High-speed programmable data planes (e.g., P4 switches, smartNICs) have enabled fast, accurate, data-driven network management systems. Such systems leverage the packet-processing capabilities of the data plane and im...
Electrical stimulation has been an emerging technique for treating neural disorders. However, the previous studies mainly used empirical methods to select stimulation parameters and linear optimal control theory-based...
详细信息
The fast development in the use of computer networks raises concerns about network availability, integrity, and confidentiality. This requires network managers to use various types of intrusion detection systems (IDS)...
详细信息
This paper proposes an attitude fault-tolerant control scheme for hypersonic flight vehicles based on extended adaptive iterative learning. Firstly, the integral of tracking error is introduced as an extended state va...
详细信息
This paper proposes an attitude fault-tolerant control scheme for hypersonic flight vehicles based on extended adaptive iterative learning. Firstly, the integral of tracking error is introduced as an extended state variable. Then, a controller based on iterative learning is designed to obtain the optimal feedback control law without faults. Additionally, for multiplicative faults in actuators, a model reference adaptive unit is expansively added to improve the system's robustness under faulty conditions by tracking a reference model. Finally, the stability of the two control modules is proven, and the method is validated in a Matlab simulation environment to achieve good attitude controlperformance in both fault-free and faulty scenarios.
The proceedings contain 379 papers. The topics discussed include: a transformer based network in monocular satellite pose estimation;controller dynamic linearization based data-driven adaptive control for a vapor-comp...
ISBN:
(纸本)9798350361674
The proceedings contain 379 papers. The topics discussed include: a transformer based network in monocular satellite pose estimation;controller dynamic linearization based data-driven adaptive control for a vapor-compression refrigeration system;cooperative awareness message generation interval prediction model based on Bayesian optimized long short-term memory neural network;preassigned time prescribed performance tracking control for high-order nonlinear systems with time-varying powers;gaussian reinforcement learning: optimal tracking control for uncertain linear systems;a velocity tracking method for quadruped robot with rhythm controller;model-free predictive control of hydraulic cylinder based on parameter prediction of extreme learning machine;and semi-supervised domain adaptation with feature separation for wind turbine anomaly detection.
The traditional machine learning models to solve optimal power flow (OPF) are mostly trained for a given power network and hence lose their generalizability to today's power networks with varying topologies and gr...
详细信息
ISBN:
(纸本)9798350318562;9798350318555
The traditional machine learning models to solve optimal power flow (OPF) are mostly trained for a given power network and hence lose their generalizability to today's power networks with varying topologies and growing plug-and-play distributed energy resources (DERs). In this paper, we propose a unified deep neural network (DNN) to predict the solutions for alternating-current (AC) OPF problems across multiple networks that are successively expanding. Specifically, we design elastic input and output layers for the vectors of given loads and OPF solutions with varying lengths in different networks. The proposed method, using a single unified DNN, can deal with different and growing numbers of buses, loads, and generators. Simulations of a network growing from 73 to 118 buses and IEEE 57/118/300-bus test systems verify the improved performance of the proposed method compared to existing methods.
This paper addresses the problem of achieving tracking consensus control for multi-agent systems (MASs) with unknown dynamics. First, an augmented neighborhood error system model is designed, and the optimal consensus...
详细信息
This paper presents a comprehensive evaluation of various wireless networks for Teleoperated Driving (ToD) applications, focusing on a hoverboard as a test vehicle. The study compares end-to-end delay and jitter acros...
详细信息
ISBN:
(纸本)9798350366495;9798350366488
This paper presents a comprehensive evaluation of various wireless networks for Teleoperated Driving (ToD) applications, focusing on a hoverboard as a test vehicle. The study compares end-to-end delay and jitter across five network setups: a private 5G network, a wireless LAN, a public LTE-A network, and two wireless CANs, based on the service level requirements outlined by the 5G Automotive Association (5GAA). Conducted over distances up to 45 kilometers, the evaluation reveals that 5G (both Stand-Alone and Non-Standalone) meets ToD requirements, although CAN networks outperform 5G in latency and jitter. Public LTE-A shows the least optimal performance, highlighting the potential of alternative network technologies for critical controlsystems until 5G matures.
Knowledge distillation is an important network compression technique, which can generate a small student network by learning the knowledge of the teacher network. However, there are two problems in the previous resear...
详细信息
The load frequency control (LFC) is crucial for stabilizing the frequency of the power grid in the intermittency of renewable energy sources. Modern LFC systems utilize open communication and automation networks that ...
详细信息
暂无评论