Energy-aware task scheduling optimization with deep reinforcement learning for large-scale heterogeneous systems

2021 ◽  
Author(s):  
Jingbo Li ◽  
Xingjun Zhang ◽  
Zheng Wei ◽  
Jia Wei ◽  
Zeyu Ji
Keyword(s):  
Reinforcement Learning ◽  
Task Scheduling ◽  
Large Scale ◽  
Heterogeneous Systems ◽  
Energy Aware ◽  
Scheduling Optimization

scholarly journals Revising the Observation Satellite Scheduling Problem Based on Deep Reinforcement Learning

2021 ◽  
Vol 13 (12) ◽  
pp. 2377
Author(s):  
Yixin Huang ◽  
Zhongcheng Mu ◽  
Shufan Wu ◽  
Benjie Cui ◽  
Yuxiao Duan
Keyword(s):  
Reinforcement Learning ◽  
Task Scheduling ◽  
Large Scale ◽  
Gradient Algorithm ◽  
Experimental Simulation ◽  
Scheduling Problem ◽  
Policy Gradient ◽  
Scheduling Method ◽  
Satellite Scheduling ◽  
Metaheuristic Optimization Algorithms

Earth observation satellite task scheduling research plays a key role in space-based remote sensing services. An effective task scheduling strategy can maximize the utilization of satellite resources and obtain larger objective observation profits. In this paper, inspired by the success of deep reinforcement learning in optimization domains, the deep deterministic policy gradient algorithm is adopted to solve a time-continuous satellite task scheduling problem. Moreover, an improved graph-based minimum clique partition algorithm is proposed for preprocessing in the task clustering phase by considering the maximum task priority and the minimum observation slewing angle under constraint conditions. Experimental simulation results demonstrate that the deep reinforcement learning-based task scheduling method is feasible and performs much better than traditional metaheuristic optimization algorithms, especially in large-scale problems.

scholarly journals Optimization Algorithms based Task Scheduling Method for Cloud Computing Environment

2019 ◽  
Vol 8 (3) ◽  
pp. 3608-3613
Keyword(s):  
Cloud Computing ◽  
Task Scheduling ◽  
Large Scale ◽  
Data Centers ◽  
Computing Environment ◽  
Energy Aware ◽  
Cloud Computing Environment ◽  
Scheduling Method ◽  
Consistent Performance ◽  
Computing Structure

There are various enhancements in the world of technology. Among that Cloud computing delivers numerous amenities over the Internet. It employs data centers which comprise hardware and software provision for loading, servers, and systems. The primary reason for the popularity of Cloud computing is consistent performance, economical operation, prompt accessibility, rapid scaling and much more. The chief cause for concern in cloud computing are the errors that happen either in the software or the hardware and energy consumption on a large scale. The clients pay only for resources utilized by them and assets which are accessible during the computing in a cloud setting. In the environment of cloud computing, Task scheduling is significant concepts which can be used to minimize the energy and time spent. The algorithms in Task scheduling might employ various measures toward dispense preference to subtasks that may generate many schedules to the divergent computing structure. Moreover, consumption of energy could be dissimilar for every source which is allocated to a job. This present research explores that the PSO-CA based energy aware task scheduling method can predict with the aim to enhance the resource distribution.

Sign in / Sign up

Export Citation Format

Share Document