The invention relates to the technical field of edge computing, and discloses an edge computing optimization method based on a big data network, and the method comprises the steps: S1, collecting network data in an edge computing environment, and carrying out the preprocessing of the collected data, including data cleaning, duplicate removal and format conversion; s2, storing and analyzing the preprocessed data, wherein the data analysis comprises data exploration, data mining and model prediction; s3, task decomposition: task scheduling is carried out according to data processing requirements and the assessed edge device capability, and calculation tasks are reasonably distributed to edge devices; and S4, collecting feedback of a task execution result and feeding back the feedback to the user, and adjusting the edge computing environment according to a task completion result. Data processing is carried out on the edge device, tasks are decomposed, the data transmission distance and time are reduced, meanwhile, the performance and the energy efficiency are optimized, and a fuzzy evaluation model is adopted to meet the requirement for edge device capability evaluation in different scenes.