检索结果-内蒙古大学图书馆

Mixture of Experts for Network Optimization: A Large Language Model-enabled Approach

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Du, Hongyang Liu, Guangyuan Lin, Yijing Niyato, Dusit Kang, Jiawen Xiong, Zehui Kim, Dong In The School of Computer Science and Engineering Nanyang Technological University Singapore639798 Singapore The State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications Beijing100876 China The School of Automation Guangdong University of Technology Key Laboratory of Intelligent Information Processing and System Integration of IoT Ministry of Education Guangzhou510006 China Guangdong-HongKong-Macao Joint Laboratory for Smart Discrete Manufacturing Guangzhou510006 China The Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore487372 Singapore The Department of Electrical and Computer Engineering Sungkyunkwan University Suwon16419 Korea Republic of

Optimizing various wireless user tasks poses a significant challenge for networking systems because of the expanding range of user requirements. Despite advancements in Deep Reinforcement Learning (DRL), the need for customized optimization tasks for individual users complicates developing and applying numerous DRL models, leading to substantial computation resource and energy consumption and can lead to inconsistent outcomes. To address this issue, we propose a novel approach utilizing a Mixture of Experts (MoE) framework, augmented with Large Language Models (LLMs), to analyze user objectives and constraints effectively, select specialized DRL experts, and weigh each decision from the participating experts. Specifically, we develop a gate network to oversee the expert models, allowing a collective of experts to tackle a wide array of new tasks. Furthermore, we innovatively substitute the traditional gate network with an LLM, leveraging its advanced reasoning capabilities to manage expert model selection for joint decisions. Our proposed method reduces the need to train new DRL models for each unique optimization problem, decreasing energy consumption and AI model implementation costs. The LLM-enabled MoE approach is validated through a general maze navigation task and a specific network service provider utility maximization task, demonstrating its effectiveness and practical applicability in optimizing complex networking systems. © 2024, CC BY.

关键词： Reinforcement learning

End-to-end 2D-3D Registration between Image and LiDAR Point Cloud for Vehicle Localization

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wang, Guangming Zheng, Yu Guo, Yanfeng Liu, Zhe Zhu, Yixiang Burgard, Wolfram Wang, Hesheng Department of Automation Shanghai Jiao Tong University Shanghai200240 China Key Laboratory of System Control and Information Processing Ministry of Education of China China Department of Artificial Intelligence Shanghai Jiao Tong University Shanghai200240 China Electrical and Computer Engineering University of California Los Angeles United States Institute of Artificial Intelligence Shanghai Jiao Tong University Shanghai200240 China Department of Electrical Engineering Shanghai Jiao Tong University Shanghai200240 China Department of Engineering University of Technology Nuremberg Germany

Robot localization using a previously built map is essential for a variety of tasks including highly accurate navigation and mobile manipulation. A popular approach to robot localization is based on image-to-point cloud registration, which combines illumination-invariant LiDAR-based mapping with economical image-based localization. However, the recent works for image-to-point cloud registration either divide the registration into separate modules or project the point cloud to the depth image to register the RGB and depth images. In this paper, we present I2PNet, a novel end-to-end 2D-3D registration network. I2PNet directly registers the raw 3D point cloud with the 2D RGB image using differential modules with a unique target. The 2D-3D cost volume module for differential 2D-3D association is proposed to bridge feature extraction and pose regression. 2D-3D cost volume module implicitly constructs the soft point-to-pixel correspondence on the intrinsic-independent normalized plane of the pinhole camera model. Moreover, we introduce an outlier mask prediction module to filter the outliers in the 2D-3D association before pose regression. Furthermore, we propose the coarse-to-fine 2D-3D registration architecture to increase localization accuracy. We conduct extensive localization experiments on the KITTI Odometry and nuScenes datasets. The results demonstrate that I2PNet outperforms the state-of-the-art by a large margin. In addition, I2PNet has a higher efficiency than the previous works and can perform the localization in real-time. Moreover, we extend the application of I2PNet to the camera-LiDAR online calibration and demonstrate that I2PNet outperforms recent approaches on the online calibration task. Copyright © 2023, The Authors. All rights reserved.

关键词： Calibration

Simultaneously Calibration of Multi Hand-Eye Robot system Based on Graph

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhou, Zishun Ma, Liping Liu, Xilong Cao, Zhiqiang Yu, Junzhi The Institute of Automation Chinese Academy of Sciences Beijing100190 China The College of Electrical Engineering and Computer Science Australian National University Canberra2601 Australia The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China The School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China The State Key Laboratory for Turbulence and Complex System Department of Advanced Manufacturing and Robotics BIC-ESAT College of Engineering Peking University Beijing100871 China

Precise calibration is the basis for the vision-guided robot system to achieve high-precision operations. systems with multiple eyes (cameras) and multiple hands (robots) are particularly sensitive to calibration errors, such as micro-assembly systems. Most existing methods focus on the calibration of a single unit of the whole system, such as poses between hand and eye, or between two hands. These methods can be used to determine the relative pose between each unit, but the serialized incremental calibration strategy cannot avoid the problem of error accumulation in a large-scale system. Instead of focusing on a single unit, this paper models the multi-eye and multi-hand system calibration problem as a graph and proposes a method based on the minimum spanning tree and graph optimization. This method can automatically plan the serialized optimal calibration strategy in accordance with the system settings to get coarse calibration results initially. Then, with these initial values, the closed-loop constraints are introduced to carry out global optimization. Simulation experiments demonstrate the performance of the proposed algorithm under different noises and various hand-eye configurations. In addition, experiments on real robot systems are presented to further verify the proposed method. © 2023, CC BY-SA.

关键词： Multipurpose robots

Relative Error-based Time-limited H2 Model Order Reduction via Oblique Projection

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zulfiqar, Umair Du, Xin Song, Qiuyan Xiao, Zhi-Hua Sreeram, Victor School of Mechatronic Engineering and Automation Shanghai University Shanghai200444 China Shanghai Key Laboratory of Power Station Automation Technology Shanghai University Shanghai200444 China School of Information and Mathematics Yangtze University Hubei Jingzhou434023 China Department of Electrical Electronic and Computer Engineering The University of Western Australia Perth6009 Australia

In time-limited model order reduction, a reduced-order approximation of the original high-order model is obtained that accurately approximates the original model within the desired limited time interval. Accuracy outside that time interval is not that important. The error incurred when a reduced-order model is used as a surrogate for the original model can be quantified in absolute or relative terms to access the performance of the model reduction algorithm. The relative error is generally more meaningful than an absolute error because if the original and reduced systems’ responses are of small magnitude, the absolute error is small in magnitude as well. However, this does not necessarily mean that the reduced model is accurate. The relative error in such scenarios is useful and meaningful as it quantifies percentage error irrespective of the magnitude of the system’s response. In this paper, the necessary conditions for a local optimum of the time-limited H2 norm of the relative error system are derived. Inspired by these conditions, an oblique projection algorithm is proposed that ensures small H2-norm relative error within the desired time interval. Unlike the existing relative error-based model reduction algorithms, the proposed algorithm does not require solutions of large-scale Lyapunov and Riccati equations. The proposed algorithm is compared with time-limited balanced truncation, time-limited balanced stochastic truncation, and time-limited iterative Rational Krylov algorithm. Numerical results confirm the superiority of the proposed algorithm over these existing algorithms. Copyright © 2022, The Authors. All rights reserved.

关键词： Riccati equations

Frequency-limited H2 Model Order Reduction Based on Relative Error

学校读者我要写书评

暂无评论

arXiv 2022年

Frequency-limited model order reduction aims to approximate a high-order model with a reduced-order model that maintains high fidelity within a specific frequency range. Beyond this range, a decrease in accuracy is acceptable due to the nature of the problem. The quality of the reduced-order model is typically evaluated using absolute or relative measures of approximation error. Relative error, which represents the percentage error, becomes particularly relevant when reducing a plant model for the purpose of designing a reduced-order controller. This paper derives the necessary conditions for achieving a local optimum of the frequency-limited H2 norm for the relative error system. Based on these optimality conditions, an oblique projection algorithm is proposed to ensure a small relative error within the desired frequency interval. Unlike existing algorithms, the proposed approach does not necessitate solving large-scale Lyapunov and Ricatti equations. Instead, the proposed algorithm relies on solving sparse-dense Sylvester equations, which typically emerge in the majority of H2 model order reduction algorithms, but can be efficiently solved. To evaluate the performance of the proposed algorithm, a comparison is conducted with three existing techniques: frequency-limited balanced truncation, frequency-limited balanced stochastic truncation, and frequency-limited iterative Rational Krylov algorithm. The comparative analysis focuses on designing reduced-order controllers for high-order plants. Numerical results confirm that the reduced-order controllers obtained using the proposed algorithm ensure superior robust closed-loop stability. Copyright © 2022, The Authors. All rights reserved.

关键词： Stochastic systems

Submodularity-based False Data Injection Attack Scheme in Multi-agent Dynamical systems

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Luo, Xiaoyu Zhao, Chengcheng Fang, Chongrong He, Jianping The Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China The State Key Laboratory of Industrial Control Technology Institute of Cyberspace Research Zhejiang University China The Department of Electrical and Computer Engineering University of Victoria BC Canada

Consensus in multi-agent dynamical systems is prone to be sabotaged by the adversary, which has attracted much attention due to its key role in broad applications. In this paper, we study a new false data injection (FDI) attack design problem, where the adversary with limited capability aims to select a subset of agents and manipulate their local multi-dimensional states to maximize the consensus convergence error. We first formulate the FDI attack design problem as a combinatorial optimization problem and prove it is NP-hard. Then, based on the submodularity optimization theory, we show the convergence error is a submodular function of the set of the compromised agents, which satisfies the property of diminishing marginal returns. In other words, the benefit of adding an extra agent to the compromised set decreases as that set becomes larger. With this property, we exploit the greedy scheme to find the optimal compromised agent set that can produce the maximum convergence error when adding one extra agent to that set each time. Thus, the FDI attack set selection algorithms are developed to obtain the near-optimal subset of the compromised agents. Furthermore, we derive the analytical suboptimality bounds and the worst-case running time under the proposed algorithms. Extensive simulation results are conducted to show the effectiveness of the proposed algorithm. Copyright © 2022, The Authors. All rights reserved.

关键词： Dynamical systems

Online distribution system state estimation via stochastic gradient algorithm

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Huang, Jianqiao Zhou, Xinyang Cui, Bai Department of Electrical and Computer Engineering Illinois Institute of Technology Chicago United States Power System Engineering Department National Renewable Energy Laboratory GoldenCO80401 United States

Distribution network operation is becoming more challenging because of the growing integration of intermittent and volatile distributed energy resources (DERs). This motivates the development of new distribution system state estimation (DSSE) paradigms that can operate at fast timescale based on real-time data stream of asynchronous measurements enabled by modern information and communications technology. To solve the real-time DSSE with asynchronous measurements effectively and accurately, this paper formulates a weighted least squares DSSE problem and proposes an online stochastic gradient algorithm to solve it. The performance of the proposed scheme is analytically guaranteed and is numerically corroborated with realistic data on IEEE-123 bus feeder. Copyright © 2021, The Authors. All rights reserved.

关键词： Energy resources

Dominant Mode Identification and Influence Mechanism Investigation of Frequency Oscillations as Affected by Automatic Generation Control

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Zhou, Tao Chen, Liufu Bu, Siqi Ye, Hua Sun, Jie School of Automation Nanjing University of Science and Technology Nanjing China Department of Electrical Engineering The Hong Kong Polytechnic University Hong Kong Special Administrative Region Hong Kong Key Laboratory of Power System Intelligent Dispatch and Control Ministry of Education Shandong University Jinan China

Several frequency oscillation events have recently been observed in practical power grids, which are strongly related with dynamic process of AGC (automatic generation control). To investigate the dynamic performance and oscillation mechanism of frequency oscillations, this paper establishes the state-space model of multi-area AGC systems containing different kinds of generator units and time-scale dynamics. Without distinguishing AGC and PFR (primary frequency regulation) modes, Homotopy method is applied to identify the dominant mode and thus analyze the key influencing factors of frequency oscillations affected by AGC dynamics. The method can clearly establish the congruent relationship between eigenvalues and state variables and is more rapid and intuitive than participation factors in this scene. Finally, simulations are performed in single-area as well as multi-area system based on real power grid data to demonstrate the proposed model and method. And relevant parameter influence mechanism and oscillation performances are investigated for AGC system oscillations. © 2022, The Authors. All rights reserved.

关键词： Time delay

Towards Energy-Efficiency: Integrating MATD3 Reinforcement Learning Method for Computational Offloading in RIS-Aided UAV-MEC Environments

学校读者我要写书评

暂无评论

IEEE Internet of Things Journal 2025年

作者： Wu, Liangshun Zhang, Cong Zhang, Bin Du, Jianbo Qu, Junsuo Key Laboratory of Embedded System and Service Computing Tongji University Ministry of Education Shanghai201804 China Shanghai Key Laboratory of Trustworthy Computing East China Normal University Shanghai201210 China School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai200240 China Xi'an Key Laboratory of Advanced Control and Intelligent Process School of Automation Xi'an University of Posts & Telecommunications Xi'an710061 China Xinjiang University of Political Science and Law Tumushuke832003 China School of Remote Sensing and Information Engineering Wuhan University Wuhan430079 China Department of Computer City University of Hong Kong 999077 Hong Kong School of Communications and Information Engineering Xi'an University of Posts & Telecommunications Xi'an710061 China

With the proliferation of IoT devices, there is an escalating demand for enhanced computing and communication capabilities. Mobile Edge Computing (MEC) addresses this need by relocating computing resources to the network edge, thereby delivering swifter and more efficient services. This paper introduces a computation offloading and energy consumption optimization framework that leverages Reconfigurable Intelligent Surfaces (RIS), Unmanned Aerial Vehicles (UAVs), and MEC. The scheme aims to maximize energy efficiency through the optimization of task allocation, RIS phase shifts, and UAV trajectories. By employing the Multi-Agent Twin Delayed Deep Deterministic Policy Gradient (MATD3) reinforcement learning algorithm, the paper further refines UAV trajectories and RIS configurations. The simulation results indicate that the proposed method surpasses the traditional Concave-Convex Procedure (CCCP) algorithm in both UAV trajectory control and RIS configuration, demonstrating quicker convergence and enhanced stability. The method proves to be adaptable to diverse environments and tasks, showcasing notable benefits in RIS-assisted interference suppression, particularly with large RIS, thereby enhancing UAV data reception rates. Additionally, MATD3 exhibits faster and smoother convergence for extended task durations and smaller RIS scenarios. Simulation results reveal that UAVs tend to move closer to RIS, with energy efficiency falling as IoT tasks increase, affirming the proposed algorithm's high energy efficiency and effectiveness. © 2025 IEEE.

关键词： Unmanned aerial vehicles (UAV)