Abstract: In the era of the internet of everything， the amount of data transmission in the power system is increasing rapidly. In order to improve the accuracy and timeliness of data processing in regional electricity retailers， a new data processing architecture based on edge computing is proposed in this paper. Firstly， the definition of edge calculation and the designed framework of nodes are clarified， and some application scenarios of edge computing in power system are introduced. Secondly， the edge computing framework for regional electricity retailers is built by analyzing the models of cloud platforms and edge nodes. At the same time， the overall operation process is designed， and the content of the integrated framework information interaction is discussed in detail. Finally， the edge computing task allocation model of regional electricity retailers is established. The information transmission performance and computational performance of edge computing nodes are analyzed using an example. The result shows that the proposed architecture is superior to the traditional cloud computing method， which provides a new idea for the electricity retailers to formulate the calculation and analysis method of the electricity package.

Key words: edge computing, regional electricity retailers, cloud platform, information interaction, time delay