MUMBAI, India, Jan. 9 -- Intellectual Property India has published a patent application (202511115809 A) filed by IMS Engineering College, Ghaziabad, Uttar Pradesh, on Nov. 23, 2025, for 'system and method for topology-aware transient stability assessment of power systems using ensemble and deep learning models.'
Inventor(s) include Atul Kumar Kushwaha; and Pushpender.
The application for the patent was published on Jan. 9, under issue no. 02/2026.
According to the abstract released by the Intellectual Property India: "The present invention relates to a system and method for transient stability assessment of electric power systems using topology-aware ensemble and deep learning models implemented on physical computing hardware. Synchrophasor and SCADA measurements together with network topology data are collected in real time and transformed into feature vectors capturing post-fault generator load angle excursions and line status information. A stability assessment server executes an ensemble module including Extreme Gradient Boosting and Random Forest models, and a deep learning module including a multi-layer perceptron and one-dimensional convolutional neural network. Model outputs are combined in a hybrid decision engine that classifies operating states as stable or unstable and provides confidence indices for control room operators. Training data are generated offline from time-domain simulations of multiple contingencies on benchmark or utility networks. The invention enables accurate, scalable and topology-sensitive transient stability assessment suitable for real-time protection and preventive control under diverse grid operating conditions."
Disclaimer: Curated by HT Syndication.
