Economic nonlinear model predictive control of fatigue for a hybrid wind-battery generation system

Anand, Abhinav; Loew, Stefan; Bottasso, Carlo L.

doi:10.1088/1742-6596/2265/3/032106

Cited by 5 publications

(4 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The assumed battery consists of a model of the electrical equivalent circuit of a 6 MW/6 MWh lithium-ion unit including electrical, thermal, and degradation, sub-models. A detailed description of the modelling approach can be found in [17]. The wind farm and battery are connected to the electricity grid through a single point of interconnection.…”

Section: Predictive Performancementioning

confidence: 99%

“…The HPP revenue is estimated as a product of market price and respective power bids. The cost of battery damage is estimated and minimised directly using the parametric online rainflow counting approach [17]. The optimisation is subject to constraints to minimise deviations between the summed (pre-)bidding (for both the day-ahead and intra-day stages) and the operational set-point of the HPP.…”

Section: Predictive Performancementioning

confidence: 99%

See 1 more Smart Citation

Site-specific production forecast through data-driven and engineering models

Braunbehrens,

Strecker,

Anand

et al. 2024

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

The present study investigates the predictive capabilities of two site-specific wind power forecasting models. The two approaches make use of a machine learning ensemble model that combines forecasts from several numerical weather predictions (NWP) to match local observations. In the first approach, the training data consists of historical site power production recordings. This yields a black-box model that includes the wind farm behaviour. The second approach is a combination of data-driven and explicit modelling. In the first step, the machine learning ensemble model forecasts the site wind conditions. Then, this input is fed to a site-specific engineering wake model. This hybrid ”grey-box” approach explicitly resolves some farm flow effects. The study shows that the performance of both methods differs over the wind speed range. The purely data-driven model performs better at medium wind speeds, which also occur more often. The hybrid method predictions agree better during periods of higher wind speeds. In the last part, the study showcases the capabilities of the forecasting methods when participating in the energy market. Additionally, the engineering wake model allows for power maximisation through wind farm control.

show abstract

Section: Predictive Performancementioning

confidence: 99%

Section: Predictive Performancementioning

confidence: 99%

Site-specific production forecast through data-driven and engineering models

Braunbehrens,

Strecker,

Anand

et al. 2024

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

show abstract

“…Q always decreases over time and usage because of the permanent loss in the capacity of the battery due to the accumulated cyclic damage Q cyc . For a given set of SOC samples, Q cyc is calculated with a novel Rainflow cycle-counting algorithm (refer to [11] for details), which explicitly considers the impact of SOC residue samples. The battery thermal model captures the dynamics of battery temperature T b as…”

Section: Hybrid Power Plantmentioning

confidence: 99%

“…The battery cyclic damage costs C cyc t are formulated using the Parameteric Online Rainflow Counting (PORFC) approach, which allows direct consideration and minimization of cyclic damage [11]. The PORFC algorithm uses a pre-processing step to identify fatigue cycles for a given set of SOC samples, and splits the respective damages over the contributing samples.…”

Section: Hybrid Power Plant: Energy Management Systemmentioning

confidence: 99%

Profit-optimal data-driven operation of a hybrid power plant participating in energy markets

Anand,

Petzschmann,

Strecker

et al. 2024

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

An energy management system (EMS) is formulated for a hybrid power plant (HPP), consisting of a wind power plant and battery storage plant, participating in bidding stages in the German energy market. The EMS utilizes supervisory control and data acquisition (SCADA) measurements from the site to improve power forecast from the wind power plant. First, the measurement data are used together with numerical weather prediction data to accurately forecast local wind conditions. Second, the measurement data are used to adapt a baseline engineering wake model that gives the total wind power generation for a given input wind condition. The EMS also uses an online cyclic damage minimization approach to accurately balance the battery damage cost against the revenue obtained by market bidding. An HPP controller is formulated to ensure proper tracking of optimal set-points. When compared with standard formulations, the proposed approach shows an accurate estimation and balancing of revenue and costs and a significant reduction in the power deviation penalty, which leads to significantly higher overall profit.

show abstract

Data-driven virtual sensor for online loads estimation of drivetrain of wind turbines

Kamel

Kretschmer²,

Pfeifer³

et al. 2023

Forsch Ingenieurwes

View full text Add to dashboard Cite

Data-driven approaches have gained interest recently in the field of wind energy. Data-driven online estimators have been investigated and demonstrated in several applications such as online loads estimation, wake center position estimations, online damage estimation. The present work demonstrates the application of machine learning algorithms to formulate an estimator of the internal loads acting on the bearings of the drivetrain of onshore wind turbines. The loads estimator is implemented as a linear state-space model that is augmented with a non-linear feed-forward neural network. The estimator infers the loads time series as a function of the standard measurements from the SCADA and condition monitoring systems (CMS). A formal analysis of the available data is carried out to define the structure of the virtual sensor regarding the order of the models, number of states, architecture of neural networks. Correlation coefficient of 98% in the time domain and matching of the frequency signature are achieved. Several applications are mentioned and discussed in this work such as online estimation of the forces for monitoring and model predictive control applications.

show abstract

Economic nonlinear model predictive control of fatigue for a hybrid wind-battery generation system

Cited by 5 publications

References 20 publications

Site-specific production forecast through data-driven and engineering models

Site-specific production forecast through data-driven and engineering models

Profit-optimal data-driven operation of a hybrid power plant participating in energy markets

Data-driven virtual sensor for online loads estimation of drivetrain of wind turbines

Contact Info

Product

Resources

About