Switched learning adaptive neuro-control strategy

Sierra-García, J. Enrique; Santos, Matilde

doi:10.1016/j.neucom.2019.12.139

Cited by 23 publications

(7 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In fact, intelligent control techniques such as fuzzy control and neural networks have been successfully used for complex systems in the energy field and in many other areas [7][8][9]. Intelligent controllers that use neural networks inside are usually called neuro-controllers [10].…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Deep learning and fuzzy logic to implement a hybrid wind turbine pitch control

Sierra-García

Santos

2021

Neural Comput & Applic

Self Cite

View full text Add to dashboard Cite

This work focuses on the control of the pitch angle of wind turbines. This is not an easy task due to the nonlinearity, the complex dynamics, and the coupling between the variables of these renewable energy systems. This control is even harder for floating offshore wind turbines, as they are subjected to extreme weather conditions and the disturbances of the waves. To solve it, we propose a hybrid system that combines fuzzy logic and deep learning. Deep learning techniques are used to estimate the current wind and to forecast the future wind. Estimation and forecasting are combined to obtain the effective wind which feeds the fuzzy controller. Simulation results show how including the effective wind improves the performance of the intelligent controller for different disturbances. For low and medium wind speeds, an improvement of 21% is obtained respect to the PID controller, and 7% respect to the standard fuzzy controller. In addition, an intensive analysis has been carried out on the influence of the deep learning configuration parameters in the training of the hybrid control system. It is shown how increasing the number of hidden units improves the training. However, increasing the number of cells while keeping the total number of hidden units decelerates the training.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Considering regular waves, the external disturbance has been modeled as a sinusoidal signal with white Gaussian noise (10).…”

Section: Mathematical Model Of the Wind Turbinementioning

confidence: 99%

Deep learning and fuzzy logic to implement a hybrid wind turbine pitch control

Sierra-García

Santos

2021

Neural Comput & Applic

Self Cite

View full text Add to dashboard Cite

show abstract

“…Chengcheng Gu and Hua Li prudently investigated and presented the different approaches and utilizations of deep learning in wind energy [27]. Hui Liu et al used the Variational Mode Decomposition (VMD) to break the wind speed data into a set, Singular Spectrum Analysis (SSA) to excerpt the learning data of all the set components, LSTM network to fulfill the prediction for the low-frequency components obtained by the VMD-SSA, and Extreme Learning Machine (ELM) to complete the prognostication for the high-frequency components, for producing a unique wind speed multistep forecasting model [ 28]. Enrique and Santos combined an adaptive neural network, a proportional-integral-derivative (PID), an inverse model of the plant, and two switches to control and track the signals appropriately [ 29].…”

Section: Introductionmentioning

confidence: 99%

Adaptive Inverse Deep Reinforcement Lyapunov learning control for a floating wind turbine

KhalafAnsar

Keighobadi

2023

Scientia Iranica

View full text Add to dashboard Cite

Offshore floating wind turbines (FWT) decrease climate change adversial effects without occupying significant land and harvesting fields. Owing to the earth planet unexpected climate, online adaptive feedback control of FWTs will be effective in the sense of optimal and uniform energy capture. In this paper, a deep reinforcement learning (DRL)-based control system is proposed to offset both the disturbance and noise effects. Large variations of wind and water waves generate enormous information give rise to convergent learning of deep neural networks model of the wind turbine. As a result of the disturbance and wind sudden variations, an adaptive inverse control equipped with DRL could easily cope with the inherent drawback of DRL i.e., tracking error. Furthermore, received rewards in the DRL algorithm are passed through the newly designed training algorithm to predict control actions such that the loss function is decreased. The attenuation of disturbance and noise on the tracking performance of closed-loop FWT is clarified through software implementation tests while the weight's convergency and update rules are proved by the direct Lyapunov theorem.

show abstract

“…Nowadays, different Artificial Intelligence (AI) and Machine Learning (ML) techniques have been applied to deal with wind turbines [3], [4] and specifically for forecasting wind features [5]. For instance, in [6], authors reach a 99% accuracy applying techniques such as Extreme Gradient Boosting (XGBoost), decision trees or Random Forest (RF) when forecasting long-term wind speed values.…”

Section: ) Introductionmentioning

confidence: 99%

Evaluation of XGBoost vs. other Machine Learning models for wind parameters identification

García-Puente,

Rodríguez-Hurtado,

Santos

et al. 2023

RE&PQJ

View full text Add to dashboard Cite

Wind energy is one of the most promising renewable energies. But wind is a quite unstable resource due to its continuous variation and random nature. This uncertainty affects the production cost. Therefore, accurate forecasting of wind and energy is very interesting for energy markets. In this work, we test a recent and powerful intelligent technique, extreme gradient boosting (XGBoost), for wind prediction. The forecasting models of some wind features with XGBoost are compared with Support Vector Regression (SVR), Gaussian Process Regression (GPR) and Neural Networks (NN) models. Specifically, the three features predicted are the active power generated by the turbine, the wind speed, and the wind direction. The results conclude that these techniques are useful for wind and energy forecasting, with XGBoost being the most outstanding one, especially for short-term predictions.

show abstract

Switched learning adaptive neuro-control strategy

Cited by 23 publications

References 15 publications

Deep learning and fuzzy logic to implement a hybrid wind turbine pitch control

Deep learning and fuzzy logic to implement a hybrid wind turbine pitch control

Adaptive Inverse Deep Reinforcement Lyapunov learning control for a floating wind turbine

Evaluation of XGBoost vs. other Machine Learning models for wind parameters identification

Contact Info

Product

Resources

About