Abstrait

The prediction research of SO2 emissions in thermal power industry

Jianguo Zhou, Sisi Fu

The prediction of sulfur dioxide (SO2) emissions in thermal power industry belongs to the small sample, poor information gray system. On this basis, this paper established a combination forecasting model based on support vector machine (SVM) and radial basis function neural network (RBFNN). The weights of the model are obtained by using genetic algorithm (GA). At last, on the basis of the historical data of thermal power industry during 1991 to 2012, it predicts SO2 emissions of thermal power industry for the next 8 years. The results showed that, the predicted results were accurate by using this model, which is an effective method for the predict of SO2 emissions of thermal power industry in our country in the future.