检索结果-内蒙古大学图书馆

Learning the continuous-time optimal decision law from discrete-time rewards

National Science Open 2024年第5期3卷 130-147页

作者： Ci Chen Lihua Xie Kan Xie Frank Leroy Lewis Yilu Liu Shengli Xie School of Automation Guangdong University of TechnologyGuangdong Key Laboratory of IoT Information TechnologyGuangzhou 510006China Key Laboratory of Intelligent Information Processing and System Integration of IoT Ministry of EducationGuangzhou 510006China School of Electrical and Electronic Engineering Nanyang Technological UniversitySingapore 639798Singapore 111 Center for Intelligent Batch Manufacturing Based on IoT Technology Guangzhou 510006China UTA Research Institute the University of Texas at ArlingtonFort Worth 76118USA Department of Electrical Engineering and Computer Science University of TennesseeKnoxville 37996USA Oak Ridge National Laboratory Oak Ridge 37830USA Guangdong-HongKong-Macao Joint Laboratory for Smart Discrete Manufacturing Guangzhou 510006China

The concept of reward is fundamental in reinforcement learning with a wide range of applications in natural and social *** an interpretable reward for decision-making that largely shapes the system's behavior has always been a challenge in reinforcement *** this work,we explore a discrete-time reward for reinforcement learning in continuous time and action spaces that represent many phenomena captured by applying physical *** find that the discrete-time reward leads to the extraction of the unique continuous-time decision law and improved computational efficiency by dropping the integrator operator that appears in classical results with integral *** apply this finding to solve output-feedback design problems in power *** results reveal that our approach removes an intermediate stage of identifying dynamical *** work suggests that the discrete-time reward is efficient in search of the desired decision law,which provides a computational tool to understand and modify the behavior of large-scale engineering systems using the optimal learned decision.

关键词： continuous-time state and action decision law learning discrete-time reward dynamical systems reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Energy Management and Optimization of Vehicle-to-grid systems for Wind Power Integration

引用

CSEE Journal of Power and Energy systems 2021年第1期7卷 172-180页

作者： Wei Wang Liu Liu Jizhen Liu Zhe Chen the State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources North China Electric Power UniversityBeijing 102206China the School of Control and Computer Engineering North China Electric Power UniversityBeijing 102206China with the Department of Energy Technology Aalborg University9220 AalborgDenmark

An approach to smoothing the fluctuations of largescale wind power is investigated using vehicle-to-grid(V2G)***,an energy management and optimization system is designed and *** using the wavelet packet decomposition method,the target grid-connected wind power,the required electric vehicle(EV)power,and supercapacitor power are *** energy management model for EVs is then developed by introducing a knapsack problem that can evaluate the needs of an EV ***,an optimized dispatch strategy for EVs and wind power is developed by using a dynamic programming method.A case study demonstrates that the energy management and optimization method for V2G systems achieves noticeable performance improvements over benchmark techniques.

关键词： Dynamic programming electric vehicle knapsack problem wavelet packet decomposition wind power integration

来源：评论

学校读者我要写书评

暂无评论

DDPS: Dynamic Differential Pricing-based Edge Offloading system with Energy Harvesting Devices

arXiv

引用

arXiv 2024年

作者： Xue, Hai Xia, Yun Xiong, Neal N. Zhang, Di Pei, Songwen School of Optical- Electrical and Computer Engineering University of Shanghai for Science and Technology Shanghai200093 China Department of Computer Science and Mathematics Sul Ross State University AlpineTX79830 United States School of Electrical and Information Engineering Zhengzhou University the Henan International Joint Laboratory of Intelligent Health Information System the National Telemedicine Center National Engineering Laboratory for Internet Medical Systems and Applications Zhengzhou450001 China

Mobile edge computing (MEC) paves the way to alleviate the burden of energy and computation of mobile users (MUs) by offloading tasks to the network edge. To enhance the MEC server utilization by optimizing its resource allocation, a well-designed pricing strategy is indispensable. In this paper, we consider the edge offloading scenario with energy harvesting devices, and propose a dynamic differential pricing system (DDPS), which determines the price per unit time according to the usage of computing resources to improve the edge server utilization. Firstly, we propose an offloading decision algorithm to decide whether to conduct the offloading operation and how much data to be offloaded if conducted, the algorithm determines offloading operation by balancing the energy harvested with the energy consumed. Secondly, for the offloading case, we formulate the game between the MUs and the server as a Stackelberg game, and propose a differential pricing algorithm to determine the optimal computing resources required by MUs. Furthermore, the proposed algorithm also reallocates computing resources for delay-sensitive devices while server resources are surplus after the initial allocation, aiming to make full use of the server computing resources. Extensive simulations are conducted to demonstrate the effectiveness of the proposed DDPS scheme. Copyright © 2024, The Authors. All rights reserved.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Critical Factors of Immersive Learning in Higher Education: A systematic Literature Review

Critical Factors of Immersive Learning in Higher Education: ...

引用

International Conference on ICT For Smart Society (ICISS)

作者： Sunardi Meyliana Arief Ramadhan Yusep Rosmansyah Computer Science Department BINUS Graduate Program Doctor of Computer Science Bina Nusantara University Jakarta Indonesia Information System Departement School of information system Bina Nusantara University Jakarta Indonesia School of Computing Telkom University Bandung Indonesia School of electrical engineering and informatics Bandung Institute of Technology Bandung Indonesia

Immersive learning has gained significant attention with the rising trend of spatial computing, particularly in the after-pandemic era. Numerous research has explored the potential of immersive learning in higher education, primarily on the educational sector. However, prior research has frequently focused too narrowly on the effects of technology and neglected to address the crucial element influencing successful immersive learning in higher education. This study seeks to pinpoint the crucial element contributing to the development of immersive learning experiences. The methodology uses a systematic literature review (SLR) from 2018 up to 2023 to investigate the critical factors of immersive Learning in Higher Education. From the 728 papers initially retrieved, 274 were considered potential candidates, and ultimately, 86 articles were selected based on their relevance to the research question. The results reveal that the critical factors include learning design, technology, immersion, engagement, interactivity, and usability. Academic interests will benefit from this SLR's consequences as institutions create models for designing suitable immersive learning, especially within the context of higher education.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Sensitivity Analysis for Stopping Criteria with Application to Organ Transplantations

Sensitivity Analysis for Stopping Criteria with Application ...

引用

Simulation Winter Conference

作者： Xingyu Ren Michael C. Fu Steven I. Marcus Department of Electrical and Computer Engineering Institute for System Research University of Maryland College Park MD USA Robert H. Smith School of Business Institute for System Research University of Maryland College Park MD USA

We consider a stopping problem and its application to the decision-making process regarding the optimal timing of organ transplantation for individual patients. At each decision period, the patient state is inspected and a decision is made whether to transplant. If the organ is transplanted, the process terminates; otherwise, the process continues until a transplant happens or the patient dies. Under suitable conditions, we show that there exists a control limit optimal policy. We propose a smoothed perturbation analysis (SPA) estimator for the gradient of the total expected discounted reward with respect to the control limit. Moreover, we show that the SPA estimator is asymptotically unbiased.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Revisiting the Curvature-aided IAG: Improved Theory and Reduced Complexity

引用

IFAC-PapersOnLine 2023年第2期56卷 5221-5226页

作者： Erik Berglund Sarit Khirirat Xuyang Wu Sindri Magnússon Mikael Johansson School of Electrical Engineering and Computer Science KTH Royal Institute of Technology SE 100 44 Stockholm Sweden Department of Machine Learning Mohamed bin Zayed University of Artificial Intelligence Abu Dhabi UAE Department of Computer and System Science Stockholm University Stockholm Sweden

The curvature-aided IAG (CIAG) algorithm is an efficient asynchronous optimization method that accelerates IAG using a delay compensation technique. However, existing step-size rules for CIAG are conservative and hard to implement, and the Hessian computation in CIAG is often computationally expensive. To alleviate these issues, we first provide an easy-to-implement and less conservative step-size rule for CIAG. Next, we propose a modified CIAG algorithm that reduces the computational complexity by approximating the Hessian with a constant matrix. Convergence results are derived for each algorithm on both convex and strongly convex problems, and numerical experiments on logistic regression demonstrate their effectiveness in practice.

关键词： asynchronous optimization delay compensation incremental aggregated gradient

来源：评论

学校读者我要写书评

暂无评论

Detail-Enhancing Framework for Reference-Based Image Super-Resolution

arXiv

引用

arXiv 2024年

作者： Wang, Zihan Xiong, Ziliang Tang, Hongying Yuan, Xiaobing Shanghai Institution of Micro-system and Information Technology University of Chinese Academy of Science China Computer Vision Laboratory Department of Electrical Engineering LiU Sweden School of Information Science and Technology Shanghai Tech University China

Recent years have witnessed the prosperity of reference-based image super-resolution (Ref-SR). By importing the high-resolution (HR) reference images into the single image super-resolution (SISR) approach, the ill-posed nature of this long-standing field has been alleviated with the assistance of texture transferred from reference images. Although the significant improvement in quantitative and qualitative results has verified the superiority of Ref-SR methods, the presence of misalignment before texture transfer indicates room for further performance improvement. Existing methods tend to neglect the significance of details in the context of comparison, therefore not fully leveraging the information contained within low-resolution (LR) images. In this paper, we propose a Detail-Enhancing Framework (DEF) for reference-based super-resolution, which introduces the diffusion model to generate and enhance the underlying detail in LR images. If corresponding parts are present in the reference image, our method can facilitate rigorous alignment. In cases where the reference image lacks corresponding parts, it ensures a fundamental improvement while avoiding the influence of the reference image. Extensive experiments demonstrate that our proposed method achieves superior visual results while maintaining comparable numerical outcomes. Copyright © 2024, The Authors. All rights reserved.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

Smart Lighting system for Children's Therapy to Prevent Nyctophobia Syndrome at Bedtime 4

Smart Lighting System for Children's Therapy to Prevent Nyct...

引用

4th International Conference on Cybernetics and Intelligent system, ICORIS 2022

作者： Pramono, Andi Munir, Badrul Farchan, Muchammad Budiman, Satrio Arif Azis, Baskoro Putra, Wahyu Waskito Interior Design Department School of Design Bina Nusantara University Jakarta Indonesia Brawijaya University Departemen of Neurology Malang Indonesia Institut Teknologi Sepuluh Nopember Faculty of Intelligent Electrical and Informatics Technology Department of Electrical Engineering Surabaya Indonesia Brawijaya University Information System Computer Science Faculty Malang Indonesia

ISBN: (纸本)9781665453950

Everyone has a fundamental desire for sleep. By sleeping, humans can conserve energy and replenish their stamina to optimal levels. Lighting is one component that influences the quality of a person's sleep. One of them is a person who sleeps with the lights on, suffers from nyctophobia, has poor sleep quality, and may be responsible for several illnesses. This study aims to develop a smart lighting device that will aid in treating youngsters with nyctophobia to get used to sleeping with the lights off to improve their sleep quality. The case study methodology used in this study entails the development of a prototype. This method employs an oximeter as a heart rate detector and a sensor comparison as the measurement device. Arduino Uno circuit and heart rate sensor are the main devices in this research. At the same time, the NRF 24L01 is a communication medium between the two Arduino Uno boards. The experimental measurements in normal conditions indicate that the heart rate sensor was nearly the same as the value displayed by the oximeter. Similarly, after running for 1 minute, both devices produced almost identical results, with an average difference of 1 Beats Per Minute (BPM). According to experiments with a heart rate sensor, the switch-off condition can be activated if the heart rate hits 90 BPM. In this case, the light will switch off once the heart rate hits 70 BPM, which might be used for sleeping individuals. © 2022 IEEE.

关键词： Oximeters

来源：评论

学校读者我要写书评

暂无评论

Darcy-Forchheimer mangetized flow based on differential type nanoliquid capturing Ohmic dissipation effects

引用

Propulsion and Power Research 2023年第3期12卷 443-455页

作者： M.Waqas Yunjie Xu M.Nasir Md Mottahir Alam Amjad Ali Pasha Kashif Irshad Bandar M.Fadhl M.S.Kausar NUTECH School of Applied Science and Humanities National University of TechnologyIslamabad 44000Pakistan Department of Mechanical Engineeing Lebanese American UniversityBeirutLebanon School of Engineering Huzhou UniversityHuzhou 313000China Faculty of Informatics and Computing University Sultan Zainal AbidinBesut Campus22200 BesutTereng-ganuMalaysia Department of Electrical and Computer Engineering King Abdulaziz UniversityJeddah 21589Saudi Arabia Aerospace Engineering Department King Abdulaziz UniversityJeddah 21589Saudi Arabia Interdisciplinary Research Centre for Renewable Energy and Power System(IRC-REPS) Research InstituteKing Fahd University of Petroleum and Minerals(KFUPM)Dhahran 31261Saudi Arabia Mechanical Engineering Department College of Engineering and Islamic ArchitectureUmm Al-Qura UniversityP.O.Box 5555Makkah 21955Saudi Arabia

Hydromagnetic nanoliquid establish an extraordinary category of nanoliquids that unveil both liquid and magnetic *** interest in the utilization of hydromagnetic nanoliquids as a heat transporting medium stem from a likelihood of regulating its flow along with heat transportation process subjected to an externally imposed magnetic *** analysis reports the hydromagnetic nanoliquid impact on differential type(second-grade)liquid from a convectively heated extending *** well-known Darcy-Forchheimer aspect capturing porosity characteristics is introduced for nonlinear *** conditions elaborating heat-mass transportation effect are *** addition,Ohmic dissipation and suction/injection aspects are also a part of this *** analysis is done by implementing the basic relations of fluid *** modeled physical problem is simplified through order *** resulting systems(partial differential expressions)are rendered to the ordinary ones by utilizing the apposite *** solutions are constructed employing homotopy *** and numeric result are addressed comprehensively to elaborate the nature of sundry parameters against physical *** velocity profile is suppressed with increasing Hartmann number(magnetic parameter)whereas it is enhanced with increment in material parameter(second-grade).With the elevation in thermophoresis parameter,temperature and concentration of nanoparticles are accelerated.

关键词： Darcy-Forchheimer magnetized flow Differential type nanoliquid Ohimc dissipation Robin conditions Homotopy algorithm

来源：评论

学校读者我要写书评

暂无评论

Enhancing Short-Term Load Forecasting Accuracy in the Power systems Using a Hybrid CNN-GRU Model 5

Enhancing Short-Term Load Forecasting Accuracy in the Power ...

引用

5th International Conference on electrical, Communication and computer engineering, ICECCE 2024

作者： Ahsan, Muhammad Aziz, Muhammad Osama Bokhari, Syed Ahmad Saleem Haris, Muhammad Iqbal, Mansoor Ullah, Kaleem University of Alabama at Birmingham Department of Computer Science BirminghamAL35294 United States University of Engineering and Technology Buildings Energy Research Center Peshawar Pakistan Harvard Extension School Harvard University CambridgeMA02138 United States Institute for Insight - J Mack Robinson College of Business Georgia State University Georgia United States University of Wah Department of Computer Science Wah Cantt Pakistan CASE UET Peshawar Department of Electrical Energy System Peshawar Pakistan

ISBN: (纸本)9798331529437

In modern power systems, Short-Term Load Forecasting (STLF) is critical in ensuring the dynamic allocation of operational reserves and accurate prediction of electrical load demand. STLF is pertinent to grid operators to ensure system stability, allocate generation resources efficiently, and provide adequate reserves to deal with unexpected fluctuations. Considering the pivotal role of STLF, this paper introduces a hybrid deep learning model for short-term load forecasting, combining Convolutional Neural Networks (CNN) and Gated Recurrent Units (GRU). The model features two parallel 32-filter convolutional layers (3×3 kernel, ReLU) for spatial feature extraction, followed by two series-connected GRU layers (42 units) to capture temporal dependencies. A final dense layer with ReLU activation generates the load forecast. This architecture effectively leverages CNNs for local pattern recognition and GRUs for modeling temporal sequences, offering a robust solution for accurate short-term load forecasting. Therefore, the efficacy of the CNN-GRU model is tested and validated using an extensive dataset sourced from the National Transmission & Dispatch Company (NTDC), Pakistan. The performance analysis reveals that hybrid CNN-GRU models achieve a substantial reduction in Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and Root Mean Square Error (RMSE), with values of 400.33, 2.89, 580.95, for single-step forecasts, respectively, and 1031.11, 5.31, and 733.19, for 24-hour forecasts. Furthermore, the simulation results demonstrate notable enhancements in load forecasting accuracy and robustness across various forecast horizons. © 2024 IEEE.

关键词： Convolutional neural networks

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：