Abstract: The continuous advancement of the construction of new power systems,the increase in the proportion of new energy sources such as wind power generation and photovoltaic power generation,the addition of new power loads represented by electric vehicles,and the participation of users in demand response in the new power market,all these have a profound impact on the grid structure and gradually enhance the spatiotemporal characteristics of customer electricity load,raising new requirements for customer load forecasting technology. In this context, this article examines and summarizes the existing technologies for customer power load forecasting. First,the paper analyzes the changes brought by power load changes to load forecasting from various aspects such as forecast methods, forecast scales, and forecast object.Second,while analyzing the shortcomings of traditional power load forecasting technologies,the paper summarizes modern power load forecasting methods and technologies;furthermore,it sorts out the challenges of data availability,diversification of influencing factors and regional differences in the field of load forecasting. Finally,to meet these challenges,analysis and prospect are given to the development of future load forecasting technology in technical and application aspects.