Since reform and opening up to the outside world, rapid industrialization and urbanization in China have played an important role in the increase of energy consumption. China became the second energy consumption country all over the world in 2008. As a big country in energy consumption, forecasting energy consumption is one of the most important tools for energy policy setting. Although there are many researchers has devoted into the relationship between energy and economy, the forecasting of energy consumption is still in its infancy. In this paper, economic indictors, such as real GDP, population, industrial structure, import and export, and government expenditure, are selected as input influencing factors on energy consumption, and then it is performed to find proper features from the data in terms of their statistical information. And then a novel forecasting model of energy consumption, LS-SVM regression prediction model, is presented. In the end, the case study is carried out to test the proposed model, which shows that it has many promising features that make it become a more reliable yet functional prediction tool for forecasting energy consumption.
[1]
Johan A. K. Suykens,et al.
Optimal control by least squares support vector machines
,
2001,
Neural Networks.
[2]
Hsiao-Tien Pao,et al.
Forecasting energy consumption in Taiwan using hybrid nonlinear models
,
2009
.
[3]
V. Ediger,et al.
ARIMA forecasting of primary energy demand by fuel in Turkey
,
2007
.
[4]
Harun Kemal Ozturk,et al.
Estimating energy demand of Turkey based on economic indicators using genetic algorithm approach
,
2004
.
[5]
Zhongchang Chen,et al.
Government expenditure and energy intensity in China
,
2010
.
[6]
B. Dong,et al.
Applying support vector machines to predict building energy consumption in tropical region
,
2005
.
[7]
M. Toksari.
Ant colony optimization approach to estimate energy demand of Turkey
,
2007
.
[8]
William E. Roper,et al.
Energy demand estimation of South Korea using artificial neural network
,
2009
.
[9]
Soner Haldenbilen,et al.
Genetic algorithm approach to estimate transport energy demand in Turkey
,
2005
.