Publications Search Results

Now showing 1 - 10 of 78
  • Publication
    Transformation in substation automation: Cyber-Resilient Digital Substations (CyReDS) in power grids
    ( 2023-09-01) ;
    Bauer, Thomas
    ;
    ;
    Kühne, Marcel
    ;
    ;
    The digitalization of substations leads to a high degree of automation, which is referred to as Digital Substations with the use of the IEC 61850. An increase in cybersecurity is necessary, and technically enabled by detection and incident response systems - security-by-design is currently often secondary. The next transformation step of substations is introduced and outlined in this paper as a cyber-resilient digital substation. Based on a state-of-the-art description, this paper presents a definition of cyber resilience for digital substations as a basis for the introduced cyber resilience monitor. The monitor acts as a central instance for recording, assessing and responding to security threats and incidents. Furthermore, the requirements for the system structure of the cyber-resilient digital substation are shown and underpinned with current research approaches.
  • Publication
    First step into automation of security assessment of critical infrastructures
    Critical infrastructures have been undergoing significant developments result- ing from new economy and society driven trends and demands. In the energy supply, decentralization and digitalization are the key processes that push a significant amount of innovation and movement into the networking of many distributed information and operational technology based energy systems. These advancements bring substantial benefits, but expose the underlying systems to a number of risks at the same time. In response, governments and sector-specific organizations have published a series of regulatory re- quirements and guidelines on cybersecurity for the industry and especially for critical infrastructures. This article describes a practical approach to con- ducting cybersecurity assessments for critical infrastructures in the form of an extended gap analysis. The goal is to develop a technique for analyzing gaps between the security measures already implemented, and the recom- mendations formulated in the legal acts and standards for different critical infrastructure sectors. The methodology includes several assessment steps and layers to address a wide range of security controls of existing standards, taking into account the limitations of conducting such security analyses in the operational environment, especially of power supply systems. In addition, a possible automation strategy for the initial phase of the security assessment is presented, in which information about the assets under investigation is col- lected and the appropriate security measures are identified. The presented approach has been developed and practically tested for a digital substation of a local German energy grid operator.
  • Publication
    Clark-Park Transformation based Autoencoder for 3-Phase Electrical Signals
    During the past decades, significant progress has been made in the field of artificial neural networks to process images (Convolutional Neural Networks), audio signals (Temporal Convolutional Networks), or textual information (Transformers). However, for electrical three-phase signals processing, these network architectures ignore important characteristics and therefore lack of computational efficiency. This can lead to performance problems and limits the application potential of neural networks for a fast and efficient local analysis of three-phase electrical current or voltage waveforms. To address this issue, a novel autoencoder architecture is proposed in this paper, which incorporates Clark-Park transformation to learn the representations of three-phase electrical signals. Using unbalanced and noisy voltage signals, the Clark-Park based autoencoder shows superior performance and computational efficiency compared to recurrent and convolutional benchmark architectures.
  • Publication
    Day-Ahead Electricity Load Prediction Based on Calendar Features and Temporal Convolutional Networks
    ( 2023)
    Richter, Lucas
    ;
    Bauer, Fabian
    ;
    ;
    Transmission system operator (TSO) have to ensure grid stability economically. This requires highly accurate load forecasts for the transmission grids. The ENTSO-E transparency platform (ETP) currently provides a load estimation and a day-ahead load prediction for different TSO in Germany. This paper shows a hybrid model architecture of a feedforward network based on calendar features to extract the general behaviour of a time-series and a temporal convolutional network to extract the relations between short-historical and future time-series values. This research shows a significant improvement of the current day-ahead load forecast and additionally a model robustness while training with a non-optimal data set.
  • Publication
    Influence of nuisance variables on the PMU-based disturbance classification in power transmission systems
    The online classification of grid disturbances in power transmission systems has been investigated since many years and shows promising results on measured and simulated PMU signals. Nonetheless, a practical deployment of machine learning techniques is still challenging due to robustness problems, which may lead to severe misclassifications in the model application. This paper formulates an advanced evaluation procedure for disturbance classification methods by introducing additional measurement noise, unknown operational points, and unknown disturbance events in the test dataset. Based on preliminary work, Siamese Sigmoid Networks are used as classification approach and are compared against several benchmark models for a simulated power transmission system at 400 kV. Different test scenarios are proposed to evaluate the disturbance classification models assuming a limited and full observability of the grid with PMUs.
  • Publication
    ODH@X - Datenraum für klimaneutrale Quartiere
    "ODH@X - Datenraum für klimaneutrale Quartiere" heißt unsere neueste Projektinitiative. Sechs Fraunhofer-Institute, zahlreiche Unternehmen, Institutionen und der ODH führen derzeit Gespräche, um ein engagiertes Konsortium für die Umsetzung dieser Vision zu bilden. Wir wollen damit den technischen Rahmen für den Austausch dezentral erfasster und verwalteter Daten zwischen den verschiedensten Stakeholdern in Quartieren schaffen. Dazu veröffentlichen wir nun mit dem Whitepaper die Vision, Mission und mögliche Anwendungsfälle vom ODH@X-Datenraum. Weitere interessierte Unternehmen sind herzlich willkommen! ODH@X soll ein Datenraum zur flexiblen Bereitstellung von Informationen und Diensten für Planung, Bau und Betrieb klimaneutraler Quartiere in Verbindung mit einer nachhaltigen und wirtschaftlichen cross-sektoralen Energieversorgung sein. "Datenraum" meint dabei nicht, dass eine zentralisierte Datenverwaltung aufgebaut wird, sondern beruht auf der Idee eines virtuellen Netzwerkes auf der Basis von etablierten Internettechnologien. Insofern ist der Datenraum also keine Datenbank, kein Data Lake und auch keine Cloud. Ein Datenraum wird jedoch solche Systeme unterschiedlicher Technologien als Komponenten einbinden und sicher zugreifbar machen. Der Datenraum soll eine offene IT-Systemarchitektur sein, die mittels Vernetzungstechnologie bestehende und neue Services sowie ganze Applikationen unterschiedlichster Art flexibel integriert. Mit der Einführung des ODH@X-Datenraums wollen wir einen aktiven Beitrag für Innovationen zwischen den Unternehmen der Bau-, Wohnungs-, Dienstleistungs- und Energiewirtschaft, den kommunalen Behörden und der in den Quartieren lebenden Menschen leisten. Damit wollen wir einerseits den energetischen Quartiersumbau beschleunigen. Andererseits soll der Datenraum die ökonomisch und ökologisch optimierte Fahrweise der cross-sektoralen Energieversorgung in Quartieren ermöglichen. Mit dem ODH@X-Datenraum, der die verschiedenen, in einem Quartier auftretenden Wertschöpfungsstufen digital verknüpft, eröffnen sich völlig neue, skalierbare Entwicklungsoptionen für die Realisierung nachhaltiger Quartiere. Dies beinhaltet sowohl die Fragen einer bezahlbaren, klimaneutralen, resilienten Energieversorgung als auch des schonenden Umgangs mit den im Quartier benötigten Ressourcen.
  • Publication
    Real-Time Simulation-Based Continuous Thévenin Impedance Monitoring Using Phasor Measurements
    The grid impedance of a power system is a significant parameter that characterizes the overall electrical behavior of the system. It is often used for assessing grid strength and can help to identify the sources of voltage profile drop, as well as fault detection and diagnosis. This paper presents an in-depth analysis of invasive and non-invasive methodologies for estimating grid impedance. It gives a review of both methodology types and evaluates their practicability for a continuous monitoring. In the paper a non-invasive method for the estimation of Thévenin equivalent (TE) impedance was selected, which employs data from Phasor Measurement Units (PMU) installed on the slack bus. The focus of the approach lies on the coupling of the evaluation with real-time (RT) simulation systems to continuously determine grid impedance under different scenarios. Since RT simulations allow the emulation of the dynamic behavior of electrical networks, a phase drift correction is implemented to compensate for the angular deviation due to frequency fluctuations. Selected results are presented to validate the effectiveness and general feasibility of the proposed method.
  • Publication
    Design and Implementation of a Hierarchical Digital Twin for Power Systems Using Real-Time Simulation
    ( 2023) ;
    Schäfer, Kevin
    ;
    Branz, Stefan
    ;
    ; ;
    Westermann, Dirk
    This paper presents a hierarchical Digital Twin architecture and implementation that uses real-time simulation to emulate the physical grid and support grid planning and operation. With the demand for detailed grid information for automated grid operations and the ongoing transformation of energy systems, the Digital Twin can extend data acquisition by establishing a reliable real-time simulation. The system uses observer algorithms to process model information about the voltage dependencies of grid nodes, providing information about the dynamic behavior of the grid. The architecture implements multiple layers of data monitoring, processing, and simulation to create node-specific Digital Twins that are integrated into a real-time Hardware-in-the-Loop setup. The paper includes a simulation study that validates the accuracy of the Digital Twin, in terms of steady-state conditions, dynamic behavior, and required processing time. The results show that the proposed architecture can replicate the physical grid with high accuracy and corresponding dynamic behavior.
  • Publication
    Siamese Sigmoid Networks for the open classification of grid disturbances in power transmission systems
    The online classification of grid disturbances is an important prerequisite for an automated and reliable operation of power transmission systems. Most of the state-of-the-art approaches assume that all classes are already known in the training phase and cannot handle new disturbance events, which appear in the application phase and lead to severe misclassifications. To mitigate this shortcoming, the disturbance detection is investigated as an open classification task and a novel recurrent Siamese neural network architecture is introduced to identify and locate known and unknown disturbance events from phasor measurements. Extending preliminary work, a probabilistic distance-based classification approach with an integrated rejection mechanism is presented, which enables to learn class-dependent decision boundaries and margins to reduce the open-set risk. A detailed performance analysis is presented including multiple benchmark methods in different closed-set and open-set classification tasks for a simulated power transmission system. Additionally, a limited and full observability of the grid with phasor measurements are addressed in the experiments.