检索结果-南通市图书馆

Distributed Energy and Reserve Scheduling in Local Energy Communities Using L-BFGS Optimization

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

CSEE Journal of Power and Energy Systems 2024年第3期10卷 942-952页

作者： Mohammad Dolatabadi Alireza Zakariazadeh Alberto Borghetti Pierluigi Siano department of management&innovation Systems University of SalernoSalernoItaly department of Electrical Electronicand Information EngineeringUniversity of BolognaBolognaItaly University of Science and technology of Mazandaran BehshahrIran department of Power Systems National University of Science and Technology POLITEHNICA BucharestBucharestRomania IEEE

Encouraging citizens to invest in small-scale renewable resources is crucial for transitioning towards a sustainable and clean energy *** energy communities(LECs)are expected to play a vital role in this ***,energy scheduling in LECs presents various challenges,including the preservation of customer privacy,adherence to distribution network constraints,and the management of computational *** paper introduces a novel approach for energy scheduling in renewable-based LECs using a decentralized optimization *** proposed approach uses the Limitedmemory Broyden–Fletcher–Goldfarb–Shanno(L-BFGS)method,significantly reducing the computational effort required for solving the mixed integer programming(MIP)*** incorporates network constraints,evaluates energy losses,and enables community participants to provide ancillary services like a regulation reserve to the grid *** assess its robustness and efficiency,the proposed approach is tested on an 84-bus radial distribution *** indicate that the proposed distributed approach not only matches the accuracy of the corresponding centralized model but also exhibits scalability and preserves participant privacy.

关键词： Distributed optimization flexibility services L-BFGS method local energy community renewables reserve

Path signature-based XAI-enabled network time series classification

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第7期67卷 91-106页

作者： Le SUN Yueyuan WANG Yongjun REN Feng XIA department of Jiangsu Collaborative innovation Center of Atmospheric Environment and Equipment technology(CICAEET) Nanjing University of Information Science and Technology School of Computing Technologies Royal Melbourne Institute of Technology

Classifying network time series(NTS) is crucial for automating network administration and ensuring cyberspace security. It enables the detection of anomalies, the identification of network attacks,and the monitoring of performance issues, thereby providing valuable support for network protection and optimization. However, modern communication networks pose challenges for NTS classification *** include handling large-scale and complex NTS data, extracting features from intricate datasets, and addressing explainability requirements. These challenges are particularly pronounced for complex 5G networks. Notably, explainability has become crucial for the widespread deployment of network automation for 5G networks and beyond. To tackle these challenges, we propose a path-signature-based NTS classification model called recurrent signature(Recur Sig). This innovative model is designed to overcome the time-consuming feature selection problem by utilizing deep-learning(DL) techniques. Additionally, it provides a solution for addressing the black-box issue associated with DL models in network automation systems(NAS) by incorporating an explainable classification approach. Extensive experimentation on various public datasets demonstrates that Recur Sig outperforms existing models in accuracy and explainability. The results indicate its potential for application in cyberspace security and automated network management, offering an explainable solution for network protection and optimization.

关键词： network time series classification explainable artificial intelligence path signature automated network management recurrent neural network

OpBench: an operator-level GPU benchmark for deep learning

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第9期67卷 76-87页

作者： Qingwen GU Bo FAN Zhengning LIU Kaicheng CAO Songhai ZHANG Shimin HU department of Computer Science and technology Tsinghua University National innovation Institute of Defense technology Academy of Military Science Beijing Fitten technology Co. Ltd.

Operators(such as Conv and ReLU) play an important role in deep neural networks. Every neural network is composed of a series of differentiable operators. However, existing AI benchmarks mainly focus on accessing model training and inference performance of deep learning systems on specific models. To help GPU hardware find computing bottlenecks and intuitively evaluate GPU performance on specific deep learning tasks, this paper focuses on evaluating GPU performance at the operator level. We statistically analyze the information of operators on 12 representative deep learning models from six prominent AI tasks and provide an operator dataset to show the different importance of various types of operators in different networks. An operator-level benchmark, OpBench, is proposed on the basis of this dataset, allowing users to choose from a given range of models and set the input sizes according to their demands. This benchmark offers a detailed operator-level performance report for AI and hardware developers. We also evaluate four GPU models on OpBench and find that their performances differ on various types of operators and are not fully consistent with the performance metric FLOPS(floating point operations per second).

关键词： deep learning operator benchmark model benchmark GPU performance analysis deep neural networks

Models to Simulate Effective Coverage of Fire Station Based on Real-Time Travel Times

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Computer Modeling in Engineering & Sciences 2024年第4期139卷 483-513页

作者： Sicheng Zhu Dingli Liu Weijun Liu Ying Li Tian Zhou department of Engineering management Changsha University of Science and TechnologyChangsha410114China

In recent years,frequent fire disasters have led to enormous damage in *** firefighting rescues can minimize the losses caused by *** the rescue processes,the travel time of fire trucks can be severely affected by traffic conditions,changing the effective coverage of fire ***,it is still challenging to determine the effective coverage of fire stations considering dynamic traffic *** paper addresses this issue by combining the traveling time calculationmodelwith the effective coverage *** addition,it proposes a new index of total effective coverage area(TECA)based on the time-weighted average of the effective coverage area(ECA)to evaluate the urban fire *** also selects China as the case study to validate the feasibility of the models,a fire station(FS-JX)in ***-JX station and its surrounding 9,117 fire risk points are selected as the fire service supply and demand points,respectively.A total of 196 simulation scenarios throughout a consecutiveweek are ***,1,933,815 sets of valid sample data are *** results showed that the TECA of FS-JX is 3.27 km^(2),which is far below the standard requirement of 7.00 km^(2) due to the traffic *** visualization results showed that three rivers around FS-JX interrupt the continuity of its effective *** proposed method can provide data support to optimize the locations of fire stations by accurately and dynamically determining the effective coverage of fire stations.

关键词： Fire services fire station effective coverage real-time traffic simulation

Mechanical performance of 22SiMn2TiB steel welded with lowtransformation- temperature filler wire and stainless steel filler wire

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Iron and Steel Research International 2024年第4期31卷 967-981页

作者： Zi-dong Lin Kai-jie Song Zhen Sun Zi-qian Zhu Xue-feng Zhao Constantinos Goulas Wei Ya Xing-hua Yu School of Materials Science and Engineering Beijing Institute of TechnologyBeijing 100081China Beijing Institute of technology Chongqing innovation Center Chongqing 401120China department of Design Production and management Faculty of Engineering Technology.University of TwenteEnschede 7500 AETheNetherlands Rotterdam Additive Manufacture Fieldlab(RAMLAB) Rotterdam 3089 JWTheNetherlands

TX-80 low-transformation-temperature(LTT)welding wire was used to replace the traditional ER 307Si welding wire to realize the connection of 22SiMn2TiB armor steel in manual overlay *** previously existing issues,such as welding cracks,large welding deformation,and severe welding residual stress,were solved to ensure good strength and ductility *** particular,with the same welding conditions,TX-80 LTT wire eliminates welding *** reduces the welding deformation no matter the base pretreatment of pre-setting angle or no pre-setting *** comparison,it was found that the microstructure at the TX-80 weld is mainly composed of martensite and a small amount of retained *** contrast,the microstructure of the ER 307Si weld consists of a large amount of austenite and a small amount of skeleton-like *** variation trend of residual stress and microhardness from the weld to the base were investigated and compared with the mechanical properties of base *** TX-80 and the ER 307Si tensile samples elongation is 6.76%and 6.01%,while the ultimate tensile strengths are 877 and 667 MPa,*** average impact toughness at room temperature of the ER 307Si weld is 143.9 J/cm^(2),much higher than that of the TX-80 weld,which is only 36.7 J/cm^(2).The relationship between impact and tensile properties with microstructure species and distribution was *** addition,the fracture surface of the tensile and the impact samples was observed and *** dimples,fewer pores,larger radiation zone,and shear lips of TX-80 samples indicate better tensile ductility and worse impact toughness than those of ER 307Si weld.

关键词： Low-transformation-temperature material 22SiMn2TiB steel Welding deformation Residual stress Martensitic transformation Mechanical property

Digital technology,the industrial internet,and cost stickiness

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

China Journal of Accounting Research 2024年第1期17卷 45-73页

作者： Lili Hui Huobao Xie Xiaofang Chen School of management Wuhan University of TechnologyWuhanChina Research Institute of Digital Governance and management Decision innovation Wuhan University of TechnologyWuhanChina School of Economics and management Wuhan UniversityWuhanChina

The deep integration of digital technology with the real economy has reconstructed production *** explore the impact of digital technology on the resource allocation behavior and efficiency of manufacturing *** a sample of Chinese A-share listed manufacturing firms over the 2010–2021 period,we find that digital technology alleviates cost stickiness,especially in enterprises with a high level of Industrial Internet platform *** effect occurs by optimizing the labor force structure and improving the economic benefits of labor capital *** analysis shows that this effect is pronounced in enterprises with high levels of labor intensity and business *** findings shed new light on the consequences and mechanism of enterprise cost optimization that is driven by technologydriven reforms.

关键词： Digital technology Cost Stickiness The Industrial Internet Labor Production Factor Empowerment

A nerve-like self-healable conductive wire

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

National Science Review 2024年第6期11卷 89-90页

作者： Xuemei Fu Benjamin C.K.Tee department of Materials Science and Engineering National University of Singapore Institute for Health innovation and technology National University of Singapore

In wearables and robotics, it is often required to deploy electronic devices at different spatially distributed locations for multi-functionality [1–3]. Thus, conductive wires for efficient interconnection of various electronic devices are ***, in practical applications, the frequent motion of wearers and robots will result in high-strain deformations of these wires, which could cause irreparable damage.

关键词：

Design of double protograph LDPC codes based JSCC systems via the ACE-PEG algorithm

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第7期67卷 339-340页

作者： Yijie LV Jiguang HE Shaohua HONG department of Information and Communication Engineering Xiamen University technology innovation Institute Centre for Wireless Communications Oulu University

In this study, we present a state-of-the-art design of double protograph low-density parity-check (DP-LDPC) codes based on progressive edge-growth (PEG) algorithm with approximated cycle extrinsic message degree (ACE)... 详细信息

关键词： Benchmarking

Higher-order properties and extensions for indirect MRAC and APPC of linear systems

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第4期67卷 218-238页

作者： Yanjun ZHANG Zhipeng ZHANG Jian SUN Lei WANG Kangkang ZHANG National Key Lab of Autonomous Intelligent Unmanned Systems Beijing Institute of Technology Beijing Institute of technology Chongqing innovation Center College of Control Science and Engineering Zhejiang University department of Electrical and Electronic Engineering Imperial College London KIOS Research and innovation Center of Excellence University of Cyprus

Recently, a reference derived some new higher-order output tracking properties for direct model reference adaptive control(MRAC) of linear time-invariant(LTI) systems: limt→∞ e~((i))(t) = 0, i = 1,..., n~*-1, where n~* and e~((i))(t) denote the relative degree of the system and the i-th derivative of the output tracking error, respectively. However, a naturally arising question involves whether indirect adaptive control(including indirect MRAC and indirect adaptive pole placement control) of LTI systems still has higher-order tracking properties. Such properties have not been reported in the literature. Therefore, this paper provides an affirmative answer to this question. Such higher-order tracking properties are new discoveries since they hold without any additional design conditions and, in particular, without the persistent excitation condition. Given the higher-order properties, a new adaptive control system is developed with stronger tracking features.(1) It can track a reference signal with any order derivatives being unknown.(2) It has higher-order exponential or practical output tracking properties.(3) Finally, it is different from the usual MRAC system, whose reference signal’s derivatives up to the n~* order are assumed to be known. Finally, two simulation examples are provided to verify the theoretical results obtained in this paper.

关键词： higher-order tracking indirect adaptive control model reference adaptive control adaptive pole placement control