Data-driven modelling for gas consumption prediction at City Gate Stations

Abstract City Gate Stations (CGS) are critical elements of Natural Gas (NG) distribution systems, as they connect national high-pressure transmission networks with local low-pressure networks. One their main tasks is to pre-heat the gas avoid dangerous sub-cooling due Joule-Thompson effect after pressure reduction stage. For this process, significant amounts thermal energy required, usually obtained by burning part flow rate. This work aims develop a data-driven model that will serve tool predict and monitor consumption CGS. The plant chosen case study for activity in region central Italy. A Multiple Linear Regression (MLR) developed trained, its predictive performance evaluated. results achieved an accuracy over 95% coefficient determination. method makes it possible create baseline evaluate CGS time using CUSUM technique find variations between actual modelled consumption, being essential monitoring effectiveness NG preheating system.