A Deep Reinforcement Learning Approach to the Optimization of Data Center Task Scheduling

Abstract

With more businesses are running online, the scale of data centers is increasing dramatically. The task-scheduling operation with traditional heuristic algorithms is facing the challenges of uncertainty and complexity of the data center environment. It is urgent to use new technology to optimize the task scheduling to ensure the efficient task execution. This study aimed at building a new scheduling model with deep reinforcement learning algorithm, which integrated the task scheduling with resource-utilization optimization. The proposed scheduling model was trained, tested, and compared with classical scheduling algorithms on real data center datasets in experiments to show the effectiveness and efficiency. The experiment report showed that the proposed algorithm worked better than the compared classical algorithms in the key performance metrics: average delay time of tasks, task distribution in different delay time levels, and task congestion degree.

Reinforcement learning based resource management for fog computing environment: Literature review, challenges, and open issues

“…Recently, the collaboration between deep learning and RL can further enhance the capabilities of resulting deep RL (DeepRL) approaches which achieves outstanding performance in complex control fields strongly shows its superiority of decision making in complex and uncertain environment [21], [22]. For example, such a DeepRL algorithm is developed to optimize the task scheduling in the data center [23]. The resource allocation problem is also tackled by using a DeepRL algorithm to achieve the optimal job-virtual machine scheduling in the cloud [24].…”

Machine Learning Empowered Intelligent Data Center Networking: A Survey

“…Therefore, a few researchers have begun to apply machine learning to solve these problems. Che et al performed task scheduling based on the actor-critic deep reinforcement learning algorithm to optimize resource utilization and task completion time [193]. Telenyk et al [211] used the Q-learning algorithm for global resource management, and realized resource optimization and energy saving through virtual machine scheduling and virtual machine aggregation.…”

“…Reliability Energy Efficiency Bandwidth Utilization Latency Security Stability Scalability Wang et al [191] YES NO YES YES NO YES NO Che et al [193] NO NO NO YES NO YES NO Liu et al [188] NO YES YES YES NO YES NO Tesauro et al [185] NO NO YES YES NO YES NO Liu et al [196,197] YES YES YES YES NO YES YES Yang et al [199] NO tifaceted. Along with the expansion of service scenarios, the resource scheduling among various virtualized entities is getting more complicated.…”

Makespan Optimisation in Cloudlet Scheduling with Improved DQN Algorithm in Cloud Computing

“…e algorithm implied QS-TDMA to be an approaching optimal TS algorithm that potentially enhanced real-time WSN performance. In [20], Che et al recommended a novel TS model with the deep RL (DRL) algorithm that incorporated TS into resource-utilisation (RU) optimisation.…”