A signal strength fluctuation prediction model based on symbolic regression

The impact of weather parameters such as temperature, humidity or dew point on the signal strength in mobile network was investigated. The aim of the paper was to propose a mathematical model which is able to predict the behaviour of such signal strength. The symbolic regression using a genetic algorithm was used to develop a model which predicts the signal strength based on current weather parameters. The average RMSE proved that the model is fully applicable and can be used, for example, in a method of decreasing the power consumption of a base station.