检索结果-内蒙古大学图书馆

17th International Symposium on Solid Oxide Fuel Cells, SOFC 2021

作者： Lyu, Zewei Han, Minfang Department of Energy and Power Engineering State Key Laboratory of Control and Simulation of Power System and Generation Equipments Tsinghua University Beijing100084 China

ISBN: (纸本)9781607685395

Performance evolution of typical Ni-YSZ anode-supported SOFCs during the initial-stage operation ( 20 h), regardless of the operating current. In the activation stage, the cell performance maintains stable or slightly increases due to the enhanced anode gas-phase diffusion. While in the subsequent aging stage, the cell performance decreases significantly and gradually approaches a plateau in about 100 hours, mainly due to the weakened anode charge transfer reaction and ionic transport processes. Therefore, it is suggested that more efforts should be focused on improving the stability of anode microstructure, especially the stability of anode functional layer. © 2021 Electrochemical Society Inc.. All rights reserved.

关键词： Chemical activation

来源：评论

学校读者我要写书评

暂无评论

Demand Response Strategy for HVAC Based on Reinforcement Learning and Imitation Learning

Demand Response Strategy for HVAC Based on Reinforcement Lea...

引用

2022 Tsinghua-IET Electrical Engineering Academic Forum, TDF 2022

作者： He, Yiliu Zhong, Haiwang Zhang, Guanglun Ruan, Guangchun Department of Electrical Engineering Tsinghua University Beijing China State Key Laboratory of Control and Simulation of Power Systems and Generation Equipment Beijing China

ISBN: (数字)9781839537998

ISBN: (纸本)9781839537998

Heating, ventilation and air conditioning (HVAC) loads have great potential for demand response due to the buildings' thermal inertia. Modelling the complex thermal dynamics of realistic buildings is essential for the building energy optimization. In this paper, Deep Q-Network (DQN), a reinforcement learning (RL) algorithm, is used to decide the indoor temperature setpoint in response to the real-time price. The agent can adjust the HVAC load to reduce the electricity cost while considering the occupants' comfort requirement. To significantly accelerate the training process, imitation learning is adopted to pre-train the RL agent using historical data. The results of the case study show that the agent's performance improves steadily and exceeds the benchmark after a short period of training. © 2022 IET Conference Proceedings. 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

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

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

Short-Term Wind power Forecasting Based on Two-Stage Feature Selection 6

Short-Term Wind Power Forecasting Based on Two-Stage Feature...

引用

6th International Conference on Energy, Electrical and power Engineering, CEEPE 2023

作者： Zheng, Jie Niu, Zhewen Han, Xiaoqing Wu, Yuxiang Cui, Xiaorui Taiyuan University of Technology Shanxi Key Laboratory of Power System Operation and Control Taiyuan China Institute of Electricity Science Shanxi Province State Grid Electricity Company Taiyuan China

ISBN: (纸本)9798350348279

The forecasting of short-term wind power is influenced by complex and changeable factors, such as climate environment, and meteorological characteristics. A single input of model features is difficult to meet the accurate forecasting requirements. However, to consider all the influencing factors, the input feature redundancy will increase the computational complexity of the forecasting model and have a negative impact on the forecasting results. Therefore, accurate and efficient feature selection is the key to improving the accuracy of data-driven wind power forecasting. In this paper, a short-term wind power forecasting method based on two-stage feature selection is proposed. Firstly, the meteorological factors and environmental factors affecting wind power forecasting are screened by using the Pearson Correlation Coefficient method. Secondly, a feature selection method of attention mechanism considering temporal correlation is proposed, which dynamically mined the potential correlation between wind power output and input characteristics from the perspective of time, and independently extracted the information of historical key moments. Finally, a bidirectional gated cyclic neural network (BIGRU) is selected as the forecasting model, taking into account the influence of historical data and future information. The results show that the proposed PCC-TA-BIGRU short-term wind power forecasting model can accurately select the factors affecting wind power forecasting and effectively improve the accuracy of short-term wind power forecasting. © 2023 IEEE.

关键词： Recurrent neural networks

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

A Classification and Recognition Model of Distributed Resources Based on Feature Extraction

A Classification and Recognition Model of Distributed Resour...

引用

2023 IEEE International Conference on Energy Technologies for Future Grids, ETFG 2023

作者： Zhu, Yu Yang, Le Yang, Xizai Lu, Jiaxin Wang, Yuqing Wang, Fei State Grid Shaanxi Electric Power Co. Ltd. Information and Communication Company Information and Communication Technology R & D Center Xi'an710048 China State Key Laboratory of Power System Operation and Control Tsinghua University Beijing100084 China

ISBN: (纸本)9781665471640

The extensive integration of distributed resources such as distributed photovoltaic system and electric vehicles enhances the uncertainty of the load side greatly. Corresponding demand response strategies can be developed for different distributed resource types and characteristics of households' load, which is of great significance for new energy consumption and stable operation of the power system. However, only the net load power of households can be obtained through smart meters instead of the distributed resource types of households. Based on this, a distributed resource classification and identification model based on feature extraction is proposed in this paper, and effectively solves the problems of low accuracy and strong data dependence of existing recognition methods. Firstly, a generalized weather class generation algorithm based on clustering and voting is established, which is used to determine the weather class of each day to provide a basis for the following feature extraction. Then, based on the typical net load profiles under different generalized weather classes, a two-stage feature extraction and a classification identification model based on integrated learning algorithms are established to identify whether a user contains DPVS and EV, respectively. Finally, based on the category labels of each user for each stage, the final classification of the category to which the user belongs is carried out. simulation experiments show that the recognition model built using the typical features extracted in the paper has good recognition accuracy. © 2023 IEEE.

关键词： classification and recognition Distributed photovoltaics system electric vehicles ensemble learning feature extraction

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

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

Statistical downscaling of numerical weather prediction based on convolutional neural networks

引用

Global Energy Interconnection 2022年第2期5卷 217-225页

作者： Hongwei Yang Jie Yan Yongqian Liu Zongpeng Song State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources North China Electric Power UniversityBeijing 102206P.R.China School of Renewable Energy North China Electric Power UniversityBeijing 102206P.R.China Renewable Energy Center China Electric Power Research InstituteBeijing 100192P.R.China State Key Laboratory of Operation and Control of Renewable Energy&Storage Systems Beijing 100192P.R.China

Numerical Weather Prediction(NWP)is a necessary input for short-term wind power *** NWP models are all based on purely physical *** requires mainframe computers to perform large-scale numerical calculations and the technical threshold of the assimilation process is *** is a need to further improve the timeliness and accuracy of the assimilation *** order to solve the above problems,NWP method based on artificial intelligence is proposed in this *** uses a convolutional neural network algorithm and a downscaling model from the global background field to establish a given wind turbine hub height *** considered the actual data of a wind farm in north China as an example to analyze the calculation *** results show that the prediction accuracy of the proposed method is equivalent to that of the traditional purely physical *** prediction accuracy in some months is better than that of the purely physical model,and the calculation efficiency is considerably *** validity and advantages of the proposed method are verified from the results,and the traditional NWP method is replaced to a certain extent.

关键词： Convolutional Neural Network Deep learning Numerical Weather Prediction

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：