检索结果-内蒙古大学图书馆

PROM: A persistent routing optimization method based on supervised learning

Journal of Network and Computer Applications 2025年 242卷

作者： Yingya Guo Zebo Huang Mingjie Ding Bin Lin Huan Luo College of Computer and Data Science Fuzhou University China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University China Engineering Research Center of Big Data Intelligence Ministry of Education China

Traditional Traffic Engineering (TE) typically improves network performance by formulating and solving routing optimization problems based on measured or predicted Traffic Matrices (TMs). However, since network traffic is dynamic, routing strategies optimized for the current measured TMs may not be suitable for future traffic patterns. To adapt to dynamic traffic, one possible solution is to perform more frequent routing updates, but this may lead to service disruptions. Another approach is the two-step method of prediction followed by optimization, which could lead to degraded performance of routing strategies due to inaccuracies in traffic prediction. Additionally, existing approaches focus solely on either distributed or centralized networks, lacking flexibility to adapt to different network architectures. To address these challenges, we propose PROM, a Machine Learning (ML)-based routing optimization model that directly predicts an effective routing strategy in an end-to-end manner based on historical traffic. This routing strategy is applicable across multiple future TMs, thereby reducing the need for frequent routing updates. Furthermore, PROM can be easily extended from a centralized implementation to a distributed one, adapting to different network architectures. To enhance model performance, we have also designed a custom loss function for routing optimization scenarios to avoid overfitting. Extensive simulation results demonstrate that PROM can predict high-quality routing strategies in future unknown traffic scenarios and is adaptable to both centralized and distributed network architectures.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

The importance of robust and reliable energy prediction models: Next generation of smart meters 10

The importance of robust and reliable energy prediction mode...

引用

10th International Conference on Simulation and Modeling Methodologies, Technologies and Applications, SIMULTECH 2020

作者： Jurado, Sergio Nebot, Àngela Mugica, Francisco Soft Computing Research Group Intelligent Data Science and Artificial Intelligence Research Center Universitat Politècnica de Catalunya Barcelona Spain

ISBN: (纸本)9789897584442

In this position paper a discussion is performed related to the importance of Energy Prediction Models (EPM) in the context of trading renewable energy in smart grids and the need to develop a new generation of Smart Meters (SMs) based on edge computing. If the electricity currently produced and consumed in the low voltage is expected to grow due to installations of PVs and the electrification of the system, we need to incentivise local energy trading and provide tools to make it possible. Currently, all energy trading mechanisms in the literature heavily rely on predictions, therefore, inaccuracy would be translated in low profitability of prosumer's investments or even worse, disappointment with the local energy markets. To guarantee robustness and reliability of predictions, we propose Flexible FIR as EPM to be used during the trading process and to integrate them in a Next Generation of SMs (NGSMs). In this document some reflections about new functionalities of NGSMs and first steps of a prototype are also addressed. © 2020 by SCITEPRESS - Science and Technology Publications, Lda. All rights reserved

关键词： Smart meters

来源：评论

学校读者我要写书评

暂无评论

Iterative Refinement of Project-Level Code Context for Precise Code Generation with Compiler Feedback

arXiv

引用

arXiv 2024年

作者： Bi, Zhangqian Wan, Yao Wang, Zheng Zhang, Hongyu Guan, Batu Lu, Fangxin Zhang, Zili Sui, Yulei Jin, Hai Shi, Xuanhua Huazhong University of Science and Technology China University of Leeds United Kingdom Chongqing University China Shanghai Jiao Tong University China University of New South Wales Australia National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China

Large Language Models (LLMs) have shown remarkable progress in automated code generation. Yet, LLM-generated code may contain errors in API usage, class, data structure, or missing project-specific information. As much of this project-specific context cannot fit into the prompts of LLMs, we must find ways to allow the model to explore the project-level code context. We present COCOGEN, a new code generation approach that uses compiler feedback to improve the LLM-generated code. COCOGEN first leverages static analysis to identify mismatches between the generated code and the project’s context. It then iteratively aligns and fixes the identified errors using information extracted from the code repository. We integrate COCOGEN with two representative LLMs, i.e., GPT-3.5-Turbo and Code Llama (13B), and apply it to Python code generation. Experimental results show that COCOGEN significantly improves the vanilla LLMs by over 80% in generating code dependent on the project context and consistently outperforms the existing retrieval-based code generation baselines. © 2024, CC BY-NC-SA.

关键词： Static analysis

来源：评论

学校读者我要写书评

暂无评论

a branch-and-price approach for the nurse rostering problem with multiple units

arXiv

引用

arXiv 2023年

作者： Hu, Wanzhe He, Xiaozhou Luo, Li Pardalos, Panos M. School of Economics and Management Chongqing University of Posts and Telecommunications Chongqing China Business School Sichuan University Sichuan Chengdu China Key Laboratory of Big Data Intelligent Computing Chongqing University of Posts and Telecommunications Chongqing China Department of Industrial and Systems Engineering Center for Applied Optimization University of Florida Gainesville United States

In this paper, we study the nurse rostering problem that considers multiple units and many soft time-related constraints. An efficient branch and price solution approach that relies on a fast algorithm to solve the pricing subproblem of the column generation process is presented. For the nurse rostering problem, its pricing subproblem can be formulated as a shortest path problem with resource constraints, which has been the backbone of several solutions for several classical problems like vehicle routing problems. However, approaches that perform well on these problems cannot be used since most constraints in the nurse rostering problem are soft. Based on ideas borrowed from global constraints in constraint programming to model rostering problems, an efficient dynamic programming algorithm with novel label definitions and dominating rules specific to soft time-related constraints is proposed. In addition, several acceleration strategies are employed to improve the branch and price algorithm. Computational results on instances of different sizes indicate that the proposed algorithm is a promising solution for the nurse rostering problem with multiple units. Copyright © 2023, The Authors. All rights reserved.

关键词： Constraint programming

来源：评论

学校读者我要写书评

暂无评论

Variational Bayes for Federated Continual Learning

arXiv

引用

arXiv 2024年

作者： Yao, Dezhong Li, Sanmu Dai, Yutong Xu, Zhiqiang Hu, Shengshan Zhao, Peilin Sun, Lichao The National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab. Cluster and Grid Computing Lab. School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China Lehigh University PA18015 United States Mohamed bin Zayed University of Artificial Intelligence United Arab Emirates Tencent AI Lab. Shenzhen China

Federated continual learning (FCL) has received increasing attention due to its potential in handling real-world streaming data, characterized by evolving data distributions and varying client classes over time. The constraints of storage limitations and privacy concerns confine local models to exclusively access the present data within each learning cycle. Consequently, this restriction induces performance degradation in model training on previous data, termed "catastrophic forgetting". However, existing FCL approaches need to identify or know changes in data distribution, which is difficult in the real world. To release these limitations, this paper directs attention to a broader continuous framework. Within this framework, we introduce Federated Bayesian Neural Network (FedBNN), a versatile and efficacious framework employing a variational Bayesian neural network across all clients. Our method continually integrates knowledge from local and historical data distributions into a single model, adeptly learning from new data distributions while retaining performance on historical distributions. We rigorously evaluate FedBNN’s performance against prevalent methods in federated learning and continual learning using various metrics. Experimental analyses across diverse datasets demonstrate that FedBNN achieves state-of-the-art results in mitigating forgetting. Copyright © 2024, The Authors. All rights reserved.

关键词： Digital storage

来源：评论

学校读者我要写书评

暂无评论

Multi User Offloading Strategy for Edge computing in Charging Load Forecasting Scenario

Multi User Offloading Strategy for Edge Computing in Chargin...

引用

Chinese Automation Congress (CAC)

作者： Hongyu Long Zhaocheng Huang Chao Liu Daolin Xu Tao Li Fan Ye Key Laboratory of Big Data Intelligent Computing School of Automation/School of Industrial Internet Chongqing University of Posts and Telecommunications Chongqing China School of Automation/School of Industrial Internet Chongqing University of Posts and Telecommunications Chongqing China Economic and Technical Research Institute of State Grid Chongqing Electric Power Company Chongqing China

In order to mitigate the impact of large-scale new energy vehicle charging access to the grid, edge computing technology is widely used in smart charging perception scenarios. By deploying various edge terminal devices or application software at the perception sites, it can collect and predict the power load in various regions, so as to effectively guide and control the charging amount of new energy vehicles. However, with the increase of computing demand brought by the increase of edge device nodes, the edge server may face the problem of insufficient computing resources, which will affect the low latency characteristics. To alleviate this problem, this paper abstracts each edge terminal device as an independent user with task computing needs, establishes a multi-user edge computing system, and proposes a multi-level resource allocation strategy for edge computing, Decompose and allocate communication channel resources and server resources in multiple rounds. This method can reduce task latency by optimizing the task offloading ratio and resource allocation method of users while meeting their basic needs. The simulation results show that this method can effectively reduce the latency of task computation in multi user scenarios.

关键词：

来源：评论

学校读者我要写书评

暂无评论

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Xiaoke Zhu Danyang Li Xiaopan Chen Fumin Qi Fan Zhang Xiao-Yuan Jing School of Computer and Information Engineering Henan University Kaifeng China Henan Engineering Research Center of Intelligent Technology and Application Henan University Kaifeng China Department of System Operation National Supercomuting Center in Shenzhen Shenzhen China Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng China School of Computer Science Wuhan University Wuhan China

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

Facial image based kinship verification aims to decide whether there exists kinship between the given facial images. In practice, the cross-generation differences will cause adverse effects on kinship verification, which limits the performance. Therefore, how to mine the implied similarity from facial images with large cross-generation divergence is an important problem in kinship verification, which has not yet been well studied. In view of this, we propose a Similarity Mining via Implicit matching pattern LEarning (SMILE) approach for kinship verification. Specifically, SMILE mainly consists of two modules, including a Semi-coupled Multi-pattern Similarity Learning (SMSL) module and a Cross-Generation Feature Normalization (CGFN) module. The SMSL module is designed to learn multiple semi-coupled matching patterns for mining the implicit facial similarity information from different perspectives. The CGFN module aims to reduce the divergence between facial images of parent and child. Extensive experiments demonstrate that the proposed approach outperforms the existing state-of-the-art methods.

关键词： Pattern matching Similarity learning

来源：评论

学校读者我要写书评

暂无评论

Admission Control with Latency Considerations for 5G Mobile Edge computing

Admission Control with Latency Considerations for 5G Mobile ...

引用

IEEE International Symposium on World of Wireless Mobile and Multimedia Networks (WoWMoM)

作者： Ye Zhang Wuyungerile Li Winston K.G. Seah Inner Mongolia Key Lab. of Wireless Networking & Mobile Computing Engineering Research Center of Ecological Big Data Ministry of Education School of Computer Science Inner Mongolia University Hohhot China Wireless Networks Research Group School of Engineering and Computer Science Victoria University of Wellington Wellington New Zealand

The fifth generation (5G) mobile network is a new generation of broadband mobile communication technology with the potential to address the increasing demands of new user services and applications that have stringent low latency and high bandwidth requirements. Besides the enhanced mobile broadband (eMBB) which is an evolution of broadband services from previous generations, the ultra reliable low latency communication (URLLC) service comes with stringent delay requirements that are needed to support new applications like autonomous vehicles, augmented/virtual reality, etc. Mobile or multiple access edge computing (MEC) emerged to provide services and computing resources for users at the network edge to provide faster access speeds and lower end-to-end delays. To better meet user needs and maximize resource utilization, network resources need to be allocated and managed efficiently. Admission control for user requests is one of the methods used that can effectively prevent network congestion, thereby improving the overall performance of the system. In this paper, we propose a RED-based Admission Control with Latency Considerations (REDAL) algorithm for user admission control that aims to increase throughput, meet users’ delay requirements and reduce packet discard rate. By explicitly accounting for user traffic delay constraints and bandwidth requirements, we are able to meet the strict delay constraints of URLLC traffic while meeting the bandwidth requirements of eMBB traffic. We validate our approach in an MEC scenario to demonstrate high resource utilization and also keeping the request discard rate below 20%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Evaluating Classifiers of Unbalanced data with Parameter Retrieval in Hybrid Sampling for Clinical Decision Support Systems

SSRN

引用

SSRN 2023年

作者： Yu, Haiyan Piri, Saeed Qiu, Hang Miao, Hongxia Center for Data and Decision Sciences School of Economics and Management Chongqing University of Posts and Telecommunications Chongqing400065 China Department of Operations and Business Analytics Lundquist College of Business University of Oregon EugeneOR97403 United States Health Big Data Research Institute School of Computing and Engineering University of Electronic Science and Technology of China Chengdu611731 China

ContextTo develop clinical decision support systems (CDSS), researchers and practitioners usually apply a machine learning (ML) classifier they expect to be the best through ML effect estimation. A standard classifier can perform well on balanced datasets, but its performance often dramatically decreases when applied to unbalanced *** objective was to conduct an experiment study for choosing the best-suited ML algorithms in CDSS and improving the classifying performance of unbalanced data with parameter retrieval in hybrid *** paper proposes a hybrid sampling approach for evaluating classifiers with unbalanced data in CDSS. In this framework, the mean responses of the classification experiments are employed to estimate the ML effect. Meanwhile, uniform designs are used in hybrid sampling (HSUD) to retrieve the optimal parameters. The efficacy of HSUD is validated through applications on six real-world clinical datasets (unbalanced) using six ML algorithms (including zero rule). The ratio of the minority to the majority ranges from 0.09 to 0.80 in the six datasets, and the sample size ranges from 187 to *** results suggest that our approach is more effective than existing unbalanced data learning methods. In particular, the AUC with HSUD is 2.48% and 8.60% higher than those with proportional and balanced sampling methods in the testing, respectively. Moreover, HSUD is efficient in choosing classifiers with unbalanced data in *** study compared multiple ML algorithms and chose the best-suited ML algorithms with unbalanced data sets in CDSS, improved their classifying performance, and provided guidelines for parameter retrieval in developing CDSS. © 2023, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Understanding and Detecting Privacy Leakage Vulnerabilities in Hyperledger Fabric Chaincodes

Understanding and Detecting Privacy Leakage Vulnerabilities ...

引用

International Symposium on Software Reliability Engineering (ISSRE)

作者： Ziming Chen Yue Li Jianbo Gao Jiashuo Zhang Ke Wang Jianbin Hu Zhi Guan Zhong Chen School of Computer Science Peking University Beijing China College of Computer Science and Technology Taiyuan University of Technology Taiyuan China Beijing Key Laboratory of Security and Privacy in Intelligent Transportation Beijing Jiaotong University Beijing China Peking University Chongqing Research Institute of Big Data Chongqing China National Engineering Research Center for Software Engineering Peking University Beijing China

ISBN: (数字)9798350353884

ISBN: (纸本)9798350353891

The application on a blockchain cannot maintain secrecy because its data is replicated across all peers in the network. To remedy this problem, Hyperledger Fabric introduces private data collection (PDC) into its smart contract (i.e. chaincode) to facilitate applications that require privacy. However, recent studies have revealed that PDC is too complex for chaincode developers to fully understand and use correctly, leading to privacy leaks vulnerabilities. In this paper, we present an empirical study on the prevalence of PDC misuse in chaincodes by extracting privacy leakage cases from StackOverflow posts and Hyperledger Fabric repositories on GitHub. Subsequently, we systematically categorize the misuse of PDC into three categories of vulnerabilities resulting in the leakage of private data and provide formal definitions for them. Furthermore, we develop PDChecker, an automated security analysis framework for identifying the privacy and security vulnerabilities in Fabric chaincodes. We evaluated PDChecker on 956 real-world chaincodes applying PDC and found that 67.78% of them contain at least one privacy leakage vulnerability. In addition, PDChecker uncovered 10 zero-day vulnerabilities documented by the China National Vulnerability database.

关键词： Privacy data privacy Distributed ledger databases Smart contracts Fabrics Blockchains Software reliability Security Software development management

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：