Search

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.

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.

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.

As the pace of progress that has followed Moore's law continues to diminish, it is critical that the US support Integrated Circuit (IC or chip) education and research to maintain technological innovation. Furthermore, US economic independence, security, and future international standing rely on having on-shore IC design capabilities. New devices with disparate technologies, improved design software toolchains and methodologies, and technologies to integrate heterogeneous systems will be needed to advance IC design capabilities. This will require rethinking both how we teach design to address the new complexity and how we inspire student interest in a hardware systems career path. The main recommendation of this workshop is that accessibility is the key issue. To this end, a National Chip Design Center (NCDC) should be established to further research and education by partnering academics and industry to train our future workforce. This should not be limited to R1 universities, but should also include R2, community college, minority serving institutions (MSI), and K-12 institutions to have the broadest effect. The NCDC should support the access, development, and maintenance of open design tools, tool flows, design kits, design components, and educational materials. Open-source options should be emphasized wherever possible to maximize accessibility. The NCDC should also provide access and support for chip fabrication, packaging and testing for both research and educational purposes., Comment: This material is based upon work supported by the NSF under Grant No. 2137629

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., Comment: 25 pages, 11 figures

Data integration is considered a classic research field and a pressing need within the information science community. Ontologies play a critical role in such a process by providing well-consolidated support to link and semantically integrate datasets via interoperability. This paper approaches data integration from an application perspective, looking at techniques based on ontology matching. An ontology-based process may only be considered adequate by assuming manual matching of different sources of information. However, since the approach becomes unrealistic once the system scales up, automation of the matching process becomes a compelling need. Therefore, we have conducted experiments on actual data with the support of existing tools for automatic ontology matching from the scientific community. Even considering a relatively simple case study (i.e., the spatio-temporal alignment of global indicators), outcomes clearly show significant uncertainty resulting from errors and inaccuracies along the automated matching process. More concretely, this paper aims to test on real-world data a bottom-up knowledge-building approach, discuss the lessons learned from the experimental results of the case study, and draw conclusions about uncertainty and uncertainty management in an automated ontology matching process. While the most common evaluation metrics clearly demonstrate the unreliability of fully automated matching solutions, properly designed semi-supervised approaches seem to be mature for a more generalized application.

Beginning with the class of 2023, Pennsylvania high school students will need to demonstrate career or postsecondary preparedness to meet statewide graduation requirements and receive a high school diploma. The new graduation requirements were enacted in 2018 by Pennsylvania's Act 158. They are intended to codify high standards for all students and improve student achievement across Pennsylvania, while also taking into account student strengths, interests, and career goals. As profiled in PERC's recent related brief, Act 158 outlines five pathways to demonstrating career or postsecondary preparedness, two of which--the Keystone pathways-- require demonstrating proficiency on Pennsylvania's end-of-course subject exams for Literature, Algebra, and Biology. The remaining three pathways to graduation--the alternative pathways--require that a student (1) either earn a "Proficient" Keystone exam score or acceptable course grades in each Keystone subject area; and (2) demonstrate college or career readiness through one or multiple alternative metrics, such as through an industry-based competency certification, successful completion of a service-learning project, or an internship or cooperative education program, among other metrics. This report examines historical performance on Keystone exams to explore the potential impact of the policy on students in the School District of Philadelphia's high schools. While data to understand the impact on graduation outcomes through each of the five pathways are not yet available, existing data on Keystone proficiency can provide insights into the Keystone proficiency and composite pathways. Thus, in this report, pre-pandemic administrative data for students in the classes of 2018 and 2019 who took Keystone exams while enrolled in District middle or high schools was used to see how many and which students would have met or almost met Keystone-associated requirements for graduation as defined by Act 158, had the policy been in effect at that time. [For the related brief, "Changing Requirements in Pennsylvania for High School Graduation. A Policy Brief on Pennsylvania Act 158," see ED626029.]

Digital Twins (DT) facilitate monitoring and reasoning processes in cyber-physical systems. They have progressively gained popularity over the past years because of intense research activity and industrial advancements. Cognitive Twins is a novel concept, recently coined to refer to the involvement of Semantic Web technology in DTs. Recent studies address the relevance of ontologies and knowledge graphs in the context of DTs, in terms of knowledge representation, interoperability and automatic reasoning. However, there is no comprehensive analysis of how semantic technologies, and specifically ontologies, are utilized within DTs. This Systematic Literature Review (SLR) is based on the analysis of 82 research articles, that either propose or benefit from ontologies with respect to DT. The paper uses different analysis perspectives, including a structural analysis based on a reference DT architecture, and an application-specific analysis to specifically address the different domains, such as Manufacturing and Infrastructure. The review also identifies open issues and possible research directions on the usage of ontologies and knowledge graphs in DTs., Comment: The Systematic Literature Review (SLR) is submitted to Future Generation Computer System journal's Special Issue on Digital Twin for Future Networks and Emerging IoT Applications (2023)

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.

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.

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.

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., Comment: arXiv admin note: substantial text overlap with arXiv:2205.03673

In a context of constant evolution and proliferation of AI technology,Hybrid Intelligence is gaining popularity to refer a balanced coexistence between human and artificial intelligence. The term has been extensively used in the past two decades to define models of intelligence involving more than one technology. This paper aims to provide (i) a concise and focused overview of the adoption of Ontology in the broad context of Hybrid Intelligence regardless of its definition and (ii) a critical discussion on the possible role of Ontology to reduce the gap between human and artificial intelligence within hybrid intelligent systems. Beside the typical benefits provided by an effective use of ontologies, at a conceptual level, the conducted analysis has pointed out a significant contribution of Ontology to improve quality and accuracy, as well as a more specific role to enable extended interoperability, system engineering and explainable/transparent systems. Additionally, an application-oriented analysis has shown a significant role in present systems (70+% of the cases) and, potentially, in future systems. However, despite the relatively consistent number of papers on the topic, a proper holistic discussion on the establishment of the next generation of hybrid-intelligent environments with a balanced co-existence of human and artificial intelligence is fundamentally missed in literature. Last but not the least, there is currently a relatively low explicit focus on automatic reasoning and inference in hybrid intelligent systems.

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.

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., Comment: 16 pages

Teacher mobility, or teacher turnover, has long garnered attention as a critical educational equity gap. This attention is warranted as, within schools, teachers have the single greatest impact on student achievement. The unprecedented interruptions to school-based learning and the trials of navigating remote and hybrid instruction due to the COVID-19 pandemic heightened concerns about the stability of the teacher workforce and the potential of a pending teacher shortage across the U.S., state of Pennsylvania, and locally in Allegheny County. This study takes a closer look at teacher mobility in the region by examining six years of data leading up to the pandemic. Specifically, this study: (1) Identifies teacher mobility trends in Allegheny County public schools from 2014-2015 to 2019-2020; (2) Describes the destinations of mobile teachers; and (3) Identifies key characteristics of mobile teachers and the schools they exited and entered within the county to determine if potential equity gaps exist. This report concludes with implications for policy and practice including a list of suggestions for educational leaders to reduce mobility and eliminate consequential disparities for students.