Study of short-term load forecasting in big data environment

This paper presents an improved support vector machine method based on the Hadoop, which can solve the problem of short-term load forecasting in the big data environment. In the control design, the fuzzy C clustering model of quantum behaved particle swarm optimization is used to analyze the historical load data. Then, the load data and the influencing factors data are stored and matched in Cloud platform, through this way which can improve the accuracy of the input data and the speed of the response. At last, the model is established. According to the certain area load big data, the improved support vector machine forecast model and the normal support vector machine forecast model are compared in forecasting accuracy and forecasting time. The results indicate that Hadoop-SVM has better predictive ability and faster computing time when processing the big data.