration optimization algorithm solve problem. Finally, design implemented test system MATLAB software, then capabilities are examined.
Language: Английский
Citations
1Intelligent-Single-Phase Auto-Reclosing Scheme using Line-Voltage-Phasor-Side Analysis
Results in Engineering, Journal Year: 2024, Volume and Issue: unknown, P. 103771 - 103771
Published: Dec. 1, 2024
Citations
1Electrical Vehicles Impact on Unbalanced Distribution Networks Considering Different Loads and Energy Prices
Heliyon, Journal Year: 2024, Volume and Issue: 10(21), P. e39233 - e39233
Published: Oct. 10, 2024
Highlights•The use of smart EVs in the network scale, addition to peak shedding, if it is used a single phase, can also lead improvement load unbalance.•Proposes an energy and cost management model for appropriate distributed deployment distribution networks provide support DN rich renewable resources.•A 13-bus has been evaluate proposed according costs imposed on DN, calculations these will be measured during 24 hours by two types household industrial loads.•The price variable day depends load.•From sensitivity analysis with relative increase or decrease load, change effects each per-unit power compared presence absence single-phase obtain more practical results.ABSTRACTThe expansion generation erratic loads create many challenges electricity (DN), like grid congestion unbalance. Technological advances recent years have made electric vehicles (EVs) economical justified connection. The This paper proposes phase including resources. By connecting disconnecting unbalanced this balanced as much possible. To model, 13 buses used, loads. These are ability improve DN. Also, load. From results. According paper, EVs, improving greatly reduces
Language: Английский
Citations
0Fuzzy logic control of a permanent magnet synchronous generator integrated in a wind system
STUDIES IN ENGINEERING AND EXACT SCIENCES, Journal Year: 2024, Volume and Issue: 5(3), P. e12720 - e12720
Published: Dec. 26, 2024
This paper deals with the use of a Permanent Magnet Synchronous Generator (PMSG) for production wind energy and injection produced into power grid. The objective this work is to model simulate system taking account problems electrical which are among others: - maintenance generator; variations high speed. contribution mainly based on control strategy generation Machine. Then, in order ensure real-time tracking optimal operating point have maximum different speeds, we used an FLC speed controller aim increasing degree efficiency improve performance our system.
Language: Английский
Citations
0Wind speed prediction based on improved Informer
Published: Dec. 6, 2024
Language: Английский
Citations
0