Long-Term Wind Speed and Power Forecasting Based on LSTM: A Comprehensive Study

Joudaki, Maryam

doi:10.1109/icredg54199.2022.9804519

Cited by 8 publications

(4 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In most of these methods, distinguishing between crack-like lines and real cracks is difficult. For effective classification and to produce a robust classification model, extracting advanced features from images of crack surfaces in concrete structures is necessary (Dargan et al ., 2020; Joudaki, 2022). Among the advantages of deep learning, we can mention automatic and multilayer learning of features, high accuracy in the results, high generalization power and identification of new data, and extensive hardware and software support.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A shallow 2D-CNN network for crack detection in concrete structures

Honarjoo,

Darvishan

2024

IJSI

View full text Add to dashboard Cite

PurposeThis study aims to obtain methods to identify and find the place of damage, which is one of the topics that has always been discussed in structural engineering. The cost of repairing and rehabilitating massive bridges and buildings is very high, highlighting the need to monitor the structures continuously. One way to track the structure's health is to check the cracks in the concrete. Meanwhile, the current methods of concrete crack detection have complex and heavy calculations.Design/methodology/approachThis paper presents a new lightweight architecture based on deep learning for crack classification in concrete structures. The proposed architecture was identified and classified in less time and with higher accuracy than other traditional and valid architectures in crack detection. This paper used a standard dataset to detect two-class and multi-class cracks.FindingsResults show that two images were recognized with 99.53% accuracy based on the proposed method, and multi-class images were classified with 91% accuracy. The low execution time of the proposed architecture compared to other valid architectures in deep learning on the same hardware platform. The use of Adam's optimizer in this research had better performance than other optimizers.Originality/valueThis paper presents a framework based on a lightweight convolutional neural network for nondestructive monitoring of structural health to optimize the calculation costs and reduce execution time in processing.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Using sensor-based methods in structural health monitoring is an effective and non-destructive approach. Therefore, this type of monitoring uses different sensors to achieve an adequate view (Joudaki, 2022; Joudaki et al ., 2020). Video and signal data analysis allow inspectors to continuously and accurately monitor the structure's health.…”

Section: Introductionmentioning

confidence: 99%

A shallow 2D-CNN network for crack detection in concrete structures

Honarjoo,

Darvishan

2024

IJSI

View full text Add to dashboard Cite

show abstract

“…In literature [3] , the wind speed and wind power of wind turbines are predicted based on the AM CNN Bi-LSTM combined model, and the accuracy and prediction error are compared with the results of LSTM and CNNLSTM. In literature [4] , variational mode decomposition (VMD) was used to preprocess and decompose wind power generation data from real wind farms, and a deep learning model (long and short term dropout regularization memory (LSTM)) was designed to accurately predict the decomposed spectra.…”

Section: Introductionmentioning

confidence: 99%

Short-term wind power prediction based on ICSA-BiLSTM

Chen,

Li,

Tao

2023

Second International Conference on Energy, Power, and Electrical Technology (ICEPET 2023)

View full text Add to dashboard Cite

In order to improve the accuracy of short-term wind power prediction, an improved chameleon Swarm algorithm is proposed and applied to the wind power prediction model established in BiLSTM. Firstly, Circle chaotic mapping was used to initialize the population of the standard Chameleon Swarm algorithm, then spiral search in the whale algorithm was used to improve the global search ability and Levy flight strategy was introduced to improve the local development ability, and then Gaussian detection was used to improve the optimization ability. Finally, the Bilstm-based prediction model was established and the historical wind farm data was used for example analysis.

show abstract

“…Likewise, in [7] a comparison between the ARMA, ANN and Support Vector Machines (SVM) is conducted for short-term forecasting of wind speed and direction. Comparative studies of hybrid ANN models are performed by [8,9] where the forecasts horizons are for short and long term wind speed and direction, suggesting the use of hybrid models can increase the accuracy in the predictions. The performance evaluation delivered in these studies are mostly based on observing the RMSE and MAPE differences between models, and do not offer stronger evidence on whether the model outperforms because of the data set randomness or because is truly predicting accurately [10].…”

Section: Introductionmentioning

confidence: 99%

Performance comparison of probabilistic and artificial neural network models for long-sequence generation of wind speed forecasts

Pina-Gongora¹,

Kazemtabrizi²,

Crabtree³

2023

IET Conf. Proc.

View full text Add to dashboard Cite

This paper presents a new method for generating long-sequence wind speed time-series forecasts for purposes of offshore wind farm asset and operations planning. Our goal is to develop a planning decision support tool with which wind farm planners and operators can make informed decisions for development and operation of future offshore wind assets considering revenue and power generation yield, as well as operation and maintenance expenditures.The proposed methodology should be computationally efficient and should be able to reliably generate accurate wind speed time-series forecasts for the required planning timescale. In this paper, we used an Autoregressive Moving average model as benchmark to evaluate and compare the performance of four different artificial neural network models namely, uni-variate Long-Short Term Memory (LSTM), uni-variate hybrid one dimensional convolutional neural network with LSTM (1D-CNN-LSTM), multivariate Long-short term memory and multivariate hybrid 1D-CNN-LSTM architectures. The performance evaluation is delivered through the statistical comparison of the metrics, RMSE, MAE and MAPE, and the final selection of the outperforming model is supported using Diebold-Mariano statistic test. Experiments consists of applying different types of pre-processing to the wind speed dataset and the modification of models' architecture to include either a batch normalization or a drop-out regularization layer are realized to aid in the selection of the most suitable model engineering. Results suggest the uni-variate hybrid 1D-CNN-LSTM is able to deliver short-term prediction for longer timescales while maintaining a suitable degree of accuracy.

show abstract

Long-Term Wind Speed and Power Forecasting Based on LSTM: A Comprehensive Study

Cited by 8 publications

References 7 publications

A shallow 2D-CNN network for crack detection in concrete structures

A shallow 2D-CNN network for crack detection in concrete structures

Short-term wind power prediction based on ICSA-BiLSTM

Performance comparison of probabilistic and artificial neural network models for long-sequence generation of wind speed forecasts

Contact Info

Product

Resources

About