期刊名称：Journal of Information and Organizational Sciences
印刷版ISSN：1846-3312
电子版ISSN：1846-9418
出版年度：2019
卷号：43
期号：1
页码：99-117
DOI：10.31341/jios.43.1.6
出版社：Faculty of Organization and Informatics University of Zagreb
摘要： Due to its many advantages, demand for natural gas has increased considerably and many models for predicting natural gas consumption are developed. The aim of this paper is to present an overview and systematic analysis of the latest research papers that deal with predictions of natural gas consumption for residential and commercial use from the year 2002 to 2017. Literature overview analysis was conducted using the two most relevant scientific databases Web of Science Core Collection and Scopus. The results indicate neural networks as the most common method used for predictions of natural gas consumption, while most accurate methods are genetic algorithms, support vector machines and ANFIS. Most used input variables are past natural gas consumption data and weather data, and prediction is most commonly made on daily and annual level on a country area level. Limitations of the research raise from relatively small number of analyzed papers but still research could be used for significant improving of prediction models for natural gas consumption.
关键词：natural gas; prediction models; energy; literature review
