Transmission network topology control offers cheap flexibility to system operators for mitigating grid congestion. However, finding the optimal sequence of topology actions remains a challenge due to the large number of possible actions. Although reinforcement learning (RL) approaches have attracted interest for long-term planning in large combinatorial action spaces, they encounter challenges such as training stability, sample efficiency, and unforeseen consequences of RL actions. Addressing these challenges, this paper proposes a hybrid curriculum-trained RL and Monte Carlo tree search (MCTS) approach to determine sequential topological actions for mitigating grid congestion. The curriculum-based approach stabilizes training by first pre-training a policy network through supervised imitation learning, followed by RL training. The policy network guides the MCTS to simulate promising future trajectories, mitigating unforeseen consequences and identifying long-term strategies to improve grid security. Moreover, the MCTS-verified actions are used for RL training, enhancing sample efficiency and training time. A distance factor is added to the MCTS, which improves convergence by prioritizing actions closer to congestion. Numerical results on the IEEE 118-bus system show that the proposed hybrid approach improves the timesteps survived by 30% compared to a standard RL approach, and by 5% compared to a brute-force baseline. Additionally, the inclusion of the distance factor increases the timesteps survived by 15%. These results highlight the potential of the proposed method for real-world applications of using sequential topological actions to effectively relieve grid congestion.

Ground fault detection in inverter-based microgrid (IBM) systems is challenging, particularly in a real-time setting, as the fault current deviates slightly from the nominal value. This difficulty is reinforced when there are partially decoupled disturbances and modeling uncertainties. The conventional solution of installing more relays to obtain additional measurements is costly and also increases the complexity of the system. In this brief, we propose a data-assisted diagnosis scheme based on an optimization-based fault detection filter with the output current as the only measurement. Modeling the microgrid dynamics and the diagnosis filter, we formulate the filter design as a quadratic programming (QP) problem that accounts for decoupling partial disturbances, robustness to nondecoupled disturbances and modeling uncertainties by training with data, and ensuring fault sensitivity simultaneously. To ease the computational effort, we also provide an approximate but analytical solution to this QP. Additionally, we use classical statistical results to provide a thresholding mechanism that enjoys probabilistic false-alarm guarantees. Finally, we implement the IBM system with Simulink and real-time digital simulator (RTDS) to verify the effectiveness of the proposed method through simulations.

The increasing share of uncertain renewable energy sources (RES) in power systems necessitates new efficient approaches for the two-stage stochastic multi-period AC optimal power flow (St-MP-OPF) optimization. The computational complexity of St-MP-OPF, particularly with AC constraints, grows exponentially with the number of uncertainty scenarios and the time horizon. This complexity poses significant challenges for large-scale transmission systems that require numerous scenarios to capture RES stochasticities. This paper introduces a scenario-based decomposition of the St-MP-OPF based on the alternating direction method of multipliers (ADMM). Additionally, this paper proposes a machine learning-accelerated ADMM approach (ADMM-ML), facilitating rapid and parallel computations of numerous scenarios with extended time horizons. Within this approach, a recurrent neural network approximates the ADMM sub-problem optimization and predicts wait-and-see decisions for uncertainty scenarios, while a master optimization determines here-and-now decisions. Additionally, we develop a hybrid approach that uses ML predictions to warm-start the ADMM algorithm, combining the computational efficiency of ML with the feasibility and optimality guarantees of optimization methods. The numerical results on the 118-bus and 1354-bus system show that the proposed ADMM-ML approach solves the St-MP-OPF with 3-4 orders of magnitude speed-ups, while the hybrid approach provides a balance between speed-ups and optimality.

Battery energy storage systems offer control over energy use and enable energy arbitrage (EA) helping to lower energy costs. However, battery owners currently fail to optimally exploit these systems for EA as the battery lifetime decreases, and many EA approaches incorrectly assume constant battery capacity. Battery performance declines over time resulting in reduced capacity that limits the economic benefits. Therefore, considering battery degradation is key to balancing economic profit and lifetime. In response, this work applies reinforcement learning to control a battery providing residential EA services and proposes a semi-supervised learning model to consider degradation. Case studies investigate three scenarios: 1) the approach is trained on a battery with an unrealistic constant maximum capacity to serve as a baseline, 2) the actions from the first scenario are applied to a real-world environment with a battery experiencing capacity decay to acknowledge the effect of neglecting degradation and 3) the approach considers a battery with a real decreasing capacity. Results show not considering degradation when operating a battery (scenario 2), leads to profits 13% lower than the ones obtained in the ideal case (scenario 1). If degradation is considered (scenario 3), the profits are only 4% lower than the profits obtained in the ideal case (scenario 1) and the battery's lifetime is extended by 20% compared to the lifetime achieved when not considering degradation (scenario 2).

Coordination between power system operators can improve the power system stability and effectively deploy resources in distribution systems (DS). The research work of this paper provides a coordination method to mitigate the impact of dynamic events on transmission systems (TS). The proposed method uses a machine learning (ML)-based model to estimate the collective dynamic response of DS under varying TS dynamic properties, DS operating conditions, and share of inverter base resources (IBRs). In addition, the ML-based model enables TS operators (TSOs) to provide feedback to DS operators (DSOs) for controlling the IBRs’ active power output to prevent post-fault instabilities. The proposed TSO-DSO coordination method includes a risk-based active power setpoint optimizer for instability prevention. The proposed method uses existing measurement and IBR control platforms available in DS and estimates the post-fault DS dynamic response considering IBR active power control actions. Case studies on synthetic models of TS and DS covering the Zeeland province in The Netherlands illustrate the application of the proposed coordination and the instability risk mitigation when optimizing IBR setpoints.

The growing share of renewable energy in shortterm European electricity markets has significantly increased congestion management costs and demands. Therefore, current market design is not optional to keep congestion costs low. A proper market would incentivize the integration of flexibilities to boost competition and lower costs, while mitigating risks of manipulation. However, assessing behavioral impacts is challenging due to increasingly interconnected market structures. Studies modeling more than two markets often overlook the strategic opportunities that emerge from these interactions, focusing instead on large-scale dynamics. To capture the detailed impact of bidding strategies, we use reinforcement learning to explore multi-market strategies. By progressively training a Deep Reinforcement Learning (DRL) agent as a market participant - from replicating established behaviors to mastering intricate multimarket interactions - we employ Domain-Informed Curriculum Learning (DomCL), a structured approach that systematically guides learning through staged complexity. We validate our approach against established two-market studies, then evaluate it in two progressively complex four-market case studies spanning a 6-bus network, including historical data. Results show that our DRL-based method improves performance while uncovering challenges that arise as strategic opportunities expand, offering a structured approach for multi-market design analysis.

Time domain simulation (TDS) is an important tool for assessing power system security under various disturbances. However, its computational cost limits the number of disturbances that can be assessed. The need for fast assessment of numerous disturbances has increased with the rapid integration of renewable energy sources. Machine learning (ML) methods have been explored to accelerate power system TDS, but these methods are studied in interpolation scenarios, where they predict outputs for inputs within the training data distribution. This work uses a state-of-the-art ML model to explore the extrapolation behavior of ML models for TDS. First, we highlight the importance of ML models’ extrapolation capacity for fast assessment of numerous diverse disturbances. Next, we demonstrate that extrapolation for discrete disturbances is more challenging than for continuous disturbances. Subsequently, we investigate how transfer learning (TL) may be used to improve the performance of ML models in TDS extrapolation scenarios. Finally, we outline the limitations of TL for power system TDS and suggest alternative approaches for developing ML models with better extrapolation performance in TDS applications.

Power system operators need new, efficient operational tools to use the flexibility of distributed resources and deal with the challenges of highly uncertain and variable power systems. Transmission system operators can consider the available flexibility in distribution systems (DSs) without breaching the DS constraints through flexibility areas. However, there is an absence of open-source packages for flexibility area estimation. This paper introduces TensorConvolutionPlus, a user-friendly Python-based package for flexibility area estimation. The main features of TensorConvolutionPlus include estimating flexibility areas using the TensorConvolution+ algorithm, the power flow-based algorithm, an exhaustive PF-based algorithm, and an optimal power flow-based algorithm. Additional features include adapting flexibility area estimations from different operating conditions and including flexibility service providers offering discrete setpoints of flexibility. The TensorConvolutionPlus package facilitates a broader adaptation of flexibility estimation algorithms by system operators and power system researchers.

Increasing renewable energy supply and distributed generating sources in the power grid lead to lower inertia levels. Lower inertia combined with higher uncertainty in operation can cause drastic frequency fluctuations when a disturbance occurs. System operators must know whether the transmission system is secure against a disturbance. Real-time models attempt to predict the frequency in near-real time however require pretraining on a large variety of possible disturbances. Training models in real-time would not require pre-training as they are directly trained on the occurring disturbance. However, training in real-time is not feasible until now as fast-occurring system dynamics require shorter prediction (and training) times for security and operation which standard machine learning models are not capable of. For the first time, this work proposes a fast training strategy that learns Neural Ordinary Differential Equations (NODE) in near real-time directly on the occurring disturbance, simultaneously addressing the inaccuracy issue of model-based dynamic studies. NODE learns the dynamics or derivatives of an ODE system that standard ODE solvers can solve. NODE provides a continuous function for predicting future dynamics in a decentralized way, hence faster frequency stability assessment for longer time spans. We propose a collocation-based sampling using the collocation gradients. Case studies on the IEEE 39-bus system show the approach is feasible for near real-time operation, accurately predicts future system states, and enables operators to apply predesigned corrective control actions, potentially making the system secure for future disturbances.

The increase in variable renewable energy sources has brought about significant changes in power system dynamics, mainly due to the widespread adoption of power electronics and nonlinear controllers. The resulting complex system dynamics and the unpredictable nature of disturbances pose substantial challenges for real-time dynamic security assessment (DSA). Machine learning (ML) methods offer advantages in terms of computational speed compared to numerical methods and simulators. Offline-trained ML models, however, are limited by their training domain; e.g., they cannot easily consider various grid topologies and data changes. Neural Ordinary Differential Equations (NODEs) leverage the integration of neural networks and ODE solvers to enable continuous-time dynamic trajectory predictions from time series data, resolving the limitation on topological and data changes. This paper introduces the Online Neural Dynamics Forecaster (ONDF) workflow, designed to monitor and assess system security in real-time using multiple NODEs trained solely with local post-fault measurements. Through several case studies, we compare the regression and DSA classification capabilities of ONDF with various ML models. Our findings demonstrate that ONDF provides a novel and scalable approach for system operators to make informed decisions and apply corrective control actions based on predicted dynamics.

This paper presents an efficient approach to battery cycle life prediction through few-shot transfer learning, addressing the challenges of costly and limited battery aging data. Leveraging freely available datasets, a multi-layer perceptron (MLP) model was pretrained on diverse battery aging datasets to adapt to new prediction tasks with minimal training samples through few-shot fine-tuning techniques on the target data. The proposed fine-tuning strategy was validated using a heterogeneous aging dataset of 347 batteries, with cycle lives ranging from 144 to 4,052 cycles, incorporating batteries with lithium iron phosphate (LFP), lithium cobalt oxide (LCO), nickel cobalt aluminum oxide (NCA), and nickel manganese cobalt oxide (NMC) chemistries, which ensures robust validation of our methods. The results show that even with few samples of data from a target task, a comparable generalization performance to training from scratch with 100% data can be achieved, thus demonstrating its effectiveness in utilizing available resources for accurate cycle life prediction.

Accelerated development of demand response service provision by the residential sector is crucial for reducing carbon-emissions in the power sector. Along with the infrastructure advancement, encouraging the end users to participate is crucial. End users highly value their privacy and control, and want to be included in the service design and decision-making process when creating the daily appliance operation schedules. Furthermore, unless they are financially or environmentally motivated, they are generally not prepared to sacrifice their comfort to help balance the power system. In this paper, we present an inverse-reinforcement-learning-based model that helps create the end users’ daily appliance schedules without asking them to explicitly state their needs and wishes. By using their past consumption data, the end consumers will implicitly participate in the creation of those decisions and will thus be motivated to continue participating in the provision of demand response services.

Advanced control, operation, and planning tools of electrical networks with ML are not straightforward. 110 experts were surveyed to show where and how ML algorithms could advance. This paper assesses this survey and research environment. Then, it develops an innovation roadmap that helps align our research community with a goal-oriented realisation of the opportunities that AI upholds. This paper finds that the R&D environment of system operators (and the surrounding research ecosystem) needs adaptation to enable faster developments with AI while maintaining high testing quality and safety. This roadmap serves system operators, academics, and labs advancing next-generation electrical network tools.

Power system operators require advanced applications in the control centers to tackle increasingly variable power transfers effectively. One urgently needed application concerns estimating the feasible available aggregated flexibility from a power system network, which can be effectively deployed to mitigate issues in interconnected networks. This paper proposes the TensorConvolution+ algorithm to address the above application. Unlike related literature approaches, TensorConvolution+ estimates the density of feasible flexibility combinations to reach a new operating point within the p-q flexibility area. This density can improve the decision-making of system operators for efficient and safe flexibility deployment. The proposed algorithm applies to radial and meshed networks, is adaptable to new operational conditions, and can consider scenarios with disconnected flexibility areas. Using convolutions and tensors, the algorithm efficiently aggregates the combinations of flexibility providers' adjustable power output that can occur for each flexibility area set point. Simulations on the meshed Oberrhein and radial CIGRE test networks illustrate the effectiveness of TensorConvolution+ for flexibility estimation with high numerical confidence and a minor computing effort. Additional simulations highlight how system operators can interpret the estimated density of feasible flexibility combinations for decision-making purposes, the algorithm's capability to estimate disconnected flexibility areas, and adapt to new operating conditions.

Extreme weather events and simultaneous k faults pose significant challenges to the security of the power system, leading to sudden line congestion. Conventionally, Line Outage Distribution Factors (LODFs) are used to compute post-fault line flows. However, as k increases, the complexity and number of required matrix inversions make these computations impractical for large systems. This paper introduces a polynomial approximation for LODFs, a method that efficiently combines and multiplies the matrices corresponding to single-line faults using Taylor series expansion. This method is faster than performing matrix inversions for each fault scenario. Moreover, we apply polynomial LODFs to compute expected line flows and enhance probabilistic security, reducing computational demands by decomposing N-k faults into repeating basis functions. Case studies on 118-, 300-, 1354- and 2328-bus systems demonstrate the accuracy and computational superiority of polynomial LODFs in assessing expected congestion and security. These findings are a first step towards managing the reliability and efficiency of power systems in the face of increasing extreme weather events.

This letter studies the problem of coordinating aggregators in the power system to provide fast frequency response as dynamic ancillary services. We approach the problem from the perspective of suboptimal H _∞ control, and propose an efficient and tractable formulation. We further develop a distributed solution method for the investigated problem, which enables aggregator agents to learn their optimal provisions in an adaptive way. More precisely, we reformulate the original problem into a state-based potential game, where the agents interact with each other towards our designed Nash equilibrium. The proposed game-theoretic learning approach decouples the coupling Linear Matrix Inequality constraint, guarantees the convergence to the equilibrium which is close enough to the original optimum. The learning process is also robust to the changes in communication graphs. We demonstrate the efficacy of our proposed approach with a case study on a 3-aggregator system.