Abstract
This paper proposes Kohonen's self-organizing neural networks embedded with genetic algorithms. The genetic algorithms are applied to decide initial weights in the Kohonen's classifiers. These initialized neural networks are then trained with training data and validated through the testing data. The proposed hybrid system has been tested on the power system static security assessment problems. The satisfactory results from both a standard test system and utility data reveal their potentials for applications.
Original language | English |
---|---|
Pages | 791-796 |
Number of pages | 6 |
Publication status | Published - 1995 |
Event | Proceedings of the 1995 Artificial Neural Networks in Engineering, ANNIE'95 - St.Louis, MO, USA Duration: 1995 Nov 12 → 1995 Nov 15 |
Other
Other | Proceedings of the 1995 Artificial Neural Networks in Engineering, ANNIE'95 |
---|---|
City | St.Louis, MO, USA |
Period | 95-11-12 → 95-11-15 |
All Science Journal Classification (ASJC) codes
- Software