Offloading Model Research Articles

Dependency-aware online task offloading based on deep reinforcement learning for IoV

The convergence of artificial intelligence and in-vehicle wireless communication technologies, promises to fulfill the pressing communication needs of the Internet of Vehicles (IoV) while promoting the development of vehicle applications. However, making real-time dependency-aware task offloading decisions is difficult due to the high mobility of vehicles and the dynamic nature of the network environment. This leads to additional application computation time and energy consumption, increasing the risk of offloading failures for computationally intensive and latency-sensitive applications. In this paper, an offloading strategy for vehicle applications that jointly considers latency and energy consumption in the base station cooperative computing model is proposed. Firstly, we establish a collaborative offloading model involving multiple vehicles, multiple base stations, and multiple edge servers. Transferring vehicular applications to the application queue of edge servers and prioritizing them based on their completion deadlines. Secondly, each vehicular application is modeled as a directed acyclic graph (DAG) task with data dependency relationships. Subsequently, we propose a task offloading method based on task dependency awareness in deep reinforcement learning (DAG-DQN). Tasks are assigned to edge servers at different base stations, and edge servers collaborate to process tasks, minimizing vehicle application completion time and reducing edge server energy consumption. Finally, simulation results show that compared with the heuristic method, our proposed DAG-DQN method reduces task completion time by 16%, reduces system energy consumption by 19%, and improves decision-making efficiency by 70%.

Online task offloading algorithm based on multi-objective optimization caching strategy

Within the realm of Mobile Edge Computing (MEC), task offloading has consistently garnered significant attention. Within the context of intricate caching environments and multi-user scenarios, conventional solutions frequently encounter difficulties in simultaneously fulfilling the demands for latency reduction and energy consumption optimization. This paper presents a novel online task offloading algorithm that leverages a multi-objective optimization caching strategy. This algorithm addresses two challenges: the Online Task Offloading (OTO) problem and the Online Task File Caching (OTFC) problem. The OTO problem is conceptualized as a multi-user game, where Nash equilibrium is employed to effectively characterize and address it. This ensures the determination of the optimal offloading strategy in the presence of various caching scenarios. Meanwhile, the OTFC problem is transformed into a Markov decision process, and through the utilization of Deep Q-Networks, we can forecast the requirements of online tasks and subsequently determine the optimal caching vector. The incorporation of the Multi-Objective Cache Policy (MOCP) algorithm precedes the finalization of the caching vector. Rooted in multi-objective optimization, this algorithm adeptly balances various caching decisions, achieving a Pareto optimal outcome. The proposed offloading model that effectively caters to the requirements of task offloading while incorporating the demands of task file caching. Moreover, the MOCP algorithm ensures optimal caching decisions across a broad range of scenarios. Simulation tests reveal that this enhanced offloading algorithm, grounded in multi-objective optimization, outperforms traditional methods in energy conservation, boasting energy savings of up to 15%.

Performance evaluation of adaptive offloading model using hybrid machine learning and statistic prediction

We introduce fast sensor diagnosis and focuses on intelligent offloading skills to enhance the sensor data screening efficiency. This study proposed the adaptive offloading model based on statistics-based prediction feedback and sensor candidate filtering. For the statistics-based filtering, sliding sensor grids and compounded sensor context were devised. This study also proposed hybrid prediction model using support vector machine (SVM) and k-nearest neighbors (KNN) machine training for the adaptive offloading. Therefore, the sensor information that is highly likely to be the cause of the actual device faults can be selected and transmitted, resulting in improved offloading performance. The test results through Google Colab show that the fault prediction accuracy of proposed models is 95%.

On an Intelligent Task Offloading Model to Jointly Optimize Latency and Energy for Electric Connected Vehicles

On an Intelligent Task Offloading Model to Jointly Optimize Latency and Energy for Electric Connected Vehicles

Research on collaborative edge network service migration strategy based on crowd clustering

The innovative application of Crowd Intelligent Devices (CIDS) in edge networks has garnered attention due to the rapid development of artificial intelligence and computer technology. This application offers users more reliable and low-latency computing services through computation offloading technology. However, the dynamic nature of network terminals and the limited coverage of edge servers pose challenges, such as data loss and service interruption. Furthermore, the high-speed mobility of intelligent terminals in the dynamic edge network environment further complicates the design of computation offloading and service migration strategies. To address these challenges, this paper explores the computation offloading model of cluster intelligence collaboration in a heterogeneous network environment. This model involves multiple intelligences collaborating to provide computation offloading services for terminals. To accommodate various roles, a switching strategy of split-cluster group collaboration is introduced, assigning the cluster head, the alternate cluster head, and the ordinary user are assigned to a group with different functions. Additionally, the paper formulates the optimal offloading strategy for group smart terminals as a Markov decision process, taking into account factors such as user mobility, service delay, service accuracy, and migration cost. To implement this strategy, the paper utilizes the deep reinforcement learning-based CCSMS algorithm. Simulation results demonstrate that the proposed edge network service migration strategy, rooted in groupwise cluster collaboration, effectively mitigates interruption delay and enhances service migration efficiency.

SRA-E-ABCO: terminal task offloading for cloud-edge-end environments

AbstractThe rapid development of the Internet technology along with the emergence of intelligent applications has put forward higher requirements for task offloading. In Cloud-Edge-End (CEE) environments, offloading computing tasks of terminal devices to edge and cloud servers can effectively reduce system delay and alleviate network congestion. Designing a reliable task offloading strategy in CEE environments to meet users’ requirements is a challenging issue. To design an effective offloading strategy, a Service Reliability Analysis and Elite-Artificial Bee Colony Offloading model (SRA-E-ABCO) is presented for cloud-edge-end environments. Specifically, a Service Reliability Analysis (SRA) method is proposed to assist in predicting the offloading necessity of terminal tasks and analyzing the attributes of terminal devices and edge nodes. An Elite Artificial Bee Colony Offloading (E-ABCO) method is also proposed, which optimizes the offloading strategy by combining elite populations with improved fitness formulas, position update formulas, and population initialization methods. Simulation results on real datasets validate the efficient performance of the proposed scheme that not only reduces task offloading delay but also optimize system overhead in comparison to baseline schemes.

Numerical study for slamming loads on the bow of a ship-type FPSO model under breaking waves

Numerical analyses were performed to investigate the characteristics of the slamming impact loads on the bow-flare of a ship-type floating production storage and offloading (FPSO) model under breaking waves. To estimate the slamming impact load, a series of breaking wave simulations was performed. From 2D wave flume tests, the grid aspect ratio, convection scheme, turbulence model, effect of surface tension, and grid dependencies were investigated. Through a series of numerical simulations, the grid system and numerical schemes were determined, and the slamming impact load simulations were conducted. It could be observed that the slamming impact loads and motions of the FPSO model in the numerical simulations were in good agreement with the experimental results. In order to investigate the relation between the slamming impact load and free motion of the FPSO model, the breaking impact simulations were performed under fixed positions and the free motion of the FPSO model. From the results, the relation between the relative angle and slamming impact load, as well as the relation between the position of the FPSO model and impulse response, are discussed.

Intelligent Resource Allocation and Task Offloading Model for IoT Applications in Fog Networks: A Game-Theoretic Approach

Fog computing is an emerging paradigm that allows IoT devices and applications to process their data at the network’s edge. However, fog servers have limited computational resources compared to the cloud system; therefore, they cannot accommodate the ever-increasing computational demand from IoT devices. In such a challenging environment, IoT users’ decision to offload their tasks to the fog node or the central cloud server is affected by the environment’s current dynamics as other IoT users are also competing to maximize their resource utilization. In this paper, we propose a computational model that considers energy consumption and transmission latency as decision parameters for task offloading of IoT applications. Second, we model the competition as a game where IoT devices’ decision for the optimal distribution of tasks is captured in a joint optimization problem for energy consumption and latency. Third, we propose a decentralized task distribution algorithm where the players learn to update their strategy based on other players’ actions. We also prove that the solution of the proposed algorithm converges to Nash equilibrium (NE). Finally, we carry out extensive evaluations and compare our computational model and results with existing studies.

Stackelberg game‐based task offloading in mobile edge computing‐enabled hierarchical multi‐coalition unmanned aerial vehicle networks

SummaryThe unmanned aerial vehicle (UAV) coalition networks have been widely used in emergency mission scenarios. The introduction of the mobile edge computing (MEC) paradigm into multi‐coalition UAV networks further improves the mission processing performance of UAV coalitions. In this paper, we investigate the problem of minimizing total task processing delay of UAV members in MEC‐enabled coalition‐based UAV networks. First, we propose a hierarchical offloading model in which multiple UAV heads decide its position selection strategy and multiple UAV members decide its offloading strategy when offloading tasks to UAV heads. Considering data arrival from multiple UAV member nodes at each UAV head, the first come first served (FCFS) queuing model is introduced when the UAV head processes tasks from members. Second, the hierarchical offloading delay minimization problem is formulated as a multi‐leader multi‐follower Stackelberg game. The existence of a Stackelberg equilibrium (SE) is proved by showing that multi‐leader subgame and multi‐follower subgame are exact potential games (EPGs) with Nash equilibrium (NE). We design a best response‐based hierarchical iterative offloading algorithm to solve SE. Finally, the simulation results show that the performance of the proposed scheme is better than that of other benchmark methods and the proposed scheme can effectively reduce the total delay for all UAV members.

A Deep-Reinforcement-Learning-Based Computation Offloading With Mobile Vehicles in Vehicular Edge Computing

Vehicular edge networks involves edge servers that are close to mobile devices to provide extra computation resource to complete the computation tasks of mobile devices with low latency and high reliability. Considerable efforts on computation offloading in vehicular edge networks have been developed to reduce the energy consumption and computation latency, in which roadside units (RSUs) are usually considered as the fixed edge servers. Nonetheless, the computation offloading with considering mobile vehicles as mobile edge servers in vehicular edge networks still needs to be further investigated. To this end, in this paper, we propose a deep reinforcement learning based computation offloading with mobile vehicles in vehicular edge computing, namely DRL-COMV, in which some vehicles (such as autonomous vehicle) are deployed and considered as the mobile edge servers that move in vehicular edge networks and cooperate with fixed edge servers to provide extra computation resource for mobile devices, in order to assist in completing the computation tasks of these mobile devices with great QoE (i.e.,low latency) for mobile devices. Particularly, the computation offloading model with considering both mobile and fixed edge servers is conducted to achieve the computation tasks offloading through vehicle-to-vehicle (V2V) communications, and a collaborative route planning is considered for these mobile edge servers to move in vehicular edge networks with objective of improving efficiency of computation offloading. Then, a deep reinforcement learning approach with designing rational reward function is proposed to determine the effective computation offloading strategies for multiple mobile devices and multiple edge servers with objective of maximizing both QoE (i.e., low latency) for mobile devices. Through performance evaluations, our results show that our proposed DRL-COMV scheme can achieve a great convergence and stability. Additionally, our results also demonstrate that our DRL-COMV scheme also can achieve better both QoE and task offloading requests hit ratio for mobile devices in comparison with existing approaches (i.e., DDPG, IMOPSOQ and GABDOS).

Dynamic Selection Slicing-Based Offloading Algorithm for In-Vehicle Tasks in Mobile Edge Computing

With the surge in tasks for in-vehicle terminals, the resulting network congestion and time delay cannot meet the service needs of users. Offloading algorithms are introduced to handle vehicular tasks, which will greatly improve the above problems. In this paper, the dependencies of vehicular tasks are represented as directed acyclic graphs, and network slices are integrated within the edge server. The Dynamic Selection Slicing-based Offloading Algorithm for in-vehicle tasks in MEC (DSSO) is proposed. First, a computational offloading model for vehicular tasks is established based on available resources, wireless channel state, and vehicle loading level. Second, the solution of the model is transformed into a Markov decision process, and the combination of the DQN algorithm and Dueling Network from deep reinforcement learning is used to select the appropriate slices and dynamically update the optimal offloading strategy for in-vehicle tasks in the effective interval. Finally, an experimental environment is set up to compare the DSSO algorithm with LOCAL, MINCO, and DJROM, the results show that the system energy consumption of DSSO algorithm resources is reduced by 10.31%, the time latency is decreased by 22.75%, and the ratio of dropped tasks is decreased by 28.71%.

Latency minimization for multiuser computation offloading in fog-radio access networks

Recently, the Fog-Radio Access Network (F-RAN) has gained considerable attention, because of its flexible architecture that allows rapid response to user requirements. In this paper, computational offloading in F-RAN is considered, where multiple User Equipments (UEs) offload their computational tasks to the F-RAN through fog nodes. Each UE can select one of the fog nodes to offload its task, and each fog node may serve multiple UEs. The tasks is computed by the fog nodes or further offloaded to the cloud via a capacity-limited fronhaul link. In order to compute all UEs' tasks quickly, joint optimization of UE-Fog association, radio and computation resources of F-RAN is proposed to minimize the maximum latency of all UEs. This min-max problem is formulated as a Mixed Integer Nonlinear Program (MINP). To tackle it, first, MINP is reformulated as a continuous optimization problem, and then the Majorization Minimization (MM) method is used to find a solution. The MM approach that we develop is unconventional in that each MM subproblem is solved inexactly with the same provable convergence guarantee as the exact MM, thereby reducing the complexity of MM iteration. In addition, a cooperative offloading model is considered, where the fog nodes compress-and-forward their received signals to the cloud. Under this model, a similar min-max latency optimization problem is formulated and tackled by the inexact MM. Simulation results show that the proposed algorithms outperform some offloading strategies, and that the cooperative offloading can exploit transmission diversity better than noncooperative offloading to achieve better latency performance.

Computational rate maximization for SWIPT-based mobile edge computing with alternative optimization algorithm

With the rapid integration of Intelligent Computing and Internet of Things technology (IoT), Iot sensor network devices are expected not only gather signal but also handle data computing. However, the intrinsic shortcomings of IoT devices on limited computing capacity and battery energy are the bottlenecks. Recently, Wireless Power Transmission (WPT) integrated with Mobile Edge Computing (MEC) provides an effective method for energy and computing resource allocation of IoT devices. However,the offloading ratio strategy and computing and energy resources allocation problems are challenging because the coupling of WPT and MEC, especially when the cost of feedback cannot be ignored. In this paper, we consider simultaneous power transfer and wireless information (SWIPT) strategy for an MEC powered IoT network, which allows the hybrid access point (HAP) to transfer energy by the feedback signal so that IoT devices can capture energy and receive feedback data simultaneously Firstly,the WP-MEC network model, local computation model and computation offloading model of the edge wireless devices (WDs) were built. Secondly, the causal relationship among computational rate ,network channel gain, energy transmission time and transmission power of HAP, CPU computing cycle frequency of WDs and offloading ratio allocation of local computing tasks were analyzed. Then,the above resource allocation problem was modeled as a non-convex problem and was decomposed into two convex sub-problems of offloading ratio strategy and computing and energy allocation. Finally, an alternative optimization methods were proposed to solve these two sub-problems in a sequential and the optimal solution was derived. The proposed algorithm and strategy were effective with the simulation results.

Dependent task offloading mechanism for cloud–edge-device collaboration

Edge computing provides abundant computing and storage resources at the edge of a network, aiming to meet the growing requirements of delay-sensitive mobile applications. To fully utilize the advantages of edge computing, it is essential to design an appropriate task offloading strategy to efficiently use edge resources. However, the existing studies of task offloading often ignored the dependencies between tasks and the limited service capabilities of edge servers, resulting in long completion times or even infeasible offloading decisions. Therefore, an efficient dependent task offloading mechanism that can optimize the overall task completion time is proposed in this paper. This mechanism is suitable in scenarios where edge servers have limited service caches and computing power. First, a collaborative offloading model that includes one cloud server, edge servers and local devices is designed. This model uses the cloud server as the offloading node to balance the workload among edge servers. Second, the research problem is formulated as a binary optimization function with the goal of minimizing the application completion time, and a dependent task offloading algorithm for a cloud–edge-device collaborative model is proposed. Finally, extensive experiments are performed to verify the effectiveness of the proposed model and algorithm. The experimental results show that compared with other algorithms, the proposed algorithm can reduce the application completion time by approximately 6% to 30%. In addition, the proposed dependent task offloading mechanism displays better adaptability and scalability for large-scale tasks.

Double Deep Q-Network Based Dynamic Framing Offloading in Vehicular Edge Computing

With the rapid development of Artificial Intelligence (AI) and the Internet of Vehicles (IoV), there is an increasing demand for deploying various intelligent applications on vehicles. Vehicular Edge Computing (VEC) is receiving extensive attention from both the industry and academia due to its benefits from the edge computing paradigm, which pushes computing tasks from the core of the network to the edge of the network. However, in the VEC environment considering vehicles to Road Side Units (RSUs), due to the mobility of vehicles, it is still a challenge to make dynamic and efficient offloading decisions for compute-intensive tasks, especially in the congestion situation. In order to minimize the total delay and waiting time of tasks from moving vehicles, we establish a dynamic offloading model for multiple moving vehicles whose tasks can be divided into sequential subtasks, so that the offloading decisions are more refined. Moreover, the proposed model is frame-based to avoid unnecessary waiting time, which makes offloading decisions when the subtasks of each vehicle are generated rather than offloading subtasks after gathering subtasks of vehicles for a time slot. Aiming to find the optimal offloading decision for sequential subtasks, we propose a Dynamic Framing Offloading algorithm based on Double Deep Q-Network (DFO-DDQN). Extensive experimental results demonstrate the effectiveness and superiority of the proposed DFO-DDQN when compared with other DRL-based methods and greedy-based methods.

Nonstationary response of floating structures to random waves

Even if ocean waves are treated as a stationary random process, dynamic responses of floating structures to random waves at the transient state are always nonstationary. When nonstationary response statistics is desired, a common technique is to apply Monte Carlo simulations; however, its implementation is costly in computational time. Analytically, this article develops an efficient method for computing nonstationary response statistics, including evolutionary power spectrum and time-varying mean-square values. Assuming a hydrodynamic software has been employed to get various frequency response functions, a prerequisite of the proposed method is to get the elevation-to-motion transfer function formulated in its pole-residue form. The proposed method is applicable to arbitrary wave spectrum and has been based on pole-residue operations implemented in the Laplace domain to obtain closed-form solutions for the response evolutionary power spectrum. Numerical examples choose a single-degree-of-freedom Spar model and a six-degree-of-freedom Floating Production Storage and Offloading model to a Pierson–Moskowitz wave spectrum, and the correctness of the computed mean-square values is verified by Monte Carlo simulations.

Analysis of Communication Simulation Model of Urban Comprehensive Energy Network Based on the Internet of Things

In urban construction, all energy infrastructures have been realized by the information structure. However, due to the non-uniform structure of each energy network, the data cannot be more compatible, and the communication guarantee based on the Internet of Things is one of the most urgent problems to be solved. In this paper, a reasonable network computing offloading model is designed in the edge computing layer, and the computing offloading algorithm is introduced. Considering the dependency between subtasks, an optimization problem is established, and a central scheduling algorithm is proposed to solve it. An optimized distributed unloading algorithm is proposed according to the solution idea of the classical distributed unloading algorithm. Simulation results show that the optimized distributed unloading algorithm proposed in this paper has good solving efficiency and performance, and reduces the task processing delay. At the same time, the experimental simulation proves that the efficiency of multiple edge servers in processing subtasks is higher than that of a single server. It is established that changing the convergence speed and communication delay stability margin of the system by changing the system eigenvalue is beneficial to design a better communication network structure to keep the system stable.

Everyone-Centric Heterogeneous Multi-Server Computation Offloading in ITS with Pervasive AI

The challenges of everyone-centric customized endto- end (E2E) service experience are spurring the worldwide interests on the sixth-generation (6G) networks. Nevertheless, in current intelligent transportation systems (ITS), fixed roadside units (RSUs) based multi-access edge computing (MEC) has the defects of poor flexibility, unbalanced utilization and high deployment cost, which cannot meet the diverse requirements for computation-intensive and latency-sensitive Internet of vehicles (IoV) services. In this article, we propose a novel MEC architecture with multiple heterogeneous servers and pervasive intelligence to provide computation offloading cooperatively for customized requirements of task vehicle users (TVUs). A potential game theory and federated deep reinforcement learning based approach, namely GT-FDRL, is proposed to decouple the offloading decision and resource allocation. First, a binary offloading model based on game theory is utilized to make offloading decisions. Secondly, horizontal federated learning is introduced to multiagent double deep Q-network (DDQN) to optimize the channel assignment and power allocation. Furthermore, the client-server architecture and federated aggregation are used to maintain the global model. A case study is presented and the simulation results demonstrate the effectiveness and robustness of our proposed approach.

Deep Reinforcement Learning for Scheduling and Offloading in UAV-Assisted Mobile Edge Networks

The low deployment cost and high mobility of unmanned aerial vehicles (UAV) have given UAVs widespread attention in mobile edge computing (MEC). Aiming at the characteristics of dynamic changes in computing tasks generated by the urban transportation network, this paper proposes an UAV-assisted edge computing offloading model; i.e., when the number of tasks is within the capacity of edge servers (ES), most of the tasks are processed by ESs, but when the amount exceeds the capacity, some tasks will be offloaded to UAV and processed by on-board servers on UAVs. To minimize the task delay and the cost of computing tasks, this paper formulates a mathematical model according to the task amount generated by the urban transportation network, in which the task delay is computed by using queueing theory. A deep reinforcement learning algorithm with double deep neural networks (DNN) is used to optimize the model and obtains the resource allocation strategy of UAVs and on-board servers and the offloading strategy of edge computing. Simulation experiments verify the effectiveness of these strategies.

Safety-Critical Task Offloading Heuristics for Workflow Applications in Mobile Edge Computing

As the fundamental mechanism in mobile edge computing (MEC), task offloading strategy is of great significance to the quality of computing services provided by MEC systems. When coping with workflow applications, the precedence relations among tasks increase the difficulty in developing task offloading strategies. This paper studies the problem of safety-critical task offloading for workflow applications in a MEC environment. Considering the precedence constraints on workflow tasks and the overhead of security services, we formulate the safety-critical workflow offloading model with the objective of jointly optimizing the total completion time and energy consumption. By using a task sequence to represent a feasible solution to the optimization model, we introduce a family of heuristics to solve the safety-critical workflow offloading problem under precedence constraints upon workflow tasks. Depending on whether the offloading solution satisfies the precedence relations among workflow tasks, task sequences can be classified into two categories, i.e., precedence-aware and precedence-unaware offloading solutions. With the satisfaction of precedence constraints, a family of heuristics by using a precedence-aware strategy and a precedence-unaware strategy is designed to offload safety-critical workflow tasks. Given an offloading sequence and the operating conditions of MEC servers, the heuristic algorithms select the currently best MEC server to offload workflow tasks. Experimental results justify the performance of the proposed algorithms in solving the safety-critical workflow offloading problem under precedence constraints.