Analyzing electricity consumption via data mining

This paper proposes a model to analyze the massive data of electricity. Feature subset is determined by the correlation-based feature selection and the data-driven methods. The attribute season can be classified successfully through five classifiers using the selected feature subset, and the best model can be determined further. The effects on analyzing electricity consumption of the other three attributes, including months, businesses, and meters, can be estimated using the chosen model. The data used for the project is provided by Beijing Power Supply Bureau. We use WEKA as the machine learning tool. The models we built are promising for electricity scheduling and power theft detection.