This paper develops a new method for voltage instability prediction using a recurrent neural network with long short-term memory. The method is aimed to be used as a supplementary warning system for system operators, capable of assessing whether the current state will cause voltage instability issues several minutes into the future. The proposed method uses a long sequence-based network, where both real-time and historic data are used to enhance the classification accuracy. The network is trained and tested on the Nordic32 test system, where combinations of different operating conditions and contingency scenarios are generated using time-domain simulations. The method shows that almost all N-1 contingency test cases were predicted correctly, and N-1-1 contingency test cases were predicted with over 95 % accuracy only seconds after a disturbance. Further, the impact of sequence length is examined, showing that the proposed long sequenced-based method provides significantly better classification accuracy than both a feedforward neural network and a network using a shorter sequence.

This study develops a machine learning-based method for a fast estimation of the dynamic voltage security margin (DVSM). The DVSM can incorporate the dynamic system response following a disturbance and it generally provides a better measure of security than the more commonly used static voltage security margin (VSM). Using the concept of transient P-V curves, this study first establishes and visualises the circumstances when the DVSM is to prefer the static VSM. To overcome the computational difficulties in estimating the DVSM, this study proposes a method based on training two separate neural networks on a data set composed of combinations of different operating conditions and contingency scenarios generated using time-domain simulations. The trained neural networks are used to improve the search algorithm and significantly increase the computational efficiency in estimating the DVSM. The machine learning-based approach is thus applied to support the estimation of the DVSM, while the actual margin is validated using time-domain simulations. The proposed method was tested on the Nordic32 test system and the number of time-domain simulations was possible to reduce with ∼70%, allowing system operators to perform the estimations in near real-time.

This paper develops a new method for voltage instability prediction using a recurrent neural network with long short-term memory. The method is aimed to be used as a supplementary warning system for system operators, capable of assessing whether the current state will cause voltage instability issues several minutes into the future. The proposed method use a long sequence-based network, where both real-time and historic data are used to enhance the classification accuracy. The network is trained and tested on the Nordic32 test system, where combinations of different operating conditions and contingency scenarios are generated using time-domain simulations. The method shows that almost all N-1 contingency test cases were predicted correctly, and N-1-1 contingency test cases were predicted with over 93 % accuracy only seconds after a disturbance. Further, the impact of sequence length is examined, showing that the proposed long sequenced-based method provides significantly better classification accuracy than both a feedforward neural network and a network using a shorter sequence.Index Terms-Dynamic security assessment, long short-term memory, recurrent neural network, voltage instability prediction, voltage security assessment.Robert Eriksson (SM'16) received the M.Sc. and Ph.D. degrees in electrical engineering from the KTH Royal in 2004. He is currently a Senior Lecturer with the Division of Electric Power Engineering, Department of Energy and Environment, Chalmers University of Technology. His current research interests include power system operation and planning, power market and deregulation issues, grid integration of renewable energy, and plug-in electric vehicles.

This paper examines how various integration aspects of full converter wind turbines, such as grid code design, control aspects, and placement of turbines, impact the long-term voltage stability of a power system. The simulations are conducted on a modified version of the Nordic32 test system. Different cases have been analyzed and show, for example, that if over-dimensioning of converters is implemented, it is mainly the converters' current capacity that should be increased since the voltage limitation of converters seldom is reached during voltage instability events. Furthermore, a restrictive reactive control scheme is tested, with the aim of minimizing the wear and maintenance of converter components. Although found to generally reduce the voltage stability, the proposed control scheme could be adopted during specific conditions where the local need of voltage support is low. The placement of larger wind farms was found to have the largest impact, both on long-term voltage stability of the system itself, and on the effect that the analyzed design and control aspects had on the system stability. Consequently, the placement of WFs is found be an important factor to consider when designing ancillary services and grid codes for wind power.

No abstract