检索结果-内蒙古大学图书馆

Energy Procurement and Retail Pricing for Electricity Retailers via Deep Reinforcement Learning with Long Short-term Memory

引用

CSEE Journal of Power and Energy Systems 2022年第5期8卷 1338-1351页

作者： Hongsheng Xu Jinyu Wen Qinran Hu Jiao Shu Jixiang Lu Zhihong Yang State Key Laboratory of Advanced Electromagnetic Engineering and Technology School of Electrical Electronic Engineering Huazhong University of Science and TechnologyWuhan 430074China NARI Group Corporation Nanjing 211106China School of Electrical Engineering Southeast UniversityNanjing 210096China State Key Laboratory of Smart Grid Protection and Control Nanjing 211106China

The joint optimization problem of energy procurement and retail pricing for an electricity retailer is converted into separately determining the optimal procurement strategy and optimal pricing strategy,under the“price-taker”*** aggregate energy consumption of end use customers(EUCs)is predicted to solve for the optimal procurement strategy vis a long short-term memory(LSTM)-based supervised learning *** optimal retail pricing problem is formulated as a Markov decision process(MDP),which can be solved by using deep reinforcement learning(DRL)***,the performance of existing DRL approaches may deteriorate due to their insufficient ability to extract discriminative features from the time-series vectors in the environmental *** propose a novel deep deterministic policy gradient(DDPG)network structure with a shared LSTM-based representation network that fully exploits the Actor’s and Critic’s *** designed shared representation network and the joint loss function can enhance the environment perception capability of the proposed approach and further improve the optimization performance,resulting in a more profitable pricing *** simulations demonstrate the effectiveness of the proposed approach.

关键词： Deep reinforcement learning electricity market energy procurement long short-term memory retail pricing

来源：评论

学校读者我要写书评

暂无评论

A new approach for calculating the average frequency of power system based on the identification of regional inertia center nodes 2

A new approach for calculating the average frequency of powe...

引用

2nd International Conference on Electrical Engineering and Computer Technology, ICEECT 2022

作者： Wan, Zhonghui Liu, Fusuo Wu, Xuelian State Key Laboratory of Smart Grid Protection and Control Jiangsu Nanjing210003 China NARI Group Corporation/State Grid Electric Power Research Institute Jiangsu Nanjing210003 China

The grid structure of the modern power system is complex and the space span is large. When the power system is disturbed to generate unbalanced power, the transient distribution process among the various synchronous units leads to the spatiotemporal distribution characteristics of the frequency response of the system. By measuring the generator Frequency and Inertia, the inertia center frequency can be calculated. Based on the two-generator system, the relationship between generator frequency and bus frequency is analyzed. A method for selecting the frequency inertia center node of the local power grid in the power system is proposed, and the inertia center frequency of the system is estimated based on the measured frequency at this point. Taking 10 machines and 39 nodes as an example, the simulation calculation is carried out to verify the effectiveness of the proposed method. © Published under licence by IOP Publishing Ltd.

关键词： Frequency response

来源：评论

学校读者我要写书评

暂无评论

Parallel Decomposition and Coordination Algorithm for Security Constrained Optimal Power Flow 1

引用

6th PURPLE MOUNTAIN FORUM on smart grid protection and control, PMF2021

作者： Xiaoqin, Xia Wei, Xu Zhen, Yuan Xiaotong, Xu NARI Group Corporation/State Grid Electric Power Research Institute Jiangsu Nanjing211106 China State Key Laboratory of Smart Grid Protection and Control Jiangsu Nanjing211106 China

ISBN: (数字)9789811671562

ISBN: (纸本)9789811671555

In order to improve the online performance of power system control decision-making, this paper proposes a method to resolve the economic optimization problem considering security constraints into a base-case optimal power flow master problem with the objective of minimizing the generation cost and a series of security check sub problems relevant to various faults. A parallel decomposition and coordination algorithm based on adjustable space slices is proposed to avoid alternating iterations. First of all, the adjustable space is sliced to form multiple slicing schemes according to different proportions. Based on the parallel computing platform and the slicing schemes, the primal dual interior point method is used to solve the base-case optimal power flow master problem. Secondly, security check of faults is carried out by parallel computing for different optimized cases. Then, the solution with the minimum cost is chosen from the safe solutions. Finally, the effectiveness of the proposed method is verified by a case of a city power gird in Guizhou province. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Deep neural network based acoustic pattern recognition system for fault localization application

引用

Applied Mathematics and Nonlinear Sciences 2024年第1期9卷

作者： Cui, Yao Huang, Xin Zhang, Xin Nari Group Corporation State Grid Electric Power Research Institute Jiangsu Nanjing211106 China State Key Laboratory of Smart Grid Protection and Control Jiangsu Nanjing211106 China

This paper explores the process of traditional voiceprint recognition, analyzes the traditional GMM recognition algorithm, and proposes a GE2E-based voiceprint recognition algorithm by combining it with the deep neural network. It firstly uses the Bi-GRU network to replace the LSTM network to prevent the lack of semantic information, then adds the SGD algorithm to optimize the speech features, and finally improves the stability and accuracy of recognition by the GE2E loss function. On this basis, a voiceprint recognition system based on GE2E is designed, and the overall performance of the system is tested. Additionally, a voiceprint recognition system is being explored for fault localization. The results show that the recognition accuracy of male voiceprints in the test is at [0.89,0.95], and the recognition accuracy of female voiceprints is at [0.88,0.96], and there is not much difference in the voiceprint recognition accuracy of the voiceprint recognition system for both male and female students, and the overall recognition accuracy is greater than 0.9. When applied in fault location, the error between the measured distance and the actual fault distance is within 0.1 meters, enabling fault location. © 2023 Yao Cui, Xin Huang and Xin Zhang, published by Sciendo.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Automatic Generation Method of Multi-Bays Graph in Power System based on Real-Time Topological Model

Automatic Generation Method of Multi-Bays Graph in Power Sys...

引用

2022 Global Conference on Robotics, Artificial Intelligence and Information Technology, GCRAIT 2022

作者： Gao, Yuan Chen, Lianjie Si, Peng Su, Yunguang Fang, Caishen Xu, Hua Huang, Kun NARI Technology Co Ltd. Nanjing China NARI Technology Co Ltd. State Key Laboratory of Smart Grid Protection and Control Nanjing China

ISBN: (数字)9781665481922

ISBN: (纸本)9781665481922

Substation supervisory control is an essential part of power grid monitoring system. Besides the power flow between substations, the running states of the devices in substations are important to the staff in power grid. At present, the substation devices with their running states are drawn in electrical bay graphs, which are widely used in the power grid dispatching department. Traditional electrical bay graphs contain devices in only one substation and the drawing process of the graph relies on manual work. In this paper, an automatic generation method of multi-bay graph in power system based on real-Time topological model is proposed. There are two stages in the method. In the first stage, necessary model information is obtained according to topology in real-Time database. In the second stage, the bay features are firstly built in the method and the classification of the bays is achieved by these features. Secondly, a data structure of device tree is proposed and the automatic layout of devices is realized based on the data structure. Finally, automatic wiring of the devices is achieved from the perspective of aesthetic and objectivity. Experimental results show that the graph drawn by the proposed method could not only reflect the actual connection mode and running states of the substation devices but also show the power flow between these substations. The proposed drawing method could reduce manual operations and improve the work efficiency of the power grid staff. © 2022 IEEE.

关键词： Data structures

来源：评论

学校读者我要写书评

暂无评论

Metallic Short Circuit Fault Location Algorithm Considering Capacitance Current based on Differential Equation

Metallic Short Circuit Fault Location Algorithm Considering ...

引用

2021 International Conference on Power System Technology, POWERCON 2021

作者： Liu, Huirong Zheng, Yuping Wu, Tonghua Hong, Feng Dai, Wei Li, Xindong NARI Group Corporation State Key Laboratory of Smart Grid Protection and Control Nanjing China

ISBN: (纸本)9781665407373

Capacitance current has significant effect on long-distance fault of high-voltage transmission line, and the current single-ended quantity location algorithm can hardly eliminate the effect of capacitance current under the power frequency. To reduce capacitance current's effect on location algorithm, this paper builds metallic grounding fault model based on RLC type circuit, takes fault location as the unknown variable, builds a mathematical location model within time domain applicable for taking account of capacitance current, and obtains the quadratic equation with one unknown for fault location. Then it substitutes the two independent variables for the linear term and quadratic term, solves independent variables through linear equation, and proves the solution exists and is unique. Then under analysis on the same difference error, it compares magnitude of error generated during calculation of the two independent variables, it corrects difference error first, and inversely solves fault location by selecting the numerically disturbed smaller independent variable. Simulation results indicate the algorithm can accurately take account of effect of capacitance current under different metallic fault conditions, and solve fault location in a stable and accurate manner. © 2021 IEEE.

关键词： Differential equations

来源：评论

学校读者我要写书评

暂无评论

A Rapid Method to Configure Inspection Object for Substation Robot Based on Visual Equipment Detection and PTZ control Model 6th

A Rapid Method to Configure Inspection Object for Substation...

引用

6th PURPLE MOUNTAIN FORUM on smart grid protection and control, PMF2021

作者： Zhang, Qingwei Sun, Han Wang, Jing State Key Laboratory of Smart Grid Protection and Control Nari Group Corporation Jiangsu Nanjing211106 China Nari Group Corporation Jiangsu Nanjing211106 China

ISBN: (纸本)9789811671555

The configuration for substation robot inspection task includes the following steps: configuring inspection object, scanning map package, building wireless AP, establishing database, etc. Previous work mostly relies on the experience of staff to configure inspection object, which is a waste of manpower and material resources. Besides, configuration for each inspection object of substation robot manually is a time-consuming task, which leads to a decrease in the effectiveness and accuracy of robot because of artificial error. A rapid configuration method to configure inspection object for substation robot inspection task is proposed based on visual equipment detection and PTZ control model. It aims to grab the inspection object automatically without manual intervention. The efficacy of the proposed method is verified through experimental results of substation. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Inspection

来源：评论

学校读者我要写书评

暂无评论

A Dual-Objective Optimization control Strategy with Markov Forecast for Battery Energy Storage System to Mitigating Wind Farm Fluctuations 6th

A Dual-Objective Optimization Control Strategy with Markov F...

引用

6th PURPLE MOUNTAIN FORUM on smart grid protection and control, PMF2021

作者： Gu, Haotian Hou, Kai Jiang, Yingwei Yin, Hang Liu, Jing Zhong, Xu NARI Group Corporation/State Grid Electric Power Research Institute Jiangsu Province Nanjing211000 China State Key Laboratory of Smart Grid Protection and Control Jiangsu Province Nanjing211000 China

ISBN: (纸本)9789811671555

In a renewable energy power system dominated by a high proportion of wind power, the configuration of energy storage system is an effective solution to mitigate wind power fluctuations, ensure the safe and stable operation of the grid, and improve the dispatch ability of wind power. This paper proposes a battery energy storage system (BESS) control strategy with the consideration of the impact of future wind power. To achieve maximum bidirectional output capability and minimum output of BESS, multi-objective hybrid optimization model is built on base of first-order low-pass filter’s variable time constant Tf, which contains two weight coefficients c1 and c2 to flexibly adjust BESS output. Markov chain prediction model is introduced to forecast the future multi-step wind power and PSO optimization algorithm is used to obtain the optimal BESS output power in real-time rolling calculation. Finally, the effectiveness of the proposed control strategy is verified through case studies. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Low pass filters

来源：评论

学校读者我要写书评

暂无评论

Algorithms to Calculate the Most Reliable Maximum Flow in Content Delivery Network

引用

Computer Systems Science & Engineering 2022年第5期41卷 699-715页

作者： Baili Zhang Keke Ling Pei Zhang Zhao Zhang Mingjun Zhong School of Computer Science and Engineering Southeast UniversityNanjing211189China State Key Laboratory of Smart Grid Protection and Control Nanjing211106China Nari Group Corporation Nanjing211106China Department of Computing Science University of AberdeenAberdeenAB243UEUK

Calculating the most reliable maximum flow(MRMF)from the edge cache node to the requesting node can provide an important reference for selecting the best edge cache node in a content delivery network(CDN).However,SDBA,as the current state-of-the-art MRMF algorithm,is too complex to meet real-time computing *** paper proposes a set of MRMF algorithms:NWCD(Negative Weight Community Deletion),SCPDAT(Single-Cycle Preference Deletion Approximation algorithm with Time constraint)and SCPDAP(Single-Cycle Preference Deletion Approximation algorithm with Probability constraint).NWCD draws on the“flow-shifting”algorithm of minimum cost and maximum flow,and further defines the concept of negative weight *** algorithm continuously deletes the negative weight communities,which can increase reliability while keeping the flow constant in the residual *** is proven that when all negative weight communities are deleted,the corresponding maximum flow is the *** tries to approach the optimal solution to the greatest extent possible within the limited time,while SCPDAP tries to reach the probability threshold in the shortest amount of *** of these adopt the strategy of first deleting single-cycle communities(which contribute more to the reliability with lower time cost).Experiments show that,compared with SDBA,NWCD combined with the probabilistic pruning achieves an order of magnitude improvement in time cost,while SCPDAT and SCPDAP demonstrate better time performance and increased applicability.

关键词： Content delivery network uncertain graph maximum flow flow reliability

来源：评论

学校读者我要写书评

暂无评论

Online Verification Method for Power grid Frequency Security Considering Multi-Time Scales Frequency Modulation Characteristics

Online Verification Method for Power Grid Frequency Security...

引用

IEEE PES Asia-Pacific Power and Energy Engineering Conference (APPEEC)

作者： Zelun Sun Liang Zheng Tong Li Feng Luo Haifeng Zhou Jingjing Ruan Zhihao Tian Laboratory of Smart Grid Protection and Control NARI Group Corporation (State Grid Electic Power Research Institute) Nanjing China State Grid Ningxia Electric Power Company Ningxia China

ISBN: (数字)9798350386127

ISBN: (纸本)9798350386134

With the large-scale integration of renewable energy such as wind power and photovoltaics, the power grid now exhibits characteristics of low inertia and reduced anti-interference ability. Consequently, it presents significant risks to the frequency security of the grid. The traditional online security verification of power grid frequency encompasses two distinct working conditions. Firstly, it involves the transient frequency security verification, which focuses on the primary frequency modulation during grid faults. Secondly, it also encompasses the medium and long-term security verification, specifically targeting the secondary frequency modulation under steady-state conditions of the power grid. This method cannot consider the multi-time scales factors of power grid frequency fluctuations. An online verification method for power grid frequency security considering multi-time scales frequency modulation characteristics is proposed. Based on the sliding filter algorithm, disturbance signals of different time scales are generated for simulation verification. Simulation methods are selected based on the fluctuation levels of disturbance signals at various time scales. By considering the priority of the primary and secondary frequency modulation time sequences of the power generating unit, an online security and stability verification method for grid frequency with consideration of multi-time scale frequency response is developed. The dynamic response process of the primary and the secondary frequency modulation of the system is simulated and verified based on the IEEE-39 system.

关键词： Time-frequency analysis Renewable energy sources Frequency modulation Fluctuations Power system stability Wind power generation Power grids Stability analysis Security Transient analysis

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：