Study On Urban Natural Gas Demand Middle-Long Term Forecasting Base On SVM Model

Theory of Forecasting is a highly integrated and complex science. It uses long historical experience and strict logical reasoning to estimate the future trends. Forecasting can instruct how to make plans, and have a direct impact on decision- making activities. At the same time, with the development of modern prediction science, human decision-making process become more rational, they pay more and more attention to hunt after the answers of uncertainty questions. So a large number of forecasting mathematical models have been invented. Since the 1990s, SVM has become the focus of scholars all over the world, it has solved the problems of over learning, dimension disaster and local minimum effectively and has changed the traditional thinking mode. Therefore, SVM will be more and more popular in all aspects of society.With the process of industrialization, the consumption of coal and oil is growing faster; environmental problem has become the pain of all the people. In the background of this situation, natural gas is greatly rewarded around the world for its rich reserves, excellent quality and low pollution. So the natural gas resource competition is very intense. In China, Natural gas is undergoing the process of widespread from expanding. With the process of substituting oil with gas, using gas for power generation and urban gasification, the strategic position will be improved a lot, and also the supply-demand contradiction question is appeared gradually. Normally, in supply link, gas resource supply department have to make"Take or Pay"protocol to downstream gas demand. Urban Gas Company needs to have a comparatively accurate estimation of the future demand.Firstly, based on finishing process of existing research data, this article demonstrated the commonly used methods of natural gas demand forecasting. Secondly, this paper analyzed the deficiency of existing index system and variable extraction. Then summarized the main influence factor of natural gas demand middle-long forecasting, established an index system for Urban Natural Gas Demand Middle-Long Term Forecasting. Thirdly, the Best Subset Regression method was used to extract input variables. Fourthly, based on that, this thesis built the PSO-LSSVM forecasting model. The GM (1, 1) model was chose to predict the input factors of regression model. Then LSSVM rolling time series model was used to forecast the consumption proportion of natural gas and electric power. We can get the natural gas supply quantum by fitting logarithmic equation. And then, we can obtain the predictive value by putting these results to the PSO-LSSVM model. Finally, this paper took the real data of CD city from 1990 to 2007 as an example. The results showed that the natural gas demand of this city will maintain an annual growth rate about 3.4 percent in the next five years; demand-supply gap may be further enlarged. So, we proposed six countermeasures for CD as follows: further strengthening the consumption of natural gas, raising the natural gas price suitably, speeding up the urban natural gas necessary pipe network construction, expanding the financing channel of natural gas project construction, striving for multi-gas source supply diligently, improving the primary data collection and statistical work of energy consumption.This article made some progresses as follows:Firstly, form the views of external environment, internal environment and consumer, this article summarized the main influence factor of natural gas demand middle-long forecasting. And the Best Subset Regression method was used to extract input variables, ultimately five basic indicators were identified, which were per capita GDP, the consumption proportion of natural gas, the consumption proportion of electric power, natural gas supply quantum and per capita disposable income.Secondly, this article introduced the PSO-LSSVM model to Urban Natural Gas Demand Middle-Long Term Forecasting for the first time. This model integrated the advantages of PSO that can search the globe minimum rapidly and of LSSVM that can solve nonlinear problem effectively. So it has the feature of fast speed and good generalization. By forecasting the actual natural gas demand of CD, it confirms that this model has lower MAPE and better rationality, which not only enrich the natural gas demand forecasting method, but also provide useful reference for similar studies.