Intelligent resource allocation and power control schemes are regarded as important methods to alleviate the problems caused by the sharp increase in the number of users and operating costs. In this paper, we propose ...
详细信息
ISBN:
(纸本)9781665491228
Intelligent resource allocation and power control schemes are regarded as important methods to alleviate the problems caused by the sharp increase in the number of users and operating costs. In this paper, we propose a multi-agent deep reinforcement learning (MADRL)-based algorithm to jointly optimize resource block (RB) allocation and power control, which aims to maximize the average spectrum efficiency (SE) of the system while meeting quality of service (QoS) constraints. In view of the fact that centralized training distributed execution retains the advantages of centralized training while reducing the amount of computation and signaling overhead, the MADRL technique can be adopted. In the proposed MADRL model, the Q function of each agent is aggregated through the value decomposition network, which strengthens the cooperation of agents and improves the convergence of the algorithm. We add a reward discount network into the original MADRL framework to adaptively adjust the attention to future rewards according to the performance of agents in the training process. Simulation experiments show that the proposed algorithm has better performance and stability than the existing alternatives.
The distribution network fault recovery reconfiguration is essential for restoring power supply to customers in a safe, efficient, and reliable manner. The study has proposed a multi-objective optimization model for t...
详细信息
Transient stability analysis (TSA) is crucial for maintaining the stability of power systems. Compared to traditional dynamic simulations, neural network-based power system TSA models have been widely applied in recen...
详细信息
ISBN:
(纸本)9798350377477;9798350377460
Transient stability analysis (TSA) is crucial for maintaining the stability of power systems. Compared to traditional dynamic simulations, neural network-based power system TSA models have been widely applied in recent years due to their strong nonlinear mapping capability and fast prediction speed. In this paper, a new TSA approach is proposed based on the Transformer neural network, which combines the encoder-decoder architecture and the attention mechanism. A multichannel feature extraction structure and a supervised contrastive learning algorithm are utilized to mitigate the overfitting phenomenon and enhance the generalization capability of the proposed model, resulting in competitive performance. The efficacy of the proposed TSA method is validated by the superior performance in the standard IEEE 39-bus test case.
The proceedings contain 25 papers. The special focus in this conference is on . The topics include: Denoising of ECG Signal Using Optimized iiR Filter Architecture—A CSD-Based Design;deep Learning Analysis for Skin C...
ISBN:
(纸本)9789819944439
The proceedings contain 25 papers. The special focus in this conference is on . The topics include: Denoising of ECG Signal Using Optimized iiR Filter Architecture—A CSD-Based Design;deep Learning Analysis for Skin Cancer Detection;Design and Development of a BCI Framework to control a UTM Using EEG Headset;approximate Compressors-Based Multiplier for Image Processing and Neuromorphic Modeling;integration of Particle Swarm Optimization and Sliding Mode control: A Comprehensive Review;design and Testing of a Solar Powered Automated Fruit and Vegetable Sorter;characterization of Dust Particles and Their Impact on the performance of Photovoltaic Panels: A Laboratory Investigation;Design and Analysis of DC-DC Boost Converter;energy Management Analysis on Smart Street Lighting for Smart Cities;design and Implementation of Smart Waste Management System;Design and Development of Efficient Feeding network Structure for Patch Antenna Array Modules in UAV Communication Applications;E—RiCoBiT—ii: A High Performing RiCoBiT (Ring Connected Binary Tree) Topology with Fully Adaptive Routing Algorithm;Design and Development of Autonomous VTOL for Medicine Deliveries in Hilly Areas;Implementation and Design of Agile and Multipurpose Autonomous Robot Using ROS;prediction of Chronic Pain Onset in Patients Experiencing Tonic Pain: A Survey;design and Analysis of Miniaturized Broadband Microstrip Patch Antenna for Aircraft Surveillance Applications;Multiplier Design for the Modulo Set {2n- 1, 2n, 2n+1- 1 } and Its Application in DCT for HEVC;Modelling performance Analysis in VLSI Testing Methodologies;Verification of AHB2APB Bridge Protocol Using UVM;Design and Verification of AMBA AHB Protocol Using UVM.
Catastrophic interference is common in many network-based learning systems, and many proposals exist for mitigating it. Before overcoming interference we must understand it better. In this work, we provide a definitio...
详细信息
Catastrophic interference is common in many network-based learning systems, and many proposals exist for mitigating it. Before overcoming interference we must understand it better. In this work, we provide a definition and novel measure of interference for value-based reinforcement learning methods such as Fitted Q-Iteration and DQN. We systematically evaluate our measure of interference, showing that it correlates with instability in controlperformance, across a variety of network architectures. Our new interference measure allows us to ask novel scientific questions about commonly used deep learning architectures and study learning algorithms which mitigate interference. Lastly, we outline a class of algorithms which we call online-aware that are designed to mitigate interference, and show they do reduce interference according to our measure and that they improve stability and performance in several classic control environments.
Developing two intrusion detection systems (IDS) to identify grey hole attacks in wireless ad hoc networks is the goal of this project. For this, the Random Forest (RF) and Decision Tree algorithms were used. The NS2 ...
详细信息
This study presents a novel trajectory tracking controller for a stratospheric airship, focusing on event-triggered control and prescribed performance. The proposed controller, based on the framework of prescribed per...
详细信息
This paper presents the phasor measurement Unit (PMU) based monitoring and management which is suitable for medium voltage networks that will have significant distributed energy resources (DER) integration. Its fundam...
详细信息
ISBN:
(纸本)9798350395082;9798350395075
This paper presents the phasor measurement Unit (PMU) based monitoring and management which is suitable for medium voltage networks that will have significant distributed energy resources (DER) integration. Its fundamental technology, its application, and its benefits to distribution networks were described. This included the differences between PMU compared to conventional supervisory control and data acquisition (SCADA) systems which are currently deployed in the distribution network. The research trend on this technology application is also surveyed and discussed. The pilot demonstration project on PMU-based monitoring and management, which is currently ongoing at one of the medium voltage level distribution systems in Qatar, is also presented. The experience of planning, installing, and commissioning the system is shared. Highlight of the capability and performance of this PMU monitoring system is also commented on.
The partitioning problem is a key problem for distributed control techniques. The problem consists in the definition of the subnetworks of a dynamical system that can be considered as individual control agents in the ...
详细信息
The sense of agency (SoA), the feeling of recognizing that the observed movement is caused by oneself, which is important in robot teleoperation, is reduced by shared control, in which the robot and the human cooperat...
详细信息
ISBN:
(纸本)9798350388039;9798350388046
The sense of agency (SoA), the feeling of recognizing that the observed movement is caused by oneself, which is important in robot teleoperation, is reduced by shared control, in which the robot and the human cooperate to control the robot. In this study, we developed a system that uses a recurrent neural network with parametric biases (RNNPB) trained on expert operational data to predict the next input from non-experts and convert it into robot commands in real time. Through an experiment with a pouring task, it was confirmed that the proposed method outputs predicted values that spatially and temporally interpolate the operational inputs, gradually correcting the robot's movements to align with the experts' trajectories. The proposed method showed a high SoA comparable to direct control;however, no statistically significant difference in task performance was observed. Future work aims to improve the generality of the model to accommodate a wider variety of input trajectories.
暂无评论