This paper proposes a new Initial CCT (Critical Clearing Time) estimation method using a hybrid neural network composed of iRprop (Improving the Resilient back PROPation Algorithm) and RAN (Resource Allocation Network...This paper proposes a new Initial CCT (Critical Clearing Time) estimation method using a hybrid neural network composed of iRprop (Improving the Resilient back PROPation Algorithm) and RAN (Resource Allocation Network). In transient stability study, CCT evaluation is very important but time consuming due to the fact it needs many iteration of time domain simulations gradually increasing the fault clearing time. The key to reduce the required computing time in this process is to find accurate initial estimation of CCT by a certain handy method before going to the iterative stage. As one of the strongest candidates of this handy method is the utilization of the pattern recognition ability of neural networks, which enable us to jump to a close estimation of the real CCT without any heavy computing burden. This paper proposes a new hybrid neural network which is a combination of the well-known iRprop and RAN. In the proposed method, the outputs of the hidden units of RAN are modified by multiplying the contribution factors calculated by an additional iRprop network. Numerical studies are done using two different test systems for the purpose of confirming the validity of the proposal. The result of the proposed method is the best. Properly evaluating the contribution of each input to the hidden units, the estimation error obtained by the proposed method is improved further than the original RAN based estimation.展开更多
The utilization of wind generation equipment, such as DFIGs （double fed induction generators）, interconnected to islanded power generation and distribution systems is investigated in order to determine their effects...The utilization of wind generation equipment, such as DFIGs （double fed induction generators）, interconnected to islanded power generation and distribution systems is investigated in order to determine their effects on the overall system operating characteristics and stability. The use of a stable power station （with high speed machines） will be critical in achieving fast and reliable transient response to network events, in particular, when large transient loads are expected on a continuous basis, i.e., industrial mining and mineral processing equipment. Simulation results of this paper assist in understanding how small power stations and wind generation equipment respond to large transients in an islanded network. In particular, detailed simulations and analyses will be presented on impacts of distributed wind generation units （1.5 MW DF1G） on the stability of a small weak network. The novelty of this paper is on detailed analyses and simulation of weak networks with interconnects DFIG＇s including their impacts on system stability under various transient operating conditions.展开更多
Limited resources are available on the application of wind generation systems interconnected to weak powemetworks. With the need to further interface DG （distributed generation） including WG （wind generation） to w...Limited resources are available on the application of wind generation systems interconnected to weak powemetworks. With the need to further interface DG （distributed generation） including WG （wind generation） to weak networks, it is necessary to establish a means of determining what is the most efficient quantity of WG that can be applied in order to maintain stability in the network. This paper establishes a concept that can be applied to weak networks. The aim is to estimate how much WG can be installed on weak networks as well as establishing characteristic responses to generation loss without and with faulted conditions. The main contribution is a thorough understanding of weak network limitation proved to be the most critical parameter in these calculations.展开更多
The performance of DFIG-based wind generation systems that interconnected to solid networks is well understood and prevalent in Europe and North America. However, the application of these renewable generating stations...The performance of DFIG-based wind generation systems that interconnected to solid networks is well understood and prevalent in Europe and North America. However, the application of these renewable generating stations to weak network has been examined in very limited occasions. Weak networks have a range of limitations from system capacities to CFCT restrictions which would need to be well understood prior to wind energy integration. Of particular interest would be how much wind generation could be integrated into a weak network prior to increasing voltage and frequency stability issues brought about by penetration issues. This paper introduces a simple and practical approach based on the equal area criteria to investigate the stability of weak networks. Simulation results that are presented to show the proposed approach is a viable preliminary assessment tool to determine system stability on weak networks with wind power penetration.展开更多
提出一种基于复合神经网络的暂态稳定评估与故障临界切除时间(CCT)裕度预测新方法,它将概率神经网络(PNN)和径向基函数(RBF)网络组合使用,充分利用两者各自的优点,以提高暂态稳定评估能力和CCT裕度预测能力。该方法首先利用PNN进行暂态...提出一种基于复合神经网络的暂态稳定评估与故障临界切除时间(CCT)裕度预测新方法,它将概率神经网络(PNN)和径向基函数(RBF)网络组合使用,充分利用两者各自的优点,以提高暂态稳定评估能力和CCT裕度预测能力。该方法首先利用PNN进行暂态事故场景分类,分类时充分考虑了相邻故障样本类型重叠的影响;进一步采用RBF网络对分类结果进行裕度预测;最后,通过自检和校正以提高预测精度。利用New England 39节点系统,通过与反向传播(BP)神经网络、RBF神经网络等方法的比较,证明了本文方法的优越性。展开更多
多年来湖南电网电压暂态稳定问题一直困扰电网运行,随着±800 k V酒泉—湖南特高压直流投运,电压暂态问题将进一步加剧。本文提出了基于电压稳定极限测试方法,确定湖南电网暂态电压薄弱环节,并通过仿真在系统暂态电压薄弱点增加动...多年来湖南电网电压暂态稳定问题一直困扰电网运行,随着±800 k V酒泉—湖南特高压直流投运,电压暂态问题将进一步加剧。本文提出了基于电压稳定极限测试方法,确定湖南电网暂态电压薄弱环节,并通过仿真在系统暂态电压薄弱点增加动态无功补偿装置,证明能显著提高系统极限切除时间,改善系统整体暂态电压稳定水平。对于优化特高压直流投运后湖南电网动态无功配置,提高暂态电压稳定水平具有重要意义。展开更多
Transient stability assessment(TSA)is of great importance in power system operation and control.One of the usual tasks in TSA is to estimate the critical clearing time(CCT)of a given fault under the given network topo...Transient stability assessment(TSA)is of great importance in power system operation and control.One of the usual tasks in TSA is to estimate the critical clearing time(CCT)of a given fault under the given network topology and pre-fault power flow.Data-driven methods try to obtain models describing the mapping between these factors and the CCT from a large number of samples.However,the influence of network topology on CCT is hard to be analyzed and is often ignored,which makes the models inaccurate and unpractical.In this paper,a novel data-driven TSA model combining Mahalanobis kernel regression and ensemble learning is proposed to deal with the problem.The model is a weighted sum of several sub-models.Each sub-model only uses the data of one topology to construct a kernel regressor.The weights are determined by both the topological similarity and numerical similarity between the samples.The similarities are decided by the parameters in Mahalanobis distance,and the parameters are to be trained.To reduce the model complexity,sub-models within the same topology category share the same parameters.When estimating CCT,the model uses not only the sub-model which the sample topology belongs to,but also other sub-models.Thus,it avoids the problem that there may be too few data under some topologies.It also efficiently utilizes information of data under all the topologies.Moreover,its decision-making process is clear and understandable,and an effective training algorithm is also designed.Test results on both the IEEE 10-machine 39-bus and a real system verify the effectiveness of the proposed model.展开更多
文摘This paper proposes a new Initial CCT (Critical Clearing Time) estimation method using a hybrid neural network composed of iRprop (Improving the Resilient back PROPation Algorithm) and RAN (Resource Allocation Network). In transient stability study, CCT evaluation is very important but time consuming due to the fact it needs many iteration of time domain simulations gradually increasing the fault clearing time. The key to reduce the required computing time in this process is to find accurate initial estimation of CCT by a certain handy method before going to the iterative stage. As one of the strongest candidates of this handy method is the utilization of the pattern recognition ability of neural networks, which enable us to jump to a close estimation of the real CCT without any heavy computing burden. This paper proposes a new hybrid neural network which is a combination of the well-known iRprop and RAN. In the proposed method, the outputs of the hidden units of RAN are modified by multiplying the contribution factors calculated by an additional iRprop network. Numerical studies are done using two different test systems for the purpose of confirming the validity of the proposal. The result of the proposed method is the best. Properly evaluating the contribution of each input to the hidden units, the estimation error obtained by the proposed method is improved further than the original RAN based estimation.
文摘The utilization of wind generation equipment, such as DFIGs （double fed induction generators）, interconnected to islanded power generation and distribution systems is investigated in order to determine their effects on the overall system operating characteristics and stability. The use of a stable power station （with high speed machines） will be critical in achieving fast and reliable transient response to network events, in particular, when large transient loads are expected on a continuous basis, i.e., industrial mining and mineral processing equipment. Simulation results of this paper assist in understanding how small power stations and wind generation equipment respond to large transients in an islanded network. In particular, detailed simulations and analyses will be presented on impacts of distributed wind generation units （1.5 MW DF1G） on the stability of a small weak network. The novelty of this paper is on detailed analyses and simulation of weak networks with interconnects DFIG＇s including their impacts on system stability under various transient operating conditions.
文摘Limited resources are available on the application of wind generation systems interconnected to weak powemetworks. With the need to further interface DG （distributed generation） including WG （wind generation） to weak networks, it is necessary to establish a means of determining what is the most efficient quantity of WG that can be applied in order to maintain stability in the network. This paper establishes a concept that can be applied to weak networks. The aim is to estimate how much WG can be installed on weak networks as well as establishing characteristic responses to generation loss without and with faulted conditions. The main contribution is a thorough understanding of weak network limitation proved to be the most critical parameter in these calculations.
文摘The performance of DFIG-based wind generation systems that interconnected to solid networks is well understood and prevalent in Europe and North America. However, the application of these renewable generating stations to weak network has been examined in very limited occasions. Weak networks have a range of limitations from system capacities to CFCT restrictions which would need to be well understood prior to wind energy integration. Of particular interest would be how much wind generation could be integrated into a weak network prior to increasing voltage and frequency stability issues brought about by penetration issues. This paper introduces a simple and practical approach based on the equal area criteria to investigate the stability of weak networks. Simulation results that are presented to show the proposed approach is a viable preliminary assessment tool to determine system stability on weak networks with wind power penetration.
文摘提出一种基于复合神经网络的暂态稳定评估与故障临界切除时间(CCT)裕度预测新方法,它将概率神经网络(PNN)和径向基函数(RBF)网络组合使用,充分利用两者各自的优点,以提高暂态稳定评估能力和CCT裕度预测能力。该方法首先利用PNN进行暂态事故场景分类,分类时充分考虑了相邻故障样本类型重叠的影响;进一步采用RBF网络对分类结果进行裕度预测;最后,通过自检和校正以提高预测精度。利用New England 39节点系统,通过与反向传播(BP)神经网络、RBF神经网络等方法的比较,证明了本文方法的优越性。
文摘多年来湖南电网电压暂态稳定问题一直困扰电网运行,随着±800 k V酒泉—湖南特高压直流投运,电压暂态问题将进一步加剧。本文提出了基于电压稳定极限测试方法,确定湖南电网暂态电压薄弱环节,并通过仿真在系统暂态电压薄弱点增加动态无功补偿装置,证明能显著提高系统极限切除时间,改善系统整体暂态电压稳定水平。对于优化特高压直流投运后湖南电网动态无功配置,提高暂态电压稳定水平具有重要意义。
基金supported by National Key R&D Program of China(No.2018YFB0904500)State Grid Corporation of China(No.SGLNDK00KJJS1800236)
文摘Transient stability assessment(TSA)is of great importance in power system operation and control.One of the usual tasks in TSA is to estimate the critical clearing time(CCT)of a given fault under the given network topology and pre-fault power flow.Data-driven methods try to obtain models describing the mapping between these factors and the CCT from a large number of samples.However,the influence of network topology on CCT is hard to be analyzed and is often ignored,which makes the models inaccurate and unpractical.In this paper,a novel data-driven TSA model combining Mahalanobis kernel regression and ensemble learning is proposed to deal with the problem.The model is a weighted sum of several sub-models.Each sub-model only uses the data of one topology to construct a kernel regressor.The weights are determined by both the topological similarity and numerical similarity between the samples.The similarities are decided by the parameters in Mahalanobis distance,and the parameters are to be trained.To reduce the model complexity,sub-models within the same topology category share the same parameters.When estimating CCT,the model uses not only the sub-model which the sample topology belongs to,but also other sub-models.Thus,it avoids the problem that there may be too few data under some topologies.It also efficiently utilizes information of data under all the topologies.Moreover,its decision-making process is clear and understandable,and an effective training algorithm is also designed.Test results on both the IEEE 10-machine 39-bus and a real system verify the effectiveness of the proposed model.
