Efficient Multi-task offloading with energy and computational resources optimization in a mobile edge computing node

Abstract

<span>With the fifth-generation (5G) networks, Mobile edge computing (MEC) is a promising paradigm to provide near computing and storage capabilities to smart mobile devices. In addition, mobile devices are most of the time battery dependent and energy constrained while they are characterized by their limited processing and storage capacities. Accordingly, these devices must offload a part of their heavy tasks that require a lot of computation and are energy consuming. This choice remains the only option in some circumstances, especially when the battery drains off. Besides, the local CPU frequency allocated to processing has a huge impact on devices energy consumption. Additionally, when mobile devices handle many tasks, the decision of the part to offload becomes critical. Actually, we must consider the wireless network state, the available processing resources at both sides, and particularly the local available battery power. In this paper, we consider a single mobile device that is energy constrained and that retains a list of heavy offloadable tasks that are delay constrained. Therefore, we formulated the corresponding optimization problem, and proposed a Simulated Annealing based heuristic solution scheme. In order to evaluate our solution, we carried out a set of simulation experiments. Finally, the obtained results in terms of energy are very encouraging. Moreover, our solution performs the offloading decisions within an acceptable and feasible timeframes.</span>

A data quarantine model to secure data in edge computing

“…It is necessary to address these issues immediately since their impact can propagate from one edge node to another and reduce the performance by affecting the data analysis process. In addition, it would be challenging to identify the root cause and results in additional repair costs and delay recovery [18]. Hence, we propose an analytical method to detect integrity attacks due to false data injection by employing a data quarantine model.…”

A comprehensive survey on nature‐inspired algorithms and their applications in edge computing: Challenges and future directions

“…The outcome of the work is to reduce the latency and energy usage of the applications with a faster response time. In Reference, 144 the authors have developed a multitask provisioning algorithm in edge networks using the SA technique. The outcomes of the work to minimize the energy usage of the applications by distributing the applications on nearby edge devices and efficiently utilize the network parameters.…”

Task Offloading in Autonomous IoT Systems using Deep Reinforcement Learning and ns3-gym

“…Several recent works have proposed solutions to solve the task offloading problem. The authors in [27], [11], [24], [17], [6], [5], [30], [2], [33] and [1] formulated task offloading as an optimization problem that they solved using heuristic methods. However, these methods are not very efficient or with an unacceptable resolution time when considering offloading scenarios with very large state space.…”

“…This reward is based on an evaluation at time t i of the cost J and represents an important part of the efficiency of the agent, especially since it ensures its convergence. We express this reward function as in (11).…”