Data-driven Feature Analysis in Control Design for Series-Compensated Transmission Systems

Li, Xinya; Fan, Xiaoyuan; Ren, Huiying; Hou, Zhangshuan; Huang, Qiuhua; Wang, Song; Ciniglio, Orlando

doi:10.1109/TPWRS.2019.2912711

Title: Data-driven Feature Analysis in Control Design for Series-Compensated Transmission Systems

Full Record
Other Related Research

Abstract

One challenge in power-system control designs is the gap between numerical model-based analysis and complex real-world power systems. With increased data and measurements being collected from power systems, data-driven analysis (e.g., machine learning) may provide an alternative approach to reveal hidden information through learning from the real system data, and provide insights for better control scheme design during the utility planning process. Data-driven feature analysis was performed to evaluate the relationships between series compensation, power generation, and path flows in a real transmission system, as well as temporal patterns. The main data-driven analysis methods, including statistical cross-correlation, multinomial logistical regression, and classification and regression trees, were integrated for feature selection and developing predictive models of series compensation. Analysis results demonstrated the effectiveness of the proposed methodology in feature analysis and the potential to help improve power-system control scheme design.

Authors:

Li, Xinya ^[1]; Fan, Xiaoyuan ^[1]; Ren, Huiying ^[1]; Hou, Zhangshuan ^[1]; Huang, Qiuhua ^[1]; Wang, Song ^[2]; Ciniglio, Orlando ^[3]

Pacific Northwest National Lab. (PNNL), Richland, WA (United States)
PacifiCorp, Portland, OR (United States)
Idaho Power Company, Boise, ID (United States)

Publication Date:: Mon Apr 22 00:00:00 EDT 2019

Research Org.:: Pacific Northwest National Lab. (PNNL), Richland, WA (United States)

Sponsoring Org.:: USDOE Office of Electricity (OE)

OSTI Identifier:: 1509840

Report Number(s):: PNNL-SA-139624
Journal ID: ISSN 0885-8950

Grant/Contract Number:: AC05-76RL01830

Resource Type:: Accepted Manuscript

Journal Name:: IEEE Transactions on Power Systems

Additional Journal Information:: Journal Volume: 34; Journal Issue: 4; Journal ID: ISSN 0885-8950

Publisher:: IEEE

Country of Publication:: United States

Language:: English

Subject:: 42 ENGINEERING; classification and regression trees, feature selection, machine learning, multinomial logistic regression, series compensation

Citation Formats


                    Li, Xinya, Fan, Xiaoyuan, Ren, Huiying, Hou, Zhangshuan, Huang, Qiuhua, Wang, Song, and Ciniglio, Orlando. Data-driven Feature Analysis in Control Design for Series-Compensated Transmission Systems.  United States: N. p., 2019. 
Web.  doi:10.1109/TPWRS.2019.2912711.

Copy to clipboard


                    Li, Xinya, Fan, Xiaoyuan, Ren, Huiying, Hou, Zhangshuan, Huang, Qiuhua, Wang, Song, & Ciniglio, Orlando. Data-driven Feature Analysis in Control Design for Series-Compensated Transmission Systems.  United States.  https://doi.org/10.1109/TPWRS.2019.2912711

Copy to clipboard


                    Li, Xinya, Fan, Xiaoyuan, Ren, Huiying, Hou, Zhangshuan, Huang, Qiuhua, Wang, Song, and Ciniglio, Orlando. Mon .  
"Data-driven Feature Analysis in Control Design for Series-Compensated Transmission Systems".  United States.  https://doi.org/10.1109/TPWRS.2019.2912711.  https://www.osti.gov/servlets/purl/1509840.

Copy to clipboard


                    
@article{osti_1509840,

  title        = {Data-driven Feature Analysis in Control Design for Series-Compensated Transmission Systems},

  author       = {Li, Xinya and Fan, Xiaoyuan and Ren, Huiying and Hou, Zhangshuan and Huang, Qiuhua and Wang, Song and Ciniglio, Orlando},

  abstractNote = {One challenge in power-system control designs is the gap between numerical model-based analysis and complex real-world power systems. With increased data and measurements being collected from power systems, data-driven analysis (e.g., machine learning) may provide an alternative approach to reveal hidden information through learning from the real system data, and provide insights for better control scheme design during the utility planning process. Data-driven feature analysis was performed to evaluate the relationships between series compensation, power generation, and path flows in a real transmission system, as well as temporal patterns. The main data-driven analysis methods, including statistical cross-correlation, multinomial logistical regression, and classification and regression trees, were integrated for feature selection and developing predictive models of series compensation. Analysis results demonstrated the effectiveness of the proposed methodology in feature analysis and the potential to help improve power-system control scheme design.},

  doi          = {10.1109/TPWRS.2019.2912711},

  journal      = {IEEE Transactions on Power Systems},

  number       = 4,

  volume       = 34,

  place        = {United States},

  year         = {Mon Apr 22 00:00:00 EDT 2019},

  month        = {Mon Apr 22 00:00:00 EDT 2019}

}

Copy to clipboard

Journal Article:

Free Publicly Available Full Text

Accepted Manuscript (DOE)

Publisher's Version of Record

https://doi.org/10.1109/TPWRS.2019.2912711

Other availability

Search WorldCat to find libraries that may hold this journal

Citation Metrics:

Cited by: 3 works

Citation information provided by
Web of Science

Save / Share:

Export Metadata

Save to My Library

Similar Records in DOE PAGES and OSTI.GOV collections:

Automated System-wide Event Detection and Classification Using Machine Learning on Synchrophasor Data

Conference Kezunovic, Mladen ; Obradovic, Zoran ; Hu, Yi

As the number of phasor measurement units (PMUs) deployed in a power system increases, and their data volume streamed to the control canter intensifies, operators are facing challenges related to the analysis of such data, which need to be observed and responded to as the measurements are displayed in the Control Room. Humans are generally unable to process such large amount of data efficiently and rapidly. There is an apparent need for automated ways to analyze the data, extract actionable information about occurrence of specific events, and characterize the events quickly and cost effectively. This paper discusses the use ofmore »« less
https://doi.org/10.2172/1891316

Full Text Available
GRAFTING: FAST, INCREMENTAL FEATURE SELECTION USING GRADIENT DESCENT IN FUNCTION SPACE

Journal Article PERKINS, SIMON J ; LACKER, KEVIN ; THEILER, JAMES - Journal of Machine Learning Research

We present a novel and flexible approach to the problem of feature selection, called grafting. Rather than considering feature selection as separate from learning, grafting treats the selection of suitable features as an integral part of learning a predictor in a regularized learning framework. To make this regularized learning process sufficiently fast for large scale problems, grafting operates in an incremental iterative fashion, gradually building up a feature set while training a predictor model using gradient descent. At each iteration, a fast gradient-based heuristic is used to quickly assess which feature is most likely to improve the existing model, thatmore »« less
Exploratory concepts on control of variable series compensation in transmission systems to improve damping of intermachine/system oscillations

Journal Article Mello, F.P. de - IEEE Transactions on Power Systems (Institute of Electrical and Electronics Engineers); (United States)

Of much current interest is the application of power electronics in ac transmission systems notably to control power flow in series elements through variable series compensation. Principles of control of such variable series compensation to damp intermachine and intersystem oscillations are developed based on the concept of reactance with dynamic characteristics similar to reactance of synchronous machines. It is shown that the measured through-power in series branches is a logical source of local control intelligence for modulation of series compensation in such branches. Nonlinear control logic schemes developed from linear analysis are demonstrated in simple examples of single and multimachinemore »« less
https://doi.org/10.1109/59.317552
Novel Application of Machine Learning Techniques for Rapid Source Apportionment of Aerosol Mass Spectrometer Datasets

Journal Article Pande, Paritosh ; Shrivastava, Manish ; Shilling, John E. ; ... - ACS Earth and Space Chemistry

In this work, we apply machine learning approaches sparse multinomial logistic regression to classify aerosol mass spectrometer (AMS) unit mass resolution (UMR) data followed by an ensemble regression technique for source apportionment of organic aerosols (OA). The classifier was trained on 60 well characterized laboratory and positive matrix factorization (PMF) deconvolved reference spectra to identify eight OA types. These include four laboratory-derived secondary organic aerosol (SOA) spectra, which include isoprene photooxidation SOA, isoprene epoxydiols (IEPOX) SOA, a monoterpene SOA type that includes a-pinene and ß-pinene SOA, and aromatic SOA from oxidation of naphthalene and m-xylene precursors, as well as PMFmore »« less
https://doi.org/10.1021/acsearthspacechem.1c00344

Full Text Available
AGGREGATE: dAta-driven modelinG preservinG contRollable dEr for outaGe mAnagemenT and rEsiliency (Final Report)

Technical Report Srivastava, Anurag K. ; Liu, Chen-Ching ; Dubey, Anamika ; ...

The AGGREGATE project team successfully developed and validated various modules for outage management. Brief summaries of each module are provided to showcase their strength for outage management and restoration for a distribution system with a high penetration of connected distribution energy resources (DERs). In recent years, inverter-based DERs have been widely deployed in distribution system. A most of behind-the-meter (BTM) solar power generation is not visible to the utility. The data-driven DER and load estimation modules are using machine learning (ML) and artificial intelligence (AI) to manage this issue, which provides an opportunity for distribution system operators (DSOs) to operatemore »« less
https://doi.org/10.2172/1828282

Full Text Available

Similar Records