A LSTM Approach for Secure Energy Efficient Computational Offloading in Mobile Edge Computing

Mobile devices may use mobile edge computing to improve energy efficiency and responsiveness by offloading computation tasks to edge servers. However, the transmissions of mobile devices may result in interference that decreases the upload rate and prolongs transmission delay. Clustering has been shown as an effective approach to improve the transmission efficiency for dense devices, but there is no distributed algorithm for the optimization of clustering and computation offloading. In this work, we study the optimization problem of computation offloading to minimize the energy consumption of mobile devices in mobile edge computing by adaptively clustering devices to improve the transmission efficiency. To address the optimization problem in a distributed manner, the decision problem of clustering and computation offloading for mobile devices is formulated as a potential game. We introduce the construction of the potential game and show the existence of Nash equilibrium in the game with a finite enhancement ability. Then, we propose a distributed algorithm of clustering and computation offloading based on game theory. We conducted a simulation to evaluate the proposed algorithm. The numerical results from our simulation show that our algorithm can improve offloading efficiency for mobile devices in mobile edge computing by improving transmission efficiency. By offloading more tasks to edge servers, both the energy efficiency of mobile devices and the responsiveness of computation-intensive applications can be improved simultaneously.

Task offloading and scheduling is an important issue in mobile edge computing (MEC). A good offloading decision can fully utilize the computing capabilities of edge servers to deliver high-quality computing services. This paper takes into account the concerns about task processing latency and mobile device's energy consumption, and formulates the task offloading problem as a deadline-constrained energy-minimization integer program. We propose a partial offloading and scheduling method based on the whale optimization algorithm to solve the formulated optimization problem. This method employs a probability model-based mapping operator to convert an individual whale into a valid offloading solution represented by a task sequence. This mapping scheme is advantageous over sorting-based rules in producing high-quality task sequence. We develop an efficient heuristic strategy to decide each task should be processed locally on the mobile device or offloaded to the edge server for execution. With all tasks in the sequence having been scheduled, the mobile device's energy consumption for task execution and data transmission can be calculated. Accordingly, we can identify the best individual whale in the population leading to the solution with lowest energy consumption. We iteratively apply the population updating rule to explore better task sequence and offloading solution. We perform extensive experiments to verify that the proposed algorithm achieves more energy-efficient offloading solutions as compared to baseline algorithms while satisfying the deadline constraint.

These days, more and more web are converting into mobile devices such as the internet of things (IoT). These applications are distributed in nature and installed on mobile and servers to achieve many business goals. With this motivation, mobile edge computing (MEC) is an evolving paradigm that reduces the energy consumption of mobile devices through the offload process. However, currently all studies only concentrated on mobile energy and widely overlooked the energy usage of the computing node resources and application deadlines during offloading and scheduling in the MEC network. This research suggests a new mobile edge cloud (mob-cloud) architecture that minimises the nodes energy and meets the deadline requirements of applications. This research formulates this problem as the convex optimisation problem under linear integer programming. The mob-cloud consists of different types of virtual machines which are implementing at the edge computing. This study introduces a novel deadline and energy-efficient task scheduling (DEETS) algorithm framework consisting of task sequencing, resource searching, and mobility-aware scheduling. Furthermore, DEETS keeps tradeoff performances between resource energy usage and task deadline. Simulation results show that the proposed DEETS outperformed all contemporary methods regarding energy usage and deadlines of applications by 50%.

This thesis collects a selective set of outcomes of a PhD course in Electronics, Telecommunications, and Information Technologies Engineering and it is focused on designing techniques to optimize computational resources in different wireless communication environments. Mobile Edge Computing (MEC) is a novel and distributed computational paradigm that has emerged to address the high users demand in 5G. In MEC, edge devices can share their resources to collaborate in terms of storage and computation. One of the computational sharing techniques is computation offloading, which brings a lot of advantages to the network edge, from lower communication, to lower energy consumption for computation. However, the communication among the devices should be managed such that the resources are exploited efficiently. To this aim, in this dissertation, computation offloading in different wireless environments with different number of users, network traffic, resource availability and devices' location are analyzed in order to optimize the resource allocation at the network edge. To better organize the dissertation, the studies are classified in four main sections. In the first section, an introduction on computational sharing technologies is given. Later, the problem of computation offloading is defined, and the challenges are introduced. In the second section, two partial offloading techniques are proposed. While in the first one, centralized and distributed architectures are proposed, in the second work, an Evolutionary Algorithm for task offloading is proposed. In the third section, the offloading problem is seen from a different perspective where the end users can harvest energy from either renewable sources of energy or through Wireless Power Transfer. In the fourth section, the MEC in vehicular environments is studied. In one work a heuristic is introduced in order to perform the computation offloading in Internet of Vehicles and in the other a learning-based approach based on bandit theory is proposed.

Mobile Edge Computing is a new technology which aims to reduce latency, to ensure highly efficient network operation and to offer an improved user experience. Considering offloading will introduce additional wireless transmission overhead, the key technical challenge of mobile edge computing is tradeoff between computation cost and wireless transmission cost, reducing energy consumption of mobile edge devices and response time of computation task at the same time. A Mobile Edge Computing System composed of Mobile Edge Device and Edge Cloud, connecting with Wireless Stations, comes out. To protect user privacy, Data Preprocessing is proposed which includes irrelevant property clean and data segmentation. Aimed at reducing total energy consumption and response time, an energy consumption priority offloading (ECPO) algorithm and a response time priority offloading (RTPO) algorithm are put forward, based on Energy Consumption Model and Response Time Model. Combining both ECPO and RTPO, a dynamic computing offloading algorithm is raised which is more universal. Finally, simulations in four scenarios, including network normal scenario, network congested scenario, device low battery scenario and task time limited scenario, demonstrate that our algorithms can effectively reduce energy consumption of mobile edge device and response time of computation task.

As the network becomes dense, multi-server mobile edge computing (MEC) systems with multiple candidate MEC servers, bring new opportunities to enrich user experience through computation offloading. Specifically, MEC server selection, as a new dimension, arises to strike a well balance between energy consumption and task execution delay of mobile device (MD). Since channel conditions between the MD and MEC server (or its connected access point) as well as available computing capability at MEC servers are time-varying, this paper aims to devise dynamic computation offloading mechanism to account for delay-energy tradeoffs in multi-server MEC systems. To this end, we jointly optimize transmit power and MEC server selection for the MD to minimize time average expected task execution delay, under the constraint of average energy consumption. With partial current network status available, we then combine Lyapunov optimization framework and multi-armed bandit framework for an online learning based computation offloading algorithm, whose feasibility and regret bound are given through theoretical analyses. Finally, simulation results are presented to demonstrate its efficiency and superiority.

Mobile edge computing (MEC) is an emerging paradigm to meet the growing computing needs from mobile applications. By offloading computing intensive mobile application tasks to MEC server, users can experience low latency, low energy consumption and high reliability services. However, due to the limited battery capacity on the device, task execution will be interrupted when the battery energy is exhausted. To solve the above problems, a task offloading strategy based on energy aware is proposed. In the scenario of multi-user and single server, the total queuing cost in the process of mobile device requesting service is analyzed by using queuing theory. Then, the mathematical model of the scene is established, and the linear weighting and objective function of time delay and energy consumption of mobile device are designed. In order to optimize the objective function and obtain the optimal solution, an improved genetic algorithm (Ga Energy Aware, GEA) is proposed. Simulation results show that the algorithm can effectively reduce the power consumption and task execution delay of mobile device.

In mobile edge computing (MEC), mobile devices can choose to offload their tasks to edge servers for execution, thereby effectively reducing the completion time of tasks and energy consumption of mobile devices. However, most of the data transfer brought by offloading relies on wireless communication technology, making the private information of mobile devices vulnerable to eavesdropping and monitoring. Privacy leakage, especially the location and association privacies, can pose a significant risk to users of mobile devices. Therefore, protecting the privacy of mobile devices during task offloading is important and cannot be ignored. This paper considers both location privacy and association privacy of mobile devices during task offloading in MEC and targets to reduce the leakage of location and association privacy while minimizing the average completion time of tasks. To achieve these goals, we design a privacy-preserving task offloading scheme to protect location privacy and association privacy. The scheme is mainly divided into two parts. First, we adopt a proxy forwarding mechanism to protect the location privacy of mobile devices from being leaked. Second, we select the proxy server and edge server for each task that needs to be offloaded. In the proxy server selection policy, we make a choice based on the location information of proxy servers, to reduce the leakage risk of location privacy. In the edge server selection strategy, we consider the privacy conflict between tasks, the computing ability, and location of edge servers, to reduce the leakage risk of association privacy plus the average completion time of tasks as much as possible. Simulated experimental results demonstrate that our scheme is effective in protecting the location privacy and association privacy of mobile devices and reducing the average completion time of tasks compared with the-state-of-art techniques.

Computationally intensive and latency sensitive applications put forward strict requirements on mobile user equipments (UEs) to provide the required computation capacity and delay. Mobile edge computing (MEC) in ultra-dense network (UDN) is considered as a promising solution that can reduce the computation limitations of UEs and extend their battery life by computation offloading. But the dense deployment of UEs, and the limited resources of small cell base stations (SBSs), which imposes more delays on computation offloading in MEC environment. In this paper, using the characteristics of UDN, we study the computation offloading management scheme based on the weighted sum of task completion time and energy consumption in MEC system. Then, we propose a computation offloading framework and formulate joint task offloading and resource allocation problem in UDNs to minimize overall cost consumption. Based on Genetic algorithm (GA) and Whale optimization algorithm (WOA), we adopt a heuristic algorithm named as GAWOA to solve this problem. Numerical results show that the algorithm has a fast convergence speed and better performance than other benchmark algorithms.

A Novel Lyapunov based Dynamic Resource Allocation for UAVs-assisted Edge Computing

This paper considers the computation offloading and resource allocation for system sum cost minimization in a mobile edge computing (MEC)network. The computation offloading decision of the user equipments (UEs)can be made through wireless link to access the MEC server. Our intent is to minimize the weighted sum cost of the system, which takes into account the energy consumption and time delay, for both task processing and data transmissions, subject to the force delay requirement of the devices. We first formulate the problem as a mixed-integer and non-convex optimization scheme. Enlightened by the superior performance of reinforcement learning (RL)on solving resource control problems, we put forward a novel RL-based scheme for computation offloading and resource allocation in MEC network. Specifically, the MEC node is considered as an “agent”, which first makes decision on whether to offloading the computing task to the MEC server, and then utilizes convex optimization algorithms to settle the radio spectrum and computation resource scheduling problem in each decision phase. The simulation results present that the RL-based method can achieve better computation offloading and resource allocation performance compared to those of local computing and remote computing modes. It also achieves very similar or slightly better performance compared to the genetic algorithm based method.

Deep Neural Networks meet computation offloading in mobile edge networks: Applications, taxonomy, and open issues

In mobile edge computing (MEC), mobile devices limited to computation and memory resources offload compute-intensive tasks to nearby edge servers. User movement causes frequent handovers in 5G urban networks. The resultant delays in task execution due to unknown user position and base station lead to increased energy consumption and resource wastage. The current MEC offloading solutions separate computation offloading from user mobility. For task offloading, techniques that predict the user’s future location do not consider user direction. We propose a framework termed COME-UP Computation Offloading in mobile edge computing with Long-short term memory (LSTM) based user direction prediction. The nature of the mobility data is nonlinear and leads to a time series prediction problem. The LSTM considers the previous mobility features, such as location, velocity, and direction, as input to a feed-forward mechanism to train the learning model and predict the next location. The proposed architecture also uses a fitness function to calculate priority weights for selecting an optimum edge server for task offloading based on latency, energy, and server load. The simulation results show that the latency and energy consumption of COME-UP are lower than the baseline techniques, while the edge server utilization is enhanced.

To enhance the security in the computational offloading process of Mobile Edge Computing (MEC) systems, this paper proposes a physical layer secure transmission scheme based on Intelligent Reflecting Surface (IRS) assistance. In this scheme, IRS is added to facilitate the task transfer between the user and the MEC server, while suppressing eavesdroppers from eavesdropping on user information, thus achieving a secure computing offload for the system. In order to maximize the safe transmission rate of the system, a flow-form optimization algorithm based on alternating optimization and conjugate gradient is designed to obtain the users transmit power as well as the phase shift of the IRS. Based on this, the computational offload rate of users and the computational resources of MEC servers are optimized by heuristic algorithms to minimize the computational offload delay of MEC systems while ensuring secure transmission. Simulation results show that the proposed scheme can reduce the total computational offload delay while guaranteeing secure transmission of the MEC system compared with other benchmark schemes and traditional artificial noise assisted schemes.

A comprehensive review of computation offloading in UAV-assisted mobile edge computing for IoT applications