Searcharxiv⌕ Search

arXiv subjects

Rupesh Sah

Publications and source records attributed to Rupesh Sah.

2 recordsLinked to original sources

Stop Early, Stay Simple: Evidence Acquisition for Power System Fault and Attack Diagnosis

Diagnostic models for cyber-physical power systems usually inspect every telemetry source for every event, although some events are clear from one source and others need several. We ask when a learned policy for choosing that evidence is worth its added complexity. To answer this, we present ActiGrid, a benchmark framework for active evidence acquisition that pairs a classifier trained to tolerate missing modalities with a Double Deep Q-Network (DQN), which either requests another source or stops and diagnoses but never operates grid actuators. On the public TU Delft digital substation and MSU/ORNL power system attack benchmarks, we compare the DQN with fixed subsets and orders, calibrated entropy stopping, a greedy value of information rule, and tree ensembles trained per subset. The learned policy does adapt to what it observes, yet it is statistically indistinguishable from entropy stopping on TU Delft and Pareto dominated by simple controls on MSU/ORNL, while compact subset classifiers outperform it while reading fewer sources on both benchmarks. Entropy stopping run over those subset classifiers reaches the highest mean Macro-F1 on TU Delft (0.928 while reading 57% of the sources) but brings no saving over a static three source subset on MSU/ORNL, where no method exceeds 0.45 Macro-F1. Selective acquisition can pay off, but on these benchmarks it does not need a learned policy.

cs.CR↗

Integrating AI and Simulation for Teaching Power System Dynamics: An Interactive Framework for Engineering Education

Artificial Intelligence (AI), especially cloud platforms and large language models (LLMs), is changing how engineering is taught by making learning more interactive and flexible. However, in electrical engineering and energy systems, students often find power system dynamics difficult to understand because the concepts are abstract, math-heavy, and there are limited opportunities for hands-on practice. This paper presents an AI-based interactive learning framework that combines simulation with intelligent feedback to improve understanding and student engagement. The framework has three connected parts: an AI layer that provides explanations and guidance, a simulation layer that models system behavior, and a user layer that allows students to interact with the system in real time. These parts work together in a continuous loop where students explore how the system behaves, change parameters, and receive feedback based on the results. The paper also provides a step-by-step process to help educators design and apply AI-supported learning environments, including breaking down concepts, using simulations, and assessing performance. This method helps students learn through practice and better understand how ideas from class apply to real power systems. It also provides a practical way to improve electrical engineering education and helps students get ready to use AI tools carefully and responsibly in engineering.

eess.SY↗