Search for: All records

The paper proposes an approach for data generation and action recommender system development when small-signal stability assessment is performed using deep learning algorithms. These algorithms are trained on labeled time-series data solving a classification task. In this paper we propose an approach that includes automatically generated labeled data for the action recommender and the deep learning methodology to implement the recommender framework. The deep learning methodology is based on convolutional neural networks (ResNet, Encoder, Time-LeNet) that are tuned for time-series input data and shown the best performance in comparison to other architectures. The proposed approach is validated on synthetic but realistic measurement data from the IEEE 9-bus system as a reference and further applied to a 769-bus system representing a region in the U. S. Eastern Interconnection. The performance of the method is evaluated using accuracy as a most common machine learning metric, as well as precision and recall. We show that the evaluation of the methodology on the generated imbalanced data has to be treated with additional metrics other than accuracy. The training time and the classification performance time is evaluated. 

Not AvailableEnergy models for power systems require ongoing updates to reflect advancements in equipment technology and the increasing complexity of power electronic devices. This study utilizes a Power Hardware-in-the-Loop (PHIL) experimental setup to validate custom photovoltaic (PV) inverter models, aiming to enhance and expedite the development of advanced renewable energy models. The research compares the performance of a physical inverter with generic Renewable Energy Source (RES) models recommended by the Western Electricity Coordinating Council (WECC). As inverter-based renewable energy sources become more prevalent in modern electrical grids, it is crucial that dynamic models accurately represent their real-world behavior. Accurate models improve our understanding of these energy resources and their interactions with the grid. The proposed model enhancements are designed to better reflect real inverter performance, based on insights from PHIL experiments. These models are developed using the open source Modelica language and the OpenIPSL Modelica Library, allowing integration across various simulation tools without re-implementation. The paper concludes with a thorough assessment, comparing the enhanced models with PHIL experiments on a real PV inverter in a controlled laboratory setting. The study provides the enhanced WECC RES models and validation data as open source resources, facilitating further research and development. 

The paper proposes an approach for fast small signal stability assessment on a short data window using deep learning algorithms. This paper shows that the proposed deep convolutional neural networks (CNNs)-based assessment approach is faster than traditional methods (i.e. Prony’s method). The evaluated CNNs are fully convolutional network (FCN), CNN with sub-sampling steps performed through max pooling (Time LeNet), time CNN, fully convolutional network with attention mechanism (Encoder), and CNN with a shortcut residual connection (ResNet). The proposed approach is validated on different synthetic measurement data sets generated from the IEEE 9-bus system that is used as a reference, and further applied to a 769-bus system representing a region in the U. S. Eastern Interconnection. We show that precision and recall are more informative metrics than accuracy for the reliability of the stability assessment process using the proposed methodology. In addition, the method’s efficiency is compared to classical Prony method. 

Enhancing grid resilience is proposed through the integration of distributed energy resources (DERs) with microgrids. Due to the diverse nature of DERs, there is a need to explore the optimal combined operation of these energy sources within the framework of microgrids. As such, this paper presents the design, implementation and validation of a Model Predictive Control (MPC)-based secondary control scheme to tackle two challenges: optimal islanded operation, and optimal re-synchronization of a microgrid. The MPC optimization algorithm dynamically adjusts input signals, termed manipulated variables, for each DER within the microgrid, including a gas turbine, an aggregate photovoltaic (PV) unit, and an electrical battery energy storage (BESS) unit. To attain optimal islanded operation, the secondary-level controller based on Model Predictive Control (MPC) was configured to uphold microgrid functionality promptly following the islanding event. Subsequently, it assumed the task of power balancing within the microgrid and ensuring the reliability of the overall system. For optimal re-synchronization, the MPC-based controller was set to adjust the manipulated variables to synchronize voltage and angle with the point of common coupling of the system. All stages within the microgrid operation were optimally achieved through one MPC-driven control system, where the controller can effectively guide the system to different goals by updating the MPC’s target reference. More importantly, the results show that the MPC-based control scheme is capable of controlling different DERs simultaneously, mitigating potentially harmful transient rotor torques from the re-synchronization as well as maintaining the microgrid within system performance requirements. 

Balanced data is required for deep neural networks (DNNs) when learning to perform power system stability assessment. However, power system measurement data contains relatively few events from where power system dynamics can be learnt. To mitigate this imbalance, we propose a novel data augmentation strategy preserving the dynamic characteristics to be learnt. The augmentation is performed using Variational Mode Decomposition. The detrended and the augmented data are tested for distributions similarity using Kernel Maximum Mean Discrepancy test. In addition, the effectiveness of the augmentation methodology is validated via training an Encoder DNN utilizing original data, testing using the augmented data, and evaluating the Encoder’s performance employing several metrics. 

This paper describes the development of a phasor-based campus microgrid model utilizing the Modelica language and the OpenIPSL library. The phasor-based modeling approach was chosen because the resulting microgrid model would yield faster simulation run times when compared to models developed using electromagnetic transient (EMT) methods. Beyond the benefits of simulation performance, this becomes necessary when attempting to understand dynamic phenomena arising under emergency conditions across time scales ranging from milliseconds to hours, which will aid in developing resiliency improvement plans for the real-world campus microgrid that the model represents. Considering the increasing number of distributed energy sources (DERs) being added to power grids across the world and the paradigm shift on how electrical grids can operate with more DERs, the implementation of such a microgrid campus model can help in the development and testing new control strategies to support new operational approaches while guaranteeing system stability and resiliency. The added benefit of having the microgrid model in Modelica is that it can be simulated in any Modelica complaint tool (both proprietary or not), preserving an open-source code, unlocked for the user to explore and adjust the implementation as well as observe and edit the mathematical formulation. This enables not only nonlinear time simulation, but also linear analysis techniques and other approaches to be applied.