| Article ID: | iaor19961636 |
| Country: | Japan |
| Volume: | E78-B |
| Issue: | 8 |
| Start Page Number: | 1187 |
| End Page Number: | 1196 |
| Publication Date: | Aug 1995 |
| Journal: | Transactions of the Institute of Electronics, Information and Communication Engineers |
| Authors: | Funabiki Nobuo, Nisihakawa Seishi |
| Keywords: | scheduling, programming: nonlinear, neural networks |
This paper presents an improved neural network for channel assignment problems in cellular mobile communication systems in the new co-channel interference model. Sengoku et al first proposed the neural network for the same problem, which can find solutions only in small size cellular systems with up to 40 cells in our simulations. For the practical use in the next generation’s cellular systems, the performance of the present improved neural network is verified by large size cellular systems with pu to 500 cells. The newly defined energy function and the motion equation with two heuristics in the neural network achieve the goal of finding optimal or near-optimum solutions in a nearly constant time.