检索结果-内蒙古大学图书馆

Highly Efficient Three-Level AC-AC Converter with Identical In-Phase and Antiphase Buck-Boost Operations

IEEE Transactions on Power Electronics 2024年第8期39卷 9929-9942页

作者： Ahmed, Hafiz Furqan Khan, Ashraf Ali Al Zaabi, Omar Mousavi, Seyyed Mohammad Javad Babaei, Ebrahim National Sun Yat-Sen University Department of Electrical Engineering Kaohsiung804 Taiwan Memorial University of Newfoundland Department of Electrical and Computer Engineering Faculty of Engineering and Applied Science St. John'sNLA1C 5S7 Canada Khalifa University Advanced Power and Energy Center Department of Electrical Engineering and Computer Science Abu Dhabi127788 United Arab Emirates University of Tabriz Faculty of Electrical and Computer Engineering Tabriz51666 Iran Near East University Engineering Faculty Nicosia99138 Turkey

In this article, a new coupled-inductors based three-level bipolar buck-boost ac-ac converter is proposed. The proposed converter can produce highly efficient and symmetric in-phase and antiphase buck and boost modes of operation with much lower component voltage and current stresses. This reduces the operation and design complexity, and helps to achieve a high-efficiency operation. The high-frequency modulating switches of the proposed converter are implemented with coupled-inductor-based dual-buck phase leg, producing three-level input and output voltages, and providing inherent protection from voltage-source short-circuit issue during switch transitions. The other salient features of the proposed converter are no-commutation issue, no need for RC snubbers or dedicated safe-commutation algorithms, provision of high-quality and continuous input/output currents, and support for nonresistive loads. An in-depth circuit analysis of the proposed converter is provided based on the proposed switch modulation strategies. The guidelines for component design/selection are discussed, followed by the comparisons with state-of-the-art three-level ac-ac converters. Finally, practical circuit verifications are performed on a laboratory-assembled prototype. © 1986-2012 IEEE.

关键词： Buck-Boost converter

来源：评论

学校读者我要写书评

暂无评论

Cloud Computing Design Patterns for MLOps: Applications to Virtual Power Plants 49

Cloud Computing Design Patterns for MLOps: Applications to V...

引用

49th Annual Conference of the IEEE Industrial Electronics Society, IECON 2023

作者： Subramanya, Rakshith Raisanen, Paula Sierla, Seppo Vyatkin, Valeriy Aalto University Department of Electrical Engineering and Automation Espoo Finland Department of Electrical Engineering and Automation Department of Computer Science Electrical and Space Engineering Luleå Sweden

ISBN: (纸本)9798350331820

Virtual Power Plants (VPPs) are a key factor in smart grids, and they use cloud computing to integrate and manage Distributed Energy Resources (DERs). VPPs use Machine Learning (ML) methods to optimize various tasks. Machine Learning Operations (MLOps) methodology is a set of techniques that targets to develop, deploy and maintain ML applications smoothly on production. Cloud design patterns (CDPs) are general reusable solutions for common cloud problems that can improve the reliability, scalability, and quality of cloud applications. This paper discusses how CDPs can help in building complex ML applications on cloud with MLOps practices which can help VPPs to optimize their workloads. The paper also provides an example implementation on a public cloud provider. © 2023 IEEE.

关键词： Cloud computing

来源：评论

学校读者我要写书评

暂无评论

Three-Level Unipolar/Bipolar Buck-Boost AC-AC Converters with Less Active Switches and No Commutation Issues

引用

IEEE Transactions on Transportation Electrification 2024年第2期10卷 4184-4200页

作者： Ahmed, Hafiz Furqan Zaabi, Omar Al El Moursi, Mohamed Shawky Hosani, Khalifa Al National Sun Yat-sen University Department of Electrical Engineering Kaohsiung80424 Taiwan Department of Electrical Engineering and Computer Science Abu Dhabi United Arab Emirates Mansoura University Faculty of Engineering Mansoura35516 Egypt

This article proposes three-level (TL) buck-boost direct ac-ac converters based on switching-cell configuration with coupled magnetics. The proposed converters use only six active switches and can produce noninverting buck (NIBu), noninverting boost (NIBo), versatile noninverting buck-boost (VNIBB), and inverting buck-boost (IBB) output voltages. Unlike the conventional ac-ac converters, pulsewidth modulation (PWM) dead and overlap times are allowed in the proposed converters without switch voltage and current overshoots, respectively, making it free of commutation issues without requiring extra circuitry and control. Moreover, high-speed power MOSFETs can be utilized without the conduction of their body diodes and related poor reverse recovery issues. The proposed converters generate TL input and output voltages, increasing the voltage levels of input-output inductors and reducing their voltage stresses. In addition, a phase shift PWM control is utilized, which enhances the actual frequency of input and output voltages by twice the operating frequency of the switching devices. Consequently, input and output inductors can be designed much smaller, while reducing input-output current ripples. The proposed circuits also feature shared-ground point between ac source and load and provide continuous input and output currents. Two circuit topologies are proposed: Type-I is a noninverting (unipolar) buck-boost converter with less magnetic components and diodes and Type-II is a bipolar buck-boost converter. The experimental test results on a 400-W laboratory circuit are given to verify the operation of the proposed converter. © 2015 IEEE.

关键词： Buck-Boost converter

来源：评论

学校读者我要写书评

暂无评论

Review of dehazing techniques: challenges and future trends

引用

Multimedia Tools and Applications 2025年第3期84卷 1103-1131页

作者： Ayoub, Abeer El-Shafai, Walid El-Samie, Fathi E. Abd Hamad, Ehab K. I. EL-Rabaie, El-Sayed M. Department of Electronics and Electrical Communication Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt Security Engineering Lab Computer Science Department Prince Sultan University Riyadh11586 Saudi Arabia Department of Information Technology College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University Riyadh11671 Saudi Arabia Electrical Engineering Department Faculty of Engineering Aswan University Aswan81542 Egypt

The phenomenon of atmospheric haze arises due to the scattering of light by minute particles suspended in the atmosphere. This optical effect gives rise to visual degradation in images and videos. The degradation is primarily influenced by two key factors: atmospheric attenuation and scattered light. Scattered light causes an image to be veiled in a whitish veil, while attenuation diminishes the image inherent contrast. Efforts to enhance image and video quality necessitate the development of dehazing techniques capable of mitigating the adverse impact of haze. This scholarly endeavor presents a comprehensive survey of recent advancements in the domain of dehazing techniques, encompassing both conventional methodologies and those founded on machine learning principles. Traditional dehazing techniques leverage a haze model to deduce a dehazed rendition of an image or frame. In contrast, learning-based techniques employ sophisticated mechanisms such as Convolutional Neural Networks (CNNs) and different deep Generative Adversarial Networks (GANs) to create models that can discern dehazed representations by learning intricate parameters like transmission maps, atmospheric light conditions, or their combined effects. Furthermore, some learning-based approaches facilitate the direct generation of dehazed outputs from hazy inputs by assimilating the non-linear mapping between the two. This review study delves into a comprehensive examination of datasets utilized within learning-based dehazing methodologies, elucidating their characteristics and relevance. Furthermore, a systematic exposition of the merits and demerits inherent in distinct dehazing techniques is presented. The discourse culminates in the synthesis of the primary quandaries and challenges confronted by prevailing dehazing techniques. The assessment of dehazed image and frame quality is facilitated through the application of rigorous evaluation metrics, a discussion of which is incorporated. To provide empiri

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Reward Shaping in Reinforcement Learning of Multi-Objective Safety Critical Systems 20

Reward Shaping in Reinforcement Learning of Multi-Objective ...

引用

20th CSI International Symposium on Artificial Intelligence and Signal Processing, AISP 2024

作者： Ravari, Fatemeh Yousefinejad Jalili, Saeed Tarbiat Modares University Electrical and Computer Engineering Faculty Computer Engineering Department Tehran Iran

ISBN: (纸本)9798350383942

Reinforcement learning (RL) depends critically on how well the reward function formulates the aim of the application. In safety-critical systems, several safety properties should be met during the RL process in addition to achieving the primary target. In this paper, we utilize the reward shaping technique to guide the RL algorithm in a way that satisfies the target and safety properties and fulfills other properties, such as efficiency, as much as possible. Reward shaping is a technique to enhance the performance of RL by adding more information to the reward function. Reward shaping functions utilize the system's main target for the base reward signal and add some other reward signals based on other system properties. Suppose each property has its own reward function. In this case, the reward is a vector rather than a scalar value, and the original reinforcement learning approach converts to multi-objective reinforcement learning (MORL). In MORL, one scalarized objective can be defined by fusing several objectives. This paper proposes an aggregation method based on prioritized aggregation operators for scalarizing multiple reward functions. We illustrate our method with two case studies: cart-pole with an obstacle and lunar-lander. The simulation results show that our method guides the RL algorithm to converge to optimal policies faster than existing approaches. © 2024 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Optimal energy management strategy based on neural network algorithm for fuel cell hybrid vehicle considering fuel cell lifetime and fuel consumption

引用

Soft Computing 2024年第19期28卷 11471-11493页

作者： Omer, Abbaker A. M. Wang, Haoping Tian, Yang Peng, Lingxi School of Mechanical and Electrical Engineering Guangzhou University Guangzhou510006 China School of Automation Nanjing University of Science and Technology Nanjing210094 China Department of Electrical and Electronics Engineering Faculty of Engineering Sciences University of Nyala Nyala Sudan

This paper proposes a new design method of energy management strategy (EMS) with adaptive super-twisting sliding mode control (ASTSMC) for fuel cell/battery/supercapacitor hybrid vehicle (FCHEV). The main objective of the proposed EMS is to improve power performance, fuel cell lifetime, and fuel consumption while considering the regulation of the DC-bus voltage. The proposed EMS is designed based on a frequency-decoupling technique using an adaptive low-pass filter, Harr wavelet transform (HWT), and FLC to decouple the required power into low, medium, and high-frequency components for fuel cell, battery, and supercapacitor, respectively. The presented frequency-decoupling-based strategy can improve the power performance of the vehicle as well as reduce load stress and power fluctuation in the fuel cell. Nevertheless, the neural network optimization algorithm (NNOA) is employed to optimize the membership functions of FLCs while considering the hydrogen consumption and constraints on the state of charge (SOC) of the battery and supercapacitor. To achieve robustness and high precision control, the ASTSMC is developed based on a nonlinear disturbance observer (NDOB) to stabilize the DC-bus voltage and currents of the energy sources, ensuring that the fuel cell, battery, and supercapacitor track their obtained reference values. The FCHEV system with the proposed EMS is modeled on MATLAB/Simulink, and three typical driving cycles such as HWFET, UDDS, and WLTP driving schedules are used for evaluation. The findings exhibit that the proposed EMS can effectively improve the fuel economy, reduce power fluctuation in the fuel cell, and prolong its lifetime compared to other existing methods such as the equivalent consumption minimization strategy (ECMS), state machine (SM), and FLC-based EMSs. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Membership functions

来源：评论

学校读者我要写书评

暂无评论

SUP: Security User Profiles for Behavioral Data Platforms

SUP: Security User Profiles for Behavioral Data Platforms

引用

2024 International Symposium on Networks, computers and Communications, ISNCC 2024

作者： Sulayman, Iman I. M. Abu Ouda, Abdelkader Western University Faculty of Engineering Department of Electrical and Computer Engineering LondonON Canada

ISBN: (纸本)9798350364910

Integrating user behavior across domains to create comprehensive profiles is crucial for system efficiency and security. This paper delves into the use of data analytics techniques to gather user data from various application domains, enabling the creation of security user profiles that contain data suitable for user authentication. Specifically, these methods are capable of identifying patterns in the users' data and then using said patterns to detect legitimate but anomalous activities performed by the users. Furthermore, we propose an innovative mechanism that dynamically integrates these profiles to create a comprehensive and global security profile for user authentication. Typically, each profile represents a distinctive entity detailing infrequent user behaviors that significantly impact identity verification. The verification process involves posing user challenge questions generated from these integrated profiles. The generated user profiles ensure the selection of questions that meet both security and usability requirements. We uphold security by issuing each question from the integrated user profiles only once, protecting user responses from potential compromise. We prioritize usability by using fresh data, which helps legitimate users recall and complete the challenge easily. © 2024 IEEE.

关键词： Behavioral data analytics Behavioral modeling Information security User profile

来源：评论

学校读者我要写书评

暂无评论

Implementation of Photovoltaic Power Maximization through Dynamic Power and Current Control 12

Implementation of Photovoltaic Power Maximization through Dy...

引用

12th International electrical engineering Congress, iEECON 2024

作者： Jantharamin, Niphat Lousuwankun, Peeradech Naresuan University Faculty Of Engineering Department Of Electrical And Computer Engineering Phitsanulok Thailand

ISBN: (纸本)9798350383591

A novel approach to optimizing photovoltaic (PV) power through adaptive step size adjustments based on variations in PV module output power and current is introduced in this research paper. Utilizing the incremental conductance technique, the algorithm dynamically adjusts the duty cycle of a step-up converter, optimizing the operating point of a PV module toward the maximum power point (MPP). By eliminating the need for a multiplier and requiring no preceding knowledge of PV module output characteristics, this approach stands out for its efficiency. Hardware implementation and a comparison with a fixed step-size strategy demonstrated superior tracking speed (52% faster) and impeccable accuracy. The proposed method accelerates the maximum power point tracking (MPPT) process and also significantly enhances the overall performance of the PV system. The study presents a breakthrough promising a more responsive and precise system for optimizing PV power, showcasing potential advancements in renewable energy technology. © 2024 IEEE.

关键词： Solar panels

来源：评论

学校读者我要写书评

暂无评论

Exploring Feature Map Correlations for Effective Fake Face Detection 11

Exploring Feature Map Correlations for Effective Fake Face D...

引用

11th International Symposium on Telecommunication, IST 2024

作者： Honarjoo, Narges Taher, Fatemeh Mansouri, Azadeh Kharazmi University Faculty of Engineering Department of Electrical and Computer Engineering Tehran Iran

ISBN: (纸本)9798350356250

In recent years, the internet and social media platforms have seen a massive influx of data, particularly images. To effectively identify fake content, we employ a deepfake detection technique aimed at determining the authenticity of uploaded material. In this paper, we achieve fake face detection with high accuracy by utilizing deep feature map relations. Our approach leverages transfer learning techniques from pretrained deep models, such as VGG16, VGG19, and ResNet50. We analyze the generated Gram Matrix of each layer, where deep feature relations are similar to the covariance matrix, reflecting correlations between different feature maps. These features are used to classify content as fake or real using a simple CNN, and the results are reported and compared. This study explores deep feature map relations as crucial indicators for detecting inconsistencies introduced by image generators. By employing pre-trained networks, we analyze and explore feature map relations generated in each layer as higher-order quality features. Experimental results demonstrate that the proposed inconsistency detection feature yields satisfactory results. The entire implementation of this work can be found at https: //***/hnarges91/Fake-Face-Detection. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Comparing Centralized and Decentralized Storage in Microgrids: Implications for Consumer Behavior 28

Comparing Centralized and Decentralized Storage in Microgrid...

引用

28th International electrical Power Distribution Conference, EPDC 2024

作者： Dousti, Hazhir Hagh, Mehrdad Tarafdar Jirdehi, Mehdi Ahmadi Kermanshah University of Technology Faculty of Electrical Engineering Department of Electrical Engineering Kermanshah Iran University of Tabriz Faculty of Electrical and Computer Engineering Tabriz Iran

ISBN: (纸本)9798350385502

Due to the increase in demand for electricity, the lack of fossil fuels, and the use of renewable energy sources, the use of energy storage systems becomes necessary. The use of storage systems in different parts of microgrids has countless advantages. These benefits include improving the overall efficiency of the system, increasing the stability of the network, the possibility of optimal control strategies at both the national and regional levels and the effective identification of vulnerabilities in the system. This paper focuses on the issue of coordinated and optimal energy management in a microgrid, especially when dealing with centralized and decentralized storage. This study simultaneously examines the impact of the presence of storage systems in both centralized and decentralized modes, as well as the creation of incentive policies to reduce demand. It examines the interaction between these two factors and their effects on cost reduction and overall network voltage deviation. The work has been done on a standard IEEE network with 69 buses using MATLAB software. It has been shown that in the presence of decentralized energy storage, network performance and consumer consumption are better, and network losses and voltage deviations are also reduced. © 2024 IEEE.

关键词： Renewable energy

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：