Deep Reinforcement Learning (DRL) presents a promising avenue for optimizing Energy Storage Systems (ESSs) dispatch in distribution networks. This paper introduces RL-ADN, an innovative open-source library specifically designed for solving the optimal ESSs dispatch in active distribution networks. RL-ADN offers unparalleled flexibility in modeling distribution networks, and ESSs, accommodating a wide range of research goals. A standout feature of RL-ADN is its data augmentation module, based on Gaussian Mixture Model and Copula (GMC) functions, which elevates the performance ceiling of DRL agents, achieving an average performance improvement of 21.43%, 1.08%, 2.76%, by augmenting five-year, one-year and three-month data, respectively. Additionally, RL-ADN incorporates the Tensor Power Flow solver, significantly reducing the computational burden of power flow calculations during training without sacrificing accuracy, maintaining voltage magnitude with an average error not exceeding 0.0001%. The effectiveness of RL-ADN is demonstrated using distribution networks with size varying, showing marked performance improvements in the adaptability of DRL algorithms for ESS dispatch tasks. Furthermore, RL-ADN achieves a tenfold increase in computational efficiency during training, making it highly suitable for large-scale network applications. The library sets a new benchmark in DRL-based ESSs dispatch in distribution networks and it is poised to advance DRL applications in distribution network operations significantly. RL-ADN is available at: https://github.com/ShengrenHou/RL-ADN and https://github.com/distributionnetworksTUDelft/RL-ADN.

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.

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.

The optimal dispatch of energy storage systems (ESSs) in distribution networks poses significant challenges, primarily due to uncertainties of dynamic pricing, fluctuating demand, and the variability inherent in renewable energy sources. By exploiting the generalization capabilities of deep neural networks (DNNs), the deep reinforcement learning (DRL) algorithms can learn good-quality control models that adapt to the stochastic nature of distribution networks. Nevertheless, the practical deployment of DRL algorithms is often hampered by their limited capacity for satisfying operational constraints in real time, which is a crucial requirement for ensuring the reliability and feasibility of control actions during online operations. This paper introduces an innovative framework, named mixed-integer programming based deep reinforcement learning (MIP-DRL), to overcome these limitations. The proposed MIP-DRL framework can rigorously enforce operational constraints for the optimal dispatch of ESSs during the online execution. This framework involves training a Q-function with DNNs, which is subsequently represented in a mixed-integer programming (MIP) formulation. This unique combination allows for the seamless integration of operational constraints into the decision-making process. The effectiveness of the proposed MIP-DRL framework is validated through numerical simulations, demonstrating its superior capability to enforce all operational constraints and achieve high-quality dispatch decisions and showing its advantage over existing DRL algorithms.

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.

The exponential increase in the integration of Variable Renewable Energy Sources and responsive storage, compensation, and prosumers in electrical power systems raises many uncertainties that affect the operation, control, and planning across different time horizons. Dynamic stability refers to a system's ability to withstand and recover from disturbances while ensuring that systemic symptoms (e.g., voltages, currents, frequency, angular displacements) remain within acceptable limits under both normal and abnormal conditions. Unacceptable excursions in systemic symptoms can cause disruptions or blackouts. A suitably developed and calibrated digital model for dynamic simulations is a key tool for this purpose. This manuscript overviews the development of a digital synthetic model for in-depth analysis and identification of the occurrence and propagation of potential instability issues. The synthetic model is inspired by accessible data on the hypothetical future situation (e.g., year 2030) of the Dutch Power System. The model has been built on the basis of generic component models and parameters from the literature, and several disturbances are evaluated by time-domain simulations. Renewable power electronic-interfaced generators and remaining synchronous generators have implemented emerging methods to provide primary control for active and reactive power support in line with the state-of-the-art recommended practice. This model is proposed as the basis for studying different stability phenomena and challenges for controller design in future operating conditions of the Dutch system in light of the large-scale addition of renewable generation.

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.

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.

The topology of low-voltage distribution networks (LVDNs) is crucial for system analysis, e.g., distributed energy resources (DERs) integration, network hosting capacity analysis, state estimation, and electric vehicle charging management. However, it is frequently unavailable or incomplete. This paper develops a data-driven topology identification approach for LVDNs with a high proportion of underground cables. The proposed approach exploits the fact that underground cables usually follow the street pattern, thus relying on open street map (OSM) and smart meter (SM) data. Three stages compose the proposed approach: In the first stage, a hierarchical minimum spanning tree algorithm is proposed to generate the initial topology with an accurate number of sub-branches from the pre-processed OSM data and peak demand. In the second stage, based on the limited SM data, the location of breakpoints in mesh topology caused by circle roads is verified and reconstructed to guarantee the radial structure of LVDNs. Finally, given multiple incomplete SM datasets, three data-driven optimization models based on a state estimation model are constructed to mitigate the error of cable length induced by OSM data. The feasibility of the proposed topology identification approach is verified on three actual LVDNs in The Netherlands and multiple incomplete SM datasets. Furthermore, the minimal amount of SM data needed to minimize the error of cable length is analyzed.

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.

Power grids are undergoing a fast-paced process of digitalization for enhanced monitoring and control capabilities and grid intelligence. However, the increased integration of digital technologies, such as the next generation of operational technologies (OTs) and digital substations, implies a new risk as information technology (IT)-OT systems are vulnerable to cyberattacks. Furthermore, the combination of heterogeneous, co-existing smart and legacy technologies generates significant vulnerabilities and security challenges. Examples of cybersecurity incidents related to power grids already exist around the world. On December 23, 2015, cyberattacks were conducted on the power grid in Ukraine that resulted in power outages, which affected 225,000 customers. More sophisticated cyberattacks on the Ukrainian power grid followed on December 17, 2016, resulting in a power outage in the distribution network where 200 MW of load was unsupplied. The complexity of cyberattacks on power systems is likely to increase. This chapter provides the state-of-the-art and essential knowledge of threats and cyberattacks on power systems. This chapter reviews major cyberattacks on power grids and industrial control systems. A detailed taxonomy of cyberattacks is provided. Power grid vulnerability to six main types of cyberattacks is discussed, that is, phishing, malware, network-based attacks, man-in-the-middle attacks, host-based attacks, and denial of service. The impact of cyberattacks on grid operation is analyzed in terms of loss of load, cascading effects, and equipment damage. A case study of a cyberattack scenario and simulation results are provided.

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.

The integration of distributed energy resources (DERs) has escalated the challenge of voltage magnitude regulation in distribution networks. Model-based approaches, which rely on complex sequential mathematical formulations, cannot meet the real-time demand. Deep reinforcement learning (DRL) offers an alternative by utilizing offline training with distribution network simulators and then executing online without computation. However, DRL algorithms fail to enforce voltage magnitude constraints during training and testing, potentially leading to serious operational violations. To tackle these challenges, we introduce a novel safe-guaranteed reinforcement learning algorithm, the DistFlow safe reinforcement learning (DF-SRL), designed specifically for real-time voltage magnitude regulation in distribution networks. The DF-SRL algorithm incorporates a DistFlow linearization to construct an expert-knowledge-based safety layer. Subsequently, the DF-SRL algorithm overlays this safety layer on top of the agent policy, recalibrating unsafe actions to safe domains through a quadratic programming formulation. Simulation results show the DF-SRL algorithm consistently ensures voltage magnitude constraints during training and real-time operation (test) phases, achieving faster convergence and higher performance, which differentiates it apart from (safe) DRL benchmark algorithms.

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.

Industrial electrification plays a crucial role in reducing carbon dioxide emissions, and ensuring power reliability is important in this process. Reliability and techno-economic evaluations are fundamental to designing, operating, and managing power systems, ensuring that electricity is delivered continuously and securely under various conditions. In particular, maintaining a reliable power supply to industrial loads is critical, especially when renewable sources are present, as these introduce greater variability and uncertainty into the operation of industrial systems. Therefore, this document aims to use a cost-effective storage approach to ensure the reliable operation of sustainable industrial multi-energy systems. In addition, three storage mitigation strategies against random operation are formulated based on financial, technical, practical, and other aspects. A synthetic industrial model consisting of generic component representations in DIgSILENT PowerFactory 2024 is taken as a case study. The structure and parameters of the synthetic model are inspired by data from the literature and a hypothetical projection of a future evolution of a 500 MW sustainable industrial multi-energy system in Rotterdam by 2035. Numerical results provide insight into the flexible and cost-effective operation of sustainable industrial multi-energy systems within the context of decarbonised future Dutch energy systems.

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.

Cyber actors can target the unsecured IEC 61850 protocols in digital substations to open circuit breakers and affect the power system operation. Thus, system operators must detect cyber-physical anomalies and differentiate in real-time between power system faults and cyber attacks on digital substations for effective incident response. In this work, we propose a novel image encoding method for event correlation using cyber-physical time-series data, i.e., Phasor Measurement Units (PMUs) and Operational Technology (OT) network traffic. More specifically, we propose a dynamic variation of the Gramian Angular Field method, which generates image streams capturing in real-time the spatial-temporal features in PMU measurements and IEC 61850 GOOSE traffic throughput. The proposed method for cyber-physical event correlation uses an image fusion technique. The method is tested using the benchmark IEEE 9-bus system. It successfully distinguishes between three-phase faults and GOOSE cyber attacks, demonstrating its usefulness for power system cyber security analytics.

Reinforcement Learning (RL) has emerged as a promising solution for defining the optimal dispatch of Energy Storage Systems (ESS) in distributed energy systems. However, a notable gap exists in the literature: a lack of comprehensive and fair comparisons between different RL algorithms, particularly between linear and nonlinear approaches. This study critically evaluates the trade-offs between computational efficiency and operational accuracy among various Linear RL (LRL) strategies and compares them against the nonlinear Deep-Q-Network (DQN) algorithm. Through a comprehensive analysis, this study benchmarks the model-based Mixed-Integer Linear Programming (MILP) results to assess and compare these algorithms' convergence, training efficiency, and optimization accuracy. Results indicate that while LRL approaches the operational cost accuracy of DQN, it faces significant trade-offs in computational efficiency and struggles with generalization across larger and varied datasets. The results illuminate critical areas for further development in LRL methodologies, particularly in enhancing their adaptability and generalization capabilities.

The energy sector's digital transformation brings mutually dependent communication and energy infrastructure, tightening the relationship between the physical and the digital world. Digital twins (DT) are the key concept for this. This paper initially discusses the evolution of the DT concept across various engineering applications before narrowing its focus to the power systems domain. By reviewing different definitions and applications, the authors present a new definition of DTs specifically tailored to power systems. Based on the proposed definition and extensive deliberations and consultations with distribution system operators, energy traders, and municipalities, the authors introduce a vision of a standard DT ecosystem architecture that offers services beyond real-time updates and can seamlessly integrate with existing transmission and distribution system operators' processes while reconciling with concepts such as microgrids and local energy communities based on a system-of-systems view. The authors also discuss their vision related to the integration of power system DTs into various phases of the system's life cycle, such as long-term planning, emphasising challenges that remain to be addressed, such as managing measurement and model errors, and uncertainty propagation. Finally, the authors present their vision of how artificial intelligence and machine learning can enhance several power systems DT modules established in the proposed architecture.

Cascading failures in power systems are extremely rare occurrences caused by a combination of multiple, low probability events. The looming threat of cyberattacks on power grids, however, may result in unprecedented large-scale cascading failures, leading to a blackout. Therefore, new analysis methods are needed to study such cyber induced phenomena. In this article, we propose a data-driven method for dynamical analysis of power system cascading failures caused by cyberattacks. We provide experimental proof on how attacks may accelerate the cascading failure mechanism, in comparison to historically observed blackouts. Using a dynamic power grid model, consisting of multiple, coordinated protection schemes, we define and analyze the point of no return in a cascading failure sequence by applying the Hilbert-Huang transform for time-frequency analysis. Numerical results indicate, cyberattacks may accelerate cascading failures at least by a factor of 3x. This is due to the excitation and non-damping of multiple frequency modes greater than 1 Hz in a short time span. The proposed method is tested using time domain simulations conducted through a modified IEEE 39-bus test system, which can simulate cascading outages using coordinated protection schemes.