Planning New Base Station Locations to Strengthen Existing Network Coverage - Application to Kestel Region

In this study, it is predicted that the coverage area of the existing base stations will become inadequate due to increasing population density in the Kestel Neighborhood of Alanya, which results in rising demand. To address this issue, new base stations that meet the current technology requirements need to be added to enhance coverage area. The objective of the study is to determine the location and capacity of the new base stations under budget constraints. First, the k-means clustering algorithm is applied to determine candidate locations for the base stations, making the large dataset manageable and avoiding the long solution time. Then, a deterministic mixed integer linear mathematical model is formulated based on the maximum coverage problem. Finally, due to the uncertainties that may occur in demand, a flexible approach is developed with a scenario-based stochastic model. In the application, real demands, base station types (macro or micro), geographical locations and regulatory requirements are also considered. The k-means clustering was implemented using the Python programming language, while the mathematical model was solved using the GUROBI optimizer integrated with Python. The effectiveness of the stochastic model was validated with the use of the Value of the Stochastic Solution (VSS) metric.