The importance of state estimation in fluid mechanics is well-established; it is required for accomplishing several tasks including design/optimization, active control, and future state prediction. A common tactic in this regards is to rely on reduced order models. Such approaches, in general, use measurement data of one-time instance. However, oftentimes data available from sensors is sequential and ignoring it results in information loss. In this paper, we propose a novel deep learning based state estimation framework that learns from sequential data. The proposed model structure consists of the recurrent cell to pass information from different time steps enabling utilization of this information to recover the full state. We illustrate that utilizing sequential data allows for state recovery from only one or two sensors. For efficient recovery of the state, the proposed approached is coupled with an auto-encoder based reduced order model. We illustrate the performance of the proposed approach using two examples and it is found to outperform other alternatives existing in the literature.
We propose a method to perform set-based state estimation of an unknown dynamical linear system using a data-driven set propagation function. Our method comes with set-containment guarantees, making it applicable to safety-critical systems. The method consists of two phases: (1) an offline learning phase where we collect noisy input-output data to determine a function to propagate the state-set ahead in time; and (2) an online estimation phase consisting of a time update and a measurement update. It is assumed that known finite sets bound measurement noise and disturbances, but we assume no knowledge of their statistical properties. These sets are described using zonotopes, allowing efficient propagation and intersection operations. We propose a new approach to compute a set of models consistent with the data and noise-bound, given input-output data in the offline phase. The set of models is utilized in replacing the unknown dynamics in the data-driven set propagation function in the online phase. Then, we propose two approaches to perform the measurement update. Simulations show that the proposed estimator yields state sets comparable in volume to the 3{\sigma} confidence bounds obtained by a Kalman filter approach, but with the addition of state set-containment guarantees. We observe that using constrained zonotopes yields smaller sets but with higher computational costs than unconstrained ones.
This paper studies the distributed state estimation in sensor network, where $m$ sensors are deployed to infer the $n$-dimensional state of a linear time-invariant (LTI) Gaussian system. By a lossless decomposition of optimal steady-state Kalman filter, we show that the problem of distributed estimation can be reformulated as synchronization of homogeneous linear systems. Based on such decomposition, a distributed estimator is proposed, where each sensor node runs a local filter using only its own measurement and fuses the local estimate of each node with a consensus algorithm. We show that the average of the estimate from all sensors coincides with the optimal Kalman estimate. Numerical examples are provided in the end to illustrate the performance of the proposed scheme.
Electricity is one of the mandatory commodities for mankind today. To address challenges and issues in the transmission of electricity through the traditional grid, the concepts of smart grids and demand response have been developed. In such systems, a large amount of data is generated daily from various sources such as power generation (e.g., wind turbines), transmission and distribution (microgrids and fault detectors), load management (smart meters and smart electric appliances). Thanks to recent advancements in big data and computing technologies, Deep Learning (DL) can be leveraged to learn the patterns from the generated data and predict the demand for electricity and peak hours. Motivated by the advantages of deep learning in smart grids, this paper sets to provide a comprehensive survey on the application of DL for intelligent smart grids and demand response. Firstly, we present the fundamental of DL, smart grids, demand response, and the motivation behind the use of DL. Secondly, we review the state-of-the-art applications of DL in smart grids and demand response, including electric load forecasting, state estimation, energy theft detection, energy sharing and trading. Furthermore, we illustrate the practicality of DL via various use cases and projects. Finally, we highlight the challenges presented in existing research works and highlight important issues and potential directions in the use of DL for smart grids and demand response.
Microgrids are localized electrical grids with control capability that are able to disconnect from the traditional grid to operate autonomously. They strengthen grid resilience, help mitigate grid disturbances, and support a flexible grid by enabling the integration of distributed energy resources. Given the likely presence of critical loads, the proper protection of microgrids is of vital importance; however, this is complicated in the case of inverter-interfaced microgrids where low fault currents preclude the use of conventional time-overcurrent protection. This paper introduces and investigates the application of dynamic state estimation, a generalization of differential protection, for the protection of radial portions of microgrids (or distribution networks); both phasor-based and dynamic approaches are investigated for protection. It is demonstrated through experiments on three case-study systems that dynamic state estimation is capable of correctly identifying model parameters for both normal and faulted operation.
In this work, we present a pragmatic approach to enable unmanned aerial vehicle (UAVs) to autonomously perform highly complicated tasks of object pick and place. This paper is largely inspired by challenge-2 of MBZIRC 2020 and is primarily focused on the task of assembling large 3D structures in outdoors and GPS-denied environments. Primary contributions of this system are: (i) a novel computationally efficient deep learning based unified multi-task visual perception system for target localization, part segmentation, and tracking, (ii) a novel deep learning based grasp state estimation, (iii) a retracting electromagnetic gripper design, (iv) a remote computing approach which exploits state-of-the-art MIMO based high speed (5000Mb/s) wireless links to allow the UAVs to execute compute intensive tasks on remote high end compute servers, and (v) system integration in which several system components are weaved together in order to develop an optimized software stack. We use DJI Matrice-600 Pro, a hex-rotor UAV and interface it with the custom designed gripper. Our framework is deployed on the specified UAV in order to report the performance analysis of the individual modules. Apart from the manipulation system, we also highlight several hidden challenges associated with the UAVs in this context.
Traffic state estimation (TSE), which reconstructs the traffic variables (e.g., density) on road segments using partially observed data, plays an important role on efficient traffic control and operation that intelligent transportation systems (ITS) need to provide to people. Over decades, TSE approaches bifurcate into two main categories, model-driven approaches and data-driven approaches. However, each of them has limitations: the former highly relies on existing physical traffic flow models, such as Lighthill-Whitham-Richards (LWR) models, which may only capture limited dynamics of real-world traffic, resulting in low-quality estimation, while the latter requires massive data in order to perform accurate and generalizable estimation. To mitigate the limitations, this paper introduces a physics-informed deep learning (PIDL) framework to efficiently conduct high-quality TSE with small amounts of observed data. PIDL contains both model-driven and data-driven components, making possible the integration of the strong points of both approaches while overcoming the shortcomings of either. This paper focuses on highway TSE with observed data from loop detectors, using traffic density as the traffic variables. We demonstrate the use of PIDL to solve (with data from loop detectors) two popular physical traffic flow models, i.e., Greenshields-based LWR and three-parameter-based LWR, and discover the model parameters. We then evaluate the PIDL-based highway TSE using the Next Generation SIMulation (NGSIM) dataset. The experimental results show the advantages of the PIDL-based approach in terms of estimation accuracy and data efficiency over advanced baseline TSE methods.
Adopting a joint approach towards state estimation and integrity monitoring results in unbiased integrity monitoring unlike traditional approaches. So far, a joint approach was used in Particle RAIM [l] for GNSS measurements only. In our work, we extend Particle RAIM to a GNSS-camera fused system for joint state estimation and integrity monitoring. To account for vision faults, we derive a probability distribution over position from camera images using map-matching. We formulate a Kullback-Leibler Divergence metric to assess the consistency of GNSS and camera measurements and mitigate faults during sensor fusion. The derived integrity risk upper bounds the probability of Hazardously Misleading Information (HMI). Experimental validation on a real-world dataset shows that our algorithm produces less than 11 m position error and the integrity risk over bounds the probability of HMI with 0.11 failure rate for an 8 m Alert Limit in an urban scenario.
Power System State Estimation (PSSE) has been a research area of interest for power engineers for a long period of time. Due to the intermittent nature of renewable energy sources, which are applied in the power network more than before, the importance of state estimation has been increased as well. Centralized state estimation due to the complexity of new networks and growing size of power network will face problems such as communication bottleneck in real-time analyzing of the system or reliability issues. Distributed state estimation is a solution for the mentioned issues. There are different implementation methods introduced for it. The results of the paper are twofold. First, we examined different approaches to distributed PSSE (DPSSE) problem, according to most important factors like iteration number, convergence rate, data needed to be transferred to/from each area and so on. Next, we proposed and discussed a new distributed stopping criterion for the methods and above-mentioned factors are obtained as well. Finally, a comparison between the total efficiency of all applied methods is done.
The term "machine learning" especially refers to algorithms that derive mappings, i.e. intput/output transforms, by using numerical data that provide information about considered transforms. These transforms appear in many problems, related to classification/clustering, regression, system identification, system inversion and input signal restoration/separation. We here first analyze the connections between all these problems, in the classical and quantum frameworks. We then focus on their most challenging versions, involving quantum data and/or quantum processing means, and unsupervised, i.e. blind, learning. Moreover, we propose the quite general concept of SIngle-Preparation Quantum Information Processing (SIPQIP). The resulting methods only require a single instance of each state, whereas usual methods have to very accurately create many copies of each fixed state. We apply our SIPQIP concept to various tasks, related to system identification (blind quantum process tomography or BQPT, blind Hamiltonian parameter estimation or BHPE, blind quantum channel identification/estimation, blind phase estimation), system inversion and state estimation (blind quantum source separation or BQSS, blind quantum entangled state restoration or BQSR, blind quantum channel equalization) and classification. Numerical tests show that our framework moreover yields much more accurate estimation than the standard multiple-preparation approach. Our methods are especially useful in a quantum computer, that we propose to more briefly call a "quamputer": BQPT and BHPE simplify the characterization of the gates of quamputers; BQSS and BQSR allow one to design quantum gates that may be used to compensate for the non-idealities that alter states stored in quantum registers, and they open the way to the much more general concept of self-adaptive quantum gates (see longer version of abstract in paper).
In many robotic applications, it is crucial to maintain a belief about the state of a system, which serves as input for planning and decision making and provides feedback during task execution. Bayesian Filtering algorithms address this state estimation problem, but they require models of process dynamics and sensory observations and the respective noise characteristics of these models. Recently, multiple works have demonstrated that these models can be learned by end-to-end training through differentiable versions of recursive filtering algorithms. In this work, we investigate the advantages of differentiable filters (DFs) over both unstructured learning approaches and manually-tuned filtering algorithms, and provide practical guidance to researchers interested in applying such differentiable filters. For this, we implement DFs with four different underlying filtering algorithms and compare them in extensive experiments. Specifically, we (i) evaluate different implementation choices and training approaches, (ii) investigate how well complex models of uncertainty can be learned in DFs, (iii) evaluate the effect of end-to-end training through DFs and (iv) compare the DFs among each other and to unstructured LSTM models.
This paper studies distributed Q-learning for Linear Quadratic Regulator (LQR) in a multi-agent network. The existing results often assume that agents can observe the global system state, which may be infeasible in large-scale systems due to privacy concerns or communication constraints. In this work, we consider a setting with unknown system models and no centralized coordinator. We devise a state tracking (ST) based Q-learning algorithm to design optimal controllers for agents. Specifically, we assume that agents maintain local estimates of the global state based on their local information and communications with neighbors. At each step, every agent updates its local global state estimation, based on which it solves an approximate Q-factor locally through policy iteration. Assuming decaying injected excitation noise during the policy evaluation, we prove that the local estimation converges to the true global state, and establish the convergence of the proposed distributed ST-based Q-learning algorithm. The experimental studies corroborate our theoretical results by showing that our proposed method achieves comparable performance with the centralized case.
Belief propagation is an algorithm that is known from statistical physics and computer science. It provides an efficient way of calculating marginals that involve large sums of products which are efficiently rearranged into nested products of sums to approximate the marginals. It allows a reliable estimation of the state and its variance of power grids that is needed for the control and forecast of power grid management. At prototypical examples of IEEE-grids we show that belief propagation not only scales linearly with the grid size for the state estimation itself, but also facilitates and accelerates the retrieval of missing data and allows an optimized positioning of measurement units. Based on belief propagation, we give a criterion for how to assess whether other algorithms, using only local information, are adequate for state estimation for a given grid. We also demonstrate how belief propagation can be utilized for coarse-graining power grids towards representations that reduce the computational effort when the coarse-grained version is integrated into a larger grid. It provides a criterion for partitioning power grids into areas in order to minimize the error of flow estimates between different areas.
Due to increasing penetration of volatile distributed photovoltaic (PV) resources, real-time monitoring of customers at the grid-edge has become a critical task. However, this requires solving the distribution system state estimation (DSSE) jointly for both primary and secondary levels of distribution grids, which is computationally complex and lacks scalability to large systems. To achieve near real-time solutions for DSSE, we present a novel hierarchical reinforcement learning-aided framework: at the first layer, a weighted least squares (WLS) algorithm solves the DSSE over primary medium-voltage feeders; at the second layer, deep actor-critic (A-C) modules are trained for each secondary transformer using measurement residuals to estimate the states of low-voltage circuits and capture the impact of PVs at the grid-edge. While the A-C parameter learning process takes place offline, the trained A-C modules are deployed online for fast secondary grid state estimation; this is the key factor in scalability and computational efficiency of the framework. To maintain monitoring accuracy, the two levels exchange boundary information with each other at the secondary nodes, including transformer voltages (first layer to second layer) and active/reactive total power injection (second layer to first layer). This interactive information passing strategy results in a closed-loop structure that is able to track optimal solutions at both layers in few iterations. Moreover, our model can handle the topology changes using the Jacobian matrices of the first layer. We have performed numerical experiments using real utility data and feeder models to verify the performance of the proposed framework.
Distribution system and market operators will need or be required to monitor closely distribution systems, due to the presence of multiple actors, such as generating and storage units, as also active loads. The reason for this is the effect of these latter actors to system operation as also to ensure they follow their commitments in the deregulated market frameworks. This paper discusses why the traditional approach to state estimation as this has been developed for transmission systems cannot be extended to distribution systems. Some preliminary proposals are made, and a high-level architecture is presented as part of an on-going research work on the matter.
For reliable and secure power grid operation, AC state-estimation (ACSE) must provide certain guarantees of convergence while being resilient against bad-data. This paper develops a circuit-theoretic weighted least absolute value (WLAV) based hybrid ACSE that satisfies these needs to overcome some of the limitations of existing ACSE methods. Hybrid refers to the inclusion of RTU and PMU measurement data, and the use of the LAV objective function enables automatic rejection of bad data while providing clear identification of suspicious measurements from the sparse residual vector. Taking advantage of linear construction of the measurement models in circuit-theoretic approach, the proposed hybrid SE is formulated as a LP problem with guaranteed convergence. To address efficiency, we further develop problem-specific heuristics for fast convergence. To validate the efficacy of the proposed approach, we run ACSE on large cases and compare the results against WLS-based algorithms. We further demonstrate the advantages of our solution methodology over standard commercial LP solvers through comparison of runtime and convergence performance.
This paper applies a custom model order reduction technique to the distribution grid state estimation problem. Specifically, the method targets the situation where, due to pseudo-measurement uncertainty, it is advantageous to run the state estimation solver potentially thousands of times over sampled input perturbations in order to compute probabilistic bounds on the underlying system state. This routine, termed the Accelerated Probabilistic State Estimator (APSE), efficiently searches for the solutions of sequential state estimation problems in a low dimensional subspace with a reduced order model (ROM). When a sufficiently accurate solution is not found, the APSE reverts to a conventional QR factorization-based Gauss-Newton solver. It then uses the resulting solution to preform a simple basis expansion of the low-dimensional subspace, thus improving the reduced model solver. Simulated test results, collected from the unbalanced three-phase 8500-node distribution grid, show the resulting algorithm to be almost an order of magnitude faster than a comparable full-order Gauss-Newton solver and thus potentially fast enough for real-time use.
In this paper, quickest detection of false data injection attack on remote state estimation is considered. A set of $N$ sensors make noisy linear observations of a discrete-time linear process with Gaussian noise, and report the observations to a remote estimator. The challenge is the presence of a few potentially malicious sensors which can start strategically manipulating their observations at a random time in order to skew the estimates. The quickest attack detection problem for a known {\em linear} attack scheme in the Bayesian setting with a Geometric prior on the attack initiation instant is posed as a constrained Markov decision process (MDP), in order to minimize the expected detection delay subject to a false alarm constraint, with the state involving the probability belief at the estimator that the system is under attack. State transition probabilities are derived in terms of system parameters, and the structure of the optimal policy is derived analytically. It turns out that the optimal policy amounts to checking whether the probability belief exceeds a threshold. Next, generalized CUSUM based attack detection algorithm is proposed for the non-Bayesian setting where the attacker chooses the attack initiation instant in a particularly adversarial manner. It turns out that computing the statistic for the generalised CUSUM test in this setting relies on the same techniques developed to compute the state transition probabilities of the MDP. Numerical results demonstrate significant performance gain under the proposed algorithms against competing algorithms.
This paper proposes a DC microgrid state estimation and sensor placement method based on compressive sensing. Formulations of various types of measurements and components are developed under the proposed framework. A measurement placing strategy to minimize the coherence of the measurement matrix and thus increase estimation accuracy is presented. Simulation results show that the proposed state estimation and sensor placing approach can effectively reduce the number of sensors to achieve a certain level of estimation accuracy.
Global Positioning System (GPS) and inertial measurement unit (IMU) sensors are commonly integrated using the extended Kalman filter (EKF), for achieving better navigation performance. However, because of nonlinearity, the performance of the EKF is affected by the initial state estimation errors, and the navigation solutions, including the attitude, diverge rapidly as the initial errors increase. This paper analyzes the data obtained from an outdoor experiment, and investigates the effect of the initial errors on the attitude estimation performance using EKF, which is used in loosely coupled low-cost smartphone GPS/IMU sensors.