With the recent growing interest in renewable energy integrated power systems across the globe for the various economic and environmental benefits, it is also significant to consider their influence on voltage stability in power systems. Therefore, this paper reports the static voltage stability impact of solar photovoltaic generation on power networks using PowerWorld simulator power-voltage (P–V)- and voltage-reactive power (V–Q)-curves to investigate the renewable energy generator model performance suitability. The impact of varying power factor control and static voltage droop control of a photovoltaic plant on the maximum generated power, threshold voltage profile and reactive power marginal loading has been examined. Besides, the concept of percentage change in voltage-power sensitivity has been systematically utilized to determine the optimal location for the solar photovoltaic generator on the power grid and the feasible penetrations have been defined for selected system buses. From the simulation results it can be concluded that in a steady-state analysis of the grid integrated power system the effects of power factor (pf) control and voltage droop control should be considered by power grid engineers for effective system operation and, equally, the application of percentage change in voltage-power sensitivity should be extended to real networks to determine the best positions for multiple installations of renewable energy resources.

This work proposes a real-time deep learning-based model for predicting the small-signal stability of an electrical network. The trained models equip power system operators with an accurate and fast monitoring tool which can be used during online operation. To achieve this objective, three different model architectures are employed in this research; stacked long short-term memory (LSTM), convolutional neural network (CNN)-LSTM and Convectional LSTM (Conv-LSTM). These models are trained using datasets which contain the oscillatory parameters (frequency and damping ratio) of both local and inter-area modes of oscillations. In addition, the voltage phasors at different buses are taken as the model input where the output comprises the real-time oscillatory patterns of the modes. Furthermore, the overall performance of proposed models is shown for the New-England 10-machine, 39-bus, IEEE 16-machine, 68-bus, 5-area, and IEEE 50-machine, 145-bus benchmark test cases. The main findings show that training CNN-LSTM and Conv-LSTM models provide better performance compared with the stacked-LSTM model. The former models have less number of parameters and thus shorter training time. In addition, CNN_LSTM and Conv-LSTM models are less prone to overfitting problems in the network and have a better ability in capturing spatial and temporal features inherent in input data.