Ahmed Elzawawy, Mahmoud Ali, Fahmy Bendary, Wagdy Mansour
Adaptive Under Frequency Load Shedding Scheme Using Genetic Algorithm Based Artificial Neural Network
This paper presents two schemes of UFLS to keep the system frequency within safe limits. GA-based scheme is introduced as an offline method to get the proper amount of shed load achieving the minimum and steady state frequency within permissible limits. Due to the probability of generation variation and generating units outage during shedding process, ANN-based scheme is presented as an online method to adjust the proper amount of load shedding at any amount of power deficit. Multi scenarios of contingences are carried out on offline mode using GA optimization technique to collect the training patterns for ANN. The ANN-based scheme can consider the generation variations during the load shedding process. Although using this scheme may shed more loads, it maintains the frequency to be within permissible limits at various disturbance scenarios particularly at the absence of secondary control. An analytic system frequency response (SFR) model with no secondary control incorporating UFLS scheme is presented. The proposed method is compared with the classical adaptive method to prove its effectiveness. Results are presented in the form of time domain simulations via MATLAB/SIMULINK.
Islanding, Blackout, Artificial Neural Network, Genetic Algorithm, Under Frequency Load Shedding, System Frequency Response
Cite this paper
Ahmed Elzawawy, Mahmoud Ali, Fahmy Bendary, Wagdy Mansour. (2019) Adaptive Under Frequency Load Shedding Scheme Using Genetic Algorithm Based Artificial Neural Network. International Journal of Computers, 4, 38-44