Risk based security assessment of power system using generalized regression neural network with feature extraction

Abstract

A comprehensive risk based security assessment which includes low voltage, line overload and voltage collapse was presented using a relatively new neural network technique called as the generalized regression neural network (GRNN) with incorporation of feature extraction method using principle component analysis. In the risk based security assessment formulation, the failure rate associated to weather condition of each line was used to compute the probability of line outage for a given weather condition and the extent of security violation was represented by a severity function. For low voltage and line overload, continuous severity function was considered due to its ability to zoom in into the effect of near violating contingency. New severity function for voltage collapse using the voltage collapse prediction index was proposed. To reduce the computational burden, a new contingency screening method was proposed using the risk factor so as to select the critical line outages. The risk based security assessment method using GRNN was implemented on a large scale 87-bus power system and the results show that the risk prediction results obtained using GRNN with the incorporation of principal component analysis give better performance in terms of accuracy.

Keywords

generalized regression neural network / line overload / low voltage / principle component analysis / risk index / voltage collapse

References

[1] MingN., MccalleyJ. D., VittalV., TayyibT.. Online risk-based security assessment [J]. IEEE T Power Syst, 2003, 18: 258-265

[2] FeiX., McCalleyJ. D.. Power system risk assessment and control in a multiobjective framework [J]. IEEE T Power Syst, 2009, 24: 78-85

[3] HalilcevicS. S., GubinaF., GubinaA. F.. Prediction of power system security levels [J]. IEEE T Power Syst, 2009, 24: 368-377

[4] KirschenD. S., JayaweeraD., NedicD. P., AllanR. N.. A probabilistic indicator of system stress [J]. IEEE T Power Syst, 2004, 19: 1650-1657

[5] KirschenD. S., JayaweeraD.. Comparison of risk-based and deterministic security assessments [J]. IET GTD, 2007, 1: 527-533

[6] di SantoM., VaccaroA., VillacciD., ZimeoE.. A distributed architecture for online power systems security analysis [J]. IEEE Trans Ind Electron, 2004, 51: 1238-1248

[7] HuaW., McCalleyJ. D., VittalV.. Risk based voltage security assessment [J]. IEEE T Power Syst, 2000, 15: 1247-1254

[8] McCalleyJ. D., VittalV., Abi-SamraN.. An overview of risk based security assessment [J]. IEEE Power Engineering Society Summer Meeting, 1999, 171: 173-178

[9] DaiY., McCalleyJ. D., Abi-SamraN., VittalV.. Annual risk assessment for overload security [J]. IEEE T Power Syst, 2001, 16: 616-623

[10] NingC. N., HsiehC. A., HsiaoT. Y., LuC. N.. Two application examples of probabilistic risk assessment in power system operations [C]. International Conference on Probabilistic Methods Applied to Power Systems, 2006StockholmIEEE1-5

[11] MohammadiM., GharehpetianG. B.. Power system on-line static security assessment by using multi-class support vector machines [J]. Journal of Applied Sciences, 2008, 8(12): 2226-2233

[12] AryaL. D., ChoubeS. C., KothariD. P.. Line outage ranking for voltage limit violations with corrective rescheduling avoiding masking [J]. Int J Electr Power Energ Syst, 2001, 23: 837-846

[13] BerizziA., BovoC., CirioD., DelfantiM., MerloM., PozziM.. Online fuzzy voltage collapse risk quantification [J]. Elec Power Syst Res, 2009, 79: 740-749

[14] ChenW. H., JiangQ. Y., CaoY. J.. Low voltage risk assessment in power system using neural network ensemble [J]. Adv Neural Network, 2006, 3972: 1416-1421

[15] XIAO F, MC CALLEY J D, OU Y, ADAMS J, MYERS S. Contingency probability estimation using weather and geographical data for on-line security assessment [C]// International Conference on Probabilistic Methods Applied to Power Systems, Stockholm, 2006, 1–7.

[16] YatesR. D., GoodmanD. J.Probability and Stochastic processes [M], 2005New JerseyJohn Wiley & Sons

[17] BalamourouganV., SidhuT. S., SachdevM. S.. Technique for online prediction of voltage collapse [J]. IEEE Proceedings-Generation, Transmission and Distribution, 2004, 151(8): 453-460

[18] AmjadyN., EsmailiM.. Application of a new sensitivity analysis framework for voltage contingency ranking [J]. IEEE T Power Syst, 2005, 20: 973-983

[19] de MouraR. D., PradaR. B.. Contingency screening and ranking method for voltage stability assessment [J]. IEEE Proceedings-Generation, Transmission and Distribution., 2005, 152(6): 891-898

[20] FlueckA. J., GonellaR., DondetiJ. R.. A new power sensitivity method of ranking branch outage contingencies for voltage collapse [J]. IEEE T Power Syst, 2002, 17: 265-270

[21] HazraJ., SinhaA. K.. A risk based contingency analysis method incorporating load and generation characteristics [J]. Int J Electr Power Energ Syst, 2010, 32: 433-442

[22] BasheerI. A., HajmeerM.. Artificial neural networks: Fundamentals, computing, design, and application [J]. J Microbiol Meth, 2000, 43: 3-31

[23] VapnikV. N.. An overview of statistical learning theory [J]. IEEE Trans Neural Network, 1999, 10: 988-999

[24] BAOYING L, RENGANG Y. A novel method based on PCA and LS-SVM for power load forecasting [C]// Third International Conference on Electric Utility Deregulation and Restructuring and Power Technologies, Nanjing, 2008: 759–763.

[25] SawhneyH., JeyasuryaB.. A feed-forward artificial neural network with enhanced feature selection for power system transient stability assessment [J]. Elec Power Syst Res, 2006, 76: 1047-1054

[26] MilanoF.. An open source power system analysis toolbox [J]. IEEE T Power Syst, 2005, 20: 1199-1206