engleski

The influence of solar radiation on the natural gas consumption forecasting

Forecasting natural gas consumption is a tool commonly used for balancing the supply and demand of natural gas. Many papers in this area describe models with a strong connection between weather parameters and natural gas consumption. Some authors used one weather parameter, usually outside temperature or derived variable heating degree-days, while the others also used wind speed and relative humidity as influential input variables. In this paper, the influence of solar radiation on forecasting residential natural gas consumption was investigated. Influence was tested on two data sets, namely on natural gas consumption data of the model house, and on natural gas consumption data of the local distribution company. Measurements of natural gas consumption and meteorological data were carried out through two heating seasons: 2011/2012 and 2012/2013. Various forecasting models with one day ahead forecasting horizon were compared in this study, including linear (auto- regressive model with exogenous inputs- ARX, stepwise regression) and nonlinear (neural networks-NN, support vector regression- SVR) modelling approaches. The models were compared to simple temperature correlation (TC) and random-walk (RW) models that represent a benchmark case for the model comparison. Results confirmed that solar radiation clearly influences natural gas consumption, and included as input variable in the forecasting model improves the forecasting results. Consequently it is recommended to use solar radiation as input variable in building forecasting models.

solar radiation ; neural networks ; linear models ; stepwise regression ; support vector regression.

nije evidentirano