A Novel Graph-Based Computation Offloading Strategy for Workflow Applications in Mobile Edge Computing

With the fast development of mobile edge computing (MEC), there is an increasing demand for running complex applications on edge. These can be represented as workflows where task dependencies are explicitly specified. To achieve better Quality Service (QoS), computation offloading widely used in MEC environment. However, many existing strategies only focus independent tasks but overlook dependencies. Meanwhile, most these based search algorithms which often time-consuming and hence not suitable delay-sensitive MEC. Therefore, a highly efficient graph-based strategy was proposed our recent work it deal with simple workflow linear (namely sequential) structure. For solving problems, novel Specifically, this nonlinear (viz. parallel, selective iterative) structures. decision plan lowest energy consumption end-device under deadline constraint found by using partition technique. We have comprehensively evaluated FogWorkflowSim platform applications. Extensive numerical results demonstrate that end device's effectively reduced 7.81% 9.51% compared PSO GA strategy. time 1% 0.2% GA, respectively.