CLC number: TP39; TM74
On-line Access: 2024-08-27
Received: 2023-10-17
Revision Accepted: 2024-05-08
Crosschecked: 2019-06-11
Cited: 0
Clicked: 6989
Hui-fang Wang, Chen-yu Zhang, Dong-yang Lin, Ben-teng He. An artificial intelligence based method for evaluating power grid node importance using network embedding and support vector regression[J]. Frontiers of Information Technology & Electronic Engineering, 2019, 20(6): 816-828.
@article{title="An artificial intelligence based method for evaluating power grid node importance using network embedding and support vector regression",
author="Hui-fang Wang, Chen-yu Zhang, Dong-yang Lin, Ben-teng He",
journal="Frontiers of Information Technology & Electronic Engineering",
volume="20",
number="6",
pages="816-828",
year="2019",
publisher="Zhejiang University Press & Springer",
doi="10.1631/FITEE.1800146"
}
%0 Journal Article
%T An artificial intelligence based method for evaluating power grid node importance using network embedding and support vector regression
%A Hui-fang Wang
%A Chen-yu Zhang
%A Dong-yang Lin
%A Ben-teng He
%J Frontiers of Information Technology & Electronic Engineering
%V 20
%N 6
%P 816-828
%@ 2095-9184
%D 2019
%I Zhejiang University Press & Springer
%DOI 10.1631/FITEE.1800146
TY - JOUR
T1 - An artificial intelligence based method for evaluating power grid node importance using network embedding and support vector regression
A1 - Hui-fang Wang
A1 - Chen-yu Zhang
A1 - Dong-yang Lin
A1 - Ben-teng He
J0 - Frontiers of Information Technology & Electronic Engineering
VL - 20
IS - 6
SP - 816
EP - 828
%@ 2095-9184
Y1 - 2019
PB - Zhejiang University Press & Springer
ER -
DOI - 10.1631/FITEE.1800146
Abstract: The identification of important nodes in a power grid has considerable benefits for safety. Power networks vary in many aspects, such as scale and structure. An index system can hardly cover all the information in various situations. Therefore, the efficiency of traditional methods using an index system is case-dependent and not universal. To solve this problem, an artificial intelligence based method is proposed for evaluating power grid node importance. First, using a network embedding approach, a feature extraction method is designed for power grid nodes, considering their structural and electrical information. Then, for a specific power network, steady-state and node fault transient simulations under various operation modes are performed to establish the sample set. The sample set can reflect the relationship between the node features and the corresponding importance. Finally, a support vector regression model is trained based on the optimized sample set for the later online use of importance evaluation. A case study demonstrates that the proposed method can effectively evaluate node importance for a power grid based on the information learned from the samples. Compared with traditional methods using an index system, the proposed method can avoid some possible bias. In addition, a particular sample set for each specific power network can be established under this artificial intelligence based framework, meeting the demand of universality.
[1]Albert R, Albert I, Nakarado GL, 2004. Structural vulnerability of the North American power grid. Phys Rev E, 69(2): 025103(R).
[2]Angra S, Ahuja S, 2017. Machine learning and its applications: a review. Int Conf on Big Data Analytics and Computational Intelligence, p.57-60.
[3]Arianos S, Bompard E, Carbone, et al., 2009. Power grid vulnerability: a complex network approach. Chaos, 19(1): 013119.
[4]Bai JL, Liu TQ, Cao GY, et al., 2008. A survey on vulnerability assessment method for power system. Power Syst Technol, 32(S2):26-30 (in Chinese).
[5]Basak D, Pal S, Patranabis DC, 2007. Support vector regression. Neur Inform Process Lett Rev, 11(10):203-224.
[6]Browne MW, 2000. Cross-validation methods. J Math Psychol, 44(1):108-132.
[7]Cai ZX, Wang XH, Ren XN, 2012. A review of complex network theory and its application in power systems. Power Syst Technol, 36(11):114-121 (in Chinese).
[8]Chen WZ, Zhang Y, Li XM, 2015. Network representation learning. Big Data Res, 1(3):8-22 (in Chinese).
[9]da Silva AML, Jardim JL, de Lima LR, et al., 2016. A method for ranking critical nodes in power networks including load uncertainties. IEEE Trans Power Syst, 31(2):1341- 1349.
[10]Fan WL, Ping H, Liu ZG, 2016. Multi-attribute node importance evaluation method based on Gini-coefficient in complex power grids. IET Gener Transm Distrib, 10(9): 2027-2034.
[11]Friedman JH, 2002. Stochastic gradient boosting. Comput Stat Data Anal, 38(4):367-378.
[12]Grover A, Leskovec J, 2016. Node2vec: scalable feature learning for networks. Proc 22nd ACM SIGKDD Int Conf on Knowledge Discovery and Data Mining, p.855-864.
[13]Jović A, Brkić K, Bogunović N, 2015. A review of feature selection methods with applications. Proc 38th Int Convention on Information and Communication Technology, Electronics and Microelectronics, p.1200-1205.
[14]Ju WY, Li YH, 2012. Identification of critical lines and nodes in power grid based on maximum flow transmission contribution degree. Autom Electr Power Syst, 36(2): 6-12 (in Chinese).
[15]Li CB, Liang JZ, 2009. A novel method of power grid differential planning. Autom Electr Power Syst, 33(24):11-15 (in Chinese).
[16]Li CB, Liu WC, Cao YJ, et al., 2014. Method for evaluating the importance of power grid nodes based on Pagerank algorithm. IET Gener Transm Distrib, 8(11):1843-1847.
[17]Lin ZZ, Wen FS, Wang HF, et al., 2017. CRITIC-based node importance evaluation in skeleton-network reconfiguration of power grids. IEEE Trans Circ Syst II, 65(2):206- 210.
[18]Nasiruzzaman ABM, Pota HR, 2011. Critical node identification of smart power system using complex network framework based centrality approach. North American Power Symp, p.1-6.
[19]Pan XD, Wu J, Liu DC, et al., 2014. A method for constructing core backbone grid in differential planning based on importance degrees of components. Autom Electr Power Syst, 38(19):40-46 (in Chinese).
[20]Pedregosa F, Varoquaux G, Gramfort A, et al., 2011. Scikit- Learn: machine learning in Python. J Mach Learn Res, 12:2825-2830.
[21]Perozzi B, Al-Rfou R, Skiena S, 2014. DeepWalk: online learning of social representations. Proc 20th ACM SIGKDD Int Conf on Knowledge Discovery and Data Mining, p.701-710.
[22]Ross S M, 1983. Stochastic Processes. Wiley, New York, SUA.
[23]Tan YD, Li XR, Cai Y, et al., 2014. Critical node identification for complex power grid based on electrical distance. Proc CSEE, 34(1):146-152 (in Chinese).
[24]Vanfretti L, Milano F, 2007. Application of the PSAT, an open source software, for educational and research purposes. IEEE Power Engineering Society General Meeting, p.24- 28.
[25]Wang B, Fang BW, Wang YJ, et al., 2016. Power system transient stability assessment based on big data and the core vector machine. IEEE Trans Smart Grid, 7(5):2561-2570.
[26]Wang HF, Shan ZB, Ying GL, et al., 2017. Evaluation method of node importance for power grid considering inflow and outflow power. J Mod Power Syst Clean Energy, 5(5): 696-703.
[27]Wang XF, Song YH, Irving M, 2008. Modern Power Systems Analysis. Springer, Boston, USA.
[28]Xu L, Wang XL, Wang XF, 2010. Cascading failure mechanism in power grid based on electric betweenness and active defence. Proc CSEE, 30(13):61-68 (in Chinese).
[29]Xu LX, Liu JY, Liu Y, et al., 2014. Node importance classified comprehensive assessment. Proc CSEE, 34(10):1609- 1617 (in Chinese).
[30]Xu Y, Dong ZY, Meng K, et al., 2011. Real-time transient stability assessment model using extreme learning machine. IET Gener Transm Distrib, 5(3):314-322.
[31]Yang C, Liu ZY, Zhao DL, et al., 2015. Network representation learning with rich text information. Proc 24th Int Conf on Artificial Intelligence, p.2111-2117.
[32]Zimmerman RD, Murillo-Sanchez CE, Thomas RJ, 2011. MATPOWER: steady-state operations, planning, and analysis tools for power systems research and education. IEEE Trans Power Syst, 26(1):12-19.
Open peer comments: Debate/Discuss/Question/Opinion
<1>