检索结果-内蒙古大学图书馆

Two-layer adaptive signal control framework for large-scale dynamically-congested networks: Combining efficient Max Pressure with Perimeter Control

arXiv

引用

arXiv 2022年

作者： Tsitsokas, Dimitrios Kouvelas, Anastasios Geroliminis, Nikolas Urban Transport Systems Laboratory School of Architecture Civil and Environmental Engineering EPFL LausanneCH-1015 Switzerland Institute for Transport Planning and Systems Department of Civil Environmental and Geomatic Engineering ETH Zurich ZurichCH-8093 Switzerland

Traffic-responsive signal control has received considerable research attention, as a cost-effective and easy-to-implement network management strategy, bearing high potential to improve performance in heavily congested networks with time-dependent traffic characteristics. Max Pressure (MP) distributed controller gained significant popularity due to its theoretically proven ability of queue stabilization and throughput maximization under specific assumptions. However, its effectiveness is questionable under over-saturated conditions and queue spill-backs, while network-wide implementation is often practically limited due to high instrumentation cost that increases with the number of controlled intersections. Perimeter control (PC) based on the concept of Macroscopic Fundamental Diagram (MFD) is a state-of-the-art aggregated control strategy that regulates exchange flows between homogeneously congested regions, with the objective of maintaining maximum regional travel production and prevent over-saturation. However, homogeneity assumption is hardly realistic under congested conditions, thus compromising PC efficiency. In this paper, the effectiveness of network-wide parallel application of PC and MP strategies embedded in a two-layer control framework is assessed in a mesoscopic simulation environment. With the aim of reducing implementation cost of network-wide MP without significantly sacrificing performance gains, we evaluate partial MP deployment to subsets of nodes, indicated as critical by a node classification algorithm that we propose, based on node traffic characteristics. A modified version of Store-and-forward dynamic traffic paradigm incorporating finite queue and spill-back consideration is used to test different configurations of the two-layer framework, as well as of each layer individually, for a real large-scale network in moderate and highly congested scenarios. Results show that: (i) combined control of MP and PC outperforms separate MP and PC applic

关键词： Cost effectiveness

来源：评论

学校读者我要写书评

暂无评论

Using Weather and Schedule-Based Pattern Matching and Feature-Based Principal Component Analysis for Whole Building Fault Detection—Part I Development of the Method

引用

Journal of engineering for Sustainable Buildings and Cities 2022年第1期3卷 011002页

作者： Chen, Yimin Wen, Jin Lo, James Building Technology and Urban Systems Division Lawrence Berkeley National Laboratory 1 Cyclotron Road Berkeley 94720 CA United States Department of Civil Architectural and Environmental Engineering Drexel University 3141 Chestnut Street Philadelphia 19104 PA United States

A whole building fault (WBF) refers to a fault occurring in one component, but may cause impacts on other components or subsystems, or arise significant impacts on energy consumption and thermal comfort. Conventional methods (such as component level rule-based method or physical model-based method) which targeted at component level fault detection cannot be successfully used to detect a WBF because of the fault propagation among the closely coupled equipment or subsystems. Therefore, a novel data-driven method named weather and schedule-based pattern matching (WPM) and feature-based principal component analysis (FPCA) method for WBF detection is developed. Three processes are established in the WPM-FPCA method to address three main issues in WBF detection. First, a feature selection process is used to pre-select data measurements which represent a whole building’s operation performance under a satisfied status, namely, baseline status. Second, a WPM process is used to locate weather and schedule patterns in the historical baseline database, which are similar to that from the current/incoming operation data, and to generate a WPM baseline. Lastly, real-time PCA models are generated for both the WPM baseline data and the current operation data. Statistic thresholds used to differentiate normal and abnormal (faulty) operations are automatically generated in this PCA modeling process. The PCA models and thresholds are used to detect the WBF. This paper is the first of a two-part study. Performance evaluation of the developed method is conducted using data collected from a real campus building and will be described in the second part of this paper. Copyright © 2021 by ASME.

关键词： big data data-driven method fault detection and diagnosis feature selection HVAC systems pattern matching smart buildings whole building fault

来源：评论

学校读者我要写书评

暂无评论

A temperature-dependent model for thermal conductivity function of unsaturated soils

A temperature-dependent model for thermal conductivity funct...

引用

2021 International Foundations Congress and Equipment Expo: From Traditional to Emerging Geotechnics, IFCEE 2021

作者： Duc Cao, Toan Vahedifard, Farshid Thota, Sannith Kumar Amirlatifi, Amin Center for Advanced Vehicular Systems Dept. of Civil and Environmental Engineering Mississippi State Univ.MS United States Dept. of Civil and Environmental Engineering Mississippi State Univ.MS United States Swalm School of Chemical Engineering Mississippi State Univ.MS United States

ISBN: (数字)9780784483428

The thermal conductivity of soil is an important property in the study of several emerging geotechnical and geoenvironmental engineering applications. In this study, a temperature-dependent model for the thermal conductivity function (TCF) of unsaturated soils is established by considering the effects of temperature on pore structure, water content, and heat transfer mechanisms. Most of the existing TCF models ignore the effects of temperature on pore structure and water content by treating the thermal conductivity only as a function of temperature and isothermal degree of saturation. To address these limitations, a new TCF model is developed by considering the effects of temperature on matric suction and the soil water retention curve (SWRC). The formulation for matric suction accounts for the effects of temperature on the surface tension, contact angle, adsorption, and enthalpy of immersion per unit area. The proposed model also applies a decay function to the degree of saturation to account for the thermal conductivity function affected by heat transfer phenomena such as conduction and convection of pore water in both liquid and vapor phases and latent heat transfer due to vaporization and condensation. A comparison between the results with experimental data obtained from the literature substantiates the validity of the model. The proposed model is used in a parametric study to examine changes in the thermal conductivity of a clay soil under temperatures ranging from 25°C to 100°C. © ASCE.

关键词： Thermal conductivity

来源：评论

学校读者我要写书评

暂无评论

Traffic Signal Optimization by Integrating Reinforcement Learning and Digital Twins

Traffic Signal Optimization by Integrating Reinforcement Lea...

引用

Smart World Congress (SWC), IEEE

作者： Vijayalakshmi K Kumarasamy Abhilasha Jairam Saroj Yu Liang Dalei Wu Michael P. Hunter Angshuman Guin Mina Sartipi Department of Computer Science and Engineering University of Tennessee at Chattanooga USA Applied Research for Mobility Systems Oak Ridge National Laboratory USA School of Civil and Environmental Engineering Georgia Institute of Technology USA

Machine learning (ML) methods, especially reinforcement learning (RL), have been widely considered for traffic signal optimization in intelligent transportation systems. Most of these ML methods are centralized, lacking in scalability and adaptability in large traffic networks. Further, it is challenging to train such ML models due to the lack of training platforms and/or the cost of deploying and training in a real traffic networks. This paper presents an approach for the integration of decentralized graph-based multi-agent reinforcement learning (DGMARL) with a Digital Twin (DT) to optimize traffic signals for the reduction of traffic congestion and network-wide fuel consumption related to stopping. Specifically, the DGMARL agents learn traffic state patterns and make decisions regarding traffic signal control with assistance from a Digital Twin module, which simulates and replicates the traffic behaviors of a real traffic network. The proposed approach was evaluated using PTV-Vissim [1], a microscopic traffic simulation platform. PTV-Vissim is also the simulation engine of the DT, enabling emulation and optimization of the traffic signals on the MLK Smart Corridor in Chattanooga, Tennessee. Compared to an actuated signal control baseline approach, experiment results show that Eco_PI, a developed performance measure capturing the impact of stops on fuel consumption, was reduced by 44.27% in a 24-hour and an average of 29.88% in a PM-peak-hour scenario.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Symplectic encoders for variational inference in nonlinear dynamics systems 30

Symplectic encoders for variational inference in nonlinear d...

引用

30th International Conference on Noise and Vibration engineering, ISMA 2022 and 9th International Conference on Uncertainty in Structural Dynamics, USD 2022

作者： Bacsa, K. Lai, Z. Liu, W. Chatzi, E. CREATE Tower 06-01 Singapore138602 Singapore ETH Zürich Department of Civil Environmental and Geomatic Engineering Stefano-Franscini-Platz 5 Zürich8093 Switzerland NUS Department of Industrial Systems and Management Engineering Drive 2 BLK 06-25 Singapore117576 Singapore

ISBN: (纸本)9789082893151

The modeling of nonlinear structural systems constitutes a non-trivial, but necessary task for control and estimation purposes. In framing robust predictors, capable of taking on complex dynamics, we propose a new variational autoencoder with physical priors, which is applied on estimation of the response of Multiple Degree of Freedom (MDOF) systems. The standard variational autoencoders architecture emphasizes compression as opposed to interpretability of the learned latent features. In the case of dynamical systems, physical prior information can both augment the extrapolation property of neural networks and increase their interpretability. We propose a new type of encoder which imposes symplectic constraints on the inferred aposteriori distribution. We demonstrate, on illustrative examples of nonlinear systems, that the proposed scheme delivers robust trajectory predictions under partial and noisy observations of said systems. The model can be shown to learn an energy-preserving latent representation of the system. © 2022 Proceedings of ISMA 2022 - International Conference on Noise and Vibration engineering and USD 2022 - International Conference on Uncertainty in Structural Dynamics. All rights reserved.

关键词： Dynamical systems

来源：评论

学校读者我要写书评

暂无评论

Preliminary safety assessment of Polish interchanges

Preliminary safety assessment of Polish interchanges

引用

作者： Budzynski, Marcin Tubis, Agnieszka Rydlewski, Mateusz Gdansk University of Technology Faculty of Civil Environmental Engineering Highway and Transportation Engineering Department Gdansk Poland Wroclaw University of Science and Technology Faculty of Mechanical Engineering Department of Maintenance and Operation of Technical Systems Wroclaw Poland

Interchanges are a key and the most complex element of a road infrastructure. The safety and functionality of interchanges determine the traffic conditions and safety of the entire road network. This applies particularly to motorways and expressways, for which they are the only way to access and exchange traffic. A big problem in Poland is the lack of comprehensive tools for designers at individual stages of the design process. This applies to guidelines or other documents regarding the location, choice of interchanges type and selection of design parameters. This does not provide sufficient material for designing safe and functional interchanges. This situation results in numerous hazards that occur on existing interchanges and errors that are still being made at all stages of the design process. Consequently, there is a risk of accidents in the area of interchanges, which often have serious consequences. The purpose of the research presented in the article is to identify main groups of hazards on the interchanges and to classify them based on field tests and audits of project documentation. The prepared classification uses the results of analyzing data on road accidents. As part of the research, a database was built that includes information on road accidents and traffic, as well as data on all existing interchanges on motorways and expressways in Poland. These data includes: interchange type, length of exit and entry lanes, total interchanges length, type of cross-section on main roads and ramps. The number and type of ramps occurring at a given interchange as well as the type of intersections, if any, were also taken into account. Based on the assessment, the level of safety was determined for individual types of interchanges. Then, the impact of selected road and traffic factors on safety was presented. The critical elements of interchanges are entries, exits, weaving sections and intersections. Assumptions were also adopted for the classification of identified

关键词： Roads and streets

来源：评论

学校读者我要写书评

暂无评论

Smart Parking Dapp: A Trust Minimised Smart Parking Solution

Smart Parking Dapp: A Trust Minimised Smart Parking Solution

引用

IEEE International Conference on Blockchain (Blockchain)

作者： Nazim Rizvic Amin Sakzad Arash Mirzaei Taha Hossein Rashidi Department of Software Systems & Cybersecurity Faculty of Information Technology Monash University Melbourne VIC Australia School of Civil and Environmental Engineering Faculty of Engineering University of New South Wales Kensington NSW Australia

Blockchain-based smart parking applications provide an opportunity to increase transparency and efficiency while protecting user data. This paper presents a decentralised smart parking application built on the Ethereum blockchain, that incorporates existing protocols and standards to improve upon previous blockchain smart parking solutions. The end result is an application that allows the tokenisation and reservation of parking spots between users. An analysis of the gas consumption of the application has indicated that scaling the application to be used by thousands of concurrent users remains as a challenge, and is primarily bottlenecked by data storage requirements. The findings from this research alongside the code repository form a strong foundation for the development of consumer-facing blockchain smart parking solutions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Development of Reservoir Operation Model Determining the Pre-Release Strategy for the Flood Events

SSRN

引用

SSRN 2024年

作者： Lee, Eunkyung Yi, Sooyeon Ji, Jungwon Hong, Junhwa Lee, Seonmi Yoon, Jeongin Yi, Jaeeung Department of Civil Systems Engineering Ajou University Suwon Korea Republic of Department of Environmental Science Policy and Management University of California Berkeley United States Technology Research Center/R&D Team Dongbu Engineering Seoul Korea Republic of

Floods are among the most prevalent natural disasters, posing substantial threats to human activities. Using flood forecast information, reservoirs can pre-release water or adjust storage to enhance flood control and water conservation benefits. However, making prompt pre-release decisions that consider both dam structure safety and downstream conditions during flood events remains challenging. The main objectives of this study are to: (a) develop a reservoir operation model that guides the operators to reduce peak release in flood season, (b) generate reference tables and graphs to determine the target reservoir elevation after pre-release, and (c) propose practical application for prompt decision-making in real-time reservoir operation. We developed a reservoir operation model that can evaluate five Flood Operation Method (FOMs). With the developed model and the interface, we applied this model to the Seomjingang Reservoir as a case study and concluded that FOM V was the best fit. The model generates the reference graphs and tables that helps the operators with guidelines to determines the target reservoir elevation after pre-release based on forecasted inflow. The reference graph and table are updated when new forecasted inflow data for the next time step becomes available. The novelty of this study lies in providing an easy-to-use, simple graph and table that assists operators in making prompt and reliable reservoir operation decisions during flood events. Our approach offers real-time operation that allows for proactive reservoir operation, helping to reduce the flood damage downstream and ensuring an adequate water supply for the upcoming dry season. © 2024, The Authors. All rights reserved.

关键词： Flood control

来源：评论

学校读者我要写书评

暂无评论

Fragility Analysis of Fixed Offshore Platform in Malaysia Under Earthquake Effect

Fragility Analysis of Fixed Offshore Platform in Malaysia Un...

引用

2023 Abu Dhabi International Petroleum Exhibition and Conference, ADIP 2023

作者： Azlan, F.S. Wahab, M.M.A. Ramli, M.Z. Rahman, A. Abdul Department of Civil and Environmental Engineering Universiti Teknologi PETRONAS Perak Darul Ridzuan Seri Iskandar Malaysia Institute of Autonomous Systems for Autonomous Facilities Universiti Teknologi PETRONAS Perak Darul Ridzuan Seri Iskandar Malaysia Fakulti Kejuruteraan Awam Universiti Teknologi Malaysia Johor Darul Takzim Skudai Malaysia Upstream C&S Department of Facilities Engineering Development Division PETRONAS Kuala Lumpur Malaysia

ISBN: (纸本)9781959025078

In Malaysia, the oil and gas industry contribute significantly to its economy over the past decades. Currently there are over 250 offshore platforms in Malaysian waters. These platforms may be vulnerable to earthquake effects coming from near and far fields since seismic loading was not considered during the design stage for all offshore structures within all three (3) offshore sectors in Malaysia waters, including Sabah. Contrary to common belief that Malaysia is located outside the Pacific Ring of Fire of recent incidents and research is proving the opposite. In this study, seismic vulnerability assessment for fixed offshore platform in Sabah water is performed. Non-linear static (Pushover Analysis) and non-linear dynamic analysis (Incremental Dynamic Analysis or IDA) were performed prior to obtaining the fragility curve. Pushover analysis shows the seismic capacity through determining the drift ratio of the structure. The outcome of the analysis will then be classified into different damage levels according to Federal Emergency Management Agency (FEMA) categories;Operational Procedure (OP), Immediate Occupancy (IO), Damage Collapse (DC), Life Safety (LS) and Collapse Prevention (CP). Incremental dynamic analysis was performed by series of non-linear response histories which enabled PGA values to be systematically scaled. The maximum displacement and drift ratio were computed and compared with the drift ratio from pushover analysis to be classified into FEMA defined damage levels. Then, the mean and standard deviation of the PGA values were computed and substituted into fragility curve equation. The curve describes the probability of damage of the fixed offshore platform under earthquake effects. From the result, the vulnerability of the fixed offshore platform in Sabah water for an earthquake was concluded to be having a low probability of damage, i.e., 6.4% OP and 4.86% IO associated to Sabah PGA value of 0.28g. © 2023, Society of Petroleum Engineers.

关键词： Earthquakes

来源：评论

学校读者我要写书评

暂无评论

Analyzing the Impact of Personalization on Fairness in Federated Learning for Healthcare 11

Analyzing the Impact of Personalization on Fairness in Feder...

引用

11th IEEE International Conference on Healthcare Informatics, ICHI 2023

作者： Wang, Tongnian Zhang, Kai Cai, Jiannan Gong, Yanmin Choo, Kim-Kwang Raymond Guo, Yuanxiong The University of Texas at San Antonio Department of Information Systems and Cyber Security San Antonio United States The University of Texas Health Science Center at Houston School of Biomedical Informatics Houston United States The University of Texas at San Antonio School of Civil and Environmental Engineering and Construction Management San Antonio United States The University of Texas at San Antonio Department of Electrical and Computer Engineering San Antonio United States

ISBN: (纸本)9798350302639

Machine learning (ML) models have the potential to generate biased outcomes, which may exacerbate existing health disparities. With privacy regulations leading to data silos in health data, federated learning (FL) has emerged as a promising solution for this issue by enabling collaborative ML without patient data sharing. Personalization within FL aims to handle performance degradation that arises due to heterogeneous data distributions across organizations. However, the relationship between personalized FL and fairness remains unclear. This paper aims to investigate and analyze the potential impact of personalized FL on fairness for healthcare. Our analysis is expected to have significant implications for fairness in federated learning and healthcare. © 2023 IEEE.

关键词： Hospital data processing

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：