the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Modular deep learning approach for wind farm power forecasting and wake loss prediction
Abstract. Power production of offshore wind farms depends on many parameters and is significantly affected by wake losses. Due to the variability of wind power and its rapidly increasing share in the total energy mix, accurate forecasting of the power production of a wind farm becomes increasingly important. This paper presents a novel data-driven methodology to construct a fast and accurate wind farm power model. The deep learning model is not limited to steady-state situations, but captures also the influence of temporal wind dynamics and the farm power controller on the power production of the wind farm. With a multi-component pipeline, multiple weather forecasts of meteorological forecast providers are incorporated to generate farm power forecasts over multiple time horizons. Furthermore, in conjunction with a data-driven turbine power model, the wind farm model can be used also to predict the wake losses. The proposed methodology includes a quantification of the prediction uncertainty, which is important for trading and power control applications. A key advantage of the data-driven approach is the high prediction speed compared to physics-based methods, such that it can be employed for applications where faster than real-time power forecasting is required. It is shown that accuracy of the proposed power prediction model is better than for some baseline machine learning models. The methodology is demonstrated for two large real-world offshore wind farms located within the Belgian-Dutch wind farm cluster in the North Sea.
- Preprint
(2247 KB) - Metadata XML
- BibTeX
- EndNote
Status: open (until 03 Oct 2024)
-
RC1: 'Comment on wes-2024-94', Anonymous Referee #1, 05 Sep 2024
reply
In this work, the authors lay out a multi-part modeling framework for making estimates of real-time power output and future projections of the performance of a real farm. They construct a series of deep learning models to map from forecasted wind conditions to real farm-observed conditions, through to a fast, accurate, and uncertainty-imbued power estimate for the farm. The result is an exemplary application of machine learning techniques to a relevant wind engineering problem that is immediately useful to farm operators.
I have two major criticisms of the manuscript, primarily centered on exposition of the methods of the work. In the wind farm control model, some clarity could be added in consideration of the intended audience of WES, who are not AI/ML users. A more circumspect description of terms including but not limited to, "convolution branches", "feed-forward neural network", "dropout layers", and "dense layers", would be useful to allow the audience-- myself included-- view the machine learning aspects of the work on their merits rather than simply as a black box Additionally, the exposition of the weather forecasting methods is sparse and should be significantly expanded. Because it holds a key to the application of the work in this manuscript, it should be clear how it works and what is strengths and weaknesses are, especially in light of the results for lookahead forecasting.
I would also like to see more analysis of the results. The model clearly performs well to make estimates of the farm power in static wind conditions. The results in dynamic conditions are less clear to interpret, and additional text and clarification of the plots in Figures 21 and 22 would be appreciated. This seems to be a major benefit that can be conferred by this approach and thus more clarity around this area would be very valuable to the end result. Moreover, this would couple with better exposition of the forecasting efforts such that together they can be used to understand where and how this approach leads to errors in forecasted farm power.
I have a few additional small technical notes, which are addressed below by line number:
- 177: the heuristic sorting algorithm for turbine selection is slightly unclear and also possibly could be effected by flow heterogeneity, blockage, or terrain; please clarify the choice of this algorithm versus purely geographic sorting, etc.
- 216: the weather forecast data, like the weather forecast modeling, lacks clarity of what it contains and how it is used
- 239: be careful with the use of "instantaneous" response variables, they can often have significant inertial effects that should be justified
- ~370: the frequency of wind resource conditions is unclear, and this passes through to understanding how frequent high TI/high wind direction variance conditions occur in e.g. Figure 6; consider highlighting wind condition frequency in some way
- 416: I suggest quantifying the quality of the CI estimates: the value should be in the 68% CI explicitly 68% of the time (rather than "most of the time") and leave the 95% CI 5% of the time (i.e. "rarely") for a well posed confidence interval
Overall the paper is of high quality and in my opinion is an exemplary application of ML to a relevant problem to wind energy researchers and operators.
Citation: https://doi.org/10.5194/wes-2024-94-RC1
Viewed
HTML | XML | Total | BibTeX | EndNote | |
---|---|---|---|---|---|
122 | 32 | 41 | 195 | 2 | 3 |
- HTML: 122
- PDF: 32
- XML: 41
- Total: 195
- BibTeX: 2
- EndNote: 3
Viewed (geographical distribution)
Country | # | Views | % |
---|
Total: | 0 |
HTML: | 0 |
PDF: | 0 |
XML: | 0 |
- 1