Soft computing methods for WiMax Network Planning on 3D Geographical Information Systems

http://repository.vnu.edu.vn/handle/VNU_123/28686


In this paper, we present an application of soft computing methods for the problem of WiMax Network Planning on 3D Geographical Information Systems (3D GIS) that optimizes both performance of the network (Coverage and Quality-of-Service) and investment costs (the number of base stations and sectors). 


A pre-processing procedure using latest results of parallel Random Forest classification algorithm to determine valid positions of base stations on a terrain of 3D GIS is proposed.
Based upon those positions, we design a generalized mathematical model taking into account 3D obstacles in path loss calculation process.

In order to generate optimal solutions of the model, a hybrid algorithm between greedy BTP and improved Particle Swarm Optimization incorporated with parallel computing is presented.
Experimental validation of the proposed method in comparison with other relevant ones is performed.

Title: 


Soft computing methods for WiMax Network Planning on 3D Geographical Information Systems
Authors: Le Hoang Son
Pham Huy Thong
Keywords: 3D GIS
Particle Swarm Optimization
Parallel Random Forest
Soft computing
WiMax Network Planning
Issue Date: 2017
Publisher: ACADEMIC PRESS INC ELSEVIER SCIENCE, 525 B ST, STE 1900, SAN DIEGO, CA 92101-4495 USA
Citation: ISIKNOWLEDGE
Abstract: In this paper, we present an application of soft computing methods for the problem of WiMax Network Planning on 3D Geographical Information Systems (3D GIS) that optimizes both performance of the network (Coverage and Quality-of-Service) and investment costs (the number of base stations and sectors). A pre-processing procedure using latest results of parallel Random Forest classification algorithm to determine valid positions of base stations on a terrain of 3D GIS is proposed. Based upon those positions, we design a generalized mathematical model taking into account 3D obstacles in path loss calculation process. In order to generate optimal solutions of the model, a hybrid algorithm between greedy BTP and improved Particle Swarm Optimization incorporated with parallel computing is presented. Experimental validation of the proposed method in comparison with other relevant ones is performed.
Description: TNS07000 ; JOURNAL OF COMPUTER AND SYSTEM SCIENCES Volume: 83 Issue: 1 Pages: 159-179 Published: FEB 2017
URI: http://repository.vnu.edu.vn/handle/VNU_123/28686
http://www.sciencedirect.com/science/article/pii/S0022000016300514
ISSN: 0022-0000
1090-2724
Appears in Collections:Bài báo của ĐHQGHN trong Web of Science


Nhận xét

Bài đăng phổ biến từ blog này

Định tuổi tương đối của đá

Multifunctional drug nanosystems: A summary of recent researches at IMS/VAST

Đình ngự triều Di Quy (Cổ Loa - Hà Nội)