A surrogate model of offshore wind farm support structures for wind farm design and financial valuation

McWilliam, Michael; Friis-Møller, Mikkel; Pollini, Nicolò; Dykes, Katherine; Jensen, Morten Hasselstrøm

doi:10.1088/1742-6596/2265/4/042048

Cited by 3 publications

(3 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For monopile-based support structures, monopiles and towers are designed following ref. [13], and the transition piece is sized based on ref. [14].…”

Section: Plant Setup and Sizingmentioning

confidence: 99%

How do technological choices affect the economic and environmental performance of offshore wind farms?

Kainz,

Guilloré,

Bottasso

2024

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

The ongoing energy transition towards fully sustainable energy systems requires designing wind farms looking beyond the sole levelized cost of energy, in order to concurrently ensure not only the economic profitability but also the environmental friendliness of future plants. Within this new approach to design, it becomes necessary to understand the effects that various possible technological choices have on both the economic and the environmental performance of wind farms. This study presents a framework designed to support these coupled economic-environmental assessments. The capabilities of the code are showcased by analysing the impact of different choices in terms of support structure type, specific power, tower height, powertrain type, and array and export voltage level for an exemplary offshore farm, chosen here as the IEA Wind 740-10-MW Reference Offshore Wind Plant with irregular layout. While the effects of many technological choices on the cost of energy are already well understood by industry, the present analysis shows that — at least in this specific case — climate change impacts are mainly driven by steel production, due to the massive amount of required material, but also, interestingly, by vessel activities. A low specific power, tall towers, and a high export cable voltage appear to offer the greatest potential for the concurrent improvement of the environmental and economic performance of the plant.

show abstract

“…For monopile-based support structures, monopiles and towers are designed following ref. [13], and the transition piece is sized based on ref. [14].…”

Section: Plant Setup and Sizingmentioning

confidence: 99%

How do technological choices affect the economic and environmental performance of offshore wind farms?

Kainz,

Guilloré,

Bottasso

2024

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

show abstract

“…• Site design: Layout geometry, row spacing, staggering, and orientation In addition to the farm level classification, a series of wind turbines of different characteristics were developed to explore the influence of parameters related to rated power, rotor diameter, and specific power on turbine power and thrust curves -and thus wake losses and power production. The series of turbines were generated via optimization using the NREL WISDEM software as described in [14,15]. The range of turbine power ratings ranged from 3 to 20 MW and specific powers from 250 to 350 W/m2.…”

Section: Classificationmentioning

confidence: 99%

A surrogate model of offshore wind farm annual energy production to support financial evaluation

Rodrigues

Friis-Møller

Dykes

et al. 2022

J. Phys.: Conf. Ser.

Self Cite

View full text Add to dashboard Cite

The preliminary financial evaluation of wind farm profitability requires fast analysis of energy production and costs while having very little specific information around the project. Early in the design process, the selection of specific wind turbines and the layout design may not yet be defined. Techno-economic and financial analysis models have been developed to use input from a small set of high-level project characteristics to estimate major cost elements and energy production for a wind farm to support quick analysis of levelized cost of energy (LCoE), or other financial metrics. Such models are typically based on prior project data and/or very simple analytical models. However, as capabilities for financial analysis of wind farms advance, so does the desire to improve the accuracy of the physical and cost modelling of the system. In this work, we develop a surrogate model of Annual Energy Production (AEP) for offshore wind farms for financial analysis applications in the early stages of development. The surrogate is developed from an parameterized engineering model and covers a large potential wind farm design space addressing different technological and site conditions. The surrogate model uncovers the underlying structure in the model in terms of input-output relationships and achieves a coefficient of determination of 0.994. The method used to develop the surrogate model can be adapted for additional dimensions of inputs as needed.

show abstract

“…Surrogate modeling, such as with Gaussian Process Regression (GPR) [52,59], additionally allows the deployment of techniques from the optimal experimental design literature [13,30,51], where initial simulation or experimental results are used to improve subsequent designs [9,10,42,54,55]. While optimal experiment design techniques are not yet widely used in offshore wind applications, some recent studies have focused on developing reduced order models (surrogate models) for studying the support structure characteristics [41] and dynamic response [60,69] of offshore wind turbines.…”

Section: Introductionmentioning

confidence: 99%

Statistical modeling of fully nonlinear hydrodynamic loads on offshore wind turbine foundations using wave episodes and targeted CFD simulations through active sampling

Guth

Katsidoniotaki

Sapsis

2023

Preprint

View full text Add to dashboard Cite

For many design applications in offshore engineering, including offshore wind turbine foundations, engineers need accurate statistics for kinematic and dynamic quantities, such as hydrodynamic forces, whose statistics depend on the stochastic sea surface elevation. Nonlinear phenomena in the wave–structure interaction require high-fidelity simulations to be analyzed accurately. However, accurate quantification of statistics requires a massive number of simulations, and the computational cost is prohibitively expensive. To avoid that cost, this study presents a machine learning framework to develop a reliable surrogate model that minimizes the need for computationally expensive numerical simulations, which is implemented for the monopile foundation of an offshore wind turbine. This framework consists of two parts. The first focuses on dimensionality reduction of stochastic irregular wave episodes and the resulting hydrodynamic force time series. The second of the framework focuses on the development of a Gaussian process regression surrogate model which learns a mapping between the wave episode and the force-on-structure. This surrogate uses a Bayesian active learning method that sequentially samples the wave episodes likely to contribute to the accurate prediction of extreme hydrodynamic forces in order to design subsequent CFD numerical simulations. Additionally, the study implements a spectrum transfer technique to combine CFD results from quiescent and extreme waves. The principal advantage of this framework is that the trained surrogate model is orders of magnitude faster to evaluate than the classical modeling methods, while built-in uncertainty quantification capabilities allows for efficient sampling of the parameter using with the CFD tools traditionally employed.

show abstract

A surrogate model of offshore wind farm support structures for wind farm design and financial valuation

Cited by 3 publications

References 8 publications

How do technological choices affect the economic and environmental performance of offshore wind farms?

How do technological choices affect the economic and environmental performance of offshore wind farms?

A surrogate model of offshore wind farm annual energy production to support financial evaluation

Statistical modeling of fully nonlinear hydrodynamic loads on offshore wind turbine foundations using wave episodes and targeted CFD simulations through active sampling

Contact Info

Product

Resources

About