Energy Aware Intelligent Task Offloading in Mobile Edge Computing Using Hyper Heuristics

To overcome the computation limitation of resource constrained wireless IoT edge devices, providing an efficient task computation offloading and resource allocation in a distributed mobile edge computing environment is considered a challenging and promising solution. The term Hyper-heuristic was mentioned in late 1960s studies. Hyper-heuristic in recent times is gaining popularity due to its general applicability of the same solution to solve different types of problems. To use a Meta-heuristic to solve a particular problem, problem-specific domain knowledge is required. However, Hyper-heuristic is rather intelligent and generic to choose appropriate heuristics with the proper sequence of execution to address a specific issue of optimization problem. Hyper-heuristic is generally a heuristic method or framework which iteratively evaluates and chooses the best low-level heuristic, to solve different types of problems. In this paper we try to optimize energy aware wireless device task offloading decisions in a mobile edge computing environment with two key criteria low energy utilization and low latency, which is a non-convex and NP-Hard problem by using a proposed novel Hyper Heuristic Framework using Stochastic Heuristic Selection (HHFSHS) using Contextual Multi-Armed Bandit (CMAB) with Epsilon-Decreasing strategy, considering two key Quality of Service (QoS) objectives computation time and energy consumption. Energy and Computation time contradict optimization parameters, where reducing computation time and latency by doing local computation at the edge device will increase the energy utilization, whereas offloading edge device task to the mobile edge server will reduce the energy utilization at the cost of increased computation time and latency incurred due to network data transfer. These multi-objective criteria are modeled as a single-objective optimization problem to minimize the latency and energy consumption of wireless devices by employing the Pareto Multi Criteria Decision Making (MCDM) strategy. Finally, evaluate its performance by comparing it with other individual meta-heuristic algorithms.