Classification of LPG clients using the Hurst exponent and the correlation coefficient

Abstract

In the research we analyzed the gas usage of different types of buildings. The analysis started with the classical theory of the buildings heating. Hence theoretical relations between gas consumption time series and the outside air temperature was introduced for different types of buildings (housing or industry). Those relations implied different auto-correlations of gas usage time series as well as different cross-correlations between gas consumption and temperature time series for different types of buildings. Hence the auto-correlation and the cross-correlation were used to imply the classification of buildings into three classes: housing, housing with high thermal capacity and industry. To investigate auto-correlation the Hurst exponent was calculated using the global DFA, while to investigate cross-correlation the Kendall's $\tau$ rank coefficient was calculated.