检索结果-内蒙古大学图书馆

SSRN 2022年

作者： Chen, Haipeng Wu, Huayue Chen, Jian Kan, Tianyang Miao, Sen Key Laboratory of Modern Power System Simulation and Control & Renewable Energy Technology Ministry of Education Northeast Electric Power University Jilin132012 China Department of Electrical Engineering Northeast Electric Power University Jilin132012 China Chengde Power Supply Company State Grid Jibei Electric Power Co. Ltd. Chengde067000 China

With increasing renewable energy penetration and the extension of the power system scale, accurate electricity price prediction has long become a challenging task. The complexity of electricity market information, insufficient model training, and the lack of model generalization ability limit the prediction accuracy of the existing electricity price forecasting methods. This paper proposes a Sequence-to-Sequence Attention algorithm based on the Double Deep Q Network optimization method for short-term electricity price prediction. This algorithm first conducts the maximum information coefficient correlation analysis to select the input dataset for the prediction model of electricity price. Secondly, the Sequence-to-Sequence Attention model is proposed for point forecasting and probabilistic forecasting of short-term electricity prices. Finally, the hyperparameters of the model are optimized by the Double Deep Q Network method, which improves the prediction accuracy and the generalization ability of the prediction model of electricity price. simulations are carried out on Pennsylvania–New Jersey–Maryland market data and the New South Wales electricity market. The results show that the proposed method has superior performance than the existing prediction methods, which is appliable for the short-term electricity price prediction and provides a powerful decision-making basis for market participants and regulators. © 2022, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Optimal Scheduling Strategy of a Regional Integrated energy system Considering renewable energy Uncertainty and Heat Network Transmission Characteristics

SSRN

引用

SSRN 2022年

作者： Chen, Haipeng Gao, Lin Zhang, Yongling Zhao, Chang Key Laboratory of Modern Power System Simulation and Control & Renewable Energy Technology Ministry of Education Northeast Electric Power University Jilin132012 China Department of Electrical Engineering Northeast Electric Power University Jilin132012 China Gongqing Institute of Science and Technology Gongqing City 332020 China National New Energy Group Jilin Jiangnan Thermal Power Limited Company Jilin132012 China

In order to overcome the curtailment of wind energy caused by "power determined by heat" of combined heat and power units, this study proposes an integrated demand response strategy and optimization method for heat-electric energy dispatching in a regional integrated energy system. Firstly, a scene analysis model based on Latin Hypercube Sampling (LHS) and Backward Reduction (BR) is constructed to analyze the probabilistic properties of wind power output in various scenes, and further provide a necessary reference for integrated energy scheduling. Secondly, the schedulable electrical power and thermal demand are evaluated with the consideration of the transmission characteristics of the heat supply network, then the integrated demand response of electric-thermal coordination is adopted to facilitate suppress the heat load fluctuation and wind power consumption. Finally, the optimal scheduling model of regional integrated energy system is established considering the source-load coordination, and the optimal output of each power unit is determined with the goal of minimizing overall cost during the scheduling period. The simulation results demonstrated that the proposed scheduling method reduces the operation cost of the integrated energy system and effectively promotes the wind energy consumption. Furthermore, it serves as a benchmark for the coordinated operation of wind turbines and power grids. © 2022, The Authors. All rights reserved.

关键词： Electric power utilization

来源：评论

学校读者我要写书评

暂无评论

Research on load demand response behavior strategies in the steel industry guided by price signals

Research on load demand response behavior strategies in the ...

引用

4th energy Conversion and Economics Annual Forum (ECE Forum 2024)

作者： Junhui Li Jiong Zhang Yan Li Peng Yu Meng Yu Hengyu Liu Xingxu Zhu Key Laboratory of Modern Power System Simulation and Control & Renewable Energy Technology Ministry of Education Northeast Electric Power University Jilin People's Republic of China State Grid Electric Power Research Institute Co. Ltd State Grid Electric Power Research Institute Wuhan Efficiency Evaluation Co. Ltd Hubei People's Republic of China State Grid Liaoning Electric Power Co. Ltd State Grid Liaoning Electric Power Company Limited Power Dispatch and Control Center Liaoning People's Republic of China State Grid Liaoning Electric Power Co. Ltd State Grid Liaoning Electric Power Company Limited Electric Power Research Institute Liaoning People's Republic of China

ISBN: (数字)9781837242924

The steel industry load has the advantages of high power consumption, high automation level, strong controllability, and strong demand response potential. In order to improve its enthusiasm for participating in the power grid and promote the consumption of renewable energy, the electricity response behavior and demand potential of each production process of the industrial load are first evaluated. The strategy of using price signals to guide the steel industry load in typical areas to participate in the demand response of the power system is proposed. Models are established for the power grid dispatch center and the industrial load response behavior respectively. In the process, the different interests and demands of the two parties, the power grid dispat ch and the industrial load, are comprehensively considered. A two-layer dispatch model is established to truly reflect the interactive game process between power supply and demand; To match the model solution with interaction, a hierarchical iterative algorithm is used to accelerate the convergence speed while ensuring the interaction between price signals and purchasing power between layers. Combining a certain industrial load area for case analysis, the results show that the proposed model not only improves the system's ability to absorb renewable energy, but also takes into account the interests and responsiveness of the steel industry load.

关键词：

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

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

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

Corrigendum to ‘Optimised configuration of multi-energy systems considering the adjusting capacity of communication base stations and risk of network congestion’ [energy volume 313 (2024) 133873]

引用

energy 2025年 314卷

作者： Dongfeng Yang Xi Wang Yong Sun Jingying Yang Xiaojun Liu Chao Jiang Key Laboratory of Modern Power System Simulation and Control & Renewable Energy Technology Ministry of Education (Northeast Electric Power University) Jilin 132012 China State Grid Jilin Electric Power Co. Ltd Changchun 30000 China

来源：评论

学校读者我要写书评

暂无评论

Seismic Interpolation Transformer for Consecutively Missing Data: A Case Study in DAS-VSP Data

arXiv

引用

arXiv 2024年

作者： Cheng, Ming Lin, Jun Dong, Xintong Lu, Shaoping Zhong, Tie College of Instrumentation and Electrical Engineering Jilin University Jilin Changchun130026 China School of Earth Sciences and Engineering Sun Yat-Sen University Guangdong Guangzhou510275 China Guangdong Zhuhai519000 China Guangdong Provincial Key Lab of Geodynamics and Geohazards Sun Yat-sen University Guangdong Guangzhou510275 China Key Laboratory of Modern Power System Simulation and Control and Renewable Energy Technology Ministry of Education Jilin132012 China Department of Communication Engineering College of Electric Engineering Northeast Electric Power University Jilin132012 China

Distributed optical fiber acoustic sensing (DAS) is a rapidly-developed seismic acquisition technology with advantages of low cost, high resolution, high sensitivity, and small interval, etc. Nonetheless, consecutively missing cases often appear in real seismic data acquired by DAS system due to some factors, including optical fiber damage and inferior coupling between cable and well. Recently, some deep-learning seismic interpolation methods based on convolutional neural network (CNN) have shown impressive performance in regular and random missing cases but still remain the consecutively missing case as a challenging task. The main reason is that the weight sharing makes it difficult for CNN to capture enough comprehensive features. In this paper, we propose a transformer-based interpolation method, called seismic interpolation transformer (SIT), to deal with the consecutively missing case. This proposed SIT is an encoder-decoder structure connected by some U-shaped swin-transformer blocks. In encoder and decoder part, the multi-head self-attention (MSA) mechanism is used to capture global features which is essential for the reconstruction of consecutively missing traces. The U-shaped swin-transformer blocks are utilized to perform feature extraction operations on feature maps with different resolutions. Moreover, we combine the loss based on structural similarity index (SSIM) and L1 norm to propose a novel loss function for SIT. In experiments, this proposed SIT outperforms U-Net and swin-transformer. Moreover, ablation studies also demonstrate the advantages of new network architecture and loss function. Copyright © 2024, The Authors. All rights reserved.

关键词： Optical fibers

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

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

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：