The location of commercial facility decides the benefit of the operator to a large degree. Existing location methods can express the static relationships between site selection result and location factors, but there still are some limites when express the dynamic and uncertain relationship between them. Hence, a dynamic, stochastic and forecastable location model should be built which can introduce the customer's behavior into the model and combine the macro pattern and micro spatial interaction. So the authors proposes Geosim-LM based on MAS. Geosim-LM has 3 kinds of agents, CustAgent, SiteAgent and GovAgent. They represent the customers, commercial fercilities and government. The land type, land price and traffic are the model environment. Then Geosim-LM is applied in the bank branches site evaluation and selection in Liwan district, Guangzhou. In existing bank branches site evaluation, there are 70% consistent in score grade between result of Geosim-LM after 200 round runing and actual rebust location. It proves the model is reliable and feasible. The conclusions can be get from the paper. MAS have advantages in location choice than existed methods. The result of Geosim-LM running can powerfully proves that building location model based on MAS is feasible.

Date Published: 3 November 2008
PDF: 8 pages
Proc. SPIE 7143, Geoinformatics 2008 and Joint Conference on GIS and Built Environment: Geo-Simulation and Virtual GIS Environments, 71431N (3 November 2008); doi: 10.1117/12.812588

Published in SPIE Proceedings Vol. 7143:
Geoinformatics 2008 and Joint Conference on GIS and Built Environment: Geo-Simulation and Virtual GIS Environments
Lin Liu; Xia Li; Kai Liu; Xinchang Zhang; Aijun Chen, Editor(s)