Wind power forecasting for the Villonaco wind farm

Wind energy is a non-programmable form of generation, hence, accurate and reliable wind energy prediction is of great importance for the efficient operation of wind farms. This article presents a study for the prediction of active power for the Villonaco Wind Farm (VWF), located in southern Ecuador at approximately 2700 m above sea level. Through the use of artificial neural networks, experimental tests are developed based on the models of Multi-Layer Perceptron (MLP), Long Short-Term Memory (LSTM), and Convolutional Neural Network (CNN) to obtain a hybrid model that fits the best characteristics of the individual models. Data from the active power SCADA (Supervisory Control and Data Acquisition) system for the years 2014 to 2018 are used to train and validate the models. Hybrid model is presented as the most appropriate option by the values obtained, viz., the mean absolute error (MAE), the mean squared error (MSE), and mean absolute percentage error (MAPE) that were 0.1365, 0.0974, and 144.26, respectively, outperforming to the others wind power forecast models.

Download Full-text

A Prediction Model for Ultra-Short-Term Output Power of Wind Farms Based on Deep Learning

International Journal of Computers Communications & Control ◽

10.15837/ijccc.2020.4.3901 ◽

2020 ◽

Vol 15 (4) ◽

Author(s):

Yongsheng Wang ◽

Jing Gao ◽

Zhiwei Xu ◽

Jidong Luo ◽

Leixiao Li

Keyword(s):

Wind Energy ◽

Prediction Model ◽

Wind Power ◽

Output Power ◽

Prediction Accuracy ◽

Wind Farm ◽

Short Term Memory ◽

Evaluation Metrics ◽

Power Prediction ◽

Short Term

The output power prediction of wind farm is the key to effective utilization of wind energy and reduction of wind curtailment. However, the prediction of output power has long been a difficulty faced by both academia and the wind power industry, due to the high stochasticity of wind energy. This paper attempts to improve the ultra-short-term prediction accuracy of output power in wind farm. For this purpose, an output power prediction model was constructed for wind farm based on the time sliding window (TSW) and long short-term memory (LSTM) network. Firstly, the wind power data from multiple sources were fused, and cleaned through operations like dimension reduction and standardization. Then, the cyclic features of the actual output powers were extracted, and used to construct the input dataset by the TSW algorithm. On this basis, the TSW-LSTM prediction model was established to predict the output power of wind farm in ultra-short-term. Next, two regression evaluation metrics were designed to evaluate the prediction accuracy. Finally, the proposed TSW-LSTM model was compared with four other models through experiments on the dataset from an actual wind farm. Our model achieved a super-high prediction accuracy 92.7% as measured by d_MAE, an evidence of its effectiveness. To sum up, this research simplifies the complex prediction features, unifies the evaluation metrics, and provides an accurate prediction model for output power of wind farm with strong generalization ability.

Download Full-text

StressNet - Deep learning to predict stress with fracture propagation in brittle materials

npj Materials Degradation ◽

10.1038/s41529-021-00151-y ◽

2021 ◽

Vol 5 (1) ◽

Author(s):

Yinan Wang ◽

Diane Oyen ◽

Weihong (Grace) Guo ◽

Anishi Mehta ◽

Cory Braker Scott ◽

...

Keyword(s):

Deep Learning ◽

Internal Stress ◽

Short Term Memory ◽

Mean Squared Error ◽

Computational Cost ◽

Brittle Materials ◽

Fracture Propagation ◽

Percentage Error ◽

Internal Stresses ◽

The Mean

AbstractCatastrophic failure in brittle materials is often due to the rapid growth and coalescence of cracks aided by high internal stresses. Hence, accurate prediction of maximum internal stress is critical to predicting time to failure and improving the fracture resistance and reliability of materials. Existing high-fidelity methods, such as the Finite-Discrete Element Model (FDEM), are limited by their high computational cost. Therefore, to reduce computational cost while preserving accuracy, a deep learning model, StressNet, is proposed to predict the entire sequence of maximum internal stress based on fracture propagation and the initial stress data. More specifically, the Temporal Independent Convolutional Neural Network (TI-CNN) is designed to capture the spatial features of fractures like fracture path and spall regions, and the Bidirectional Long Short-term Memory (Bi-LSTM) Network is adapted to capture the temporal features. By fusing these features, the evolution in time of the maximum internal stress can be accurately predicted. Moreover, an adaptive loss function is designed by dynamically integrating the Mean Squared Error (MSE) and the Mean Absolute Percentage Error (MAPE), to reflect the fluctuations in maximum internal stress. After training, the proposed model is able to compute accurate multi-step predictions of maximum internal stress in approximately 20 seconds, as compared to the FDEM run time of 4 h, with an average MAPE of 2% relative to test data.

Download Full-text

Performance Analysis of Wind Power Prediction using ANFIS and Gaussian-SVM

SMART MOVES JOURNAL IJOSCIENCE ◽

10.24113/ijoscience.v4i5.135 ◽

2018 ◽

Vol 4 (5) ◽

pp. 10

Author(s):

Devyani Patidar ◽

Dr. Krishna Teerth Chaturvedi

Keyword(s):

Wind Energy ◽

Wind Power ◽

Power Plants ◽

Performance Metrics ◽

Mean Squared Error ◽

Research Work ◽

Clean Energy ◽

Electricity Production ◽

Efficient Operation ◽

Squared Error

Wind energy is one of the most economical sources of renewable electricity, with the largest resources available in the world. It is one of the most promising sources of clean energy and extends its reach to electricity production. Today, wind technologies are making a significant contribution to the growing clean electricity market worldwide. The rapid growth of wind energy and the increase in wind energy production require serious research in various fields. Because wind energy depends on time, it is variable and intermittent on different time scales. Therefore, accurate wind energy prediction is considered an important contribution to the reliable integration of large scale wind energy. Wind energy forecasting methods can be used to plan the ownership, planning and delivery of activities by network operators to maximize electricity traders' revenues. The increasing prevalence of wind power in power plants raises important questions arising from their intermittent and uncertain nature. These challenges require a precise prediction tool for wind power generation to plan the efficient operation of electrical systems and ensure reliability of supply. In this research work two classifier’s performance are evaluated on the real-time dataset. The accuracy of the models has been measured using four performance metrics namely, the Mean Squared Error (MSE), Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE) and Mean Absolute Percentage Error(MAPE). From the result analysis it has been concluded that gaussian SVM outperforms better as compared to the ANFIS model. The result is analysed on different testing dataset of different seasons and averaged error is used to analyse the performance measures.

Download Full-text

Numerical Weather Prediction and Artificial Neural Network Coupling for Wind Energy Forecast

Energies ◽

10.3390/en14020338 ◽

2021 ◽

Vol 14 (2) ◽

pp. 338

Author(s):

Lorenzo Donadio ◽

Jiannong Fang ◽

Fernando Porté-Agel

Keyword(s):

Machine Learning ◽

Wind Energy ◽

Wind Power ◽

Numerical Weather Prediction ◽

Wind Farm ◽

Weather Prediction ◽

Wind Power Forecasting ◽

Numerical Weather ◽

Artificial Neural ◽

Power Forecasting

In the past two decades, wind energy has been under fast development worldwide. The dramatic increase of wind power penetration in electricity production has posed a big challenge to grid integration due to the high uncertainty of wind power. Accurate real-time forecasts of wind farm power outputs can help to mitigate the problem. Among the various techniques developed for wind power forecasting, the hybridization of numerical weather prediction (NWP) and machine learning (ML) techniques such as artificial neural networks (ANNs) are attracting many researchers world-wide nowadays, because it has the potential to yield more accurate forecasts. In this paper, two hybrid NWP and ANN models for wind power forecasting over a highly complex terrain are proposed. The developed models have a fine temporal resolution and a sufficiently large prediction horizon (>6 h ahead). Model 1 directly forecasts the energy production of each wind turbine. Model 2 forecasts first the wind speed, then converts it to the power using a fitted power curve. Effects of various modeling options (selection of inputs, network structures, etc.) on the model performance are investigated. Performances of different models are evaluated based on four normalized error measures. Statistical results of model predictions are presented with discussions. Python was utilized for task automation and machine learning. The end result is a fully working library for wind power predictions and a set of tools for running the models in forecast mode. It is shown that the proposed models are able to yield accurate wind farm power forecasts at a site with high terrain and flow complexities. Especially, for Model 2, the normalized Mean Absolute Error and Root Mean Squared Error are obtained as 8.76% and 13.03%, respectively, lower than the errors reported by other models in the same category.

Download Full-text

Projected Avoided Costs of Conventional Power Plants in Libya Using Wind Energy

Solar Energy and Sustainable Development ◽

10.51646/jsesd.v1i1.31 ◽

2021 ◽

Vol 1 (1) ◽

Author(s):

W. I Abuzend ◽

W. A El-Osta ◽

M. A Ekhlat ◽

E Borass

Keyword(s):

Wind Energy ◽

Wind Power ◽

Power Plants ◽

Energy Systems ◽

Mean Value ◽

Generation System ◽

Energy Technologies ◽

Wind Power Installation ◽

The Mean ◽

Wind Energy Systems

This paper investigates the costs that can be avoided by using wind energy in the central coastal area of Libya. The investigation of the capacity credit was performed in a previous work. The analysis included Fuel saving, capacity saving and emission reduction (NO, SO2 and CO2) to the atmosphere. The avoided costs were translated into equivalent energy costs of wind energy systems. The evaluation was conducted using the reliability (LOLP) analysis and the contribution of wind system during peak demand to the utility total electricity generation system. The calculations were carried out using WASP (Wien Automatic System Planning Package) for the proposed period of 2009-2019 where wind power installation would increase from 100 MW in 2009 to 500 MW in 2019. The results showed that the avoided costs of wind energy will increase from 2.4 c/kWh in 2009 to 8.6 c/kWh in 2019. The mean value of the avoided costs of wend energy over the 10-year period is 6 c/kWh, which would make wind power economically competitive with conventional power plants in Libya. Further investigations of detailed external costs of all energy systems in the national energy mix, as well as the feed in tariff, are recommended and should be introduced to the national energy sectors in order to promote implementation of wind energy and other renewable energy technologies.

Download Full-text

Forecasting Wind Power Generation Using Artificial Neural Network: “Pawan Danawi”—A Case Study from Sri Lanka

Journal of Electrical and Computer Engineering ◽

10.1155/2021/5577547 ◽

2021 ◽

Vol 2021 ◽

pp. 1-10

Author(s):

Amila T. Peiris ◽

Jeevani Jayasinghe ◽

Upaka Rathnayake

Keyword(s):

Neural Network ◽

Power Generation ◽

Wind Power ◽

Wind Farm ◽

Mean Squared Error ◽

Wind Power Generation ◽

Training Algorithms ◽

Training Algorithm ◽

Squared Error ◽

Ann Models

Wind power, as a renewable energy resource, has taken much attention of the energy authorities in many countries, as it is used as one of the major energy sources to satisfy the ever-increasing energy demand. However, careful attention is needed in identifying the wind power potential in a particular area due to climate changes. In this sense, forecasting both wind power generation and wind power potential is essential. This paper develops artificial neural network (ANN) models to forecast wind power generation in “Pawan Danawi”, a functioning wind farm in Sri Lanka. Wind speed, wind direction, and ambient temperature of the area were used as the independent variable matrices of the developed ANN models, while the generated wind power was used as the dependent variable. The models were tested with three training algorithms, namely, Levenberg-Marquardt (LM), Scaled Conjugate Gradient (SCG), and Bayesian Regularization (BR) training algorithms. In addition, the model was calibrated for five validation percentages (5% to 25% in 5% intervals) under each algorithm to identify the best training algorithm with the most suitable training and validation percentages. Mean squared error (MSE), coefficient of correlation (R), root mean squared error ratio (RSR), Nash number, and BIAS were used to evaluate the performance of the developed ANN models. Results revealed that all three training algorithms produce acceptable predictions for the power generation in the Pawan Danawi wind farm with R > 0.91, MSE < 0.22, and BIAS < 1. Among them, the LM training algorithm at 70% of training and 5% of validation percentages produces the best forecasting results. The developed models can be effectively used in the prediction of wind power at the Pawan Danawi wind farm. In addition, the models can be used with the projected climatic scenarios in predicting the future wind power harvest. Furthermore, the models can acceptably be used in similar environmental and climatic conditions to identify the wind power potential of the area.

Download Full-text

Assessment of wind energy potential and characteristics in Qatar for clean electricity generation

Wind Engineering ◽

10.1177/0309524x211043855 ◽

2021 ◽

pp. 0309524X2110438

Author(s):

Carlos Méndez ◽

Yusuf Bicer

Keyword(s):

Wind Energy ◽

Wind Power ◽

Power Density ◽

Wind Farm ◽

Wind Farms ◽

Wind Rose ◽

Energy Potential ◽

Wind Power Density ◽

Wind Speeds ◽

Wind Energy Potential

The present study analyzes the wind energy potential of Qatar, by generating a wind atlas and a Wind Power Density map for the entire country based on ERA-5 data with over 41 years of measurements. Moreover, the wind speeds’ frequency and direction are analyzed using wind recurrence, Weibull, and wind rose plots. Furthermore, the best location to install a wind farm is selected. The results indicate that, at 100 m height, the mean wind speed fluctuates between 5.6054 and 6.5257 m/s. Similarly, the Wind Power Density results reflect values between 149.46 and 335.06 W/m2. Furthermore, a wind farm located in the selected location can generate about 59.7437, 90.4414, and 113.5075 GWh/y electricity by employing Gamesa G97/2000, GE Energy 2.75-120, and Senvion 3.4M140 wind turbines, respectively. Also, these wind farms can save approximately 22,110.80, 17,617.63, and 11,637.84 tons of CO2 emissions annually.

Download Full-text

Wind power generation forecast by coupling numerical weather prediction model and gradient boosting machines in Yahyalı wind power plant

Wind Engineering ◽

10.1177/0309524x20972115 ◽

2020 ◽

pp. 0309524X2097211

Author(s):

Cem Özen ◽

Umur Dinç ◽

Ali Deniz ◽

Haldun Karan

Keyword(s):

Power Generation ◽

Wind Power ◽

Hybrid Model ◽

Spatial Resolution ◽

Numerical Weather Prediction ◽

Wind Farm ◽

Weather Prediction ◽

Numerical Weather Prediction Model ◽

Wind Power Generation ◽

Gradient Boosting

Forecasting of the wind speed and power generation for a wind farm has always been quite challenging and has importance in terms of balancing the electricity grid and preventing energy imbalance penalties. This study focuses on creating a hybrid model that uses both numerical weather prediction model and gradient boosting machines (GBM) for wind power generation forecast. Weather Research and Forecasting (WRF) model with a low spatial resolution is used to increase temporal resolutions of the computed new or existing variables whereas GBM is used for downscaling purposes. The results of the hybrid model have been compared with the outputs of a stand-alone WRF which is well configured in terms of physical schemes and has a high spatial resolution for Yahyalı wind farm over a complex terrain located in Turkey. Consequently, the superiority of the hybrid model in terms of both performance indicators and computational expense in detail is shown.

Download Full-text

Comparison of Different Time Series Methods for Short-Term Forecasting of Wind Power Production

ASME 2010 4th International Conference on Energy Sustainability, Volume 2 ◽

10.1115/es2010-90270 ◽

2010 ◽

Cited By ~ 1

Author(s):

Gong Li ◽

Jing Shi

Keyword(s):

Wind Power ◽

Wind Farm ◽

Mean Squared Error ◽

Network Models ◽

Absolute Error ◽

Power Production ◽

Model Parameters ◽

Short Term ◽

Bp Network ◽

Persistence Model

Reliable short-term predictions of the wind power production are critical for both wind farm operations and power system management, where the time scales can vary in the order of several seconds, minutes, hours and days. This comprehensive study mainly aims to quantitatively evaluate and compare the performances of different Box & Jenkins models and backpropagation (BP) neural networks in forecasting the wind power production one-hour ahead. The data employed is the hourly power outputs of an N.E.G. Micon 900-kilowatt wind turbine, which is installed to the east of Valley City, North Dakota. For each type of Box & Jenkins models tested, the model parameters are estimated to determine the corresponding optimal models. For BP network models, different input layer sizes, hidden layer sizes, and learning rates are examined. The evaluation metrics are mean absolute error and root mean squared error. Besides, the persistence model is also employed for purpose of comparison. The results show that in general both best performing Box & Jenkins and BP models can provide better forecasts than the persistence model, while the difference between the Box & Jenkins and BP models is actually insignificant.

Download Full-text

Hybrid Forecasting Model for Short-Term Wind Power Prediction Using Modified Long Short-Term Memory

Energies ◽

10.3390/en12203901 ◽

2019 ◽

Vol 12 (20) ◽

pp. 3901 ◽

Cited By ~ 4

Author(s):

Namrye Son ◽

Seunghak Yang ◽

Jeongseung Na

Keyword(s):

Wind Speed ◽

Wind Energy ◽

Wind Power ◽

Short Term Memory ◽

Hybrid Methods ◽

Observation Data ◽

Short Term ◽

Term Memory ◽

Current Observation ◽

Long Short Term Memory

Renewable energy has recently gained considerable attention. In particular, the interest in wind energy is rapidly growing globally. However, the characteristics of instability and volatility in wind energy systems also affect power systems significantly. To address these issues, many studies have been carried out to predict wind speed and power. Methods of predicting wind energy are divided into four categories: physical methods, statistical methods, artificial intelligence methods, and hybrid methods. In this study, we proposed a hybrid model using modified LSTM (Long short-term Memory) to predict short-term wind power. The data adopted by modified LSTM use the current observation data (wind power, wind direction, and wind speed) rather than previous data, which are prediction factors of wind power. The performance of modified LSTM was compared among four multivariate models, which are derived from combining the current observation data. Among multivariable models, the proposed hybrid method showed good performance in the initial stage with Model 1 (wind power) and excellent performance in the middle to late stages with Model 3 (wind power, wind speed) in the estimation of short-term wind power. The experiment results showed that the proposed model is more robust and accurate in forecasting short-term wind power than the other models.

Download Full-text