关键词： Mobile IoT   Mobile edge computing   Perceptual task offloading   Population optimizing of quantum   behavior particle   Chaos perturbation strategy  

摘要： To solve the problem of high time consumption and energy loss of edge computing perceptual task offloading in the mobile IoT (Internet of things), it is necessary to increase the particle population diversity and the performance of escaping the local optimum solution in the intelligent optimization algorithm. For the offloading scenario of multi edge center servers and smart devices of multi IoT users, the NQPSOOM method (A new method of user perceptual task offloading in the IoT based on optimizing strategy of quantum behavior particle population) was proposed. The adaptability variance of the quantum behavior particle population was designed to measure the convergence of the particle population. The logistic chaos perturbation strategy was used to improve the performance of the intelligent optimization algorithm of escaping the local optimum solution. The exchange and mutation operations of fast elite non-dominated sorting genetic algorithm based on crowding coefficient were designed to select the particle population with a high diversity of quantum behavior particle population. Compared with the other five perceptual task computing offloading methods in recent three years, considering the convergence of the perceptual offloading model, the impact of the number of smart devices of IoT users, the number of edge center servers and the perceptual task data size on the optimal offloading method, the NQPSOOM method improves the performance of the perceptual task offloading model, including reducing the adaptability of the intelligent optimization algorithm by 4.89% on average, that is, facilitating the convergence speed of the intelligent optimization algorithm by 4.89%, and lowering the time consumption of the algorithm by 4.08% and energy loss by 3.91% on average.(c) 2022 Elsevier B.V. All rights reserved.

关键词： Mobile edge computing   Stackelberg game   Computing offload   Pricing  

摘要： Mobile edge server (MES) can meet the low latency requirements of End user (EU) tasks, but the MES computing resources are limited. This paper proposes an IDs-assisted MES (MES-IDs) computing model to expand MES. However, how to find a task offload strategy to minimize EU calculation costs and improve MES and ID benefits on a task completion basis. This paper proposes a three-way optimization calculation method based on the Stackelberg game to reduce the problem complexity, which decomposes into EUs-BS and BS-IDs problems. The EUs-BS problem design pricing scheme obtains the EU task optimal offload rate. The BS-IDs problem uses nonlinear pricing methods to find the optimal task offload problem between MES and ID on the resource unit price, a multi-constrained nonlinear convex optimization problem. We propose an immune Metropolis-based particle swarm loss optimization algorithm (PIMA) to obtain an approximate optimal solution for the nonlinear convex optimization problem by adjusting the resource price. Numerical simulation results show that compared with GSP and PSI algorithms, the PIMA algorithm shows more robust stability and can effectively reduce task completion delay and computational cost.

关键词： Mobile edge computing   Pricing   PSO   Stackelberg game   Task offloading  

摘要： The task offloading technology in mobile edge computing can improve the benefits of each device. Moreover, designing reasonable prices for computing resources is critical to balancing the interests of end servers and devices. However, unbalanced information availability complicates this issue. To address this problem, the Stackelberg game is introduced to describe the relationship between the MEC server and end users (EUs). Then, the task offloading decision problem of EUs is simplified and proved by derivation. Last, uniform pricing and differentiated pricing algorithms are proposed. The differentiated pricing strategy is proposed by the PSO-based pricing optimization algorithm (DPOA), which can precisely constrain the offloading of each EU. Simulation results show the DPOA effectively improve profit of the server, and reduce latency of EUs.

关键词： Mobile edge computing   Wireless power transfer   Computation offloading   Reinforcement learning  

摘要： The method of charging mobile devices with wireless power transfer (WPT) from the base station (BS) integrated with mobile edge computing (MEC) increases the potential of MEC. The increasing demand for intelligent computation offloading requires effective decisions among local or remote computation specifically in wireless fading channels of the dynamic environment. Our main aim is to generate an effective offloading decision between local and remote computation in a real-time environment for each wireless channel while preserving optimal computation rate. In this article, we consider a wireless powered MEC system that governs a binary offloading decision to execute the task locally at the edge devices or the remote server. We propose a reinforcement learning based intelligent online offloading (RLIO) framework that adopts an optimal offloading action based on reinforcement methods. This framework acquires a worthy decision among local or remote computation for the time varying wireless channel conditions in dense networks. Numerical results show that the proposed framework can achieve optimal performance while preserving the computation time compared with existing optimization methods. Second, the average execution cost of RLIO is less than 0.4 ms per channel, which enables real-time and optimal offloading in dynamic and large-scale networks.

关键词： Clustering   mobile edge computing   multi-objective optimization   multi-workflow offloading   SPEA2  

摘要： To cope with the rapid development of the Internet of Things (IoT) and the increasing demand for real-time services, mobile edge computing (MEC) has become a promising solution which extends centralised cloud computing, to provision computing resources, storage and network services closer to the mobile device from the network edge. While computation offloading is a key feature in MEC to enable real-time services, offloading workflow tasks in MEC is an NP-hard problem. Typically, the problem of multi-workflow offloading with multi-objective optimization is still an open and challenging issue. Therefore, this article proposes a multi-objective clustering evolutionary algorithm called MCEA to minimize the cost and energy consumption of multi-workflow execution under the deadline constraint. First, the sub-deadline constraint is added during initialization to generate more initial solutions that satisfy the deadline constraint. Then an adaptive clustering method is adopted to guide individuals to find a suitable mate during crossover operation. Finally, the probabilities of crossover and mutation are dynamically adjusted based on the historical information to control the evolution direction and convergence speed of algorithm. Comprehensive experiments are carried out for complex workflow applications on FogWorkflowSim, which demonstrate that MCEA can achieve better performance than four representative algorithms in three evaluation metrics.

关键词： Mobile edge computing   Computation offloading   Deep reinforcement learning   Neural fictitious self-play   Proximal policy optimization   Quality of experience  

摘要： In Mobile Edge Computing (MEC), offloading tasks from mobile devices to edge servers may accelerate the processing speed and save the energy of the devices, hence improving device users' quality of experience. Recently, reinforcement learning (RL) is increasingly used for offload decision making. RL seeks long-term cumulative benefits and is proved useful for a sequence of decisions, thus is well suited for the work. Due to privacy and security concerns, mobile devices may be unwilling to expose their local information, leading to a fully decentralized MEC environment. Independent RL (IRL) emerges as a promising solution for this scenario. However, IRL solutions are faced with the non-stationarity issue, which arises when the components are changing their policies. In this paper, we proposing adopting the Neural Fictitious Self-Play (NFSP) architecture for offload decision making. NFSP explicitly tackles the non-stationarity issue with the built-in self-play mechanism, and uses a mixed strategy consisting of deep RL and the past average strategy, which is approximated by supervised deep learning. Furthermore, we use the Proximal Policy Optimization (PPO) algorithm as the RL component and exploit the Gated Recurrent Unit (GRU) to deal with the partial-observability issue in fully decentralized MEC. We conduct extensive simulation experiment, the result of which shows that our method outperforms the raw IRL approaches, validating the effectiveness of our proposed method.(c) 2022 Elsevier B.V. All rights reserved.

关键词： Learning-based network optimization   Network slicing   Content Delivery Network   Mobile Edge Computing   Uncertain programming  

摘要： Network Slicing (NS) and Mobile Edge Computing (MEC) are recognized as a promising paradigm for mobile Content Delivery Network (CDN) by instantiating Virtual Network Functions (VNFs) on MEC platforms. Mobile network exhibits intrinsic dynamics, where user requests patterns vary in time and space due to human behaviors. The requirements and distribution of users are arbitrary spatio-temporal stochastic variables, which makes the deployment and reconfiguration of a CDN slice a challenging task. In this work, by adopting a periodical reconfiguration strategy, we consider a CDN slice system which operates in discrete time intervals. Within each time interval, we formalize the CDN-MEC-VNFs Planning (CMVP) problem based on uncertain programming to tackle the dynamic and uncertain mobile network environment, where user requests are treated as random variables with arbitrary pattern. Then, we propose a data-driven and learning-based algorithm which integrates Stochastic Simulation (SS), Deep Neural Networks (DNN) and meta-heuristic algorithm to determine the provisioning of the CDN slice from historical user requests information. The practicability of the proposed mechanism in offline training and online running are also discussed. Finally, we conducted intensive real-trace driven simulations to demonstrate the effectiveness of our approach on planning CDN slice with higher QoS under dynamic system environment and arbitrary user requests by comparing towards several baselines.

关键词： mobile edge computing   Industrial Internet   resource allocation   virtual network function   multi-UAVs   deep reinforcement learning  

摘要： This paper focuses on reducing execution delays of dynamic computing tasks in UAV-assisted fault-prone mobile edge computing (FP-MEC) systems, which combine mobile edge computing (MEC) and network function virtualization (NFV) technologies. FP-MEC is suited to meet Industrial Internet (IIN) requirements such as data privacy, low latency, and low-cost industrial scalability in specific scenarios. However, the reliability of virtual network functions (VNFs) deployed on UAVs could impact system performance. Thus, this paper proposes the dynamic task scheduling optimization algorithm (DTSOA) based on deep reinforcement learning (DRL) for resource allocation design. The formulated execution delay optimization problem is described as an integer linear programming problem and it is an NP-hard problem. To overcome the intractable problem, this paper discretizes it into a series of single-time slot optimization problems. Furthermore, the experimental rigor is improved by constructing a real-time server state update system to calculate the real-time server load situation and crash probability. Theoretical analysis and experiments show that the DTSOA has better application prospects than Q-learning and the recent search method (RSM), and it is closer to the traversal search method (TSM).

关键词： high-speed railway   mobile edge computing   mobile 5G   picocell base station  

摘要： The fifth-generation (5G) wireless communication has experienced an upsurge of interest for empowering vertical industries, due to its high data volume, extremely low latency, high reliability, and significant improvement in user experience. Specifically, deploying 5G on high-speed railway (HSR) is critical for the promotion of smart travelling such that passengers can connect to the Internet and utilize the on-board time to continue their usual activities. However, there remains a series of challenges in practical implementation, such as the serious Doppler shift caused by the high mobility, the carriage penetration loss especially in the high-frequency bands, frequent handovers, and economic issues. To address these challenges, we propose three schemes in this article to improve the coverage of 5G networks on the train. In particular, we provide a comprehensive description of each scheme in terms of their network architecture and service establishment procedures. Specifically, the mobile edge computing (MEC) is used as the key technology to provide low-latency services for on-board passengers. Moreover, these three schemes are compared among themselves regarding the quality-of-service, the scalability of service, and the related industry development status. Finally, we discuss various potential research directions and open issues in terms of deploying 5G networks on HSR.

关键词： Task analysis   Servers   Energy consumption   Vehicle dynamics   Internet of Things   Benchmark testing   Wireless communication   Mobile edge computing   proactive cache placement   computation offloading   branch-and-bound   optimization  

摘要： This letter investigates a cache-enabled multiuser mobile edge computing (MEC) system with dynamic task arrivals, taking into account the impact of proactive cache placement on the system's overall energy consumption. We consider that an access point (AP) schedules a wireless device (WD) to offload computational tasks while executing the tasks of a finite library in the task caching phase, such that the nearby WDs with the same task request arriving later can directly download the task results in the task arrival and execution phase. We aim for minimizing the system's weighted-sum energy over a finite-time horizon, by jointly optimizing the task caching decision and the MEC execution of the AP, and local computing as well as task offloading of the WDs at each time slot, subject to caching capacity, task causality, and completion deadline constraints. The formulated design problem is a mixed-integer nonlinear program. Under the assumption of fully predicable task arrivals, we first propose a branch-and-bound (BnB) based method to obtain the optimal offline solution. Next, we propose two low-complexity schemes based on convex relaxation and task-popularity, respectively. Finally, numerical results show the benefit of the proposed schemes over existing benchmark schemes.