arXiv subjects

Shuchismita Biswas

Publications and source records attributed to Shuchismita Biswas.

9 recordsLinked to original sources

arXiv2026

Skill-Based AI Agents for Power-System Studies

This paper describes a skill-based agentic framework for power-system studies using Model Context Protocol (MCP)-connected engineering tools. A custom MCP server was developed to expose Siemens PTI PSSE functions for power-flow analysis, dynamic simulation, result extraction, and model-validation workflows. Two implementation pathways built on a programmable OpenAI Agents software development kit (SDK) and a Claude Code command-line interface (CLI) were evaluated, both using reusable skills, subagents, MCP tools, data-repository connections, and local shell/Python execution. Both frontier-model-based implementations successfully executed representative study tasks. Success was evaluated based on task completion, output accuracy, and the need for human expert interventions. Results based on public datasets show that agentic systems can greatly accelerate power system dynamic simulation process for transmission planning studies leveraging industry-grade simulation platforms. This points toward a shift in transmission planning practice, where agentic systems could handle routine simulation setup and result extraction, allowing engineers to focus expert judgment on scenario design and interpretation rather than tool operation.

eess.SY↗

arXiv2026

Assessing Risks of Hydro-Generator Shaft Fatigue from Data Center Load Oscillations

Large AI data center loads can introduce persistent sub-synchronous active-power oscillations that may impact nearby generators by exciting torsional modes and increasing shaft stress. This paper presents a model-based framework for evaluating hydro-generator shaft fatigue risk under oscillatory loading. An electromagnetic transient simulation model is developed using a two-mass turbine-generator shaft representation with parameters from real-world generation units and a configurable AI data center load. The risk assessment is performed in two stages. First, a network transfer function quantifies the propagation of load oscillations from the data center point of interconnection to the hydro-generator terminal. A plant transfer function then characterizes the resulting shaft torque amplification. A frequency-scan approach identifies resonance regions and evaluates torque amplification at individual forcing frequencies. Parametric studies show that amplification is strongly affected by generator-to-turbine inertia ratio and torsional damping. Lower inertia ratios shift torsional modes to lower frequencies and increase amplification, indicating that some Kaplan-type units may be more susceptible than comparable Francis or Pelton units. Reduced damping further increases resonant response and fatigue exposure. A simplified fatigue assessment based on S--N curves and the Goodman diagram relates simulated torque response to mechanical integrity. The resulting Goodman safety factor provides a practical metric for evaluating the impact of persistent AI data center oscillations on hydro-generator service life and supports interconnection studies, oscillation limits, and plant-level monitoring strategies.

eess.SY↗

arXiv2021

A Model-Agnostic Method for PMU Data Recovery Using Optimal Singular Value Thresholding

This paper presents a fast model-agnostic method for recovering noisy Phasor Measurement Unit (PMU) datastreams with missing entries. The measurements are first transformed into a Page matrix, and the original signals are reconstructed using low-rank matrix estimation based on optimal singular value thresholding. Two variations of the recovery algorithm are shown- a) an offline block-processing method for imputing past measurements, and b) an online method for predicting future measurements. Information within a PMU channel (temporal correlation) as well as from different PMUchannels in a network (spatial correlation) are utilized to recover degraded data. The proposed method is fast and needs no explicit knowledge of the underlying system model or measurement noise distribution. The performance of the recovery algorithms is illustrated using simulated measurements from the IEEE 39-bus test system as well as real measurements from an anonymized U.S. electric utility. Extensive numeric tests show that the original signals can be accurately recovered in the presence of additive noise, consecutive data drop as well as simultaneous data erasure across multiple PMU channels.

eess.SP↗

arXiv2021

Model Validation Study for Central American Regional Electrical Interconnected System

The Central American Regional Interconnected Power System (SER) connects six countries: Guatemala, El Salvador, Honduras, Nicaragua, Costa Rica, and Panama, it is operated by the regional system operator Ente Operador Regional (EOR). Due to its geographical shape and layout of major transmission lines, SER has a weakly meshed grid, where disturbances can easily propagate, challenging its reliability. Having an accurate dynamic model is important for EOR when facing those reliability challenges. This paper describes interconnection-level model validation efforts for the SER and Mexico interconnected system. A detailed equivalent model of Mexico is incorporated in the existing SER planning model used by EOR. The resultant model is then validated using simulated dynamic contingency analysis and real system disturbance data. A fully automated suite of scripts is also developed and shared with EOR engineers. This work helps EOR improve their validation routine practices, to continuously improve SER dynamic model, and hence its reliability.

eess.SY↗

arXiv2020

Chance-Constrained Optimal Distribution Network Partitioning to Enhance Grid Resilience

This paper formulates a chance-constrained optimal distribution network partitioning (ODNP) problem addressing uncertainties in load and renewable energy generation; and presents a solution methodology using sample average approximation (SAA). The objective is to identify potential sub-networks in the existing distribution grid; that are likely to survive as self-adequate islands if supply from the main grid is lost. {This constitutes a planning problem.} Practical constraints like ensuring network radiality and availability of grid-forming generators are considered. Quality of the obtained solution is evaluated by comparison with: a) an upper bound on the probability that the identified islands are supply-deficient, and b) a lower bound on the optimal value of the true problem. Performance of the ODNP formulation is illustrated on a modified IEEE 37-bus feeder. It is shown that the network flexibility is well utilized; the partitioning changes with risk budget; and that the SAA method is able to yield good quality solutions with modest computation cost.

eess.SY↗

arXiv2020

Deep Neural Network based Wide-Area Event Classification in Power Systems

This paper presents a wide-area event classification in transmission power grids. The deep neural network (DNN) based classifier is developed based on the availability of data from time-synchronized phasor measurement units (PMUs). The proposed DNN is trained using Bayesian optimization to search for the best hyperparameters. The effectiveness of the proposed event classification is validated through the real-world dataset of the U.S. transmission grids. This dataset includes line outage, transformer outage, frequency event, and oscillation events. The validation process also includes different PMU outputs, such as voltage magnitude, angle, current magnitude, frequency, and rate of change of frequency (ROCOF). The simulation results show that ROCOF as input feature gives the best classification performance. In addition, it is shown that the classifier trained with higher sampling rate PMUs and a larger dataset has higher accuracy.

eess.SP↗

arXiv2019

A Routing and Link Scheduling Strategy for Smart Grid NAN Communications

As large scale deployment of smart devices in the power grid continues, research efforts need to increasingly focus on efficient communication of generated information. This paper describes a strategy for static routing and scheduling of messages in a multi-hop wireless Smart Grid Neighborhood Area Network (NAN) with multiple source nodes and a common set of destinations or gateways. The problem is formulated as a Mixed Integer Linear Program (MILP) and solved using commercial optimization solver CPLEX. Feasibility of the scheme is demonstrated using different network models, constraints, message injection rates, and initial conditions. It is shown that the proposed approach can be used to generate an optimal link schedule for collecting user-generated bids in a transactive energy market in the least possible time. It is also shown that the methodology is applicable to multiple destination nodes and that their location affects message delivery time.

cs.NI↗

arXiv2019

Proactive Islanding of the Power Grid to Mitigate High-Impact Low-Frequency Events

This paper proposes a methodology for enhancing power systems resiliency by proactively splitting an interconnected grid into small self-sustaining islands in preparation for extreme events. The idea is to posture the system so that cascading outages can be bound within affected areas, preventing the propagation of disturbances to the rest of the system. This mitigation strategy will prove especially useful when advance notification of a threat is available but its nature not well understood. In our method, islands are determined using a constrained hierarchical spectral clustering technique. We further check the viability of the resultant islands using steady-state AC power flow. The performance of the approach is illustrated using a detailed PSS/E model of the heavily meshed transmission network operated by PJM Interconnection in the eastern USA. Representative cases from different seasons show that variations in power flow patterns influence island configuration.

eess.SY↗

arXiv2019

DeVLearn: A Deep Visual Learning Framework for Localizing Temporary Faults in Power Systems

Frequently recurring transient faults in a transmission network may be indicative of impending permanent failures. Hence, determining their location is a critical task. This paper proposes a novel image embedding aided deep learning framework called DeVLearn for faulted line location using PMU measurements at generator buses. Inspired by breakthroughs in computer vision, DeVLearn represents measurements (one-dimensional time series data) as two-dimensional unthresholded Recurrent Plot (RP) images. These RP images preserve the temporal relationships present in the original time series and are used to train a deep Variational Auto-Encoder (VAE). The VAE learns the distribution of latent features in the images. Our results show that for faults on two different lines in the IEEE 68-bus network, DeVLearn is able to project PMU measurements into a two-dimensional space such that data for faults at different locations separate into well-defined clusters. This compressed representation may then be used with off-the-shelf classifiers for determining fault location. The efficacy of the proposed framework is demonstrated using local voltage magnitude measurements at two generator buses.

eess.SY↗