2001 Fiscal Year Final Research Report Summary
Research on Neural Network Based Dynamic Channel Assignment Systems in Cellular Mobfle Communication Systems
| Project/Area Number |
10555126
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (B)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 展開研究 |
|---|
| Research Field |
情報通信工学
|
|---|
| Research Institution | NIIGATA UNIVERSITY |
|---|
Principal Investigator |
SENGOKU Masakazu NIIGATA UNIVERSITY, Faculty of Engineering, Professor, 工学部, 教授 (30002017)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
NAKANO Keisuke NIIGATA UNIVERSITY, Faculty of Engineering, Associate Professor, 工学部, 助教授 (80269547)
SATO Takuro Nugata. Institute of Technology, Faculty of Engineering, Professor, 工学部, 教授 (20271603)
OKADA Kazunori Communication Research Laboratory, Yokosuka Radio Cornmunications Research Center Senior Researcher, 横須賀無線通信研究センター, 主任研究員(研究職)
SHINODA Shoji Chuo University, Faculty of Science and Engineering Professor, 理工学部, 教授 (40055207)
YAMADA Yoshihide National Defense Academy School of Electrical and Computer Engineering, Professor, 電気工学教室, 教授
|
|---|
| Project Period (FY) |
1998 – 2001
|
| Keywords | Mobile communication / Cellular system / Channel assignment / Base station location / Cell location / Neural net / Genetic algorithm / Optimization methods |
|---|
| Research Abstract |
Because demand for mobile communication services rapidly increases, the efficient use of frequency bands is an important issue. For the efficient use of the frequency bands, mobile communication networks should be highly optimized. Also, it is neciessary to apply intelligent control methods to mobile communication networks. To optimize the mobile networks, we must solve some NP complete problems quiclfly. For this purpose,neural networks and generic algorithms can be used, and it is very important to develop quick dynamic channel assignment systems using neural networks and genetic algorithms. The objective of this project is to develop dynamic channel assignment systems using neural networks and genetic algorithms, and to evaluate performance of the systems. It is considered that we can apply parallel computation systems consisting of some CPUs to dynamic channel assignment systems. Hence, this project develops dynamic channel assignment systems based on neural networks or genetic algorithms with parallel computation. This project has developed such systems for dynamic channel assignment. Through the evaluation process, we confirmed performance improvement by using the developed method. Also, we examined channel assignment methods to adapt to traffic fluctuation caused by vehicles' traffic fluctuation. Also, this project developed an approximate method to theoretically analyze communication traffic characteristics of dynamic channel assignment methods considering mobility. Other optimization problems and fundamental problems to improve mobile communication systems were also considered.
|
