检索结果-内蒙古大学图书馆

10th IEEE Smart World Congress, SWC 2024

作者： Cheng, Long Yan, Huiru Zhou, Hanlin Wang, Ying Tang, Haichuan Fang, Fang North China Electric Power University State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources School of Control and Computer Engineering Beijing China Institute of Computing Technology Chinese Academy of Sciences Beijing China Ai Lab of Crrc Academy Beijing China

ISBN: (纸本)9798331520861

Preventing network attacks and protecting user privacy are consistently hot research topics in the Internet of Things (IoT) and edge computing fields. Recent advancements in Federated Learning (FL) have shown promise in addressing these challenges. FL allows various clients to collaboratively build an intrusion detection system (IDS) without sharing their private data. However, most existing methods train a single intrusion detection model for all clients and assume that the training and test data distribution are identical, leading to unsatisfactory detection accuracy and generalization abilities in practice. To overcome these challenges, this paper introduces a prototype-guided personalized FL approach named PG-FedIDS. We propose two novel mechanisms within this method. Firstly, we utilize class prototypes as auxiliary information carriers to generate personalized models for each client, rather than generating a single global model as in previous works. Secondly, we propose a prototype-guided ensemble learning strategy, which can leverage the global knowledge in prototypes to enhance detection accuracy and generalization abilities for each client. We conduct extensive experiments on two benchmark datasets with different evaluation test settings. The results demonstrate that our PG-FedIDS achieves promising detection accuracy and consistently outperforms other FL baselines. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

A Study of Nanosecond Clock Synchronization Methods for Real-Time Transient Simulation

A Study of Nanosecond Clock Synchronization Methods for Real...

引用

International Conference on Communications, Information system and Computer Engineering (CISCE)

作者： Qi Guo Yuanhong Lu Jingyue Zhang Jie Zhang Haiping Guo Binjiang Hu State Key Laboratory of HVDC Electric Power Research Institute China Southern Power Grid Guangdong Provincial Key Laboratory of Intelligent Operation and Control for New Energy Power System CSG Key Laboratory for Power System Simulation Electric Power Research Institute China Southern Power Grid Guangdong China

ISBN: (数字)9798350353174

ISBN: (纸本)9798350353181

Conventional nanosecond clock synchronization protocols are generally target-type or content-type, the synchronization rate is low, which leads to the increasing of the mean value difference of synchronization, so we propose to study the design of nanosecond clock synchronization method for real-time transient simulation. Combined with the actual clock synchronization requirements, we first calculate the link congestion coefficient, adopt a multilevel approach to strengthen the synchronization rate, set up a multilevel clock synchronization protocol, based on which we determine the clock source quality coefficients and construct a nanosecond clock synchronization model for real-time transient simulation, and use redundancy processing to achieve clock synchronization. The test results show that compared with the high-efficiency phase-color clock synchronization method and the cross-clock synchronization method, the mean synchronization difference of the designed transient simulation nanosecond clock synchronization method is controlled to be less than 0.5, which indicates that the designed clock synchronization method is more efficient, stable, and targeted, and the synchronization effect is significantly improved.

关键词： Protocols Redundancy Real-time systems Stability analysis Synchronization Transient analysis Thermal stability

来源：评论

学校读者我要写书评

暂无评论

Probabilistic Statistical Model of Station Load Based on Improved Cluster Analysis and Kernel Density Estimation

Probabilistic Statistical Model of Station Load Based on Imp...

引用

power Science and Technology (ICPST), IEEE International Conference on

作者： Jing Wang Qinqin Ma Fei Xu Xi Chen Huaizhao Ji Information and Communication Company State Grid Shaanxi Electric Power Company Xi'an China Department of Electrical Engineering State Key Laboratory of Power System Operation and Control Tsinghua University Beijing China

ISBN: (数字)9798350349030

ISBN: (纸本)9798350349047

In order to more accurately describe the load changes in the power system and establish a suitable load model, a probabilistic statistical model of desk load based on improved cluster analysis and nonparametric kernel density estimation is proposed. Firstly, the shortcomings of ISODATA clustering algorithm are analyzed, based on which this algorithm is improved by optimizing the selection of initial clustering centers to enhance the effect of clustering and accelerate the convergence speed of the algorithm, and the improved algorithm is used to cluster the power users and analyze the characteristics of electricity consumption of different users. Then, the probability distributions of different loads in each quarter are calculated by using non-parametric kernel density estimation method, and their probability density curves are extracted. Combined with the actual analysis of the load data of a number of users in a station area, compared with the traditional clustering algorithm in terms of clustering effect, the results verified the superiority of the algorithm proposed in this paper and the application value of the proposed model.

关键词： Analytical models Electricity Clustering algorithms Estimation Predictive models Probabilistic logic Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Two-level VSC real-time simulation modeling method based on controlled source compensation 2

Two-level VSC real-time simulation modeling method based on ...

引用

2nd International Conference on Energy, power, and Electrical Technology, ICEPET 2023

作者： Hu, Binjiang Xi, Xinze Zhu, Yihua Xing, Chao Li, Shuyong Ma, Zun Huang, Libin State Key Laboratory of HVDC Electric Power Research Institute CSG 11 of Kexiang Road Huangpu District Guangzhou510663 China Guangdong Provincial Key Laboratory of Intelligent Operation and Control for New Energy Power System 11 of Kexiang Road Huangpu District Guangzhou510663 China CSG Key Laboratory of Power System Simulation 11 of Kexiang Road Huangpu District Guangzhou510663 China Electric Power Research Institute of Yunnan Power Grid Co. Ltd. Kunming650217 China

ISBN: (纸本)9781510668270

The accurate modeling of two-level VSC is of great significance for the real-time simulation of new power systems, and the modeling of its core component switch group has attracted more and more attention. Since traditional binary resistance models require time to "backtrack" to accurately locate the switching moment, interpolation is difficult to use for real-time simulation. In this paper, a two-level VSC real-time simulation modeling method based on controlled source compensation is proposed. This method combines the controlled source model with the binary resistance model, uses the binary resistance model to ensure the simulation accuracy when the switching state is constant, and introduces the controlled source model to compensate for the error caused by the delay of the trigger signal when the switching state is switched. According to the two-level VSC real-time simulation model realized by this method, while reducing the non-characteristic subharmonics, the admittance matrix can be pre-stored, which effectively reduces the model computing resource occupation, and is suitable for a variety of complex power electronic system modeling methods. © 2023 SPIE.

关键词： Electric switches

来源：评论

学校读者我要写书评

暂无评论

On Fast-Converged Deep Reinforcement Learning for Optimal Dispatch of Large-Scale power systems Under Transient Security Constraints

SSRN

引用

SSRN 2024年

作者： Xiao, Tannan Chen, Ying Diao, Han Huang, Shaowei Shen, Chen State Key Laboratory of Power System Operation and Control Tsinghua University Beijing10084 China Department of Electrical Engineering Tsinghua University Beijing10084 China

power system optimal dispatch with transient security constraints is commonly represented as Transient Security-Constrained Optimal power Flow (TSC-OPF). Deep Reinforcement Learning (DRL)-based TSC-OPF trains efficient decision-making agents that are adaptable to various scenarios and provide solution results quickly. However, due to the high dimensionality of the state space and action spaces, as well as the non-smoothness of dynamic constraints, existing DRL-based TSC-OPF solution methods face a significant challenge of the sparse reward problem, which greatly limits the practical applications of these methods in large-scale power grids. To address this issue, a fast-converged DRL method for TSC-OPF is proposed in this paper. On the one hand, the Markov Decision Process (MDP) modeling of TSC-OPF is improved by reducing the observation space and smoothing the reward design, thus facilitating agent training. On the other hand, an improved Deep Deterministic Policy Gradient algorithm with Curriculum learning, Parallel exploration, and Ensemble decision-making (DDPG-CPEn) is introduced to drastically enhance the efficiency of agent training and the accuracy of decision-making. The effectiveness of the proposed method is demonstrated through experiments on the IEEE 39-bus system and a practical 710-bus regional power grid. In both systems, the training process shows stable and rapid convergence. Furthermore, the efficiency and accuracy of the well-trained agents are confirmed by testing them in new scenarios and comparing their dispatch results with those obtained using the particle swarm optimization algorithm. The source code of the proposed method is made public on GitHub. © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Research on a Refined Evaluation Method of New Distribution Network Carrying Capacity Considering Reliability and Economy

Research on a Refined Evaluation Method of New Distribution ...

引用

power Science and Technology (ICPST), IEEE International Conference on

作者： Wanming Zhang Minghui Bai Fei Xu Hongjia Miao Yong Zhou Chengde Power Supply Company State Grid Jibei Electric Power Co.Ltd Chengde China Department of Electrical Engineering State Key Laboratory of Power System Operation and Control Tsinghua University Beijing China

ISBN: (数字)9798350349030

ISBN: (纸本)9798350349047

With the large-scale access of distributed power supply to the distribution network, the excessively high penetration rate of photovoltaic(PV) units will seriously affect the normal operation of the distribution network. At present, it is urgent to evaluate the capacity of distributed PV that can be accessed by the distribution network. Therefore, this paper proposes a new refined evaluation method for the carrying capacity of the distribution network considering reliability and economy. Firstly, we establish a multilevel evaluation system and model of carrying capacity, use the affiliation function to process the multi-objective function and merge it into a single-objective function, and then transform the evaluation indexes into comprehensive scores by the combination assignment method, and then transform the carrying capacity model into a second-order conical planning model for solving. Finally, the IEEE33 node distribution network is used as an example for simulation and analysis. By comparing the comprehensive scores under different scenarios, the differences in the carrying capacity of the system under different operating conditions can be intuitively derived, which proves the validity and feasibility of the algorithm and evaluation index system proposed in this paper.

关键词： Photovoltaic systems Analytical models power supplies Distribution networks Transforms Probabilistic logic Planning

来源：评论

学校读者我要写书评

暂无评论

Practical Research on On-Line Monitoring and control Function Module of Relay Protection in Smart Substation 18

Practical Research on On-Line Monitoring and Control Functio...

引用

18th International Conference on AC and DC power Transmission, ACDC 2022

作者： Huang, Zhida Wu, Wencong Cai, Haiqing Huang, Libin State Key Laboratory of HVDC Electric Power Research Institute CSG Guangzhou510663 China National Energy Power Grid Technology R&D Centre Guangzhou510663 China Guangdong Provincial Key Laboratory of Intelligent Operation and Control for New Energy Power System Guangzhou510663 China CSG Key Laboratory for Power System Simulation Guangzhou510663 China

ISBN: (数字)9781839537615

ISBN: (纸本)9781839537615

At present, the power grid is carrying out the practical work of smart substation On-line monitoring and control function module of relay protection. Compared with traditional substations, the new-generation assurance system has been greatly improved in 7 functional modules, including fault archiving, special maintenance information patrol, fixed value checking, configuration checking, substation testing, intelligent alarm, and master station modeling. It can fully adapt to the functional requirements of smart substations and traditional substations. This paper analyzes the monitoring and analysis requirements of the assurance system based on the equipment configuration of the station control layer of the new generation of intelligent substations, and proposes a complete design scheme of seven functional modules from three aspects: functional requirements, implementation logic, and performance design. The practical application results in the power grid simulation laboratory show that the On-line monitoring and control function module of relay protection based on the guarantee system can be compatible with the traditional 103 substations and 61850 substations and achieve the expected goals and performance requirements. It has the value of promotion and application. © ACDC 2022. All rights reserved.

关键词： Relay protection

来源：评论

学校读者我要写书评

暂无评论

Study on Block Strategy Optimization of Passive Isolated Island operation of DXB UHVDC Project 6th

Study on Block Strategy Optimization of Passive Isolated Isl...

引用

6th PURPLE MOUNTAIN FORUM on Smart Grid Protection and control, PMF2021

作者： Huang, Run Zhang, Lifei Wu, Chen Li, Chengxiang Yang, Lei Wu, Mingkang Yunnan Power Grid Co. Ltd Kunming650011 China State Key Laboratory of HVDC China Southern Power Grid Electric Power Research Institute Guangzhou China Guangdong Provincial Key Laboratory of Intelligent Operation and Control for New Energy Power System Guangzhou China CSG Key Laboratory for Power System Simulation China Southern Power Grid Electric Power Research Institute Guangzhou China

ISBN: (纸本)9789811671555

Due to the lack of generators at sending end in the early operation stage of the DXB UHVDC project, if it passively entered into island operation mode, the system will encounter harmonic instability and will cause a great risk to the steady operation. In previous projects, the common solution is to disconnect AC filters and block bipolar DC with a certain time delay when receiving island operation signal. However HVDC system may block valves, cut generation capacity or shed power by error when receiving false island operation signal. Therefore, the blocking strategy at low power under passive island mode has been improved. In DXB UHVDC project, the power on AC tie lines is used as criteria for island operation to prevent false action. The logic and realization of the control strategy are illustrated, then RTDS simulations are carried out and it is verified that by judging the power on AC tie lines, the system can effectively prevent from entering island mode by error. Finally, the field test proved that the proposed improved strategy will not cause rejecting of the existing "island blocking logic". The proposed strategy can be a reference to other DC projects. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Computer circuits

来源：评论

学校读者我要写书评

暂无评论

A framework of day-ahead wind supply power forecasting by risk scenario perception

引用

IEEE Transactions on Sustainable Energy 2025年

作者： Yang, Mao Huang, Yutong Wang, Zhao Wang, Bo Su, Xin Northeast Electric Power University Key Laboratory of Modern Power System Simulation and Control & Renewable Energy Technology Ministry of Education Jilin132012 China China Electric Power Research Institute State Key Laboratory of Operation and Contr Ol of Renewable Energy & Storage Systems Beijing100912 China

Wind power forecasting (WPF) systems are essential to maintain the safe and stable operation of the power system in case of large-scale grid-connected wind farms. However, the current forecasting has the problem of disunity between statistical value and application value, that is, it only pays attention to its forecasting accuracy and ignores the risks caused by it in the power system. In order to solve the above problems, this study proposes a framework of wind supply power forecasting (WSPF) for wind farm cluster, which takes into account the risk scenario perception. First of all, aiming at the predicted risk phenomenon in WPF, TimesNet combined with the fluctuation information of Numerical Weather Prediction (NWP) wind speed is used to identify the corresponding risk scenarios. Secondly, the effective consumption area and power supply risk area evaluation index, as well as the accuracy of WSPF are defined, and the optimal forecasting curve correction scheme is fitted according to the index. Thirdly, taking into account the correction scheme and identification results, a variety of predictors are used to verify the WSPF according to the above framework. Finally, the proposed method is applied to a wind farm cluster in Inner Mongolia Autonomous region of China, the average accuracy of WSPF has increased by 37%, which verifies the effectiveness and universality of this method. © 2010-2012 IEEE.

关键词： Wind forecasting

来源：评论

学校读者我要写书评

暂无评论

Mechanism and Influencing Factor Analysis of High Frequency Oscillation in PMSG-Based Wind Farm With Grid-Connected system 6

Mechanism and Influencing Factor Analysis of High Frequency ...

引用

6th IEEE International Conference on Energy Internet, ICEI 2022

作者： Luo, Chao Zhu, Yihua Huang, Libin Yu, Jiawei Electric Power Research Institute China Southern Power Grid State Key Laboratory of Hvdc Guangzhou China National Energy Power Grid Technology R&d Centre Guangzhou China Guangdong Provincial Key Laboratory of Intelligent Operation and Control for New Energy Power System Guangzhou China

ISBN: (纸本)9781665493277

Under the background of vigorously developing wind power, permanent magnet synchronous generator (PMSG)-based wind turbines have been widely used in offshore wind farms. However, the high frequency oscillations (HFOs) of PMSG-based wind farms with grid-connected system have occurred frequently in recent years, which have a bad impact on the safe and stable operation of the power system. And current researches only preliminarily reveal the mechanism, which are lacking in discussion on the key factors involved in HFOs. This paper establishes the high frequency impedance model of PMSG-based wind farm with grid-connected system. To identify the key factors involved in HFO, the impedance sensitivity method is used to obtain the quantitative relationship of the influence of each parameter on HFO. It can be concluded that the control delay, LCL filter parameters, collector lines parameters have the greatest influence on the HFO of the wind farm, but the characteristic of negative resistance caused by control delay is the root cause of HFO. Finally, this paper establishes the model of PMSG-based wind farm with grid-connected system on the PSCAD/EMTDC and verifies the correctness of the theoretical analysis. The conclusions of this paper can provide a reference basis for the mitigation strategies of HFOs. © 2022 IEEE.

关键词： Permanent magnets

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：