Evaluation of the most influential parameters of heat load in district heating systems

摘要: Abstract The aim of this study is to investigate the potential soft computing methods for selecting most relevant variables predictive models consumers’ heat load in district heating systems (DHS). Data gathered from one substations were used simulation process. ANFIS (adaptive neuro-fuzzy inference system) method was applied data obtained these measurements. process variable selection implemented order detect predominant affecting short-term multistep prediction systems. It also select minimal input subset initial set – current and lagged (up 10 steps) load, outdoor temperature, primary return temperature. results could be simplification so as avoid multiple variables. While are promising, further work required get that directly practice.