arXiv subjects

Michael Chertkov

Publications and source records attributed to Michael Chertkov.

At least 37 records · Page 2Linked to original sources

arXiv2024

Mixing Artificial and Natural Intelligence: From Statistical Mechanics to AI and Back to Turbulence

The paper reflects on the future role of AI in scientific research, with a special focus on turbulence studies, and examines the evolution of AI, particularly through Diffusion Models rooted in non-equilibrium statistical mechanics. It underscores the significant impact of AI on advancing reduced, Lagrangian models of turbulence through innovative use of deep neural networks. Additionally, the paper reviews various other AI applications in turbulence research and outlines potential challenges and opportunities in the concurrent advancement of AI and statistical hydrodynamics. This discussion sets the stage for a future where AI and turbulence research are intricately intertwined, leading to more profound insights and advancements in both fields.

cs.LG↗

arXiv2024

Space-Time Diffusion Bridge

In this study, we introduce a novel method for generating new synthetic samples that are independent and identically distributed (i.i.d.) from high-dimensional real-valued probability distributions, as defined implicitly by a set of Ground Truth (GT) samples. Central to our method is the integration of space-time mixing strategies that extend across temporal and spatial dimensions. Our methodology is underpinned by three interrelated stochastic processes designed to enable optimal transport from an easily tractable initial probability distribution to the target distribution represented by the GT samples: (a) linear processes incorporating space-time mixing that yield Gaussian conditional probability densities, (b) their diffusion bridge analogs that are conditioned to the initial and final state vectors, and (c) nonlinear stochastic processes refined through score-matching techniques. The crux of our training regime involves fine-tuning the nonlinear model, and potentially the linear models -- to align closely with the GT data. We validate the efficacy of our space-time diffusion approach with numerical experiments, laying the groundwork for more extensive future theory and experiments to fully authenticate the method, particularly providing a more efficient (possibly simulation-free) inference.

stat.ML↗

arXiv2024

Differentiable Simulator For Dynamic & Stochastic Optimal Gas & Power Flows

In many power systems, particularly those isolated from larger intercontinental grids, operational dependence on natural gas becomes pivotal, especially during fluctuations or unavailability of renewables coupled with uncertain consumption patterns. Efficient orchestration and inventive strategies are imperative for the smooth functioning of these standalone gas-grid systems. This paper delves into the challenge of synchronized dynamic and stochastic optimization for independent transmission-level gas-grid systems. Our approach's novelty lies in amalgamating the staggered-grid method for the direct assimilation of gas-flow PDEs with an automated sensitivity analysis facilitated by SciML/Julia, further enhanced by an intuitive linkage between gas and power grids via nodal flows. We initiate with a single pipe to establish a versatile and expandable methodology, later showcasing its effectiveness with increasingly intricate examples.

math.OC↗

arXiv2024

Unraveling the Geography of Infection Spread: Harnessing Super-Agents for Predictive Modeling

Our study presents an intermediate-level modeling approach that bridges the gap between complex Agent-Based Models (ABMs) and traditional compartmental models for infectious diseases. We introduce "super-agents" to simulate infection spread in cities, reducing computational complexity while retaining individual-level interactions. This approach leverages real-world mobility data and strategic geospatial tessellations for efficiency. Voronoi Diagram tessellations, based on specific street network locations, outperform standard Census Block Group tessellations, and a hybrid approach balances accuracy and efficiency. Benchmarking against existing ABMs highlights key optimizations. This research improves disease modeling in urban areas, aiding public health strategies in scenarios requiring geographic specificity and high computational efficiency.

cs.CY↗

arXiv2023

Deciphering the Dance of the Winds and Waves: Unraveling Anomalous Dynamics in Floating Offshore Wind Turbines

We study the Floating Offshore Wind Turbine (FOWT) dynamic response to high wind velocity scenarios utilizing an extensive Markov Chain Monte Carlo simulation involving 10,000 trials of a reduced model from \cite{betti_development_2014} with a blade-pitch PID controller. The research emphasizes analysis of extreme events in surge, pitch and heave of FOWT, identifying and categorizing them based on their statistics, correlations and causal relations to wind and waves. A significant discovery is the differentiation of anomalies into short-correlated and long-correlated types, with the latter primarily influenced by wind conditions. For example, one of our findings is that while specific wave conditions may amplify anomalies, wind remains the predominant factor in long-term anomalous pitch behaviors. We anticipate that further development of this analysis of the operation's critical extreme events will be pivotal for advancing control strategies and design considerations in FOWTs, accommodating the turbulent environment they encounter.

math.DS↗

arXiv2023

Universality and Control of Fat Tails

Motivated by applications in hydrodynamics and networks of thermostatically-control loads in buildings we study control of linear dynamical systems driven by additive and also multiplicative noise of a general position. Utilizing mathematical theory of stochastic multiplicative processes we present a universal way to estimate fat, algebraic tails of the state vector probability distributions. This prompts us to introduce and analyze mean-q-power stability criterion, generalizing the mean-square stability criterion, and then juxtapose it to other tools in control.

eess.SY↗

arXiv2023

Physics informed machine learning with Smoothed Particle Hydrodynamics: Hierarchy of reduced Lagrangian models of turbulence

Building efficient, accurate and generalizable reduced order models of developed turbulence remains a major challenge. This manuscript approaches this problem by developing a hierarchy of parameterized reduced Lagrangian models for turbulent flows, and investigates the effects of enforcing physical structure through Smoothed Particle Hydrodynamics (SPH) versus relying on neural networks (NN)s as universal function approximators. Starting from Neural Network (NN) parameterizations of a Lagrangian acceleration operator, this hierarchy of models gradually incorporates a weakly compressible and parameterized SPH framework, which enforces physical symmetries, such as Galilean, rotational and translational invariances. Within this hierarchy, two new parameterized smoothing kernels are developed in order to increase the flexibility of the learn-able SPH simulators. For each model we experiment with different loss functions which are minimized using gradient based optimization, where efficient computations of gradients are obtained by using Automatic Differentiation (AD) and Sensitivity Analysis (SA). Each model within the hierarchy is trained on two data sets associated with weekly compressible Homogeneous Isotropic Turbulence (HIT): (1) a validation set using weakly compressible SPH; and (2) a high fidelity set from Direct Numerical Simulations (DNS). Numerical evidence shows that encoding more SPH structure improves generalizability to different turbulent Mach numbers and time shifts, and that including the novel parameterized smoothing kernels improves the accuracy of SPH at the resolved scales.

physics.flu-dyn↗

arXiv2023

Data-Driven Mori-Zwanzig: Reduced Order Modeling of Sparse Sensors Measurements for Boundary Layer Transition

Understanding, predicting and controlling laminar-turbulent boundary-layer transition is crucial for the next generation aircraft design. However, in real flight experiments, or wind tunnel tests, often only sparse sensor measurements can be collected at fixed locations. Thus, in developing reduced models for predicting and controlling the flow at the sensor locations, the main challenge is in accounting for how the surrounding field of unobserved variables interacts with the observed variables at the fixed sensor locations. This makes the Mori-Zwanzig (MZ) formalism a natural choice, as it results in the Generalized Langevin Equations which provides a framework for constructing non-Markovian reduced-order models that includes the effects the unresolved variables have on the resolved variables. These effects are captured in the so called memory kernel and orthogonal dynamics. In this work, we explore the data-driven MZ formulations to two boundary layer flows obtained from DNS data; a low speed incompressible flow; and a high speed compressible flow over a flared cone at Mach 6. An array of "sensors" are placed near the surface of the solid boundary, and the MZ operators are learned and the predictions are compared to the Extended Dynamic Mode Decomposition (EDMD), both using delay embedded coordinates. Further comparisons are made with Long Short-Term Memory (LSTM) and a regression based projection framework using neural networks for the MZ operators. First we compare the effects of including delay embedded coordinates with EDMD and Mori based MZ and provide evidence that using both memory and delay embedded coordinates minimizes generalization errors on the relevant time scales. Next, we provide numerical evidence that the data-driven regression based projection MZ model performs best with respect to the prediction accuracy (minimum generalization error) on the relevant time scales.

physics.flu-dyn↗

arXiv2023

Control of Line Pack in Natural Gas System: Balancing Limited Resources under Uncertainty

We build and experiment with a realistic but reduced natural gas model of Israel. The system is unusual because (a) it is controlled from a limited number of points which are at, or close to, the gas extraction sites offshore of Israel's Mediterranean coast; (b) control specifies average flux at inlet, not pressure; (c) there are no inland compressors to regulate pressure; (d) power system is the main consumer of gas (70\% of Israel's power is generated at gas-fired power plants distributed across the country). Nature of the system suggests that a special attention should be given to understanding dynamics driven by fast transients in gas consumption meeting intra-day variations in the electricity demand, and accounting for increasing role of uncertain renewable generation (mainly solar). Based on all of the above we pose and resolve a sequence of dynamic and control challenges, such as: How to time ramping up- and down- injection of gas to guarantee a healthy intra-day line-pack which meets both pressure constraints and gas-extraction patterns? We report simulation results and utilize monotonicity properties of the natural gas flows which render robustness of our conclusions to the uncertainties of the edge withdrawals of gas.

math.DS↗

arXiv2023

A Physics-Informed Machine Learning for Electricity Markets: A NYISO Case Study

This paper addresses the challenge of efficiently solving the optimal power flow problem in real-time electricity markets. The proposed solution, named Physics-Informed Market-Aware Active Set learning OPF (PIMA-AS-OPF), leverages physical constraints and market properties to ensure physical and economic feasibility of market-clearing outcomes. Specifically, PIMA-AS-OPF employs the active set learning technique and expands its capabilities to account for curtailment in load or renewable power generation, which is a common challenge in real-world power systems. The core of PIMA-AS-OPF is a fully-connected neural network that takes the net load and the system topology as input. The outputs of this neural network include active constraints such as saturated generators and transmission lines, as well as non-zero load shedding and wind curtailments. These outputs allow for reducing the original market-clearing optimization to a system of linear equations, which can be solved efficiently and yield both the dispatch decisions and the locational marginal prices (LMPs). The dispatch decisions and LMPs are then tested for their feasibility with respect to the requirements for efficient market-clearing results. The accuracy and scalability of the proposed method is tested on a realistic 1814-bus NYISO system with current and future renewable energy penetration levels.

cs.LG↗

arXiv2022

Statistical Mechanics of Thermostatically Controlled Multi-Zone Buildings

We study the collective phenomena and constraints associated with the aggregation of individual cooling units from a statistical mechanics perspective. These units are modelled as Thermostatically Controlled Loads (TCLs) and represent zones in a large commercial or residential building. Their energy input is centralized and controlled by a collective unit -- the Air Handling Unit (AHU) -- delivering cool air to all TCLs, thereby coupling them together. Aiming to identify representative qualitative features of the AHU-to-TCL coupling, we build a realistic but also sufficiently simple model and analyze it in two distinct regimes: the Constant Supply Temperature (CST) and the Constant Power Input (CPI) regimes. In both cases, we center our analysis on the relaxation dynamics of individual TCL temperatures to a statistically steady state. We observe that while the dynamics are relatively fast in the CST regime, resulting in all TCLs evolving around the control setpoint, the CPI regime reveals emergence of a \emph{bi-modal probability distribution and two, possibly strongly separated, time scales}. We observe that the two modes in the CPI regime are associated with all TCLs being in the same low and high-temperature states, respectively, with occasional (and therefore possibly rare) collective transition between the modes akin in the Kramer's phenomenon of statistical physics. To the best of our knowledge, this phenomenon was overlooked in the context of the multi-zone energy building engineering, even thought it has direct implications on the operations of centralized cooling systems in buildings. It teaches us that a balance needs to be struck between occupational comfort -- related to variations in the individual temperatures -- and power output predictability -- the main focus of the DR schemes.

physics.soc-ph↗

arXiv2022

Lagrangian Large Eddy Simulations via Physics Informed Machine Learning

High Reynolds Homogeneous Isotropic Turbulence is fully described within the Navier-Stokes (NS) equations, which are notoriously difficult to solve numerically. Engineers, interested primarily in describing turbulence at a reduced range of resolved scales, have designed heuristics, known as Large Eddy Simulation (LES). LES is described in terms of the temporally evolving Eulerian velocity field defined over a spatial grid with the mean-spacing correspondent to the resolved scale. This classic Eulerian LES depends on assumptions about effects of sub-grid scales on the resolved scales. Here, we take an alternative approach and design novel LES heuristics stated in terms of Lagrangian particles moving with the flow. Our Lagrangian LES, thus L-LES, is described by equations generalizing the weakly compressible Smoothed Particle Hydrodynamics formulation with extended parametric and functional freedom, which is then resolved via Machine Learning training on Lagrangian data from Direct Numerical Simulations of the NS equations. The L-LES model includes physics-informed parameterization and functional form, by combining physics-based parameters and physics-inspired Neural Networks to describe the evolution of turbulence within the resolved range of scales. The sub-grid scale contributions are modeled separately with physical constraints to account for the effects from un-resolved scales. We build the resulting model under the Differentiable Programming framework to facilitate efficient training. We experiment with loss functions of different types, including physics-informed ones accounting for statistics of Lagrangian particles. We show that our Lagrangian LES model is capable of reproducing Eulerian and unique Lagrangian turbulence structures and statistics over a range of turbulent Mach numbers.

physics.flu-dyn↗

arXiv2022

Towards Model Reduction for Power System Transients with Physics-Informed PDE

This manuscript reports the first step towards building a robust and efficient model reduction methodology to capture transient dynamics in a transmission level electric power system. Such dynamics is normally modeled on seconds-to-tens-of-seconds time scales by the so-called swing equations, which are ordinary differential equations defined on a spatially discrete model of the power grid. Following Seymlyen (1974) and Thorpe, Seyler, and Phadke (1999), we suggest to map the swing equations onto a linear, inhomogeneous Partial Differential Equation (PDE) of parabolic type in two space and one time dimensions with time-independent coefficients and properly defined boundary conditions. We illustrate our method on the synchronous transmission grid of continental Europe. We show that, when properly coarse-grained, i.e., with the PDE coefficients and source terms extracted from a spatial convolution procedure of the respective discrete coefficients in the swing equations, the resulting PDE reproduces faithfully and efficiently the original swing dynamics. We finally discuss future extensions of this work, where the presented PDE-based modeling will initialize a physics-informed machine learning approach for real-time modeling, $n-1$ feasibility assessment and transient stability analysis of power systems.

eess.SY↗

arXiv2022

Machine Learning for Electricity Market Clearing

This paper seeks to design a machine learning twin of the optimal power flow (OPF) optimization, which is used in market-clearing procedures by wholesale electricity markets. The motivation for the proposed approach stems from the need to obtain the digital twin, which is much faster than the original, while also being sufficiently accurate and producing consistent generation dispatches and locational marginal prices (LMPs), which are primal and dual solutions of the OPF optimization, respectively. Availability of market-clearing tools based on this approach will enable computationally tractable evaluation of multiple dispatch scenarios under a given unit commitment. Rather than direct solution of OPF, the Karush-Kuhn-Tucker (KKT) conditions for the OPF problem in question may be written, and in parallel the LMPs of generators and loads may be expressed in terms of the OPF Lagrangian multipliers. Also, taking advantage of the practical fact that many of the Lagrangian multipliers associated with lines will be zero (thermal limits are not binding), we build and train an ML scheme which maps flexible resources (loads and renewables) to the binding lines, and supplement it with an efficient power-grid aware linear map to optimal dispatch and LMPs. The scheme is validated and illustrated on IEEE models. We also report a trade of analysis between quality of the reconstruction and number of samples needed to train the model.

eess.SY↗

arXiv2022

Prediction and Prevention of Pandemics via Graphical Model Inference and Convex Programming

Hard-to-predict bursts of COVID-19 pandemic revealed significance of statistical modeling which would resolve spatio-temporal correlations over geographical areas, for example spread of the infection over a city with census tract granularity. In this manuscript, we provide algorithmic answers to the following two inter-related public health challenges. (1) Inference Challenge: assuming that there are $N$ census blocks (nodes) in the city, and given an initial infection at any set of nodes, what is the probability for a subset of census blocks to become infected by the time the spread of the infection burst is stabilized? (2) Prevention Challenge: What is the minimal control action one can take to minimize the infected part of the stabilized state footprint? To answer the challenges, we build a Graphical Model of pandemic of the attractive Ising (pair-wise, binary) type, where each node represents a census track and each edge factor represents the strength of the pairwise interaction between a pair of nodes. We show that almost all attractive Ising Models on dense graphs result in either of the two modes for the most probable state: either all nodes which were not infected initially became infected, or all the initially uninfected nodes remain uninfected. This bi-modal solution of the Inference Challenge allows us to re-state the Prevention Challenge as the following tractable convex programming: for the bare Ising Model with pair-wise and bias factors representing the system without prevention measures, such that the MAP state is fully infected for at least one of the initial infection patterns, find the closest, in $l_1$ norm, set of factors resulting in all the MAP states of the Ising model, with the optimal prevention measures applied, to become safe.

cs.SI↗

arXiv2021

Physics-Informed Machine Learning of the Lagrangian Dynamics of Velocity Gradient Tensor

Reduced models describing the Lagrangian dynamics of the Velocity Gradient Tensor (VGT) in Homogeneous Isotropic Turbulence (HIT) are developed under the Physics-Informed Machine Learning (PIML) framework. We consider VGT at both Kolmogorov scale and coarse-grained scale within the inertial range of HIT. Building reduced models requires resolving the pressure Hessian and sub-filter contributions, which is accomplished by constructing them using the integrity bases and invariants of VGT. The developed models can be expressed using the extended Tensor Basis Neural Network (TBNN). Physical constraints, such as Galilean invariance, rotational invariance, and incompressibility condition, are thus embedded in the models explicitly. Our PIML models are trained on the Lagrangian data from a high-Reynolds number Direct Numerical Simulation (DNS). To validate the results, we perform a comprehensive out-of-sample test. We observe that the PIML model provides an improved representation for the magnitude and orientation of the small-scale pressure Hessian contributions. Statistics of the flow, as indicated by the joint PDF of second and third invariants of the VGT, show good agreement with the "ground-truth" DNS data. A number of other important features describing the structure of HIT are reproduced by the model successfully. We have also identified challenges in modeling inertial range dynamics, which indicates that a richer modeling strategy is required. This helps us identify important directions for future research, in particular towards including inertial range geometry into TBNN.

physics.flu-dyn↗

arXiv2021

Which Neural Network to Choose for Post-Fault Localization, Dynamic State Estimation and Optimal Measurement Placement in Power Systems?

We consider a power transmission system monitored with Phasor Measurement Units (PMUs) placed at significant, but not all, nodes of the system. Assuming that a sufficient number of distinct single-line faults, specifically pre-fault state and (not cleared) post-fault state, are recorded by the PMUs and are available for training, we, first, design a comprehensive sequence of Neural Networks (NNs) locating the faulty line. Performance of different NNs in the sequence, including Linear Regression, Feed-Forward NN, AlexNet, Graphical Convolutional NN, Neural Linear ODE and Neural Graph-based ODE, ordered according to the type and amount of the power flow physics involved, are compared for different levels of observability. Second, we build a sequence of advanced Power-System-Dynamics-Informed and Neural-ODE based Machine Learning schemes trained, given pre-fault state, to predict the post-fault state and also, in parallel, to estimate system parameters. Finally, third, and continuing to work with the first (fault localization) setting we design a (NN-based) algorithm which discovers optimal PMU placement.

stat.ML↗

arXiv2021

Embedding Power Flow into Machine Learning for Parameter and State Estimation

Modern state and parameter estimations in power systems consist of two stages: the outer problem of minimizing the mismatch between network observation and prediction over the network parameters, and the inner problem of predicting the system state for given values of the parameters. The standard solution of the combined problem is iterative: (a) set the parameters, e.g. to priors on the power line characteristics, (b) map input observation to prediction of the output, (c) compute the mismatch between predicted and observed output, (d) make a gradient descent step in the space of parameters to minimize the mismatch, and loop back to (a). We show how modern Machine Learning (ML), and specifically training guided by automatic differentiation, allows to resolve the iterative loop more efficiently. Moreover, we extend the scheme to the case of incomplete observations, where Phasor Measurement Units (reporting real and reactive powers, voltage and phase) are available only at the generators (PV buses), while loads (PQ buses) report (via SCADA controls) only active and reactive powers. Considering it from the implementation perspective, our methodology of resolving the parameter and state estimation problem can be viewed as embedding of the Power Flow (PF) solver into the training loop of the Machine Learning framework (PyTorch, in this study). We argue that this embedding can help to resolve high-level optimization problems in power system operations and planning.

eess.SY↗