Abstract: The power load is affected by various factors such as temperature, economy, special events, and multi-factor coupling, which makes the quantitative analysis of the causes of the power load growth difficult. At the same time, current load analysis is mostly focused on prediction, and it is uncommon to analyze the causes of load growth.Therefore, based on a study on the construction method of power load data characteristics, a power load growth attribution analysis method is proposed. Firstly, the meteorological correlation indicators, the economic development-based natural load growth indicators, the electrical quantity correction-based industrial structure change indicators, and the event trend consistency evaluation indicators are constructed. And then, the meteorological load, natural economic load, industrial expansion load and random load are respectively extracted, and the contribution rate is used to quantify the influence degree of each factor on the load growth. Finally, the power consumption data of two northwestern provinces are used to verify the proposed method, which indicates that the proposed method is effectively quantify the causes of load growth.