VMAgent: Scheduling Simulator for Reinforcement Learning

Abstract

A novel simulator called VMAgent is introduced to help RL researchers better explore new methods, especially for virtual machine scheduling. VMAgent is inspired by practical virtual machine (VM) scheduling tasks and provides an efficient simulation platform that can reflect the real situations of cloud computing. Three scenarios (fading, recovering, and expansion) are concluded from practical cloud computing and corresponds to many reinforcement learning challenges (high dimensional state and action spaces, high non-stationarity, and life-long demand). VMAgent provides flexible configurations for RL researchers to design their customized scheduling environments considering different problem features. From the VM scheduling perspective, VMAgent also helps to explore better learning-based scheduling solutions.

A Review on Reinforcement Learning in Production Scheduling: An Inferential Perspective

“…But in some practical application other components (such as, e.g., dispatch time and suspend time) may play important role. Therefore, validation of proposed solutions through simulation is often used (see, e.g., [78][79][80][81]). The next important co-occurred keyword in Table 3 -smart manufacturing represents the implementation domain of production scheduling based on RL.…”

On data reduction for dynamic vector bin packing

“…We used two open data sets. The first one is "Huawei-East-1" released by Huawei [30]. 1 We denote this data set Huawei.…”