arXiv subjects

Meng Yue

Publications and source records attributed to Meng Yue.

At least 19 recordsLinked to original sources

arXiv2026

Task-Conditional Faithfulness Auditing of Multimodal LLMs for Grid Diagnosis

Multimodal large language models (LLMs) can combine topology, measurements, and incident text for grid diagnosis, yet answer accuracy does not establish that task-appropriate evidence was used. This letter proposes a general framework in order to conduct task-conditional faithfulness audit. It compares self-reported reliance, intervention-derived behavioral reliance, and preregistered engineering importance. The framework first registers task-specific evidence requirements and compares them with self-reported reliance and behavioral changes under controlled modality ablations. To resolve detected discrepancies, we design an evidence-gated correction and re-audit mechanism that regenerates failed responses under evidence constraints and independently re-ablates them to verify improved grounding without performance loss. Case studies evaluate three differently scaled LLMs on IEEE 39- and 118-bus scenarios. These results validate the framework ability to detect, diagnose, and correct task-conditional faithfulness failures.

cs.AI↗

arXiv2026

Network Interdependency-Informed Power System Dynamic Trajectory Prediction Utilizing Black-Box Modeling of Multiple Inverter-Based Resources

Black-box modeling of inverter-based resources (IBRs) has attracted growing interest for real-time grid operation and control in the presence of proprietary electronic control architectures. Existing machine learning (ML)-based online dynamic trajectory prediction approaches using IBR black-box models either significantly accumulate prediction errors when multiple surrogates are simultaneously used or ignore measurement errors, limiting their deployment in practical grids. To address these limitations, this paper proposes a novel network interdependency-informed ML algorithm for online dynamic trajectory prediction in IBR-integrated power systems. A modular spatiotemporal attention network (STAN)-based predictor for the black-box modeling of each IBR unit is first proposed. Utilizing past measurements, the proposed STAN can effectively capture and predict the spatiotemporal dynamics of IBRs by employing an attention mechanism to attend to the most pertinent features for trajectory prediction. Furthermore, a novel hybrid physics-informed loss function that integrates a decoupled linearized AC power flow formulation is proposed. The proposed loss function effectively ensures physical consistency of predictions within network operation while avoiding the computational complexity of iterative power flow solving, thereby enabling efficient gradient backpropagation and overall improved prediction accuracy. Case studies on the IEEE 14- and WECC 179-bus systems demonstrate that the proposed method achieves significant accuracy enhancement and robustness against measurement errors, outperforming recent ML-based trajectory prediction methods.

eess.SY↗

arXiv2025

From Natural Language to Solver-Ready Power System Optimization: An LLM-Assisted, Validation-in-the-Loop Framework

This paper introduces a novel Large Language Models (LLMs)-assisted agent that automatically converts natural-language descriptions of power system optimization scenarios into compact, solver-ready formulations and generates corresponding solutions. In contrast to approaches that rely solely on LLM to produce solutions directly, the proposed method focuses on discovering a mathematically compatible formulation that can be efficiently solved by off-the-shelf optimization solvers. Directly using LLMs to produce solutions often leads to infeasible or suboptimal results, as these models lack the numerical precision and constraint-handling capabilities of established optimization solvers. The pipeline integrates a domain-aware prompt and schema with an LLM, enforces feasibility through systematic validation and iterative repair, and returns both solver-ready models and user-facing results. Using the unit commitment problem as a representative case study, the agent produces optimal or near-optimal schedules along with the associated objective costs. Results demonstrate that coupling the solver with task-specific validation significantly enhances solution reliability. This work shows that combining AI with established optimization frameworks bridges high-level problem descriptions and executable mathematical models, enabling more efficient decision-making in energy systems

cs.AI↗

arXiv2025

A Deep Reinforcement Learning Method for Multi-objective Transmission Switching

Transmission switching is a well-established approach primarily applied to minimize operational costs through strategic network reconfiguration. However, exclusive focus on cost reduction can compromise system reliability. While multi-objective transmission switching can balance cost savings with reliability improvements, feasible solutions become exceedingly difficult to obtain as system scale grows, due to the inherent nonlinearity and high computational demands involved. This paper proposes a deep reinforcement learning (DRL) method for multi-objective transmission switching. The method incorporates a dueling-based actor-critic framework to evaluate the relative impact of each line switching decision within the action space, which improves decision quality and enhances both system reliability and cost efficiency. Numerical studies on the IEEE 118-bus system verify the effectiveness and efficiency of the proposed approach compared to two benchmark DRL algorithms.

eess.SY↗

arXiv2025

Reinforcement Learning Based Symbolic Regression for Load Modeling

With the increasing penetration of renewable energy sources, growing demand variability, and evolving grid control strategies, accurate and efficient load modeling has become a critical yet challenging task. Traditional methods, such as fixed-form parametric models and data-driven approaches, often struggle to balance accuracy, computational efficiency, and interpretability. This paper introduces a novel symbolic regression algorithm based on the Actor-Critic reinforcement learning framework, specifically tailored for dynamic load modeling. The algorithm employs a trainable expression tree with controlled depth and a predefined set of operators to generate compact and interpretable mathematical expressions. The Actor network probabilistically selects operators for the symbolic expression, while the Critic evaluates the resulting expression tree through a loss function. To further enhance performance, a candidate pool mechanism is implemented to store high-performing expressions, which are subsequently fine-tuned using gradient descent. By focusing on simplicity and precision, the proposed method significantly reduces computational complexity while preserving interpretability. Experimental results validate its superior performance compared to existing benchmarks, which offers a robust and scalable solution for dynamic load modeling and system analysis in modern power systems.

eess.SY↗

arXiv2024

Diffusion Model-based Parameter Estimation in Dynamic Power Systems

Parameter estimation, which represents a classical inverse problem, is often ill-posed as different parameter combinations can yield identical outputs. This non-uniqueness presents a critical barrier to accurate and unique identification. Here we introduce a parameter estimation framework to address such limits: the Joint Conditional Diffusion Model-based Inverse Problem Solver. By leveraging the stochasticity of diffusion models, it produces candidate solutions that capture underlying parameter distributions conditioned on the observations. Joint conditioning on multiple observations further narrows the posterior distributions of non-identifiable parameters. For composite load model parameterization, a challenging task in dynamic power systems, the proposed method achieves a 58.6% reduction in parameter estimation error compared to the single-condition model. It also accurately replicates system's dynamic responses under various electrical faults with root mean square errors below $4 \times {10^{ - 3}}$, exhibiting comprehensive advantages in calibration and efficiency over existing methods. Given its data-driven nature, it provides a general framework for parameter estimation while effectively mitigating the non-uniqueness problem across scientific domains.

cs.AI↗

arXiv2024

Conformalized Prediction of Post-Fault Voltage Trajectories Using Pre-trained and Finetuned Attention-Driven Neural Operators

This paper proposes a new data-driven methodology for predicting intervals of post-fault voltage trajectories in power systems. We begin by introducing the Quantile Attention-Fourier Deep Operator Network (QAF-DeepONet), designed to capture the complex dynamics of voltage trajectories and reliably estimate quantiles of the target trajectory without any distributional assumptions. The proposed operator regression model maps the observed portion of the voltage trajectory to its unobserved post-fault trajectory. Our methodology employs a pre-training and fine-tuning process to address the challenge of limited data availability. To ensure data privacy in learning the pre-trained model, we use merging via federated learning with data from neighboring buses, enabling the model to learn the underlying voltage dynamics from such buses without directly sharing their data. After pre-training, we fine-tune the model with data from the target bus, allowing it to adapt to unique dynamics and operating conditions. Finally, we integrate conformal prediction into the fine-tuned model to ensure coverage guarantees for the predicted intervals. We evaluated the performance of the proposed methodology using the New England 39-bus test system considering detailed models of voltage and frequency controllers. Two metrics, Prediction Interval Coverage Probability (PICP) and Prediction Interval Normalized Average Width (PINAW), are used to numerically assess the model's performance in predicting intervals. The results show that the proposed approach offers practical and reliable uncertainty quantification in predicting the interval of post-fault voltage trajectories.

cs.LG↗

arXiv2024

Discovery and Characterization of Cross-Area and Intra-Area SSOs Sensitive to Delay in Droop Control of Grid-Forming Converters

Subsynchronous oscillations (SSOs) involving grid-forming converters (GFCs) are in a less familiar territory of power system dynamics. This letter reports a new phenomenon namely cross-area SSOs in grids with 100% droop-controlled GFC-based renewable penetration, which was discovered during our study on evaluating the adequacy of quasistationary phasor calculus (QPC) and space phasor calculus (SPC)-based models in capturing SSOs. We present frequency-domain characterization of such oscillatory modes in addition to intra-area SSOs in grids involving GFCs and study the impact of a delay in power-frequency droop feedback loop in regards to their stability. Electromagnetic transient (EMT) simulations validate our findings.

eess.SY↗

arXiv2024

A Case Study on Modeling Adequacy of a Grid with Subsynchronous Oscillations Involving IBRs

A case study on modeling adequacy of a grid in presence of renewable resources based on grid-forming converters (GFCs) is the subject matter of this paper. For this purpose, a 4-machine 11-bus IEEE benchmark model is modified by considering GFCs replacing synchronous generators that led to unstable subsynchronous oscillations (SSOs). We aim to: (a) understand if transmission network dynamics should be considered in such cases, (b) revisit the space-phasor-calculus (SPC) in d-q frame under balanced condition that captures such phenomena and lends itself to eigenvalue analysis, and (c) emphasize limitations of such models while underscoring their importance for large-scale power system simulations. Time-domain and frequency-domain results from SPC and quasistationary phasor calculus (QPC) models are compared with electromagnetic transient (EMT)-based simulations. It is shown that models with transmission line dynamics in SPC framework can capture the SSO mode while QPC models that neglect these dynamics fail to do so.

eess.SY↗

arXiv2024

An Approach to Evaluate Modeling Adequacy for Small-Signal Stability Analysis of IBR-related SSOs in Multimachine Systems

Time-varying phasor-based analysis of subsynchronous oscillations (SSOs) involving grid-following converters (GFLCs) and its benchmarking with electromagnetic transient (EMT) models have so far been restricted to highly simplified grid models with constant voltage sources behind series R-L circuits. In this paper, modeling adequacy of bulk power systems with synchronous generators (SGs), transmission systems, loads, and GFLCs are considered. To this end, we revisit the notions of time-varying phasor calculus, highlighting the distinction between space-phasor-calculus (SPC) and two often interchangeably used frameworks namely baseband-abc and generalized averaging. We present the models of grids in SPC framework that include transmission line dynamics, load dynamics, and SG stator transients. Next, we propose a generic approach to study modeling adequacy in small-signal sense by (a) identifying critical modes through eigenvalue and singular value analysis followed by (b) using weighted maximum singular value error magnitudes as metrics, and (c) further cross-validation. Using a modified 4-machine IEEE benchmark model with up to 3 GFLCs we show that SPC framework can be used for analysis of SSOs. Further, we consider the quasistationary phasor calculus (QPC) framework that neglects transmission line, load, and SG stator dynamics to show its adequacy in SSO modeling and analysis. Time-domain and frequency-domain results with EMT models are also presented.

eess.SY↗

arXiv2023

Cooperative Multi-Agent Deep Reinforcement Learning for Adaptive Decentralized Emergency Voltage Control

Under voltage load shedding (UVLS) for power grid emergency control builds the last defensive perimeter to prevent cascade outages and blackouts in case of contingencies. This letter proposes a novel cooperative multi-agent deep reinforcement learning (MADRL)-based UVLS algorithm in an adaptive decentralized way. With well-designed input signals reflecting the voltage deviation, newly structured neural networks are developed as intelligent agents to obtain control actions and their probabilities to accommodate high uncertainties in volatile power system operations. Moreover, the interaction among the agents for coordinated control is implemented and refined by a state-of-the-art attention mechanism, which helps agents concentratively learn effective interacted information. The proposed method realizes decentralized coordinated control, adapting to extremely high uncertainties. Case studies on an IEEE benchmark system indicate the superior performance of the proposed algorithm.

eess.SY↗

arXiv2023

Federated attention consistent learning models for prostate cancer diagnosis and Gleason grading

Artificial intelligence (AI) holds significant promise in transforming medical imaging, enhancing diagnostics, and refining treatment strategies. However, the reliance on extensive multicenter datasets for training AI models poses challenges due to privacy concerns. Federated learning provides a solution by facilitating collaborative model training across multiple centers without sharing raw data. This study introduces a federated attention-consistent learning (FACL) framework to address challenges associated with large-scale pathological images and data heterogeneity. FACL enhances model generalization by maximizing attention consistency between local clients and the server model. To ensure privacy and validate robustness, we incorporated differential privacy by introducing noise during parameter transfer. We assessed the effectiveness of FACL in cancer diagnosis and Gleason grading tasks using 19,461 whole-slide images of prostate cancer from multiple centers. In the diagnosis task, FACL achieved an area under the curve (AUC) of 0.9718, outperforming seven centers with an average AUC of 0.9499 when categories are relatively balanced. For the Gleason grading task, FACL attained a Kappa score of 0.8463, surpassing the average Kappa score of 0.7379 from six centers. In conclusion, FACL offers a robust, accurate, and cost-effective AI training model for prostate cancer pathology while maintaining effective data safeguards.

cs.CV↗

arXiv2023

On Approximating the Dynamic Response of Synchronous Generators via Operator Learning: A Step Towards Building Deep Operator-based Power Grid Simulators

This paper develops an Operator Learning framework for approximating the dynamic response of synchronous generators. The framework can be used to (i) build a neural network-based generator model that interacts with a power grid simulator or (ii) shadow the true generator's transient response. First, we develop a data-driven Deep Operator Network (DeepONet) to approximate the infinite-dimensional solution operator of the generators. Then, we design a numerical scheme based on DeepONet that simulates the generator's response over a given time horizon. The proposed scheme recursively employs the trained DeepONet to simulate the response for a given multi-dimensional input that describes the interaction between the generator and the power grid. In addition, we design a residual DeepONet numerical scheme that can incorporate information from existing mathematical models. We accompany this residual DeepONet scheme with an estimate for the prediction's cumulative error. Finally, we build a data aggregation (DAgger) strategy that allows fine-tuning of DeepONets using aggregated training data that the DeepONets will likely encounter during interactive simulations with other grid components. As a proof of concept, we demonstrate that the proposed frameworks can effectively approximate the transient model of a synchronous generator.

cs.LG↗

arXiv2022

DeepGraphONet: A Deep Graph Operator Network to Learn and Zero-shot Transfer the Dynamic Response of Networked Systems

This paper develops a Deep Graph Operator Network (DeepGraphONet) framework that learns to approximate the dynamics of a complex system (e.g. the power grid or traffic) with an underlying sub-graph structure. We build our DeepGraphONet by fusing the ability of (i) Graph Neural Networks (GNN) to exploit spatially correlated graph information and (ii) Deep Operator Networks~(DeepONet) to approximate the solution operator of dynamical systems. The resulting DeepGraphONet can then predict the dynamics within a given short/medium-term time horizon by observing a finite history of the graph state information. Furthermore, we design our DeepGraphONet to be resolution-independent. That is, we do not require the finite history to be collected at the exact/same resolution. In addition, to disseminate the results from a trained DeepGraphONet, we design a zero-shot learning strategy that enables using it on a different sub-graph. Finally, empirical results on the (i) transient stability prediction problem of power grids and (ii) traffic flow forecasting problem of a vehicular system illustrate the effectiveness of the proposed DeepGraphONet.

cs.LG↗

arXiv2022

DeepONet-Grid-UQ: A Trustworthy Deep Operator Framework for Predicting the Power Grid's Post-Fault Trajectories

This paper proposes a new data-driven method for the reliable prediction of power system post-fault trajectories. The proposed method is based on the fundamentally new concept of Deep Operator Networks (DeepONets). Compared to traditional neural networks that learn to approximate functions, DeepONets are designed to approximate nonlinear operators. Under this operator framework, we design a DeepONet to (1) take as inputs the fault-on trajectories collected, for example, via simulation or phasor measurement units, and (2) provide as outputs the predicted post-fault trajectories. In addition, we endow our method with a much-needed ability to balance efficiency with reliable/trustworthy predictions via uncertainty quantification. To this end, we propose and compare two methods that enable quantifying the predictive uncertainty. First, we propose a \textit{Bayesian DeepONet} (B-DeepONet) that uses stochastic gradient Hamiltonian Monte-Carlo to sample from the posterior distribution of the DeepONet parameters. Then, we propose a \textit{Probabilistic DeepONet} (Prob-DeepONet) that uses a probabilistic training strategy to equip DeepONets with a form of automated uncertainty quantification, at virtually no extra computational cost. Finally, we validate the predictive power and uncertainty quantification capability of the proposed B-DeepONet and Prob-DeepONet using the IEEE 16-machine 68-bus system.

math.NA↗

arXiv2022

glassoformer: a query-sparse transformer for post-fault power grid voltage prediction

We propose GLassoformer, a novel and efficient transformer architecture leveraging group Lasso regularization to reduce the number of queries of the standard self-attention mechanism. Due to the sparsified queries, GLassoformer is more computationally efficient than the standard transformers. On the power grid post-fault voltage prediction task, GLassoformer shows remarkably better prediction than many existing benchmark algorithms in terms of accuracy and stability.

cs.LG↗

arXiv2021

Adaptive Load Shedding for Grid Emergency Control via Deep Reinforcement Learning

Emergency control, typically such as under-voltage load shedding (UVLS), is broadly used to grapple with low voltage and voltage instability issues in practical power systems under contingencies. However, existing emergency control schemes are rule-based and cannot be adaptively applied to uncertain and floating operating conditions. This paper proposes an adaptive UVLS algorithm for emergency control via deep reinforcement learning (DRL) and expert systems. We first construct dynamic components for picturing the power system operation as the environment. The transient voltage recovery criteria, which poses time-varying requirements to UVLS, is integrated into the states and reward function to advise the learning of deep neural networks. The proposed approach has no tuning issue of coefficients in reward functions, and this issue was regarded as a deficiency in the existing DRL-based algorithms. Extensive case studies illustrate that the proposed method outperforms the traditional UVLS relay in both the timeliness and efficacy for emergency control.

eess.SY↗

arXiv2020

Review on Set-Theoretic Methods for Safety Verification and Control of Power System

Increasing penetration of renewable energy introduces significant uncertainty into power systems. Traditional simulation-based verification methods may not be applicable due to the unknown-but-bounded feature of the uncertainty sets. Emerging set-theoretic methods have been intensively investigated to tackle this challenge. The paper comprehensively reviews these methods categorized by underlying mathematical principles, that is, set operation-based methods and passivity-based methods. Set operation-based methods are more computationally efficient, while passivity-based methods provide semi-analytical expression of reachable sets, which can be readily employed for control. Other features between different methods are also discussed and illustrated by numerical examples. A benchmark example is presented and solved by different methods to verify consistency.

eess.SY↗