Comparative Study of Base Transceiver Stations Infrastructure Planning Using Machine Learning for Under Construction Area: A Case Study of Ibu Kota Nusantara

Abstract

Communication is a fundamental human need that occurs directly or through technologies like telephones and signal transmitters such as BTS and satellites. Satellites, including Starlink, serve as additional solutions for internet access needs, particularly in remote areas, albeit higher costs remain a factor necessitating conventional BTS infrastructure development. Telecommunication operators face challenges in constructing BTS in areas with limited access and complex financial considerations due to low demand in rural areas, requiring careful planning. This study utilizes several supporting variables with the aid of machine learning techniques such as Linear Regression, SVR, Random Forest, and Gradient Boosting to forecast BTS requirements. Comparative analysis shows that the random forest machine learning method provides the best modeling results compared to linear regression, Gradient Boosting, and SVR methods. Despite the superior performance of the random forest method, further fine-tuning is still needed through parameter adjustments and evaluation of variables used to achieve an even better model. The modeling results can be utilized to predict the BTS infrastructure needs in IKN, estimated at 61,135 units. In BTS development planning, mobile operators can collaborate both among themselves and with Internet Service Providers (ISPs) utilizing satellite media. Utilizing shared towers can be an option for cost-efficient BTS infrastructure development.