The invention relates to a service migration method based on a particle swarm in an
edge computing environment, and belongs to the technical field of mobile communication. The method comprises the following steps: S1, modeling a
server; S2, reporting a service request: equipment sends own state information to a local network controller; S3, finding out the equipment of which the
delay does not meet the requirement: the local network controller estimates the
delay of the equipment according to the received
equipment state information and the network information collected by the state collectionmodule, and judges whether the
delay requirement of the corresponding type of task is met or not; and S4, formulating a migration decision: selecting the equipment which cannot meet the requirementsfor the
server, comprehensively considering
energy consumption and time delay in combination with factors such as task size, task type, link stability,
server state and the like, and formulating the migration decision with the maximum income. According to the invention, service migration can be triggered in real time when the equipment performance does not reach the standard, and the income of service migration is maximized while the task requirements of each piece of equipment are met.