检索结果-内蒙古大学图书馆

Edge-Driven Industrial Computing Power Networks: Digital Twin-Empowered Service Provisioning by Hybrid Soft Actor-Critic

引用

IEEE Transactions on Vehicular Technology 2025年第5期74卷 8095-8109页

作者： Zhang, Long Song, Deng-Ao Zhang, Hongliang Tian, Ni Zhuang, Zirui Niyato, Dusit Han, Zhu Hebei University of Engineering School of Information and Electrical Engineering Handan056038 China Peking University State Key Laboratory of Advanced Optical Communication Systems and Networks School of Electronics Beijing100871 China Beijing University of Posts and Telecommunications State Key Laboratory of Networking and Switching Technology Beijing100876 China Nanyang Technological University College of Computing and Data Science 639798 Singapore University of Houston Department of Electrical and Computer Engineering HoustonTX77004 United States Kyung Hee University Department of Computer Science and Engineering Seoul446-701 Korea Republic of

With the proliferation of data-intensive industrial applications, the collaboration of computing powers among standalone edge servers is vital to provision such services for smart devices. In this paper, we propose an edge-driven industrial computing power network (CPN) by orchestrating the computing and network resources of edge servers through the centralized resource scheduling and decentralized task computing. However, efficient task offloading and collaborative processing is challenging, which requires higher degrees of network automation and intelligence. Therefore, we incorporate digital twins (DTs) into the edge-driven CPN architecture, where the DTs are created as the digital replicas to assist both the computation offloading and collaborative processing. A joint optimization problem of the computing power assignment, service association, task partition, and transmit power control is formulated for maximizing the system average weighted utility. Due to the temporal-spatial variability of tasks and the resulted dynamic environment, we transform the original problem as a Markov decision process aiming at maximizing the long-term average weighted utility. To efficiently handle the high-dimensional discrete-continuous action space, a hybrid soft actor-critic based deep reinforcement learning algorithm is developed for optimizing the joint design. Simulation results validate the superiority of our proposed algorithm over the benchmarks, showing the significant gains obtained by integrating DTs into the edge-driven CPN. © 1967-2012 IEEE.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Isolated Single-stage Three-phase AC/DC Converter using Bidirectional Switches

Isolated Single-stage Three-phase AC/DC Converter using Bidi...

引用

2023 IEEE Energy Conversion Congress and Exposition, ECCE 2023

作者： Narwal, Ramandeep Wong, Isaac Bhattacharya, Subhashish Baliga, B. Jayant Hopkins, Douglas C. North Carolina State University Freedm Systems Center Department of Electrical and Computer Engineering RaleighNC27695 United States

ISBN: (纸本)9798350316445

The advent of the SiC Bidirectional FET (BiDFET), a monolithic 1.2 kV bidirectional switch, has rendered the single-stage three-phase AC/DC converter topology a promising approach for implementing AC/DC converters. This topology, which integrates a full-bridge converter with a single-phase to three-phase matrix converter via a high-frequency transformer, is particularly suitable for applications requiring galvanic isolation, buck-boost functionality, and bidirectional power flow. The single-stage design eliminates the need for bulky and unreliable electrolytic capacitors, and utilizes a single magnetic component for power transfer. In the matrix converter, bidirectional switches, which were traditionally implemented using combinations of multiple semiconductor devices such as MOSFETs, IGBTs, and diodes, can now be realized using the single-chip solution, BiDFET. This advancement leads to a lower switch count, compact converter implementation, with lower inductance commutation cells, thereby enhancing the overall efficiency and compactness of the system. The paper presents a unified model of the converter, considering all control parameters, including the duty cycles and phase shift of transformer voltages. Detailed expressions for power transfer, transformer currents, and currents at AC and DC ports are provided. Additionally, the paper outlines the conditions necessary for soft-switching of all switches and the commutation schemes required for the practical implementation of the matrix converter modulation scheme. A hardware prototype of a 10 kW, 480 VRMS, LL/ 800 V AC/DC system has been developed, and experimental results are presented to demonstrate its performance. © 2023 IEEE.

关键词： BiDFET Bidirectional switches commutation dual active bridge (DAB) four-quadrant switches isolated AC/DC converter matrix converter modeling modulation SiC bidirectional FET soft switching zero voltage switching (ZVS)

来源：评论

学校读者我要写书评

暂无评论

Dynamic Pulsed Load Mitigation in PV-Battery-Supercapacitor systems: A Hybrid PI-NN Controller Approach

Dynamic Pulsed Load Mitigation in PV-Battery-Supercapacitor ...

引用

2023 IEEE Design Methodologies Conference, DMC 2023

作者： Aghmadi, Ahmed Ali, Ola Hussein, Hossam Mohammed, Osama A. Florida International University Energy Systems Research Laboratory Department of Electrical and Computer Engineering MiamiFL33174 United States

ISBN: (纸本)9798350315547

DC microgrids are becoming more and more popular, however there are still difficulties involving ongoing instability that are mostly caused by imbalances in energy supply and demand, particularly in situations with pulse load or variable pulse load patterns. Innovative solutions are required since these disruptive load dynamics significantly decrease the effectiveness of conventional PV-Battery control systems. conventional Proportional-Integral (PI) controllers, although widely employed, may encounter limitations when confronted with the unique challenges posed by specific load patterns, notably pulse load scenarios. These dynamic load profiles, characterized by rapid and unpredictable changes. The inherent non-linearity and variability in such load conditions can result in suboptimal control performance, potentially leading to voltage instability and transients within the microgrid. To overcome these issues and improve control performance, the introduction of Neural Network (NN) controllers promises to be a potential approach. NN controllers have a remarkable capacity to learn and adapt from data, making them particularly well-suited for situations characterized by non-linear and dynamic load behavior. In this study, a hybrid PI-NN (Proportional-Integral Neural Network) controller is introduced to reduce load effects, especially pulsed loads, in PV systems with batteries and supercapacitors. This method efficiently optimizes energy storage. For voltage control, it utilizes a PI system, which divides the reference current into low and high-frequency components for battery and supercapacitor control. For enhanced sensitivity and dynamic responsiveness, neural network control replaces conventional PIs. The performance of the hybrid PI-NN controller is evaluated in this work, with an emphasis on its potential to improve PV system efficiency in severe load circumstances. © 2023 IEEE.

关键词： Supercapacitor

来源：评论

学校读者我要写书评

暂无评论

Enhancing Solar Radiation Forecasting with Hybrid Ensemble Empirical Mode Decomposition and Machine Learning Techniques

Enhancing Solar Radiation Forecasting with Hybrid Ensemble E...

引用

2023 IEEE International Conference on Environment and electrical engineering and 2023 IEEE Industrial and Commercial Power systems Europe, EEEIC / I and CPS Europe 2023

作者： Aghmadi, Ahmed Mohammed, Osama Florida International University Energy Systems Research Laboratory Department of Electrical and Computer Engineering MiamiFL33174 United States

ISBN: (纸本)9798350347432

The importance of short-term solar radiation forecasting for power system use and management cannot be overstated. However, Non-stationarity and unpredictability make accurate forecasting difficult. Time series approaches are suitable for forecasting stationary time series derived from a non-stationary sequence. Empirical Mode Decomposition (EMD) and Ensemble Empirical Mode Decomposition (EEMD) are time-domain decomposition methods used to separate the components of the original solar radiation time series that have distinct time1-scale characteristics. As a result, the components are forecasted using the Back Propagation Neural Network (BPNN) model, which is a simple and effective machine learning method. This paper presents a hybrid EMD/EEMD-BPNN model for predicting short-term solar irradiance. To identify unique data information at different time scales, EMD/EEMD first breaks up the solar radiation time series into several stationary or fundamental sub-series. The next step is to create BPNN models with specified parameters for each subsequence to forecast new ones. Finally, each subsequence's projected value is combined to generate the final forecast result. The accuracy of solar forecasts has greatly increased, especially when utilizing hybrid methods. Furthermore, using the proposed hybrid technique for multistep forecasting resulted in even more improvement. The basic BPNN model for 15 min time step achieves predicting with a root mean square error (RMSE) of roughly 416.04 W/m2 for 15min;however, this error decreases to 65.25 W/m2 with the EMD-Hybrid Model, and 32.86 W/m2 with the EEMD-Hybrid Model. In addition, the results of the skill score have proven clearly that EMD/EEMD-BPNN Model performs better compared to typical BPNN using several meteorological inputs © 2023 IEEE.

关键词： Empirical mode decomposition

来源：评论

学校读者我要写书评

暂无评论

Stochastic Characterization-Based Performance Analysis of an Emulated Communication Network for Cyber-Physical Shipboard Power systems

Stochastic Characterization-Based Performance Analysis of an...

引用

2023 IEEE Electric Ship Technologies Symposium, ESTS 2023

作者： Abdelrahman, Mahmoud S. Nguyen, Tung-Lam Mohammed, Osama A. Florida International University Energy Systems Research Laboratory Department of Electrical and Computer Engineering MiamiFL33174 United States

ISBN: (纸本)9781665465151

Emerging advanced and innovative Information and Communication Technologies (ICT), automation strategies, and associated algorithms in the traditional power system have transformed it into a Cyber-Physical Power System (CPPS). Energy management and control are crucial in the Shipboard Power System operation. For instance, to meet the ship's energy and other ancillary demands, especially the mission-critical loads that require practical and secure network communication. Therefore, a comprehensive modeling and testing and validation approach was developed in this paper. This enables flexible system-level aspect evaluation through numerous experiments, including virtual, real, and mixed lab settings. This paper presents a scalable and flexible three-layer cyber-physical co-simulation platform implemented in the FIU smart grid testbed. This includes real-time power system simulation using OPAL-RT, ns3 for communication network emulation, and MATLAB/SIMULINK for implementing various applications. To demonstrate the platform's effective operation, energy management with a central controller for SPS was configured and implemented to test the communication network performance by creating tools to characterize the network latency for this application. © 2023 IEEE.

关键词： Ships

来源：评论

学校读者我要写书评

暂无评论

RUL Estimation for Power Electronic Devices Using RNNs

RUL Estimation for Power Electronic Devices Using RNNs

引用

Prognostics and System Health Management Conference (PHM)

作者： Congrui Cai Zhonghai Lu Embedded Systems Master Program School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Department of Electrical Engineering School of Electrical Engineering and Computer Science KTH Royal Institute of Technology

ISBN: (数字)9798350360585

ISBN: (纸本)9798350360592

Recurrent Neural Networks (RNNs) are commonly used in data-driven approaches to estimate the Remaining Useful Lifetime (RUL) of power electronic devices. RNNs are preferred because their intrinsic feedback mechanisms are better suited to model time-series data. However, the impact of RNN complexity on estimation accuracy is rarely discussed in the literature. This issue is important because choosing a lower-complexity model that delivers the same or similar performance as a higher-complexity model can increase implementation efficiency. In the paper, we use three RNN models, namely, the vanilla version, LSTM (Long Short Term Memory) and GRU (Gated Recurrent Unit) to conduct RUL estimation for power electronic devices. We use two accelerated aging datasets, one dataset targeting the package failure of MOSFETs, and the other dataset targeting package failure of power diodes. Our study shows that a lower-complexity RNN does not necessarily deliver a lower performance. Similarly, a higher-complexity model does not assure a higher performance. As such, our work highlights the importance of selecting a proper neural network for RUL estimation not biased towards complex models. This is especially useful and important for implementing such RUL estimation techniques in embedded resource-constrained and speed-limited computins platforms.

关键词： Performance evaluation Semiconductor device modeling Recurrent neural networks Computational modeling Estimation Power electronics Data models

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient and Latency-Aware Task Offloading for Industrial Cloud-Edge systems with Heterogeneous CPUs and GPUs

引用

IEEE Internet of Things Journal 2025年第13期12卷 25757-25772页

作者： Zhai, Jiahui Bi, Jing Yuan, Haitao Zhang, Jia Buyya, Rajkumar Beijing University of Technology College of Computer Science Beijing100124 China Beihang University School of Automation Science and Electrical Engineering Beijing100191 China Southern Methodist University Department of Computer Science DallasTX75206 United States Lab School of Computing and Information Systems MelbourneVIC3010 Australia

The unprecedented prosperity of the Industrial Internet of Things has significantly driven the transition from traditional manufacturing to intelligent one. In industrial environments, resource-constrained industrial equipments (IEs) often fail to meet the diverse demands of numerous compute-intensive and latency-sensitive tasks. Mobile edge computing has emerged as an innovative paradigm to reduce latency and energy consumption for IEs. However, the increasing number of IEs in industrial settings relies on heterogeneous platforms integrated with different processing units, i.e., CPUs and GPUs. To address this challenge, we propose a software-defined networking-based equipment-edge-cloud architecture with three-stage heterogeneous computing. This architecture accurately models the multi-task processing of both scientific and concurrent workflows in real industrial environments. We formulate a joint optimization problem to simultaneously minimize task completion time and energy consumption for IEs. To solve this problem, we design an Improved Two-stage Multi-Objective Evolutionary Algorithm (IT-MOEA). IT-MOEA employs a novel multi-objective grey wolf optimizer based on manta ray foraging and associative learning to accelerate convergence in the early evolution stages and adopts a diversity-enhancing immune algorithm to enhance diversity in the later stages. Simulation results with various benchmarks demonstrate that IT-MOEA outperforms several state-of-the-art single-objective optimization algorithms by an average of 24.7% and multi-objective algorithms by 41.0% in terms of delay and energy consumption. © 2025 IEEE.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

CONTINUOUS-TIME IDENTIFICATION OF DYNAMIC STATE-SPACE MODELS BY DEEP SUBSPACE ENCODING 11

CONTINUOUS-TIME IDENTIFICATION OF DYNAMIC STATE-SPACE MODELS...

引用

11th International Conference on Learning Representations, ICLR 2023

作者： Beintema, Gerben I. Schoukens, Maarten Tóth, Roland Department of Electrical Engineering Eindhoven University of Technology Netherlands Systems and Control Laboratory Institute for Computer Science and Control Budapest Hungary

Continuous-time (CT) modeling has proven to provide improved sample efficiency and interpretability in learning the dynamical behavior of physical systems compared to discrete-time (DT) models. However, even with numerous recent developments, the CT nonlinear state-space (NL-SS) model identification problem remains to be solved in full, considering common experimental aspects such as the presence of external inputs, measurement noise, latent states, and general robustness. This paper presents a novel estimation method that addresses all these aspects and that can obtain state-of-the-art results on multiple benchmarks with compact fully connected neural networks capturing the CT dynamics. The proposed estimation method called the subspace encoder approach (SUBNET) ascertains these results by efficiently approximating the complete simulation loss by evaluating short simulations on subsections of the data, by using an encoder function to estimate the initial state for each subsection and a novel state-derivative normalization to ensure stability and good numerical conditioning of the training process. We prove that the use of subsections increases cost function smoothness together with the necessary requirements for the existence of the encoder function and we show that the proposed state-derivative normalization is essential for reliable estimation of CT NL-SS models. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

Frequency Stability Enhancement in Low-Inertia Power System Using an Optimal Control Scheme

Frequency Stability Enhancement in Low-Inertia Power System ...

引用

2023 IEEE International Conference on Environment and electrical engineering and 2023 IEEE Industrial and Commercial Power systems Europe, EEEIC / I and CPS Europe 2023

作者： Ali, Ola Mohammed, Osama A. Florida International University Energy Systems Research Laboratory Department of Electrical and Computer Engineering MiamiFL33174 United States

ISBN: (纸本)9798350347432

Power system dynamics have significantly changed with the global integration of renewable energy sources (RESs). Traditionally, the stored kinetic energy is used for compensating the generation mismatch using the rotating mass of the Synchronous Generators (SGs). With the increase in RESs penetration, SGs are being replaced by inverter-based RESs generation systems which are decoupled from the power systems through power converters. Therefore, the total inertia of the system has decreased, and the system's stability is significantly impacted as the value of the rate of change of frequency (ROCOF) and frequency deviations will be increased. To overcome these challenges, inertia emulation from various energy storage systems (ESS) is used to act as a virtual source of inertia power. This work presents an isolated microgrid (MG) that includes conventional power generation sources and RESs, and an optimal virtual inertia (VI) control loop is proposed for frequency stability enhancement. Supercapacitors (SC) bank with a PID controller presents the VI control loop and acts as a supplementary source for inertia power to support the frequency stability of the system. A genetic algorithm (GA) is used as an optimization technique to get the optimal values of the PID controller gains. The performance of the islanded MG with the proposed optimal control scheme is examined under different operating conditions with varying levels of RESs penetration and system parameters uncertainties. The proposed technique showed its effectiveness and robustness over the system's operation without VI control for keeping the system stable under different operating conditions. © 2023 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

State of Charge Estimation Using Data-Driven Models for Inverter-Based systems

State of Charge Estimation Using Data-Driven Models for Inve...

引用

2023 IEEE Design Methodologies Conference, DMC 2023

作者： Hussein, Hossam Donekal, Abhishek Aghmadi, Ahmed Rafin, S M Sajjad Hossain Mohammed, Osama A. Florida International University Energy Systems Research Laboratory Department of Electrical and Computer Engineering MiamiFL33174 United States

ISBN: (纸本)9798350315547

Lithium-ion batteries are playing a critical role in many applications nowadays, from small-scale electronic devices to grid-scale storage systems. To maintain its continuous operation and increase its life span, the state of charge of the battery should be determined to ensure safe operating conditions. Among the existing charge estimation methods, data-driven models are flourishing these days. This work presents a state of charge estimation for the eFlex 52.8V/5.4 kWh lithium iron phosphate battery pack at the Energy systems Research Laboratory (ESRL) at FIU. Three different machine learning models were implemented and trained through Python code to achieve the most accurate SoC estimation. Although the three proposed models can efficiently estimate the battery's SoC with an acceptable error percentage, the random forest regression model has proven its outperformance among the selected models with a percentage mean square error less than 0.01. © 2023 IEEE.

关键词： Lithium-ion batteries

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：