检索结果-内蒙古大学图书馆

Bottlenecks and Countermeasures of High-Penetration Renewable Energy Development in China

engineering 2021年第11期7卷 1611-1622页

作者： Jizhen Liu Qinghua Wang Ziqiu Song Fang Fang State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources North China Electric Power UniversityBeijing 102206China School of Control and Computer Engineering North China Electric Power UniversityBeijing 102206China

China has become the world’s largest producer and consumer of energy,and ranks first in its wind and solar power installation ***,serious wind and solar curtailment in China has significantly hindered the development and utilization of renewable *** address problems in the consumption of renewable energy,this paper analyzes four key factors affecting the capacity of power generated from renewable energy sources:power balance,power regulation performance,transmission capacity,and load *** on these bottlenecks,we propose seven solutions:centralized and distributed development of renewable energy,improving the peak-load regulation flexibility of thermal power,increasing the proportion of gas turbines and pumped-hydropower storage,construction of transmission channels and a flexible smart grid developing demand response and virtual power plants,adopting new energy active support and energy storage,and establishing appropriate policies and market *** Chinese Government and energy authorities have issued a series of policies and measures,and in the past three years,China has had remarkable achievements in the adoption of renewable *** rate of idle wind capacity decreased from 17%in 2016 to 7%in 2018,and that of solar decreased from 10%in 2016 to 3%in 2018.

关键词： Bottlenecks Countermeasures Idle wind and solar power Renewable energy

来源：评论

学校读者我要写书评

暂无评论

Flagger: Cooperative Acceleration for Large-Scale Cross-Silo Federated Learning Aggregation

Flagger: Cooperative Acceleration for Large-Scale Cross-Silo...

引用

Annual International Symposium on computer Architecture, ISCA

作者： Xiurui Pan Yuda An Shengwen Liang Bo Mao Mingzhe Zhang Qiao Li Myoungsoo Jung Jie Zhang Computer Hardware and System Evolution Laboratory Peking University Chinese Academy of Sciences Institute of Computing Technology Xiamen University Chinese Academy of Sciences Institute of Information Engineering KAIST and Panmnesia

ISBN: (数字)9798350326581

ISBN: (纸本)9798350326598

Cross-silo federated learning (FL) leverages homomorphic encryption (HE) to obscure the model updates from the clients. However, HE poses the challenges of complex cryptographic computations and inflated ciphertext sizes. As cross-silo FL scales to accommodate larger models and more clients, the overheads of HE can overwhelm a CPU-centric aggregator architecture, including excessive network traffic, enormous data volume, intricate computations, and redundant data movements. Tackling these issues, we propose Flagger, an efficient and high-performance FL aggregator. Flagger meticulously integrates the data processing unit (DPU) with computational storage drives (CSD), employing these two distinct near-data processing (NDP) accelerators as a holistic architecture to collaboratively enhance FL aggregation. With the delicate delegation of complex FL aggregation tasks, we build Flagger-DPU and Flagger-CSD to exploit both in-network and in-storage HE acceleration to streamline FL aggregation. We also implement Flagger-Runtime, a dedicated software layer, to coordinate NDP accelerators and enable direct peer-to-peer data exchanges, markedly reducing data migration burdens. Our evaluation results reveal that Flagger expedites the aggregation in FL training iterations by ${436\%}$ on average, compared with traditional CPU-centric aggregators.

关键词： Training Solid modeling Runtime Federated learning Computational modeling computer architecture Telecommunication traffic

来源：评论

学校读者我要写书评

暂无评论

CMD: A Cache-assisted GPU Memory Deduplication Architecture

arXiv

引用

arXiv 2024年

作者： Zhao, Wei Feng, Dan Tong, Wei Wei, Xueliang Wu, Bing The Wuhan National Laboratory for Optoelectronics Key Laboratory of Information Storage System Engineering Research Center of Data Storage Systems and Technology Ministry of Education of China School of Computer Science and Technology Huazhong University of Science and Technology China

Massive off-chip accesses in GPUs are the main performance bottleneck, and we divided these accesses into three types: (1) Write, (2) Data-Read, and (3) Read-Only. Besides, We find that many writes are duplicate, and the duplication can be inter-dup and intra-dup. While inter-dup means different memory blocks are identical, and intra-dup means all the 4B elements in a line are the same. In this work, we propose a cache-assisted GPU memory deduplication architecture named CMD to reduce the off-chip accesses via utilizing the data duplication in GPU applications. CMD includes three key design contributions which aim to reduce the three kinds of accesses: (1) A novel GPU memory deduplication architecture that removes the inter-dup and inter-dup lines. As for the inter-dup detection, we reduce the extra read requests caused by the traditional read-verify hash process. Besides, we design several techniques to manage duplicate blocks. (2) We propose a cache-assisted read scheme to reduce the reads to duplicate data. When an L2 cache miss wants to read the duplicate block, if the reference block has been fetched to L2 and it is clean, we can copy it to the L2 missed block without accessing off-chip DRAM. As for the reads to intra-dup data, CMD uses the on-chip metadata cache to get the data. (3) When a cache line is evicted, the clean sectors in the line are invalidated while the dirty sectors are written back. However, most read-only victims are re-referenced from DRAM more than twice. Therefore, we add a full-associate FIFO to accommodate the read-only (it is also clean) victims to reduce the re-reference counts. Experiments show that CMD can decrease the off-chip accesses by 31.01%, reduce the energy by 32.78% and improve performance by 37.79%. Besides, CMD can improve the performance of memory-intensive workloads by 50.18%. © 2024, CC BY-NC-ND.

关键词： Cache memory

来源：评论

学校读者我要写书评

暂无评论

Balance Multi-Head Attention based on Software and Hardware Co-design 9

Balance Multi-Head Attention based on Software and Hardware ...

引用

9th IEEE International Conference on Cyber Security and Cloud Computing and 8th IEEE International Conference on Edge Computing and Scalable Cloud, CSCloud-EdgeCom 2022

作者： Xu, Dian Hu, Wei Liu, Fang Fan, Zimeng Shi, Qingsong Wuhan University of Science and Technology Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System College of Computer Science Wuhan China Wuhan University Department of Information Engineering Wuhan Institute of City School of Computer Science Wuhan China Zhejiang University College of Computer Science Hangzhou China

ISBN: (数字)9781665480666

ISBN: (纸本)9781665480666

Recently, the Transformer-based models have achieved leading results in many research areas such as natural language processing and computer vision. However, since Transformer-based models have a huge computational complexities, optimization for Transformer is the focus of current research. the core of Transformer models is the attention module, and in this paper we propose a software and hardware co-designed attention module, which reduces the computational units of the multi-head attention module by balancing the The inference time of the attention module is reduced by balancing the computational units of multiple attention modules. At the same time, we design the corresponding structure on FPGA, which accelerate 14.6x inference time in comparison with the original attention module implementation on GPU. We applied this attention module to multiple visual Transformer models and tested the accuracy difference between the balanced multi-head attention module-based model and the original model on CIFAR-10, and obtained a result of 80.46%, which lower from the original version by 0.18%. © 2022 IEEE.

关键词： Field programmable gate arrays (FPGA)

来源：评论

学校读者我要写书评

暂无评论

Transfer Task-Averaged Natural Gradient for Efficient Many-Task Optimization

引用

IEEE Transactions on Evolutionary Computation 2024年

作者： Li, Yanchi Gong, Wenyin Gu, Qiong China University of Geosciences School of Computer Wuhan430074 China Hubei University of Arts and Science School of Computer Engineering Xiangyang441053 China Hubei University of Arts and Science Hubei Key Laboratory of Power System Design and Test for Electrical Vehicle Xiangyang441053 China

With the increasing requirement for computational efficiency in evolutionary algorithms when tackling many optimization tasks concurrently, many-task optimization (MaTO) has gained much attention in recent years. It involves extracting and transferring the knowledge from successful search experiences across many tasks. As the number of tasks and variable scale grows in MaTO, the need for efficient knowledge transfer in evolutionary algorithms becomes indispensable. In this paper, we present a task-averaged natural gradient-assisted natural evolution strategy (TNG-NES) to deal with MaTO efficiently. The task-averaged natural gradient captures how a group of task distributions evolves, considering their overall trends of mean and covariance. This can accelerate the optimization process across all tasks by leveraging the evolutionary similarities among multiple task search distributions. Notably, TNG-NES exhibits linear computational complexity concerning the number of tasks for knowledge transfer. Additionally, to adaptively utilize task-averaged natural gradient for distribution evolution and mitigate negative transfer, we introduce a transfer adaptive control mechanism for TNG-NES. We conducted extensive experiments on CEC19-MaTO, WCCI22-MaTO, our proposed large-scale MaTO benchmark suite, and real-world applications. The results validate the effectiveness of TNG-NES, outperforming state-of-the-art MaTO algorithms. © 1997-2012 IEEE.

关键词： Knowledge transfer

来源：评论

学校读者我要写书评

暂无评论

Localization Method of Underwater Robot Based on Sonar Image 5

Localization Method of Underwater Robot Based on Sonar Image

引用

5th International Conference on Information Communication and Signal Processing, ICICSP 2022

作者： Li, Lirong Mei, Bing Chen, Peng Yu, Liang Gong, Pengcheng Hubei University of Technology Hubei Key Laboratory for High-efficiency Utilization of Solar Energy and Operation Control of Energy Storage System Wuhan China Hubei University of Technology Hubei Engineering Research Center for Safety Monitoring of New Energy and Power Grid Equipment Wuhan China School of Mechanical Engineering Shanghai Jiao Tong University State Key Laboratory of Mechanical System and Vibration Shanghai China School of Computer Science & Engineering Wuhan Institute of Technology Wuhan China

ISBN: (纸本)9781665485890

In this paper, we propose a positioning algorithm based on sonar images, which is mainly used for the positioning of underwater robots, so that the robots can obtain the position information in real time when operating underwater and avoid colliding with the underwater walls. First, the underwater space was detected with multibeam sonar, and the sonar images of the underwater space wall were found to have line segment characteristics;Composite denoising, threshold segmentation and Canny edge detection are applied to the sonar image to extract the contours of the underwater spatial wall. Then the characteristic line segments of the underwater spatial wall are detected based on the LSD (Line Segment Detector) line segment detection algorithm. In terms of line segment classification, a method is proposed to effectively classify line segments using the origin of the sonar image and the slope of the detected line segment. To further demonstrate the effectiveness of the localization algorithm in this paper, the specific steps of the algorithm are illustrated with the example of underwater rectangular space. © 2022 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Depression Scale Dictionary Decomposition Framework for Multimodal Automatic Depression Level Prediction

引用

IEEE Transactions on Circuits and systems for Video Technology 2025年第6期35卷 6195-6210页

作者： Niu, Mingyue Wang, Xu Gong, Jibing Liu, Bin Tao, Jianhua Schuller, Bjorn W. Yanshan University School of Information Science and Engineering Hebei province Qinhuangdao066004 China Hebei Key Laboratory of Computer Virtual Technology and System Integration China Technology Co. Ltd Bejing100022 China Bejing100190 China Tsinghua University Department of Automation Bejing100190 China University of Chinese Academy of Sciences School of Artificial Intelligence Beijing100049 China University of Augsburg ZD.B. Chair of Embedded Intelligence for Health Care and Wellbeing Augsburg Germany Glam - Group on Language Audio and Music United Kingdom

Currently, many researchers aim to achieve automatic depression level prediction via speech and video behavior analysis. However, previous works have struggled to decompose audio and video sequences into the information related to and unrelated to depression scores, hindering the model's perception of depression cues. Besides, previous works implement multimodal fusion using attention mechanisms or linear layers, but failed to simultaneously consider the Euclidean relationship among tokens and the non-Euclidean relationship among channels, which bring limitations in capturing depression cues. In response to the above issues, we propose a depression scale dictionary decomposition framework, which mainly includes a Bidirectional Dictionary Decomposition (BDD) module and a Bidirectional Multimodal Fusion (BMF) module. The BDD module can use the dictionaries generated based on the depression scale to semantically decompose audio and video sequences into the information related to and unrelated to depression scores along token and channel dimensions for promoting depression cue perception. Moreover, considering the respective characteristics of tokens and channels, the BMF module uses linear layers and graph convolution to achieve cross-modal mixing, which is used to aggregate audio and video sequences for predicting depression levels. The validation on AVEC 2013, AVEC 2014 and DAIC-WOZ datasets demonstrates our method's superiority. © 1991-2012 IEEE.

关键词： Boolean functions

来源：评论

学校读者我要写书评

暂无评论

GLC++: Source-Free Universal Domain Adaptation through Global-Local Clustering and Contrastive Affinity Learning

arXiv

引用

arXiv 2024年

作者： Qu, Sanqing Zou, Tianpei Röhrbein, Florian Lu, Cewu Chen, Guang Tao, Dacheng Jiang, Changjun The School of Automotive Engineering Department of Computer Science Tongji University China The Faculty of Computer Science Chemnitz University of Technology Germany The Department of Computer Science Shanghai Jiao Tong University China The School of Computer Science Faculty of Engineering The University of Sydney Australia The Department of Computer Science Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University China

Deep neural networks often exhibit sub-optimal performance under covariate and category shifts. Source-Free Domain Adaptation (SFDA) presents a promising solution to this dilemma, yet most SFDA approaches are restricted to closed-set scenarios. In this paper, we explore Source-Free Universal Domain Adaptation (SF-UniDA) aiming to accurately classify "known" data belonging to common categories and segregate them from target-private "unknown" data. We propose a novel Global and Local Clustering (GLC) technique, which comprises an adaptive one-vs-all global clustering algorithm to discern between target classes, complemented by a local k-NN clustering strategy to mitigate negative transfer. Despite the effectiveness, the inherent closed-set source architecture leads to uniform treatment of "unknown" data, impeding the identification of distinct "unknown" categories. To address this, we evolve GLC to GLC++, integrating a contrastive affinity learning strategy. We examine the superiority of GLC and GLC++ across multiple benchmarks and category shift scenarios. Remarkably, in the most challenging open-partial-set scenarios, GLC and GLC++ surpass GATE by 16.7% and 18.6% in H-score on VisDA, respectively. GLC++ enhances the novel category clustering accuracy of GLC by 4.3% in open-set scenarios on Office-Home. Furthermore, the introduced contrastive learning strategy not only enhances GLC but also significantly facilitates existing methodologies. Copyright © 2024, The Authors. All rights reserved.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

UAV Swarm Path Planning for Sensor Data Collection via Double Pre-Partitioned Deep Q-Network

引用

IEEE Sensors Journal 2025年

作者： Zhang, Heng Gao, Yuan Wang, Xin He, Yunpeng Yang, Ming Wu, Xiaoming Yang, Chaoqun Cao, Xianghui Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Jinan250014 China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Industrial Network and Information System Security Jinan250014 China Jiangsu Ocean University School of Computer Engineering Lianyungang222000 China Southeast University School of Automation Nanjing210096 China

Collision-free path planning is a significant challenge in deploying unmanned aerial vehicle (UAV) swarms for sensor data collection tasks, particularly in uncertain environments. This paper addresses the problem of designing flight strategies for energy-constrained UAV swarms using deep reinforcement learning. We propose a locally-aware double pre-partitioned deep Q-network (DPPDQN) for flight planning of multiple UAVs in large-scale uncertain industrial environments. This algorithm aims to collect data from ground sensors with communication constraints while avoiding mutual collisions. In the proposed algorithm, we first introduce a node pre-partitioning scheme using an improved clustering algorithm, which efficiently reduces the number of access points for UAVs through effective data aggregation. Subsequently, we employ an area pre-partitioning algorithm that segments the detection area into several subregions based on the number of UAVs available for operation, thereby preventing collisions among the UAV swarm during task execution. Finally, we propose a deep Q-Network algorithm incorporating a convolutional neural network, which utilizes the local perceptions of UAVs as state inputs to address the 'curse of dimensionality"occurring in large-scale environments. systematic simulation experiments validate the effectiveness and advantages of the proposed method. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Multi-level graph contrastive learning for cold-start recommendation in mashup development

引用

Information Sciences 2025年 717卷

作者： Sun, Mengmeng Xu, Yueshen Tan, Zeyu You, Dianlong Chen, Zhen School of Information Science and Engineering Yanshan University Qinhuangdao066004 China School of Computer Science and Technology Xidian University Xi'an710071 China Hebei Key Laboratory for Computer Virtual Technology and System Integration Yanshan University Qinhuangdao066004 China

One longstanding challenge in cloud API recommender systems is the Mashup cold-start problem, i.e., to recommend suitable cloud APIs for new Mashups without any historical invocation records. To address this challenge, researchers typically integrate various auxiliary information and feed them into a supervised learning model, or provide contextual information beyond interaction behaviors via explicit graph connections. However, these researches fail to 1) explore the functionally complementary relationship between Mashups and cloud APIs, and 2) model their semantic associations. To this end, we propose a Multi-level Graph Contrastive Learning, namely MGCL. Unlike traditional single-view methods, we comprehensively model Mashup-API relationships from three views: interaction, functionally complementary, and semantics. The interaction view captures dynamic behaviors, while the other two reveal associations based on static attributes. Additionally, we design a multi-level graph contrastive learning mechanism to fuse information from these views in a self-supervised manner, enabling both cold- and warm-start Mashup representations to benefit from dynamic interaction behaviors and static attributes. Extensive experiments on real-world datasets demonstrate that MGCL outperforms state-of-the-art methods in both Mashup cold- and warm-start scenarios. The implementations are available at: https://***/MengMeng3399/MGCL. © 2025 Elsevier Inc.

关键词： Contrastive Learning

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：