Introduction to artificial neural systems
Introduction to artificial neural systems
Alleviation of transmission system overloads using fuzzy reasoning
Fuzzy Sets and Systems - Special issue on applications of fuzzy theory in electronic power systems
Corrective action planning using RBF neural network
Applied Soft Computing
Prediction of transmission line overloading using intelligent technique
Applied Soft Computing
Adaptation in differential evolution: A numerical comparison
Applied Soft Computing
Hi-index | 0.01 |
This paper is a modest attempt to address an intelligent technique based on Cascade Back Propagation Neural network (CBPN) for detection of line overloads, prediction of overloading amount and alleviation of overloads using generation rescheduling with N-1 contingency in restructured power system. In the present competitive power market, power transmission congestion has become more intensified and recurrent than the vertically bundled system. Transmission line congestion initiates the cascading outages which forces the system to collapse. Accurate prediction and alleviation of line overloads are the suitable corrective actions to avoid network collapse. The most obvious technique for network Congestion Management (CM) is rescheduling the power output of generators. The proposed CBPN comprises three Artificial Neural Networks (ANNs) in cascade. ANN1 is used as a classifier, which classifies the system state as secure or insecure. ANN2 is used for the prediction of overloading amount in the overloaded lines and ANN3 gives optimal generation rescheduling values for alleviating the overloads. The real power and reactive power of loads at all the load buses and the line outage number are considered as input variables to ANN1, ANN2 and ANN3. The effectiveness of the proposed approach is tested for various contingencies in the IEEE30 Bus System. The experimental results show that the proposed approach is computationally fast, reliable and efficient, in restoring the system to the normal state after a contingency with minimal control actions.