Abstract
Aiming at the problem of insufficient accuracy and timeliness of transmission line parameters in the grid energy management system (EMS) parameter library, a dynamic optimization method of transmission line parameters based on grey support vector regression is proposed. Firstly, the influence of operating conditions and meteorological factors on the changes of parameters is analyzed. Based on this, the correlation quantification method of transmission line parameters is designed based on Pearson coefficient, and the influence coefficient value is obtained. Then, with the influence coefficient as the constraint condition, a method for selecting strong influence characteristics of line parameters based on improved Elastic Net is proposed. Finally, based on the grey prediction theory, a grey support vector regression (GM-SVR) parameter optimization model is constructed to realize the dynamic optimization of line parameter values under the power grid operation state. The effectiveness and feasibility of the proposed method is verified through the commissioning of the reactance parameters of the actual local loop network transmission line.
Highlights
Overhead transmission lines are the main components of the power grid
This paper proposes a new method for dynamic optimization of transmission line parameters based on grey support vector regression (GM-SVR), which effectively improves the accuracy and timeliness of transmission line parameters in the grid energy management system (EMS) parameter library
The time series changes of transmission line parameters are affected by the operating conditions of the power grid and the complex meteorological environment
Summary
Overhead transmission lines are the main components of the power grid. Various advanced calculations of the power system, such as grid modeling, state estimation, power flow calculation, and relay protection settings, require accurate transmission line parameters (Bendjabeur et al, 2019). In order to reduce the interference of low-impact features in the historical section dataset to the later model training, the correlation between transmission line parameters and each impact feature was analyzed and quantified In this stage, considering that there is little difference in significant influence rules between different circuits in the same local ring network area, and in order to avoid weakening the influence relationship between measurement features and parameters over a long time span. Through correlation analysis and quantitative results, it can be found that the absolute value of the Pearson correlation coefficient of the transmission line’s first-end active power (P), first-end current (I) and ambient temperature and reactance parameter (X) are greater than 0.7 It shows that the five transmission line measurement characteristics have a strong influence on the parameter values under the time sequence state, and they are not negligible characteristics when training the reactance value correction model. The pass rate of state estimation has been significantly improved
Sign-in/Register to view highlights & summary 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.
