Operating the electrical power systems at normal conditions is our goal always. This
is what represents the ideal state of electrical power system work. Hence, the electrical
power system work in case of insufficient electrical power requires avoid
ing since it leads
to big losses in national economy.
These losses could be huge when we talk about connection borders between systems
as per overload frame, because of lack of electrical power request. The impact of these
conditions could be noticeably decreased at a reasonable limit of electrical power request.
When we find out the optimal solution of electrical power systems operation and the
communication lines between them while considering the losses of consumers
disconnecting that guarantee the stability of loads. Finally, it is so at full use of maneuver
(available cases) spare power properties when applying the instant correction of regime.
This paper studies the basic approach to solve these issues which imply the reliability
definitions.
This paper shows a new approach to determine the presence of defects and to classify the defect type online based on Artificial Neural Networks (ANNs) in electrical power system transmission lines. This algorithm uses current and voltage signals samp
led at 1
KHz as an input for the proposed ANNs without the involvement of a moving data window, so input data will be processed as a string of data. The model depends on three neural networks one for each phase and another fourth neural network for the involvement of the ground during the fault. Response time of the classifier is less than 5 ms. Moreover modern power system requires a fast, robust and accurate technique for online processing.
Simulation studies show that the proposed technique is able to distinguish the fault type very accurate. Also this technique succeeded in determining of all defect types under all system conditions, so it is 100 percent accurate, so it is suitable for online application.
