Performance Evaluation of RSSI Prediction Methods in Wireless Communication Networks

Rifki, Mhd Ikhsan (Universitas Islam Negeri Sumatera Utara)
Ikhwan, Ali (University Malaysia Perlis)
Muhammad, Faisal (IPB University)

Zero : Jurnal Sains, Matematika, dan Terapan
Vol 8, No 1 (2024): Zero: Jurnal Sains Matematika dan Terapan

Continuous communication services that ensure user connectivity with the communication network are important. The communication network should be able to accommodate erratic user movements with high mobility. This research studies the performance of three different RSSI prediction methods: decision trees, random forests, and linear regression. Evaluation is carried out using statistical metrics, including mean squared error (MSE), root mean squared error (RMSE), mean absolute error (MAE), and percentage accuracy. This analysis was carried out to understand how well each model predicted RSSI values based on distance. The research results show that Decision Tree Performance has an accuracy of 83.333%, Random Forest has a high accuracy of 97.2545%, and the Linear Regression Model provides quite good predictions with an accuracy of 91.6667% in predicting RSSI values.