Pengujian Long-Short Term Memory (LSTM) Pada Prediksi Trafik Lalu Lintas Menggunakan Multi Server

This study presents a test of the long short term memory (LSTM) algorithm on traffic prediction with multi edge server and cloud architectures. IoT sensors located roadside such as cameras location data each driver are used stored in center. When sends travel time request to nearby server, predictions will be made or server. Server selection is based destination driver's request. If area, However, if Then predict done LSTM. following modeling density 128 256. By learning from previous traffic, LSTM greater gets proportion errors, namely RMSE 10.78%, MAE 8.24%, MAPE 19.87%.