检索结果-内蒙古大学图书馆

DRL-Based Time-Varying Workload Scheduling With Priority and Resource Awareness

IEEE Transactions on Network and service Management 2025年第3期22卷 2838-2852页

作者： Liu, Qifeng Fan, Qilin Zhang, Xu Li, Xiuhua Wang, Kai Xiong, Qingyu Chongqing University School of Big Data and Software Engineering Chongqing400044 China Chongqing University Key Laboratory of Dependable Service Computing in Cyber Physical Society of Ministry of Education Chongqing400044 China Nanjing University School of Electronic Science and Engineering Nanjing210023 China Haihe Laboratory of Information Technology Application Innovation Tianjin300072 China Harbin Institute of Technology School of Computer Science and Technology Weihai264209 China Shandong Key Laboratory of Industrial Network Security Weihai264209 China

With the proliferation of cloud services and the continuous growth in enterprises' demand for dynamic multi-dimensional resources, the implementation of effective strategy for time-varying workload scheduling has become increasingly significant. In this paper, we propose a deep reinforcement learning (DRL)-based method for time-varying workload scheduling, aiming to allocate resources efficiently across servers in the cluster. Specifically, we integrate a classifier and queue scorer to construct a priority queue that exploits temporal resource utilization patterns across different workload classes. Then, we design parallel graph attention layers to capture the dimensional features and temporal dynamics of cloud server cluster. Moreover, we propose a DRL algorithm to generate scheduling strategies that can adapt to dynamic environments. Validation on real-world traces from Google cluster demonstrates that our method outperforms existing approaches in key metrics of cloud server cluster management. © 2004-2012 IEEE.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

Low-Cost Beam Steering that Covers the Entire Azimuthal Plane Powered by Amplitude-Only Synthesis of a Quintuple-Dipole Source

引用

Electromagnetic Science 2023年第3期1卷 100-113页

作者： Da Yi Zhiyang Qi Mingchun Tang Dajiang Li Yilin Lang Xingchang Wei The Key Laboratory of Dependable Service Computing in Cyber Physical Society Ministry of Education College of Microelectronics and Communication EngineeringChongqing UniversityChongqing 400044China Chongqing Key Laboratory of Space Information Network and Intelligent Information Fusion Chongqing UniversityChongqing 400044China College of Information Science and Electronic Engineering Zhejiang UniversityHangzhou 310027China

A new amplitude-only synthesis approach in quintuple electric dipoles(EDs)is proposed to enable the regulation of power flow in the azimuthal *** regulation methodology is investigated analytically with double ED,triple ED and quintuple ED ***,when the phase difference between the EDs switches,the double ED model,acting as a reconfigurable source,can work in two modes with different power flow directions,i.e.,unidirectional mode and bidirectional ***,from the triple ED model,it is verified that the power flow in the two working modes can be regulated to the desired direction in the azimuthal plane with high precision by controlling the feeding amplitudes of the ***,a quintuple ED model is developed to enhance the symmetry and consistency of the power flow regulation in the ***,a prototype of the azimuthal beam steering system,including digitally controlled radio-frequency(RF)frontend tuning circuits,optimized practical feeding elements,and an end-fire radiator,is designed,fabricated and *** unidirectional and bidirectional modes are observed,and satisfactory single-beam and dual-beam steering performance in the azimuthal plane is *** most phased arrays that realize beam steering by configuring phases,the beam steering of the proposed reconfigurable source in each mode can be arbitrarily synthesized only by the amplitudes of the quintuple feeding elements,which provides a new route for realizing low-cost and multifunctional beam-steering systems.

关键词： Electric dipole Reconfigurable devices Amplitude-only synthesis Beam steering

来源：评论

学校读者我要写书评

暂无评论

SHIS Model of E-mail Virus Propagation

引用

Chinese Journal of Electronics 2023年第4期21卷 619-622页

作者： Jiang ZHONG Ang LI Luosheng WEN College of Computer Science Chongqing University Chongqing China Key Laboratory of Dependable Service Computing in Cyber Physical Society Ministry of Education Chongqing China

By analyzing the characteristics of many E-mail viruses in reality, we address an SHIS (Susceptible- hidden-infected-susceptible) model in this paper. In our model, on the one hand, the state H is introduced, which denotes user receives some E-mails with virus but s/he doesn't activate them and they aren't infectious. On the other hand, the topology of E-mail network is considered. The model not only describes better the practical condition of E-mail virus propagation than existing models, but also makes it possible to analyze the users' behavior. By analyzing the rate equation of the model, we study the epidemic threshold and the equilibrium point. We also present the relationship between the infected density and two important parameters: the percentage of activating E- mail with virus and the frequency, in which users check the Email box. Finally, some numerical simulations are also presented to show the correctness of theoretical analysis. Our model would help to understand and control E-mail virus spreading.

关键词： Analytical models Epidemics Network topology Buildings Numerical simulation Mathematical models Numerical models

来源：评论

学校读者我要写书评

暂无评论

Intelligent Vehicle Lateral and Longitudinal Decoupled Dynamic Modeling and Control System Simulation Based on GRU-FNN

Intelligent Vehicle Lateral and Longitudinal Decoupled Dynam...

引用

Energy and Power Engineering, Control Engineering (EPECE), International Conference on

作者： Bowen Zhang Key Laboratory of Dependable Service Computing in Cyber Physical Society of Ministry of Education School of Automation Chongqing University Chongqing P. R. China

ISBN: (数字)9798350366099

ISBN: (纸本)9798350366105

This study focuses on the problem of vehicle dynamics modeling within the framework of intelligent vehicles cyber-physical systems. Initially, a mechanistic analysis of vehicle dynamics is conducted, and, leveraging its characteristics, we design a composite neural network that integrates Gated Recurrent Unit (GRU) and Feedforward Neural Network (FNN), employing a data-driven modeling methodology. Subsequently, a novel neural network-based digital mapping proxy model for vehicle dynamics is formulated. Comparative experiments among various methods demonstrate that our proposed approach yields higher precision in both lateral and longitudinal dynamic models. The application of our model to the vehicle longitudinal speed tracking control system validates its suitability and real-time performance in control system simulation.

关键词： Data-driven modeling Space vehicles Power engineering Intelligent vehicles Predictive models cyber-physical systems Logic gates

来源：评论

学校读者我要写书评

暂无评论

CLIP-Driven Multi-Scale Instance Learning for Weakly Supervised Video Anomaly Detection

CLIP-Driven Multi-Scale Instance Learning for Weakly Supervi...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Zhangbin Qian Jiawei Tan Zhilong Ou Hongxing Wang School of Big Data and Software Engineering Chongqing University China Key Laboratory of Dependable Service Computing in Cyber Physical Society Chongqing University Ministry of Education China

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

Existing weakly supervised video anomaly detection methods mainly employ Multiple Instance Learning (MIL) to identify abnormal snippets in untrimmed videos. However, the semantics and presentations of anomalies frequently exhibit ambiguity that MIL is difficult to tackle. Moreover, MIL suffers from false alarms due to its independent optimization of each instance, neglecting temporal correlation between adjacent snippets. Consequently, we badly need to better connect abnormal presentations and their semantics, as well as to enable multi-temporal-scale anomaly discovery. This paper proposes a CLIP-Driven Multi-Scale Instance Learning (CMSIL) framework with two branches including Vision-Language (VL) and Multi-Scale Instance Learning (MSIL). The VL branch leverages the powerful visual concept priors from Contrastive Language-Image Pre-training (CLIP) to generate pseudo anomalies, thereby providing suspected anomaly cues for model training guidance. The MSIL branch utilizes a feature pyramid to fully mine fine-grained temporal dependencies by employing MIL within each pyramid level to learn anomalous patterns across different temporal scales. By collaborating with the two branches, the proposed CMSIL shows better proficiency in handling anomalies with varying durations. Extensive experiments on the XD-Violence and UCF-Crime datasets demonstrate the superior performance of our method. The code is available at https://***/casperZB/CMSIL.

关键词： Training Visualization Correlation Codes Semantics Focusing Streaming media Anomaly detection Optimization Context modeling

来源：评论

学校读者我要写书评

暂无评论

Neighbor Relations Matter in Video Scene Detection

Neighbor Relations Matter in Video Scene Detection

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Jiawei Tan Hongxing Wang Jiaxin Li Zhilong Ou Zhangbin Qian Key Laboratory of Dependable Service Computing in Cyber Physical Society (Chongqing University) Ministry of Education China School of Big Data and Software Engineering Chongqing University China

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Video scene detection aims to temporally link shots for obtaining semantically compact scenes. It is essential for this task to capture scene-distinguishable affinity among shots by similarity assessment. However, most methods relies on ordinary shot-to-shot similarities, which may inveigle similar shots into being linked even though they are from different scenes, and meanwhile hinder dissimilar shots from being blended into a complete scene. In this paper, we propose NeighborNet to inject shot contexts into shot-to-shot similarities through carefully exploring the relations between semantic/temporal neighbors of shots over a local time period. In this way, shot-to-shot similarities are remeasured as semantic/temporal neighbor-aware similarities so that NeighborNet can learn context embedding into shot features using graph convolutional network. As a result, not only do the learned shot features suppress the affinity among similar shots from different scenes, but they also promote the affinity among dissimilar shots in the same scene. Experimental results on public benchmark datasets show that our proposed NeighborNet yields substantial improvements in video scene detection, especially outperforms released state-of-the-arts by at least 6% in Average Precision (AP). The code is available at https://***/ExMorgan-Alter/NeighborNet.

关键词： Learning systems Computer vision Codes Graph convolutional networks Image edge detection Semantics Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

Leveraging GCN and User Friendship for Next POI Recommendation 22

Leveraging GCN and User Friendship for Next POI Recommendati...

引用

Proceedings of the 2022 5th International Conference on Machine Learning and Natural Language Processing

作者： Cheng Fu Wei Zhou Junhao Wen Xiangxing Guo Yuhang Chang School of Bigdata and Software Engineering Chongqing University China and Key Laboratory of Dependable Service Computing in Cyber Physical Society Moe China

ISBN: (纸本)9781450399067

The next POI (point of interest) recommendation aims to explore the behaviour patterns from users’ historical check-in records and recommend the next location. However, solving the data sparsity problem and improving the model recommendation performance are still considerable challenges in POI recommendations. This paper proposes a GFUC model consisting of the GCN (Graph Convolutional Networks) and FUC (Friendship of User Context) modules. The GCN module integrates weighted graph convolutional networks to obtain the best representation of users and POIs. The FUC module divides user check-in records with multiple fine-grain manners. Then it incorporates the user friendship and context information, significantly improving the model’s performance while solving the data sparsity problem. More specifically, experimental results show that our proposed GFUC model improves the performance of POI recommendations by more than 10% on both Yelp and Gowalla datasets with the evaluation metrics Precision@10.

关键词： Collaborative Filtering

来源：评论

学校读者我要写书评

暂无评论

Why not Just Look for Answers? Using a More Direct Way for API Recommendation

Why not Just Look for Answers? Using a More Direct Way for A...

引用

Asia-Pacific Conference on Software Engineering

作者： Changxin Liu Ling Xu Wenhan Mu Rui Qin Key Laboratory of Dependable Service Computing in Cyber Physical Society (Chongqing University) Ministry of Education China School of Big Data and Software Engineering Chongqing University Chongqing China

ISBN: (数字)9798331534011

ISBN: (纸本)9798331534028

Automated API recommendation technology can help developers quickly find target APIs that meet their require-ments. Some retrieval-based API recommendation approaches, such as BIKER and CLEAR, adopt an indirect API recommen-dation strategy. Although these approaches have shown good performance, we observed two limitations in these approaches: (1) These approaches heavily relies on the coverage of the collected question titles proposed by developers; (2) These approaches ignore the API source code information. To overcome the two limitations, we propose an approach named AnsAPIRec (Answer- directed API Recommendation), which leverages a pre-trained model and joint-attention mechanism in this paper. In addition to the fully qualified name of the API, AnsAPIRec extracts the corresponding source code from the JDK as an additional feature. AnsAPIRec adopts a direct API recommendation strategy, which directly calculates the similarity between user queries and API features, i.e., API fully qualified name and API source code, to find the target API, alleviating the reliance on question titles. To further enhance AnsAPIRec's ability to understand the semantics of the inputs, we propose a joint-attention mechanism to learn the interdependent representations between the queries and API features. This deep semantic fusion mechanism enables AnsAPIRec to perform well in understanding user intent and API functionality. We reused the APIBench-Q dataset, containing 5885 queries for training and 653 queries for testing. The experimental result shows that AnsAPIRec achieved an MRR of 0.473, significantly outperforming the baseline approaches, BIKER and CLEAR.

关键词： Training Source coding Semantics Feature extraction Testing Software engineering

来源：评论

学校读者我要写书评

暂无评论

RFID E-plate Data based Travel Time Reliability Estimation of Urban Expressway 4

RFID E-plate Data based Travel Time Reliability Estimation o...

引用

2021 4th International Symposium on Big Data and Applied Statistics, ISBDAS 2021

作者： Zhong, Siyuan School of Automation Chongqing University Chongqing400000 China Key Laboratory of Dependable Service Computing in Cyber Physical Society of Ministry of Education Chongqing China

Travel time distribution shows the aggregation degree of vehicle travel time in road network, and travel time reliability is the key index to measure the aggregation degree of travel time. In order to quantitatively evaluate the fluctuation of travel time of expressway vehicles, it is necessary to establish an estimation method of travel time reliability of expressway. Travel time reliability estimation needs to obtain travel time data of vehicles. Traditional Global Position System (GPS) and video detection methods are easily affected by external factors such as weather and environment, and the description of travel time distribution is not comprehensive under the condition of low permeability. On the other hand, in the evaluation of travel time reliability, although there are lots of travel time probability distribution models, the correlation of vehicle travel time between links is ignored when calculating travel time reliability. In order to estimate travel time reliability more accurately, based on Radio Frequency Identification (RFID) electronic license plate (E-plate) data, this paper proposes a path travel time reliability evaluation model considering travel time correlation between links. First, the RFID readers installed on the gantry of expressway acquires data from the electronic tags deployed on vehicles. Secondly, a percentile travel time estimation method is proposed based on Cornish-Fisher expansion and the skewness of travel time distribution. Finally, considering the reliability estimation of travel time under the correlation of links, the estimated value is closer to the true value. The experimental results show that the travel time reliability estimation method considering the correlation between links improves the accuracy of estimation in the expressway network environment. © Published under licence by IOP Publishing Ltd.

关键词： Travel time

来源：评论

学校读者我要写书评

暂无评论

A novel wideband beam reconfigurable magneto-electric dipole patch antenna

引用

Progress In Electromagnetics Research C 2021年 109卷 111-123页

作者： Wang, Min Yang, Huifeng Hu, Nan Xie, Wenqing Mo, Yuxin Chen, Zhenghan Liu, Zhongyuan Chen, Zhengchuan School of Optoelectronic Engineering Chongqing University of Posts and Telecommunications China A-INFO Inc Beijing100084 China The Key Laboratory of Dependable Service Computing in Cyber-Physical Society Ministry of Education and the School of Microelectronics and Communication Engineering Chongqing University China

—A novel wideband beam reconfigurable magneto-electric dipole patch antenna is presented in this paper. The proposed antenna consists of two H-shaped patches, two folded patches, an E-shaped feeding structure, a side-slotted ground, and a large reflective ground. Two H-shaped patches are horizontally placed on both sides of the feed structure, and two folded patches are assembled vertically to the upper ground, which are designed as the magneto-electric dipole structure. Two symmetrically sided slots are etched on the upper ground to reduce the profile, and an E-shaped strip is employed in the feeding structure to broaden the bandwidth. To suppress the backward radiation, a lower ground with large size is designed as a reflector. Four binary switches are symmetrically integrated on the stubs of H-shaped patches. By switching them ON or OFF simultaneously, the current distribution is changed to achieve beam reconfigurability. Finally, a set of antenna prototype with four configurations is fabricated and measured. The measured results show that maximum impedance bandwidth achieves up to 77.8% at 2.7 GHz from 2.0 GHz to 4.1 GHz. At 2.7 GHz, the measured peak gains are 8.4 dBi, 9.3 dBi, 8.1 dBi, and 8.7 dBi, where the beams point to −21◦,0◦,21◦,and34◦, respectively in E-plane. © 2021, Electromagnetics Academy. All rights reserved.

关键词： Microstrip antennas

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：