The present invention discloses a method for collaborative scheduling of
edge computing tasks, which comprises the following steps: S1, modeling an
edge computing system, wherein the
edge computing system is divided into three
layers, which are, from bottom to top, a terminal
network layer, an edge computing layer, and a cloud layer; the terminal
network layer comprises a plurality of sensors, the edge computing layer comprises a plurality of Raspberry Pis, the plurality of Raspberry Pis form an
edge server layer, and the cloud layer is provided with an
adaptation strategy controller; S2, dividing all the above
Raspberry Pi edge servers into resource request points and
resource supply points according to whether there are computing resources remaining in the time slot; S3, modeling the request point and calculating its utility function; S4, calculating the
resource supply point RPI j Modeling is performed to find its utility function; S5, finding the Nash equilibrium of the non-cooperative game point. The present invention decomposes a large and complex task into a small and simple fine-grained task component set, thereby reducing the computing load of a
single task and optimizing the overall performance and cost of computing task
processing.