检索结果-内蒙古大学图书馆

10th International Conference on Learning Representations, ICLR 2022

作者： Chen, Yixuan Shi, Yubin Li, Dongsheng Wang, Yujiang Dong, Mingzhi Zhao, Yingying Dick, Robert Lv, Qin Yang, Fan Shang, Li China and Shanghai Key Laboratory of Data Science School of Computer Science Fudan University Shanghai China Microsoft Research Asia Shanghai China Department of Computing Imperial College London London United Kingdom Department of Electrical Engineering and Computer Science University of Michigan Michigan United States Department of Computer Science University of Colorado Boulder Boulder United States School of Microelectronics Fudan University Shanghai China

Disentangled feature representation is essential for data-efficient learning. The feature space of deep models is inherently compositional. Existing β-VAE-based methods, which only apply disentanglement regularization to the resulting embedding space of deep models, cannot effectively regularize such compositional feature space, resulting in unsatisfactory disentangled results. In this paper, we formulate the compositional disentanglement learning problem from an information-theoretic perspective and propose a recursive disentanglement network (RecurD) that propagates regulatory inductive bias recursively across the compositional feature space during disentangled representation learning. Experimental studies demonstrate that RecurD outperforms β-VAE and several of its state-of-the-art variants on disentangled representation learning and enables more data-efficient downstream machine learning tasks. © 2022 ICLR 2022 - 10th International Conference on Learning Representationss. All rights reserved.

关键词： Information theory

来源：评论

学校读者我要写书评

暂无评论

An Artificial Intelligence Solution for Energy Management in Smart Grid

An Artificial Intelligence Solution for Energy Management in...

引用

2023 IEEE International Conference on Artificial Intelligence and Green Energy, ICAIGE 2023

作者： Naceur, Ferdaws Ben Toumi, Sana Salah, Chokri Ben Mahjoub, Mohamed Ali National School of Engineers of Sousse University of Sousse LATIS- Laboratory of Advanced Technology and Intelligent Systems Sousse4023 Tunisia Higher Institute of Computer Science and Communication Technologies of Hammam Sousse University of Sousse Sousse4011 Tunisia Department of Electrical Engineering Monastir Tunisia Brest29238 France Issat Sousse Sousse Tunisia

ISBN: (纸本)9798350325539

This paper deals with an intelligent decision-making strategy of energy management for a smart grid within an element storage in order to reduce the system cost and improve its reliability. Indeed, the integration of distributed energy storage devices allows the customers to store energy and reuse at a later time or delayed some appliances operation according to a time-varying price signal. The adopted strategy is based on an artificial intelligence control algorithm 'fuzzy logic'. The main objective is to determine the appropriate source (grid or battery) used for meeting the consumer. The decision solution shows the system reliability where the switches are synchronized. Switches draw electricity from the grid for both load and battery when price is low and in contrary when electricity price is high, we find a variation's price correspondance with the switch drawing electricity from the battery. The obtained results are verified carrying out Matlab simulation using real data such as the electricity price (Price (t)) and the battery state of charge (SOC (t)). © 2023 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Experimental Evaluation of the Impact of Using Oriented Steel in Proportion to Segmentation on Core Loss of AC Electric Machine Stator

Experimental Evaluation of the Impact of Using Oriented Stee...

引用

IEEE Energy Conversion Congress and Exposition, ECCE

作者： Bhuvan Khoshoo Anmol Aggarwal John Agapiou Shanelle N. Foster Department of Electrical & Computer Engineering Michigan State University East Lansing MI USA General Motors Pontiac MI USA Manufacturing Systems Research Laboratory General Motors Warren MI USA

ISBN: (数字)9798350376067

ISBN: (纸本)9798350376074

The strategic incorporation of oriented steel in a segmented stator AC electric machine has the potential to enhance machine performance by reducing core losses compared to a machine designed with non-oriented steel. However, the introduction of cut-edges and the stress on individual segments resulting from segmented stator construction may have unintended consequences. Despite several attempts to assess the impact of cut-edges or oriented steel on core losses in segmented stators, the literature lacks an analysis of the loss separation between tooth and back-iron components using manufactured stators. This gap in understanding prevents a comprehensive assessment of the true impact of using oriented steel in segmented stator construction for core loss improvement. In this work, the loss of each tooth and back-iron segment is calculated by conducting experiments with three different electromagnetic devices, specifically H-shaped steel laminations. By comparing the results from three manufactured stators, we elucidate the influence of oriented steel in proportion to the segmented stator construction.

关键词： Electromagnetic devices Stator cores Lamination Core loss Energy conversion Loss measurement Iron Sensors Steel Stress

来源：评论

学校读者我要写书评

暂无评论

Flexibility Prediction of Aggregated Electric Vehicles and Domestic Hot Water systems in Smart Grids

引用

engineering 2021年第8期7卷 1101-1114页

作者： Junjie Hu Huayanran Zhou Yihong Zhou Haijing Zhang Lars Nordströmd Guangya Yang State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources(North China Electric Power University) Beijing 102206China Division of Electric Power and Energy Systems School of Electrical Engineering and Computer ScienceKTH Royal Institute of TechnologyStockholm 10044Sweden Center for Electric Power and Energy Department of Electrical Engineering Technical University of DenmarkKgs Lyngby 2800Denmark

With the growth of intermittent renewable energy generation in power grids,there is an increasing demand for controllable resources to be deployed to guarantee power quality and frequency *** flexibility of demand response(DR)resources has become a valuable solution to this ***,existing research indicates that problems on flexibility prediction of DR resources have not been *** study applied the temporal convolution network(TCN)-combined transformer,a deep learning technique to predict the aggregated flexibility of two types of DR resources,that is,electric vehicles(EVs)and domestic hot water system(DHWS).The prediction uses historical power consumption data of these DR resources and DR signals(DSs)to facilitate *** prediction can generate the size and maintenance time of the aggregated *** accuracy of the flexibility prediction results was verified through simulations of case *** simulation results show that under different maintenance times,the size of the flexibility *** proposed DR resource flexibility prediction method demonstrates its application in unlocking the demand-side flexibility to provide a reserve to grids.

关键词： Load flexibility Electric vehicles Domestic hot water system Temporal convolution network-combined transformer Deep learning

来源：评论

学校读者我要写书评

暂无评论

Assessment of Protection Schemes and their Security under Denial of Service Attacks

Assessment of Protection Schemes and their Security under De...

引用

International Conference on Environment and electrical engineering (EEEIC)

作者： Kharchouf Ibtissam Mahmoud S. Abdelrahman Abdulmeen Alrashide Osama A. Mohammed Department of Electrical and Computer Engineering Energy Systems Research Laboratory Florida International University Miami Fl USA Department of Electrical &#x0026 Computer Engineering Florida International University Miami FL USA

ISBN: (数字)9781665485371

ISBN: (纸本)9781665485388

The widespread use of information and communication technology in today's electrical grid makes it increasingly vulnerable to cyber-attacks resulting in major operational and security issues. The efficiency assessment of cyber threats and their negative impact on the system is important but challenging to detect, mitigate, or prevent. Conducting such evaluation on real systems infrastructure is impractical or even impossible. In this paper, we discuss the capabilities that we have in our laboratory facilities at the FIU's smart grid testbed research facility. The testbed was built as an integrated hardware-based AC/DC system where the hardware, software, and communication-based technology can be used to envision a complete Cyber-Physical smart grid framework. Our focus is on the substation automation system where we discuss the IEC 61850 security vulnerabilities and further assess the effect of Denial of Service (DoS) attacks on the physical system. The DoS is being performed in two forms flooding attack and GOOSE poisoning attack. A case study of a transmission line fault of the proposed protection scheme is being conducted. Comparison and evaluation of the impact of DoS cyber-attacks on the physical system are discussed. The experimental results showed the impact of DoS attacks on the protection scheme's dependability and security, where the need to develop detection and mitigation techniques to overcome the IEC 61850 vulnerabilities.

关键词： Power transmission lines Substation automation Software Hardware Real-time systems Smart grids Information and communication technology

来源：评论

学校读者我要写书评

暂无评论

Single-Phase and Two-Phase Liquid Immersion Cooling of Data Center Power Supply Units for Heat Capture

Single-Phase and Two-Phase Liquid Immersion Cooling of Data ...

引用

Intersociety Conference on Thermal and Thermomechanical Phenomena in Electronic systems (ITHERM)

作者： Haoyun Qiu Pouya Kabirzadeh Vivek S. Garimella Arjit Bali Keerthivasan Gurusami Kang Joon Lee Andrew Stillwell Todd Salamon Nenad Miljkovic Department of Mechanical Science and Engineering University of Illinois Urbana-Champaign Urbana IL Department of Electrical and Computer Engineering University of Illinois Urbana-Champaign Urbana IL Optical Systems and Device Research Laboratory Nokia Bell Labs Murray Hill NJ

ISBN: (数字)9798350364330

ISBN: (纸本)9798350364347

Data center power supply units (PSU) have high power density due to the increasing power demand and their low profiles. Air cooling proves to be increasingly difficult in mitigating the hot spots, and it also consumes extra energy in fluid delivery, air conditioning, and rejection to the ambience. In this work, we redesign and modify the PSU cooling infrastructure and adopt quiescent immersion cooling. This design removes all active air-cooling elements and enables heat capture. The PSU used in the experiments is a 2 kW 80 Plus Platinum commercial unit (Bel PET2000-12-074RA). The cooling performance was characterized by tracking the steady-state case temperatures of the switching semiconductors. Flutec PP1 was used to study the cooling performance variations with respect to PSU load and capture temperature. Conventional fan-cooled PSU with heat sinks served as the benchmark. Experiments show that two-phase immersion cooling grants an overall enhancement of 4.4× over the original air-cooling approach at 40 °C heat capture. The results suggest that heat rejection from the dielectric fluid to the riding heatsink is the main bottleneck, and further reduction of the thermal resistance would allow heat capture at a temperature closer to the liquid boiling point. The PSU thermal management approach studied here can help lower data center power usage effectiveness (PUE) while increasing PSU power delivery density.

关键词： Power system measurements Cooling Density measurement Thermal resistance Thermomechanical processes Immersion cooling Switches Thermal management Resistance heating Data center power

来源：评论

学校读者我要写书评

暂无评论

GNS3 Communication Network Emulation for Substation GOOSE Based Protection Schemes

GNS3 Communication Network Emulation for Substation GOOSE Ba...

引用

International Conference on Environment and electrical engineering (EEEIC)

作者： Abdulmueen Alrashide Mahmoud S. Abdelrahman Ibtissam Kharchouf Osama A. Mohammed Department of Electrical and Computer Engineering Florida International University Energy Systems Research Laboratory Miami Fl USA Department of Electrical &#x0026 Computer Engineering Florida International University Miami FL USA

ISBN: (数字)9781665485371

ISBN: (纸本)9781665485388

This paper presents a communication network model used to study the impact of the communication layer on smart grid protection schemes. Communication failure due to hardware malfunction or cyber-attack could lead to major impacts on the smart grid. Some critical devices require real-time data or close to real-time to make the right decision at the right time and keep the system in a stable zone, such as a protection relay. Active man in the middle attack adds additional latency to the packet delivery. A false data injection attack could drive the system to an unstable point, eventually leading to a blackout. This paper designed and implemented communication emulation model for a local area network on the FIU smart grid testbed. Two cases were tested in the developed communication model. In the first case, two physical raspberry pi boards were used to represent two nodes in the smart grid and one traffic generated within the virtual network. In the second case, five ABB Protection Relays and COM600 substation automation devices were connected to GNS3. The two cases showed that GNS3 could be used to emulate the communications network and study the impact of the network performance on the real-world substation environment.

关键词： Performance evaluation LAN emulation Substation automation Emulation Europe Real-time systems Hardware

来源：评论

学校读者我要写书评

暂无评论

H∞optimal control design of static var compensator coupling hybrid active power filter based on harmonic state-space modeling

引用

CPSS Transactions on Power Electronics and Applications 2021年第3期6卷 227-234页

作者： Gong, Cheng Sou, Wai-Kit Lam, Chi-Seng State Key Laboratory of Analog and Mixed-Signal VLSI University of Macau Macao 999078 China also with the Institute of Microelectronics University of Macau Macao 999078 China and also with the Department of Electrical and Computer Engineering Faculty of Science and Technology University of Macau Macao 999078 China

Compared with the conventional active power filter (APF), the static var compensator coupling hybrid active power filter (SVC-HAPF) has distinct characteristics of low DC-link operating voltage, which can lower the system and operational costs. It also has a wider operational range than the conventional hybrid active power filter (HAPF). In this paper, a harmonic state-space (HSS) modeling is firstly proposed to address the nonlinearity issue of the SVC-HAPF. The HSS based SVC-HAPF model is linear time-invariant (LTI), which enables the optimal control techniques. Then, the linear matrix inequality (LMI) based H∞ optimal control design is proposed, which finds the optimal controller parameters via convex optimization algorithm. The proposed controller for the SVC-HAPF achieves high steady-state accuracy, fast transient response, and fixed switching frequency simultaneously. Finally, simulation and experimental results are also provided to verify the effectiveness and performance of the optimal controller for the SVC-HAPF in comparison with the recent developed state-of-the-art multi-quasi-proportional-resonant (MQPR) controller, which shows superior control performances. © 2017 CPSS.

关键词： State space methods

来源：评论

学校读者我要写书评

暂无评论

6th Place Solution to Google Universal Image Embedding

arXiv

引用

arXiv 2022年

作者： Gkelios, Socratis Kastellos, Anestis Chatzichristofis, Savvas A. Department of Electrical and Computer Engineering Democritus University of Thrace Greece Intelligent Systems Laboratory Department of Computer Science Neapolis University Pafos Cyprus

This paper presents the 6th place solution to the Google Universal Image Embedding competition on Kaggle. Our approach is based on the CLIP architecture;a powerful pre-trained model used to learn visual representations from natural language supervision. We also utilized the SubCenter ArcFace loss with dynamic margins to improve the distinctive power of class separability and embeddings. Finally, a diverse dataset has been created based on the test’s set categories and the leaderboard’s feedback. By carefully crafting a training scheme to enhance transfer learning, our submission scored 0.685 on the private leaderboard. Copyright © 2022, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

A 23-nA Quiescent Current Output-Capacitorless LDO Regulator for IoT Devices

A 23-nA Quiescent Current Output-Capacitorless LDO Regulator...

引用

International Conference on ASIC

作者： Shengnan Zhou Xiangyu Mao Cheng Huang Rui P. Martins Yan Lu State Key Laboratory of Analog and Mixed-Signal VLSI Institute of Microelectronics and FST-DECE University of Macau Macao China Department of Electrical and Computer Engineering Iowa State University Ames USA

This paper presents an ultra-low quiescent current output-capacitorless low dropout regulator (OCL-LDO) with fast transient response. We design a rail-to-rail error amplifier with improved adaptive biasing, which provides a limited bias current at heavy load for better load regulation. The buffer with adaptive biasing and almost zero input-output voltage shift and embedded body-bias, combines the error amplifier and the gate of M P . The proposed LDO is designed in a 65-nm CMOS process. Simulation result shows that the proposed LDO consumes a quiescent current of only 23 nA at a supply voltage of 0.8 V. The voltage undershoot is 98 mV during a 20-mA maximum load transient. And we obtain a FOM T of 0.00023 ps.

关键词：

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：