arXiv subjects

Larry Pileggi

Publications and source records attributed to Larry Pileggi.

At least 19 recordsLinked to original sources

arXiv2025

Homotopy-Guided Self-Supervised Learning of Parametric Solutions for AC Optimal Power Flow

Learning to optimize (L2O) parametric approximations of AC optimal power flow (AC-OPF) solutions offers the potential for fast, reusable decision-making in real-time power system operations. However, the inherent nonconvexity of AC-OPF results in challenging optimization landscapes, and standard learning approaches often fail to converge to feasible, high-quality solutions. This work introduces a \textit{homotopy-guided self-supervised L2O method} for parametric AC-OPF problems. The key idea is to construct a continuous deformation of the objective and constraints during training, beginning from a relaxed problem with a broad basin of attraction and gradually transforming it toward the original problem. The resulting learning process improves convergence stability and promotes feasibility without requiring labeled optimal solutions or external solvers. We evaluate the proposed method on standard IEEE AC-OPF benchmarks and show that homotopy-guided L2O significantly increases feasibility rates compared to non-homotopy baselines, while achieving objective values comparable to full OPF solvers. These findings demonstrate the promise of homotopy-based heuristics for scalable, constraint-aware L2O in power system optimization.

cs.LG↗

arXiv2025

Cyber-Resilient System Identification for Power Grid through Bayesian Integration

Power grids increasingly need real-time situational awareness under the ever-evolving cyberthreat landscape. Advances in snapshot-based system identification approaches have enabled accurately estimating states and topology from a snapshot of measurement data, under random bad data and topology errors. However, modern interactive, targeted false data can stay undetectable to these methods, and significantly compromise estimation accuracy. This work advances system identification that combines snapshot-based method with time-series model via Bayesian Integration, to advance cyber resiliency against both random and targeted false data. Using a distance-based time-series model, this work can leverage historical data of different distributions induced by changes in grid topology and other settings. The normal system behavior captured from historical data is integrated into system identification through a Bayesian treatment, to make solutions robust to targeted false data. We experiment on mixed random anomalies (bad data, topology error) and targeted false data injection attack (FDIA) to demonstrate our method's 1) cyber resilience: achieving over 70% reduction in estimation error under FDIA; 2) anomalous data identification: being able to alarm and locate anomalous data; 3) almost linear scalability: achieving comparable speed with the snapshot-based baseline, both taking <1min per time tick on the large 2,383-bus system using a laptop CPU.

eess.SY↗

arXiv2025

Adaptive Federated Learning via Dynamical System Model

Hyperparameter selection is critical for stable and efficient convergence of heterogeneous federated learning, where clients differ in computational capabilities, and data distributions are non-IID. Tuning hyperparameters is a manual and computationally expensive process as the hyperparameter space grows combinatorially with the number of clients. To address this, we introduce an end-to-end adaptive federated learning method in which both clients and central agents adaptively select their local learning rates and momentum parameters. Our approach models federated learning as a dynamical system, allowing us to draw on principles from numerical simulation and physical design. Through this perspective, selecting momentum parameters equates to critically damping the system for fast, stable convergence, while learning rates for clients and central servers are adaptively selected to satisfy accuracy properties from numerical simulation. The result is an adaptive, momentum-based federated learning algorithm in which the learning rates for clients and servers are dynamically adjusted and controlled by a single, global hyperparameter. By designing a fully integrated solution for both adaptive client updates and central agent aggregation, our method is capable of handling key challenges of heterogeneous federated learning, including objective inconsistency and client drift. Importantly, our approach achieves fast convergence while being insensitive to the choice of the global hyperparameter, making it well-suited for rapid prototyping and scalable deployment. Compared to state-of-the-art adaptive methods, our framework is shown to deliver superior convergence for heterogeneous federated learning while eliminating the need for hyperparameter tuning both client and server updates.

cs.LG↗

arXiv2025

Integrating Forecasting Models Within Steady-State Analysis and Optimization

Extreme weather variations and the increasing unpredictability of load behavior make it difficult to determine power grid dispatches that are robust to uncertainties. While machine learning (ML) methods have improved the ability to model uncertainty caused by loads and renewables, accurately integrating these forecasts and their sensitivities into steady-state analyses and decision-making strategies remains an open challenge. Toward this goal, we present a generalized methodology that seamlessly embeds ML-based forecasting engines within physics-based power flow and grid optimization tools. By coupling physics-based grid modeling with black-box ML methods, we accurately capture the behavior and sensitivity of loads and weather events by directly integrating the inputs and outputs of trained ML forecasting models into the numerical methods of power flow and grid optimization. Without fitting surrogate load models, our approach obtains the sensitivities directly from data to accurately predict the response of forecasted devices to changes in the grid. Our approach combines the sensitivities of forecasted devices attained via backpropagation and the sensitivities of physics-defined grid devices. We demonstrate the efficacy of our method by showcasing improvements in sensitivity calculations and leveraging them to design a robust power dispatch that improves grid reliability under stochastic weather events. Our approach enables the computation of system sensitivities to exogenous factors which supports broader analyses that improve grid reliability in the presence of load variability and extreme weather conditions.

eess.SY↗

arXiv2024

A Hybrid Simulation of DNN-based Gray Box Models

Simulation is vital for engineering disciplines, as it enables the prediction and design of physical systems. However, the computational challenges inherent to large-scale simulations often arise from complex device models featuring high degrees of nonlinearities or hidden physical behaviors not captured by first principles. Gray-box models combine deep neural networks (DNNs) with physics-based models to address the computational challenges in modeling physical systems. A well-crafted gray box model capitalizes on the interpretability and accuracy of a physical model while incorporating DNNs to capture hidden physical behaviors and mitigate computational load associated with highly nonlinear components. Previously, gray box models have been constructed by defining an explicit combination of physics-based and DNN models to represent the behavior of sub-systems; however this cannot represent the coupled interactions within physical systems. We explore an implicit gray box model, where both DNNs and physical equations share a common set of state-variables. While this approach captures coupled interactions at the boundary of DNN and physics-based models, simulating the implicit gray box model remains an open-ended problem. In this work, we introduce a new hybrid simulation that integrates DNNs into the numerical solvers of simulation engines to fully simulate implicit gray box models of large physical systems. This is accomplished by backpropagating through the DNN to calculate Jacobian values during each iteration of the numerical method. The hybrid simulation improves the accuracy and runtime compared to physics-based simulation and enables reusable DNN models with lower data requirements. We explore the advantages of this approach as compared to physics-based, black box, and other gray box methods for simulating the steady-state and transient behavior of power systems.

eess.SY↗

arXiv2024

FedECADO: A Dynamical System Model of Federated Learning

Federated learning harnesses the power of distributed optimization to train a unified machine learning model across separate clients. However, heterogeneous data distributions and computational workloads can lead to inconsistent updates and limit model performance. This work tackles these challenges by proposing FedECADO, a new algorithm inspired by a dynamical system representation of the federated learning process. FedECADO addresses non-IID data distribution through an aggregate sensitivity model that reflects the amount of data processed by each client. To tackle heterogeneous computing, we design a multi-rate integration method with adaptive step-size selections that synchronizes active client updates in continuous time. Compared to prominent techniques, including FedProx and FedNova, FedECADO achieves higher classification accuracies in numerous heterogeneous scenarios.

cs.LG↗

arXiv2024

Second-Order Optimization via Quiescence

Second-order optimization methods exhibit fast convergence to critical points, however, in nonconvex optimization, these methods often require restrictive step-sizes to ensure a monotonically decreasing objective function. In the presence of highly nonlinear objective functions with large Lipschitz constants, increasingly small step-sizes become a bottleneck to fast convergence. We propose a second-order optimization method that utilizes a dynamic system model to represent the trajectory of optimization variables as an ODE. We then follow the quasi-steady state trajectory by forcing variables with the fastest rise time into a state known as quiescence. This optimization via quiescence allows us to adaptively select large step-sizes that sequentially follow each optimization variable to a quasi-steady state until all state variables reach the actual steady state, coinciding with the optimum. The result is a second-order method that utilizes large step-sizes and does not require a monotonically decreasing objective function to reach a critical point. Experimentally, we demonstrate the fast convergence of this approach for optimizing nonconvex problems in power systems and compare them to existing state-of-the-art second-order methods, including damped Newton-Raphson, BFGS, and SR1.

math.OC↗

arXiv2024

A Convex Method of Generalized State Estimation using Circuit-theoretic Node-breaker Model

An accurate and up-to-date topology is critical for situational awareness of a power grid; however, wrong switch statuses due to physical damage, communication error, or cyber-attack, can often result in topology errors. To maintain situation awareness under the possible topology errors and bad data, this paper develops ckt-GSE, a circuit-theoretic generalized state estimation method using node-breaker (NB) model. Ckt- GSE is a convex and scalable model that jointly estimates AC state variables and network topology, with robustness against different data errors. The method first constructs an equivalent circuit representation of the AC power grid by developing and aggregating linear circuit models of SCADA meters, phasor measurement units(PMUs), and switching devices. Then based on this circuit, ckt-GSE defines a constrained optimization problem using weighted least absolute value (WLAV) objective to form a robust estimator. The problem is a Linear Programming (LP) problem whose solution includes accurate AC states and a sparse vector of noise terms to identify topology errors and bad data.This paper is the first to explore a circuit-theoretic approach for an AC-network constrained GSE algorithm that is: 1) applicable to the real-world data setting, 2) convex without relaxation, scalable with our circuit-based solver; and 3) robust with the ability to identify and reject different data errors

eess.SY↗

arXiv2024

Contingency Analyses with Warm Starter using Probabilistic Graphical Model

Cyberthreats are an increasingly common risk to the power grid and can thwart secure grid operations. We propose to extend contingency analysis to include cyberthreat evaluations. However, unlike the traditional N-1 or N-2 contingencies, cyberthreats (e.g., MadIoT) require simulating hard-to-solve N-k (with k >> 2) contingencies in a practical amount of time. Purely physics-based power flow solvers, while being accurate, are slow and may not solve N-k contingencies in a timely manner, whereas the emerging data-driven alternatives are fast but not sufficiently generalizable, interpretable, and scalable. To address these challenges, we propose a novel conditional Gaussian Random Field-based data-driven method that performs fast and accurate evaluation of cyberthreats. It achieves speedup of contingency analysis by warm-starting simulations, i.e., improving starting points, for the physical solvers. To improve the physical interpretability and generalizability, the proposed method incorporates domain knowledge by considering the graphical nature of the grid topology. To improve scalability, the method applies physics-informed regularization that reduces model complexity. Experiments validate that simulating MadIoT-induced attacks with our warm starter becomes approximately 5x faster on a realistic 2000-bus system.

cs.CR↗

arXiv2023

Towards Hyperparameter-Agnostic DNN Training via Dynamical System Insights

We present a stochastic first-order optimization method specialized for deep neural networks (DNNs), ECCO-DNN. This method models the optimization variable trajectory as a dynamical system and develops a discretization algorithm that adaptively selects step sizes based on the trajectory's shape. This provides two key insights: designing the dynamical system for fast continuous-time convergence and developing a time-stepping algorithm to adaptively select step sizes based on principles of numerical integration and neural network structure. The result is an optimizer with performance that is insensitive to hyperparameter variations and that achieves comparable performance to state-of-the-art optimizers including ADAM, SGD, RMSProp, and AdaGrad. We demonstrate this in training DNN models and datasets, including CIFAR-10 and CIFAR-100 using ECCO-DNN and find that ECCO-DNN's single hyperparameter can be changed by three orders of magnitude without affecting the trained models' accuracies. ECCO-DNN's insensitivity reduces the data and computation needed for hyperparameter tuning, making it advantageous for rapid prototyping and for applications with new datasets. To validate the efficacy of our proposed optimizer, we train an LSTM architecture on a household power consumption dataset with ECCO-DNN and achieve an optimal mean-square-error without tuning hyperparameters.

cs.LG↗

arXiv2023

Power Grid Behavioral Patterns and Risks of Generalization in Applied Machine Learning

Recent years have seen a rich literature of data-driven approaches designed for power grid applications. However, insufficient consideration of domain knowledge can impose a high risk to the practicality of the methods. Specifically, ignoring the grid-specific spatiotemporal patterns (in load, generation, and topology, etc.) can lead to outputting infeasible, unrealizable, or completely meaningless predictions on new inputs. To address this concern, this paper investigates real-world operational data to provide insights into power grid behavioral patterns, including the time-varying topology, load, and generation, as well as the spatial differences (in peak hours, diverse styles) between individual loads and generations. Then based on these observations, we evaluate the generalization risks in some existing ML works causedby ignoring these grid-specific patterns in model design and training.

eess.SY↗

arXiv2023

An Equivalent Circuit Approach to Distributed Optimization

Distributed optimization is an essential paradigm to solve large-scale optimization problems in modern applications where big-data and high-dimensionality creates a computational bottleneck. Distributed optimization algorithms that exhibit fast convergence allow us to fully utilize computing resources and effectively scale to larger optimization problems in a myriad of areas ranging from machine learning to power systems. In this work, we introduce a new centralized distributed optimization algorithm (ECADO) inspired by an equivalent circuit model of the distributed problem. The equivalent circuit (EC) model provides a physical analogy to derive new insights to develop a fast-convergent algorithm. The main contributions of this approach are: 1) a weighting scheme based on a circuit-inspired aggregate sensitivity analysis, and 2) an adaptive step-sizing derived from a stable, Backward-Euler numerical integration. We demonstrate that ECADO exhibits faster convergence compared to state-of-the art distributed optimization methods and provably converges for nonconvex problems. We leverage the ECADO features to solve convex and nonconvex optimization problems with large datasets such as: distributing data for logistic regression, training a deep neural network model for classification, and solving a high-dimensional problem security-constrained optimal power flow problem. Compared to state-of-the-art centralized methods, including ADMM, centralized gradient descent, and DANE, this new ECADO approach is shown to converge in fewer iterations.

eess.SY↗

arXiv2023

An Equivalent Circuit Workflow for Unconstrained Optimization

We introduce a new workflow for unconstrained optimization whereby objective functions are mapped onto a physical domain to more easily design algorithms that are robust to hyperparameters and achieve fast convergence rates. Specifically, we represent optimization problems as an equivalent circuit that are then solved solely as nonlinear circuits using robust solution methods. The equivalent circuit models the trajectory of component-wise scaled gradient flow problem as the transient response of the circuit for which the steady-state coincides with a critical point of the objective function. The equivalent circuit model leverages circuit domain knowledge to methodically design new optimization algorithms that would likely not be developed without a physical model. We incorporate circuit knowledge into optimization methods by 1) enhancing the underlying circuit model for fast numerical analysis, 2) controlling the optimization trajectory by designing the nonlinear circuit components, and 3) solving for step sizes using well-known methods from the circuit simulation. We first establish the necessary conditions that the controls must fulfill for convergence. We show that existing descent algorithms can be re-derived as special cases of this approach and derive new optimization algorithms that are developed with insights from a circuit-based model. The new algorithms can be designed to be robust to hyperparameters, achieve convergence rates comparable or faster than state of the art methods, and are applicable to optimizing a variety of both convex and nonconvex problems.

math.OC↗

arXiv2023

ECCO: Equivalent Circuit Controlled Optimization

We propose an adaptive optimization algorithm for solving unconstrained scaled gradient flow problems that achieves fast convergence by controlling the optimization trajectory shape and the discretization step sizes. Under a broad class of scaling functions, we establish convergence of the proposed approach to critical points of smooth objective functions, while demonstrating its flexibility and robustness with respect to hyperparameter tuning. First, we prove convergence of component-wise scaled gradient flow to a critical point under regularity conditions. We show that this controlled gradient flow dynamics is equivalent to the transient response of an electrical circuit, allowing for circuit theory concepts to solve the problem. Based on this equivalence, we develop two optimization trajectory control schemes based on minimizing the charge stored in the circuit: a second order method that uses the true Hessian and an alternate first order method that approximates the optimization trajectory with only gradient information. While the control schemes are derived from circuit concepts, no circuit knowledge is needed to implement the algorithms. To find the value of the critical point, we propose a time step search routine for Forward Euler discretization that controls the local truncation error, a method adapted from circuit simulation ideas. In simulation we find that the trajectory control outperforms uncontrolled gradient flow, and the error-aware discretization out-performs line search with the Armijo condition. Our algorithms are evaluated on convex and non-convex test functions, including neural networks, with convergence speeds comparable to or exceeding Adam.

eess.SY↗

arXiv2023

Actionable Three-Phase Infeasibility Optimization with Varying Slack Sources

Modern distribution grids that include numerous distributed energy resources (DERs) and battery electric vehicles (BEVs) will require simulation and optimization methods that can capture behavior under infeasible operating scenarios to assess reliability. A three-phase infeasibility analysis (TPIA) localizes and identifies power deficient areas in distribution feeders via a non-convex optimization that injects and subsequently minimizes slack sources, subject to AC network constraints. In this paper, we extend the TPIA framework by introducing operational bounds to ensure realistic, actionable solutions. We incorporate current, reactive power, and susceptance slack sources to model real-world assets, and discuss their potential use cases. We show that the voltage-bounded TPIA formulations provide actionable solutions for realistic networks of up to 5360 nodes where power flow simulations either fail or return low-voltage solutions. We demonstrate reactive power compensation using the slack susceptance formulation on an infeasible test case.

math.OC↗

arXiv2022

A Risk-Managed Steady-State Analysis to Assess the Impact of Power Grid Uncertainties

Electricity systems are experiencing increased effects of randomness and variability due to emerging stochastic assets. The increased effects introduce new uncertainties into power systems that can impact system operability and reliability. Existing steady-state methods for assessing system-level operability and reliability are primarily deterministic, therefore, ill-suited to capture randomness and variability. This work introduces a probabilistic steady-state analysis inspired by statistical worst-case circuit analysis to evaluate the risk of operational violations due to stochastic resources. Compared to parallelized Monte Carlo analyses (MCS), we have seen up to 24x improvement in runtime speed using our approach without significant loss of probabilistic accuracy for a Texas7k low-wind day test system.

eess.SY↗

arXiv2022

Towards Practical Physics-Informed ML Design and Evaluation for Power Grid

When applied to a real-world safety critical system like the power grid, general machine learning methods suffer from expensive training, non-physical solutions, and limited interpretability. To address these challenges for power grids, many recent works have explored the inclusion of grid physics (i.e., domain expertise) into their method design, primarily through including system constraints and technical limits, reducing search space and defining meaningful features in latent space. Yet, there is no general methodology to evaluate the practicality of these approaches in power grid tasks, and limitations exist regarding scalability, generalization, interpretability, etc. This work formalizes a new concept of physical interpretability which assesses how a ML model makes predictions in a physically meaningful way and introduces an evaluation methodology that identifies a set of attributes that a practical method should satisfy. Inspired by the evaluation attributes, the paper further develops a novel contingency analysis warm starter for MadIoT cyberattack, based on a conditional Gaussian random field. This method serves as an instance of an ML model that can incorporate diverse domain knowledge and improve on these identified attributes. Experiments validate that the warm starter significantly boosts the efficiency of contingency analysis for MadIoT attack even with shallow NN architectures.

cs.LG↗

arXiv2022

Three-Phase Infeasibility Analysis for Distribution Grid Studies

With the increase of distributed energy resources in the distribution grid, planning to ensure sufficient infrastructure and resources becomes critical. Planning at the distribution level is limited by the complexities of optimizing unbalanced systems. In this paper we develop a three-phase infeasibility analysis that identifies weak locations in a distribution network. This optimization is formulated by adding slack current sources at nodes in the system and minimizing their norm subject to distribution power flow constraints. Through this analysis we solve instances of power flow that would otherwise be infeasible and diverge. Under conditions when power flow is feasible, our approach is equivalent to standard three-phase power flow; however, for cases where power flow fails, the nonzero slack injection currents compensate for missing power to make the grid feasible. Since an uncountable number of injected currents can provide feasibility, we further explore the optimization formulation that best fits the solution objective through use of both a least squares and an L1 norm objective. Our L1 norm formulation localizes power deficient locations through its inherent sparsity. We show the efficacy of this approach on realistic unbalanced testcases up to 8500 nodes and for a scenario with a high penetration of electric vehicles.

math.OC↗