检索结果-内蒙古大学图书馆

Renewable Energy and Power Quality Journal 2024年第6期22卷 168-178页

作者： Fan, Xiaoxuan Zhang, Sai Liang, Xiao Wang, Zhihao Peng, Tao State Grid Laboratory of Grid Advanced Computing and Applications China Electric Power Research Institute Co. Ltd Beijing China State Grid Jiangsu Electric Power Co. Ltd Nanjing China

With the rapid development of large language models, their application in various industries is becoming more and more common, especially in the power sector. Electricity power standard knowledge, as an industry specification for electric power equipment, engineering construction and operation management, can guide product production and engineering practice to improve production efficiency and quality level. In order to help solve the problem of low efficiency of electric power standard knowledge supply and assist the generation of electric power standard knowledge, we proposes an electric standard knowledge auxiliary generation method based on retrieval enhancement generation, which uses the retrieval model and evaluation model to provide large language model with accurate external knowledge, and then uses the generation model to provide a more efficient and accurate solution for the generation of standard knowledge in the electric industry. The experimental results indicate that the approach introduced in this paper can effectively generate accurate electricity-related knowledge and holds significant practical value. © 2024, European Association for the Development of Renewable Energy, Environment and Power Quality (EA4EPQ). All rights reserved.

关键词： Knowledge generation Knowledge-assisted Large language model Power standards knowledge Retrieval

来源：评论

学校读者我要写书评

暂无评论

Topology Identification of Distribution Networks Using Multi-Object Binary Classification Graph Transformer

Topology Identification of Distribution Networks Using Multi...

引用

IEEE Conference on Energy Internet and Energy System Integration (EI2)

作者： Siyan Liu Danni Shi State Grid Laboratory of Grid Advanced Computing and Applications State Grid Smart Grid Research Institute Co. Ltd. Beijing China

With the continuous increase of renewable energy, the distribution network's structure tends to be more complex. The real-time topology is difficult to obtain timely and the topol-ogy categories increases exponentially, which poses challenges to further analysis and the network's computation. Traditional distribution network topology identification methods rely on high computational complexity and require a large number of fault samples. To address these problems, this paper proposed a Multi-Object(MO) binary classification graph transformer method for topology identification. Through mapping the switch status and voltage measurement and branch conductance of the distribution network, a MO classification mechanism is introduced, performing binary classification for each edge with undetermined connection status, and physically map the output of the identification model to the switches status in the distribution network. The method utilized a Graph Transformer-based convolutional neural network which used to extract the nodes and the edges features. Combing the proposed architecture with an online hard example mining mechanism and maximum spanning tree filter strategy, the model collapse caused by imbalanced data is dealt with and the accurate identification is realized. The proposed method is validated by the IEEE 33-bus distribution network system, and the results show the high accuracy for practical topology identification.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Guest Editorial: Special issue on computational methods and artificial intelligence applications in low-carbon energy systems

引用

IET Renewable Power Generation 2024年第3期18卷 303-305页

作者： Wang, Yishen Zhou, Fei Guerrero, Josep M. Baker, Kyri Chen, Yize Wang, Hao Xu, Bolun Xu, Qianwen Zhu, Hong Agwan, Utkarsha State Grid Laboratory of Grid Advanced Computing and Applications State Grid Smart Grid Research Institute Co. Ltd. Beijing China Department of Energy Technology Aalborg University Aalborg Denmark Department of Civil Environmental and Architectural Engineering University of Colorado-Boulder BoulderCO United States Guangzhou China Department of Data Science and AI Monash University ClaytonVIC Australia Department of Earth and Environmental Engineering Columbia University New YorkNY United States Electric Power and Energy Systems Division KTH Royal Institute of Technology Stockholm Sweden State Grid Jiangsu Electric Power Co. Ltd. Nanjing China Department of Electrical Engineering and Computer Sciences University of California - Berkeley BerkeleyCA United States

来源：评论

学校读者我要写书评

暂无评论

Fast Cross-Modality Knowledge Transfer via a Contextual Autoencoder Transformation

Fast Cross-Modality Knowledge Transfer via a Contextual Auto...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Min Zheng Chunpeng Wu Yue Wang Yantao Jia Weiwei Liu Long Lin Shuai Chen Fei Zhou State Grid Laboratory of Grid Advanced Computing and Applications State Grid Smart Grid Research Institute Co. Ltd. Beijing China Huawei Technologies Co. Ltd Beijing China

Cross-modality knowledge transfer aims to apply knowledge learned in the source modality to the target modality. It is more challenging than the general knowledge transfer task because of the aggravated modality shift problem due to introducing heterogeneous data. This paper proposes a novel fast cross-modality knowledge transfer method via a contextual autoencoder transformation. In particular, the encoder projects the contextual representations of the source modality into the target modality. Then to bridge the semantic shared among source and target modalities, the decoder exerts an additional constraint to reconstruct the original source modality. We show that this constraint is beneficial for mitigating the shift problem and improves the generalization from heterogeneous modalities. Remarkably, the autoencoder is linear and symmetric, facilitating scalability for large-scale datasets. Experimental results on two widely used benchmarks demonstrate that the proposed method surpasses several state-of-the-arts baselines, validating its effectiveness and efficiency.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Active Learning Model Production Method for Electric Power Inspection Image Multi-target Detection

An Active Learning Model Production Method for Electric Powe...

引用

IEEE Information Technology and Mechatronics Engineering Conference (ITOEC)

作者： Jiangqi Chen Bo Wang Xi Zhang Kunlun Gao Peng Wu State Grid Laboratory of Grid Advanced Computing and Applications Beijing China State Grid Smart Grid Research Institute Co. Ltd Beijing China

With the development of intelligent electric power inspection technology, electric power companies use UAVs, cameras, robots and other equipment for power transmission line inspections, and take a large number of inspection images. In recent years, the image multi-target detection model has been maturely applied in the intelligent inspection of electric power. The current image intelligent detection model mainly relies on a large number of image sample labels. Power companies have a small number of labeled image samples, and a large number of unlabeled. But manual data annotation is very expensive, and cost lots of time and money. Moreover, there will be certain errors in manual annotation, so it is necessary to repeat the annotation and verification to reduce the error. But this will also increase the cost. This article proposes an active learning model production method for electric power inspection image multi-target detection. We select samples for annotation according to some strategies, and select labeled samples for verification. This method can reduce the cost of sample annotation, and improve the model. productivity. Compared with the traditional random labeling strategy, our method can achieve the same accuracy with only 20% of the annotation cost. With 50% of the annotation cost, the mAP index will increase by 12%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Analysis and optimization of sparse LU factorization of power matrix based on GLU

Analysis and optimization of sparse LU factorization of powe...

引用

12th International Conference on Renewable Power Generation (RPG 2023)

作者： C. Shi L. Lin H. Yang S. Wang State Grid Laboratory of Grid Advanced Computing and Applications State Grid Smart Grid Research Institute co.Ltd Beijing People's Republic of China

ISBN: (数字)9781839539497

With the continuous improvement of power grid stability and reliability requirements, improving the efficiency and accuracy of power system simulation has become an important research topic. The sparse LU factorization is one of the key modules of the sparse direct solver, which usually plays a dominant role in the solving time of the sparse linear algebra equation of power system. In order to improve the efficiency of sparse LU factorization, we propose: 1) an adaptive mode partition strategy based on GLU, and select the mode to be used according to the characteristics of the matrix to be decomposed, which improves the computational efficiency of LU factorization; 2) a dynamic Nstream value taking method for the stream pattern, which determines the number of streams to be used based on the dimensions of the sub-matrix, 3) a pipeline model for the continuous layer with the size of 1 in GLU, which improves the parallelism of sparse LU factorization and helps to improve the computing efficiency. The results show that the proposed improvement can achieve better results, and the speed of LU factorization is increased by more than 30% on rajat12 and circuit_2.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Aggregation Strategy of Flexible Industrial Load Based on K-Means Clustering

An Aggregation Strategy of Flexible Industrial Load Based on...

引用

China International Electrical and Energy Conference (CIEEC)

作者： Shuya Lei Wensi Zhang Yishen Wang Zhiqing Sun Mohan Liu Mingjian Cui State Grid Laboratory of Grid Advanced Computing and Applications State Grid Smart Grid Research Institute Co. Ltd. Beijing China State Grid Hangzhou Power Supply Company Hangzhou China School of Electrical and Information Engineering Tianjin University Tianjin China

ISBN: (数字)9798350359558

ISBN: (纸本)9798350359565

In response to the “carbon peaking and carbon neutrality” goals, the energy structure in China has undergone a great transformation. Construction of the new power system has begun. The proportion of renewable generation has increased gradually. However, the operation and scheduling of the power system are influenced by the increasing renewable generation. This paper develops a multi-timescale flexible industrial load aggregation response method based on the K-means clustering analysis. First, the K-means method is used to cluster the daily load curves of different industries to obtain the typical electricity consumption behaviors. Second, the visual models of flexible industrial load are established based on the results of clustering analysis. Finally, the optimization model is constructed to generate the aggregation strategy in different timescales. The effectiveness of the developed method is verified via a load aggregator simulation case.

关键词： Industries Renewable energy sources Visualization Optimization models Electricity Production Power systems

来源：评论

学校读者我要写书评

暂无评论

A Fast Belief Propagation-Based Distributed Gauss– Newton Method for Power System State Estimation

A Fast Belief Propagation-Based Distributed Gauss– Newton M...

引用

IEEE International Conference on Cloud computing and Big Data Analysis (ICCCBDA)

作者： Peng Guo Danni Shi Xuan Wang Xinghua Shi State Grid Laboratory of Grid Advanced Computing and Applications State Grid Smart Grid Research Institute Co. Ltd Beijing China State Grid Zhejiang Eletric Power Co. Ltd Zhejiang China

State estimation is the foundation for a variety of online power system applications in energy management systems, and the stability of power systems is directly impacted by the speed with which current system states can be obtained through state estimation. This paper proposed a fast Gaussian-Newton state estimation method for power systems based on parallel belief propagation, which implements the Gaussian belief process via multi-core and multi-thread parallel computation to achieve efficient state estimation. Simulation findings on numerous IEEE-standard power systems show that the suggested technique outperforms the traditional algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on Capacity Configuration Optimization of Multi-Energy Complementary System Using Deep Reinforce Learning

Research on Capacity Configuration Optimization of Multi-Ene...

引用

IEEE International Conference on Power and Energy Systems (ICPES)

作者： Zhuang Tang Bo Chai Jie Li Yishen Wang Siyan Liu Xinghua Shi State Grid Laboratory of Grid Advanced Computing and Applications State Grid Smart Grid Research Institute Co. Ltd Beijing China State Grid Zhejiang Eletric Power Co. Ltd Hangzhou China

The output power of wind, solar, and hydro energy in a multi-energy complementary system (MECS) with the heating system exhibits certain fluctuations. Gas power generation and battery can reduce these problems. However, relying solely on the experience of designers to determine the capacity configuration is challenging, as it may compromise the system's safety and result in wasteful investments. To address these issues, the capacity configuration optimization problem of the MECS can be formulated as a multi-objective optimization problem. This paper proposes a MECS capacity optimization method based on deep reinforcement learning (DRL), specifically the deep deterministic strategy gradient (DDPG) algorithm. By transforming the multi-objective optimization problem into a Markov decision process, this approach effectively resolves it. The primary objective of the optimization is to ensure the stability of the system's power supply, while the secondary objective is to minimize the economic cost of the system. To evaluate the proposed method, simulations were conducted based on the characteristic curves of energy generation. The results demonstrate that utilizing the DDPG algorithm enables the rapid determination of the optimal capacity configuration for wind, solar, and battery. This approach improves the stability and economic efficiency of the multi-energy complementary system, while utilizing excess electrical energy for heating through heat pumps, greatly improving energy utilization efficiency.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Graph computing applications In Unit Commitment Historical Data Management

Graph Computing Applications In Unit Commitment Historical D...

引用

Sustainable Power and Energy Conference (iSPEC)

作者： Yishen Wang Fei Zhou Hong Zhu Siyan Liu Zhuang Tang He Yang State Grid Laboratory of Grid Advanced Computing and Applications Beijing China State Grid Smart Grid Research Institute Co. Ltd Beijing China State Grid Jiangsu Electric Power Co. Ltd Nanjing China

The development of new types of power systems poses several key challenges for super-large-scale online analysis and optimization. These challenges include data merging, computation performance, and operation optimization. The uncertainty arising from renewable energy sources and load fluctuations has resulted in highly volatile power flow patterns compared to previous systems. As a result, the operating states of the system are more vulnerable to potential operational risks during critical periods. From the perspective of unit commitment, optimizing system resources involves increasingly complex constraints and variables. Graph computing has shown exceptional performance in online power system analysis, particularly in topology-related analysis. This paper explores the application of graph computing techniques to enhance security-constrained unit commitment historical data management. It offers new insights into the utilization of graph computing to improve unit commitment.

关键词：

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：