arXiv subjects

Yuanqing Xia

Publications and source records attributed to Yuanqing Xia.

At least 55 records · Page 3Linked to original sources

arXiv2022

On Polynomially Solvable Constrained Input Selections for Fixed and Switched Linear Structured Systems

This paper investigates two related optimal input selection problems for fixed (non-switched) and switched structured systems. More precisely, we consider selecting the minimum cost of inputs from a prior set of inputs, and selecting the inputs of the smallest possible cost with a bound on their cardinality, all to ensure system structural controllability. Those problems have attracted much attention recently; unfortunately, they are NP-hard in general. In this paper, it is found that, if the input structure satisfies certain `regularizations', which are characterized by the proposed restricted total unimodulairty notion, those problems can be solvable in polynomial time via linear programming (LP) relaxations. Particularly, the obtained characterizations depend only on the incidence matrix relating the inputs and the source strongly connected components (SCC) of the system structure, irrespective of how the inputs actuate states within the same SCC. They cover all the currently known polynomially solvable cases (such as the dedicated input case), and contain many new cases unexploited in the past, among which the source-SCC separated input (SSSI) constraint is highlighted. Further, for switched systems, the obtained polynomially solvable condition (namely the joint SSSI constraint) does not require each of the subsystems to satisfy the SSSI constraint. We achieve these by first formulating those problems as equivalent integer linear programmings (ILPs), and then proving total unimodularity of the corresponding constraint matrices. This property allows us to solve those ILPs efficiently via LP-relaxation. We also discuss solutions obtained via LP-relaxation and LP-rounding in the general case. Several examples are given to illustrate the obtained theoretical results.

eess.SY↗

arXiv2022

Workflow-based Fast Data-driven Predictive Control with Disturbance Observer in Cloud-edge Collaborative Architecture

Data-driven predictive control (DPC) has been studied and used in various scenarios, since it could generate the predicted control sequence only relying on the historical input and output data. Recently, based on cloud computing, data-driven predictive cloud control system (DPCCS) has been proposed with the advantage of sufficient computational resources. However, the existing computation mode of DPCCS is centralized. This computation mode could not utilize fully the computing power of cloud computing, of which the structure is distributed. Thus, the computation delay could not been reduced and still affects the control quality. In this paper, a novel cloud-edge collaborative containerised workflow-based DPC system with disturbance observer (DOB) is proposed, to improve the computation efficiency and guarantee the control accuracy. First, a construction method for the DPC workflow is designed, to match the distributed processing environment of cloud computing. But the non-computation overheads of the workflow tasks are relatively high. Therefore, a cloud-edge collaborative control scheme with DOB is designed. The low-weight data could be truncated to reduce the non-computation overheads. Meanwhile, we design an edge DOB to estimate and compensate the uncertainty in cloud workflow processing, and obtain the composite control variable. The UUB stability of the DOB is also proved. Third, to execute the workflow-based DPC controller and evaluate the proposed cloud-edge collaborative control scheme with DOB in the real cloud environment, we design and implement a practical workflow-based cloud control experimental system based on container technology. Finally, a series of evaluations show that, the computation times are decreased by 45.19% and 74.35% for two real-time control examples, respectively, and by at most 85.10% for a high-dimension control example.

eess.SY↗

arXiv2022

Zero-Norm Distance to Controllability of Linear Systems: Complexity, Bounds, and Algorithms

Determining the distance between a controllable system to the set of uncontrollable systems, namely, the controllability radius problem, has been extensively studied in the past. However, the opposite direction, that is, determining the `distance' between an uncontrollable system to the set of controllable systems, has seldom been considered. In this paper, we address this problem by defining the notion of zero-norm distance to controllability (ZNDC) to be the smallest number of entries (parameters) in the system matrices that need to be perturbed to make the original system controllable. We show genericity exists in this problem, so that other matrix norms (such as the $2$-norm or the Frobenius norm) adopted in this notion are nonsense. For ZNDC, we show it is NP-hard to compute, even when only the state matrix can be perturbed. We then provide some nontrivial lower and upper bounds. For its computation, we provide two heuristic algorithms. The first one is by transforming the ZNDC into a problem of structural controllability of linearly parameterized systems, and then greedily selecting the candidate links according to a suitable objective function. The second one is based on the weighted $l_1$-norm relaxation and the convex-concave procedure, which is tailored for ZNDC when additional structural constraints are involved in the perturbed parameters. Finally, we examine the performance of our proposed algorithms in several typical uncontrollable networks in multi-agent systems.

math.OC↗

arXiv2022

KubeAdaptor: A Docking Framework for Workflow Containerization on Kubernetes

As Kubernetes becomes the infrastructure of the cloud-native era, the integration of workflow systems with Kubernetes is gaining more and more popularity. To our knowledge, workflow systems employ scheduling algorithms that optimize task execution order of workflow to improve performance and execution efficiency. However, due to its inherent scheduling mechanism, Kubernetes does not execute containerized scheduling following the optimized task execution order of workflow amid migrating workflow systems to the Kubernetes platform. This inconsistency in task scheduling order seriously degrades the efficiency of workflow execution and brings numerous challenges to the containerized process of workflow systems on Kubernetes. In this paper, we propose a cloud-native workflow engine, also known as KubeAdaptor, a docking framework able to implement workflow containerization on Kubernetes, integrate workflow systems with Kubernetes, ensuring the consistency of task scheduling order. We introduce the design and architecture of the KubeAdaptor, elaborate on the functionality implementation and the event-trigger mechanism within the KubeAdaptor. Experimental results about four real-world workflows show that the KubeAdaptor ensures the consistency of the workflow systems and Kubernetes in the task scheduling order. Compared with the baseline Argo workflow engine, the KubeAdaptor achieves better performance in terms of the average execution time of task pod, average workflow lifecycle, and resource usage rate.

cs.DC↗

arXiv2022

Cloud-based computational model predictive control using a parallel multi-block ADMM approach

Heavy computational load for solving nonconvex problems for large-scale systems or systems with real-time demands at each sample step has been recognized as one of the reasons for preventing a wider application of nonlinear model predictive control (NMPC). To improve the real-time feasibility of NMPC with input nonlinearity, we devise an innovative scheme called cloud-based computational model predictive control (MPC) by using an elaborately designed parallel multi-block alternating direction method of multipliers (ADMM) algorithm. This novel parallel multi-block ADMM algorithm is tailored to tackle the computational issue of solving a nonconvex problem with nonlinear constraints.

math.OC↗

arXiv2022

RFLBAT: A Robust Federated Learning Algorithm against Backdoor Attack

Federated learning (FL) is a distributed machine learning paradigm where enormous scattered clients (e.g. mobile devices or IoT devices) collaboratively train a model under the orchestration of a central server (e.g. service provider), while keeping the training data decentralized. Unfortunately, FL is susceptible to a variety of attacks, including backdoor attack, which is made substantially worse in the presence of malicious attackers. Most of algorithms usually assume that the malicious at tackers no more than benign clients or the data distribution is independent identically distribution (IID). However, no one knows the number of malicious attackers and the data distribution is usually non identically distribution (Non-IID). In this paper, we propose RFLBAT which utilizes principal component analysis (PCA) technique and Kmeans clustering algorithm to defend against backdoor attack. Our algorithm RFLBAT does not bound the number of backdoored attackers and the data distribution, and requires no auxiliary information outside of the learning process. We conduct extensive experiments including a variety of backdoor attack types. Experimental results demonstrate that RFLBAT outperforms the existing state-of-the-art algorithms and is able to resist various backdoor attack scenarios including different number of attackers (DNA), different Non-IID scenarios (DNS), different number of clients (DNC) and distributed backdoor attack (DBA).

cs.CR↗

arXiv2021

Design and Implementation of Data-driven Predictive Cloud Control System

Nowadays, the rapid increases of the scale and complexity of the controlled plants bring new challenges such as computing power and storage for conventional control systems. Cloud computing is concerned as a powerful solution to handle the complex large-scale control missions using sufficient computing resources. However, the developed computing ability enables more complex devices and mass data being involved and thus the applications of model-based algorithms are constrained. Motivated by the above, we propose an original data-driven predictive cloud control system. To achieve the proposed system, a practical data-driven predictive cloud control platform rather than only a numerical simulator is established and together a cloud-edge communication scheme is developed. Finally, the verification of simulations and experiments as well as discussions demonstrate the effectiveness of the proposed system.

eess.SY↗

arXiv2021

Fast Subspace Identification Method Based on Containerised Cloud Workflow Processing System

Subspace identification (SID) has been widely used in system identification and control fields since it can estimate system models only relying on the input and output data by reliable numerical operations such as singular value decomposition (SVD). However, high-dimension Hankel matrices are involved to store these data and used to obtain the system models, which increases the computation amount of SID and leads SID not suitable for the large-scale or real-time identification tasks. In this paper, a novel fast SID method based on cloud workflow processing and container technology is proposed to accelerate the traditional algorithm. First, a workflow-based structure of SID is designed to match the distributed cloud environment, based on the computational feature of each calculation stage. Second, a containerised cloud workflow processing system is established to execute the logic- and data- dependent SID workflow mission based on Kubernetes system. Finally, the experiments show that the computation time is reduced by at most $91.6\%$ for large-scale SID mission and decreased to within 20 ms for the real-time mission parameter.

eess.SY↗

arXiv2021

DMS-GCN: Dynamic Mutiscale Spatiotemporal Graph Convolutional Networks for Human Motion Prediction

Human motion prediction is an important and challenging task in many computer vision application domains. Recent work concentrates on utilizing the timing processing ability of recurrent neural networks (RNNs) to achieve smooth and reliable results in short-term prediction. However, as evidenced by previous work, RNNs suffer from errors accumulation, leading to unreliable results. In this paper, we propose a simple feed-forward deep neural network for motion prediction, which takes into account temporal smoothness and spatial dependencies between human body joints. We design a Multi-scale Spatio-temporal graph convolutional networks (GCNs) to implicitly establish the Spatio-temporal dependence in the process of human movement, where different scales fused dynamically during training. The entire model is suitable for all actions and follows a framework of encoder-decoder. The encoder consists of temporal GCNs to capture motion features between frames and semi-autonomous learned spatial GCNs to extract spatial structure among joint trajectories. The decoder uses temporal convolution networks (TCNs) to maintain its extensive ability. Extensive experiments show that our approach outperforms SOTA methods on the datasets of Human3.6M and CMU Mocap while only requiring much lesser parameters. Code will be available at https://github.com/yzg9353/DMSGCN.

cs.CV↗

arXiv2021

TFDPM: Attack detection for cyber-physical systems with diffusion probabilistic models

With the development of AIoT, data-driven attack detection methods for cyber-physical systems (CPSs) have attracted lots of attention. However, existing methods usually adopt tractable distributions to approximate data distributions, which are not suitable for complex systems. Besides, the correlation of the data in different channels does not attract sufficient attention. To address these issues, we use energy-based generative models, which are less restrictive on functional forms of the data distribution. In addition, graph neural networks are used to explicitly model the correlation of the data in different channels. In the end, we propose TFDPM, a general framework for attack detection tasks in CPSs. It simultaneously extracts temporal pattern and feature pattern given the historical data. Then extract features are sent to a conditional diffusion probabilistic model. Predicted values can be obtained with the conditional generative network and attacks are detected based on the difference between predicted values and observed values. In addition, to realize real-time detection, a conditional noise scheduling network is proposed to accelerate the prediction process. Experimental results show that TFDPM outperforms existing state-of-the-art attack detection methods. The noise scheduling network increases the detection speed by three times.

cs.CR↗

arXiv2021

Partial Strong Structural Controllability

This paper introduces a new controllability notion, termed partial strong structural controllability (PSSC), on a structured system whose entries of system matrices are either fixed zero or indeterminate, which naturally extends the conventional strong structural controllability (SSC) and bridges the gap between structural controllability and SSC. Dividing the indeterminate entries into two categories, generic entries and unspecified entries, a system is PSSC, if for almost all values of the generic entries in the parameter space except for a set of measure zero, and any nonzero (complex) values of the unspecified entries, the corresponding system is controllable. We highlight that this notion generalizes the generic property embedded in the conventional structural controllability for single-input systems. We then give algebraic and (bipartite) graph-theoretic necessary and sufficient conditions for single-input systems to be PSSC. Conditions for multi-input systems are subsequently given for a special case. It is shown the established results can induce a new maximum matching based criterion for SSC over the system bipartite graph representations.

eess.SY↗

arXiv2021

Total Unimodularity and Strongly Polynomial Solvability of Constrained Minimum Input Selections for Structural Controllability: an LP-based Method

This paper investigates several cost-sparsity induced optimal input selection problems for structured systems. Given are an autonomous system and a prescribed set of input links, where each input link has a non-negative cost. The problems include selecting the minimum cost of input links, and selecting the input links with the smallest possible cost with a bound on their cardinality, all to ensure system structural controllability. Current studies show that in the dedicated input case (i.e., each input can actuate only a state variable), the former problem is polynomially solvable by some graph-theoretic algorithms, while the general nontrivial constrained case is largely unexploited. We show these problems can be formulated as equivalent integer linear programming (ILP) problems. Subject to a certain condition on the prescribed input configurations that contains the dedicated input one as a special case, we demonstrate that the constraint matrices of these ILPs are totally unimodular. This property allows us to solve those ILPs efficiently simply via their linear programming (LP) relaxations, leading to a unifying algebraic method for these problems with polynomial time complexity. It is further shown those problems could be solved in strongly polynomial time, independent of the size of the costs and cardinality bounds. Finally, an example is provided to illustrate the power of the proposed method.

eess.SY↗

arXiv2021

AdaL: Adaptive Gradient Transformation Contributes to Convergences and Generalizations

Adaptive optimization methods have been widely used in deep learning. They scale the learning rates adaptively according to the past gradient, which has been shown to be effective to accelerate the convergence. However, they suffer from poor generalization performance compared with SGD. Recent studies point that smoothing exponential gradient noise leads to generalization degeneration phenomenon. Inspired by this, we propose AdaL, with a transformation on the original gradient. AdaL accelerates the convergence by amplifying the gradient in the early stage, as well as dampens the oscillation and stabilizes the optimization by shrinking the gradient later. Such modification alleviates the smoothness of gradient noise, which produces better generalization performance. We have theoretically proved the convergence of AdaL and demonstrated its effectiveness on several benchmarks.

cs.LG↗

arXiv2021

ScoreGrad: Multivariate Probabilistic Time Series Forecasting with Continuous Energy-based Generative Models

Multivariate time series prediction has attracted a lot of attention because of its wide applications such as intelligence transportation, AIOps. Generative models have achieved impressive results in time series modeling because they can model data distribution and take noise into consideration. However, many existing works can not be widely used because of the constraints of functional form of generative models or the sensitivity to hyperparameters. In this paper, we propose ScoreGrad, a multivariate probabilistic time series forecasting framework based on continuous energy-based generative models. ScoreGrad is composed of time series feature extraction module and conditional stochastic differential equation based score matching module. The prediction can be achieved by iteratively solving reverse-time SDE. To the best of our knowledge, ScoreGrad is the first continuous energy based generative model used for time series forecasting. Furthermore, ScoreGrad achieves state-of-the-art results on six real-world datasets. The impact of hyperparameters and sampler types on the performance are also explored. Code is available at https://github.com/yantijin/ScoreGradPred.

cs.LG↗

arXiv2021

PTSC: a New Definition for Structural Controllability under Numerical Perturbations

This paper proposes a novel notion for structural controllability under structured numerical perturbations, namely the perturbation-tolerant structural controllability (PTSC), on a single-input structured system whose entries can be classified into three categories: fixed zero entries, unknown generic entries whose values are fixed but unknown, and perturbed entries that can take arbitrary complex values. Such a system is PTSC if, for almost all values of the unknown generic entries in the parameter space, the corresponding controllable system realizations can preserve controllability under arbitrary complex-valued perturbations with their structure prescribed by the perturbed entries. This new notion can characterize the generic property in controllability preservation under structured numerical perturbations. We give a necessary and sufficient condition for a single-input system to be PTSC, whose verification has polynomial time complexity. Our results can serve as some feasibility conditions for the conventional structured controllability radius problems from a generic view.

eess.SY↗

arXiv2021

Observability Robustness under Sensor Failures: a Computational Perspective

This paper studies the robustness of observability of a linear time-invariant system under sensor failures from a computational perspective. To be precise, the problem of determining the minimum number of sensors whose removal can destroy system observability, as well as the problem of determining the minimum number of state variables that need to be prevented from being directly measured by the existing sensors to destroy observability, is investigated. The first one is closely related to the ability of unique state reconstruction of a system under adversarial sensor attacks, and the dual of both problems are in the opposite direction of the well-studied minimal controllability problems. It is proven that all these problems are NP-hard, both for a numerical system and a structured system, even restricted to some special cases. It is also shown that the first problems both for a numerical system and a structured one share a cardinality-constrained submodular minimization structure, for which there is no known constant or logarithmic factor approximation in general. On the other hand, for the first two problems, under a reasonable assumption often met by practical systems, that the eigenvalue geometric multiplicities of the numerical systems or the matching deficiencies of the structured systems are bounded by a constant, by levering the rank-one update property of the involved rank function, it is possible to obtain the corresponding optimal solutions by traversing a subset of the feasible solutions. We show such a method has polynomial time complexity in the system dimensions and the number of sensors.

math.OC↗

arXiv2021

Fixed-Time Cooperative Behavioral Control for Networked Autonomous Agents with Second-Order Nonlinear Dynamics

In this paper, we investigate the fixed-time behavioral control problem for a team of second-order nonlinear agents, aiming to achieve a desired formation with collision/obstacle~avoidance. In the proposed approach, the two behaviors(tasks) for each agent are prioritized and integrated via the framework of the null-space-based behavioral projection, leading to a desired merged velocity that guarantees the fixed-time convergence of task errors. To track this desired velocity, we design a fixed-time sliding mode controller for each agent with state-independent adaptive gains, which provides a fixed-time convergence of the tracking error. The control scheme is implemented in a distributed manner, where each agent only acquires information from its neighbors in the network. Moreover, we adopt an online learning algorithm to improve the robustness of the closed system with respect to uncertainties/disturbances. Finally, simulation results are provided to show the effectiveness of the proposed approach.

math.OC↗

arXiv2021

Structural Controllability of Networked Relative Coupling Systems

This paper studies the controllability of networked relative coupling systems (NRCSs), in which subsystems are of fixed high-order linear dynamics and coupled through relative variables depending on their neighbors, from a structural perspective. The purpose is to explore conditions for subsystem dynamics and network topologies under which for almost all weights of the subsystem interaction links, the corresponding numerical NRCSs are controllable, which is called structurally controllable. Three types of subsystem interaction fashions are considered: 1) each subsystem is single-input-single-output (SISO), 2) each subsystem is multiple-input-multiple-output (MIMO), and the weights for all channels between two subsystems are identical, and 3) each subsystem is MIMO, but different channels between two subsystems can be weighted differently. {We show that all parameter-dependent modes of the NRCSs are generically controllable under some necessary connectivity conditions. We then derive necessary and/or sufficient conditions for structural controllability depending on subsystem dynamics and network topologies' connectivity in a decoupled form for all the three interaction fashions.} We also extend our results to handle certain subsystem heterogeneities and demonstrate their direct applications on some practical systems, including the mass-spring-damper system and the power network.

eess.SY↗