检索结果-内蒙古大学图书馆

energy Engineering and power Systems (EEPS), International Conference on

作者： Tao Meng Chenggang Li Dexin Li Jiajun Zhang Electric Power Research Institute State Grid Jilin Electric Power Co. Ltd Key Laboratory of Modern Power System Simulation and Control & Renewable Energy Technology Ministry of Education School of Electrical Engineering Northeast Electric Power University Changchun China Electric Power Research Institute State Grid Jilin Electric Power Co. Ltd Changchun China

With the target of "peak carbon dioxide emission" and "carbon neutrality", the installed capacity of renewable energy power generation is increasing rapidly. To improve the absorption capacity of renewable energy, the frequency regulation ability of flexible load is considered. Diffusion strategy is an optimal strategy for the distributed multi-agent system. Considering the flexible load, the grid-connected photovoltaic power applies the diffusion strategy to optimize the scheduling strategy. The effectiveness of the proposed optimal algorithm is verified by a simulation example. The results show that the proposed algorithm can realize frequency regulation, and improve the installed capacity of photovoltaic power generation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Ultra-Short-Term Multi-Step Prediction of Wind power Based on modernTCN and Multi-Task Learning

Ultra-Short-Term Multi-Step Prediction of Wind Power Based o...

引用

IEEE International Conference on power and power and renewable energy (ICPRE)

作者： Mao Yang Xiangyu Li Zifen Han Yong Sun Xiqiang Chang Key Laboratory of Modern Power System Simulation and Control & Renewable Energy Technology Ministry of Education (Northeast Electric Power University) Jilin China State Grid Gansu Electric Power Company Gansu China State Grid Jilinsheng Economic And Technological Research Institute Jilin China State Grid Xinjiang Electric Power CO. LTD Xinjiang China

ISBN: (数字)9798350377460

ISBN: (纸本)9798350377477

The intermittent and fluctuating nature of wind energy makes it difficult to accurately predict wind power, leading to low penetration in the wind power grid. To address this problem, this paper designs ultra-short-term multi-step prediction of wind power based on modernTCN and multi-task learning to improve the prediction accuracy. Firstly, modernTCN's ability to have a large receptive field and capture cross-variate timing dependencies is exploited to obtain multivariate timing feature information and establish a multi-step mapping of input features to power. Then it is inputted into the MMoE multi-task learning method, and the prediction results are corrected to obtain the ultra-short-term prediction of wind power using multiple expert networks and gating units. The experimental results show that the method proposed in this paper can effectively improve the ultra-short-term prediction accuracy of wind power, and can provide a favourable reference for the scheduling centre to adjust the power generation plan in real-time response to the power demand.

关键词： renewable energy sources Accuracy Wind energy Wind power generation Predictive models Multitasking Feature extraction Real-time systems Timing Wind forecasting

来源：评论

学校读者我要写书评

暂无评论

Wind power Forecasting Considering Data Privacy Protection: A Federated Deep Reinforcement Learning Approach

arXiv

引用

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

Fuzzy control Based Virtual Synchronous Generator for Self-Adaptative control in Hybrid Microgrid

SSRN

引用

SSRN 2022年

作者： Lyu, Ling Wang, Xuesong Zhang, Liang Zhang, Zhe Koh, Leong Hai Key Laboratory of Modern Power System Simulation and Control & Renewable Energy Technology Ministry of Education Northeast Electric Power University Jilin132012 China State Grid Hebei Electric Power Company Cangzhou Power Supply Company Cangzhou061000 China School of Electrical and Electronic Engineering Nanyang Technological University 639798 Singapore National Metrology Centre 138635 Singapore

When there is a large penetration of renewable energy sources, maintaining the stability of a low-inertia microgrid becomes a major difficulty. However, in such systems, the virtual inertia values are often fixed constants, and the choice of their values will significantly affect the frequency and voltage stability of the microgrid. Higher frequency and voltage oscillations may occur due to improper selection of fixed virtual inertia values. Therefore, virtual inertia-based control has attracted a lot of attention. In this paper, an adaptive virtual inertia control system using a fuzzy system is proposed through the setting of fuzzy logic rules and affiliation functions to provide adaptive inertia control for the system to ensure the stability of frequency and voltage. In the proposed adaptive control strategy, the virtual inertia values are automatically adjusted according to the signal deviation and rate of change of the actual system, avoiding the selection of inappropriate inertia values and providing fast inertial response. Simulation and experimental results show that the proposed adaptive control algorithm, by combining the advantages of large inertia and small inertia, enables effective improvement of the dynamic response of the system voltage and frequency in both rectifier and inverter modes. The effectiveness of the proposed control strategy is verified. © 2022, The Authors. All rights reserved.

关键词： Fuzzy control

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

Conditional Adversarial Domain Adaption based on Self-attention

Journal of Network Intelligence

引用

Journal of Network Intelligence 2022年第1期7卷 175-188页

作者： Zhao, Li-Quan Zhang, Yu-Peng Teng, Zi-Ming Jiang, Zi-Cong Cui, Ying Kan, Zhong-Feng Key Laboratory of Modern Power System Simulation and Control & Renewable Energy Technology Ministry of Education Northeast Electric Power University Jilin132012 China College of information and communication Jilin University Changchun130012 China Graduate school of Information Science and Electrical Engineering Kyushu University Fukuoka819-0395 Japan Zhuhai Power Supply Bureau Guangdong Electric Power Corporation Zhuhai519000 China Jilin Power Supply Bureau Jilin Electric Power Corporation Jilin132012 China

Transfer learning is a deep learning method. It transforms knowledge in the source domain and feeds it to the target domain to improve the performance of the target domain model. The conditional adversarial domain adaption method is one of a number of transfer learning methods. It uses Resnet as the feature extraction network;however, Resnet can only determine the relationship between local features, and so its feature extraction accuracy is limited. To overcome this problem, a self-attention layer has been designed in order to determine the relationship among all features. This layer is added between the fourth layer and fifth layer of Resnet. Besides, a cross-entropy function is introduced into loss function, and a sigmoid layer is designed and used as the out layer in conditional adversarial domain adaption. These produce gradient disappearance in the deep network, and influence the discriminator training effect. To solve that problem, a least squares function is used as to design the loss function. The new type of loss function does not require the sigmoid function. Using theoretical analysis, we explain how this new loss function can be used to solve the gradient disappearance problem, thus rendering the network structure more stable. We compare our proposed method with other datasets, including Joint Adaptation Networks, adversarial domain adaptation, conditional adversarial domain adaption, Resnet-50, domain-adversarial neural network on imageCLEF-DA, Office-Home, and Office-31. Our simulation results show that the proposed conditional adversarial domain adaption based on self-attention method has the fastest convergence speed and highest accuracy the among different datasets. © 2022, Taiwan Ubiquitous Information CO LTD. All rights reserved.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Domain Adaptation Using Attention Network and New Loss Function

Journal of Network Intelligence

引用

Journal of Network Intelligence 2022年第3期7卷 704-718页

作者： Zhao, Li-Quan Zhou, Si-Ying Teng, Zi-Ming Jiang, Zi-Cong Jia, Yan-Fei Key Laboratory of Modern Power System Simulation and Control & Renewable Energy Technology Ministry of Education Northeast Electric Power University Jilin132012 China College of information and communication Jilin University Changchun130012 China Graduate school of Information Science and Electrical Engineering Kyushu University Fukuoka819-0395 Japan School of Electrical and Information Engineering Beihua University Jilin132013 China

An unsupervised domain adaptation method is proposed based on the step-wise adaptive feature norm method to improve transfer learning accuracy. The feature extraction network consists of channel attention and spatial attention modules, which en-hance feature extraction ability. To reduce the influence of dimension change on channel weight, a convolution layer with the same kernel size is used to replace the fully connected layer in the bottleneck layer used in the common channel attention module. In addition, a smooth loss function is also proposed. The curve of the proposed function is smoother than the L2 function that is the least square error function. The proposed function’s gradient changes more slowly than the L2 function. The proposed function is used as the activate function of classification prediction regression to reduce the risk of gradient explosion. Compared with a selection of existing methods (Resnet50, conditional domain adversarial networks method, deep adaptive network method, joint adaptation network method, domain adaptation neural network method, and stepwise adaptive feature norm method), the proposed transfer learning method has the highest accuracy than other methods on different datasets for all tasks. © 2022 Taiwan Ubiquitous Information CO LTD. All rights reserved.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Optimization control Strategy of Pumped Storage power Station Considering Cost Allocation

Optimization Control Strategy of Pumped Storage Power Statio...

引用

International Conference on power System technology (powerCON)

作者： Jun Yan Qinglong Song Qi Guo Lijian Xin Fancheng Meng Shuo Yu Jiaxu Zhou Cuiping Li Junhui Li Inner Mongolia Power (Group) Co. Ltd. Hohhot China Key Laboratory of Modern Power System Simulation and Control & Renewable Energy Technology Ministry of Education Northeast Electric Power University Jilin China Power Dispatching and Control Branch Inner Mongolia Power (Group) Co. Ltd. Hohhot China Inner Mongolia Electric Power (Group) Co. Ltd. Inner Mongolia Electric Power Research Institute Branch Hohhot China

Against the backdrop of the increasing proportion of new energy generation, pumped storage, as the main energy storage method, face problems of low utilization and poor economic benefits. To improve the enthusiasm and overall efficiency of pumped storage power stations, this article proposes an optimized control strategy for pumped storage power stations that takes into account cost sharing. This strategy combines the PSS allocation system operation rules and control strategies to improve the utilization of PSS capacity by expanding its application scenario range, and to increase its enthusiasm for extraction by increasing rental income; This article takes a regional power grid in northwest China as an example for analysis, and the results show that the proposed strategy can effectively improve the utilization level and economic benefits of PSS.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Selective Preferred Orientation for High-Performance Antimony Selenide Thin-Film Solar Cells Via Substrate Surface Modulation

SSRN

引用

SSRN 2022年

作者： Zhou, Jing Zhu, Jiawei He, Weilan Cao, Yu Pang, Jinbo Ni, Jian Zhang, Jianjun School of Chemical Engineering Northeast Electric Power University Jilin132012 China Key Laboratory of Modern Power System Simulation and Control & Renewable Energy Technology Ministry of Education School of Electrical Engineering Northeast Electric Power University Jilin132012 China University of Jinan Jinan250022 China College of Electronic Information and Optical Engineering Nankai University Tianjin300350 China

Antimony selenide (Sb2Se3) has rapidly emerged in the field of photovoltaics using one-dimensional crystal structure. However, the power conversion efficiency (PCE) of Sb2Se3 solar cells is influenced by the orientation of the Sb2Se3 photoactive layers. In this study, we investigate the influence of substrate properties on the preferred orientation and microstructure of Sb2Se3 films systematically. With the rise of substrate surface temperature and the decline of substrate surface bonding energy, the preferred orientation of the Sb2Se3 films altered from (hk0) to (hk1) and finally to (002). After summarizing the performance of different preferentially oriented Sb2Se3 solar cells, the results showed that the (hk0)-preferentially oriented devices exhibited a poor performance of less than 1.1%. As the preferred orientation of Sb2Se3 absorbers changed from (hk0) to (hk1), the carrier transport changed from inter-ribbon charge hopping to transportation along the (Sb4Se6)n ribbons. This enhanced the carrier transport efficiency, thereby leading to the enhancement of the PCE to 2%–3%. Furthermore, when the (002) texture coefficient (TC) of the Sb2Se3 films was between 1.8 and 3.6, the PCE of the devices was further enhanced to above 3.5%. A maximum PCE of 4.79% can be obtained when the (002) TC was 3.24. This study reveals the relationship between the Sb2Se3 film preferred orientation and device performance, and demonstrates an effective way to precisely control the Sb2Se3 film microstructure to obtain a high PCE. © 2022, The Authors. All rights reserved.

关键词： Selenium compounds

来源：评论

学校读者我要写书评

暂无评论

Fault Detection Method for Insulators Using Improved YOLOv4

Journal of Network Intelligence

引用

Journal of Network Intelligence 2022年第4期7卷 818-834页

作者： Zhao, Li-Quan Jiang, Zi-Cong Teng, Zi-Ming Jia, Yan-Fei Key Laboratory of Modern Power System Simulation and Control & Renewable Energy Technology Ministry of Education Northeast Electric Power University 168 Changchun Road Jilin132012 China Graduate school of Information Science and Electrical Engineering Kyushu University Fukuoka819-0395 Japan College of information and communication Jilin University Changchun130012 China School of Electrical and Information Engineering Beihua University Jilin132013 China

A defective insulator detection method based on improved You Only Look Once version 4 (YOLOv4) is proposed to improve the precision of defective insulator detection. This method designs a dual-branch attention block by simulating the attention process of the human eye, and introduces it into the backbone of YOLOv4 to extract richer information on defective insulator features. To make the output feature map of shallow layer network fuse more different scale features, a path aggregation network has been designed. To improve detection accuracy, the spatial pyramid pooling has been replaced by atrous spatial pyramid pooling. A dynamic non-maximum suppression method is proposed to improve defective insulator detection accuracy. It employs an adaptive threshold control strategy and weighted operation to full use of the predicted box. We compare our method with defective insulator detection methods based on YOLO and R-CNN. Our simulation results show that the proposed method is more accurate than defective insulator detection methods based on YOLO, and has a faster detection speed than methods based on R-CNN. Compared with the defective insulator detection method based on R-CNN that has the highest mean average precision, the mean average precision of the proposed method is lower, but its detection speed is faster. Compared with YOLOv4, its detection speed is slower, but the mean average precision is higher. The proposed method strikes a satisfactory tradeoff between detection speed and mean average precision. © 2022, Taiwan Ubiquitous Information CO LTD. All rights reserved.

关键词： Object detection

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：