检索结果-南通市图书馆

Protection and Control of Modern power Systems 2022年第1期7卷 788-800页

作者： Biao Xu Guiyuan Zhang Ke Li Bing Li Hongyuan Chi Yao Yao Zhun Fan Shantou University ShantouChina The AI Application and Innovation Center of China Mobile Communications Group Guangdong Co. Ltd.ShantouChina

As high amounts of new energy and electric vehicle(EV)charging stations are connected to the distribution network,the voltage deviations are likely to occur,which will further affect the power *** is challenging to manage high quality voltage control of a distribution network only relying on the traditional reactive power control *** the reactive power regulation potentials of new energy and EVs can be tapped,it will greatly reduce the reactive power optimization pressure on the *** this in mind,our reasearch first adds EVs to the traditional distribution network model with new forms of energy,and then a multi-objective optimization model,with achieving the lowest line loss,voltage deviation,and the highest static voltage stability margin as its objectives,is ***,the corresponding model parameters are set under different climate and equipment ***,the optimization model under specific scenarios is ***,considering the supply and demand relation-ship of the network,an improved technique for order preference by similarity to an ideal solution decision method is proposed,which aims to judge the adaptability of different algorithms to the optimized model,so as to select a most suitable algorithm for the ***,a comparison is made between the constructed model and a model without new *** results reveal that the constructed model can provide a high quality reactive power regula-tion strategy.

关键词： Renewable energy Electric vehicle Multi-objective optimization Pareto front reactive power optimization

Data-driven reactive power optimization of Distribution Networks via Graph Attention Networks

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Modern power Systems and Clean Energy 2024年第3期12卷 874-885页

作者： Wenlong Liao Dechang Yang Qi Liu Yixiong Jia Chenxi Wang Zhe Yang Wind Engineering and Renewable Energy Laboratory Ecole Polytechnique Federale de Lausanne(EPFL)Lausanne 1015Switzerland the College of Information and Electrical Engineering China Agricultural UniversityBeijing 100083China the College of Electrical Engineering and Automation Shandong University of Science and TechnologyQingdao 266590China the Department of Electrical and Electronic Engineering(Energy Digitalization Laboratory) The University of Hong KongHong KongChina the Department of Electrical Engineering The Hong Kong Polytechnic UniversityHong KongChina

reactive power optimization of distribution networks is traditionally addressed by physical model based methods,which often lead to locally optimal solutions and require heavy online inference time *** improve the quality of the solution and reduce the inference time burden,this paper proposes a new graph attention networks based method to directly map the complex nonlinear relationship between graphs(topology and power loads)and reactive power scheduling schemes of distribution networks,from a data-driven *** graph attention network is tailored specifically to this problem and incorporates several innovative features such as a self-loop in the adjacency matrix,a customized loss function,and the use of max-pooling ***,a rulebased strategy is proposed to adjust infeasible solutions that violate *** results on multiple distribution networks demonstrate that the proposed method outperforms other machine learning based methods in terms of the solution quality and robustness to varying load ***,its online inference time is significantly faster than traditional physical model based methods,particularly for large-scale distribution networks.

关键词： reactive power optimization graph neural network distribution network machine learning data-driven

Data-driven reactive power optimization for Distribution Networks Using Capsule Networks

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Journal of Modern power Systems and Clean Energy 2022年第5期10卷 1274-1287页

作者： Wenlong Liao Jiejing Chen Qi Liu Ruijin Zhu Like Song Zhe Yang AAU Energy Aalborg UniversityAalborgDenmark School of Softwareand Microelectronics Peking UniversityBeijingChina Key Laboratory of Smart Gridof Ministry of Education Tianjin UniversityTianjinChina School of Electrical Engineering Tibet Agriculture and Animal Husbandry UniversityLinzhiChina Maintenance Branch of State Grid Jibei Electric power Co. Ltd.BeijingChina

The construction of advanced metering infrastructure and the rapid evolution of artificial intelligence bring opportunities to quickly searching for the optimal dispatching strategy for reactive power optimization. This can be realized by mining existing prior knowledge and massive data without explicitly constructing physical models. Therefore, a novel datadriven approach is proposed for reactive power optimization of distribution networks using capsule networks(CapsNet). The convolutional layers with strong feature extraction ability are used to project the power loads to the feature space to realize the automatic extraction of key features. Furthermore, the complex relationship between input features and dispatching strategies is captured accurately by capsule layers. The back propagation algorithm is utilized to complete the training process of the CapsNet. Case studies show that the accuracy and robustness of the CapsNet are better than those of popular baselines(e.g.,convolutional neural network, multi-layer perceptron, and casebased reasoning). Besides, the computing time is much lower than that of traditional heuristic methods such as genetic algorithm, which can meet the real-time demand of reactive power optimization in distribution networks.

关键词： Data-driven reactive power optimization distribution networks deep learning capsule networks

Chaos quantum particle swarm optimization for reactive power optimization considering voltage stability

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Journal of Harbin Institute of Technology(New Series) 2010年第3期17卷 351-356页

作者：瞿苏寒马平蔡兴国 School of Electrical Engineering and Automation Harbin Institute of Technology School of Automation Engineering Qingdao University

The reactive power optimization considering voltage stability is an effective method to improve voltage stablity margin and decrease network losses,but it is a complex combinatorial optimization problem involving nonlinear functions having multiple local minima and nonlinear and discontinuous constraints. To deal with the problem,quantum particle swarm optimization (QPSO) is firstly introduced in this paper,and according to QPSO,chaotic quantum particle swarm optimization (CQPSO) is presented,which makes use of the randomness,regularity and ergodicity of chaotic variables to improve the quantum particle swarm optimization algorithm. When the swarm is trapped in local minima,a smaller searching space chaos optimization is used to guide the swarm jumping out the local minima. So it can avoid the premature phenomenon and to trap in a local minima of QPSO. The feasibility and efficiency of the proposed algorithm are verified by the results of calculation and simulation for IEEE 14-buses and IEEE 30-buses systems.

关键词： reactive power optimization voltage stability margin quantum particle swarm optimization chaos optimization

Research on reactive power optimization of Offshore Wind Farms Based on Improved Particle Swarm optimization

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Energy Engineering 2023年第9期120卷 2013-2027页

作者： Zhonghao Qian Hanyi Ma Jun Rao Jun Hu Lichengzi Yu Caoyi Feng Yunxu Qiu Kemo Ding State Grid Jiangsu Nantong Electric power Co. Ltd.Nantong226000China College of Energy and Electrical Engineering Hohai UniversityNanjing211100China

The lack of reactive power in offshore wind farms will affect the voltage stability and power transmission quality of wind *** improve the voltage stability and reactive power economy of wind farms,the improved particle swarmoptimization is used to optimize the reactive power planning in wind ***,the power flow of offshore wind farms is modeled,analyzed and *** improve the global search ability and local optimization ability of particle swarm optimization,the improved particle swarm optimization adopts the adaptive inertia weight and asynchronous learning *** the minimum active power loss of the offshore wind farms as the objective function,the installation location of the reactive power compensation device is compared according to the node voltage amplitude and the actual engineering ***,a reactive power optimizationmodel based on Static Var Compensator is established inMATLAB to consider the optimal compensation capacity,network loss,convergence speed and voltage amplitude enhancement effect of *** the compensation methods in several different locations,the compensation scheme with the best reactive power optimization effect is ***,the optimization results of the standard particle swarm optimization and the improved particle swarm optimization are compared to verify the superiority of the proposed improved algorithm.

关键词： Offshore wind farms improved particle swarm optimization reactive power optimization adaptive weight asynchronous learning factor voltage stability

Hierarchically Correlated Equilibrium Q-learning for Multi-area Decentralized Collaborative reactive power optimization

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

CSEE Journal of power and Energy Systems 2016年第3期2卷 65-72页

作者： Min Tan Chuanjia Han Xiaoshun Zhang Lexin Guo Tao Yu Yangjiang power Supply Bureau China Southern Power Grid CompanyYangjiang 529500China College of Electric power South China University of TechnologyGuangzhou 510640China Shenzhen power Supply Co. LtdShenzhen 518000China

A hierarchically correlated equilibrium Q-learning(HCEQ)algorithm for reactive power optimization that considers carbon emission on the grid-side as an optimization objective,is proposed *** on the multi-area decentralized collaborative framework,the controllable variables in each region are divided into several optimization layers,which is an effective method for solving the limitations posed by *** HCEQ provides constant information on the interaction between the state-action value function matrices,as well as on the cooperative game equilibrium among agents in each *** acquiring the optimal value function matrix in the pre-learning process,HCEQ is able to quickly achieve an optimal solution *** of the IEEE 57-bus system is performed,which demonstrates that the proposed algorithm can effectively solve multi-area decentralized collaborative reactive power optimization,with the desired global search capabilities and convergence speed.

关键词： Hierarchically correlated equilibrium multiarea decentralized collaborative reactive power optimization reinforcement learning

power System reactive power optimization Based on Global Differential Evolution Algorithm 25th

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Power System Reactive Power Optimization Based on Global Dif...

第25届中国控制与决策会议

作者： Peifeng Wu Jianhua Zhang School of Electrical and Electronic Engineering North China Electric Power University

ISBN: (纸本)9781467355339

The reactive power optimization problem has a significant influence on secure and economic operation of power systems. reactive power optimization of power systems is a kind of mixed nonlinear integer programming problem and can reduce network loss by changing transformer taps, adjusting generator terminal voltage and connecting shunt capacitors. This paper proposes global differential evolution （GDE） algorithm which can improve the convergence speed and avoid local optimum. GDE is utilized to solve the reactive power optimization *** results show that GDE algorithm is an effective algorithm to solve reactive power optimization problem and its optimization result is better than other algorithms

关键词： Global Differential Evolution Algorithm reactive power optimization Network Loss

reactive power optimization of Distribution Network Based on Beluga whale optimization Algorithm

在线全文

cnki会议

学校读者我要写书评

暂无评论

Reactive Power Optimization of Distribution Network Based on...

第35届中国过程控制会议

作者： Lingxiong Zhang Yiqiang Yang Xingzhong Xiong Wan Xu Sichuan University of Science and Engineering Automation and Information Engineering Artificial Intelligence Key Laboratory of Sichuan Province

In order to improve voltage quality and meet the safety and economic operation of the distribution network, reactive power optimization of the distribution network adopts voltage control by reducing system losses. Compare and analyze the Beluga whale optimization algorithm(BWO) with particle swarm optimization algorithm and dragonfly algorithm, and compare the convergence effects and differences in solving the optimal values of each algorithm. Establish a mathematical model for reactive power optimization with the minimum active power loss in the system. Using the power flow balance equation and voltage upper and lower limits as constraints, determine the optimal reactive power compensation amount for the system and select a reactive power compensator to achieve precise compensation. Taking the IEEE33 node distribution network system as an example, simulation analysis was conducted on the Matlab platform. The results showed that the BWO algorithm has faster convergence speed, better global search ability, and optimization ability, proving that the algorithm can reduce network losses and improve voltage quality.

关键词： distribution network reactive power optimization Active network loss BWO algorithm

reactive power optimization Compensation of Line Losses Calculation in Rural Areas

在线全文

cnki会议

学校读者我要写书评

暂无评论

Reactive Power Optimization Compensation of Line Losses Calc...

第30届中国控制与决策会议

作者： Sun Feng Yan Licheng Guo Zhitong Chen Yanhong power Science Research Institute Of Liaoning Electric power Limited Company College Of Information Science And Engineering Northeastern University

With the rapid development of smart grid and the rapid increase of electricity load, area planning and management work is lagging behind the smart grid development, area voltage quality is poor, the line loss rate is more and more sudden, line loss calculation exact is the key for the reduction measures. In this paper, the calculation of the improved line loss and the reactive power compensation are carried out on the area. The objective function is used to calculate the approximate reactive power compensation of the area by genetic algorithm and sensitivity analysis. Finally classify the area according to the per capita sales of electricity, in each type select a typical area and then reactive power configuration program in random area is achieved through the weighted impact of the electrical characteristics of reactive power loss.

关键词： Line loss calculation area reactive power optimization

reactive power optimization of Electric power System Incorporating Wind power Based on Parallel Immune Particle Swarm optimization

在线全文

cnki会议

学校读者我要写书评

暂无评论

Reactive Power Optimization of Electric Power System Incorpo...

第26届中国控制与决策会议

作者： WANG Tianhong YUAN Guili ZHU Lei YU Tong China power Complete Equipment Co. Ltd School of Control and Computer Engineering North China Electric Power University

This paper aims at the characteristics of reactive power optimization of the electric power system with the wind farm;proposing a new method for reactive power optimization on the entire power grid which uses the Parallel Immune Particle Swarm optimization. It uses integer and real number hybrid encoding, improves the efficiency of compiling. And it combines the continuous and discrete particle swarm optimization, and introduces immune operators to improve the convergence precision. IEEE-14 and IEEE-30 system simulation examples show that the new method has better global convergence ability, faster convergence rate and higher accuracy.

关键词： Wind power reactive power optimization Particle Swarm optimization Immune Algorithm Integer and Real Number Hybrid Encoding.