Dependent task unloading method, terminal equipment and storage medium

By adopting the dual-channel dependent task offloading method of Actor-Critic model and GRU gated unit in an edge computing environment, the problem that the existing technology cannot effectively schedule dependent tasks is solved, and more efficient and adaptive task offloading and model generalization are achieved.

CN119645510APending Publication Date: 2025-03-18HUNAN UNIV OF SCI & TECH
0 Cites 2 Cited by

Patent Information

Application Number
CN202410147161.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-02-02
Publication Date
2025-03-18

AI Technical Summary

Technical Problem

The existing task unloading methods cannot effectively schedule interdependent tasks, resulting in relying on expert experience in the process of agent learning, insufficient self-learning ability, and inability to adapt to handle tasks in complex systems in real time.

Method used

Using a dependent task offload method based on the Actor-Critic model, the Actor network and the Critic network are initialized, heterogeneous DAG task features are integrated, scheduling actions are randomly selected, and the scheduling features are reconstructed using the GRU gated unit to realize the dual-channel decision-making mechanism, and the network parameters are constantly updated through reinforcement learning.

Benefits of technology

It realizes the optimal unloading decision while finding the optimal scheduling path of DAG tasks, improves the adaptability and computing efficiency of the task unloading algorithm, and enhances the generalization ability and stability of the model.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses a dependent task unloading method, a terminal device and a storage medium, and provides a multi-dependent task double-path dynamic unloading and scheduling scheme with two state embedding layers based on the dependent task unloading method, and characteristic vectors of a plurality of dependent tasks are captured by using a double-path GRU, so that the dynamic unloading and scheduling of the dependent tasks is realized. Remodeling the dependency task into a directed acyclic graph according to the feature vector, performing feature fusion of the multi-heterogeneous dependency task to obtain an optimal scheduling path of the multi-heterogeneous dependency task, training an unloading model according to the obtained optimal scheduling path, and making an optimal unloading decision; in consideration of the limitation of local edge model training, a new edge-cloud cooperative unloading framework is provided, and a trained unloading scheduling model in a heterogeneous edge server is uploaded to a cloud for weighted aggregation updating so as to improve the generalization ability of the model. The method has the characteristics of improving the calculation efficiency to more accurately and quickly process tasks and multi-task low-overhead processing.
Need to check novelty before this filing date? Find Prior Art