Abstract
Investigators discuss new findings in Machine Learning. According to news originating from Manchester, United Kingdom, by NewsRx correspondents, research stated, "This paper proposes a machine learn ing-based method for predicting generator rotor angle responses (trajectories) f ollowing large disturbance in power system. A Long Short-Term Memory (LSTM)-base d Recurrent Neural Network (RNN) is used to predict responses at any time instan t after the fault inception by designing the input and output of the network wit h predefined sliding time windows." Our news journalists obtained a quote from the research from the University of M anchester, "The numbers of neurons in the LSTM and Fully-Connected (FC) layers a re optimised with the Particle Swarm Optimisation (PSO) algorithm, which was pro ved to be effective in similar tasks in past research. A wide range of realistic constraints associated with the use of the Phasor Measurement Unit (PMU) data h as been considered, to demonstrate the feasibility of the proposed method when a pplied in real systems."
NETL
NSTL