This paper proposes a critical clearing time (CCT) estimation method by the domain of attraction (DA) of a state-reduction model of power systems using sum of squares (SOS) programming. By exploiting the property of t...This paper proposes a critical clearing time (CCT) estimation method by the domain of attraction (DA) of a state-reduction model of power systems using sum of squares (SOS) programming. By exploiting the property of the Jacobian matrix and the structure of the boundary of the DA, it is found the DA of the state-reduction model and that of the full model of a power system are topological isomorphism. There are one-to-one correspondence relationships between the number of equilibrium points, the type of equilibrium points, and solutions of the two system models. Based on these findings, an expanding interior algorithm is proposed with SOS programming to estimate the DA of the state-reduction model. State trajectories of the full model can be transformed to those of the state-reduction model by orthogonal or equiradius projection. In this way, CCT of a grid fault is estimated with the DA of the state-reduction model. The calculational burden of SOS programming in the DA estimation using the state-reduction model is rather small compared with using the full model. Simulation results show the proposed expanding interior algorithm is able to provide a tight estimation of DA of power systems with higher accuracy and lower time costs.展开更多
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
随着面向高比例可再生能源新型电力系统的转型,系统运行特性日趋复杂。暂态功角稳定(transientangle stability,TAS)与暂态电压稳定(transient voltage stability,TVS)问题相互耦合且频发,为系统安全稳定评估带来严峻挑战。研究首先采...随着面向高比例可再生能源新型电力系统的转型,系统运行特性日趋复杂。暂态功角稳定(transientangle stability,TAS)与暂态电压稳定(transient voltage stability,TVS)问题相互耦合且频发,为系统安全稳定评估带来严峻挑战。研究首先采用变步长二分法通过调用PSASP从时间维度上构建了暂态电压与暂态功角的稳定边界。研究了不同故障位置、感应电动机占比、负荷率对稳定边界的影响并依托边界确定主导失稳模式。其次提出一种基于注意力机制与一维卷积神经网络融合的电力系统功角稳定及电压稳定裕度评估的新方法。该方法直接面向测量数据,将节点稳态与暂态运行的电压幅值、有功功率、无功功率数据作为输入特征,节省了数据处理时间。通过一维卷积神经网络构建输入特征与极限切除时间的映射,利用注意力机制进一步提高了模型预测效果。通过新英格兰IEEE39节点系统进行分析验证,结果表明该方法可以实现暂态安全裕度的快速评估且具有较高的预测精度。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
基金supported in part by Science and Technology Projects in Guangzhou under Grant No.202102020221Young Elite Scientists Sponsorship Program by CSEE under Grant No.CSEE-YESS-2018007State Key Program of National Natural Science Foundation of China under Grant No.U1866210.
文摘This paper proposes a critical clearing time (CCT) estimation method by the domain of attraction (DA) of a state-reduction model of power systems using sum of squares (SOS) programming. By exploiting the property of the Jacobian matrix and the structure of the boundary of the DA, it is found the DA of the state-reduction model and that of the full model of a power system are topological isomorphism. There are one-to-one correspondence relationships between the number of equilibrium points, the type of equilibrium points, and solutions of the two system models. Based on these findings, an expanding interior algorithm is proposed with SOS programming to estimate the DA of the state-reduction model. State trajectories of the full model can be transformed to those of the state-reduction model by orthogonal or equiradius projection. In this way, CCT of a grid fault is estimated with the DA of the state-reduction model. The calculational burden of SOS programming in the DA estimation using the state-reduction model is rather small compared with using the full model. Simulation results show the proposed expanding interior algorithm is able to provide a tight estimation of DA of power systems with higher accuracy and lower time costs.
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.
文摘随着面向高比例可再生能源新型电力系统的转型,系统运行特性日趋复杂。暂态功角稳定(transientangle stability,TAS)与暂态电压稳定(transient voltage stability,TVS)问题相互耦合且频发,为系统安全稳定评估带来严峻挑战。研究首先采用变步长二分法通过调用PSASP从时间维度上构建了暂态电压与暂态功角的稳定边界。研究了不同故障位置、感应电动机占比、负荷率对稳定边界的影响并依托边界确定主导失稳模式。其次提出一种基于注意力机制与一维卷积神经网络融合的电力系统功角稳定及电压稳定裕度评估的新方法。该方法直接面向测量数据,将节点稳态与暂态运行的电压幅值、有功功率、无功功率数据作为输入特征,节省了数据处理时间。通过一维卷积神经网络构建输入特征与极限切除时间的映射,利用注意力机制进一步提高了模型预测效果。通过新英格兰IEEE39节点系统进行分析验证,结果表明该方法可以实现暂态安全裕度的快速评估且具有较高的预测精度。
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。
