engleski

Deadline-Aware Task Offloading and Resource Allocation in a Secure Fog-Cloud Environment

With the rapid growth of the Internet of Things (IoT) devices and the emergence of delay-sensitive task completion, task offloading in a fog-cloud environment becomes a promising solution for limitations in performing computation-intensive applications. Such a fog-cloud system should jointly consider resource allocation and task offloading to satisfy deadline requirements. Auctions are often considered a convenient tool to provide incentives for task offloading and efficiently allocate resources. However, due to virtualization, the cloud segment in the fog-cloud system is prone to malicious attacks. The deployment of security mechanisms may alleviate this issue. However, their operation consumes a part of computing capacity. In this paper, we propose a novel simulation model for deadline-aware resource allocation and task offloading in the hierarchical fog-cloud system with security considerations. Depending on the offloading primary objective, we propose two novel task offloading schemes: greedy task offloading and deadline-aware task offloading. Resource allocation of the fog and the cloud layer is based on the truthful double auction. A Vickrey-Clarke-Grove (VCG) driven resource allocation is established for winner determination. The proposed simulation model is used to analyze utility functions in the observed fog-cloud environment depending on the offered security level and the selected task offloading scheme.

Fog-cloud environment ; Task offloading ; Resource allocation ; Delay-sensitivity ; Auctions ; Security

nije evidentirano