Abstract
With the increase of power load demand and the complexity of power grid structure, the problem of voltage stability is becoming more serious, and it is urgent to study the countermeasures. In this paper, a DNN-based distributed voltage stability online monitoring method for large-scale power grids is proposed. Unlike the traditional load margin methods, the proposed method uses a local index load impedance modulus margin (LIMM) index to determine the optimal installation locations of PMUs, which is more efficiently. Moreover, the DNN is applied to learn the nonlinear relationship between the power system operation state and its corresponding LIMM. By this way, the corresponding LIMM value can be predicted through the state variables of nodes from the installed PMUs. This method can greatly improve the calculation speed of LIMM and assess the system voltage stability level in real-time, which help the system operator to judge the operating state and take measures in time. Finally, the proposed method is tested on the 14-bus system and then on the 118-bus system respectively, and the simulation results verify the effectiveness and correctness of the proposed method.
Highlights
With the improvement of intelligent level of the electrical power system and the access of various distributed generation, the voltage stability problem of power system becomes more serious
The computational performance is another advantage of this proposed method, which would be more obvious in the large-scale power system
This paper proposes a DNN based distributed voltage stability online monitoring method for large scale power grid
Summary
With the improvement of intelligent level of the electrical power system and the access of various distributed generation, the voltage stability problem of power system becomes more serious. The load margin index is a type of the global index, which cannot give the weak bus information (Wang et al, 2016; Malbasa et al, 2017). To address this problem, an artificial neural network (ANN) method is proposed to quickly estimate the load margin of power system in (Zhou et al, 2010). The ANN-based method requires a large number of CPF calculations in different cases to form the training sample set, which leads to the low efficiency of the whole scheme. In (Sunitha et al, 2013), the PMU data and the deep neural
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
