<![CDATA[The increasing use of internet services in local internet networks such as RT/RW Net and small-scale internet service providers requires stable network quality to support user activities optimally. Problems such as high delay, packet loss, jitter, and low throughput often cause a decrease in internet service quality. This study aims to analyze the stability of local internet services using Quality of Service (QoS) parameters and apply predictive analysis to predict network stability conditions. The QoS parameters used in this study include delay, throughput, jitter, and packet loss. The research method used is quantitative, with data collection conducted through network monitoring using tools such as Wireshark, MikroTik Monitoring, and Speedtest. The collected data were processed and analyzed using the Decision Tree predictive method to classify network conditions into stable, fairly stable, and unstable categories. The results showed that QoS parameters significantly affect internet service stability, where delay and packet loss are the most dominant factors influencing network quality. The predictive model used was able to classify network conditions with an accuracy rate of 87.5%. Based on these results, predictive analysis based on QoS parameters can be used as a solution to support monitoring and decision-making in managing local internet services more effectively and efficiently.]]>
Copyrights © 2026
