Skip to main content
Springer Nature Link
Log in

Prediction of electrical power disturbances using machine learning techniques

  • Original Research
  • Published:
Journal of Ambient Intelligence and Humanized Computing Aims and scope Submit manuscript

Abstract

Electrical power disturbances have negative social, economic, and political impacts. They can lead to catastrophic results that may end with blackouts. Increased understanding, analysis, and prediction of electrical disturbances can help to avoid the occurrence of major disturbances or at least to limit their consequences. This paper develops a system that predicts the type of electrical disturbances using machine learning techniques (MLTs). The proposed system is used for features selection and classification of an open source electrical disturbances dataset available online. Ant colony optimization is used for the features selection and 5 MLTs are adopted for classification; k-nearest neighbor, artificial neural networks, decision tree, logistic regression, and naïve bayes. The findings and results showed that the proposed system has the ability to efficiently classify electrical disturbances with a classification accuracy ranging from 74.57 to 86.11% depending on the classifier used.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

References

  • Akaber P, Moussa B, Debbabi M, Assi C (2016) Cascading link failure analysis in interdependent networks for maximal outages in smart grid. In: Smart grid communications (SmartGridComm), 2016 IEEE international conference on, IEEE, Sydney, Australia

  • Amin M (2004) North American electricity infrastructure: system security, quality, reliability, availability, and efficiency challenges and their societal impacts

  • Bompard E, Estebsari A, Huang T, Fulli G (2016) A framework for analyzing cascading failure in large interconnected power systems: a post-contingency evolution simulator. Int J Electr Power Energy Syst 81:12–21

    Article  Google Scholar 

  • Carpaneto E, Chicco G (2008) Distribution system minimum loss reconfiguration in the hyper-cube ant colony optimization framework. Electr Power Syst Res 78(12):2037–2045

    Article  Google Scholar 

  • Chen J, Thorp J, Parashar M (2001) Analysis of electric power system disturbance data. In: hicss, IEEE, Maui, Hawaii, USA. https://dblp.org/rec/conf/hicss/ChenTP01

  • Church C, Morsi WG, El-Hawary M, Diduch C, Chang L (2011) Voltage collapse detection using ant colony optimization for smart grid applications. Electr Power Syst Res 81(8):1723–1730

    Article  Google Scholar 

  • Coello CC, Dehuri S, Ghosh S (2009) Swarm intelligence for multi-objective problems in data mining. Springer, Berlin

    Book  Google Scholar 

  • Cornforth D (2009a) Applications of data mining to time series of electrical disturbance data. In: Power & energy society general meeting, 2009. PES’09. IEEE, IEEE, Calgary, Alberta, Canada

  • Cornforth D (2009b) Long tails from the distribution of 23 years of electrical disturbance data. In: Power systems conference and exposition, 2009. PSCE’09. IEEE/PES, IEEE, Calgary, Alberta, Canada

  • Cornforth D, Nesbitt K (2013) Quality assessment of clusters of electrical disturbances: a case study. In: Industrial electronics and applications (ICIEA), 2013 8th IEEE conference on, IEEE, Melborne, Australia

  • Dehuri S, Ghosh S, Coello C (2009) An introduction to swarm intelligence for multi-objective problems. In: Swarm Intelligence for multi-objective problems in data mining. Springer, Berlin, Heidelberg, pp 1–17

    Google Scholar 

  • Dorigo M, Maniezzo V, Colorni A (1996) Ant system: optimization by a colony of cooperating agents. IEEE Trans Syst Man Cybern Part B (Cybern) 26(1):29–41

    Article  Google Scholar 

  • El Houby EM, Yassin NI, Omran S (2017) A hybrid approach from ant colony optimization and K-nearest neighbor for classifying datasets using selected features. Informatica 41(4):495–506

    MathSciNet  Google Scholar 

  • Freitas AA (2003) A survey of evolutionary algorithms for data mining and knowledge discovery. In: Ghosh A, Tsutsui S (eds) Advances in evolutionary computing. Springer, Berlin, Heidelberg, pp 819–845

    Chapter  Google Scholar 

  • Guo H, Zheng C, Iu HH-C, Fernando T (2017) A critical review of cascading failure analysis and modeling of power system. Renew Sustain Energy Rev 80:9–22

    Article  Google Scholar 

  • Han J, Kamber M, Pei J (2006) Data mining: concept and techniques, 2nd edn. Morgan Kaufman Publisher, San Francisco

    MATH  Google Scholar 

  • Hines P, Apt J, Liao H, Talukdar S (2006) The frequency of large blackouts in the United States electrical transmission system: an empirical study. In: 2nd Carnegie Mellon conference on electric power, January, CiteSeer

  • Kanan HR, Faez K, Taheri SM (2007) Feature selection using ant colony optimization (ACO): a new method and comparative study in the application of face recognition system. In: Perner P (ed) Advances in data mining. Theoretical aspects and applications. ICDM 2007. Lecture notes in computer science, vol 4597. Springer, Berlin, Heidelberg, pp 63–76

    Google Scholar 

  • Kira K, Rendell LA (1992) The feature selection problem: traditional methods and a new algorithm. Aaai 2:129–134

    Google Scholar 

  • Krishnapuram B, Carin L, Figueiredo MA, Hartemink AJ (2005) Sparse multinomial logistic regression: fast algorithms and generalization bounds. IEEE Trans Pattern Anal Mach Intell 27(6):957–968

    Article  Google Scholar 

  • Leung KM (2007) Naive Bayesian classifier. Polytechnic University Department of Computer Science/Finance and Risk Engineering, New York

    Google Scholar 

  • Li J, Dueñas-Osorio L, Chen C, Shi C (2017) AC power flow importance measures considering multi-element failures. Reliabil Eng Syst Saf 160:89–97

    Article  Google Scholar 

  • Liu YY, Yang M, Ramsay M, Li XS, Coid JW (2011) A comparison of logistic regression, classification and regression tree, and neural networks models in predicting violent re-offending. J Quantum Criminol 27(4):547–573

    Article  Google Scholar 

  • López-Cruz PL, Bielza C, Larrañaga P (2015) Directional naive Bayes classifiers. Pattern Anal Appl 18(2):225–246

    Article  MathSciNet  Google Scholar 

  • Mitzenmacher M, Upfal E (2017) Probability and computing: randomization and probabilistic techniques in algorithms and data analysis. Cambridge University Press, Cambridge

    MATH  Google Scholar 

  • Mousa A, El-Wahed WFA, Rizk-Allah R (2011) A hybrid ant colony optimization approach based local search scheme for multiobjective design optimizations. Electr Power Syst Res 81(4):1014–1023

    Article  Google Scholar 

  • Nerc D (2001) Review of selected electric system disturbances in North America, 1999 system disturbances. North American Electric Reliability Council, Princeton

    Google Scholar 

  • Nerc D (2002) Review of selected electric system disturbances in North America, 1996 System Disturbances. North American Electric Reliability Council, Princeton

    Google Scholar 

  • Nerc D (2004a) Review of selected electric system disturbances in North America, 1997 system disturbances. North American Electric Reliability Council, Princeton

    Google Scholar 

  • Nerc D (2004b) Review of selected electric system disturbances in North America, 2002 system disturbances. North American Electric Reliability Council, Princeton

    Google Scholar 

  • Ouyang M (2013) Comparisons of purely topological model, betweenness based model and direct current power flow model to analyze power grid vulnerability. Chaos Interdiscip J Nonlinear Sci 23(2):023114

    Article  MathSciNet  Google Scholar 

  • Rosario SF, Thangadurai K (2015) RELIEF: feature selection approach. Int J Innov Res Dev 4(11):218–224 (ISSN 2278–0211)

    Google Scholar 

  • Simonoff JS, Restrepo CE, Zimmerman R (2007) Risk-management and risk-analysis-based decision tools for attacks on electric power. Risk Anal 27(3):547–570

    Article  Google Scholar 

  • Tabakhi S, Moradi P, Akhlaghian F (2014) An unsupervised feature selection algorithm based on ant colony optimization. Eng Appl Artif Intell 32:112–123

    Article  Google Scholar 

  • Talukdar SN, Apt J, Ilic M, Lave LB, Morgan MG (2003) Cascading failures: survival versus prevention. Electr J 16(9):25–31

    Article  Google Scholar 

  • Veloza OP, Santamaria F (2016) Analysis of major blackouts from 2003 to 2015: classification of incidents and review of main causes. Electr J 29(7):42–49

    Article  Google Scholar 

  • Warnier M, Dulman S, Koç Y, Pauwels E (2017) Distributed monitoring for the prevention of cascading failures in operational power grids. Int J Crit Infrastruct Prot 17:15–27

    Article  Google Scholar 

  • Wu X, Kumar V, Quinlan JR, Ghosh J, Yang Q, Motoda H, McLachlan GJ, Ng A, Liu B, Philip SY (2008) Top 10 algorithms in data mining. Knowl Inf Syst 14(1):1–37

    Article  Google Scholar 

  • Xue F, Bompard E, Huang T, Jiang L, Lu S, Zhu H (2017) Interrelation of structure and operational states in cascading failure of overloading lines in power grids. Phys A 482:728–740

    Article  Google Scholar 

Download references

Acknowledgements

The authors would like to thank Professor David Cornforth of the School of Electrical Engineering and Computing, University of Newcastle, Australia for his guidance and support to this research work.

Author information

Authors and Affiliations

  1. Systems and Information Department, Engineering Research Division, National Research Centre, Dokki, Cairo, 12311, Egypt

    Shaimaa Omran & Enas M. F. El Houby

Authors
  1. Shaimaa Omran
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Enas M. F. El Houby
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Shaimaa Omran.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Omran, S., El Houby, E.M.F. Prediction of electrical power disturbances using machine learning techniques. J Ambient Intell Human Comput 11, 2987–3003 (2020). https://doi.org/10.1007/s12652-019-01440-w

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12652-019-01440-w

Keywords