PyTorchKR Papers

최신 논문

총 1,050편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2210.06729

A Stream Learning Approach for Real-Time Identification of False Data Injection Attacks in Cyber-Physical Power Systems

This paper presents a novel data-driven framework to aid in system state estimation when the power system is under unobservable false data injection attacks. The proposed framework dynamically detects and classifies false data injection attacks. Then, it retrieves the control signal using the acquired information. This process is accomplished in three main modules, with novel designs, for detection, classification, and control signal retrieval. The detection module monitors historical changes in phasor measurements and captures any deviation pattern caused by an attack on a complex plane. This approach can help to reveal characteristics of the attacks including the direction, magnitude, and ratio of the injected false data. Using this information, the signal retrieval module can easily recover the original control signal and remove the injected false data. Further information regarding the attack type can be obtained through the classifier module. The proposed ensemble learner is compatible with harsh learning conditions including the lack of labeled data, concept drift, concept evolution, recurring classes, and independence from external updates. The proposed novel classifier can dynamically learn from data and classify attacks under all these harsh learning conditions. The introduced framework is evaluated w.r.t. real-world data captured from the Central New York Power System. The obtained results indicate the efficacy and stability of the proposed framework.

arXiv:2210.06071공식 코드 · Papers with Code

Self-Validated Physics-Embedding Network: A General Framework for Inverse Modelling

Physics-based inverse modeling techniques are typically restricted to particular research fields, whereas popular machine-learning-based ones are too data-dependent to guarantee the physical compatibility of the solution. In this paper, Self-Validated Physics-Embedding Network (SVPEN), a general neural network framework for inverse modeling is proposed. As its name suggests, the embedded physical forward model ensures that any solution that successfully passes its validation is physically reasonable. SVPEN operates in two modes: (a) the inverse function mode offers rapid state estimation as conventional supervised learning, and (b) the optimization mode offers a way to iteratively correct estimations that fail the validation process. Furthermore, the optimization mode provides SVPEN with reconfigurability i.e., replacing components like neural networks, physical models, and error calculations at will to solve a series of distinct inverse problems without pretraining. More than ten case studies in two highly nonlinear and entirely distinct applications: molecular absorption spectroscopy and Turbofan cycle analysis, demonstrate the generality, physical reliability, and reconfigurability of SVPEN. More importantly, SVPEN offers a solid foundation to use existing physical models within the context of AI, so as to striking a balance between data-driven and physics-driven models.

arXiv:2210.05518

Autonomous Asteroid Characterization Through Nanosatellite Swarming

This paper first defines a class of estimation problem called simultaneous navigation and characterization (SNAC), which is a superset of simultaneous localization and mapping (SLAM). A SNAC framework is then developed for the Autonomous Nanosatellite Swarming (ANS) mission concept to autonomously navigate about and characterize an asteroid including the asteroid gravity field, rotational motion, and 3D shape. The ANS SNAC framework consists of three modules: 1) multi-agent optical landmark tracking and 3D point reconstruction using stereovision, 2) state estimation through a computationally efficient and robust unscented Kalman filter, and 3) reconstruction of an asteroid spherical harmonic shape model by leveraging a priori knowledge of the shape properties of celestial bodies. Despite significant interest in asteroids, there are several limitations to current asteroid rendezvous mission concepts. First, completed missions heavily rely on human oversight and Earth-based resources. Second, proposed solutions to increase autonomy make oversimplifying assumptions about state knowledge and information processing. Third, asteroid mission concepts often opt for high size, weight, power, and cost (SWaP-C) avionics for environmental measurements. Finally, such missions often utilize a single spacecraft, neglecting the benefits of distributed space systems. In contrast, ANS is composed of multiple autonomous nanosatellites equipped with low SWaP-C avionics. The ANS SNAC framework is validated through a numerical simulation of three spacecraft orbiting asteroid 433 Eros. The simulation results demonstrate that the proposed architecture provides autonomous and accurate SNAC in a safe manner without an a priori shape model and using only low SWaP-C avionics.

arXiv:2210.02700

Minimal-order Appointed-time Unknown Input Observers: Design and Applications

This paper presents a framework on minimal-order appointed-time unknown input observers for linear systems based on the pairwise observer structure. A minimal-order appointed-time observer is first proposed for the linear system without the unknown input, which can estimate the state exactly at the preset time by seeking for the unique solution of a system of linear equations. To further release the computational burden, another form of the appointed-time observer is designed. For the general linear system with the unknown input acting on both the system dynamics and the measured output, the model reconfiguration is made to decouple the effect of the unknown input, and the gap between the existing reduced-order appointed-time unknown input observer and the possible minimal-order appointed-time observer is revealed. Based on the reconstructed model, the minimal-order appointed-time unknown input observer is presented to realize state estimation of linear system with the unknown input at the arbitrarily small preset time. The minimal-order appointed-time unknown input observer is then applied to the design of fully distributed adaptive output-feedback attack-free consensus protocols for linear multi-agent systems.

arXiv:2210.01232

Split-Spectrum Based Distributed State Estimation for Linear Systems

This paper studies a distributed state estimation problem for both continuous- and discrete-time linear systems. A simply structured distributed estimator (comprising interconnected local estimators) is first described for estimating the state of a continuous and multi-channel linear system whose sensed outputs are distributed across a fixed multi-agent network. The estimator is then extended to non-stationary networks whose graphs switch according to a switching signal. The estimator is guaranteed to solve the problem, provided a network-widely shared high gain condition achieving a form of spectrum separation is satisfied. As an alternative to sharing a common gain across the network, a fully distributed version of the estimator is also studied in which each agent adaptively adjusts a local gain, though the practicality of this approach is subject to a robustness issue common to adaptive control. A discrete-time version of the distributed state estimation problem is also studied, and a corresponding estimator based again on spectrum separation, but not high gain, is proposed for time-varying networks. For each scenario, it is explained how to construct the estimator so that the state estimation errors in the local estimators all converge to zero exponentially fast at a fixed but arbitrarily chosen rate, provided the network's graph is strongly connected for all time. The proposed estimators are inherently resilient to abrupt changes in the number of agents and communication links in the inter-agent communication graph upon which the algorithms depend, provided the network is redundantly strongly connected and redundantly jointly observable.

arXiv:2209.15239

Smart Meters Integration in Distribution System State Estimation with Collaborative Filtering and Deep Gaussian Process

The problem of state estimations for electric distribution system is considered. A collaborative filtering approach is proposed in this paper to integrate the slow time-scale smart meter measurements in the distribution system state estimation, in which the deep Gaussian process is incorporated to infer the fast time-scale pseudo measurements and avoid anomalies. Numerical tests have demonstrated the higher estimation accuracy of the proposed method.

arXiv:2209.14081

Improved event-based particle filtering in resource-constrained remote state estimation

Event-based sampling has been proposed as a general technique for lowering the average communication rate in remote state estimation, which can be important in scenarios with constraints on resources such as network bandwidth or sensor energy. Recently, the interest of applying particle filters to event-based state estimation has seen an upswing, partly to tackle nonlinear and non-Gaussian problems, but also since event-based sampling does not allow an analytic solution for linear--Gaussian systems. Thus far, very little has been mentioned regarding the practical issues that arise when applying particle filtering to event-based state estimation. In this paper, we provide such a discussion by (i) demonstrating that there exists a high risk of sample degeneracy at new events, for which the auxiliary particle filter provides an intuitive solution, (ii) introducing a new alternative to the local predictor approach based on precomputing state estimates which is better suited to solve the issue of observer-to-sensor communication for closed-loop triggering in difficult systems, and (iii) exploring the difficulties surrounding the increased computational load when implementing the particle filter under event-based sampling.

arXiv:2209.12629공식 코드 · Papers with Code

Power System Anomaly Detection and Classification Utilizing WLS-EKF State Estimation and Machine Learning

Power system state estimation is being faced with different types of anomalies. These might include bad data caused by gross measurement errors or communication system failures. Sudden changes in load or generation can be considered as anomaly depending on the implemented state estimation method. Additionally, considering power grid as a cyber physical system, state estimation becomes vulnerable to false data injection attacks. The existing methods for anomaly classification cannot accurately classify (discriminate between) the above mentioned three types of anomalies, especially when it comes to discrimination between sudden load changes and false data injection attacks. This paper presents a new algorithm for detecting anomaly presence, classifying the anomaly type and identifying the origin of the anomaly, i.e., measurements that contain gross errors in case of bad data, or buses associated with loads experiencing a sudden change, or state variables targeted by false data injection attack. The algorithm combines analytical and machine learning (ML) approaches. The first stage exploits an analytical approach to detect anomaly presence by combining $\chi^2$-test and anomaly detection index. The second stage utilizes ML for classification of anomaly type and identification of its origin, with particular reference to discrimination between sudden load changes and false data injection attacks. The proposed ML based method is trained to be independent of the network configuration which eliminates retraining of the algorithm after network topology changes. The results obtained by implementing the proposed algorithm on IEEE 14 bus test system demonstrate the accuracy and effectiveness of the proposed algorithm.

arXiv:2209.12136

Vision-based Perimeter Defense via Multiview Pose Estimation

Previous studies in the perimeter defense game have largely focused on the fully observable setting where the true player states are known to all players. However, this is unrealistic for practical implementation since defenders may have to perceive the intruders and estimate their states. In this work, we study the perimeter defense game in a photo-realistic simulator and the real world, requiring defenders to estimate intruder states from vision. We train a deep machine learning-based system for intruder pose detection with domain randomization that aggregates multiple views to reduce state estimation errors and adapt the defensive strategy to account for this. We newly introduce performance metrics to evaluate the vision-based perimeter defense. Through extensive experiments, we show that our approach improves state estimation, and eventually, perimeter defense performance in both 1-defender-vs-1-intruder games, and 2-defenders-vs-1-intruder games.

arXiv:2209.11638

GSP-Based MAP Estimation of Graph Signals

In this paper, we consider the problem of recovering random graph signals from nonlinear measurements. We formulate the maximum a-posteriori probability (MAP) estimator, which results in a nonconvex optimization problem. Conventional iterative methods for minimizing nonconvex problems are sensitive to the initialization, have high computational complexity, and do not utilize the underlying graph structure behind the data. In this paper we propose two new estimators that are both based on the Gauss-Newton method: 1) the elementwise graph-frequency-domain MAP (eGFD-MAP) estimator; and 2) the graph signal processing MAP (GSP-MAP) estimator. At each iteration, these estimators are updated by the outputs of two graph filters, with the previous state estimator and the residual as the input graph signals. The eGFD-MAP estimator is an ad-hoc method that minimizes the MAP objective function in the graph frequency domain and neglects mixed-derivatives of different graph frequencies in the Jacobian matrix as well as off-diagonal elements in the covariance matrices. Consequently, it updates the elements of the graph signal independently, which reduces the computational complexity compared to the conventional MAP estimator. The GSP-MAP estimator is based on optimizing the graph filters at each iteration of the Gauss-Newton algorithm. We state conditions under which the eGFD-MAP and GSP- MAP estimators coincide with the MAP estimator, in the case of an observation model with orthogonal graph frequencies. We evaluate the performance of the estimators for nonlinear graph signal recovery tasks with synthetic data and with the real-world problem of state estimation in power systems. These simulations show the advantages of the proposed estimators in terms of computational complexity, mean-squared-error, and robustness to the initialization of the iterative algorithms.

arXiv:2209.10938

Combined Unbalanced Distribution System State and Line Impedance Matrix Estimation

To address the challenges that the decarbonization of the energy sector is bringing about, advanced distribution network management and operation strategies are being developed. Many of these strategies require accurate network models to work effectively. However, distribution network data are known to contain errors, and attention has been given to techniques that allow to derive improved network information. This paper presents a novel method to derive line impedance values from smart meter measurement time series, with realistic assumptions in terms of meter accuracy, resolution and penetration. The method is based on unbalanced state estimation and is cast as a non-convex quadratically constrained optimization problem. Both line lengths and impedance matrix models can be estimated based on an exact nonlinear formulation of the steady-state three-phase network physics. The method is evaluated on the IEEE European Low Voltage feeder (906 buses) and shows promising results.

arXiv:2209.10032

Robust Dynamic State Estimation of Multi-Machine Power Networks with Solar Farms and Dynamics Loads

Conventional state estimation routines of electrical grids are mainly reliant on dynamic models of fossil fuel-based resources. These models commonly contain differential equations describing synchronous generator models and algebraic equations modeling power flow/balance equations. Fuel-free power systems that are driven by inertia-less renewable energy resources will hence require new models and upgraded estimation routines. To that end, in this paper we propose a robust estimator for an interconnected model of power networks comprised of a comprehensive ninth order synchronous generator model, advanced power electronics-based models for photovoltaic (PV) power plants, constant power loads, constant impedance loads, and motor loads. The presented state estimator design is based on Lyapunov stability criteria for nonlinear differential algebraic equation (DAE) models and is posed as a convex semi-definite optimization problem. Thorough simulations studies have been carried out on IEEE-39 bus test system to showcase the robustness of the proposed estimator against unknown uncertainty from load demand and solar irradiance.

arXiv:2209.09977공식 코드 · Papers with Code

Learning Bilinear Models of Actuated Koopman Generators from Partially-Observed Trajectories

Data-driven models for nonlinear dynamical systems based on approximating the underlying Koopman operator or generator have proven to be successful tools for forecasting, feature learning, state estimation, and control. It has become well known that the Koopman generators for control-affine systems also have affine dependence on the input, leading to convenient finite-dimensional bilinear approximations of the dynamics. Yet there are still two main obstacles that limit the scope of current approaches for approximating the Koopman generators of systems with actuation. First, the performance of existing methods depends heavily on the choice of basis functions over which the Koopman generator is to be approximated; and there is currently no universal way to choose them for systems that are not measure preserving. Secondly, if we do not observe the full state, then it becomes necessary to account for the dependence of the output time series on the sequence of supplied inputs when constructing observables to approximate Koopman operators. To address these issues, we write the dynamics of observables governed by the Koopman generator as a bilinear hidden Markov model, and determine the model parameters using the expectation-maximization (EM) algorithm. The E-step involves a standard Kalman filter and smoother, while the M-step resembles control-affine dynamic mode decomposition for the generator. We demonstrate the performance of this method on three examples, including recovery of a finite-dimensional Koopman-invariant subspace for an actuated system with a slow manifold; estimation of Koopman eigenfunctions for the unforced Duffing equation; and model-predictive control of a fluidic pinball system based only on noisy observations of lift and drag.

arXiv:2209.08908

Adaptive Output Feedback Model Predictive Control

Model predictive control (MPC) for uncertain systems in the presence of hard constraints on state and input is a non-trivial problem, and the challenge is increased manyfold in the absence of state measurements. In this paper, we propose an adaptive output feedback MPC technique, based on a novel combination of an adaptive observer and robust MPC, for single-input single-output discrete-time linear time-invariant systems. At each time instant, the adaptive observer provides estimates of the states and the system parameters that are then leveraged in the MPC optimization routine while robustly accounting for the estimation errors. The solution to the optimization problem results in a homothetic tube where the state estimate trajectory lies. The true state evolves inside a larger outer tube obtained by augmenting a set, invariant to the state estimation error, around the homothetic tube sections. The proof for recursive feasibility for the proposed `homothetic and invariant' two-tube approach is provided, along with simulation results on an academic system.

arXiv:2209.08185

LEARNEST: LEARNing Enhanced Model-based State ESTimation for Robots using Knowledge-based Neural Ordinary Differential Equations

State estimation is an important aspect in many robotics applications. In this work, we consider the task of obtaining accurate state estimates for robotic systems by enhancing the dynamics model used in state estimation algorithms. Existing frameworks such as moving horizon estimation (MHE) and the unscented Kalman filter (UKF) provide the flexibility to incorporate nonlinear dynamics and measurement models. However, this implies that the dynamics model within these algorithms has to be sufficiently accurate in order to warrant the accuracy of the state estimates. To enhance the dynamics models and improve the estimation accuracy, we utilize a deep learning framework known as knowledge-based neural ordinary differential equations (KNODEs). The KNODE framework embeds prior knowledge into the training procedure and synthesizes an accurate hybrid model by fusing a prior first-principles model with a neural ordinary differential equation (NODE) model. In our proposed LEARNEST framework, we integrate the data-driven model into two novel model-based state estimation algorithms, which are denoted as KNODE-MHE and KNODE-UKF. These two algorithms are compared against their conventional counterparts across a number of robotic applications; state estimation for a cartpole system using partial measurements, localization for a ground robot, as well as state estimation for a quadrotor. Through simulations and tests using real-world experimental data, we demonstrate the versatility and efficacy of the proposed learning-enhanced state estimation framework.

arXiv:2209.09191

The dGLI Cloth Coordinates: A Topological Representation for Semantic Classification of Cloth States

Robotic manipulation of cloth is a highly complex task because of its infinite-dimensional shape-state space that makes cloth state estimation very difficult. In this paper we introduce the dGLI Cloth Coordinates, a low-dimensional representation of the state of a rectangular piece of cloth that allows to efficiently distinguish key topological changes in a folding sequence, opening the door to efficient learning methods for cloth manipulation planning and control. Our representation is based on a directional derivative of the Gauss Linking Integral and allows us to represent both planar and spatial configurations in a consistent unified way. The proposed dGLI Cloth Coordinates are shown to be more accurate in the classification of cloth states and significantly more sensitive to changes in grasping affordances than other classic shape distance methods. Finally, we apply our representation to real images of a cloth, showing we can identify the different states using a simple distance-based classifier.

arXiv:2209.07206

Encrypted distributed state estimation via affine averaging

Distributed state estimation arises in many applications such as position estimation in robot swarms, clock synchronization for processor networks, and data fusion. One characteristic is that agents only have access to noisy measurements of deviations between their own and neighboring states. Still, estimations of their actual state can be obtained in a fully distributed manner using algorithms such as affine averaging. However, running this algorithm, requires that the agents exchange their current state estimations, which can be a privacy issue (since they eventually reveal the actual states). To counteract this threat, we propose an encrypted version of the affine averaging algorithm in this paper. More precisely, we use homomorphic encryption to realize an encrypted implementation, where only one ``leader'' agent has access to its state estimation in plaintext. One main challenge (which often arises for recursive encrypted computations) is to prevent overflow w.r.t.~the bounded message space of the cryptosystem. We solve this problem by periodically resetting the agents' states with the help of the leader. We study the resulting system dynamics with respect to different reset strategies and support our findings with extensive numerical simulations.

arXiv:2209.06588공식 코드 · Papers with Code

Data-Efficient Collaborative Decentralized Thermal-Inertial Odometry

We propose a system solution to achieve data-efficient, decentralized state estimation for a team of flying robots using thermal images and inertial measurements. Each robot can fly independently, and exchange data when possible to refine its state estimate. Our system front-end applies an online photometric calibration to refine the thermal images so as to enhance feature tracking and place recognition. Our system back-end uses a covariance-intersection fusion strategy to neglect the cross-correlation between agents so as to lower memory usage and computational cost. The communication pipeline uses Vector of Locally Aggregated Descriptors (VLAD) to construct a request-response policy that requires low bandwidth usage. We test our collaborative method on both synthetic and real-world data. Our results show that the proposed method improves by up to 46 % trajectory estimation with respect to an individual-agent approach, while reducing up to 89 % the communication exchange. Datasets and code are released to the public, extending the already-public JPL xVIO library.

arXiv:2209.05146

Secure state estimation over Markov wireless communication channels (extended version)

This note studies state estimation in wireless networked control systems with secrecy against eavesdropping. Specifically, a sensor transmits a system state information to the estimator over a legitimate user link, and an eavesdropper overhears these data over its link independent of the user link. Each connection may be affected by packet losses and is modeled by a finite-state Markov channel (FSMC), an abstraction widely used to design wireless communication systems. This paper presents a novel concept of optimal mean square expected secrecy over FSMCs and delineates the design of a secrecy parameter requiring the user mean square estimation error (MSE) to be bounded and eavesdropper MSE unbounded. We illustrate the developed results on an example of an inverted pendulum on a cart whose parameters are estimated remotely over a wireless link exposed to an eavesdropper.