Wind turbine power output prediction using a new hybrid neuro-evolutionary method

Neshat, Mehdi; Nezhad, Meysam Majidi; Abbasnejad, Ehsan; Mirjalili, Seyedali; Groppi, Daniele; Heydari, Azim; Tjernberg, Lina Bertling; Garcia, Davide Astiaso; Alexander, Bradley; Shi, Qinfeng; Wagner, Markus

doi:10.1016/j.energy.2021.120617

Cited by 87 publications

(25 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An empirical study using the Lillgrund offshore windfarm showed that their model improved RMSE by between 4.13% and 31.03%. In a further study, Neshat et al [40] used a hybrid neuro-evolutionary approach on SCADA data based on greedy nelder-mead and a random local search algorithm. Their model outperformed other neural networks in terms of MSE, MAE and RMSE.…”

Section: Literature Reviewmentioning

confidence: 99%

Power Forecasting of Regional Wind Farms via Variational Auto-Encoder and Deep Hybrid Transfer Learning

et al. 2022

View full text Add to dashboard Cite

Wind power is a sustainable green energy source. Power forecasting via deep learning is essential due to diverse wind behavior and uncertainty in geological and climatic conditions. However, the volatile, nonlinear and intermittent behavior of wind makes it difficult to design reliable forecasting models. This paper introduces a new approach using variational auto-encoding and hybrid transfer learning to forecast wind power for large-scale regional windfarms. Transfer learning is applied to windfarm data collections to boost model training. However, multiregional windfarms consist of different wind and weather conditions, which makes it difficult to apply transfer learning. Therefore, we propose a hybrid transfer learning method consisting of two feature spaces; the first was obtained from an already trained model, while the second, small feature set was obtained from a current windfarm for retraining. Finally, the hybrid transferred neural networks were fine-tuned for different windfarms to achieve precise power forecasting. A comparison with other state-of-the-art approaches revealed that the proposed method outperforms previous techniques, achieving a lower mean absolute error (MAE), i.e., between 0.010 to 0.044, and a lowest root mean square error (RMSE), i.e., between 0.085 to 0.159. The normalized MAE and RMSE was 0.020, and the accuracy losses were less than 5%. The overall performance showed that the proposed hybrid model offers maximum wind power forecasting accuracy with minimal error.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Power Forecasting of Regional Wind Farms via Variational Auto-Encoder and Deep Hybrid Transfer Learning

et al. 2022

View full text Add to dashboard Cite

show abstract

“…As a result, the forecasting models properly capture the long-term steady trend in timing across time, periodic duration and amplitude fluctuations, as well as irregular changes caused by random factors. When comparing with a single single method, the weighted combination method can effectively reduce the upper limit of error and improve the robustness of the forecasting results, greatly improving wind speed and wind power forecasting accuracy [15,19,20,22,24,[69][70][71][72][73][74]. Neshat et al [74] utilized a mixture of autoencoder and cluster to decrease the random noise in the original data sequence, then use Variational Mode Decomposition (VMD), Greedy Nelder Mead (GNM) search technique, and Adaptive Randomised Local Search to optimize the hyper-parameters of VMD (ARLS).…”

Section: Hybrid Forecasting Modeling Based On Neural Network-related Approachesmentioning

confidence: 99%

“…When comparing with a single single method, the weighted combination method can effectively reduce the upper limit of error and improve the robustness of the forecasting results, greatly improving wind speed and wind power forecasting accuracy [15,19,20,22,24,[69][70][71][72][73][74]. Neshat et al [74] utilized a mixture of autoencoder and cluster to decrease the random noise in the original data sequence, then use Variational Mode Decomposition (VMD), Greedy Nelder Mead (GNM) search technique, and Adaptive Randomised Local Search to optimize the hyper-parameters of VMD (ARLS). Finally, a hyper-parameter optimizer combining LSTM and the Self-adaptive Differential Evolution (SaDE) algorithm and sine cosine optimisation approach is employed for modeling.…”

Section: Hybrid Forecasting Modeling Based On Neural Network-related Approachesmentioning

confidence: 99%

The Hidden-Layers Topology Analysis of Deep Learning Models in Survey for Forecasting and Generation of theWind Power and Photovoltaic Energy

Xu¹,

Shao²,

Deng³

et al. 2022

Computer Modeling in Engineering &Amp; Sciences

View full text Add to dashboard Cite

As wind and photovoltaic energy become more prevalent, the optimization of power systems is becoming increasingly crucial. The current state of research in renewable generation and power forecasting technology, such as wind and photovoltaic power (PV), is described in this paper, with a focus on the ensemble sequential LSTMs approach with optimized hidden-layers topology for short-term multivariable wind power forecasting. The methods for forecasting wind power and PV production. The physical model, statistical learning method, and machine learning approaches based on historical data are all evaluated for the forecasting of wind power and PV production. Moreover, the experiments demonstrated that cloud map identification has a significant impact on PV generation. With a focus on the impact of photovoltaic and wind power generation systems on power grid operation and its causes, this paper summarizes the classification of wind power and PV generation systems, as well as the benefits and drawbacks of PV systems and wind power forecasting methods based on various typologies and analysis methods.

show abstract

“…In addition, the changing characteristics of the meshing force on the gears, the dynamic stress generated by the impact on the gears during shifting, and the dynamic characteristics of the key nodes of the gear teeth are also issues that people pay attention to. There is a large impact phenomenon when the transmission system shifts, resulting in poor comfort [8][9][10].…”

Section: Introductionmentioning

confidence: 99%

Optimization of the Quality of the Automatic Transmission Shift and the Power Transmission Characteristics

Zhang

Liu

2022

Energies

View full text Add to dashboard Cite

We have established a simulation platform for the machine–electro-hydraulic coupling system of the transmission system and the control system to study the root causes of the problems of large shifting impact and slow change of the machine tool transmission system. The dynamic analysis of the gear shift work of the gearbox was carried out, and the main factors affecting its shift instability were studied. With the impact and sliding power as the optimization goals, the shift quality is optimized based on the multi-objective genetic algorithm. Through the shift experiment, it was found that the power interruption phenomenon during the shift process was eliminated after optimization, and the quality of the shift was improved. Simulated planetary row wheel gear meshing force was found in the same gear, and the second planetary row gear meshing force was the largest among the planetary rows. The stress of the node near the top of the tooth is greater than the stress of the node near the node circle and the root of the tooth, and the two sides of the tooth top are relatively larger than the intermediate stress. The dynamic simulation model of the planetary gearbox system with rigid–soft hybrid can obtain the stress distribution of the solar wheel at the maximum impact moment and the stationary stage, as well as the dynamic stress of the key nodes of the solar wheel, which lays the foundation for the fatigue strength and life prediction of the gear system.

show abstract

Wind turbine power output prediction using a new hybrid neuro-evolutionary method

Cited by 87 publications

References 64 publications

Power Forecasting of Regional Wind Farms via Variational Auto-Encoder and Deep Hybrid Transfer Learning

Power Forecasting of Regional Wind Farms via Variational Auto-Encoder and Deep Hybrid Transfer Learning

The Hidden-Layers Topology Analysis of Deep Learning Models in Survey for Forecasting and Generation of theWind Power and Photovoltaic Energy

Optimization of the Quality of the Automatic Transmission Shift and the Power Transmission Characteristics

Contact Info

Product

Resources

About