Prediction for the Maximum Frequency Deviation of Post-disturbance Based on the Deep Belief Network

A method based on the deep belief network (DBN) to predict the maximum frequency deviation of post-disturbance is proposed. The input characteristics of the deep belief network are constructed by 21-dimensional data, including load level, the value of power shortage after disturbance, electromagnetic power and the mechanical power of generators, etc. The output characteristics include the maximum frequency deviation after disturbance and its appearance time. Besides, a new sample organization way is proposed in this paper to improve the accuracy of predicted results by assembling samples with the same regular pattern in a set. The effectiveness and accuracy of the proposed sample organization way based on DBN are tested on the New England 39-bus system, by comparing the prediction results of the proposed method with the results of the simulation, the other sample organization way and other machine learning models.

[1]  P. M. Anderson,et al.  A low-order system frequency response model , 1990 .

[2]  F. Schweppe,et al.  Dynamic Equivalents for Average System Frequency Behavior Following Major Distribances , 1972 .

[3]  H. H. Happ,et al.  Power System Control and Stability , 1979, IEEE Transactions on Systems, Man, and Cybernetics.

[4]  P. Cochat,et al.  Et al , 2008, Archives de pediatrie : organe officiel de la Societe francaise de pediatrie.

[5]  Liu Ke-tian.  Improvement of Direct Predictive Algorithm of Power System Steady Frequency After Disturbances , 2010 .

[6]  Feifei Bai,et al.  The Anatomy of the 2016 South Australia Blackout: A Catastrophic Event in a High Renewable Network , 2018, IEEE Transactions on Power Systems.

[7]  Yoh-Han Pao,et al.  Prediction of power system frequency response after generator outages using neural nets , 1993 .

[8]  Tsuyoshi Murata,et al.  {m , 1934, ACML.

[9]  Bo Qibi.  Minimum frequency prediction based on v-SVR for post-disturbance power system , 2015 .

[10]  Inesc Porto.  Using a Neural Network to Predict the Dynamic Frequency Response of a Power System to an Under-Frequency Load Shedding Scenario , 2000 .

[11]  Geoffrey E. Hinton.  A Practical Guide to Training Restricted Boltzmann Machines , 2012, Neural Networks: Tricks of the Trade.

[12]  M. Pai.  Energy function analysis for power system stability , 1989 .

[13]  Tara N. Sainath,et al.  FUNDAMENTAL TECHNOLOGIES IN MODERN SPEECH RECOGNITION Digital Object Identifier 10.1109/MSP.2012.2205597 , 2012 .

[14]  K. R. Padiyar,et al.  ENERGY FUNCTION ANALYSIS FOR POWER SYSTEM STABILITY , 1990 .