Cloud Workflow Task and Virtualized Resource Collaborative Adaptive Scheduling Algorithm Based on Distributed Deep Learning
Delong Cui, Jianpeng Lin, Zhiping Peng, Qirui Li, Jieguang He, Yiheng Yuan, Mian Guo · 2020
Cloud workflow task scheduling and resource allocation are core issues in cloud computing environment. Balancing the quality of user service and the revenue of service providers is a challenge in cloud workflow task scheduling and resource allocation. Therefore, we propose a cloud workflow task and virtualized resource collaborative adaptive scheduling algorithm based on heterogeneous distributed deep learning. This solves the multi-queue multi-cluster workflow task scheduling and resource allocation problem by combining multiple heterogeneous deep neural networks as the scheduling model of the cloud system. An optimal scheduling strategy is generated by minimizing the workflow task delay and energy consumption. Results from extensive experiments show that the proposed framework can effectively solve the multi-objective optimization problem of cloud Workflow task scheduling and resource allocation, and provide a nearly optimal scheduling strategy.