检索结果-内蒙古大学图书馆

4th International Conference on Intelligent Power and Systems, ICIPS 2024

作者： Chai, Yuze Lin, Rongheng Wang, Baigen Wang, Ou Zhao, Qian Liu, Huizhou Beijing University of Posts and Telecommunications School of Computer Science State Key Lab of Networking and Switching Technology Beijing China Anqing Power Supply Company State Grid Anhui Electric Power Co. Ltd. Anqing China State Grid Anhui Electric Power Co. Ltd. Hefei China

ISBN: (纸本)9798331532765

The topology diagram of the power network is an indispensable tool in power system planning and operation. Although traditional hand-drawn power network topology diagrams can depict the basic framework of the network, they struggle to meet actual needs, especially when emphasizing certain key nodes, making manual methods cumbersome. This paper, based on the principles of graph theory and force-directed layout algorithms, converts the layout problem of the network into a graphical display problem, further extending it to three dimensional space. By introducing the concept of node importance into the traditional force-directed layout algorithm, key nodes are assigned additional gravitational weights, bringing them closer to the center in the layout, highlighting their importance within the network. Additionally, three-dimensional spatial considerations are introduced, allowing the layout diagram to be rotated and viewed from fixed angles, enabling better observation of node details from specific perspectives. Through experiments on the IEEE 14-bus system, this method has proven effective in visualizing power network topology, particularly in highlighting key nodes and enhancing 3D visual effects. © 2024 IEEE.

关键词： Network topology

来源：评论

学校读者我要写书评

暂无评论

Melon: Breaking the MemoryWall for Resource-Efficient On-Device Machine Learning 22

Melon: Breaking the MemoryWall for Resource-Efficient On-Dev...

引用

20th ACM International Conference on Mobile Systems, Applications and Services, MobiSys 2022

作者： Wang, Qipeng Xu, Mengwei Jin, Chao Dong, Xinran Yuan, Jinliang Jin, Xin Huang, Gang Liu, Yunxin Liu, Xuanzhe Key Lab of High Confidence Software Technologies Peking University Beijing China State Key Laboratory of Networking and Switching Technology Bupt Beijing China Tsinghua University Beijing China

ISBN: (纸本)9781450391856

On-device learning is a promising technique for emerging privacy-preserving machine learning paradigms. However, through quantitative experiments, we find that commodity mobile devices cannot well support state-of-the-art DNN training with a large enough batch size, due to the limited local memory capacity. To fill the gap, we propose Melon, a memory-friendly on-device learning framework that enables the training tasks with large batch size beyond the physical memory capacity. Melon judiciously retrofits existing memory saving techniques to fit into resource-constrained mobile devices, i.e., recomputation and micro-batch. Melon further incorporates novel techniques to deal with the high memory fragmentation and memory adaptation. We implement and evaluate Melon with various typical DNN models on commodity mobile devices. The results show that Melon can achieve up to 4.33× larger batch size under the same memory budget. Given the same batch size, Melon achieves 1.89× on average (up to 4.01×) higher training throughput, and saves up to 49.43% energy compared to competitive alternatives. Furthermore, Melon reduces 78.59% computation on average in terms of memory budget adaptation. © 2022 ACM.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A Novel Environment Object Modeling Method for Vehicular ISAC Scenarios

arXiv

引用

arXiv 2025年

作者： Jiang, Hanyuan Zhang, Yuxiang Liu, Yameng Zhang, Jianhua Tian, Lei Jiang, Tao State Key Lab of Networking and Switching Technology Beijing University of Posts and Telecommunications Beijing China China Mobile Research Institution Beijing China

Integrated Sensing and Communication (ISAC), as a fundamental technology of 6G, empowers Vehicle-to-Everything (V2X) systems with enhanced sensing capabilities. One of its promising applications is the reliance on constructed maps for vehicle positioning. Traditional positioning methods primarily rely on Line-of-Sight (LOS), but in urban vehicular scenarios, obstructions often result in predominantly Non-Line-of-Sight (NLOS) conditions. Existing researched indicate that NLOS paths, characterized by one-bounce reflection on building wall with determined delay and angle, can support sensing and positioning. However, experimental validation remains insufficient. To address this gap, channel measurements are conducted in an urban street to explore the existence of strong reflected paths in the presence of a vehicle target. The results show significant power contribution from NLOS paths, with large Environmental Objects (EOs) playing a key role in shaping NLOS propagation. Then, a novel model for EO reflection is proposed to extend the Geometry-Based Stochastic Model (GBSM) for ISAC channel standardization. Simulation results validate the model’s ability to capture EO’s power and position characteristics, showing that higher EO-reflected power and closer distance to Rx reduce Delay Spread (DS), which is more favorable for positioning. This model provides theoretical guidance and empirical support for ISAC positioning algorithms and system design in vehicular scenarios. Copyright © 2025, The Authors. All rights reserved.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Data-driven Industrial Enterprise Order Scheduling and Optimization 6

Data-driven Industrial Enterprise Order Scheduling and Optim...

引用

6th International Conference on Frontier Technologies of Information and Computer, ICFTIC 2024

作者： Xu, Sen Lin, Rongheng Wang, Baigen Wang, Ou Zhao, Qian Liu, Huizhou School of Computer Science Beijing University of Posts and Telecommunications State Key l Lab of Networking and Switching Technology Beijing China Anqing Power Supply Company State Grid Anhui Electric Power Co. Ltd. Anqing China State Grid Anhui Electric Power Co. Ltd. Hefei China

ISBN: (纸本)9798331541750

As China's industrial enterprises continue to grow and competition intensifies, efficient order scheduling and management have become essential to operational success. Many enterprises face challenges such as dispersed and unstandardized order data, reliance on manual scheduling, and limited data analysis capabilities. This study leverages priority-based and genetic algorithms, supported by extensive original fixed data (e.g., reservation order data, raw material supply data, production process data) and system-generated production data (e.g., sub-order data, raw material demand data), to design an optimized order scheduling method. The proposed algorithm not only meets order acceptance and scheduling requirements but also improves the rationality of order scheduling and the effectiveness of resource allocation. By reducing the rate of incomplete orders caused by raw material supply constraints and tight delivery times, this algorithm offers industrial enterprises a standardized production process, thereby enhancing overall operational efficiency and competitiveness. © 2024 IEEE.

关键词： genetic algorithm order scheduling priority

来源：评论

学校读者我要写书评

暂无评论

Short-Term Load Forecasting Method Based on ARIMA and LSTM 22

Short-Term Load Forecasting Method Based on ARIMA and LSTM

引用

22nd IEEE International Conference on Communication technology, ICCT 2022

作者： Chen, Shuo Lin, Rongheng Zeng, Wei Beijing University of Posts and Telecommunications School of Computer Science State Key Lab of Networking and Switching Technology Beijing China State Grid Jiangxi Electric Power Research Institute Jiangxi China

ISBN: (纸本)9781665470674

This paper explores the classic prediction algorithms such as Autoregressive Integrated Moving Average model (ARIMA) and Long Short-Term Memory Neural Network (LSTM), and combines the advantages of both, and proposes a short-term forecast method ARIMA-LSTM fusion model. This model computes the final predicted value by applying a linear correctio to the LSTM model error. Using ARIMA and LSTM as a comparison algorithm, train and predict the next day's load with ARIMA-LSTM. The root mean square error (RMSE), mean absolute percentage error (MAPE), and the worst relative error (WRE) were used to evaluate the performance of the proposed algorithm. After testing, the RMSE of the proposed model is 0.433, while ARIMA and LSTM are 0.461 and 0.445 respectively. ARIMA-LSTM also has better results and performs well on different types of power datasets. © 2022 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Gdb: Gated Convolutions-Based Document Binarization

SSRN

引用

SSRN 2023年

作者： Yang, Zongyuan Xiong, Yongping Wu, Guibin The State Key Lab. of Switching and Networking Technology Beijing University of Posts and Telecommunications Beijing100876 China

Document binarization is a key pre-processing step for many document analysis tasks. However, existing methods can not extract stroke edges finely, mainly due to the fairtreatment nature of vanilla convolutions and the extraction of stroke edges without adequate supervision by boundary-related information. In this paper, we formulate text extraction as the learning of gating values and propose an end-to-end gated convolutionsbased network (GDB) to solve the problem of imprecise stroke edge extraction. The gated convolutions are applied to selectively extract the features of strokes with different attention. Our proposed framework consists of two stages. Firstly, a coarse sub-network with an extra edge branch is trained to get more precise feature maps by feeding a priori mask and edge. Secondly, a refinement sub-network is cascaded to refine the output of the first stage by gated convolutions based on the sharp edge. For global information, GDB also contains a parallelized multi-scale operation to combine local and global features. We conduct comprehensive experiments on ten Document Image Binarization Contest (DIBCO) datasets from 2009 to 2019. Experimental results show that our proposed methods outperform the state-of-the-art methods in terms of all metrics on average and achieve top ranking on six benchmark datasets. © 2023, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

CACA Agent: Capability Collaboration based AI Agent

arXiv

引用

arXiv 2024年

作者： Xu, Peng Wang, Haoran Wang, Chuang Liu, Xu State Key Lab of Networking and Switching Technology Beijing University of Posts and Telecommunications Beijing China China Academy of Industrial Internet Beijing China

As AI Agents based on Large Language Models (LLMs) have shown potential in practical applications across various fields, how to quickly deploy an AI agent and how to conveniently expand the application scenario of AI agents has become a challenge. Previous studies mainly focused on implementing all the reasoning capabilities of AI agents within a single LLM, which often makes the model more complex and also reduces the extensibility of AI agent functionality. In this paper, we propose CACA Agent (Capability Collaboration based AI Agent), using an open architecture inspired by service computing. CACA Agent integrates a set of collaborative capabilities to implement AI Agents, not only reducing the dependence on a single LLM, but also enhancing the extensibility of both the planning abilities and the tools available to AI agents. Utilizing the proposed system, we present a demo to illustrate the operation and the application scenario extension of CACA Agent. Copyright © 2024, The Authors. All rights reserved.

关键词： Computer architecture

来源：评论

学校读者我要写书评

暂无评论

Graph-based Anomaly Detection and Root Cause Analysis for Microservices in Cloud-Native Platform

Graph-based Anomaly Detection and Root Cause Analysis for Mi...

引用

Sustainable Computing and Communications (SustainCom), IEEE International Conference on

作者： Xinwei Wang Xu Liu Peng Xu Haoran Du Beijing University of Posts and Telecommunications State Key Lab of Networking and Switching Technology Beijing China China Academy of Industrial Internet Beijing China

ISBN: (数字)9798331521059

ISBN: (纸本)9798331521066

Due to the excellent characteristics of microservices architecture, such as high scalability, high fault tolerance, and ease of maintenance, and the flexible, efficient, and scalable deployment environment provided by cloud-native platforms, an increasing number of applications are being constructed based on microservices architecture. In such scenarios, the complexity of anomaly detection rises sharply due to the involvement of numerous interrelated microservices components and the complex invocation relationships among these components in each microservices application. Existing anomaly detection methods struggle to maintain sufficient accuracy in such complex environments. To address this challenge, this paper proposes the Graph-based Anomaly Detection and Root Cause Analysis (GADRCA) method for Microservices in Cloud-Native Platform. This method leverages graph structures to comprehensively considers the fundamental distribution characteristics of multiple resource consumption metrics involved in the runtime of microservices applications, such as response time, CPU usage, and memory usage. It also preserves the structural information of trace data within microservices to achieve more comprehensive anomaly detection. Upon identifying anomalous traces, the method determines the direction of anomaly propagation using the traces root cause analysis approach based on multiple metric anomaly types. Finally, a topological graph approach is employed to accurately pinpoint the root cause service. The proposed method’s effectiveness in enhancing anomaly detection and root cause analysis has been demonstrated through a series of experiments.

关键词： Measurement Root cause analysis Runtime Scalability Memory management Fault tolerant systems Microservice architectures Maintenance Time factors Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Time-Varying Channel Measurement and Analysis at 105 GHz in an Indoor Factory

Time-Varying Channel Measurement and Analysis at 105 GHz in ...

引用

European Conference on Antennas and Propagation, EuCAP

作者： Yufeng Qin Pan Tang Lei Tian Jiaxin Lin Zhaowei Chang Peijie Liu Jianhua Zhang Tao Jiang State Key Lab of Networking and Switching Technology Beijing University of Posts and Telecommunications Beijing China China Mobile Research Institute Beijing China

As one of the sixth-generation (6G) candidate technologies, terahertz (THz) communication is considered a promising way to achieve high-precision capability and large capacity in the Industrial Internet of Things (IIoT) due to its wide bandwidth and short wavelength. This paper presents time-varying THz channel measurements at 105 GHz in an indoor factory (InF). Firstly, the number of the multipath components (MPC) and root-mean-square delay spread (RMS DS) in line-of-sight (LoS) and nonline-of-sight (NLoS) environments are analyzed and compared. Secondly, the correlation between power delay profiles (PDP) is described by the temporal PDP correlation coefficient (TPCC). Finally, the local region of stationarity (LRS) method is employed to characterize the stationary distance. A Burr distribution is used to fit the distribution of stationary distance. The work contributes to modeling the THz channel in the time-varying environment in InF.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cascaded channel modeling and experimental validation for RIS assisted communication system

arXiv

引用

arXiv 2024年

作者： Zhang, Jiwei Zhang, Yuxiang Jiang, Tao Gong, Huiwen Xing, Hongbo Tian, Lei State Key Lab of Networking and Switching Technology Beijing University of Posts and Telecommunications Beijing China China Mobile Research Institution Beijing China

Reconfigurable Intelligent Surface (RIS) is considered as a promising technology for 6G due to its ability to actively modify the electromagnetic propagation environment. Accurate channel modeling is essential for the design and evaluation of RIS assisted communication systems. Most current research models the RIS channel as a cascade of Tx-RIS and RIS-Rx sub-channels. However, most validation efforts regarding this assumption focus on large-scale path loss. To further explore this, in this paper, we derive and extend a convolution expression of RIS cascaded channel model based on the previously proposed Geometry-based Stochastic Model (GBSM)-based RIS cascaded channels. This model follows the 3GPP standard framework and leverages parameters such as angles, delays, and path powers defined in the GBSM model to more accurately reflect the small-scale characteristics of RIS multipath cascades. To verify the accuracy of this model, we conduct measurements of the Tx-RIS-Rx channel, Tx-RIS, and RIS-Rx sub-channels in a factory environment at 6.9 GHz, using the measured data to demonstrate the model’s validity and applicability in real-world scenarios. Validation with measured data shows that the proposed model accurately describes the characteristics of the RIS cascaded channel in terms of delay, angle, and power in complex multipath environments, providing important references for the design and deployment of RIS systems. Copyright © 2024, The Authors. All rights reserved.

关键词： Multipath propagation

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：