FALCON- FArm Level CONtrol for wind turbines using multi-agent deep reinforcement learning

Padullaparthi, Venkata Ramakrishna; Nagarathinam, Srinarayana; Vasan, Arunchandar; Menon, Vishnu; Sudarsanam, Depak

doi:10.1016/j.renene.2021.09.023

Cited by 18 publications

(3 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Weather forecasts are based on digital tools and are used, for example, for power prediction [20]. Manual and automated control is relevant not only for optimizing revenue but also for increasing the wind-farm lifetime [13]. Condition monitoring could also help during decommissioning.…”

Section: Introductionmentioning

confidence: 99%

Digital Twins in Wind Energy: Emerging Technologies and Industry-Informed Future Directions

Stadtmann,

Rasheed,

Kvamsdal

et al. 2023

IEEE Access

View full text Add to dashboard Cite

This article presents a comprehensive overview of the digital twin technology and its capability levels, with a specific focus on its applications in the wind energy industry. It consolidates the definitions of digital twin and its capability levels on a scale from 0-5; 0-standalone, 1-descriptive, 2-diagnostic, 3predictive, 4-prescriptive, 5-autonomous. It then, from an industrial perspective, identifies the current state of the art and research needs in the wind energy sector. It is concluded that the main challenges hindering the realization of highly capable digital twins fall into one of the four categories; standards-related, data-related, model-related, and industrial acceptance related. The article proposes approaches to the identified challenges from the perspective of research institutes and offers a set of recommendations for various stakeholders to facilitate the acceptance of the technology. The contribution of this article lies in its synthesis of the current state of knowledge and its identification of future research needs and challenges from an industry perspective, ultimately providing a roadmap for future research and development in the field of digital twin and its applications in the wind energy industry.

show abstract

Section: Introductionmentioning

confidence: 99%

Digital Twins in Wind Energy: Emerging Technologies and Industry-Informed Future Directions

Stadtmann,

Rasheed,

Kvamsdal

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…8 A method to generate control rules by fuzzy modeling of structural vibrations was proposed in the literature. 9 The method is validated by numerical simulation of a single degree of freedom system. Literature 10 reviewed the progress of the research on active fuzzy control of structural vibration over the past 20 years and then identified the development direction by combining the existing advanced fuzzy control methods and related intelligent control techniques.…”

Section: Introductionmentioning

confidence: 99%

“…Song et al proposed an improved immpa algorithm to find the optimal weight coefficients to optimize the fuzzy regulator and improve the accuracy of the fuzzy regulator, thus reducing the torque fluctuation of the engine 8 . A method to generate control rules by fuzzy modeling of structural vibrations was proposed in the literature 9 . The method is validated by numerical simulation of a single degree of freedom system.…”

Section: Introductionmentioning

confidence: 99%

ADRC‐based optimized control system for wind turbine power generator

2023

Adv Control Appl

View full text Add to dashboard Cite

As a renewable and clean energy source, wind energy can be converted into electricity by wind turbines. Currently, it is challenging to suppress the edgewise vibration of the wind turbine blades to improve the efficiency and service life of wind turbines. In this paper, active disturbance rejection control (ADRC)is applied to vibration suppression at the blade edge of wind turbines. First, the proposed system is mathematically modeled and analyzed in the frequency domain. Second, the ADRC is designed for the proposed system. Then, time domain analysis, frequency domain analysis, and uncertainty analysis of the closed‐loop system were carried out. It has been shown that the proposed controller has 12.2% less overshoot and 55.8% less setting time when subjected to perturbations than the PID controller. And the proposed controller has 33.9% less overshoot and 55.9% less setting time when subjected to perturbations than the SMC. Furthermore, the resonance frequency range of the proposed controller has been effectively reduced, and the peak resonance has been reduced by 41.7%. This reflects that the ADRC has a significant vibration suppression effect on blade edgewise vibrations compared with PID controllers and SMC.

show abstract