Filters

Settings

Now showing1 - 3 of 3
  • Some of the metrics are blocked by your 
    consent settings
    Item type:Publication, Access status: without files ,
    Performance Assessment of State Estimation in Cyber-Physical Energy Systems
    (2021-06-28)
    Hassan, Batoul Hage
    ;
    Narayan, Anand
    ;
    Babazadeh, Davood
    ;
    Klaes, Marcel
    ;
    Lehnhoff, Sebastian
    In addition to various advantages, the strong interaction between power systems and Information and Communication Technologies (ICT) makes Cyber-Physical Energy Systems susceptible to new disturbances. State estimation (SE) is a vital part of the energy management system, for several other monitoring, management, and control services. Failure of state estimation leads to loss of situational awareness, which in turn has a detrimental impact on the grid operation. Therefore, it is essential to monitor the performance of state estimation considering various disturbances. This paper presents a model to assess the performance of the SE service by taking into consideration its requirements from both power and ICT domains. Following a review of existing approaches for performance assessment of the SE service in Smart Grids, a detailed description of the proposed model including its elements, metrics, and states is provided. The model is then evaluated using different scenarios considering the CIGRE MV benchmark grid.
    Publicationtype: Conference Paper
      45
  • Some of the metrics are blocked by your 
    consent settings
    Item type:Publication, Access status: without files ,
    Wind Turbine Failure Prediction Model using SCADA-based Condition Monitoring System
    (2021-06-28)
    Alzawaideh, Bara
    ;
    Teimourzadeh Baboli, Payam
    ;
    Babazadeh, Davood
    ;
    Horodyvskyy, Susanne
    ;
    Koprek, Isabel
    The ultimate goal of a condition monitoring system for wind turbines (WT) is to predict the upcoming failures; this could be achieved using artificial intelligence techniques. In this paper, a model for detecting excessive temperature anomalies in key components of WT i.e. gearbox, generator and transformer is proposed. This model consists of integrated modules continuously interact following the never-ending learning paradigm based on artificial neural networks addressing the challenge of the limited pre-classified data and lacking of the concept to be learned for a system with continuous change of its operating conditions: (i) the Normal Behavior (NB) module estimates the temperature of the WT key components, (ii) the Expected Time To Failure (ETTF) module calculates the deviation between the estimated normal temperature and the real-time measurement data to predict the upcoming failure of WT key components a few hours before occurring a failure, (iii) in the Anomaly Detection (AD) module, the temperature deviation time series signal is divided into normal or abnormal clusters. The proposed methodology has been applied on a real wind farm data in Germany. The results show that the system could correctly detect a large number of WT upcoming failures, this implies the effectiveness and generalization of the proposed model in terms of classification accuracy.
    Publicationtype: Conference Paper
      99
  • Some of the metrics are blocked by your 
    consent settings
    Item type:Publication, Access status: without files ,
    Power Systems Digital Twin under Measurement and Model Uncertainties: Network Parameter Tuning Approach
    (2021-06-28)
    Wibbeke, Jelke
    ;
    Aldebs, Mohannad
    ;
    Babazadeh, Davood
    ;
    Teimourzadeh Baboli, Payam
    ;
    Lehnhoff, Sebastian
    This paper addresses how a power system Digital Twin (DT) can be structured, what it should be able to do, and how it can possibly be implemented with already known methods. To this end, a structural framework for the design of power system DTs is presented. The framework consists of functional blocks such as model execution and model validation, with which the core of the DT, the virtual entity, is be built. Subsequently, a power system DT has been studied. Here, established approaches of state and parameter estimation like the weighted least squares or extended Kalman filter have been used as parts of the functional blocks. Combined they form an adaptive model of the physical system, which can be used in the framework. In particular, it turns out that under certain circumstances the accuracy of potential sensor measurement data may not be sufficient to realize the described methods under field conditions.
    Publicationtype: Conference Paper
      74