Abstract
This paper presents a novel approach for Voltage Stability Margin (VSM) estimation that combines a Kernel Extreme Learning Machine (KELM) with a Mean-Variance Mapping Optimization (MVMO) algorithm. Since the performance of a KELM depends on a proper parameter selection, the MVMO is used to optimize such task. In the proposed MVMO-KELM model the inputs and output are the magnitudes of voltage phasors and the VSM index, respectively. A Monte Carlo simulation was implemented to build a data base for the training and validation of the model. The data base considers different operative scenarios for three type of customers (residential commercial and industrial) as well as N-1 contingencies. The proposed MVMO-KELM model was validated with the IEEE 39 bus power system comparing its performance with a support vector machine (SVM) and an Artificial Neural Network (ANN) approach. Results evidenced a better performance of the proposed MVMO-KELM model when compared to such techniques. Furthermore, the higher robustness of the MVMO-KELM was also evidenced when considering noise in the input data.
Highlights
The competitive tendency of deregulated electricity markets, along with limitations in network expansion planning due to several factors that include environmental constraints and investment delays have caused electric power systems to often perform very close to their operative and stability limits
The proposed method improves the performance of the Voltage Stability Margin (VSM) estimation, but increases the training times for the
The optimum parameters that must be identified for support vector regression (SVR) are ε, C and γ according to equation (2); while the optimum parameters to identify for Kernel Extreme Learning Machine (KELM) are C and γ
Summary
The competitive tendency of deregulated electricity markets, along with limitations in network expansion planning due to several factors that include environmental constraints and investment delays have caused electric power systems to often perform very close to their operative and stability limits One of these relates to voltage stability, which is violated when the power system no longer has the capacity to maintain stable voltages in all or some of its buses after a disturbance has taken place. The ever-growing integration of intermittent renewable energies and the development of smart grids have increased the complexity of power systems operation and planning In this context, conventional methods of voltage stability based on offline studies are not up to the challenges that are facing current power systems [4]; system operators must adopt new methods to monitor and evaluate voltage stability near real time. Monitoring of these systems is essential to guarantee a safe operation, and it must be carried out in real time to reach a high accuracy [5,6,7]
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 call
