Search

In this work, we introduce a planning neural operator (PNO) for predicting the value function of a motion planning problem. We recast value function approximation as learning a single operator from the cost function space to the value function space, which is defined by an Eikonal partial differential equation (PDE). Specifically, we recast computing value functions as learning a single operator across continuous function spaces which prove is equivalent to solving an Eikonal PDE. Through this reformulation, our learned PNO is able to generalize to new motion planning problems without retraining. Therefore, our PNO model, despite being trained with a finite number of samples at coarse resolution, inherits the zero-shot super-resolution property of neural operators. We demonstrate accurate value function approximation at 16 times the training resolution on the MovingAI lab's 2D city dataset and compare with state-of-the-art neural value function predictors on 3D scenes from the iGibson building dataset. Lastly, we investigate employing the value function output of PNO as a heuristic function to accelerate motion planning. We show theoretically that the PNO heuristic is $\epsilon$-consistent by introducing an inductive bias layer that guarantees our value functions satisfy the triangle inequality. With our heuristic, we achieve a 30% decrease in nodes visited while obtaining near optimal path lengths on the MovingAI lab 2D city dataset, compared to classical planning methods (A*, RRT*).

The increasing integration of renewable energy resources into power grids has led to time-varying system inertia and consequent degradation in frequency dynamics. A promising solution to alleviate performance degradation is using power electronics interfaced energy resources, such as renewable generators and battery energy storage for primary frequency control, by adjusting their power output set-points in response to frequency deviations. However, designing a frequency controller under time-varying inertia is challenging. Specifically, the stability or optimality of controllers designed for time-invariant systems can be compromised once applied to a time-varying system. We model the frequency dynamics under time-varying inertia as a nonlinear switching system, where the frequency dynamics under each mode are described by the nonlinear swing equations and different modes represent different inertia levels. We identify a key controller structure, named Neural Proportional-Integral (Neural-PI) controller, that guarantees exponential input-to-state stability for each mode. To further improve performance, we present an online event-triggered switching algorithm to select the most suitable controller from a set of Neural-PI controllers, each optimized for specific inertia levels. Simulations on the IEEE 39-bus system validate the effectiveness of the proposed online switching control method with stability guarantees and optimized performance for frequency control under time-varying inertia.

Neural operator approximations of the gain kernels in PDE backstepping has emerged as a viable method for implementing controllers in real time. With such an approach, one approximates the gain kernel, which maps the plant coefficient into the solution of a PDE, with a neural operator. It is in adaptive control that the benefit of the neural operator is realized, as the kernel PDE solution needs to be computed online, for every updated estimate of the plant coefficient. We extend the neural operator methodology from adaptive control of a hyperbolic PDE to adaptive control of a benchmark parabolic PDE (a reaction-diffusion equation with a spatially-varying and unknown reaction coefficient). We prove global stability and asymptotic regulation of the plant state for a Lyapunov design of parameter adaptation. The key technical challenge of the result is handling the 2D nature of the gain kernels and proving that the target system with two distinct sources of perturbation terms, due to the parameter estimation error and due to the neural approximation error, is Lyapunov stable. To verify our theoretical result, we present simulations achieving calculation speedups up to 45x relative to the traditional finite difference solvers for every timestep in the simulation trajectory., Comment: 13 pages, 4 figures

We propose CoNSAL (Combining Neural networks and Symbolic regression for Analytical Lyapunov function) to construct analytical Lyapunov functions for nonlinear dynamic systems. This framework contains a neural Lyapunov function and a symbolic regression component, where symbolic regression is applied to distill the neural network to precise analytical forms. Our approach utilizes symbolic regression not only as a tool for translation but also as a means to uncover counterexamples. This procedure terminates when no counterexamples are found in the analytical formulation. Compared with previous results, CoNSAL directly produces an analytical form of the Lyapunov function with improved interpretability in both the learning process and the final results. We apply CoNSAL to 2-D inverted pendulum, path following, Van Der Pol Oscillator, 3-D trig dynamics, 4-D rotating wheel pendulum, 6-D 3-bus power system, and demonstrate that our algorithm successfully finds their valid Lyapunov functions. Code examples are available at https://github.com/HaohanZou/CoNSAL., Comment: Workshop paper, accepted by Workshop on Foundations of Reinforcement Learning and Control at the 41st International Conference on Machine Learning, Vienna, Austria

This paper develops a risk-aware net demand forecasting product for virtual power plants, which helps reduce the risk of high operation costs. At the training phase, a bilevel program for parameter estimation is formulated, where the upper level optimizes over the forecast model parameter to minimize the conditional value-at-risk (a risk metric) of operation costs. The lower level solves the operation problems given the forecast. Leveraging the specific structure of the operation problem, we show that the bilevel program is equivalent to a convex program when the forecast model is linear. Numerical results show that our approach effectively reduces the risk of high costs compared to the forecasting approach developed for risk-neutral decision makers., Comment: Submitted to The 56th North American Power Symposium (NAPS 2024)

The increasing penetration of converter-based renewable generation has resulted in faster frequency dynamics, and low and variable inertia. As a result, there is a need for frequency control methods that are able to stabilize a disturbance in the power system at timescales comparable to the fast converter dynamics. This paper proposes a combined linear and neural network controller for inverter-based primary frequency control that is stable at time-varying levels of inertia. We model the time-variance in inertia via a switched affine hybrid system model. We derive stability certificates for the proposed controller via a quadratic candidate Lyapunov function. We test the proposed control on a 12-bus 3-area test network, and compare its performance with a base case linear controller, optimized linear controller, and finite-horizon Linear Quadratic Regulator (LQR). Our proposed controller achieves faster mean settling time and over 50% reduction in average control cost across $100$ inertia scenarios compared to the optimized linear controller. Unlike LQR which requires complete knowledge of the inertia trajectories and system dynamics over the entire control time horizon, our proposed controller is real-time tractable, and achieves comparable performance to LQR., Comment: This paper is to appear in IEEE Control System Letters (L-CSS)

Over the last decade, data-driven methods have surged in popularity, emerging as valuable tools for control theory. As such, neural network approximations of control feedback laws, system dynamics, and even Lyapunov functions have attracted growing attention. With the ascent of learning based control, the need for accurate, fast, and easy-to-use benchmarks has increased. In this work, we present the first learning-based environment for boundary control of PDEs. In our benchmark, we introduce three foundational PDE problems - a 1D transport PDE, a 1D reaction-diffusion PDE, and a 2D Navier-Stokes PDE - whose solvers are bundled in an user-friendly reinforcement learning gym. With this gym, we then present the first set of model-free, reinforcement learning algorithms for solving this series of benchmark problems, achieving stability, although at a higher cost compared to model-based PDE backstepping. With the set of benchmark environments and detailed examples, this work significantly lowers the barrier to entry for learning-based PDE control - a topic largely unexplored by the data-driven control community. The entire benchmark is available on Github along with detailed documentation and the presented reinforcement learning models are open sourced., Comment: 26 pages 10 figures. Accepted L4DC 2024

Large penetration of renewable energy sources (RESs) brings huge uncertainty into the electricity markets. While existing deterministic market clearing fails to accommodate the uncertainty, the recently proposed stochastic market clearing struggles to achieve desirable market properties. In this work, we propose a value-oriented forecasting approach, which tactically determines the RESs generation that enters the day-ahead market. With such a forecast, the existing deterministic market clearing framework can be maintained, and the day-ahead and real-time overall operation cost is reduced. At the training phase, the forecast model parameters are estimated to minimize expected day-ahead and real-time overall operation costs, instead of minimizing forecast errors in a statistical sense. Theoretically, we derive the exact form of the loss function for training the forecast model that aligns with such a goal. For market clearing modeled by linear programs, this loss function is a piecewise linear function. Additionally, we derive the analytical gradient of the loss function with respect to the forecast, which inspires an efficient training strategy. A numerical study shows our forecasts can bring significant benefits of the overall cost reduction to deterministic market clearing, compared to quality-oriented forecasting approach.

In this paper, we introduce a novel framework for building learning and control, focusing on ventilation and thermal management to enhance energy efficiency. We validate the performance of the proposed framework in system model learning via two case studies: a synthetic study focusing on the joint learning of temperature and CO2 fields, and an application to a real-world dataset for CO2 field learning. For building control, we demonstrate that the proposed framework can optimize the control actions and significantly reduce the energy cost while maintaining a comfort and healthy indoor environment. When compared to existing traditional methods, an optimization-based method with ODE models and reinforcement learning, our approach can significantly reduce the energy consumption while guarantees all the safety-critical air quality and control constraints. Promising future research directions involve validating and improving the proposed PDE models through accurate estimation of airflow fields within indoor environments. Additionally, incorporating uncertainty modeling into the PDE framework for HVAC control presents an opportunity to enhance the efficiency and reliability of building HVAC system management.

Observers for PDEs are themselves PDEs. Therefore, producing real time estimates with such observers is computationally burdensome. For both finite-dimensional and ODE systems, moving-horizon estimators (MHE) are operators whose output is the state estimate, while their inputs are the initial state estimate at the beginning of the horizon as well as the measured output and input signals over the moving time horizon. In this paper we introduce MHEs for PDEs which remove the need for a numerical solution of an observer PDE in real time. We accomplish this using the PDE backstepping method which, for certain classes of both hyperbolic and parabolic PDEs, produces moving-horizon state estimates explicitly. Precisely, to explicitly produce the state estimates, we employ a backstepping transformation of a hard-to-solve observer PDE into a target observer PDE, which is explicitly solvable. The MHEs we propose are not new observer designs but simply the explicit MHE realizations, over a moving horizon of arbitrary length, of the existing backstepping observers. Our PDE MHEs lack the optimality of the MHEs that arose as duals of MPC, but they are given explicitly, even for PDEs. In the paper we provide explicit formulae for MHEs for both hyperbolic and parabolic PDEs, as well as simulation results that illustrate theoretically guaranteed convergence of the MHEs., Comment: 7 pages, 1 figure, submitted to ACC 2024

Large language models (LLMs) have achieved huge success for their general knowledge and ability to solve a wide spectrum of tasks in natural language processing (NLP). Due to their impressive abilities, LLMs have shed light on potential inter-discipline applications to foster scientific discoveries of a specific domain by using artificial intelligence (AI for science, AI4S). In the meantime, utilizing NLP techniques in geoscience research and practice is wide and convoluted, contributing from knowledge extraction and document classification to question answering and knowledge discovery. In this work, we take the initial step to leverage LLM for science, through a rather straightforward approach. We try to specialize an LLM into geoscience, by further pre-training the model with a vast amount of texts in geoscience, as well as supervised fine-tuning (SFT) the resulting model with our custom collected instruction tuning dataset. These efforts result in a model GeoGalactica consisting of 30 billion parameters. To our best knowledge, it is the largest language model for the geoscience domain. More specifically, GeoGalactica is from further pre-training of Galactica. We train GeoGalactica over a geoscience-related text corpus containing 65 billion tokens, preserving as the largest geoscience-specific text corpus. Then we fine-tune the model with 1 million pairs of instruction-tuning data consisting of questions that demand professional geoscience knowledge to answer. In this technical report, we will illustrate in detail all aspects of GeoGalactica, including data collection, data cleaning, base model selection, pre-training, SFT, and evaluation. We open-source our data curation tools and the checkpoints of GeoGalactica during the first 3/4 of pre-training.

Recent shifts toward sustainable energy systems have witnessed the fast deployment of carbon-free and carbon-efficient generations across the power networks. However, the benefits of carbon reduction are not experienced evenly throughout the grid. Each generator can have distinct carbon emission rates. Due to the existence of physical power flows, nodal power consumption is met by a combination of a set of generators, while such combination is determined by network topology, generators' characteristics and power demand. This paper describes a technique based on physical power flow model, which can efficiently compute the nodal carbon emissions contributed by each single generator given the generation and power flow information. We also extend the technique to calculate both the nodal average carbon emission and marginal carbon emission rates. Simulation results validate the effectiveness of the calculations, while our technique provides a fundamental tool for applications such as carbon auditing, carbon-oriented demand management and future carbon-oriented capacity expansion., Comment: Accepted at ACM e-Energy 2024. Code available at https://github.com/chennnnnyize/Carbon_Emission_Power_Grids

Renewable energy forecasting is the workhorse for efficient energy dispatch. However, forecasts with small mean squared errors (MSE) may not necessarily lead to low operation costs. Here, we propose a forecasting approach specifically tailored for operational purposes, by incorporating operational problems into the estimation of forecast models via designing a loss function. We formulate a bilevel program, where the operation problem is at the lower level, and the forecast model estimation is at the upper level. We establish the relationship between the lower-level optimal solutions and forecasts through multiparametric programming. By integrating it into the upper-level objective for minimizing expected operation cost, we convert the bilevel problem to a single-level one and derive the loss function for training the model. It is proved to be piecewise linear, for linear operation problem. Compared to the commonly used loss functions, e.g. MSE, our approach achieves lower operation costs., Comment: submitted to PSCC 2024

Energy forecasting is an essential task in power system operations. Operators usually issue forecasts and leverage them to schedule energy dispatch ahead of time. However, forecast models are typically developed in a way that overlooks the operational value of the forecasts. To bridge the gap, we design a value-oriented point forecasting approach for sequential energy dispatch problems with renewable energy sources. At the training phase, we align the loss function with the overall operation cost function, thereby achieving reduced operation costs. The forecast model parameter estimation is formulated as a bilevel program. Under mild assumptions, we convert the upper-level objective into an equivalent form using the dual solutions obtained from the lower-level operation problems. Additionally, a novel iterative solution strategy is proposed for the newly formulated bilevel program. Under such an iterative scheme, we show that the upper-level objective is locally linear regarding the forecast model output, and can act as the loss function. Numerical experiments demonstrate that, compared to commonly used statistical quality-oriented point forecasting methods, forecasts obtained by the proposed approach result in lower operation costs. Meanwhile, the proposed approach is more computationally efficient than traditional two-stage stochastic programs., Comment: submitted to IEEE Transactions on Smart Grid

Voltage control generally requires accurate information about the grid's topology in order to guarantee network stability. However, accurate topology identification is challenging for existing methods, especially as the grid is subject to increasingly frequent reconfiguration due to the adoption of renewable energy. In this work, we combine a nested convex body chasing algorithm with a robust predictive controller to achieve provably finite-time convergence to safe voltage limits in the online setting where there is uncertainty in both the network topology as well as load and generation variations. In an online fashion, our algorithm narrows down the set of possible grid models that are consistent with observations and adjusts reactive power generation accordingly to keep voltages within desired safety limits. Our approach can also incorporate existing partial knowledge of the network to improve voltage control performance. We demonstrate the effectiveness of our approach in a case study on a Southern California Edison 56-bus distribution system. Our experiments show that in practical settings, the controller is indeed able to narrow the set of consistent topologies quickly enough to make control decisions that ensure stability in both linearized and realistic non-linear models of the distribution grid., Comment: Published in IEEE Transactions on Smart Grid, vol. 15, no. 5, pp. 4754-4764, Sept. 2024. arXiv admin note: substantial text overlap with arXiv:2206.14369

Energy storage are strategic participants in electricity markets to arbitrage price differences. Future power system operators must understand and predict strategic storage arbitrage behaviors for market power monitoring and capacity adequacy planning. This paper proposes a novel data-driven approach that incorporates prior model knowledge for predicting the strategic behaviors of price-taker energy storage systems. We propose a gradient-descent method to find the storage model parameters given the historical price signals and observations. We prove that the identified model parameters will converge to the true user parameters under a class of quadratic objective and linear equality-constrained storage models. We demonstrate the effectiveness of our approach through numerical experiments with synthetic and real-world storage behavior data. The proposed approach significantly improves the accuracy of storage model identification and behavior forecasting compared to previous blackbox data-driven approaches., Comment: accepted by IEEE Transactions on Smart Grid, 2023

Large language models (LLMs) have achieved great success in general domains of natural language processing. In this paper, we bring LLMs to the realm of geoscience with the objective of advancing research and applications in this field. To this end, we present the first-ever LLM in geoscience, K2, alongside a suite of resources developed to further promote LLM research within geoscience. For instance, we have curated the first geoscience instruction tuning dataset, GeoSignal, which aims to align LLM responses to geoscience-related user queries. Additionally, we have established the first geoscience benchmark, GeoBench, to evaluate LLMs in the context of geoscience. In this work, we experiment with a complete recipe to adapt a pre-trained general-domain LLM to the geoscience domain. Specifically, we further train the LLaMA-7B model on 5.5B tokens of geoscience text corpus, including over 1 million pieces of geoscience literature, and utilize GeoSignal's supervised data to fine-tune the model. Moreover, we share a protocol that can efficiently gather domain-specific data and construct domain-supervised data, even in situations where manpower is scarce. Meanwhile, we equip K2 with the abilities of using tools to be a naive geoscience aide. Experiments conducted on the GeoBench demonstrate the effectiveness of our approach and datasets on geoscience knowledge understanding and utilization.We open-source all the training data and K2 model checkpoints at https://github.com/davendw49/k2.

We study the optimal control of multiple-input and multiple-output dynamical systems via the design of neural network-based controllers with stability and output tracking guarantees. While neural network-based nonlinear controllers have shown superior performance in various applications, their lack of provable guarantees has restricted their adoption in high-stake real-world applications. This paper bridges the gap between neural network-based controllers and the need for stabilization guarantees. Using equilibrium-independent passivity, a property present in a wide range of physical systems, we propose neural Proportional-Integral (PI) controllers that have provable guarantees of stability and zero steady-state output tracking error. The key structure is the strict monotonicity on proportional and integral terms, which is parameterized as gradients of strictly convex neural networks (SCNN). We construct SCNN with tunable softplus-$\beta$ activations, which yields universal approximation capability and is also useful in incorporating communication constraints. In addition, the SCNNs serve as Lyapunov functions, giving us end-to-end performance guarantees. Experiments on traffic and power networks demonstrate that the proposed approach improves both transient and steady-state performances, while unstructured neural networks lead to unstable behaviors., Comment: arXiv admin note: text overlap with arXiv:2206.00261

Ensuring the frequency stability of electric grids with increasing renewable resources is a key problem in power system operations. In recent years, a number of advanced controllers have been designed to optimize frequency control. These controllers, however, almost always assume that the net load in the system remains constant over a sufficiently long time. Given the intermittent and uncertain nature of renewable resources, it is becoming important to explicitly consider net load that is time-varying. This paper proposes an adaptive approach to frequency control in power systems with significant time-varying net load. We leverage the advances in short-term load forecasting, where the net load in the system can be accurately predicted using weather and other features. We integrate these predictions into the design of adaptive controllers, which can be seamlessly combined with most existing controllers including conventional droop control and emerging neural network-based controllers. We prove that the overall control architecture achieves frequency restoration decentralizedly. Case studies verify that the proposed method improves both transient and frequency-restoration performances compared to existing approaches.

Electric vehicle (EV) charging couples the operation of power and traffic networks. Specifically, the power network determines the charging price at various locations, while EVs on the traffic network optimize the charging power given the price, acting as price-takers. We model such decision-making processes by a bilevel program, with the power network at the upper-level and the traffic network at the lower-level. However, since the two networks are managed by separate entities and the charging expense term, calculated as the product of charging price and charging demand, is nonlinear. Solving the bilevel program is nontrivial. To overcome these challenges, we derive the charging demand function using multiparametric programming theory. This function establishes a piecewise linear relationship between the charging price and the optimal charging power, enabling the power network operator to manage EV charging power independently while accounting for the coupling between the two networks. With the derived function, we are also able to replace the nonlinear charging expense term with a piecewise quadratic one, thus guaranteeing solution optimality. Our numerical studies demonstrate that different traffic demands can have an impact on charging patterns and the power network can effectively incentivize charging at low-price nodes through price setting., Comment: submitted to IEEE Transactions on Smart Grid

Deep reinforcement learning approaches are becoming appealing for the design of nonlinear controllers for voltage control problems, but the lack of stability guarantees hinders their deployment in real-world scenarios. This paper constructs a decentralized RL-based controller featuring two components: a transient control policy and a steady-state performance optimizer. The transient policy is parameterized as a neural network, and the steady-state optimizer represents the gradient of the long-term operating cost function. The two parts are synthesized through a safe gradient flow framework, which prevents the violation of reactive power capacity constraints. We prove that if the output of the transient controller is bounded and monotonically decreasing with respect to its input, then the closed-loop system is asymptotically stable and converges to the optimal steady-state solution. We demonstrate the effectiveness of our method by conducting experiments with IEEE 13-bus and 123-bus distribution system test feeders., Comment: Published in IEEE Control Systems Letters, vol. 7, pp. 2845-2850, 2023 with CDC presentation

Unlike ODEs, whose models involve system matrices and whose controllers involve vector or matrix gains, PDE models involve functions in those roles functional coefficients, dependent on the spatial variables, and gain functions dependent on space as well. The designs of gains for controllers and observers for PDEs, such as PDE backstepping, are mappings of system model functions into gain functions. These infinite dimensional nonlinear operators are given in an implicit form through PDEs, in spatial variables, which need to be solved to determine the gain function for each new functional coefficient of the PDE. The need for solving such PDEs can be eliminated by learning and approximating the said design mapping in the form of a neural operator. Learning the neural operator requires a sufficient number of prior solutions for the design PDEs, offline, as well as the training of the operator. In recent work, we developed the neural operators for PDE backstepping designs for first order hyperbolic PDEs. Here we extend this framework to the more complex class of parabolic PDEs. The key theoretical question is whether the controllers are still stabilizing, and whether the observers are still convergent, if they employ the approximate functional gains generated by the neural operator. We provide affirmative answers to these questions, namely, we prove stability in closed loop under gains produced by neural operators. We illustrate the theoretical results with numerical tests and publish our code on github. The neural operators are three orders of magnitude faster in generating gain functions than PDE solvers for such gain functions. This opens up the opportunity for the use of this neural operator methodology in adaptive control and in gain scheduling control for nonlinear PDEs., Comment: 17 pages, 8 figures

We introduce a framework for eliminating the computation of controller gain functions in PDE control. We learn the nonlinear operator from the plant parameters to the control gains with a (deep) neural network. We provide closed-loop stability guarantees (global exponential) under an NN-approximation of the feedback gains. While, in the existing PDE backstepping, finding the gain kernel requires (one offline) solution to an integral equation, the neural operator (NO) approach we propose learns the mapping from the functional coefficients of the plant PDE to the kernel function by employing a sufficiently high number of offline numerical solutions to the kernel integral equation, for a large enough number of the PDE model's different functional coefficients. We prove the existence of a DeepONet approximation, with arbitrarily high accuracy, of the exact nonlinear continuous operator mapping PDE coefficient functions into gain functions. Once proven to exist, learning of the NO is standard, completed "once and for all" (never online) and the kernel integral equation doesn't need to be solved ever again, for any new functional coefficient not exceeding the magnitude of the functional coefficients used for training. We also present an extension from approximating the gain kernel operator to approximating the full feedback law mapping, from plant parameter functions and state measurement functions to the control input, with semiglobal practical stability guarantees. Simulation illustrations are provided and code is available on github. This framework, eliminating real-time recomputation of gains, has the potential to be game changing for adaptive control of PDEs and gain scheduling control of nonlinear PDEs. The paper requires no prior background in machine learning or neural networks., Comment: 16 Pages, 8 Figures

Recent advancements in reinforcement learning algorithms have opened doors for researchers to operate and optimize building energy management systems autonomously. However, the lack of an easily configurable building dynamical model and energy management task simulation and evaluation platform has arguably slowed the progress in developing advanced and dedicated reinforcement learning (RL) and control algorithms for building operation tasks. Here we propose "BEAR", a physics-principled Building Environment for Control And Reinforcement Learning. The platform allows researchers to benchmark both model-based and model-free controllers using a broad collection of standard building models in Python without co-simulation using external building simulators. In this paper, we discuss the design of this platform and compare it with other existing building simulation frameworks. We demonstrate the compatibility and performance of BEAR with different controllers, including both model predictive control (MPC) and several state-of-the-art RL methods with two case studies., Comment: Accepted at ACM e-Energy 2023; Code available at https://github.com/chz056/BEAR

State estimation is important for a variety of tasks, from forecasting to substituting for unmeasured states in feedback controllers. Performing real-time state estimation for PDEs using provably and rapidly converging observers, such as those based on PDE backstepping, is computationally expensive and in many cases prohibitive. We propose a framework for accelerating PDE observer computations using learning-based approaches that are much faster while maintaining accuracy. In particular, we employ the recently-developed Fourier Neural Operator (FNO) to learn the functional mapping from the initial observer state and boundary measurements to the state estimate. By employing backstepping observer gains for previously-designed observers with particular convergence rate guarantees, we provide numerical experiments that evaluate the increased computational efficiency gained with FNO. We consider the state estimation for three benchmark PDE examples motivated by applications: first, for a reaction-diffusion (parabolic) PDE whose state is estimated with an exponential rate of convergence; second, for a parabolic PDE with exact prescribed-time estimation; and, third, for a pair of coupled first-order hyperbolic PDEs that modeling traffic flow density and velocity. The ML-accelerated observers trained on simulation data sets for these PDEs achieves up to three orders of magnitude improvement in computational speed compared to classical methods. This demonstrates the attractiveness of the ML-accelerated observers for real-time state estimation and control., Comment: Accepted to the 61st IEEE Conference on Decision and Control (CDC), 2022

This paper proposes a novel energy storage price arbitrage algorithm combining supervised learning with dynamic programming. The proposed approach uses a neural network to directly predicts the opportunity cost at different energy storage state-of-charge levels, and then input the predicted opportunity cost into a model-based arbitrage control algorithm for optimal decisions. We generate the historical optimal opportunity value function using price data and a dynamic programming algorithm, then use it as the ground truth and historical price as predictors to train the opportunity value function prediction model. Our method achieves 65% to 90% profit compared to perfect foresight in case studies using different energy storage models and price data from New York State, which significantly outperforms existing model-based and learning-based methods. While guaranteeing high profitability, the algorithm is also light-weighted and can be trained and implemented with minimal computational cost. Our results also show that the learned prediction model has excellent transferability. The prediction model trained using price data from one region also provides good arbitrage results when tested over other regions.

Forward invariance is a long-studied property in control theory that is used to certify that a dynamical system stays within some pre-specified set of states for all time, and also admits robustness guarantees (e.g., the certificate holds under perturbations). We propose a general framework for training and provably certifying robust forward invariance in Neural ODEs. We apply this framework to provide certified safety in robust continuous control. To our knowledge, this is the first instance of training Neural ODE policies with such non-vacuous certified guarantees. In addition, we explore the generality of our framework by using it to certify adversarial robustness for image classification.

This paper examines the problem of optimizing the charging pattern of electric vehicles (EV) by taking real-time electricity grid carbon intensity into consideration. The objective of the proposed charging scheme is to minimize the carbon emissions contributed by EV charging events, while simultaneously satisfying constraints posed by EV user's charging schedules, charging station transformer limits, and battery physical constraints. Using real-world EV charging data and California electricity generation records, this paper shows that our carbon-aware real-time charging scheme saves an average of 3.81% of carbon emission while delivering satisfactory amount of energy. Furthermore, by using an adaptive balanced factor, we can reduce 26.00% of carbon emission on average while compromising 12.61% of total energy delivered., Comment: Accepted at SmartGridComm 2022; First two authors contribute equally

Deep reinforcement learning has been recognized as a promising tool to address the challenges in real-time control of power systems. However, its deployment in real-world power systems has been hindered by a lack of explicit stability and safety guarantees. In this paper, we propose a stability-constrained reinforcement learning (RL) method for real-time voltage control, that guarantees system stability both during policy learning and deployment of the learned policy. The key idea underlying our approach is an explicitly constructed Lyapunov function that leads to a sufficient structural condition for stabilizing policies, i.e., monotonically decreasing policies guarantee stability. We incorporate this structural constraint with RL, by parameterizing each local voltage controller using a monotone neural network, thus ensuring the stability constraint is satisfied by design. We demonstrate the effectiveness of our approach in both single-phase and three-phase IEEE test feeders, where the proposed method can reduce the transient control cost by more than 25% and shorten the voltage recovery time by 21.5% on average compared to the widely used linear policy, while always achieving voltage stability. In contrast, standard RL methods often fail to achieve voltage stability., Comment: This paper is accepted by TCNS. arXiv admin note: text overlap with arXiv:2109.14854

Voltage control generally requires accurate information about the grid's topology in order to guarantee network stability. However, accurate topology identification is a challenging problem for existing methods, especially as the grid is subject to increasingly frequent reconfiguration due to the adoption of renewable energy. Further, running existing control mechanisms with incorrect network information may lead to unstable control. In this work, we combine a nested convex body chasing algorithm with a robust predictive controller to achieve provably finite-time convergence to safe voltage limits in the online setting where the network topology is initially unknown. Specifically, the online controller does not know the true network topology and line parameters, but instead must learn them over time by narrowing down the set of network topologies and line parameters that are consistent with its observations and adjusting reactive power generation accordingly to keep voltages within desired safety limits. We demonstrate the effectiveness of the approach using a case study, which shows that in practical settings the controller is indeed able to narrow the set of consistent topologies quickly enough to make control decisions that ensure stability., Comment: Code: https://github.com/chrisyeh96/voltctrl

Learning a dynamical system requires stabilizing the unknown dynamics to avoid state blow-ups. However, current reinforcement learning (RL) methods lack stabilization guarantees, which limits their applicability for the control of safety-critical systems. We propose a model-based RL framework with formal stability guarantees, Krasovskii Constrained RL (KCRL), that adopts Krasovskii's family of Lyapunov functions as a stability constraint. The proposed method learns the system dynamics up to a confidence interval using feature representation, e.g. Random Fourier Features. It then solves a constrained policy optimization problem with a stability constraint based on Krasovskii's method using a primal-dual approach to recover a stabilizing policy. We show that KCRL is guaranteed to learn a stabilizing policy in a finite number of interactions with the underlying unknown system. We also derive the sample complexity upper bound for stabilization of unknown nonlinear dynamical systems via the KCRL framework.

We study the control of networked systems with the goal of optimizing both transient and steady-state performances while providing stability guarantees. Linear proportional-integral (PI) controllers are almost always used in practice, but the linear parameterization of the controller fundamentally limits its performance. Learning-based approaches are becoming popular in designing nonlinear controllers, but the lack of stability guarantees makes the learned controllers difficult to apply in practical applications. This paper bridges the gap between neural network-based controller design and the need for stability guarantees. Using equilibrium-independent passivity, a property present in a wide range of physical systems, we propose structured neural-PI controllers that have provable guarantees on the convergence of output to a desired agreement value. If communication between neighbours is available, we further extend the controller to distributedly achieve optimal resource allocation at the steady state. We explicitly characterize the stability conditions and engineer neural networks that satisfy them by design. Experiments on traffic and power networks demonstrate that the proposed approach can improve transient and steady-state performances compared to existing state-of-the-art, while unstructured neural networks lead to unstable behaviors.

With the development of sensing and communication technologies in networked cyber-physical systems (CPSs), multi-agent reinforcement learning (MARL)-based methodologies are integrated into the control process of physical systems and demonstrate prominent performance in a wide array of CPS domains, such as connected autonomous vehicles (CAVs). However, it remains challenging to mathematically characterize the improvement of the performance of CAVs with communication and cooperation capability. When each individual autonomous vehicle is originally self-interest, we can not assume that all agents would cooperate naturally during the training process. In this work, we propose to reallocate the system's total reward efficiently to motivate stable cooperation among autonomous vehicles. We formally define and quantify how to reallocate the system's total reward to each agent under the proposed transferable utility game, such that communication-based cooperation among multi-agents increases the system's total reward. We prove that Shapley value-based reward reallocation of MARL locates in the core if the transferable utility game is a convex game. Hence, the cooperation is stable and efficient and the agents should stay in the coalition or the cooperating group. We then propose a cooperative policy learning algorithm with Shapley value reward reallocation. In experiments, compared with several literature algorithms, we show the improvement of the mean episode system reward of CAV systems using our proposed algorithm., Comment: This paper has been accepted by the 2022 IEEE International Conference on Robotics and Automation (ICRA 2022)

Current state-of-the-art model-based reinforcement learning algorithms use trajectory sampling methods, such as the Cross-Entropy Method (CEM), for planning in continuous control settings. These zeroth-order optimizers require sampling a large number of trajectory rollouts to select an optimal action, which scales poorly for large prediction horizons or high dimensional action spaces. First-order methods that use the gradients of the rewards with respect to the actions as an update can mitigate this issue, but suffer from local optima due to the non-convex optimization landscape. To overcome these issues and achieve the best of both worlds, we propose a novel planner, Cross-Entropy Method with Gradient Descent (CEM-GD), that combines first-order methods with CEM. At the beginning of execution, CEM-GD uses CEM to sample a significant amount of trajectory rollouts to explore the optimization landscape and avoid poor local minima. It then uses the top trajectories as initialization for gradient descent and applies gradient updates to each of these trajectories to find the optimal action sequence. At each subsequent time step, however, CEM-GD samples much fewer trajectories from CEM before applying gradient updates. We show that as the dimensionality of the planning problem increases, CEM-GD maintains desirable performance with a constant small number of samples by using the gradient information, while avoiding local optima using initially well-sampled trajectories. Furthermore, CEM-GD achieves better performance than CEM on a variety of continuous control benchmarks in MuJoCo with 100x fewer samples per time step, resulting in around 25% less computation time and 10% less memory usage. The implementation of CEM-GD is available at $\href{https://github.com/KevinHuang8/CEM-GD}{\text{https://github.com/KevinHuang8/CEM-GD}}$.