Application of Temperature Prediction Model Based on LSTNet in Telecommunication Room

Abstract

In this paper, we present an application of a temperature prediction model based on the Long- and Short-term Time-series network (LSTNet). The model allows predicting the indoor temperature for the next 20 to 60 minutes based on the operating status of the telecommunications room and the outdoor weather condition. In addition, we propose a mechanism for the automatic model update that is triggered when the accuracy of the prediction model is reduced or when the telecommunications room equipment is replaced.