Code Offloading Research Articles

Dynamic offloading for energy-aware scheduling in a mobile cloud

Mobile cloud computing (MCC) brings rich computational resources to mobile users, network operators, and cloud computing providers. The battery capacity of mobile devices poses several complex challenges, hence it is necessary to save energy by offloading applications to the remote cloud resources, especially when the scheduling is in a dynamic mobile cloud computing environment. To make a tradeoff decision involving energy consumption, deadline, and the system load, we proposed an iterated greedy taboo-mechanism algorithm (IGTMA) to solve the above issues in MCC environment. Compared to state-of-art approaches such as Adaptive First Come First Served (AFCFS), Minimize Execution Time (MINET), and tradeoff decisions for code offloading (TRADEOFF), the simulation experiment results show that our proposed IGTMA reduces energy consumption and enhances the number of finished jobs.

An Adaptive Offloading Mechanism for Mobile Cloud Computing: A Niching Genetic Algorithm Perspective

The fast evolution of mobile applications demonstrates the growing need for more resources and processing power on mobile devices. Mobile Cloud Computing (MCC) combines cloud computing with mobile devices, enabling sophisticated and resource-intensive applications to operate on mobile devices regardless of their performance limits (e.g., battery life, memory utilization, and computation). Overcoming these constraints is accomplished using a well-known technique called computation offloading, which entails offloading heavy processing to resourceful servers and getting the results from these servers. Many studies have been done on mobile code offloading, with the goal of avoiding the stated limits and reducing execution time or battery consumption through single- or multiple-site offloading, so that people can use their phones and tablets more. However, the majority of existing techniques make offloading choices based on profile data, which implies a stable network environment and forces an object to be offloaded to the same site. As a consequence of these challenges, this research proposes a novel strategy for enhancing the multisite offloading mechanism by combining a Niching Genetic Algorithm (NGA) with a Markov Decision Process (MDP). MDP is used to determine the most optimal location for each application’s modules to be executed. GA was used to determine the optimal transition probability for components operating on several sites. To aid in initial population selection, the proposed model employs a niche model in the form of a context-based clearing (CBC) technique to improve the variability of the genes inside the chromosome in order to minimize their association. The simulation results reveal that the proposed technique consumes little power and executes quickly while determining the optimal offloading decision with lower generation numbers.

Enhancing Dynamic Binary Translation in Mobile Computing by Leveraging Polyhedral Optimization

Dynamic binary translation (DBT) is gaining importance in mobile computing. Mobile Edge Computing (MEC) augments mobile devices with powerful servers, whereas edge servers and smartphones are usually based on heterogeneous architecture. To leverage high‐performance resources on servers, code offloading is an ideal approach that relies on DBT. In addition, mobile devices equipped with multicore processors and GPU are becoming ubiquitous. Migrating x86_64 application binaries to mobile devices by using DBT can also make a contribution to providing various mobile applications, e.g., multimedia applications. However, the translation efficiency and overall performance of DBT for application migration are not satisfactory, because of runtime overhead and low quality of the translated code. Meanwhile, traditional DBT systems do not fully exploit the computational resources provided by multicore processors, especially when translating sequential guest applications. In this work, we focus on leveraging ubiquitous multicore processors to improve DBT performance by parallelizing sequential applications during translation. For that, we propose LLPEMU, a DBT framework that combines binary translation with polyhedral optimization. We investigate the obstacles of adapting existing polyhedral optimization in compilers to DBT and present a feasible method to overcome these issues. In addition, LLPEMU adopts static‐dynamic combination to ensure that sequential binaries are parallelized while incurring low runtime overhead. Our evaluation results show that LLPEMU outperforms QEMU significantly on the PolyBench benchmark.

RETRACTED ARTICLE: Energy aware smartphone tasks offloading to the cloud using gray wolf optimization

In recent era, the task offloading to cloud servers from the smartphones is a promising strategy in improving the smartphones capability and its battery lifetime. The effectiveness of task offloading is found by considering the communication cost and energy consumption, which is considered as crucial factors. These two factors enables the smartphone devices to incur proper decisions whether to perform task offloading or not. In this paper, a heterogeneous framework is designed to improve the energy efficiency of mobile phones by considering various system parameters like local cloudlets, remote cloud servers, task and non-task offloading smartphone and radio access networks. The task offloading framework uses a meta-heuristic algorithm namely Gray Wolf Optimization (GWO) to schedule the task by optimizing the system parameters and this enables to make optimal decision on task offloading. The GWO does the scheduling of tasks in optimal way to enable restriction free communication between the mobile device and cloud server. This reduces the consumption of energy in mobile devices. The GWO task offloading framework is simulated using CloudSim simulation tool and the results are compared in terms of various parameters. The result shows that the GWO task offloading framework is efficient than conventional Online Code Offloading and Scheduling and Adaptive Partitioning and Dynamic Selective Offloading.

Mildip: An energy efficient code offloading framework in mobile cloudlets

The explosive growth of connected mobile devices in Edge of Things (EoT) computing offers an opportunity to support high-quality life in smart cities but also results in an extremely high energy consumption in battery limited mobile devices. Accordingly, to increase the battery life or improve performance of mobile devices, code offloading has been proposed. Moreover, with the development of the technology about low-latency and low-power of device-to-device communication, offloading codes to surrounding mobile devices in nearby cloudlets has been widely applied. However, the existing works on the mobile cloudlets mostly focus on code distribution and scheduling but ignores the affection of the energy efficiency of CPU. According to the CPU Energy/Frequency Convexity Rule, there is an optimal clock frequency that can minimize energy consumption. In recent years, a novel processor architectures with adjustable frequency have been proposed to deliver various kinds of energy efficiency and CPU performance. Taking the processor frequency into consideration, we propose an energy-efficient code offloading framework as MilDip to offload partitioned heavy tasks to around mobile devices and to operate these tasks in the state of low CPU performance and high energy efficiency. We formulate offloading problem as a mixed-integer nonlinear optimization problem, with the goal of energy efficiency maximization. Based on the formulation, we further propose a heuristic algorithm COFS based on CPU frequency scaling. Extensive simulated experiments are provided to evaluate the performance of our method. The simulation results show that up to 77% of energy can be saved by using COFS compared to the local execution. Moreover, when enough devices surround the terminal, COFS energy consumption tends to stabilize. From the experiments, we can also conclude that COFS can save more about 20% ~ 50% energy consumption comparing to other schemes.

Enabling multi-hop remote method invocation in device-to-device networks

To avoid shrinking down the performance and preserve energy, low-end mobile devices can collaborate with the nearby ones by offloading computation intensive code. However, despite the long research history, code offloading is dilatory and unfit for applications that require rapidly consecutive requests per short period. Even though Remote Procedure Call (RPC) is apparently one possible approach that can address this problem, the RPC-based or message queue-based techniques are obsolete or unwieldy for mobile platforms. Moreover, the need of accessibility beyond the limit reach of the device-to-device (D2D) networks originates another problem. This article introduces a new software framework to overcome these shortcomings by enabling routing RPC architecture on multiple group device-to-device networks. Our framework provides annotations for declaring distribution decision and out-of-box components that enable peer-to-peer offloading, even when a client app and the service provider do not have a direct network link or Internet connectivity. This article also discusses the two typical mobile applications that built on top of the framework for chatting and remote browsing services, as well as the empirical experiments with actual test-bed devices to unveil the low overhead conduct and similar performance as RPC in reality.

Practical Implementation of Femtolet Based Peer-to-Peer Network

Energy and latency aware code offloading is a demanding research area for nowadays. In this paper, for the first time we have successfully implemented the prototype of femtolet for fifth generation mobile network. Mobile devices are registered under a femtolet. The femtolet provides voice call service as well as code offloading facilities to the mobile devices. A femtolet has coverage of 10–20 m. In a particular indoor zone, there may be a number of femtolets allocated. These femtolets communicate with each other and form a peer-to-peer network. When a mobile device has to execute a resource intensive application, it requests the femtolet. If the femtolet is unable to process the task, it asks its nearby peer that is either a femtolet or a cloudlet to offload it. If the nearby peer is also unable then forwards the request to the most powerful peer i.e. the remote cloud server. The remote cloud server further executes the task. The experimental analysis shows that the proposed offloading scheme reduces the energy and latency in code offloading by approximately 10–22% and 11–14% respectively than the existing cooperative offloading model.

Efficient mobile code offloading in heterogeneous wireless networks

SummaryMobile data offloading has already appeared to offer the means of addressing the challenges of limited computing capability and battery life of mobile devices. Most existing code offloading frameworks only consider migrating an application within a single network at a time and failed to fully utilize the energy efficiency mechanism of the latest CPU chips. To tackle these issues, we propose an offloading approach under both a multitasking environment and a heterogeneous network to increase energy and execution efficiency. The offloading problem was formulated as a biobjective optimization problem that aims to save energy and keep a good performance by combining mobile cloud computing with big.LITTLE technology under a heterogeneous network equipped with cellular and WiFi connectivity. By varying the applications and network scenarios, the experimental results show that with offloading a single application using our proposed framework, the data‐intensive application can obviously benefit when the access point density of WiFi reaches 0.0002 unit/m2. Under multiple application scenarios, our proposed framework can increase processing speed by an average of 0.3× over the single application and can save an average of 25% power over the single application.

Echo: An Edge-Centric Code Offloading System With Quality of Service Guarantee

Code offloading is promising to accelerate mobile applications and save energy of mobile devices by shifting some computation to cloud. However, existing code offloading systems suffer from a long communication delay between mobile devices and cloud. To address this challenge, in this paper, we consider to deploy edge nodes in the proximity of mobile devices, and study how they benefit code offloading. We design an edge-centric code offloading system, called Echo, over a three-layer computing hierarchy consisting of mobile devices, edge and cloud. A critical problem needs to be addressed by Echo is to decide which method should be offloaded to which computing platform (edge or cloud). Different from existing offloading systems that let mobile devices individually make offloading decisions, Echo implements a centralized decision engine at the edge node. This edge-centric design can fully exploit the limited hardware resources at the edge to provide an offloading service with Quality of Service guarantee. Furthermore, we propose some novel mechanisms, e.g., lazy object transmission and differential object update, to further improve system performance. The results of a small-scale real deployment and trace-driven simulations show that Echo significantly outperforms existing

Towards a practical framework for code offloading in the Internet of Things

Mobile code offloading is a popular technique for enhancing the apparent capabilities of resource constrained devices. It is of particular interest for developers trying to push ever more complex algorithms into embedded devices that belong to the Internet of Things (IoT). Although there is much research into this area in the realm of smartphones and tablets, the same cannot be said for IoT devices, for which very few code offloading frameworks exist. This paper presents MobiCOP-IoT, an extension of the MobiCOP mobile code offloading solution for the smartphone and tablet ecosystem, that supports embedded devices and Google’s newest IoT initiative, Android Things. MobiCOP-IoT allows developers to deploy surrogates on both distant clouds and proximate nodes located on the edge. As such, MobiCOP-IoT enabled applications can take advantage of the benefits of mobile edge computing to further enhance their capabilities. We tested MobiCOP-IoT in a variety of scenarios and we found improvements of up to 9 times in terms of performance and energy for centralized cloud deployments, and up to 16 times in the case of edge scenarios. Moreover, we show the platform is capable of automatic horizontal scaling, which allows it to adapt to varying network traffic conditions; and multitenancy, wherein a single server instance is capable of attending multiple clients’ requests with minimal loss in performance.

Circa: collaborative code offloading among multiple mobile devices

For mobile users who seek extra power or computing resources to perform computation-intensive tasks, code offloading to remote infrastructures is a promising solution. However, most of the recent works mainly target on code offloading from single mobile devices to remote cloud servers, which restricts the potential of offloading only to devices with available Internet access. Moreover, offloading to remote cloud computing platforms is not always guaranteed to be time efficient and energy conserving. In this paper, we propose Circa, a framework that demonstrates the feasibility of code offloading among multiple mobile devices in the same vicinity, leveraging the presence of iBeacons. Circa eliminates the costs incurred by connecting to a remote cloud and running virtual machine instances in the cloud. With iBeacons, neighbouring devices can discover and support one another through collaborative code offloading with short-range communication, obviating the need for centralized servers . We also propose task allocation algorithms to select reliable collaborators among nearby mobile devices and disseminate the computation intensive tasks among them efficiently in a fair fashion. The performance of the task allocation algorithm is evaluated based on three different mobility models. We also implement a prototype of the Circa framework on an iOS platform and validate its feasibility and efficiency using iOS devices . According to the experimental results, by involving nearby mobile devices as collaborators, Circa is able to reduce the total execution time of an offloaded task substantially, while preserving the satisfactory performance of mobile applications .

Android Unikernel: Gearing mobile code offloading towards edge computing

Recently, Mobile Cloud Computing (MCC) which utilizes cloud to enhance mobile device’s performance, is becoming more and more popular. A typical approach of MCC is to offload some computation-intensive tasks onto cloud servers to execute and fetch results back. However, this schema suffers greatly from the long-distance network transmission latency and server boot-up latency, leading to high-delay response, which is unacceptable for most real-time applications. Mobile Edge Computing (MEC) or Mobile Fog Computing (MFC) can drastically reduce transmission latency by offloading the tasks onto the edge servers without transferring to remote data centers. However, traditional virtual machines (VM) or containers used in MCC are too heavyweight for resource-constrained environment of edge or fog servers. In this paper, we argue that enhanced unikernel can be used as task runtime in MEC or MFC to efficiently support mobile code offloading. To achieve this goal, we put forward the concept of Rich-Unikernel which aims to support various applications in one unikernel while avoiding their time-consuming recompilation. Following the design of Rich-Unikernel, we implement a not only lightweight but also flexible runtime for offloaded codes, called Android Unikernel, by integrating basic Android system libraries into OSv unikernel. Our experiment shows, compared with VM and container, Android Unikernel introduces much less boot-up delay, memory footprint, image size and energy consumption.

C2OF2N: a low power cooperative code offloading method for femtolet-based fog network

Power and delay aware cloud service provisioning to mobile devices has become a promising domain today. This paper proposes and implements a cooperative offloading approach for indoor mobile cloud network. In the proposed work mobile devices register under femtolet which is a home base station with computation and data storage facilities. The resources of the mobile devices are collaborated in such a way that different mobile devices can execute different types of computations based on cooperative federation. The proposed offloading scheme is referred as cooperative code offloading in femtolet-based fog network. If none of the mobile device can execute the requested computation, then femtolet executes the computation. Use of femtolet provides the mobile devices voice call service as well as cloud service access. Femtolet is used as the fog device in our approach. The proposed model is simulated using Qualnet version 7. The simulation results demonstrate that the proposed scheme minimizes the energy by 15% and average delay up to 12% approximately than the existing scheme. Hence, the proposed model is referred as a low power offloading approach.

Increasing the Efficiency of Code Offloading in n-tier Environments with Code Bubbling

Code offloading strives for increasing the energy efficiency and execution speed of mobile applications on resource-constrained mobile devices. First approaches only considered a code offloading between two (or three) tiers, executing code either locally on a mobile device or remotely on a powerful server. However, new execution environments comprise multiple tiers, containing highly distributed heterogeneous resources. To this end, we present our Code Bubbling Offload System (CoBOS) that targets n-tier environments containing highly distributed heterogeneous resources with different performance characteristics and cost implications. In such n-tier environments, it is very costly for a resource-constrained mobile device to gather a global view on available resources, why we propose the novel concept of code bubbling. Code bubbling moves code dynamically and adaptively toward more powerful and more distant tiers, enabling an efficient and scalable code offloading in n-tier environments. Each tier makes autonomous decisions to execute code in the tier or forward it further to the next tier. To support such a recursive escalation of code along autonomous tiers, CoBOS offloads self-contained offload requests that possess all information required for a decision-making and processing. Our real-world evaluation shows that CoBOS decreases execution time by 83% and energy consumption by 77% for code offloading in n-tier environments.

Dual-Side Optimization for Cost-Delay Tradeoff in Mobile Edge Computing

Mobile code offloading (MCO) is a technology that offloads computing tasks from mobile devices to remote servers managed by code offload service providers (CSPs). Nowadays, it is recommended that the remote servers be placed on the edge of the network to support modern applications, e.g., augmented reality, which demand stringent and ultralow latency or high bandwidth. To date, previous studies have independently addressed code offloading policy in mobile devices and pricing/server provisioning policies in the CSP; moreover, the system models for both user side and CSP side have not adequately reflected their practical aspects. This paper designs a practical model for the both sides and takes account of them in an integrated MCO framework simultaneously. By leveraging Lyapunov drift-plus-penalty technique, we propose code offloading, local CPU clock frequency, and network interface selection policies for mobile users, and propose MCO service pricing and server provisioning policies for the CSP in each of a competition scenario and a cooperation scenario. In the competition scenario, we propose a Com-UC algorithm for mobile users and a Com-PC algorithm for the CSP with the aim to minimize each cost for each queue stability constraint. In the cooperation scenario, we propose a Coo-JC algorithm with the aim to minimize their sum cost for both mobile users and CSP. Via trace-driven simulations, we demonstrate that Com-UC saves at most 71% of its cost and Com-PC attains 82% profit gain for the same delay compared to existing algorithms; moreover, the cooperation between mobile users and CSP additionally reduces costs and delays.

An Online Algorithm for Task Offloading in Heterogeneous Mobile Clouds

Mobile cloud computing is emerging as a promising approach to enrich user experiences at the mobile device end. Computation offloading in a heterogeneous mobile cloud environment has recently drawn increasing attention in research. The computation offloading decision making and tasks scheduling among heterogeneous shared resources in mobile clouds are becoming challenging problems in terms of providing global optimal task response time and energy efficiency. In this article, we address these two problems together in a heterogeneous mobile cloud environment as an optimization problem. Different from conventional distributed computing system scheduling problems, our joint offloading and scheduling optimization problem considers unique contexts of mobile clouds such as wireless network connections and mobile device mobility, which makes the problem more complex. We propose a context-aware mixed integer programming model to provide off-line optimal solutions for making the offloading decisions and scheduling the offloaded tasks among the shared computing resources in heterogeneous mobile clouds. The objective is to minimize the global task completion time (i.e., makespan). To solve the problem in real time, we further propose a deterministic online algorithm—the Online Code Offloading and Scheduling (OCOS) algorithm—based on the rent/buy problem and prove the algorithm is 2-competitive. Performance evaluation results show that the OCOS algorithm can generate schedules that have around two times shorter makespan than conventional independent task scheduling algorithms. Also, it can save around 30% more on makespan of task execution schedules than conventional offloading strategies, and scales well as the number of users grows.

Augmentation Techniques for Mobile Cloud Computing

Despite the rapid growth of hardware capacity and popularity in mobile devices, limited resources in battery and processing capacity still lack the ability to meet increasing mobile users’ demands. Both conventional techniques and emerging approaches are brought together to fill this gap between user demand and mobile devices’ limited capabilities. Recent research has focused on enhancing the performance of mobile devices via augmentation techniques. Augmentation techniques for mobile cloud computing refer to the computing paradigms and solutions to outsource mobile device computation and storage to more powerful computing resources in order to enhance a mobile device’s computing capability and energy efficiency (e.g., code offloading). Adopting augmentation techniques in the heterogeneous and intermittent mobile cloud computing environment creates new challenges for computation management, energy efficiency, and system reliability. In this article, we aim to provide a comprehensive taxonomy and survey of the existing techniques and frameworks for mobile cloud augmentation regarding both computation and storage. Different from the existing taxonomies in this field, we focus on the techniques aspect, following the idea of realizing a complete mobile cloud computing system. The objective of this survey is to provide a guide on what available augmentation techniques can be adopted in mobile cloud computing systems as well as supporting mechanisms such as decision-making and fault tolerance policies for realizing reliable mobile cloud services. We also present a discussion on the open challenges and future research directions in this field.

MobiCOP: A Scalable and Reliable Mobile Code Offloading Solution

Code offloading is a popular technique for extending the natural capabilities of mobile devices by migrating processor‐intensive tasks to resource‐rich surrogates. Despite multiple platforms for offloading being available in academia, these frameworks have yet to permeate the industry. One of the primary reasons for this is limited experimentation in practical settings and lack of reliability, scalability, and options for distribution. This paper introduces MobiCOP, a new code offloading framework designed from the ground up with these requirements in mind. It features a novel design fully self‐contained in a library and offers compatibility with most stock Android devices available today. Compared to local task executions, MobiCOP offers performance improvements of up to 17x and increased battery efficiency of up to 25x, shows minimum performance degradation in environments with unstable networks, and features an autoscaling module that allows its server counterpart to scale to an arbitrary number of offloading requests. It is compatible with the most relevant Android technologies optimized for heavy computation (NDK and Renderscript) and has so far been well received by fellow mobile developers. We hope MobiCOP will help bring mobile code offloading closer to the industry realm.

Accelerating Linux and Android applications on low‐power devices through remote GPGPU offloading

SummaryLow‐power devices are usually highly constrained in terms of CPU computing power, memory, and GPGPU resources for real‐time applications to run. In this paper, we describe RAPID, a complete framework suite for computation offloading to help low‐powered devices overcome these limitations. RAPID supports CPU and GPGPU computation offloading on Linux and Android devices. Moreover, the framework implements lightweight secure data transmission of the offloading operations. We present the architecture of the framework, showing the integration of the CPU and GPGPU offloading modules. We show by extensive experiments that the overhead introduced by the security layer is negligible. We present the first benchmark results showing that Java/Android GPGPU code offloading is possible. Finally, we show the adoption of the GPGPU offloading into BioSurveillance, a commercial real‐time face recognition application. The results show that, thanks to RAPID, BioSurveillance is being successfully adapted to run on low‐power devices. The proposed framework is highly modular and exposes a rich application programming interface to developers, making it highly versatile while hiding the complexity of the underlying networking layer.

Reduction of Complexity of On-Board Embedded Robotic System Processors Using Code Offloading

Appearance of highly intelligent and advanced robots that react and recognize to their environment has lead to the increment in the complexity of the embedded systems that govern their reaction. This developing multifaceted nature, over a timeframe, has influenced the general responsiveness and battery life of the robot. From controlling a drone to an internet controlled coffee maker, an on-board processor for the calculation of all control signs is required for setting off a reaction to the stimuli. At the point when the unpredictability of the embedded system rises, more convoluted computation is required to react to those inputs. This has not only reduced the general responsiveness and battery life of the robot but also has additionally prompted the need of overhauling the equipment to suit the upsurge in the calculation required. The solution to this problem is by offloading the critical tasks like control signal computation or image processing to a centralized server which would eliminate the requirement of complex on-board processors. A comprehensive analysis is presented on the feasibility of such code offloading in embedded robotic systems and its applicability to other domains is discussed. The obtained results will be compared to the results obtained in other domains involving code offloading and analysed to strike out any patterns in their results.