检索结果-内蒙古大学图书馆

Network Partition-Based Zonal Voltage Control for Distribution Networks With Distributed PV Systems

IEEE TRANSACTIONS ON SMART GRID 2018年第5期9卷 4087-4098页

作者： Zhao, Bo Xu, Zhicheng Xu, Chen Wang, Caisheng Lin, Feng Zhejiang Elect Power Corp Res Inst Hangzhou 310014 Zhejiang Peoples R China Hefei Univ Technol Dept Elect Engn & Automat Hefei 230009 Anhui Peoples R China Wayne State Univ Dept Elect & Comp Engn Detroit MI 48202 USA

As the penetration level of distributed photovoltaic (PV) systems keeps increasing in distribution networks, overvoltage due to reverse power flow is an urgent issue to be addressed. This paper proposes a voltage regulation method by utilizing the voltage control capability of PV inverters. A novel network partition approach based on a community detection algorithm is presented to realize zonal voltage control in a shorter control response time using the minimum amount of reactive power compensation and active power curtailment. An improved modularity index that considers local reactive power balance is introduced to partition a distribution network into several clusters/communities with PVs based on the node voltage sensitivity analysis. An optimal reactive and active power control strategy is proposed for voltage control in each cluster. The voltage management of the overall system can he achieved by controlling each cluster separately. The proposed approach is applied to the voltage control of a practical 10 kV, 37-node feeder. Case studies on the real distribution network and a modified IEEE 123-node system are carried out to verify the feasibility and effectiveness of the proposed method.

关键词： PV system generation zonal voltage control optimal power management community detection algorithm

来源：评论

学校读者我要写书评

暂无评论

Detecting Communities in Sparse MANETs

引用

IEEE-ACM TRANSACTIONS ON NETWORKING 2011年第5期19卷 1434-1447页

作者： Drugan, Ovidiu Valentin Plagemann, Thomas Munthe-Kaas, Ellen Univ Oslo Dept Informat N-0316 Oslo Norway

In sparse mobile ad hoc networks, placement of services and data is crucial to assure their availability to all nodes because sparse population of nodes can lead to (frequent) network partitions. If these dynamic networks display a fairly stable cluster structure, it is possible to utilize this structure to improve service and data availability. However, clustering in a dynamic network is a very challenging task due to the ever-changing topology and irregular density of such a network. In this paper, we investigate clustering of dynamic networks with the help of community detection mechanisms, using only topology information from the local routing table. The main aim of our approach is to reduce to "zero" the communication overhead needed for cluster management and to dynamically adapt to the size and layout of the network. We have performed extensive experiments to evaluate the consistency, quality, and stability of the clustering returned by our algorithms. The results show that our nonintrusive clustering indeed discovers temporary groups of nodes that form stable clusters in the network. Moreover, even though the local routing tables in general reflect slightly diverging topologies, our results still show only small differences between the communities detected at different nodes.

关键词： Clustering community detection algorithm network topology rescue operations sparse mobile ad hoc networks (MANETs) wireless communications

来源：评论

学校读者我要写书评

暂无评论

Policy Gradient-Based Core Placement Optimization for Multichip Many-Core Systems

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2023年第8期34卷 4529-4543页

作者： Myung, Wooshik Lee, Donghyun Song, Chenhang Wang, Guanrui Ma, Cheng Tsinghua Univ Dept Precis Instrument Ctr Brain Inspired Comp Res Beijing 100084 Peoples R China

As many deep neural network models become deeper and more complex, processing devices with stronger computing performance and communication capability are required. Following this trend, the dependence on multichip many-core systems that have high parallelism and reasonable transmission costs is on the rise. In this work, in order to improve routing performance of the system, such as routing runtime and power consumption, we propose a reinforcement learning (RL)based core placement optimization approach, considering application constraints, such as deadlock caused by multicast paths. We leverage the capability of deep RL from indirect supervision as a direct nonlinear optimizer, and the parameters of the policy network are updated by proximal policy optimization. We treat the routing topology as a network graph, so we utilize a graph convolutional network to embed the features into the policy network. One step size environment is designed, so all cores are placed simultaneously. To handle large dimensional action space, we use continuous values matching with the number of cores as the output of the policy network and discretize them again for obtaining the new placement. For multichip system mapping, we developed a community detection algorithm. We use several datasets of multilayer perceptron and convolutional neural networks to evaluate our agent. We compare the optimal results obtained by our agent with other baselines under different multicast conditions. Our approach achieves a significant reduction of routing runtime, communication cost, and average traffic load, along with deadlock-free performance for inner chip data transmission. The traffic of interchip routing is also significantly reduced after integrating the community detection algorithm to our agent.

关键词： Optimization Routing Training System recovery Power demand Neural networks Topology community detection algorithm deadlock-free placement physical mapping reinforcement learning (RL)

来源：评论

学校读者我要写书评

暂无评论

On Utilizing Communities Detected From Social Networks in Hashtag Recommendation

引用

IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS 2020年第4期7卷 971-982页

作者： Alsini, Areej Datta, Amitava Huynh, Du Q. Univ Western Australia Dept Comp Sci & Software Engn Perth WA 6009 Australia Umm Al Qura Univ Dept Comp Sci Mecca 715 Saudi Arabia

Personalized recommendation automatically predicts the top-y hashtags to a given tweet. Most research in the literature of hashtag recommendation focused on the content of the posts such as words and topics. Although these methods have measured the performance of hashtag recommendation on large data sets, there is a lack of analysis on how these methods perform on small communities. Motivated by the well-studied research area of community detection algorithms that aggregate strongly connected users with similar interests and behaviors, in this article, we propose a community-based hashtag recommendation framework, which studies hashtag recommendation through tweet similarity task and applies it on communities detected using the Clique percolation method, Louvain algorithm, and label propagation method. The detected communities are extracted from four social network constructions based on following, mention, hashtag, and topic. Compared to the three state-of-the-art hashtag recommendation methods, our extensive experiments show that our community-based method outperforms these methods, thus giving a higher hit rate. Our in-depth analysis demonstrates that the performance of hashtag recommendation is the best when the communities are generated using the Clique percolation method (CPM) from the network of users who share similar usage of hashtags.

关键词： Twitter Tagging detection algorithms Australia Clustering algorithms Data mining community detection algorithm content similarity hashtag recommendation network graphs predictive models social computing

来源：评论

学校读者我要写书评

暂无评论

Model-data matching method for natural disaster emergency service scenarios: implementation based on a knowledge graph and community discovery algorithm

引用

NATURAL HAZARDS 2024年第5期120卷 4233-4255页

作者： Liu, Honghao Hu, Zhuowei Yang, Ziqing Wang, Mi Capital Normal Univ Coll Resources Environm & Tourism Beijing Peoples R China

Massive disaster-related data and model methods are available in different stages of natural disaster emergency management;however, they often lack the representation of the significance of crucial information. In addition, traditional methods are difficult to automate and fine-match, resulting in greater difficulty in intelligent applications. To address this problem, interconnected knowledge arranged in a knowledge graph and a community discovery algorithm were used to match disaster data with the appropriate method under a unified description framework. Based on the knowledge graph constructed by ontology mapping, this study aimed to represent and store the complex entities and relationships among disaster-related information. The node importance analysis and community discovery algorithm were used to analyze the community structure of important nodes, and a typical rainstorm flood disaster risk assessment emergency service scenario was taken as an example for experimental verification. The results showed that the constructed knowledge graph of natural disaster emergency services can support the formal expression of semantic correlation between disaster scenarios, model methods, and disaster data. The community discovery method performed well in overlapping community module degrees. The method proposed in this study can be used to formalize the representation and storage of massive heterogeneous data and conduct fine matching after quantitative analysis of the importance of model methods and data required for risk assessment of emergency service scenarios. Furthermore, the proposed method can provide theoretical support for improving the scientificity, accuracy, and interpretability of risk assessment decision management and promoting knowledge-driven intelligent emergency information service capabilities.

关键词： Disaster data matching Knowledge graph community detection algorithm Emergency risk assessment Ontology mapping

来源：评论

学校读者我要写书评

暂无评论

An interaction-based method for detecting overlapping community structure in real-world networks

引用

INTERNATIONAL JOURNAL OF DATA SCIENCE AND ANALYTICS 2022年第1期14卷 27-44页

作者： Kumar, Pawan Dohare, Ravins Indira Gandhi Natl Open Univ Sch Sci New Delhi India Jamia Millia Islamia Ctr Interdisciplinary Res Basic Sci New Delhi 110025 India

A central theme of network analysis, these days, is the detection of community structure as it offers a coarse-grained view of the network at hand. A more interesting and challenging task in network analysis involves the detection of overlapping community structure due to its wide-spread applications in synthesising and interpreting the data arising from social, biological and other diverse fields. Certain real-world networks possess a large number of nodes whose memberships are spread through multiple groups. This phenomenon called community structure with pervasive overlaps has been addressed partially by the development of a few well-known algorithms. In this paper, we presented an algorithm called Interaction Coefficient-based Local community detection (IC-LCD) that not only uncovers the community structures with pervasive overlaps but do so efficiently. The algorithm extracted communities through a local expansion strategy which underlie the notion of interaction coefficient. We evaluated the performance of IC-LCD on different parameters such as speed, accuracy and stability on a number of synthetic and real-world networks, and compared the results with well-known baseline algorithms, namely DEMON, OSLOM, SLPA and COPRA. The results give a clear indication that IC-LCD gives competitive performance with the chosen baseline algorithms in uncovering the community structures with pervasive overlaps. The time complexity of IC-LCD is O(nc(max)), where n is the number of nodes, and c(max) is the maximum size of a community detected in a network.

关键词： Node interaction coefficient Edge interaction coefficient Pervasive overlap community detection algorithm

来源：评论

学校读者我要写书评

暂无评论

A recommender system based on local topology features and message rate 2

A recommender system based on local topology features and me...

引用

2nd International Congress on Technology, Communication and Knowledge (ICTCK)

作者： Rokni, Mohadeseh Moattar, Mohammad. H. Jalali, Mehrdad Islamic Azad Univ Mashhad Branch Dept Comp Engn Mashhad Iran

ISBN: (纸本)9781467397629

Social networks have become an indispensable part of every day's life. A vast majority of people use at least one social network to communicate with friends or business partners. Different applications of social networks are used to meet diverse needs of users. Social networks use recommender systems to provide wider experience for their users. Friend recommendation has been the most popular and important application used to expand the circle of friends and social communication. Social networks are very dynamic. Every moment new people are added and new forms of relationship are formed. Therefore, evaluating social networks is a complicated task. In this paper, the focus is both on the characteristics of social networks as well as the messages sent between and among the nodes. A mixed method will be suggested which will initially use a community detection algorithm based on message rate as a pruning algorithm. It will then divide the network into several communities. Afterwards, the FriendLink algorithm will be employed in order to estimate the similarity score between all users based on the properties of the network structure and the rate of the messages sent. Finally, users with maximal similarity will be suggested as friends to the target user. The results of testing a Facebook-like dataset revealed that the suggested method is of a great precision and accuracy as compared to FriendLink and CSM algorithms.

关键词： social networks Friend recommendation network structure community detection algorithm

来源：评论

学校读者我要写书评

暂无评论

Linking Collaborative Filtering and Social Networks: Who are my Mentors?

Linking Collaborative Filtering and Social Networks: Who are...

引用

International Conference on Advances in Social Network Analysis and Mining (ASONAM)

作者： Brun, Armelle Boyer, Anne Nancy Univ LORIA 615 Rue Jardin Bot F-54506 Vandoeuvre Les Nancy France

ISBN: (纸本)9780769541389

This paper proposes a new approach of mentor selection in memory-based collaborative filtering when no rating is available. Users are represented under the form of a social network. The selection of mentors is performed through the use of a community detection algorithm used in the frame of social networks. It allows to recommend items to a given user, by applying democratic voting rules within his community.

关键词： Mentor detection collaborative filtering community detection algorithm democratic voting rules groupware information filtering local community detection memory based collaborative filtering mentor selection recommender systems social networking (online) social networks

来源：评论

学校读者我要写书评

暂无评论

NUVER: Network Based Vulnerability Visualizer 30

NUVER: Network Based Vulnerability Visualizer

引用

IEEE 30th Annual Software Technology Conference (STC)

作者： Sparks, Hailey Ghosh, Krishnendu Coll Charleston Dept Comp Sci Charleston SC 29424 USA

ISBN: (纸本)9798350319415

The deluge of attacks on IT infrastructure has necessitated the understanding of cybersecurity vulnerabilities for mitigation. A two-step novel model is developed to harness the time-stamped data to analyze the vulnerability trends. In the first step of the model, a text network is created from the vulnerability report. A software is constructed that analyzes vulnerabilities by leveraging natural language processing and network theory. The network theoretic study provides details of the complex relationships between vulnerabilities. The visualizations from the tool provide information for security researchers for an in-depth study of vulnerabilities.

关键词： community detection algorithm Natural Language Processing Network Theory Software Vulnerabilities

来源：评论

学校读者我要写书评

暂无评论

Online Network Partition for Voltage Control in Power Systems with Large Penetration of Renewable Energy 5

Online Network Partition for Voltage Control in Power System...

引用

5th Asia Conference on Power and Electrical Engineering (ACPEE)

作者： Yang, Yang Sun, Yichao Wang, Qi Zhu, Ling Wang, Yu Wang, Yiran Nanjing Normal Univ Sch Elect & Automat Engn Nanjing Peoples R China NARI Technol Co Ltd Power Syst Stabil Control Co Nanjing Peoples R China

ISBN: (数字)9781728152813

ISBN: (纸本)9781728152813

Network partition is the basis of voltage control, aiming at reducing load of communication devices and calculation modules, whilst solving var-voltage problems on the spot in larger and larger complex power networks. Power systems with large penetration of renewable energy such as solar or wind energy have time-variant operation characteristics and network partition in such networks requires efficiency and less running time to keep up with the changes. Generally, partition methods are mostly based electrical connection between buses and clustering methods, whose aim is to cluster buses that have similar voltage reaction characteristics into the same set. There are many ways to obtain electrical connection and partition networks, and their effects and efficiency vary from one to another. In this paper is proposed a practical method to do the computation of electrical connection while partitioning the power network into smaller sub-graphs online in less CPU time than traditional power network partitioning methods. Its aim is to optimize the index of partition, as well as to minimize inter-zone connection while maximizing intra-zone connection, fitting the partition results with different operation characteristics of renewable energy sources. The method to do the calculation of electrical connection matrix is based on a modified method of sensitivity while the partition method is based on the widely applied concept modularity and community detection algorithm.

关键词： Online Voltage Control Power Network Partition Renewable Energy community detection algorithm Electrical Connection

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：