检索结果-内蒙古大学图书馆

Data-Driven Power Flow Estimation for MVDC Distribution Systems Based on Physics-Embedded FCN

IEEE Transactions on Smart Grid 2025年第4期16卷 2816-2829页

作者： Sun, Pingyang Wu, Rongcheng Shen, Zhiwei Wang, Hongyi Li, Gen Khalid, Muhammad Konstantinou, Georgios School of Electrical Engineering and Telecommunications UNSW Sydney Australia University of Technology Sydney Data Science Institute Australia Aalborg University Department of AAU energy Denmark Energy Technology and Computer Science Section Department of Engineering Technology Ballerup2750 Denmark King Fahd University of Petroleum and Minerals Electrical Engineering Department Interdisciplinary Research Center for Sustainable Energy Systems Dhahran31261 Saudi Arabia

Maintaining high prediction accuracy with varying grid topologies poses a significant challenge to adopting neural network (NN)-based approaches for power flow (PF) estimation in medium-voltage direct current (MVDC) distribution systems. This paper proposes a physics-embedded fully convolutional network (PEFCN) to improve the accuracy. Physics-embedded techniques are incorporated in the proposed PEFCN through 1) architecture reconstruction, and 2) loss function reformulation. Architecture is reconstructed by input channel conversion calculation in a new physics operation layer. This process offers physical connections among the three input matrix channels (voltage, current, and line conductance). Three new physics loss terms are included in the loss function to restrict the outliers violating the limits of converter power ratings and terminal MVDC voltages. The two operations enable the FCN to achieve improved prediction accuracy and strong generalization capabilities. Five MVDC distribution systems, characterized by different dc voltage levels and topology configurations, serve to validate the superiority of the proposed PEFCN over other NNs in the PF estimation for scenarios involving both fixed and varying system structures. Moreover, a modified IEEE 69-bus distribution system is further used to demonstrate the applicability of the proposed PEFCN for larger systems. © 2010-2012 IEEE.

关键词： DC distribution systems

来源：评论

学校读者我要写书评

暂无评论

Virtual synchronous generator-based control of modular multilevel converter for integration into weak grid

引用

IET Renewable Power Generation 2023年第12期17卷 3097-3107页

作者： HosseinNataj, Saeed Gholamian, Sayyed Asghar Rezanejad, Mohammad Mehrasa, Majid Faculty of Electrical and Computer Engineering Babol Noshirvani University of Technology Babol Iran Faculty of Engineering and Technology University of Mazandaran Mazandaran Babolsar Iran Grand ForksND United States

Integrating Power Electronics Converters (PECs)-based renewable energy sources can establish a weak grid due to the substantial inertia reduction leading to severe frequency fluctuations. In this paper, a control strategy based on the Virtual Synchronous Generator (VSG) concept is designed for a three-phase Modular Multilevel Converter (MMC) connected to a weak grid. The proposed VSG control approach improves the frequency response during transient mode, resulting in a 66.7% enhancement at the Point of Common Coupling (PCC). The proposed strategy is shaped within four control loops wherein the VSG-dependent output current control possesses the duty of enriching the MMC output current tracking capability. Focusing on the MMC output current-based transfer function, the effectiveness of this capability is guaranteed using the frequency domain analysis including the Nyquist and Bode diagrams. Moreover, a comprehensive discussion was carried out regarding the impact of VSG on the voltage of submodule capacitors and the circulating current. Simulation results in MATLAB/Simulink environment validate the accuracy and weak grid-connected MMC performance under the proposed VSG-based control technique. To further verify the superiority of the proposed strategy, two control techniques including Droop and SEBIR are compared with the VSG proposed controller. © 2023 The Authors. IET Renewable Power Generation published by John Wiley & Sons Ltd on behalf of The Institution of engineering and technology.

关键词： Synchronous generators

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning Enabled Bi-level Robust Parameter Optimization of Hydropower-dominated Systems for Damping Ultra-low Frequency Oscillation

引用

Journal of Modern Power Systems and Clean Energy 2023年第6期11卷 1770-1783页

作者： Guozhou Zhang Junbo Zhao Weihao Hu Di Cao Nan Duan Zhe Chen Frede Blaabjerg School of Mechanical and Electrical Engineering University of Electronic Science and Technology of ChinaChengdu 610054China IEEE Department of Electrical and Computer Engineering University of ConnecticutStorrsCT06269USA Lawrence Livermore National Laboratory LivermoreUSA Department of Energy Technology Aalborg University9220 AalborgDenmark

This paper proposes a robust and computationally efficient control method for damping ultra-low frequency oscillations(ULFOs) in hydropower-dominated systems. Unlike the existing robust optimization based control formulation that can only deal with a limited number of operating conditions, the proposed method reformulates the control problem into a bi-level robust parameter optimization model. This allows us to consider a wide range of system operating conditions. To speed up the bi-level optimization process, the deep deterministic policy gradient(DDPG) based deep reinforcement learning algorithm is developed to train an intelligent agent. This agent can provide very fast lower-level decision variables for the upper-level model, significantly enhancing its computational efficiency. Simulation results demonstrate that the proposed method can achieve much better damping control performance than other alternatives with slightly degraded dynamic response performance of the governor under various types of operating conditions.

关键词： Bi-level robust parameter optimization deep reinforcement learning deep deterministic policy gradient ultralow frequency oscillation damping control stability

来源：评论

学校读者我要写书评

暂无评论

Priority based k-coverage hole restoration and m-connectivity using whale optimization scheme for underwater wireless sensor networks

引用

International Journal of Intelligent Networks 2023年第1期4卷 240-252页

作者： Kumari, Sangeeta Mishra, Pavan Kumar Sangaiah, Arun Kumar Anand, Veena School of Computer Science Engineering and Technology Bennett University U.P Greater Noida India India Department of Electrical and Computer Engineering Lebanese American University Byblos Lebanon India

Coverage hole restoration and connectivity is a typical problem for underwater wireless sensor networks. In underwater applications like underwater oilfield reservoirs, undersea minerals and monitoring etc., where nodes face many hurdles and are unable to cover the required region during a natural disaster such as tsunami, flood, earthquakes, and environmental interference. It creates a coverage hole and consumes high energy with bad network quality. This problem considered as an NP-complete problem where a set of sensor nodes is required to identify the k-coverage hole and m-connectivity. In the literature, researchers have not focused on k-coverage hole restoration and m-connectivity issues during natural disasters and environmental interference. To mitigate this problem, we proposed priority-based coverage hole restoration and -connection using a whale optimization scheme to restore coverage holes and extract relevant information for the construction of undersea oilfield reservoirs, minerals, and mines. In this scheme, we identified the list of k-coverage holes and addressed autonomous underwater vehicles (AUVs) to place the additional mobile nodes in an appropriate coverage hole. A novel multi-objective function is formulated to obtain the optimal path for AUVs. Furthermore, while restoring coverage holes, we checked the connectivity of nodes. In the network, each node coordinated sleep scheduling with neighbor nodes to maintain energy efficiency. Performance evaluation of the proposed scheme shows better results than the existing schemes under different network scenarios which provide maximum coverage and connectivity, less energy consumption with a high convergence rate. © 2023 The Authors

关键词： Autonomous underwater vehicles

来源：评论

学校读者我要写书评

暂无评论

Vision-Based Navigation for a Small-Sized Drone: A Simple AI Strategy at IMAV'22

Vision-Based Navigation for a Small-Sized Drone: A Simple AI...

引用

2024 IEEE International Conference on Cybernetics and Innovations, ICCI 2024

作者： Farooq, Adil Nain Zukhraf, Syeda Zillay Shafi, Sadman Kamal, Mohsin Chumuang, Narumol University Of Cyprus Department Of Electrical And Computer Engineering Cyprus Penn State University Department Of Electrical Engineering United States National University Of Sciences And Technology School Of Electrical Engineering And Computer Science Pakistan Muban Chombueng Rajabhat University Department Of Digital Media Technology Thailand

ISBN: (纸本)9798350370096

Autonomous drone racing competitions serve as a testing ground for enhancing the perceptual, planning, and control aspects of micro unmanned aerial vehicles (MAVs). This study thoroughly outlines the strategy, methodology, and technical development of a lightweight collision avoidance module for small drones, employed during our participation in the IMAV 2022 Nanocopter AI Challenge held at TU Delft, The Nether-lands. Tailored for nano-sized drones, this competition presented challenges related to agile maneuvers, obstacle avoidance, and navigation in a dynamic indoor arena. We provide detailed insights into our obstacle avoidance algorithm, employing an AI computer vision approach and showcasing its robust performance in dynamic environments. The accuracy of the proposed strategy was verified through simulation testing, highlighting the effectiveness of our approach in a simulated Webots environment across diverse parameter settings. The shared insights aim to contribute significantly to the ongoing evolution of autonomous drone navigation. Moreover, the simulation of our proposed strategy can be seen on the YouTube video link: https://***/HVZPAfyf57M. © 2024 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Investigation of DNA discontinuity for detecting tuberculosis

引用

Journal of Ambient Intelligence and Humanized Computing 2024年第1期15卷 1149-1163页

作者： Nimmy, Sonia Farhana Sarowar, Md. Golam Dey, Nilanjan Ashour, Amira S. Santosh, K.C. Department of Computer Science and Engineering Notre Dame University Dhaka Bangladesh Department of Computer Science and Engineering East West University Dhaka Bangladesh Department of Information Technology Techno India College of Technology Kolkata India Department of Electronics and Electrical Communications Engineering Faculty of Engineering Tanta University Tanta Egypt Vermillion United States

Discontinuity in long Deoxyribonucleic Acid (DNA) sequences creates harmful diseases. Changes in the DNA structure refers to changes in the human immunity system. Tuberculosis is a critical disease that causes coughing, fatigue, unintentional weight loss and fever on aged people due to the disorder in the DNA. Breaks or mutations over long DNA sequences are the pivotal reasons for this fatal disease. This study developed an automated machine learning technique to assess the total number of such breaks in the long DNA sequences. Data cleansing and deep neural network techniques are applied to handle this big data. The National Center for Biotechnology Information (NCBI) database has been used to extract the amino acid sequences for Tuberculosis disease from the big DNA datasets. Results reveal that the proposed automated approach is significantly effective for the determination of DNA sequence breaks for the tuberculosis diseases due to the high sensitivity of Markov chain as well as the effective normalization techniques. This approach fixed the size of the training datasets and recursively divide the whole dataset into certain length. The study also adopts multiple predictions approaches, such as the hidden Markov chain, Box-Cox transformation and linear transformation to forecast about the breaks for any long positions of the training and testing datasets. The results demonstrated that hidden the Markov chain model provided faster analysis with more accurate and reliable results. © Springer-Verlag GmbH Germany, part of Springer Nature 2018.

关键词： DNA

来源：评论

学校读者我要写书评

暂无评论

Class-conditional domain adaptation for semantic segmentation

引用

Computational Visual Media 2024年第5期10卷 1013-1030页

作者： Yue Wang Yuke Li James H.Elder Runmin Wu Huchuan Lu School of Information and Communication Engineering Dalian University of TechnologyDalian 116024China School of Computer Science Wuhan UniversityWuhan 430072China Department of Electrical Engineering and Computer Science York UniversityToronto M3J 1P3Canada Department of Computer Science the University of Hong KongHong Kong 999077China

Semantic segmentation is an important sub-task for many ***,pixel-level ground-truth labeling is costly,and there is a tendency to overfit to training data,thereby limiting the generalization *** domain adaptation can potentially address these problems by allowing systems trained on labelled datasets from the source domain(including less expensive synthetic domain)to be adapted to a novel target *** conventional approach involves automatic extraction and alignment of the representations of source and target domains *** limitation of this approach is that it tends to neglect the differences between classes:representations of certain classes can be more easily extracted and aligned between the source and target domains than others,limiting the adaptation over all ***,we address:this problem by introducing a Class-Conditional Domain Adaptation(CCDA)*** incorporates a class-conditional multi-scale discriminator and class-conditional losses for both segmentation and ***,they measure the segmentation,shift the domain in a classconditional manner,and equalize the loss over *** results demonstrate that the performance of our CCDA method matches,and in some cases,surpasses that of state-of-the-art methods.

关键词： domain adaptation generative adversarial networks semantic segmentation cityscapes

来源：评论

学校读者我要写书评

暂无评论

Iterative Equalization of CPM with Unitary Approximate Message Passing

引用

IEEE Transactions on Vehicular technology 2025年第6期74卷 9343-9356页

作者： Liu, Zilong Song, Yi Guo, Qinghua Sun, Peng Gong, Kexian Wang, Zhongyong Zhengzhou University School of Electrical and Information Engineering Zhengzhou450001 China Henan Zhengzhou450001 China Henan University of Technology Henan Engineering Research Center of Grain Condition Intelligent Detection and Application Henan Zhengzhou450001 China Henan University of Technology College of Science and Engineering Henan Zhengzhou450001 China University of Wollongong School of Electrical Computer and Telecommunications Engineering WollongongNSW2522 Australia

Continuous phase modulation (CPM) has extensive applications in wireless communications due to its high spectral and power efficiency. However, its nonlinear characteristics pose significant challenges for detection in frequency selective fading channels. This paper proposes an iterative receiver tailored for the detection of CPM signals over frequency selective fading channels. This design leverages the factor graph framework to integrate equalization, demodulation, and decoding functions. The equalizer employs the unitary approximate message passing (UAMP) algorithm, while the unitary transformation is implemented using the fast Fourier transform (FFT) with the aid of a cyclic prefix (CP), thereby achieving low computational complexity while with high performance. For CPM demodulation and channel decoding, with belief propagation (BP), we design a message passing-based maximum a posteriori (MAP) algorithm, and the message exchange between the demodulator, decoder and equalizer is elaborated. With proper message passing schedules, the receiver can achieve fast convergence. Simulation results show that compared with existing turbo receivers, the proposed receiver delivers significant performance enhancement with low computational complexity. © 1967-2012 IEEE.

关键词： Demodulation

来源：评论

学校读者我要写书评

暂无评论

ANNDRA-IoT:A Deep Learning Approach for Optimal Resource Allocation in Internet of Things Environments

引用

computer Modeling in engineering & Sciences 2025年第3期142卷 3155-3179页

作者： Abdullah M.Alqahtani Kamran Ahmad Awan Abdulaziz Almaleh Osama Aletri Department of Electrical and Electronic Engineering College of Engineering and Computer ScienceJazan UniversityJazan45142Saudi Arabia Department of Information Technology The University of HaripurHaripur22620Pakistan College of Computer Science King Khalid UniversityAbha62529Saudi Arabia Department of Computing College of Engineering and ComputingUmm Al-Qura UniversityMakkah21955Saudi Arabia

Efficient resource management within Internet of Things(IoT)environments remains a pressing challenge due to the increasing number of devices and their diverse *** study introduces a neural network-based model that uses Long-Short-Term Memory(LSTM)to optimize resource allocation under dynam-ically changing *** to monitor the workload on individual IoT nodes,the model incorporates long-term data dependencies,enabling adaptive resource distribution in real *** training process utilizes Min-Max normalization and grid search for hyperparameter tuning,ensuring high resource utilization and consistent *** simulation results demonstrate the effectiveness of the proposed method,outperforming the state-of-the-art approaches,including Dynamic and Efficient Enhanced Load-Balancing(DEELB),Optimized Scheduling and Collaborative Active Resource-management(OSCAR),Convolutional Neural Network with Monarch Butterfly Optimization(CNN-MBO),and Autonomic Workload Prediction and Resource Allocation for Fog(AWPR-FOG).For example,in scenarios with low system utilization,the model achieved a resource utilization efficiency of 95%while maintaining a latency of just 15 ms,significantly exceeding the performance of comparative methods.

关键词： Internet of things resource optimization deep learning optimal resource allocation neural network efficiency

来源：评论

学校读者我要写书评

暂无评论

Guest Editorial Special Section on Distributed Edge Learning in Wireless Networks

IEEE Open Journal of the Communications Society

引用

IEEE Open Journal of the Communications Society 2023年 4卷 2729-2732页

作者： Gong, Xiaowen Huang, Kaibin Chen, Mingzhe Fischione, Carlo Zhang, Jun Choi, Wan Auburn University Department of Electrical and Computer Engineering AuburnAL36849 United States The University of Hong Kong Department of Electrical and Electronic Engineering Pokfulam Hong Kong Kth Royal Institute of Technology Division of Networks and System Engineering Stockholm114 28 Sweden University of Miami Department of Electrical and Computer Engineering MiamiFL33146 United States The Hong Kong University of Science and Technology Department of Electronic and Computer Engineering Sai Kung Hong Kong Seoul National University Department of Electrical and Computer Engineering Seoul08826 Korea Republic of

Distributed machine learning at the network edge has emerged as a promising new paradigm. Various machine learning (ML) technologies will distill Artificial Intelligence (AI) from enormous mobile data to automate future wireless networking and a wide range of Internet-of-Things (IoT) applications. In distributed edge learning, multiple edge devices train a common learning model collaboratively without sending their raw data to a central server, which not only helps to preserve data privacy but also reduces network traffic. However, distributed edge training and edge inference typically still require extensive communications among devices and servers connected by wireless links. As a result, the salient features of wireless networks, including interference and channels’ heterogeneity, time-variability, and unreliability, have significant impacts on the learning performance.

关键词： Special issues and sections Edge computing Distributed computing Wireless networks Learning systems Machine learning

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：