检索结果-南通市图书馆

Journal of Modern Power Systems and Clean Energy 2024年第4期12卷 1217-1226页

作者： Zifeng Zhang Yuntao Ju state grid information&telecommunication Group Co. Ltd.Beijing BranchBejingChina School of Electrical and Control Engineering North China University of TechnologyBeijingChina

Networked microgrids(NMGs)are critical in theaccommodation of distributed renewable ***,theexisting centralized state estimation(SE)cannot meet the demandsof NMGs in distributed energy *** currentestimator is also not robust against bad *** study introducesthe concepts of relative error to construct an improvedrobust SE(IRSE)optimization model with mixed-integer nonlinearprogramming(MINLP)that overcomes the disadvantage ofinaccurate results derived from different measurements whenthe same tolerance range is considered in the robust SE(RSE).To improve the computation efficiency of the IRSE optimizationmodel,the number of binary variables is reduced based on theprojection statistics and normalized residual methods,which effectivelyavoid the problem of slow convergence or divergenceof the algorithm caused by too many integer ***,an embedded consensus alternating direction of multiplier method(ADMM)distribution algorithm based on outer approximation(OA)is proposed to solve the IRSE optimization *** algorithm can accurately detect bad data and obtain SE resultsthat communicate only the boundary coupling informationwith *** tests show that the proposed algorithmeffectively detects bad data,obtains more accurate SE results,and ensures the protection of private information in all microgrids.

关键词： Distributed optimization alternating direction of multiplier methods(ADMM) robust state estimation(RSE) mixed-integer nonlinear programming(MINLP) networked microgrid(NMG)

Real-Time Energy Management for Net-Zero Power Systems Based on Shared Energy Storage

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 Modern Power Systems and Clean Energy 2024年第2期12卷 371-380页

作者： Pengbo Du Bonan Huang Ziming Liu Chao Yang Qiuye Sun School of information Science and Engineering Northeastern UniversityShenyang 110004China information and Communication Branch State Grid Liaoning Electric Power Company Ltd.Shenyang 110004China IEEE

Battery energy storage systems(BESSs)serve a crucial role in balancing energy fluctuations and reducing carbon emissions in net-zero power ***,the efficiency and cost performance have remained significant challenges,which hinders the widespread adoption and development of *** address these challenges,this paper proposes a real-time energy management scheme that considers the involvement of prosumers to support net-zero power *** scheme is based on two shared energy storage models,referred to as energy storage sale model and power line lease *** energy storage sale model balances real-time power deviations by energy interaction with the goal of minimizing system costs while generating revenue for shared energy storage providers(ESPs).Additionally,power line lease model supports peer-to-peer(P2P)power trading among prosumers through the power lines laid by ESPs to connect each *** model allows ESP to earn profits from the use of power lines while balancing power deviations and better consuming renewable *** results validate the effectiveness of the proposed scheme,ensuring stable power supply for net-zero power systems and providing benefits for both the ESP and prosumers.

关键词： Shared energy storage energy storage provider(ESP) energy management peer-to-peer(P2P)trading net-zero power system

Distributed Graph Database Load Balancing Method Based on Deep Reinforcement Learning

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第6期79卷 5105-5124页

作者： Shuming Sha Naiwang Guo Wang Luo Yong Zhang Nanjing NARI information&Communication Technology Co. Ltd.Nanjing210032China state grid Electric Power Research Institute Nanjing211106China state grid Shanghai Municipal Eleciric Power company Shanghai200122China

This paper focuses on the scheduling problem of workflow tasks that exhibit *** indepen-dent batch tasks,workflows typically consist of multiple subtasks with intrinsic correlations and *** necessitates the distribution of various computational tasks to appropriate computing node resources in accor-dance with task dependencies to ensure the smooth completion of the entire *** scheduling must consider an array of factors,including task dependencies,availability of computational resources,and the schedulability of ***,this paper delves into the distributed graph database workflow task scheduling problem and proposes a workflow scheduling methodology based on deep reinforcement learning(DRL).The method optimizes the maximum completion time(makespan)and response time of workflow tasks,aiming to enhance the responsiveness of workflow tasks while ensuring the minimization of the *** experimental results indicate that the Q-learning Deep Reinforcement Learning(Q-DRL)algorithm markedly diminishes the makespan and refines the average response time within distributed graph database *** quantifying makespan,Q-DRL achieves mean reductions of 12.4%and 11.9%over established First-fit and Random scheduling strategies,***,Q-DRL surpasses the performance of both DRL-Cloud and Improved Deep Q-learning Network(IDQN)algorithms,with improvements standing at 4.4%and 2.6%,*** reference to average response time,the Q-DRL approach exhibits a significantly enhanced performance in the scheduling of workflow tasks,decreasing the average by 2.27%and 4.71%when compared to IDQN and DRL-Cloud,*** Q-DRL algorithm also demonstrates a notable increase in the efficiency of system resource utilization,reducing the average idle rate by 5.02%and 9.30%in comparison to IDQN and DRL-Cloud,*** findings support the assertion that Q-DRL not only upholds a lower average

关键词： Reinforcement learning workflow task scheduling load balancing

Safety monitoring method for powerline corridors based on single‐stage detector and visual matching

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

High Voltage 2024年第4期9卷 805-815页

作者： Jinheng Li Hanbo Zheng Peng Liu Yanshen Liang Feng Shuang Junjie Huang Guangxi Key Laboratory of Power System Optimization and Energy Technology Guangxi UniversityNanningChina China Southern Power grid Guangxi Power grid company ltd. NanningChina state grid Hubei Electric Power Research Institute WuhanChina

Effective monitoring and early warning of overhead power lines are critical for ensuring power supply stability and personnel ***,existing methods that rely solely on single vision or light detection and ranging(LiDAR)have limitations such as numerous invalid alarms,hardware equipment constraints,and lack of real-time monitoring *** article proposes an intelligent monitoring method for safety distance of the powerline corridor based on heterogeneous sensor ***,an optimised single-stage detector is designed to detect safety hazard *** the detector,the backbone network and the sample matching strategy are improved;in addition,the learning strategy is ***,the pose transformation relationship is obtained through the visual matching of prior LiDAR information and *** back projection transformation of 2D–3D is achieved according to the ***,a monocular camera-based end-to-end distance measurement scheme is proposed by combining 2D object information with coordinate transformation *** scheme is applied to the distance measurements from hazard objects to *** experimental results show that the optimisation method improves the detection accuracy and reduces the computational complexity of the ***,case experiments with continuous frame data verify the effectiveness of the safety distance monitoring scheme.

关键词： visual hardware matching

Distributed Photovoltaic Real-Time Output Estimation Based on Graph Convolutional Networks

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 Shanghai Jiaotong university(Science) 2024年第2期29卷 290-296页

作者：陈利跃洪道鉴何星卢东祁张乾谢妮娜徐一洲应煌浩 state grid Zhejiang Electric Power Co. Ltd.Hangzhou 310007China state grid Zhejiang Taizhou Power Supply company Taizhou 318000ZhejiangChina Department of Automation School of Electronic Information and Electrical EngineeringShanghai Jiao Tong UniversityShanghai 200240China

The rapid growth of distributed photovoltaic(PV)has remarkable influence for the safe and economic operation of power *** view of the wide geographical distribution and a large number of distributed PV power stations,the current situation is that it is dificult to access the current dispatch data *** to the temporal and spatial characteristics of distributed PV,a graph convolution algorithm based on adaptive learning of adjacency matrix is proposed to estimate the real-time output of distributed PV in regional power *** actual case study shows that the adaptive graph convolution model gives different adjacency matrixes for different PV stations,which makes the corresponding output estimation algorithm have higher accuracy.

关键词： distributed photovoltaic(PV) graph convolution network power estimation

Real-Time Safety Behavior Detection Technology of Indoors Power Personnel Based on Human Key Points

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 Shanghai Jiaotong university(Science) 2024年第2期29卷 309-315页

作者：杨坚李聪敏洪道鉴卢东祁林秋佳方兴其喻谦张乾 state grid Zhejiang Taizhou Power Supply company Taizhou 318000ZhejiangChina Department of Automation Shanghai Jiao Tong UniversityShanghai 200240China Zhejiang Huayun information Technology Co. Ltd.Hangzhou 310012China

Safety production is of great significance to the development of enterprises and *** often cause great losses because of the particularity environment of electric ***,it is important to improve the safety supervision and protection in the electric power *** this paper,we simulate the actual electric power operation scenario by monitoring equipment and propose a real-time detection method of illegal actions based on human body key points to ensure safety behavior in real *** this method,the human body key points in video frames were first extracted by the high-resolution network,and then classified in real time by spatial-temporal graph convolutional *** results show that this method can effectively detect illegal actions in the simulated scene.

关键词： real-time behavior recognition human key points high-resolution network spatial-temporal graph convolutional network

A Coordinated Two-stage Decentralized Flexibility Trading in Distribution grids with MGs

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Protection and Control of Modern Power Systems 2024年第5期9卷 54-69页

作者： Tao Xu Rujing Wang He Meng Mengchao Li Hongru Wang Yu Ji Ying Zhang Qingrong Zheng Ping Song Jiani Xiang Key Laboratory of Smart grid of Ministry of Education Tianjin UniversityTianjin 300072China state grid Shanghai Energy Interconnection Research Institute Co. Ltd.Shanghai 200031China Key Laboratory of Smart grid Demand Response Shanghai 200030China state grid Shanghai Municipal Electric Power company Shanghai 200122China

Renewable energy dominated future power grids require enhanced system flexibility,in particular,activating the participation from various distributed en-ergy resources(DERs).A coordinated two-stage flexibility trading framework for distribution system with mi-crogrids(MGs)is proposed in this *** day-ahead stage,a peer to peer(P2P)trading mechanism and the associate leasing strategy of shared energy storage system are performed to solve the power variations caused by the wide spread integration of renewable resources,where asymmetric Nash bargaining is used to realize the fair revenue allocation according to the contribution of each MG in P2P *** intra-day stage,given the power imbalances from unexpected uncertainties,MGs exploit the adjustability of the DERs in responding to rapid flexibility requirements issued by distribution system *** particular,the average consensus based de-centralized Newton method with super linear convergence is utilized to meet the requirements of flexibility while maintaining the information *** feasibility,effectiveness and equity of the proposed trading strategies are verified through various simulation *** Terms—Microgrids,decentralized Newton,flexi-bility trading,asymmetric Nash bargaining,peer-to-peer.

关键词： Microgrids decentralized Newton flexibility trading asymmetric Nash bargaining peer-to-peer

FaultMonitoring Strategy for PV System Based on I-V Feature Library

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Energy Engineering 2024年第3期121卷 643-660页

作者： Huaxing Zhao Yanbo Che Gang Wen Yijing Chen School of Electrical and information Engineering Tianjin UniversityTianjin300000China state grid Shuozhou Electric Power Supply company Shuozhou036000China China Huaneng Clean Energy Research lnstitute Technology Co. Ltd.Beijing102209China

Long-term use in challenging natural conditions is possible for photovoltaic modules,which are extremely prone to *** to diagnose and address faults in Photovoltaic(PV)power systems in a timely manner can cause permanent damage to PV modules and,in more serious cases,***,research into photovoltaic module defect detection techniques is crucial for the growth of the photovoltaic sector as well as for maintaining national economic prosperity and ensuring public *** the drawbacks of the current real-time and historical data-based methods for monitoring distributed PV systems,this paper proposes a method for monitoring PV systems at the module or string level that can be achieved by monitoring only electrical *** approach doesn’t need a lot of tests to get the operational data of PV modules beforehand and only requires theoretical feature libraries of PV modules through panel parameter *** present operating conditions and the open-circuit and short-circuit faults can be precisely identified by comparing the observed open-circuit voltage and short-circuit current with the corresponding data in the theoretical feature *** that,by comparing the measured maximum power point voltage and current with the corresponding data in the theoretical feature library through the threshold method,aging and shadowing faults can be accurately *** testing was done to see whether the suggested method was *** results show that the proposed technique is able to diagnose open-circuit faults,short-circuit faults,aging faults,and shadowing faults with shadow occlusion above 20%.

关键词： PV system lambert W function threshold method

Image format pipeline and instrument diagram recognition method based on deep learning

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Biomimetic Intelligence & Robotics 2024年第1期4卷 36-44页

作者： Guanqun Su Shuai Zhao Tao Li Shengyong Liu Yaqi Li Guanglong Zhao Zhongtao Li Shandong Qingniao IIoT Co. ltd.Jinan 250014China Jinan Housing and Urban-Rural Development Bureau Jinan 250012China state grid Shandong Electric Extrahigh Voltage company Jinan 250018China School of information Science and Engineering University of JinanJinan 250022China

In this study,we proposed a recognition method based on deep artificial neural networks to identify various elements in pipelines and instrumentation diagrams(P&ID)in image formats,such as symbols,texts,and ***,the P&ID image format is recognized manually,and there is a problem with a high recognition error rate;therefore,automation of the above process is an important issue in the processing plant *** China National Offshore Petrochemical Engineering *** the image set used in this study,which contains 51 P&ID drawings in the *** converted the PDF P&ID drawings to PNG P&IDs with an image size of 8410×*** addition,we used labeling software to annotate the images,divided the dataset into training and test sets in a 3:1 ratio,and deployed a deep neural network for *** method proposed in this study is divided into three *** first step segments the images and recognizes symbols using YOLOv5+*** second step determines text regions using character region awareness for text detection,and performs character recognition within the text region using the optical character recognition *** third step is pipeline recognition using YOLOv5+*** symbol recognition accuracy was 94.52%,and the recall rate was 93.27%.The recognition accuracy in the text positioning stage was 97.26%and the recall rate was 90.27%.The recognition accuracy in the character recognition stage was 90.03%and the recall rate was 91.87%.The pipeline identification accuracy was 92.9%,and the recall rate was 90.36%.

关键词： Deep learning Image processing Piping and instrumentation Object recognition Pipeline recognition

A Disturbance Localization Method for Power System Based on Group Sparse Representation and Entropy Weight Method

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Energy Engineering 2024年第8期121卷 2275-2291页

作者： Zeyi Wang Mingxi Jiao Daliang Wang Minxu Liu Minglei Jiang He Wang Shiqiang Li Changchun Power Supply company State Grid Jilin Electric Power Co.Ltd.Changchun130021China Economic and Technical Research Institute State Grid Jilin Electric Power Co.Ltd.Changchun130022China Key Laboratory of Modern Power System Simulation and Control&Renewable Energy Technology Northeast Electric Power UniversityJilin132012China

This paper addresses the problem of complex and challenging disturbance localization in the current power system operation environment by proposing a disturbance localization method for power systems based on group sparse representation and entropy weight *** different electrical quantities are selected as observations in the compressed sensing *** entropy weighting method is employed to calculate the weights of different observations based on their relative disturbance ***,by leveraging the topological information of the power system and pre-designing an overcomplete dictionary of disturbances based on the corresponding system parameter variations caused by disturbances,an improved Joint Generalized Orthogonal Matching Pursuit(J-GOMP)algorithm is utilized for *** reconstructed sparse vectors are divided into three *** at least two parts have consistent node identifiers,the node is identified as the disturbance *** the node identifiers in all three parts are inconsistent,further analysis is conducted considering the weights to determine the disturbance *** results based on the IEEE 39-bus system model demonstrate that the proposed method,utilizing electrical quantity information from only 8 measurement points,effectively locates disturbance positions and is applicable to various disturbance types with strong noise resistance.

关键词： Disturbance location compressed sensing group sparse representation entropy power method GOMP algorithm