Energy Efficient and Low Delay Partial Offloading Scheduling and Power Allocation for MEC

Mobile edge computing (MEC) is a promising technique to enhance the computation capacity at the edge of mobile networks. The joint problem of partial offloading decision, offloading scheduling and resource allocation for MEC systems is a challenge issue. In this paper, we investigate the problem of partial offloading scheduling and resource allocation for mobile edge computing systems with multiple independent tasks. Our goal is to minimize the weighted sum of the execution delay and energy consumption while guaranteeing the transmission power constraints of the tasks. The execution delay of tasks running in MEC and mobile edge devices are both considered. The energy consumption of both the tasks computing and task data transmission are considered as well. In order to tackle these issues, we formulate an energy-efficient and low-delay partial offloading scheduling and power allocation problem in single-user MEC systems, which is a non-convex mixed-integer optimization problem. A two-level alternation method framework based on decomposition optimization strategy is proposed. Furthermore, we propose Joint Partial Offloading scheduling and power Allocation (JPOA) iterative algorithm based on Lagrangian constrained optimization and Johnson method. Numerical results demonstrate JPOA algorithm achieves the most noticeable delay performance with a large energy consumption reduction.