Reinforcement Learning for Security-Aware Workflow Application Scheduling in Mobile Edge Computing

Abstract

Mobile edge computing as a novel computing paradigm brings remote cloud resource to the edge servers nearby mobile users. Within one-hop communication range of mobile users, a number of edge servers equipped with enormous computation and storage resources are deployed. Mobile users can offload their partial or all computation tasks of a workflow application to the edge servers, thereby significantly reducing the completion time of the workflow application. However, due to the open nature of mobile edge computing environment, these tasks, offloaded to the edge servers, are susceptible to be intentionally overheard or tampered by malicious attackers. In addition, the edge computing environment is dynamical and time-variant, which results in the fact that the existing quasistatic workflow application scheduling scheme cannot be applied to the workflow scheduling problem in dynamical mobile edge computing with malicious attacks. To address these two problems, this paper formulates the workflow scheduling problem with risk probability constraint in the dynamic edge computing environment with malicious attacks to be a Markov Decision Process (MDP). To solve this problem, this paper designs a reinforcement learning-based security-aware workflow scheduling (SAWS) scheme. To demonstrate the effectiveness of our proposed SAWS scheme, this paper compares SAWS with MSAWS, AWM, Greedy, and HEFT baseline algorithms in terms of different performance parameters including risk probability, security service, and risk coefficient. The extensive experiments results show that, compared with the four baseline algorithms in workflows of different scales, the SAWS strategy can achieve better execution efficiency while satisfying the risk probability constraints.

Leveraging Reinforcement Learning for online scheduling of real-time tasks in the Edge/Fog-to-Cloud computing continuum

“…Other works are still focused on scheduling but targeting the energy consumption [11], [12], vehicular networks [13], [14], network resources allocation [15] or security [16].…”

Workflow Makespan Minimization for Partially Connected Edge Network: A Deep Reinforcement Learning-Based Approach

“…In addition, the traffic of transmitted data in the core network decreases significantly as tasks are executed near the end-user. Currently, there are many task offloading and resource allocation algorithms designed for edge computing under different scenarios [1,2,5], but research on workflow scheduling in edge networks is still in its infancy [6][7][8][9].…”

“…In regard to edge computing, the data transmission delay is further nonnegligible and is becoming the major bottleneck in optimizing the makespan of a workflow. The cost and makespan minimization problem of workflows in edge networks have been extensively studied in the recent years [7,9,[15][16][17]. Georgios et al [16] study the error propagation mechanism in the workflow in a fog computing environment: the authors emphasize that when imprecise evaluation of a task in the workflow exists, the error is likely to be propagated to the task's predecessor tasks and its descendants, thus resulting in error in predicting the actual makespan.…”

“…In the authors' work, a pseudo task is added as the entry point of all workflows and the makespan is optimized in a centralized manner. Huang et al [9] consider the security of the mobile edge network and schedule the tasks under the threat of malicious attacks. Here, the makespan and the encryption level are jointly optimized to achieve a tradeoff between efficiency and security.…”