In many decision settings, the definitive ground truth is either non-existent or inaccessible. We introduce a framework for evaluating classifiers based solely on human judgments. In such cases, it is helpful to compare automated classifiers to human judgment. We quantify a classifier's performance by its rater equivalence: the smallest number of human raters whose combined judgment matches the classifier's performance. Our framework uses human-generated labels both to construct benchmark panels and to evaluate performance. We distinguish between two models of utility: one based on agreement with the assumed but inaccessible ground truth, and one based on matching individual human judgments. Using case studies and formal analysis, we demonstrate how this framework can inform the evaluation and deployment of AI systems in practice.

Machine Learning models are increasingly used in businesses to detect faults and anomalies in complex systems. In this work, we take this approach a step further: beyond merely detecting anomalies, we aim to identify the optimal control strategy that restores the system to a safe state with minimal disruption. We frame this challenge as a counterfactual problem: given a Machine Learning model that classifies system states as either "good" or "anomalous," our goal is to determine the minimal adjustment to the system's control variables (i.e., its current status) that is necessary to return it to the "good" state. To achieve this, we leverage a mathematical model that finds the optimal counterfactual solution while respecting system-specific constraints. Notably, most counterfactual analysis in the literature focuses on individual cases where a person seeks to alter their status relative to a decision made by a classifier--such as for loan approval or medical diagnosis. Our work addresses a fundamentally different challenge: optimizing counterfactuals for a complex energy system, specifically an offshore wind turbine oil-type transformer. This application not only advances counterfactual optimization in a new domain but also opens avenues for broader research in this area. Our tests on real-world data provided by our industrial partner show that our methodology easily adapts to user preferences and brings savings in the order of 3 million e per year in a typical farm. Introduction Energy systems are becoming increasingly more complex, making it more challenging--and more critical--to detect faults early and develop strategies to mitigate them. In this context, Machine Learning (ML) techniques have become an industry standard for early fault detection [16]. Energy companies can monitor various sensor readings from the turbines and apply ML methods to identify potential issues with components. In this paper, we define a fault (or faulty state) as a condition where a component is in an unsafe status, while an anomaly refers to any irregularity that is not necessarily dangerous. Note that faults are a subset of anomalies. When a fault is detected, a controller is immediately activated to prevent severe damage to the turbine. Machine Learning models can detect anomalies in advance, providing companies with a window of time to intervene before faults occur.

With the increasing amount of renewable energy in the grid, long-term wind power forecasting for multiple decades becomes more critical. In these long-term forecasts, climate data is essential as it allows us to account for climate change. Yet the resolution of climate models is often very coarse. In this paper, we show that by including turbine locations when downscaling with Gaussian Processes, we can generate valuable aggregate wind power predictions despite the low resolution of the CMIP6 climate models. This work is a first step towards multi-decadal turbine-location-aware wind power forecasting using global climate model output.

This information was projected on the life cycle of the Their distributed communicating nature makes them vulnerable turnout according to time aging and operation aging to cyberattacks [2]. The security of CPS has criteria in order to compute a cyberthreat likelihood for emerged as a complex problem, after discovering the each current curve observed. Maintenance operators use Stuxnet malware [3] that targeted the Iranian industrial the estimated likelihood to assess the authenticity of each control system.

Wind turbine power curve models translate ambient conditions into turbine power output. They are essential for energy yield prediction and turbine performance monitoring. In recent years, increasingly complex machine learning methods have become state-of-the-art for this task. Nevertheless, they frequently encounter criticism due to their apparent lack of transparency, which raises concerns regarding their performance in non-stationary environments, such as those faced by wind turbines. We, therefore, introduce an explainable artificial intelligence (XAI) framework to investigate and validate strategies learned by data-driven power curve models from operational wind turbine data. With the help of simple, physics-informed baseline models it enables an automated evaluation of machine learning models beyond standard error metrics. Alongside this novel tool, we present its efficacy for a more informed model selection. We show, for instance, that learned strategies can be meaningful indicators for a model's generalization ability in addition to test set errors, especially when only little data is available. Moreover, the approach facilitates an understanding of how decisions along the machine learning pipeline, such as data selection, pre-processing, or training parameters, affect learned strategies. In a practical example, we demonstrate the framework's utilisation to obtain more physically meaningful models, a prerequisite not only for robustness but also for insights into turbine operation by domain experts. The latter, we demonstrate in the context of wind turbine performance monitoring. Alongside this paper, we publish a Python implementation of the presented framework and hope this can guide researchers and practitioners alike toward training, selecting and utilizing more transparent and robust data-driven wind turbine power curve models.

The ever-growing use of wind energy makes necessary the optimization of turbine operations through pitch angle controllers and their maintenance with early fault detection. It is crucial to have accurate and robust models imitating the behavior of wind turbines, especially to predict the generated power as a function of the wind speed. Existing empirical and physics-based models have limitations in capturing the complex relations between the input variables and the power, aggravated by wind variability. Data-driven methods offer new opportunities to enhance wind turbine modeling of large datasets by improving accuracy and efficiency. In this study, we used physics-informed neural networks to reproduce historical data coming from 4 turbines in a wind farm, while imposing certain physical constraints to the model. The developed models for regression of the power, torque, and power coefficient as output variables showed great accuracy for both real data and physical equations governing the system. Lastly, introducing an efficient evidential layer provided uncertainty estimations of the predictions, proved to be consistent with the absolute error, and made possible the definition of a confidence interval in the power curve.

Accurate wind turbine power curve models, which translate ambient conditions into turbine power output, are crucial for wind energy to scale and fulfill its proposed role in the global energy transition. While machine learning (ML) methods have shown significant advantages over parametric, physics-informed approaches, they are often criticised for being opaque 'black boxes', which hinders their application in practice. We apply Shapley values, a popular explainable artificial intelligence (XAI) method, and the latest findings from XAI for regression models, to uncover the strategies ML models have learned from operational wind turbine data. Our findings reveal that the trend towards ever larger model architectures, driven by a focus on test set performance, can result in physically implausible model strategies. Therefore, we call for a more prominent role of XAI methods in model selection. Moreover, we propose a practical approach to utilize explanations for root cause analysis in the context of wind turbine performance monitoring. This can help to reduce downtime and increase the utilization of turbines in the field.

The fast development of renewable energies is a necessity to mitigate climate changes [22]. Wind energy has developed rapidly over the past three decades, with an average annual growth rate of 23.6% between 1990 and 2016 [17], and is now considered as a mature technology. The share of renewable energies in global electricity generation reached 29% in 2020, and is expected to keep growing fast in coming years [18] which raises a number of challenges, stemming from the variability and spatial distribution of the resource. Then, in order to facilitate the dynamic management of electricity networks, forecasts of wind energy require continual improvement. Short timescales, from a few minutes to a few hours, are of particular importance for operations. To produce forecasts, one can rely on several distinct sources of information. On timescales of half a day to about a week, deterministic weather forecasts provide a representation on a grid of the atmospheric state, including wind speed near the surface. The skill of such numerical weather forecasts (NWP) models has continually increased over the past decades [2], while their spatial resolution has also grown finer (down to few km).

Different machine learning (ML) models are trained on SCADA and meteorological data collected at an onshore wind farm and then assessed in terms of fidelity and accuracy for predictions of wind speed, turbulence intensity, and power capture at the turbine and wind farm levels for different wind and atmospheric conditions. ML methods for data quality control and pre-processing are applied to the data set under investigation and found to outperform standard statistical methods. A hybrid model, comprised of a linear interpolation model, Gaussian process, deep neural network (DNN), and support vector machine, paired with a DNN filter, is found to achieve high accuracy for modeling wind turbine power capture. Modifications of the incoming freestream wind speed and turbulence intensity, $TI$, due to the evolution of the wind field over the wind farm and effects associated with operating turbines are also captured using DNN models. Thus, turbine-level modeling is achieved using models for predicting power capture while farm-level modeling is achieved by combining models predicting wind speed and $TI$ at each turbine location from freestream conditions with models predicting power capture. Combining these models provides results consistent with expected power capture performance and holds promise for future endeavors in wind farm modeling and diagnostics. Though training ML models is computationally expensive, using the trained models to simulate the entire wind farm takes only a few seconds on a typical modern laptop computer, and the total computational cost is still lower than other available mid-fidelity simulation approaches.

A wind turbines' power curve is easily accessible damage sensitive data, and as such is a key part of structural health monitoring in wind turbines. Power curve models can be constructed in a number of ways, but the authors argue that probabilistic methods carry inherent benefits in this use case, such as uncertainty quantification and allowing uncertainty propagation analysis. Many probabilistic power curve models have a key limitation in that they are not physically meaningful - they return mean and uncertainty predictions outside of what is physically possible (the maximum and minimum power outputs of the wind turbine). This paper investigates the use of two bounded Gaussian Processes in order to produce physically meaningful probabilistic power curve models. The first model investigated was a warped heteroscedastic Gaussian process, and was found to be ineffective due to specific shortcomings of the Gaussian Process in relation to the warping function. The second model - an approximated Gaussian Process with a Beta likelihood was highly successful and demonstrated that a working bounded probabilistic model results in better predictive uncertainty than a corresponding unbounded one without meaningful loss in predictive accuracy. Such a bounded model thus offers increased accuracy for performance monitoring and increased operator confidence in the model due to guaranteed physical plausibility.