We introduce a physics-informed neural network for power flow (PINN4PF) that effectively captures the nonlinear dynamics of large-scale modern power systems. The proposed neural network (NN) architecture consists of two important advancements in the training pipeline: (A) a double-head feed-forward NN that aligns with power flow (PF), including an activation function that adjusts to the net active and reactive power injections patterns, and (B) a physics-based loss function that partially incorporates power system topology information through a novel hidden function. The effectiveness of the proposed architecture is illustrated through 4-bus, 15-bus, 290-bus, and 2224-bus test systems and is evaluated against two baselines: a linear regression model (LR) and a black-box NN (MLP). The comparison is based on (i) generalization ability, (ii) robustness, (iii) impact of training dataset size on generalization ability, (iv) accuracy in approximating derived PF quantities (specifically line current, line active power, and line reactive power), and (v) scalability. Results demonstrate that PINN4PF outperforms both baselines across all test systems by up to two orders of magnitude, not only in terms of direct criteria, e.g., generalization ability, but also in terms of derived physical quantities.

Electricity Consumption Profiles (ECPs) are crucial for operating and planning power distribution systems, especially with the increasing number of low-carbon technologies such as solar panels and electric vehicles. Traditional ECP modeling methods typically assume the availability of sufficient ECP data. However, in practice, the accessibility of ECP data is limited due to privacy issues or the absence of metering devices. Few-shot learning (FSL) has emerged as a promising solution for ECP modeling in data-scarce scenarios. Nevertheless, standard FSL methods, such as those used for images, are unsuitable for ECP modeling because (1) these methods usually assume several source domains with sufficient data and several target domains. However, in the context of ECP modeling, there may be thousands of source domains, e.g., households with a moderate amount of data, and thousands of target domains, e.g., households that ECP are required to be modeled. (2) Standard FSL methods usually involve cumbersome knowledge transfer mechanisms, such as pre-training and fine-tuning. To address these limitations, this paper proposes a novel FSL framework that integrates Transformers with Gaussian Mixture Models (GMMs) for ECP modeling. The proposed approach is fine-tuning-free, computationally efficient, and robust even with extremely limited data. Results show that our method can accurately restore the complex ECP distribution with a minimal amount of ECP data (e.g., only 1.6% of the complete domain dataset) and outperforms state-of-the-art time series modeling methods in the context of ECP modeling.

Cyber attacks on power grids are imminent and potentially have a severe impact, as evidenced by the cyber attacks in Ukraine in 2015, 2016, and 2022. In response to this challenge, machine learning-based Intrusion Detection Systems (IDS) have become more prevalent as a potential mitigation owing to their alignment with the latest advances in artificial intelligence. However, existing anomaly detection methods for power grid Operational Technology (OT) are often inadequate, as they primarily focus on detecting power grid physical anomalies at the later attack stages and suffer from the scarcity of available data for supervised machine learning. To address these limitations, we propose a novel semi-supervised IDS specifically for digital substations of the power system. The proposed detection method identifies the distinctive distance similarity of digital substation OT communication traffic using a Convolutional Neural Network and Chebyshev distance of packet payloads, and Kolmogorov-Smirnov of packets’ interarrival time using Fast Fourier Transform amplitude. Subsequently, these traffic features are combined into a vector and classified using a novel hybrid semi-supervised Self-Organizing Map (SOM) and Density-Based Spatial Clustering of Applications with Noise (DBSCAN). Results indicate that the proposed method can identify zero-day attacks and achieve accuracy and F1 above 95%.

Integrating electric vehicles (EVs) into the power grid can revolutionize energy management strategies, offering both challenges and opportunities for creating a more sustainable and resilient grid. In this context, model predictive control (MPC) emerges as a powerful tool for addressing the complexities of Grid-to-Vehicle (G2V) and Vehicle-to-Grid (V2G) enabled demand response management. By leveraging advanced optimization techniques, MPC algorithms can anticipate future grid conditions and dynamically adjust EV charging and discharging schedules. However, no standard tools exist to evaluate novel energy management strategies based on MPC approaches. This work focuses on harnessing the potential of MPC in G2V and V2G applications by providing open-source algorithms that allow the maximization of EV flexibility and support demand response initiatives while mitigating the impact on EV battery health. Through extensive simulation and analysis, we demonstrate the efficacy of our approach in maximizing the benefits of G2V and V2G while assessing the impact on the longevity and reliability of EV batteries. Specifically, the proposed methods enable the optimization of EV charging and discharging schedules in real-time, taking into account fluctuating energy prices, grid constraints, and EV user preferences.

Electric-vehicle smart charging requires quick decision-making under uncertainty while enforcing strict electricity grid and user requirements. Mathematical optimization becomes too slow at scale, while online reinforcement learning struggles with sparse rewards and safety. This paper proposes GNN-DT, a topology-aware Decision Transformer that combines graph neural network embeddings with sequence modeling to learn charging policies from offline trajectories. The method operates over variable numbers of vehicles and chargers without retraining. Evaluated on realistic smart charging scenarios, GNN-DT achieves near-optimal performance, reaching rewards within 5 percent of an oracle solver while using up to 10× fewer training trajectories than baseline methods. It consistently outperforms online and offline reinforcement learning approaches and generalizes to unseen fleet sizes and network topologies. Inference runs in milliseconds, making the approach suitable for real-time deployment in large-scale charging systems.

This contribution deals with the optimization of the frequency response of a multi-area, multi-energy HVDC-HVAC cyber-physical power system, representing a power electronic-dominated power system. The system consists of a three-area system, modified so that the areas are electromagnetically decoupled through MMC-based HVDC links, and different controllable energy sources, such as fully decoupled wind turbines type IV and proton exchange membrane electrolysers, are installed at various points of the system. The modified system exhibits three decoupled areas with different generation and demand mixes characterized by different inertia levels and increased controllability due to the converters’ capabilities. The outer controllers of the power electronic interfaced elements installed have been modified with the active power gradient control scheme to respond to frequency excursions and provide fast frequency support to the grid in case of commonly occurred active power-frequency imbalances. A problem formulation for coordinated optimization is presented, aiming at a coordinated tuning of the parameters of the frequency controllers of the synthetic inertia elements participating in the frequency regulation against critical commonly occurred active power-frequency imbalances. The formulations consider the minimization of the dynamic displacements of the areas’ speed following an active power imbalance. To effectively solve the optimization problem and enhance the frequency stability of the system, a powerful metaheuristic optimization algorithm, the mean-variance mapping optimization (MVMO) algorithm, has been utilized. The optimization results can effectively highlight the tuning strategy that achieves the best frequency response of the system under various commonly occurred active power frequency disturbances. It can also provide further insight on the proper utilization of various sources of synthetic inertia with respect to their response capabilities. Finally, the simulation results can also clarify the importance of the location of installation of converter-based elements providing fast frequency support with respect to the grid node the imbalance occurs.

As the adoption of electric vehicles (EVs) accelerates, addressing the challenges of large-scale, city-wide optimization becomes critical in ensuring efficient use of charging infrastructure and maintaining electrical grid stability. This study introduces EV-GNN, a novel graph-based solution that addresses scalability challenges and captures uncertainties in EV behavior from a Charging Point Operator’s (CPO) perspective. We prove that EV-GNN enhances classic Reinforcement Learning (RL) algorithms’ scalability and sample efficiency by combining an end-to-end Graph Neural Network (GNN) architecture with RL and employing a branch pruning technique. We further demonstrate that the proposed architecture’s flexibility allows it to be combined with most state-of-the-art deep RL algorithms to solve a wide range of problems, including those with continuous, multi-discrete, and discrete action spaces. Extensive experimental evaluations show that EV-GNN significantly outperforms state-of-the-art RL algorithms in scalability and generalization across diverse EV charging scenarios, delivering notable improvements in both small- and large-scale problems.

Digitalization is paving the way toward enhanced power grid operational capabilities and intelligence. The increased digitalization, however, also implies a greater risk of cyber vulnerabilities and threats. Therefore, various power systems facets such as transmission and distribution systems, digital substations, control centers, and wide-area communication networks are vulnerable to cyber-attacks. The most notable cyber-attacks on power grids are the twin attacks on the Ukrainian power grid in 2015 and 2016. These incidents clearly highlighted that cyber-attacks on power grids are an imminent threat that needs to be addressed. Keeping this in mind, this chapter provides essential knowledge of cyber-attack mitigation for cyber-physical power systems, i.e., secure communication protocols for operational technologies, penetration testing using cyber ranges and cyber-physical co-simulation, security controls, and intrusion detection and prevention systems. Among the wide-scope mitigation, artificial intelligence is highlighted as an emerging solution. This chapter presents how hybrid deep learning based on graph convolutional long short-term memory is used for anomaly detection in power system operational technology (OT) networks. Unlike traditional signature and supervised learning-based intrusion detection, the hybrid deep learning anomaly detection utilizes the OT traffic throughput. It takes advantage of the OT traffic’s deterministic and homogenous characteristics to provide a robust and flexible anomaly detection for a wide scope of cyber-attacks. The traffic anomalies are incorporated into an attack graph that aids power system operators identify and localize anomalies of active attacks on power systems in near real time. Cyber-attack case studies and cyber-physical co-simulation results are provided to demonstrate the efficiency of hybrid deep learning for anomaly detection.

This paper presents a pivotal stability analysis of the Dutch power system within the context of increased renewable energy integration, employing multiple future scenarios to navigate the inherent uncertainties. A large-scale synthetic model, utilizing ENTSOE-E reference data, uses time-domain simulations and eigenvalue analysis to assess the influence of systemic inertia and kinetic energy on the power system's dynamic frequency and angular stability. The study identifies specific inertia and kinetic energy projections that could undermine the stability of the Dutch power system and potentially affect the continental European power system. It also discusses potential enhancements, including supplementary damping control, to improve the primary control functions of power electronics interfaced generation. The results highlight the critical need for power system planners and operators to take proactive steps to prevent instabilities, ensuring that renewable energy integration strengthens rather than compromises power system reliability.

This study presents an innovative approach to risk-aware decision-making in water resource management. We focus on a case study in the Netherlands, where risk awareness is key to water system design and policy-making. Recognizing the limitations of deterministic methods in the face of weather, energy system, and market uncertainties, we propose a scalable stochastic Model Predictive Control (MPC) framework that integrates probabilistic forecasting, scenario generation, and stochastic optimal control. We utilize Combined Quantile Regression Deep Neural Networks and Non-parametric Bayesian Networks to generate probabilistic scenarios that capture realistic temporal dependencies. The energy distance metric is applied to optimize scenario selection and generate scenario trees, ensuring computational feasibility without compromising decision quality. A key feature of our approach is the introduction of Exceedance Risk (ER) constraints, inspired by Conditional-Value-at-Risk (CVaR), to enable more nuanced and risk-aware decision-making while maintaining computational efficiency. In this work, we enable the Noordzeekanaal–Amsterdam-Rijnkanaal (NZK-ARK) system to participate in Demand Response (DR) services by dynamically scheduling pumps to align with low hourly electricity prices on the Day Ahead and Intraday markets. Through historical simulations using real water system and electricity price data, we demonstrate that incorporating uncertainty can significantly reduce operational costs—by up to 44 percentage points compared to a deterministic approach—while maintaining safe water levels. The modular nature of the framework also makes it adaptable to a wide range of applications, including hydropower and battery storage systems.

The increasing digitalization of Cyber-Physical Power Systems (CPPS) has enhanced power system operation and control but has also expanded the attack surface for cyber threats. Detection of early-stage attacks such as reconnaissance and Denial-of-Service (DoS) is critical to prevent power system-wide disruptions. Centralized Machine Learning (ML)-based techniques have been proposed for detecting cyber attacks. However, they struggle to ensure data privacy. Federated Learning (FL) can address this issue through collaborative model training without raw data sharing. Yet, FL’s performance degrades under non-Independent and Identically Distributed (non-IID) data, a common scenario in real-world CPPS environments. In this paper, we propose a cluster-based FL method using Bidirectional Long Short-Term Memory (BiLSTM) for attack detection at the early stages of the cyber kill chain. It uses unsupervised clustering of client model updates for aggregation robustness and model generalization across heterogeneous clients. By grouping clients based on similarity in model updates, our method mitigates the adverse effects of data heterogeneity while preserving data privacy. The UNSW-NB15 dataset is used for distributed training under non-IID conditions and evaluation of the proposed method. Experimental results demonstrate that our cluster-based FL method achieves over 95% detection accuracy, proving its effectiveness in distributed cyber attacks detection in power systems.

Unscheduled event handling capability and swift recovery from transient events are indispensable study areas to ensure reliability in offshore multiterminal high-voltage dc (MT-HVdc) grids. This article focuses on enhancing the reliability of half-bridge modular multilevel converters (HB-MMCs) in MT-HVdc grids by introducing a predictive dc fault ride-through (DC-FRT) recovery controller and fault separation devices. A novel dc protection-informed zonal DC-FRT scheme for HB-MMCs is proposed, incorporating a model predictive planner for optimized control inputs based on local and interstation measurements and converter constraints. A real-time digital simulator environment simulates the approach, which improves lower level control during fault interruption and suppression by utilizing fault detection and location information. In addition, the study examines two control schemes to assess the impact of communication delays in MT-HVdc grids, a critical factor for system stability and reliability during faults. These schemes include a centralized scheme with delays in input and output signals and a decentralized approach focusing on external signal delays. Both are compared against a baseline centralized control with no delays. These approaches explore alternatives for the placement of the proposed controller, considering potential delays in interstation high-speed communication. The findings underscore the significance of the proposed DC-FRT control in reinforcing MT-HVdc systems against faults, which contributes to efficient recovery and grid stability.

As a part of energy transition, the shift from internal combustion engines (ICEs) to electric vehicles (EVs) has accelerated the development of the EV charging infrastructure (EVCI). EVCI rely heavily on information and communication technologies (ICTs) and the Internet of Things (IoT). As a result, the susceptibility to cyber attacks increases. However, although EVCI are strongly intertwined with cyber-physical power systems (CPPSs), the consequences of such a cyber attack on the power grid are not widely researched. In this paper, we present a comprehensive cyber-physical system architecture of the EV charging infrastructure based on the industry practice in The Netherlands, which is applicable to European distribution systems. We present a survey of work on EVCI cyber security and CPPS resilience. We combine unique industrial insights with the academic state-of-the-art. We show that although cyber security of EVCI is researched, the state-of-the-art inadequately covers the consequences for CPPSs, especially distribution networks. We survey the current work on CPPS resilience and conclude that while cyber attacks are often recognized as high impact low probability (HILP) disturbances of CPPSs, the resilience-related research on cyber attacks on EVCI is lacking. Therefore, we present a novel method to model the stochastic EV charging behaviour based on probability density functions (PDFs). We validate the method using PowerFactory models of distribution networks supplied by a Dutch distribution system operator (DSO). We demonstrate the effects of cyber attacks on EVCI on distribution networks voltages. Under the investigated operational scenario, the impact is not significant. However the results do underline the importance of researching cyber attacks on EVCI from a CPPS resilience perspective. Research into future scenarios of energy transition is essential for future resilient operation of power grids.

This editorial introduces the Special Issue “Methodologies and Applications of Digital Twin for Renewable-Dominant Power Systems”, which highlights key research addressing the challenges associated with integrating renewable energy sources into power systems. Digital twins provide an advanced framework for modeling, simulation, and optimization of these complex systems, driven by the need to address the impact of power electronics and multi-source energies. The contributions featured in this issue focus on the application of DT technologies in renewable-dominant systems, offering solutions for enhancing system stability, optimization, and operational efficiency.

Distribution system operators (DSOs) often lack high-quality data on low-voltage distribution networks (LVDNs), including the topology and the phase connection of residential customers. The phase connection is essential for phase balancing assessment and distributed energy resources (DERs) integration. The existing load profiles-based approaches rely on stepwise subtraction of the identified customers in a step-by-step identification procedure, while the accuracy of each step is not guaranteed. This paper introduces a siamese neural network model to identify single-phase connections without requiring stepwise subtraction. It comprises self-taught learning (STT) and a phase-label identification strategy. The introduced self-taught learning enables DSOs to train a recurrent neural network-based Siamese network (RSN) only relying on an unlabelled dataset. Besides, the siamese network (SN) is robust to noise and fluctuations in the data to a certain extent, making the proposed method robust to measurement errors. A Kendall correlation-based phase modification strategy is introduced to modified phase labels with lower confidence, aiming to mitigate the accuracy loss induced by the limited generalization of SN. The proposed approach is tested on the IEEE European low voltage test feeder and a residential network in the Netherlands Simulation results illustrate the feasibility and robustness of the proposed approach on incomplete datasets. The accuracy exceeded 83% and 90%, respectively, when using datasets of less than 20 days with and without measurement errors.

Increased electrification of energy end-usage can lead to network congestion during periods of high consumption. Flexibility of loads, such as aggregate smart charging of Electric Vehicles (EVs), is increasingly leveraged to manage grid congestion through various market-based mechanisms. Under such an arrangement, this paper quantifies the effect of lead time on the aggregate flexibility of EV fleets. Simulations using realworld charging transactions spanning over different categories of charging stations are performed for two flexibility products (redispatch and capacity limitations) when offered along with different business-as-usual (BAU) schedules. Results show that the variation of tradable flexibility depends mainly on the BAU schedules, the duration of the requested flexibility, and its start time. Further, the implication of these flexibility products on the average energy costs and emissions is also studied for different cases. Simulations show that bidirectional (V2G) charging outperforms unidirectional smart charging in all cases.

The Digital Twins (DT) have emerged as the technology that provides capabilities to simulate and analyze cyber-physical systems’ behaviors using digital replicas. This is achieved through high-fidelity digital models, bi-directional communication and (near) real-time data exchange between physical real-world systems and DTs. Despite its capabilities of facilitating real-time monitoring, optimization, and predicting system performance, effectively leveraging DT for power system applications requires integrating data from heterogeneous sources and addressing various data related aspects. These include data modeling, exchange and interoperability. One promising concept to address these aspects is that of data federation which promotes interoperability, allowing DTs to operate autonomously, yet interact seamlessly. While various studies in literature have addressed DT applications, technologies, and challenges, a comprehensive review on the data federation aspects within power systems still needs to be investigated. This research seeks to bridge this gap by providing an in-depth review of DT practices in academia and industry, functional and non-functional requirements, and enabling technologies, with emphasis on data federation. Its role in enhancing system-wide interoperability in the power system, along with associated challenges are summarized and discussed.

Residential Load Profile (RLP) generation is critical for the operation and planning of distribution networks, especially as diverse low-carbon technologies (e.g., photovoltaic and electric vehicles) are increasingly adopted. This paper introduces a novel flow-based generative model, termed Full Convolutional Profile Flow (FCPFlow), uniquely designed for conditional and unconditional RLP generation. By introducing two new layers – the invertible linear layer and the invertible normalization layer – the proposed FCPFlow architecture shows three main advantages compared to traditional statistical and contemporary deep generative models: (1) it is well-suited for RLP generation under continuous conditions, such as varying weather and annual electricity consumption, (2) it demonstrates superior scalability in different datasets compared to traditional statistical models, and (3) it also demonstrates better modeling capabilities in capturing the complex correlation of RLPs compared with deep generative models.

Reinforcement learning (RL) has become a promising approach for optimizing the dispatch of energy storage systems (ESSs) in distributed energy systems. Utilizing linear methods in the Q-representation of RL often struggles to balance accuracy and efficiency, while neural network (NN) performs well but falls short in terms of explainability and interpretability. To address these challenges, we developed and evaluated a deep-Q-symbolic-network (DQSN) framework, which integrates a symbolic network (SN) into the deep-Q-network (DQN) architecture for optimal dispatch of ESS. We benchmarked the performance of DQSN against DQN using mixed-integer linear programming (MILP) results, focusing on algorithm convergence, training duration, and operational cost accuracy. Our findings indicate that DQSN achieves slightly superior rewards and reduced operational costs with a modest increase in training time. Additionally, while DQN demonstrates superior generalization to unseen scenarios, DQSN excels in accurately fitting training data, enabling DQSN to be a viable alternative to DQN, particularly in applications requiring explainability and interpretability.

Achieving carbon neutrality in industrial ports demands a radical transformation of current energy systems. This paper presents a model-based optimization approach for the operation of a multi-energy cluster, considering a hypothetical evolution of a multi-energy industrial cluster in the Netherlands. The aim is to establish a new system operation strategy that supports the transition towards a carbon-neutral energy system. The synthetic model of the used multi-energy cluster integrates five energy carriers - electricity, natural gas, hydrogen, ammonia, and heat - using an energy hub approach to enable sector coupling and enhance flexibility. Physics-based modeling of electrical power flows is included to ensure technical feasibility in the power system. The model minimizes total cluster's cost while ensuring reliable energy supply. The optimization is implemented in Python by using the PyPSA toolbox and mixed-integer linear programming. A full-year, hourly-resolution simulation under three weather scenarios reveals optimal system operation strategies. Numerical results highlight the benefits of multi-energy cluster operation for managing renewable variability and identify ammonia as a key flexibility provider, supporting hydrogen and electricity systems through conversion and storage. The strategy emphasizes cross-sector economic optimization, dynamic dispatch, and enhanced flexibility, offering practical insights for decarbonizing industrial ports and informing future energy investment planning.