Using a Support Vector Machine (SVM) to Improve Generalization Ability of Load Model Parameters
Abstract
Load modeling plays an important role in power system stability analysis and planning studies. The parameters of load models may experience variations in different application situations. Choosing appropriate parameters is critical for dynamic simulation and stability studies in power system. This paper presents a method to select the parameters with good generalization ability based on a given large number of available parameters that have been identified from dynamic simulation data in different scenarios. Principal component analysis is used to extract the major features of the given parameter sets. Reduced feature vectors are obtained by mapping the given parameter sets into principal component space. Then support vectors are found by implementing a classification problem. Load model parameters based on the obtained support vectors are built to reflect the dynamic property of the load. All of the given parameter sets were identified from simulation data based on the New England 10-machine 39-bus system, by taking into account different situations, such as load types, fault locations, fault types, and fault clearing time. The parameters obtained by support vector machine have good generalization capability, and can represent the load more accurately in most situations.
- Authors:
- Publication Date:
- Research Org.:
- Pacific Northwest National Lab. (PNNL), Richland, WA (United States)
- Sponsoring Org.:
- USDOE
- OSTI Identifier:
- 977335
- Report Number(s):
- PNNL-SA-62314
830403000; TRN: US201013%%474
- DOE Contract Number:
- AC05-76RL01830
- Resource Type:
- Conference
- Resource Relation:
- Conference: 2009 IEEE/PES Power Systems Conference & Exhibition (PSCE)
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 24 POWER TRANSMISSION AND DISTRIBUTION; CLASSIFICATION; PLANNING; POWER SYSTEMS; SIMULATION; STABILITY; USA; VECTORS; Load modeling, parameter identification, principal components analysis, support vector machine, fault location, fault type, load type, clearing time, generalization
Citation Formats
Ma, Jian, Dong, Zhao Yang, and Zhang, Pei. Using a Support Vector Machine (SVM) to Improve Generalization Ability of Load Model Parameters. United States: N. p., 2009.
Web. doi:10.1109/PSCE.2009.4839969.
Ma, Jian, Dong, Zhao Yang, & Zhang, Pei. Using a Support Vector Machine (SVM) to Improve Generalization Ability of Load Model Parameters. United States. https://doi.org/10.1109/PSCE.2009.4839969
Ma, Jian, Dong, Zhao Yang, and Zhang, Pei. 2009.
"Using a Support Vector Machine (SVM) to Improve Generalization Ability of Load Model Parameters". United States. https://doi.org/10.1109/PSCE.2009.4839969.
@article{osti_977335,
title = {Using a Support Vector Machine (SVM) to Improve Generalization Ability of Load Model Parameters},
author = {Ma, Jian and Dong, Zhao Yang and Zhang, Pei},
abstractNote = {Load modeling plays an important role in power system stability analysis and planning studies. The parameters of load models may experience variations in different application situations. Choosing appropriate parameters is critical for dynamic simulation and stability studies in power system. This paper presents a method to select the parameters with good generalization ability based on a given large number of available parameters that have been identified from dynamic simulation data in different scenarios. Principal component analysis is used to extract the major features of the given parameter sets. Reduced feature vectors are obtained by mapping the given parameter sets into principal component space. Then support vectors are found by implementing a classification problem. Load model parameters based on the obtained support vectors are built to reflect the dynamic property of the load. All of the given parameter sets were identified from simulation data based on the New England 10-machine 39-bus system, by taking into account different situations, such as load types, fault locations, fault types, and fault clearing time. The parameters obtained by support vector machine have good generalization capability, and can represent the load more accurately in most situations.},
doi = {10.1109/PSCE.2009.4839969},
url = {https://www.osti.gov/biblio/977335},
journal = {},
number = ,
volume = ,
place = {United States},
year = {Fri Apr 24 00:00:00 EDT 2009},
month = {Fri Apr 24 00:00:00 EDT 2009}
}