Several incidents that occurred around the world involving power failure
caused by unscheduled line outages were identified as one of the main
contributors to power failure and cascading blackout in electric power
environment. With the advancement of computer technologies, artificial
intelligence (AI) has been widely accepted as one method that can be applied
to predict the occurrence of unscheduled disturbance. This paper presents
the development of automatic contingency analysis and ranking algorithm
for the application in the Artificial Neural Network (ANN). The ANN is
developed in order to predict the post-outage severity index from a set of preoutage
data set. Data were generated using the newly developed automatic
contingency analysis and ranking (ACAR) algorithm. Tests were conducted
on the 24-bus IEEE Reliability Test Systems. Results showed that the developed
technique is feasible to be implemented practically and an agreement was
achieved in the results obtained from the tests. The developed ACAR can be
utilised for further testing and implementation in other IEEE RTS test systems
particularly in the system, which required fast computation time. On the other
hand, the developed ANN can be used for predicting the post-outage severity
index and hence system stability can be evaluated.
This paper presents adaptive particle swarm optimization for solving non-convex economic dispatch problems. In this study, a new technique was developed known as adaptive particle swarm optimization (APSO), to alleviate the problems experienced in the traditional particle swarm optimisation (PSO). The traditional PSO was reported that this technique always stuck at local minima. In APSO, economic dispatch problem are considered with valve point effects. The search efficiency was improved when a new parameter was inserted into the velocity term. This has achieved local minima. In order to show the effectiveness of the proposed technique, this study examined two case studies, with and without contingency.