A knowledge management system based on artificial intelligence (AI) methods: A flexible fuzzy regression-analysis of variance algorithm for natural gas consumption estimation

A knowledge management (KM) system has a different schema that one of them has been studied in the present study. One of version of KM is based on artificial intelligence (AI) methods. KM based on AI has been investigated in the present work based on natural gas consumption estimation domain. Developing accurate and flexible model to natural gas consumption estimation is a strategic step in policy and decision-making process in energy sector. This paper provides a stage algorithm during that it gains optimal fuzzy regression model for studding natural gas consumption in sixteen countries according to data in years 1989 till 2007. Different countries have selected from Africa, America, Asia, Europe and Middle East based on high, middle and low GDP index and for every one of them nine fuzzy regression models have executed and the results and error of each model have calculated. Preprocess has been done on the initial data to gain better results which the min-max method has been used for this purpose. Two criterions have been used to determining suitable and appropriate fuzzy regression model in each country. Firstly, fuzzy regression models with MAPE value below 10 is deleted from the assessment and remained fuzzy regression models are compared with ANOVA. Upon logic that given algorithm sketches for some countries none of used models are proper while for other countries optimal model is gained in first or second filter of algorithm. To show the applicability and superiority of the proposed flexible Fuzzy regression model the data for oil consumption in Japan, Thailand, Bangladesh from Asia and Norway, Italy, Bulgaria from Europe and Qatar, Iran, Iraq from Middle East and The united state, Mexico, Bolivia from North America and Libya, Tunisia, Nigeria from Africa during 1989 to 2007 are used.