检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Li, Yang Wang, Ruinong Li, Yuanzheng Zhang, Meng Long, Chao The Key Laboratory of Modern Power System Simulation Control and Renewable Energy Technology Ministry of Education Northeast Electric Power University Jilin132012 China The State Grid Jilin Electric Power Co. Ltd Jilin Power Supply Company Chuanying District Jilin132001 China The School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China The School of National Key Laboratory of Science and Technology Vessel Integrated Power System Naval University of Engineering Wuhan430033 China The School of Water Energy and Environment Cranfield University United Kingdom

In a modern power system with an increasing proportion of renewable energy, wind power prediction is crucial to the arrangement of power grid dispatching plans due to the volatility of wind power. However, traditional centralized forecasting methods raise concerns regarding data privacy-preserving and data islands problem. To handle the data privacy and openness, we propose a forecasting scheme that combines federated learning and deep reinforcement learning (DRL) for ultra-short-term wind power forecasting, called federated deep reinforcement learning (FedDRL). Firstly, this paper uses the deep deterministic policy gradient (DDPG) algorithm as the basic forecasting model to improve prediction accuracy. Secondly, we integrate the DDPG forecasting model into the framework of federated learning. The designed FedDRL can obtain an accurate prediction model in a decentralized way by sharing model parameters instead of sharing private data which can avoid sensitive privacy issues. The simulation results show that the proposed FedDRL outperforms the traditional prediction methods in terms of forecasting accuracy. More importantly, while ensuring the forecasting performance, FedDRL can effectively protect the data privacy and relieve the communication pressure compared with the traditional centralized forecasting method. In addition, a simulation with different federated learning parameters is conducted to confirm the robustness of the proposed scheme. Copyright © 2022, The Authors. All rights reserved.

关键词： Electric load dispatching

来源：评论

学校读者我要写书评

暂无评论

Research on Active Support control Strategy and its Performance of renewable energy power Station with Multiple energy Sources

Research on Active Support Control Strategy and its Performa...

引用

IEEE Conference on energy Internet and energy system Integration (EI2)

作者： Guanming Zeng Liang Tu Yihua Zhu Yun Hu Chao Luo Shengnan Li State Key Laboratory of HVDC Electric Power Research Institute China Southern Power Grid National Energy Power Grid Technology R&D Centre Guangzhou China 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 Guangzhou China State Key Laboratory of HVDC Electric Power Research Institute China Southern Power Grid CSG Key Laboratory for Power System Simulation Electric Power Research Institute China Southern Power Grid Guangzhou China National Energy Power Grid Technology R&D Centre Guangdong Provincial Key Laboratory of Intelligent Operation and Control for New Energy Power System Guangzhou China Yunnan Power Grid Co. Ltd. Electric Power Research Institute Kunming Yunnan

The increasing integration of renewable energy reduces the inertia and frequency support capacity of the power system. The issue of frequency stability has become one of the core issues in the security and stability of power system and the efficient consumption of renewable energy nowadays. To improve the performance of renewable energy power station (REPS), based on the analysis of typical active support control logic and relative performance requirements of REPS with single energy source (SES), an active support control strategy and coordinated control logic of active power of REPS with multiple energy sources (MES) are proposed in this paper. The performance of proposed strategy is theoretically analyzed from the aspect of dominant energy source and the effect of the capacity of energy storage. The effectiveness of the proposed strategy and the accuracy of the theoretical analysis of performance are verified by realtime simulation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A disturbance localization method for power system based on group sparse representation of compressed sensing

A disturbance localization method for power system based on ...

引用

Electrical Engineering, Big Data and Algorithms (EEBDA), IEEE International Conference on

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. Changchun China Economic and Technical Research Institute of State Grid Jilin Electric Power Co. Ltd. Changchun China Key Laboratory of Modern Power System Simulation and Control & Renewable Energy Technology Ministry of Education (Northeast Electric Power University) Jilin China

This paper proposes a new disturbance localization method for power system based on group sparse representation of compressed sensing. Based on the analysis of disturbance characteristics of power system, the sparse dictionary of compressed sensing group is constructed by the admittance matrix, impedance matrix, and power variation matrix. In addition, the traditional generalized orthogonal matching pursuit reconstruction algorithm is improved to obtain the group sparse coefficients corresponding to the above dictionaries for compressive sensing sparse reconstruction, and the corresponding weights of each class in the group sparse dictionary are determined based on the entropy weight method to realize the accurate location of power system disturbances. In this paper, the IEEE 39 node power systems are built on the PSCAD/EMTDC simulation platform for experimental verification, and three common disturbances of cutting generator capacity, cutting load capacity and single-phase grounding short circuit are analyzed respectively. The simulation results show that the proposed method can achieve the accurate location of common disturbances in power systems with limited measurement device configurations, and has the advantages of less computation and strong robustness to noise.

关键词： Location awareness Dictionaries simulation Reconstruction algorithms Entropy Robustness power systems

来源：评论

学校读者我要写书评

暂无评论

Application of deep reinforcement learning in power system scheduling strategy simulation

Application of deep reinforcement learning in power system s...

引用

energy, power and Electrical Engineering (EPEE), International Conference on

作者： Binjiang Hu Libin Huang Yufeng Hu Jie Zhang Haiping Guo Yuanhong Lu Zeqi Hong Jingyue Zhang Hui Luo Guangdong Provincial Key Laboratory of Intelligent Operation and Control for New Energy Power System Guangzhou China State Key Laboratory of HVDC Electric Power Research Institute China Southern Power Grid Guangzhou China National Energy Power Grid Technology R&D Centre Guangzhou China CSG Key Laboratory for Power System Simulation Electric Power Research Institute China Southern Power Grid Guangzhou China

ISBN: (数字)9798331518066

ISBN: (纸本)9798331518073

With the increasing scale and complexity of power system, the current scheduling strategy methods often have the problems of limited adaptability and unsatisfactory results. Therefore, a power system scheduling method using DQN (Deep Q Network) is introduced in this study. This method uses neural network model to learn and optimize scheduling strategy, and has strong adaptability and enhanced global optimization ability. Comparative evaluations with genetic algorithms and particle swarm algorithms on IEEE-118 and SG-126 datasets show that the proposed method has significant advantages in terms of cumulative reward and stable runtime.

关键词： Electrical engineering Runtime Neural networks power system stability Deep reinforcement learning Stability analysis Real-time systems Particle swarm optimization Optimization Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Technical Research on simulation and Predictive Analysis of Wind Farms in power systems

Technical Research on Simulation and Predictive Analysis of ...

引用

energy, power and Electrical Engineering (EPEE), International Conference on

作者： Tianyu Guo Libin Huang Yanjun Zhao Haiping Guo Yuanhong Lu Jie Zhang Hui Luo Binjiang Hu National Energy Power Grid Technology R&D Centre Guangzhou China State Key Laboratory of HVDC Electric Power Research Institute China Southern Power Grid Guangzhou China CSG Key Laboratory for Power System Simulation Electric Power Research Institute China Southern Power Grid Guangzhou China Guangdong Provincial Key Laboratory of Intelligent Operation and Control for New Energy Power System Guangzhou China

ISBN: (数字)9798331518066

ISBN: (纸本)9798331518073

To address the issue of insufficient accuracy in wind power output forecasting, this paper proposes a Support Vector Machine (VSM) model based on similar day matching and kernel entropy component analysis for wind power prediction. The model effectively extracts similar day features through the similar day approach and optimizes feature representation by combining it with kernel entropy component analysis (KECA), ultimately employing the SVM model for wind farm power forecasting. simulation results demonstrate that using this model for optimizing wind power generation predictions enhances the accuracy of wind power forecasts, surpassing the precision of single-method predictions. The Similar Day-KECA-SVM method leverages historical data from similar days and features extracted through KECA, with SVM performing the final prediction. This approach adeptly handles complex patterns and nonlinear relationships in wind power forecasting, thereby achieving superior predictive performance.

关键词： Support vector machines Analytical models Accuracy Wind speed Wind power generation Predictive models Feature extraction Entropy Forecasting Kernel

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of power system simulation Platform Based on Cloud Computing

Design and Implementation of Power System Simulation Platfor...

引用

energy, power and Electrical Engineering (EPEE), International Conference on

作者： Yuanhong Lu Haiping Guo Yanjun Zhao Libin Huang Binjiang Hu Hui Luo Jingyue Zhang National Energy Power Grid Technology R&D Centre Guangzhou China State Key Laboratory of HVDC Electric Power Research Institute China Southern Power Grid 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 Electric Power Research Institute China Southern Power Grid Guangzhou China

ISBN: (数字)9798331518066

ISBN: (纸本)9798331518073

power system simulation involves simulating the operating states and dynamic processes of power systems using mathematical models and computer technology to analyze and predict system behavior. Traditional simulation methods struggle to meet the needs of large-scale, complex power grids due to significant demands for computational resources. Cloud computing, with its high scalability, resource pooling, and on-demand services, is ideally suited for the extensive simulation calculations required by modern power systems. Despite its advantages, the application of cloud computing in power system simulation poses challenges related to data security and privacy, particularly in collaborative simulations involving multiple power entities. This paper presents the design and implementation of a cloud computing-based power system simulation platform. The proposed platform leverages the distributed computing capabilities of cloud computing, integrates federated learning to ensure data privacy, and utilizes advanced power system simulation technologies. This approach significantly enhances simulation efficiency and accuracy while providing data security and privacy protection. The platform offers reliable decision support for power system planning, operation, and control.

关键词： Cloud computing Data privacy Accuracy Federated learning Data security power system simulation power system dynamics power system stability power grids Testing

来源：评论

学校读者我要写书评

暂无评论

Space Charge Characteristics of Oil-paper under AC/DC Composite Voltage

Space Charge Characteristics of Oil-paper under AC/DC Compos...

引用

Conference on Electrical Insulation and Dielectric Phenomena, (CEIDP)

作者： Yuanxiang Zhou Xin Huang Ling Zhang Yunxiao Zhang Zhongliu Zhou Chenyuan Teng Lei Xue Meng Huang The Wind Solar Storage Division of State Key Laboratory of Power System and Generation Equipment School of Electrical Engineering Xinjiang University Urumqi China China State Key Laboratory of Control and Simulation of Power Systems and Generation Equipment Tsinghua University Haidian Beijing China State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources North China Electric Power Universiy Beijing China

ISBN: (纸本)9781728195728;9781728195735

Oil-paper insulation bears AC/DC composite voltage in converter transformers. However, the AC/DC space charge behavior is still not clear, which will result in electric field distortion, material aging and even insulation failure. In this work, the space charge distribution of oil-paper under the AC/DC composite voltage with the AC/DC ratio of 1:1, 1:3, 1:5, and 1:7, is studied by pulse electroacoustic (PEA) method, respectively. It was found that as DC component increases, the accumulated charge near the electrode decreases, while the interior charge increases. It suggests that DC stress mainly influences the amount and the depth of space charge accumulation. AC component has a relatively significant impact on the injection and extraction behavior of space charge near the electrode. Furthermore, AC/DC composite voltage enhances the migration of space charge compared with that under DC voltage. This research contributes to the further understanding of the space charge characteristics of oil-paper under AC/DC composite voltage, which will benefit the safe and stable operation of converter transformers.

关键词： Electrodes Conferences Space charge Oil insulation Aging Distortion Dielectrics

来源：评论

学校读者我要写书评

暂无评论

Research on the Application of Big Data in Transient Stability simulation of power systems

Research on the Application of Big Data in Transient Stabili...

引用

energy, power and Electrical Engineering (EPEE), International Conference on

作者： Jie Zhang Haiping Guo Yanjun Zhao Libin Huang Binjiang Hu Hui Luo Jingyue Zhang State Key Laboratory of HVDC Electric Power Research Institute China Southern Power Grid 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 CSG Key Laboratory for Power System Simulation Electric Power Research Institute China Southern Power Grid Guangzhou China

ISBN: (数字)9798331518066

ISBN: (纸本)9798331518073

With the rapid expansion of smart grids, there is a growing complexity in power system dynamics, which increases the availability of real-time operational data and underscores the need for advanced transient stability simulations. Traditional transient stability analysis methods are constrained by their computational demands and may compromise accuracy. Furthermore, deep learning-based methods often focus on the application of a single algorithm, lacking a systematic consideration of the entire simulation process. To address these challenges, this study proposes a novel approach that leverages big data to enhance transient stability simulations. By integrating deep learning and ensemble learning techniques, the model significantly improves the accuracy and efficiency of predicting transient instabilities. The methodology utilizes a multi-source data acquisition and fusion scheme to ensure data comprehensiveness and a distributed storage architecture to handle large-scale datasets effectively. Advanced visualization technologies are also employed to enhance the interpretability of the simulation results. This comprehensive framework aims to support the safe and stable operation of power systems amid increasing complexity and data availability.

关键词： Accuracy Computational modeling power system stability Big Data Predictive models Stability analysis Data models Real-time systems Transient analysis Thermal stability

来源：评论

学校读者我要写书评

暂无评论

Neural Network technology Applied in Fault Detection and simulation of power systems

Neural Network Technology Applied in Fault Detection and Sim...

引用

2024 8th International Conference on Electrical, Mechanical and Computer Engineering (ICEMCE)

作者： Zeqi Hong Libin Huang Yufeng Hu Haiping Guo Yuanhong Lu Binjiang Hu Jingyue Zhang Hui Luo State Key Laboratory of HVDC Electric Power Research Institute China Southern Power Grid 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 CSG Key Laboratory for Power System Simulation Electric Power Research Institute China Southern Power Grid Guangzhou China

ISBN: (数字)9798331506230

ISBN: (纸本)9798331506247

With the escalating demand for power inspection and equipment maintenance, developing effective algorithms for power system fault detection is crucial for ensuring the safety and stability of power systems. This paper leveragesthe Trellis network, enhanced with an attention module, to significantly improve the Trellis network’s capability in recognizing power fault images, thus better addressing fault identification tasks within power systems. Through testing on a self-constructed dataset and comparative experiments with models such as DCNN, RCNN, and DenseNet, the proposed attention mechanismenhanced Trellis network algorithm has demonstrated its effectiveness and superiority in fault detection.

关键词： Fault diagnosis Accuracy Attention mechanisms Fault detection Neural networks power system stability Predictive models Feature extraction Electrical fault detection Maintenance

来源：评论

学校读者我要写书评

暂无评论

Distributed power system simulation and Monitoring Supported by Cloud technology : A grid optimization scheduling method based on MADRL

Distributed Power System Simulation and Monitoring Supported...

引用

energy, power and Electrical Engineering (EPEE), International Conference on

作者： Hui Luo Jie Zhang Yufeng Hu Jingyue Zhang Haiping Guo Libin Huang China Southern Power Grid CSG Key Laboratory for Power System Simulation Electric Power Research Institute Guangzhou China China Southern Power Grid State Key Laboratory of HVDC Electric Power Research Institute Guangzhou China Guangdong Provincial Key Laboratory of Intelligent Operation and Control for New Energy Power System Guangzhou China National Energy Power Grid Technology R&D Centre Guangzhou China

ISBN: (数字)9798331518066

ISBN: (纸本)9798331518073

This study explores the optimization of Distributed Generation systems (DGS) within a Multi-Agent Deep Reinforcement Learning (MADRL) framework. The focus is on transforming the overall optimization goal of the system into a global reward function and designing local rewards adapted to heterogeneous agents. Using the IEEE 33 node system as a case study, the impact of power aggregation and load management from photovoltaic systems, energy storage systems, electric vehicle charging facilities, and HVAC systems is analyzed. The results demonstrate that the proposed edge-cloud collaborative framework optimizes resource allocation and scheduling. The cloud platform is capable of integrating data from diverse sources and managing it in a unified manner, thereby coordinating the operations of multiple heterogeneous agents. The scalability and flexibility of cloud technology allow for the dynamic adjustment of computational resources according to demand, ensuring global optimization and the judicious allocation of resources.

关键词： Photovoltaic systems HVAC Processor scheduling system performance Collaboration Deep reinforcement learning Smart grids Resource management Vehicle dynamics energy storage

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：