Daily natural gas consumption prediction by MARS and CMARS models for residential users in Ankara

Download
2015
Yılmaz, Yavuz
Energy efficient construction and operation of modern energy transmission and distribution systems is one of the major challenging problems in engineering area. Prior to every kind of natural gas related study, regardless of their financial or engineering features, demand forecast figures should be seen. Decision making of natural gas investment planning and operation in a city, region or country are highly important engineering problems that have very important economic effects. Determination of the total gas supply import expenditures, the tariffs, additional costs for the extra investments in order to provide safe and continuous gas supply to additional consumers are some of the other confronted problems. Additionally, predicting residential purpose users gas consumption is indispensable for efficient system operation and required for planning decisions at natural gas Local Distribution Companies (LDCs) and Transmission System Operator companies (TSOs). Residential users are major consumers that usually demand significant amount of total gas supplied in distribution systems especially in winter season. Due to the fact that all residential users should be satisfied and the distribution systems have limited capacity for the gas supply, proper planning and forecasting in high seasons and whole year have become critical and essential. This study is conducted for the responsibility area of Bas¸kentgaz which is the local gas company of Ankara. As of gas year of 2014, Başkentgaz owns approximately 90% of overall maximum permissible residential consumption capacity of Ankara with its districts residential user gas distribution network. Within the scope of this work, MARS (Multivariate Adaptive Regression Splines) and CMARS (Conic Multivariate Adaptive Regression Splines) predictive models for one-day ahead natural gas consumption of residential users are formed. The models not only compare both methods, but they also analyze the effect of actual daily minimum and maximum temperatures versus the Heating Degree Day (HDD) equivalent of their average. Using the obtained one-day ahead models with daily data on 2009-2012, the daily consumption of each day in 2013 has been predicted and the results have been compared with the actual data obtained from Başkentgaz. The outcomes of the study present MARS and CMARS methods to the natural gas industry as two new competitive approaches. The thesis is ended with a conclusion and an outlook to the future studies.
Citation Formats
Y. Yılmaz, “Daily natural gas consumption prediction by MARS and CMARS models for residential users in Ankara,” M.S. - Master of Science, Middle East Technical University, 2015.