Data Mining: An Overview from a Database Perspective
IEEE Transactions on Knowledge and Data Engineering
Tax forecasting theory and model based on SVM optimized by PSO
Expert Systems with Applications: An International Journal
Expert Systems with Applications: An International Journal
Expert Systems with Applications: An International Journal
Expert Systems with Applications: An International Journal
Hi-index | 0.10 |
Middle-long forecasting of electric power load is crucial to electric investment, which is the guarantee of the healthy development of electric industry. In this paper, the particle swarm optimization (PSO) is used as a training algorithm to obtain the weights of the single forecasting method to form the combined forecasting method. Firstly, several forecasting methods are used to do middle-long power load forecasting. Then the upper forecasting methods are measured by several indices and the entropy method is used to form a comprehensive forecasting method evaluation index, following which the PSO is used to attain a combined forecasting method (PSOCF) with the best objective function value. We then obtain the final result by adding all the results of every single forecasting method. Taking actual load data of a power grid company in North China as a sample, the results show that PSOCF model improves the forecasting precision compared to the traditional models.