Title :
Adaptive critic design based dynamic optimal power flow controller for a smart grid
Author :
Liang, Jiaqi ; Harley, Ronald G. ; Venayagamoorthy, Ganesh K.
Author_Institution :
Sch. of Electr. & Comput. Eng., Georgia Inst. of Technol., Atlanta, GA, USA
Abstract :
An adaptive critic design (ACD) based dynamic optimal power flow control (DOPFC) is proposed in this paper as a solution to the smart grid operation in a high short-term uncertainty and variability environment. With the increasing penetration of intermittent renewable generation, power system stability and security need to be ensured dynamically as the system operating condition continuously changes. The proposed DOPFC dynamically tracks the power system optimal operating point by continuously adjusting the steady-state set points from the traditional OPF algorithms. The ACD technique, specifically the dual heuristic dynamic programming (DHP), is used to provide nonlinear optimal control, where the control objective is formulated explicitly to incorporate system operation economy, stability and security considerations. A 12 bus test power system is used to demonstrate the development and effectiveness of the proposed ACD-based DOPFC using recurrent neural networks.
Keywords :
dynamic programming; load flow control; neurocontrollers; nonlinear control systems; optimal control; power system dynamic stability; power system security; smart power grids; 12-bus test power system; ACD technique; DHP; DOPFC; adaptive critic design; dual heuristic dynamic programming; dynamic optimal power flow controller; intermittent renewable generation; nonlinear optimal control; optimal operating point; power system security; power system stability; recurrent neural networks; smart grid operation; steady-state set points; system operation economy; Automatic generation control; Generators; Power system dynamics; Power system stability; Recurrent neural networks; Training; Adaptive critic designs; dynamic optimal power flow control; neurocontrol; power system wide-area control; recurrent neural networks; smart grid;
Conference_Titel :
Computational Intelligence Applications In Smart Grid (CIASG), 2011 IEEE Symposium on
Conference_Location :
Paris
Print_ISBN :
978-1-4244-9893-2
DOI :
10.1109/CIASG.2011.5953340