检索结果-内蒙古大学图书馆

learning-Based Adaptive Optimal control of Linear Time-Delay systems: A Policy Iteration Approach

ieee TRANSACTIONS ON AUTOMATIC control 2024年第1期69卷 629-636页

作者： Cui, Leilei Pang, Bo Jiang, Zhong-Ping NYU Tandon Sch Engn Dept Elect & Comp Engn Control & Networks Lab Brooklyn NY 11201 USA

This article studies the adaptive optimal control problem for a class of linear time-delay systems described by delay differential equations. A crucial strategy is to take advantage of recent developments in reinforcement learning and adaptive dynamic programming and develop novel methods to learn adaptive optimal controllers from finite samples of input and state data. In this article, the data-driven policy iteration (PI) is proposed to solve the infinite-dimensional algebraic Riccati equation iteratively in the absence of exact model knowledge. Interestingly, the proposed recursive PI algorithm is new in the present context of continuous-time time-delay systems, even when the model knowledge is assumed known. The efficacy of the proposed learning-based control methods is validated by means of practical applications arising from metal cutting and autonomous driving.

关键词： Optimal control Aerospace electronics Mathematical models Heuristic algorithms Delays Trajectory Stability criteria Adaptive dynamic programming (ADP) linear time-delay systems optimal control policy iteration (PI)

来源：评论

学校读者我要写书评

暂无评论

data-Based Collaborative learning for Multiagent systems Under Distributed Denial-of-Service Attacks

引用

ieee TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL systems 2024年第1期16卷 75-85页

作者： Xu, Yong Wu, Zheng-Guang Beijing Inst Technol Sch Automat Beijing 100081 Peoples R China Zhejiang Univ Inst Cyber Syst & Control Hangzhou 310027 Peoples R China Zhejiang Normal Univ Coll Math & Comp Sci Jinhua 321004 Zhejiang Peoples R China

This article employs a reinforcement learning (RL) technique to investigate the distributed output tracking control of heterogeneous multiagent systems (MASs) under multiple Denial-of-Service (DoS) attacks. Different from existing results where the dynamic of the leader is known for partial or all agents, the leader's system matrix is completely unknown for each follower in this article. To learn the leader system matrix, a data-based learning mechanism is first proposed using the idea of the data-driven method. Then, under the data-based learning mechanism, a resilient predictor subject to multiple DoS attacks is exploited to provide the estimation of the leader's state for each agent, where adversaries attack different communication links independently. Moreover, a resilient dynamic output feedback controller is proposed to solve the output tracking control problem based on the output regulation theory. To consider the transient responses of agents, an RL-based dynamic output feedback controller is developed to realize the optimal output tracking control by solving discounted algebraic Riccati equations (AREs) in both offline and online ways. Theoretical analysis shows that the secure output tracking control of MASs can be achieved under the proposed data-based resilient learning control algorithm. Finally, a numerical example is provided to verify the effectiveness of theoretical analysis.

关键词： Denial-of-Service (DoS) attacks multiagent systems (MASs) reinforcement learning (RL) tracking control

来源：评论

学校读者我要写书评

暂无评论

Event-triggered Adaptive Cooperative control for Nonstrict-Feedback Nonlinear Multiagent systems 12

Event-triggered Adaptive Cooperative Control for Nonstrict-F...

引用

ieee 12th data driven control and learning systems conference (DDCLS)

作者： Nie, Liduo Wang, Xin Southwest Univ Coll Elect & Informat Engn Chongqing 400715 Peoples R China

ISBN: (纸本)9798350321050

This study examines the leader-follower consistency issue in a particular class of multiagent systems and provides an event-triggered adaptive control approach. The event-triggered mechanism designed in this paper dramatically reduces the communication load and data transmission, which can better serve practical production applications. It is shown that the suggested control method prevents Zeno behavior and ensures that all signals in a closed-loop system are bounded. The effectiveness of the suggested control method is confirmed by the simulation results.

关键词： Adaptive control event-triggered method consistency tracking nonlinear multiagent neural networks

来源：评论

学校读者我要写书评

暂无评论

Efficient Self-learning Tracking control for Switched systems: A Triggered-learning Model Predictive control Method

引用

ieee TRANSACTIONS ON CIRCUITS AND systems II-EXPRESS BRIEFS 2025年第5期72卷 748-752页

作者： Dong, Tianxiang Qi, Yiwen Guo, Shitong Fuzhou Univ Coll Elect Engn & Automat Fuzhou 350108 Peoples R China Shenyang Aerosp Univ Sch Automat Shenyang 110136 Peoples R China

Existing model predictive control (MPC) methods lack online learning capability in complex environments. Reinforcement learning (RL) requires a lot of data and computing resources to obtain optimal control. This brief uses efficient self-learning to solve this problem. "Efficient" refers to the use of triggered-learning mechanism (TLM) to manage computing resources on demand. This brief proposes a triggered-learning model predictive control (TL-MPC) method for switched systems. The proposed TL-MPC endows MPC with learning capabilities through the TLM. TLM includes a Deep Deterministic Policy Gradient (DDPG) based control incremental self-learning tuning strategy and a performance-driven event-triggering strategy. The first strategy is to give the MPC controller a control increment to optimize control effect. The second strategy is to realize the on-demand learning and reduce computational resources by comparing two cost functions that characterize the system performance. In addition, the stability of switched systems under TL-MPC is analyzed using the Lyapunov function and the average dwell time technique. Finally, the effectiveness of the proposed method is verified by simulation.

关键词： Model predictive control self-learning tuning triggered learning reinforcement learning switched systems Model predictive control self-learning tuning triggered learning reinforcement learning switched systems

来源：评论

学校读者我要写书评

暂无评论

Adaptive Voltage control of Single-Inductor 3x Multilevel Converters Interfaced DC Microgrids Using Multi-Agent Approximate Q-learning

引用

ieee ACCESS 2024年 12卷 114295-114303页

作者： Abdulkader, Rasheed M. Salem, Mohamed Senjyu, Tomonobu Imam Mohammad Ibn Saud Islamic Univ IMSIU Dept Elect Engn Riyadh 11432 Saudi Arabia Univ Sains Malaysia USM Sch Elect & Elect Engn Nibong Tebal 14300 Penang Malaysia Libyan Author Sci Res Tripoli Libya Univ Ryukyus Fac Engn Nishihara Nakagami Okinaw 9030213 Japan

Single-inductor 3x multilevel boost (SI-3xMLB) converters, recognized for their potential to supply multiple output voltage levels, are gaining much attention in microgrids due to their capability to diverse sub-systems with changing voltage requirements. However, some loads, such as constant power loads (CPLs), threaten the stability of SI-3xMLB converters due to their negative impedance properties. Thus, advanced regulation mechanisms are necessitated to reduce the destabilization effect of such loads in the microgrids. In response to the issue, in this paper, an adaptive data-driven controller with an observer is designed to mitigate the effect of non-ideal CPLs in dc/dc SI-3xMLB converters. The suggested data-driven controller can stabilize the system outputs using the input-output (I/O). In particular, the multi-agent fuzzy approximate Q-learning (MAFQ-learning) is employed to adjust the coefficients embedded in the data-driven controller dynamically. To do this, a reward function is defined according to the voltage control requirements of the dc/dc SI-3xMLB converter. By interacting the agent of MAFQ-learning with the environment, tunable control coefficients are adaptively adjusted. This process finds optimal policy, allowing the controller to dynamically respond to the effects of CPLs. The real-time responses based on the Arduino platform revealed the superior performance of the suggested controller to stabilize the dc/dc SI-3xMLB boost converter feeding CPL than the discrete time-averaged model predictive control (DTA-MPC), the optimal PI control based on state-action-reward-state-action (SARSA) technique.

关键词： Voltage control Microgrids Switches Q-learning Real-time systems Observers Batteries DC machines Multi-agent systems Predictive control Multiple DC microgrids multi-agent systems fuzzy approximate Q-learning real-time control discrete time-averaged model predictive control (DTA-MPC)

来源：评论

学校读者我要写书评

暂无评论

Optimal Group Consensus of Multiagent systems in Graphical Games Using Reinforcement learning

引用

ieee TRANSACTIONS ON systems MAN CYBERNETICS-systems 2025年第3期55卷 2343-2353页

作者： Wang, Yuhan Wang, Zhuping Zhang, Hao Yan, Huaicheng Tongji Univ Shanghai Res Inst Intelligent Autonomous Syst Shanghai 201210 Peoples R China Frontiers Sci Ctr Intelligent Autonomous Syst Natl Key Lab Autonomous Intelligent Unmanned Syst Minist Educ Shanghai 201210 Peoples R China Tongji Univ Coll Elect & Informat Engn Dept Control Sci & Engn Shanghai 201804 Peoples R China East China Univ Sci & Technol Sch Informat Sci & Engn Shanghai 200237 Peoples R China

This article investigates the optimal group consensus problem (GCP) in multiagent systems (MASs). To address this problem, a novel distributed optimal control policy is designed in the framework of off-policy reinforcement learning (RL). First, a framework for multiagent differential graphical games is formulated. Second, a min-max strategy is then introduced to ensure the achievement of group consensus through a data-driven value iteration (VI) approach. Finally, the presented consensus control policy is extended to address the group formation tracking problem (GFTP) of nonholonomic mobile robots, with a numerical example to illustrate the efficacy of the proposed results. Compared with the existing literature, this article has the following contributions: 1) A group of agents are decomposed into multiple subgroups to accomplish different consensus objectives;2) the prior knowledge of agents' dynamics and initial stabilizing control gains can be eliminated;and 3) the performance index function (PIF) for each agent is designed to integrate not only its individual control policy but also that of its neighboring agents.

关键词： Games Vectors Symmetric matrices Consensus control Reinforcement learning Optimal control Multi-agent systems Electronic mail Differential games Collaboration data-driven control differential graphical game group consensus reinforcement learning (RL) value iteration (VI)

来源：评论

学校读者我要写书评

暂无评论

Inverse Reinforcement learning for Discrete-Time systems With data Dropouts

引用

ieee TRANSACTIONS ON CYBERNETICS 2025年第4期55卷 1744-1757页

作者： Fan, Jialu Shi, Pengfei Xue, Wenqian Lian, Bosen Cui, Yunfang Lewis, Frank L. Northeastern Univ State Key Lab Synthet Automat Proc Ind & Int Joint Shenyang 110819 Peoples R China Univ Florida Elect & Comp Engn Dept Gainesville FL 32611 USA Auburn Univ Elect & Comp Engn Dept Auburn AL 36849 USA Univ Texas Arlington UTA Res Inst Ft Worth TX 76118 USA

This article proposes inverse reinforcement learning (IRL) algorithms for tracking control of linear networked control systems under random state dropouts during wireless transmission. The controlled system aims to track the optimal trajectory of a target system, despite the cost function governing the target's behaviors being unknown. The problem is complicated by random state dropouts occurring in two crucial scenarios: 1) the reception of the target's state and 2) feedback of the controlled system's states. Our approach enables the controlled system to infer the target's cost function and optimal control policy, thereby facilitating effective tracking. Specifically, we develop a model-based IRL algorithm that integrates the Smith predictor for state estimation. Then, we advance a state-dropout-aware inverse Q-learning algorithm that uses solely accessible system data, eliminating the need for system models. The theoretical validity of the proposed algorithms is rigorously established, and their practical effectiveness is validated through numerical simulations.

关键词： Cost function control systems Optimal control Target tracking Trajectory Prediction algorithms Wireless networks Stability analysis Fans Electronic mail data dropouts data-driven tracking control inverse reinforcement learning (IRL) reinforcement learning (RL)

来源：评论

学校读者我要写书评

暂无评论

Model-Based and data-driven Stochastic Hybrid control for Rumor Propagation in Dual-Layer Network

引用

ieee TRANSACTIONS ON COMPUTATIONAL SOCIAL systems 2025年第2期12卷 777-791页

作者： Zhong, Xiaojing Luo, Chaolong Deng, Feiqi Liu, Guiyun Li, Chunlei Hu, Zhipei Guangzhou Univ Sch Mech & Elect Engn Guangzhou 510006 Peoples R China South China Univ Technol Sch Automat Guangzhou 510641 Peoples R China Guangzhou Univ Inst New Media & Social Dev Huangpu Grad Sch Guangzhou 510006 Peoples R China

Toward exploring the positive impact of media debunking and random blocking on the spread of rumors, we discuss a stochastic hybrid control strategy that combines an individual and media debunking method, a continuous stochastic blocking method, and an impulse interruption method. Using stochastic analysis, the almost sure exponential stability of the controlled system is analyzed, along with the expression of control intensities. To balance rumor suppression, minimize control costs, and enhance the generality of control, a data-driven machine learning (ML) approach is developed to provide suboptimal control solutions. Numerical simulations based on two real-case datasets are carried out to validate the theoretical results and evaluate the potential impact of the model-based, data-driven stochastic hybrid control strategy.

关键词： data-driven ML control algorithm dual-layer network model rumor debunking method stochastic blocking method stochastic hybrid control data-driven ML control algorithm dual-layer network model rumor debunking method stochastic blocking method stochastic hybrid control

来源：评论

学校读者我要写书评

暂无评论

Robust and Kernelized data-Enabled Predictive control for Nonlinear systems

引用

ieee TRANSACTIONS ON control systems TECHNOLOGY 2024年第2期32卷 611-624页

作者： Huang, Linbin Lygeros, John Dorfler, Florian Swiss Fed Inst Technol Dept Informat Technol & Elect Engn CH-8092 Zurich Switzerland

This article presents a robust and kernelized data-enabled predictive control (RoKDeePC) algorithm to perform model-free optimal control for nonlinear systems using only input and output data. The algorithm combines robust predictive control and a multistep predictor of nonlinear systems obtained from regularized kernel methods. The latter is based on implicitly learning the nonlinear behavior of the system via the representer theorem. Instead of seeking a model and then performing control design, our method goes directly from data to control. This allows us to robustify the control inputs against the uncertainties in data by considering a min-max optimization problem to calculate the robust and optimal control sequence. We show that by incorporating an appropriate uncertainty set, this min-max problem can be reformulated as a nonconvex but structured minimization problem. By exploiting its structure, we present a projected gradient descent algorithm to effectively solve this problem. Finally, we test the RoKDeePC method on two nonlinear example systems-one academic case study and a grid-forming converter feeding a nonlinear load-and compare it with some existing nonlinear data-driven predictive control methods.

关键词： Trajectory Kernel Predictive control Nonlinear systems Behavioral sciences Uncertainty Optimization data-driven control kernel methods nonlinear control predictive control robust optimization

来源：评论

学校读者我要写书评

暂无评论

Deep Meta-Reinforcement learning-Based data-driven Active Fault Tolerance Load Frequency control for Islanded Microgrids Considering Internet of Things

引用

ieee INTERNET OF THINGS JOURNAL 2024年第6期11卷 10295-10303页

作者： Li, Jiawen Cheng, Yuanyuan Shanghai Univ Elect Power Sch Elect & Informat Engn Shanghai 201306 Peoples R China Shanghai Jiao Tong Univ Sch Elect Informat & Elect Engn Dept Elect Engn Shanghai 200240 Peoples R China

This article proposes a data-driven active fault tolerance load frequency control (DDAFT-LFC) method for island microgrids. It is demonstrated that DDAFT-LFC can effectively prevent frequency control loss caused by sudden off-grid faults affecting regulating units and emergency faults in microgrids, as well as reduce the total generation cost and improve the frequency stability of an island microgrid relying on a high renewable energy input. The method adopts an active fault tolerance strategy which can adapt to the complex stochastic environment, thus improving the robustness of the LFC strategy and achieving multiobjective optimization of dynamic performance and economic efficiency via regulation of the controller's control strategy. In order to realize active fault-tolerance, this article proposes a deep meta-deterministic policy gradient (DMDPG) algorithm, which employs a meta-reinforcement learning method to help the agent to perform multitask collaborative learning in order to adapt to changes in microgrid environment parameters caused by changes in the unit combinations. The method is validated in an experiment of the island microgrid of the China Southern Power Grid (CSG).

关键词： Microgrids Frequency control Costs Fault tolerant systems Fault tolerance Optimization Power system stability data-driven active fault tolerance load frequency control (DDAFT-LFC) deep meta-deterministic policy gradients (DMDPGs) islanded microgrids load frequency control (LFC) multiobjective optimal control

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：