关键词： Task analysis   Resource management   Servers   Computational modeling   Bandwidth   Vectors   Uncertainty   Intelligent reflecting surface (IRS)   mobile edge computing   partial offloading   online ridge regression   multi-armed bandit  

摘要： In the ever-evolving realm of wireless communications, the integration of intelligent reflecting surface (IRS) and mobile edge computing for task offloading has ignited extensive curiosity. However, previous research primarily concentrated on task offloading assuming that a user equipment (UE) possesses the system channel information and the computing resources of base stations (BSs). Acknowledging that UEs typically lack access to such system information, and in pursuit of equilibrium in computing loads between UEs and BSs, we present a bilateral online task allocation approach grounded in partial offloading to minimize task completion latency. Specifically, addressing uncertainties in channel information and available computing resources at BSs, we employ the online ridge regression method on the UE side to continuously adjust the task allocation proportion for offloading to BSs. On the IRS side, we formulate the BS selection as a multi-armed bandit problem, proposing an online learning algorithm based on Thompson sampling to determine the set of BSs for edge computing while managing the task allocation among the selected BSs. Simulation results demonstrate the superior performance of our algorithm.

关键词： Servers   Cloud computing   Task analysis   Computer architecture   Edge computing   Optimization   Costs   Computation offloading   edge computing   mobile edge computing   mobility management   resource allocation  

摘要： Mobile edge computing (MEC) is a promising technology that aims to reduce the total latency of user equipment (UE) by deploying computation resources at the edge of mobile networks. UE mobility is a challenging factor that causes the traditional MEC architecture to suffer from several issues, such as decreased efficiency and frequent service interruptions. One popular method to manage UE mobility is virtual machine (VM) migration, which requires high bandwidth and causes undesirable latency, rendering it impractical for real-time tasks with stringent latency requirements. This paper proposes a hierarchical architecture for MEC networks that facilitates mobility management and mitigates the need for VM migration. In order to utilize this architecture efficiently, a Markov chain-based predictive strategy is introduced to predict UE mobility. Afterward, an optimization problem is formulated to make the optimal long-term offloading decisions for UEs such that their expected cost is minimized subject to latency commitments and resource consumption constraints. Simulation results demonstrate that the proposed scheme reduces the cost of high-mobility UEs by up to 25% compared to traditional schemes. Furthermore, the measures of movement direction predictability and offloading decision popularity are introduced that provide insights into the behavior of the proposed and counterpart schemes.

关键词： mobile edge computing   crowdsourcing   incentive mechanism  

摘要： Crowdsourcing becomes a popular data -collection method to relieve the burden of high cost and latency for data -gathering. Since the involved users in crowdsourcing are volunteers, need incentives to encourage them to provide data. However, the current incentive mechanisms mostly pay attention to the data quantity, while ignoring the data quality. In this paper, we design a Data -quality awaRe IncentiVe mEchanism (DRIVE) for collaborative tasks based on the Stackelberg game to motivate users with high quality, the highlight of which is the dynamic reward allocation scheme based on the proposed data quality evaluation method. In order to guarantee the data quality evaluation response in real-time, we introduce the mobile edge computing framework. Finally, one case study is given and its real -data experiments demonstrate the superior performance of DRIVE.

关键词： Federated learning   mobile edge computing   cloud radio access network   resource allocation   SDR method  

摘要： In this paper, a mobile edge computing (MEC) assisted multi-layer architecture is proposed to support the implementation of federated learning in Internet of Things (IoT) networks. In this architecture, when performing a federated learning based task, data samples can be partially offloaded to MEC servers and cloud server rather than only processing the task at the IoT devices. After collecting local model parameters from devices and MEC servers, cloud server makes an aggregation and broadcasts it back to all devices. An optimization problem is presented to minimize the total federated training latency by jointly optimizing decisions on data offloading ratio, computation resource allocation and bandwidth allocation. To solve the formulated NP hard problem, the optimization problem is converted into quadratically constrained quadratic program (QCQP) and an efficient algorithm is proposed based on semidefinite relaxation (SDR) method. Furthermore, the scenario with the constraint of indivisible tasks in devices is considered and an applicable algorithm is proposed to get effective offloading decisions. Simulation results show that the proposed solutions can get effective resource allocation strategy and the proposed multi-layer federated learning architecture outperforms the conventional federated learning scheme in terms of the learning latency performance.

关键词： satellite edge computing   earth observation satellite   task offloading   mobile edge computing  

摘要： Satellite edge computing (SEC) plays an increasing role in earth observation, due to its global coverage and low-latency computing service. In SEC, it is pivotal to offload diverse observation-data-processing tasks to the appropriate satellites. Nevertheless, due to the sparse intersatellite link (ISL) connections, it is hard to gather complete information from all satellites. Moreover, the dynamic arriving tasks will also influence the obtained offloading assignment. Therefore, one daunting challenge in SEC is achieving optimal offloading assignments with consideration of the dynamic delay-sensitive tasks. In this paper, we formulate task offloading in SEC with delay-sensitive tasks as a mixed-integer linear programming problem, aiming to minimize the weighted sum of deadline violations and energy consumption. Due to the limited ISLs, we propose a fully-decentralized method, called the PI-based task offloading (PITO) algorithm. The PITO operates on each satellite in parallel and only relies on local communication via ISLs. Tasks can be directly offloaded on board without depending on any central server. To further handle the dynamic arriving tasks, we propose a re-offloading mechanism based on the match-up strategy, which reduces the tasks involved and avoids unnecessary insertion attempts by pruning. Finally, extensive experiments demonstrate that PITO outperforms state-of-the-art algorithms when solving task offloading in SEC, and the proposed re-offloading mechanism is significantly more efficient than existing methods.

关键词： Backscatter   Batteries   Switches   Servers   Protocols   Task analysis   Interference   Mobile edge computing   backscatter communication   user reciprocity   resource allocation  

摘要： This article proposes a new cooperative offloading protocol termed "user reciprocity" for backscatter communication (BackCom)-aided mobile edge computing (MEC) systems, whose quintessence is that each user can switch alternately between the active or the BackCom mode in different slots, and one user works in the active mode and the other user works in the BackCom mode in each time slot. Specifically, the user in the BackCom mode can always use the signal transmitted by the user in the active mode for more data transmission in a spectrum-sharing manner. To evaluate the proposed protocol, a computation efficiency (CE) maximization-based optimization problem is formulated by jointly power control, time scheduling, power reflection coefficient (RC) adjustment, and computing frequency allocation, while adhering to constraints on energy budgets, computing frequency thresholds, minimum computed bits, and harvested energy. To solve this non-convex problem, Dinkelbach's method and quadratic transform are first employed to transform the complex fractional forms into linear ones. Then, an iterative algorithm is designed by decomposing the resulting problem to obtain the suboptimal solution. For analytical insights, we not only provide some closed-form solutions, but also derive the analytical performance gain with reciprocal mode. Simulation results demonstrate that the proposed scheme outperforms benchmark schemes regarding the CE.

关键词： Deep reinforcement learning   Mobile edge computing   Unmanned aerial vehicle   Counterfactual inference   Whale optimization algorithm  

摘要： In heterogeneous wireless networks, massive user equipments (UEs) generate computing tasks with timevarying heterogeneous requirements. To improve the service quality, this paper formulates a unmanned aerial vehicles (UAVs)-assisted mobile edge computing (MEC) framework for time -varying heterogeneous task requirements. In the framework, the task delay and the number of successfully executed tasks are optimized by jointly controlling the trajectories of multiple UAVs. To address the considered trajectory planning optimization problem, a collaborative multi -agent deep reinforcement learning (MADRL) algorithm is proposed, where each UAV is regarded as a learning agent. First, a counterfactual inference based personalized policy update mechanism is proposed to evaluate the independent policy of agents by comparing the policy with a designed counterfactual policy. Based on this idea, each agent updates a personalized policy from both group and individual interests to improve its cooperation ability in dynamic and complex environments. Then, a diversified experience sampling mechanism is proposed to enhance the efficiency of policy evaluation and update with rich experiences provided by the environment interaction and the modified whale optimization algorithm. Finally, evaluation results demonstrate the superiority and effectiveness of the proposed MADRL algorithm.

关键词： integrated sensing and communication   UAV   mobile edge computing   wireless energy harvesting   genetic algorithm   successive convex approximation algorithm  

摘要： In this paper, a joint optimization algorithm of offloading decision, energy harvesting time, and unmanned aerial vehicle (UAV) location is proposed for user equipment (UEs)'s task completion latency problem in a communication-sensing-computing integration scenario with wireless energy supply. Under the constraints of causality of energy harvesting consumption by the UEs and conditional mutual information, the total latency minimization problem of the UEs is established. Firstly, the optimization variables of the problem are transformed from three variables of offloading decision, energy harvesting time, and UAV location to two variables of offloading decision and UAV location by means of the derived closed expression, and then the transformed optimization problem is decomposed into the offloading decision optimization sub-problem and the UAV location optimization sub-problem to be solved alternately and iteratively. The genetic algorithm is employed to tackle the optimization sub-problem of offloading decisions, and the successive convex approximation algorithm is applied to the drone positioning optimization sub-problem. Simulation results show that the proposed algorithm in this paper reduces the average task completion latency by 35 percent and 15 percent, respectively, compared to the two baseline algorithms for different numbers of UEs.

关键词： Task analysis   Resource management   Field programmable gate arrays   Approximation algorithms   Wireless communication   Servers   Reinforcement learning   Heterogeneous edge environments   latency minimization   mobile edge computing  

摘要： Mobile edge computing has emerged as a prevalent computing paradigm to support applications that demand low latency and high computational capacity. Hardware reconfigurable accelerators exhibit high energy efficiency and low latency compared to general-purpose servers, making them ideal for integration into mobile edge computing systems. This article investigates the problem of joint task offloading, access point selection, and resource allocation in heterogeneous edge environments for latency minimization. Given the heterogeneity of edge computing devices and the interdependence of the decisions required for offloading, access point selection, and resource allocation, it is challenging to optimize over them simultaneously. We decomposed the proposed problem into two disjoint subproblems and developed algorithms for each of them. The first subproblem is to jointly determine access point selection and communication resource allocation decisions, for which we have proposed an algorithm with a provable approximation ratio of 2.62/(1-8 lambda), where lambda is a tunable parameter balancing the approximation ratio and time complexity. Additionally, we offer a faster variant of the algorithm with an approximation ratio of (root 3+1)(2). The second subproblem is to determine offloading and computing resource allocation decisions jointly and is NP-hard, where we developed algorithms based on relaxation and rounding. We conducted comprehensive numerical simulations to evaluate the proposed algorithms, and the results demonstrated that our algorithms outperformed existing baselines and achieved near-optimal performance across various settings.

关键词： Computation offloading   knowledge-defined networking   mobile edge computing   deep reinforcement learning  

摘要： With the proliferation of devices connected to the Internet of Things (IoT), the complexity of network management has increased. To intelligently manage large-scale networks, we propose a Knowledge-Defined Edge Computing Networks (KDECN) architecture. Edge Nodes (ENs) deployed in the KDECN architecture are responsible for collecting and preprocessing the relevant information uploaded by User Devices (UDs), and provide computation resources for UDs. Futhermore, since multiple UDs share system computation resources, one computing decision will affect the subsequent decision-making of other UDs. Thus, accurately predicting the demands for UD task requests is a key challenge to maximize long-term execution utility. To this end, we deploy the LSTM-based Task Request Demand Prediction (TRDP) method on the management plane of KDECN architecture to predict the task request quantity of UDs in each future time slot. In order to maximize long-term execution utility of the system, we propose a Deep Reinforcement Learning (DRL)-based Long-term Computation Offloading and computation Resource Allocation (L-CORA) algorithm. Specifically, the proposed L-CORA algorithm makes computing decisions based on the prediction of the offloading task quantity and the personalized demands of UDs to ensure the long-term quality of computing service. Extensive experiments with Shanghai real-world datasets to prove that the KDECN-based L-CORA algorithm effectively improves the average utility of the system.