Low-inertia power systems require more innovative operation, control, and protection strategies to maintain the operation secure and reliable. One of the challenges related to these systems is the need for knowledge of the inertia level (kinetic energy stored in the rotating masses) in real time. This paper proposes a framework for training and deploying machine learning methods for real-time power systems’ kinetic energy forecasting. Linear Regression and Long Short-Term Memory methods are implemented in the Python interpreter of the Typhoon HIL 404 real-time simulator for forecasting the kinetic energy of the Nordic Power System in real-time. This paper provides implementation details together with possible future expansions of the framework. Simulation results show that the trained models can predict the kinetic energy in a forecasting horizon of four hours with a Mean Absolute Error lower than other methods currently available in the literature.@en

This paper is a step forward in the effort to create an appropriate open-access library of benchmark test systems for offline and real-time simulations. The library will consist of 13 test systems for steady-state and dynamic power system analysis considering different relevant features (topology, control mode and element details). In this scientific paper, the authors selected one of the test systems, the 5-bus test transmission system, in meshed topology. Details of its implementation using several power system analysis platforms for offline and online/real-time simulation. Offline steady-state performance results are presented using PowerWorld, DIgSILENT PowerFactory and IPSA. Plots of the main electromechanical variables of the time-domain response considering a generator outage are presented using offline simulations from PowerFactory and real-time simulation ePHASORSIM. Simulation results show very minimal discrepancies between the results considering different platforms.

@en

This paper presents a simple validation of ePHASORSIM's user-defined model of a Virtual Synchronous Machine (VSM) suitable for real-time simulations. The validation consists of a software-to-software comparison of the real-time simulator ePHASORSIM against the offline transient simulation tool PowerFactory. The comparison evaluates the models in the native library and user-defined models imported to ePHASORSIM. These user-defined models are coded in a Modelica environment and imported as a functional mock-up unit (FMU) model-the dynamic model of a voltage source converter operating as a VSM was implemented to test this functionality. A modified version of the IEEE 39-bus New England system was used for testing and validation. The time series from each (software) transient simulation were compared using the percentage error and the mean percentage error (MPE); the results demonstrate the suitability of the proposed approach.

@en