The wind farm control problem is challenging, since conventional model-based control strategies require tractable models of complex aerodynamical interactions between the turbines and suffer from the curse of dimension when the number of turbines increases. Recently, model-free and multi-agent reinforcement learning approaches have been used to address this challenge. In this article, we introduce WFCRL (Wind Farm Control with Reinforcement Learning), the first open suite of multi-agent reinforcement learning environments for the wind farm control problem. WFCRL frames a cooperative Multi-Agent Reinforcement Learning (MARL) problem: each turbine is an agent and can learn to adjust its yaw, pitch or torque to maximize the common objective (e.g. the total power production of the farm). WFCRL also offers turbine load observations that will allow to optimize the farm performance while limiting turbine structural damages. Interfaces with two state-of-the-art farm simulators are implemented in WFCRL: a static simulator (FLORIS) and a dynamic simulator (FAST.Farm). For each simulator, 10 wind layouts are provided, including 5 real wind farms. Two state-of-the-art online MARL algorithms are implemented to illustrate the scaling challenges. As learning online on FAST.Farm is highly time-consuming, WFCRL offers the possibility of designing transfer learning strategies from FLORIS to FAST.Farm.

Wind energy resource quantification, air pollution monitoring, and weather forecasting all rely on rapid, accurate measurement of local wind conditions. Visual observations of the effects of wind--the swaying of trees and flapping of flags, for example--encode information regarding local wind conditions that can potentially be leveraged for visual anemometry that is inexpensive and ubiquitous. Here, we demonstrate a coupled convolutional neural network and recurrent neural network architecture that extracts the wind speed encoded in visually recorded flow-structure interactions of a flag and tree in naturally occurring wind. Predictions for wind speeds ranging from 0.75-11 m/s showed agreement with measurements from a cup anemometer on site, with a root-mean-squared error approaching the natural wind speed variability due to atmospheric turbulence. Generalizability of the network was demonstrated by successful prediction of wind speed based on recordings of other flags in the field and in a controlled wind tunnel test. Furthermore, physicsbased scaling of the flapping dynamics accurately predicts the dependence of the network performance on the video frame rate and duration.

We propose a novel Bayesian approach to modelling nonlinear alignments of time series based on latent shared information. We apply the method to the real-world problem of finding common structure in the sensor data of wind turbines introduced by the underlying latent and turbulent wind field. The proposed model allows for both arbitrary alignments of the inputs and non-parametric output warpings to transform the observations. This gives rise to multiple deep Gaussian process models connected via latent generating processes. We present an efficient variational approximation based on nested variational compression and show how the model can be used to extract shared information between dependent time series, recovering an interpretable functional decomposition of the learning problem. We show results for an artificial data set and real-world data of two wind turbines.

The new assets we provide in this paper are listed hereafter. Moreover, IMP-MARL contains wrappers to facilitate its implementation on typical MARL ecosystems, i.e., Gym [42], RLLib [45], and PyMarl [9], as detailed in Section 4. To reproduce the work reported in this paper, the following process can be executed: (i) cloning the repository, (ii) installing a virtual environment with the package requirements, and (iii) executing the script instructions of the corresponding method and IMP-MARL environments. In addition to the instructions for reproducing our results, we also provide tutorials to add new environments or wrappers. We also provide the data files resulting from our experiments, enabling the reproduction of any reported result without re-running the experiments, as well as the corresponding implementation code, hence facilitating future cross-comparisons. The readily available results include Figures 3, 11, and 12, along with Tables 13, 14, 15. Configuration, execution, and results files are permanently stored at Zenodo, accessible via https:// zenodo.org/record/8032339. Additionally, the controller networks' weights of the best policies presented in Figure 3 are also stored there, thus fostering further interpretability studies of MARLbased strategies. The dataset is open-access and registered with the Digital Object Identifier (DOI) 10.5281/zenodo.8032339. More information and dedicated tutorials can be found on the repository.

We introduce IMP-MARL, an open-source suite of multi-agent reinforcement learning (MARL) environments for large-scale Infrastructure Management Planning (IMP), offering a platform for benchmarking the scalability of cooperative MARL methods in real-world engineering applications. In IMP, a multi-component engineering system is subject to a risk of failure due to its components' damage condition. Specifically, each agent plans inspections and repairs for a specific system component, aiming to minimise maintenance costs while cooperating to minimise system failure risk. With IMP-MARL, we release several environments including one related to offshore wind structural systems, in an effort to meet today's needs to improve management strategies to support sustainable and reliable energy systems. Supported by IMP practical engineering environments featuring up to 100 agents, we conduct a benchmark campaign, where the scalability and performance of state-of-the-art cooperative MARL methods are compared against expert-based heuristic policies. The results reveal that centralised training with decentralised execution methods scale better with the number of agents than fully centralised or decentralised RL approaches, while also outperforming expert-based heuristic policies in most IMP environments. Based on our findings, we additionally outline remaining cooperation and scalability challenges that future MARL methods should still address. Through IMP-MARL, we encourage the implementation of new environments and the further development of MARL methods.

Drones could be used for NHS-related missions in remote areas, inspecting offshore wind turbines and supplying oil rigs by 2026 as part of a new regulatory regime in the UK. David Willetts, the head of a new government unit helping to deploy new technologies in Britain, said there were obvious situations where drones could be used if the changes go ahead next year. Ministers announced plans this month to allow drones to fly long distances without their operators seeing them. Drones cannot be flown "beyond visual line of sight" under current regulations, making their use for lengthy journeys impossible. In an interview with the Guardian, Lord Willetts, chair of the Regulatory Innovation Office (RIO), said the changes could come as soon as 2026, but that they would apply in "atypical" aviation environments at first, which would mean remote areas and over open water. Referring to the NHS, Willetts said there was potentially a huge market for drone operators.

We study a long-run mean-variance team stochastic game (MV-TSG), where each agent shares a common mean-variance objective for the system and takes actions independently to maximize it. MV-TSG has two main challenges. First, the variance metric is neither additive nor Markovian in a dynamic setting. Second, simultaneous policy updates of all agents lead to a non-stationary environment for each individual agent. Both challenges make dynamic programming inapplicable. In this paper, we study MV-TSGs from the perspective of sensitivity-based optimization. The performance difference and performance derivative formulas for joint policies are derived, which provide optimization information for MV-TSGs. We prove the existence of a deterministic Nash policy for this problem. Subsequently, we propose a Mean-Variance Multi-Agent Policy Iteration (MV-MAPI) algorithm with a sequential update scheme, where individual agent policies are updated one by one in a given order. We prove that the MV-MAPI algorithm converges to a first-order stationary point of the objective function. By analyzing the local geometry of stationary points, we derive specific conditions for stationary points to be (local) Nash equilibria, and further, strict local optima. To solve large-scale MV-TSGs in scenarios with unknown environmental parameters, we extend the idea of trust region methods to MV-MAPI and develop a multi-agent reinforcement learning algorithm named Mean-Variance Multi-Agent Trust Region Policy Optimization (MV-MATRPO). We derive a performance lower bound for each update of joint policies. Finally, numerical experiments on energy management in multiple microgrid systems are conducted.

The wind farm control problem is challenging, since conventional model-based control strategies require tractable models of complex aerodynamical interactions between the turbines and suffer from the curse of dimension when the number of turbines increases. Recently, model-free and multi-agent reinforcement learning approaches have been used to address this challenge. In this article, we introduce WFCRL (Wind Farm Control with Reinforcement Learning), the first open suite of multi-agent reinforcement learning environments for the wind farm control problem. WFCRL frames a cooperative Multi-Agent Reinforcement Learning (MARL) problem: each turbine is an agent and can learn to adjust its yaw, pitch or torque to maximize the common objective (e.g. the total power production of the farm). WFCRL also offers turbine load observations that will allow to optimize the farm performance while limiting turbine structural damages. Interfaces with two state-of-the-art farm simulators are implemented in WFCRL: a static simulator (FLORIS) and a dynamic simulator (FAST.Farm). For each simulator, 10 wind layouts are provided, including 5 real wind farms. Two state-of-the-art online MARL algorithms are implemented to illustrate the scaling challenges. As learning online on FAST.Farm is highly time-consuming, WFCRL offers the possibility of designing transfer learning strategies from FLORIS to FAST.Farm.

Contextual Bayesian optimization (CBO) is a powerful framework for sequential decision-making given side information, with important applications, e.g., in wind energy systems. In this setting, the learner receives context (e.g., weather conditions) at each round, and has to choose an action (e.g., turbine parameters). Standard algorithms assume no cost for switching their decisions at every round. However, in many practical applications, there is a cost associated with such changes, which should be minimized. We introduce the episodic CBO with movement costs problem and, based on the online learning approach for metrical task systems of Coester and Lee [19], propose a novel randomized mirror descent algorithm that makes use of Gaussian Process confidence bounds. We compare its performance with the offline optimal sequence for each episode and provide rigorous regret guarantees. We further demonstrate our approach on the important real-world application of altitude optimization for Airborne Wind Energy Systems. In the presence of substantial movement costs, our algorithm consistently outperforms standard CBO algorithms.

--Short-term forecasting models typically assume the availability of input data (features) when they are deployed and in use. However, equipment failures, disruptions, cyberattacks, may lead to missing features when such models are used operationally, which could negatively affect forecast accuracy, and result in suboptimal operational decisions. In this paper, we use adaptive robust optimization and adversarial machine learning to develop forecasting models that seamlessly handle missing data operationally. We propose linear-and neural network-based forecasting models with parameters that adapt to available features, combining linear adaptation with a novel algorithm for learning data-driven uncertainty set partitions. The proposed adaptive models do not rely on identifying historical missing data patterns and are suitable for real-time operations under stringent time constraints. Extensive numerical experiments on short-term wind power forecasting considering horizons from 15 minutes to 4 hours ahead illustrate that our proposed adaptive models are on par with imputation when data are missing for very short periods (e.g., when only the latest measurement is missing) whereas they significantly outperform imputation when data are missing for longer periods. We further provide insights by showcasing how linear adaptation and data-driven partitions (even with a few subsets) approach the performance of the optimal, yet impractical, method of retraining for every possible realization of missing data. Index T erms--Short-term forecasting, wind power forecasting, missing data, adaptive robust optimization, data-driven uncertainty set partitioning, adversarial learning. V ariable renewable energy sources, such as wind and solar, dominate low-carbon power systems. To deal with their inherent uncertainty and variability, system operators manage operational risk based on a forward-looking grid status estimation [1]. For instance, they run short-term scheduling applications to evaluate the reliability of market-based dispatch, which are based on short-term energy forecasts with a horizon ranging from a few minutes to several hours ahead [2]. A. Background and Motivation A critical assumption underpinning the forecasting models is that input data, a.k.a.