TY - GEN
T1 - Recurrent ANN based AGC of a two-area power system with DFIG based wind turbines considering asynchronous tie-lines
AU - Sharma, Gulshan
AU - Niazi, K. R.
AU - Ibraheem,
N1 - Publisher Copyright:
© 2014 IEEE.
PY - 2014
Y1 - 2014
N2 - Modern power systems are large and complex with growing trends to integrate wind energy to the grid. The penetration of wind energy has motivated researchers to investigate the dynamic participation of doubly fed induction generators (DFIG) based wind turbines in automatic generation control (AGC) besides conventional generators. Power system is highly non-linear and complex. However, with dynamic participation of DFIG, the AGC problem becomes more complex. Under such conditions classical AGC are not suitable. Therefore, a new non-linear recurrent artificial neural network (ANN) based regulator for solution of AGC problem is proposed in this paper. The proposed AGC regulator is trained for a wide range of operating conditions and load changes using an off-line data set generated from the most accurate solution methodology of the power system. The back propagation-through time-algorithm is used as ANN learning rule. A two-area power system connected via asynchronous tie-lines with dynamic participation from DFIG based wind turbines in presence of system non-linearity such as governor dead-band is considered to demonstrate the effectiveness of the proposed AGC regulator and compared with that obtained using conventional PI, under wide range of operating conditions and area load disturbances.
AB - Modern power systems are large and complex with growing trends to integrate wind energy to the grid. The penetration of wind energy has motivated researchers to investigate the dynamic participation of doubly fed induction generators (DFIG) based wind turbines in automatic generation control (AGC) besides conventional generators. Power system is highly non-linear and complex. However, with dynamic participation of DFIG, the AGC problem becomes more complex. Under such conditions classical AGC are not suitable. Therefore, a new non-linear recurrent artificial neural network (ANN) based regulator for solution of AGC problem is proposed in this paper. The proposed AGC regulator is trained for a wide range of operating conditions and load changes using an off-line data set generated from the most accurate solution methodology of the power system. The back propagation-through time-algorithm is used as ANN learning rule. A two-area power system connected via asynchronous tie-lines with dynamic participation from DFIG based wind turbines in presence of system non-linearity such as governor dead-band is considered to demonstrate the effectiveness of the proposed AGC regulator and compared with that obtained using conventional PI, under wide range of operating conditions and area load disturbances.
KW - automatic generation control
KW - doubly fed induction generator
KW - recurrent neural networks
UR - http://www.scopus.com/inward/record.url?scp=84966688697&partnerID=8YFLogxK
U2 - 10.1109/ICAETR.2014.7012881
DO - 10.1109/ICAETR.2014.7012881
M3 - Conference contribution
AN - SCOPUS:84966688697
T3 - 2014 International Conference on Advances in Engineering and Technology Research, ICAETR 2014
BT - 2014 International Conference on Advances in Engineering and Technology Research, ICAETR 2014
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2014 International Conference on Advances in Engineering and Technology Research, ICAETR 2014
Y2 - 1 August 2014 through 2 August 2014
ER -
