关键词： Internet of Things   Predictive models   Computational modeling   Topology   Training   Stress   Data models   Trust   mobile edge computing   machine learning  

摘要： We propose a data-driven distributed machine learning approach to scalably predict the trustworthiness of homogeneous IoT services in heterogeneous Mobile Edge Computing (MEC)-based IoT systems. The proposed approach formulates training distributed trust prediction models within an MEC-based IoT system as a Network Lasso problem. We then introduce a variant of the Stochastic Alternating Method of Multipliers framework enriched with the ability for feature selection at each MEC layer. To verify the effectiveness of the proposed approach, we carried out a comprehensive evaluation on three real-world datasets adjusted to exhibit the context-dependent trust information accumulated in MEC environments within a given MEC topology. The experimental results affirmed the effectiveness of our approach and its suitability to predict trustworthiness of IoT services in MEC-based IoT systems.

关键词： Quality of service   Privacy   Load management   Computational efficiency   Resource management   Task analysis   Data aggregation   Decentralization   load balancing   mobile edge computing   peer-offloading algorithm   small cells  

摘要： In order to fit the requirements of future enterprise management networks with multiple service providers, conventional mobile edge computing enabled small cells (MEC-SCs) peer-offloading requires research efforts towards fully-decentralized computation-efficient global-optimal quality of service (QoS) aware load balancing, while ensuring service providers' privacy protection. In this article, we propose a new fully-decentralized on-demand MEC-SC peer-offloading NETwork (named DEEP-NET), targeting QoS-aware load balancing with enhanced latency and service providers' privacy protection. Newly developed federated gradient descent based algorithm is fully decentralized to MEC-SCs, which only requires local data and privacy-free inter-MEC-SC data sharing to achieve global optimal QoS-/latency-aware fairness. Result analysis for convergence of the proposed DEEP-NET provides guidance to the future topology optimization of fully-decentralized on-demand MEC-SC deployment. Besides, DEEP-NET outperforms the benchmarks with dynamic user demand to achieve optimal load balancing, with enhanced QoS, latency, and service providers' privacy.

关键词： Mobile edge computing   Non-Orthogonal Multiple Access   Delay-sensitive   Industrial internet of things   Prediction-based deep reinforcement learning  

摘要： Mobile Edge Computing (MEC) and Non-Orthogonal Multiple Access (NOMA) have been treated as promising technologies to process the delay-sensitive tasks in the Industrial Internet of Things (IIoT) network. The cooperation among multiple MEC servers is essential to improve the processing capacity of MEC systems. However, the dynamic IIoT environment with unknown changing models, including time-varying wireless channels, diversified task requests, and dynamic load on wireless resources and multiple MEC servers, may continuously affect the task offloading decision and NOMA user pairing, which brings great challenges to the resource management in the NOMA-MEC-based IIoT network. In order to solve this problem, we design a distributed deep reinforcement learning (DRL) based solution to improve the task satisfaction ratio by jointly optimizing the task offloading decision and the sub-channel assignment to support the binary computing offloading policy. For each IIoT device agent, to deal with the problem of partial state observability, the Recurrent Neural Network (RNN) is employed to predict the load states of sub-channels and MEC servers, which is further used for the decision of the RL agent. Simulation results show that the proposed prediction-based-DRL (P-DRL) method can achieve higher task satisfaction ratio than exiting schemes.

关键词： Mobile edge computing   Task offloading scheme   Time-correlated traffic   VM repair   Delay-energy tradeoff  

摘要： Mobile Edge Computing (MEC) has evolved into a key technology that can leverage resources of computing, storage and network deployed at the proximity of the Mobile Devices (MDs). How to offload delay-sensitive and energy-constraint tasks is of research importance. In this paper, considering time-correlated traffic and Virtual Machine (VM) repair, we come up with a method to evaluate the task offloading scheme in a MEC system. Applying a Markovian Arrival Process (MAP) to describe the task arrivals in a MEC system, the local computing offloading and the MEC offloading are modeled as a MAP/M/1 queue and a MAP/M/N/N+K queue with VM repair, respectively. By exploiting the matrix-geometric solution approach and the Gauss-Seidel approach, we give the average delay, the energy consumption level and computation resource availability. Next, we provide numerical results to investigate the influence of the offload rate on the response performance and the energy efficiency with different correlation coefficients and the influence of the repair rate and the service rate of a VM on the availability. In addition, an improved Sine and Cosine Algorithm (SCA) is developed to acquire the optimal offload rate with a delay-energy tradeoff.

关键词： Mobile edge computing   Computation power maximization   Restricted multiple knapsack problem   Differential evolution  

摘要： High-density connection is among the natures of next-generation wireless communication systems. Meanwhile, various computation-intensive smart applications are becoming growing popularity with the technology boom. Thus, strong computation power will become a crucial requirement for wireless communication systems. Mobile edge computing provides a promising solution to this requirement by pushing a cloud-like computation capacity to the network edge. This study aims to maximize the computation power of a mobile edge computing enabled dense network. To this end, a computation bits maximization problem is formulated by jointly optimizing offloading decision and resource allocation. The problem is a mixed-variable nonlinear programming problem. First, by analyzing the feasibility of computation modes and constructing a user distribution strategy, the original problem is decoupled into two sub-problems, i.e., the assignment of the offloading users and resource allocation. The offloading users' assignment is modeled as a restricted multiple knapsack problem, and a profit density is defined to maximize the overall profits of multiple knapsacks. Then, an improved differential evolution algorithm is developed to address the knapsack problem, in which mutation and repair operators are designed according to the profit density. Based on the optimal solution to the knapsack problem, the resource allocation sub-problem is solved by the corresponding calculation. Finally, extensive experiments are conducted to evaluate the performance of our scheme. Results show that: (1) our scheme provides superior computation power compared to that of benchmark schemes;(2) the performance gain of our scheme over benchmark schemes expands with growing connection density. Therefore, our scheme is an effective computation power optimization scheme.

关键词： Mobile edge computing  

摘要： In the current internet of things era, various devices can provide more services by connecting to the Internet. However, the explosive growth of connected devices will cause cloud core overload and significant network delays. To overcome these overload and delay problems, the mobile edge computing (MEC) network is proposed to provide most of the computing and storage near the radio access network to reduce the traffic of the core cloud network and provide lower latency for the terminal. Mobile edge computing can work with third parties to develop multiple services, such as mobile big data analysis and context-aware services. However, while using the service, it may also encounter a large amount of popular data being accessed in a short period of time. Without proper handling of replica generation and deployment, even in low-latency environments, it can still kill the benefits of MEC due to increased access time. Although many scholars have proposed related issues for copy replication, there are *** that can be improved. To avoid the situation of insufficient availability of replicas, replica replication is performed, but infinite replicas may lead to a significant increase in traffic and waste of resources. And when deploying replicas, it is necessary to avoid placing them on congested nodes and consider how to achieve better load balancing. To improve the above problems, we synthesize the advantages of previous algorithms, make up for the shortcomings, and propose an adaptive replica configuration mechanism to predict the popularity of files and replicate replicas to low-blocking nodes. This method spreads the subsequent access workload by copying the popular file in advance to improve the system's overall performance. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Mobile edge computing   Power control   Computation offloading   Deep deterministic policy gradient   Double Deep Q -Networks  

摘要： Smart mobile devices have recently emerged as a promising computing platform for computation tasks. However, the task performance is restricted by the computing power and battery capacity of mobile devices. Mobile edge computing, an extension of cloud computing, solves this problem well by providing computational support to mobile devices. In this paper, we discuss a mobile edge computing system with a server and multiple mobile devices that need to perform computation tasks with priorities. The limited resources of the mobile edge computing server and mobile device make it challenging to develop an offloading strategy to minimize both delay and energy consumption in the long term. To this end, an online algorithm is proposed, namely, the double reinforcement learning computation offloading (DRLCO) algorithm, which jointly decides the offloading decision, the CPU frequency, and transmit power for computation offloading. Concretely, we first formulate the power scheduling problem for mobile users to minimize energy consumption. Inspired by reinforcement learning, we solve the problem by presenting a power scheduling algorithm based on the deep deterministic policy gradient (DDPG). Then, we model the task offloading problem to minimize the delay of tasks and propose a double Deep Q -networks (DQN) based algorithm. In the decision-making process, we fully consider the influence of task queue information, channel state information, and task information. Moreover, we propose an adaptive prioritized experience replay algorithm to improve the model training efficiency. We conduct extensive simulations to verify the effectiveness of the scheme, and the simulation results show that compared with the conventional schemes, our method reduces the delay by 48% and the energy consumption by 53%.& COPY;2022 Elsevier Inc. All rights reserved.

关键词： Device to device   Ant colony optimization   Weighted genetic algorithm   Hybrid energy harvesting   Mobile edge computing  

摘要： The constraints owing to the usage of batteries as well as cellular clients' restrictions in computing capability cause concern. This is related to allocating resources in Device to Device (D2D) aided edge computing systems. Hence, these prompt the respective approaches to investigate the harnessing of electrical energy in a hybrid way. The computing resource of the Mobile Edge Computing (MEC) server reaches the limit of its computing capability. The adjacent base station's user can act as a relay node by setting up the D2D relay links for the computing responsibilities of the users. Earlier these were left under the previous base station. Now they can be transferred to the new base station's MEC server. This has enough resources. The goal of the resource allocation approaches is to improvise energy efficiency under computation delay constraints and energy harvesting constraints. The formulation of the problem in the proposal is done as a mixed-integer non-linear problem (MINLP). It achieves one of the best solutions. The computational intricacy is small. Hence, the paper proposes a Weighted Genetic Algorithm (WGA) pivoted resource allocating method for 5G networks' D2D type communications. Genetic algorithms assumed due popularity for allocating networks as well as rendering them optimized. An optimal effect is realized by adopting the optimization algorithm like WGA rather than the algorithms namely Ant Colony Optimization (ACO), Standard Particle Swarm Optimization (SPSO) and Quantum Behaved Particle Swarm Optimization (QPSO). Simulated outcomes infer that WGA has an edge over the mentioned algorithms in energy efficiency, SINR and throughput. Added to that studies imply that such schemes' self-learning ability (i.e. WGA, ACO) yields improved results for problems with higher complexity.

关键词： vehicle-to-infrastructure   internet of vehicles   mobile edge computing   channel occlusion   task scheduling   non-dominated sorting genetic algorithm-III  

摘要： In recent years, as more and more vehicles request service from roadside units (RSU), the vehicle-to-infrastructure (V2I) communication links are under tremendous pressure. This paper first proposes a dynamic dense traffic flow model under the condition of fading channel. Based on this, the reliability is redefined according to the real-time location information of vehicles. The on-board units (OBU) migrate intensive computing tasks to the appropriate RSU to optimize the execution time and calculating cost at the same time. In addition, competitive delay is introduced into the model of execution time, which can describe the channel resource contention and data conflict in dynamic scenes of the internet of vehicles (IoV). Next, the task scheduling for RSU is formulated as a multi-objective optimization problem. In order to solve the problem, a task scheduling algorithm based on a reliability constraint (TSARC) is proposed to select the optimal RSU for task transmission. When compared with the genetic algorithm (GA), there are some improvements of TSARC: first, the quick non-dominated sorting is applied to layer the population and reduce the complexity. Second, the elite strategy is introduced with an excellent nonlinear optimization ability, which ensures the diversity of optimal individuals and provides different preference choices for passengers. Third, the reference point mechanism is introduced to reserve the individuals that are non-dominated and close to reference points. TSARC's Pareto based multi-objective optimization can comprehensively measure the overall state of the system and flexibly schedule system resources. Furthermore, it overcomes the defects of the GA method, such as the determination of the linear weight value, the non-uniformity of dimensions among objectives, and poor robustness. Finally, numerical simulation results based on the British Highway Traffic Flow Data Set show that the TSARC performs better scalability and efficiency than other met

关键词： Unmanned aerial vehicle   Mobile edge computing   Multi -chrome genetic algorithm   Evolutionary algorithm   Autonomous system  

摘要： This paper proposes a multi-unmanned aerial vehicle (UAV)-enabled autonomous mobile edge comput-ing (MEC) system, in which several UAVs are deployed to provide services to user devices (UDs). The aim is to reduce/minimize the overall energy consumption of the autonomous system via designing the optimal trajectories of multiple UAVs. The problem is very complicated to be solved by traditional methods, as one has to take into account the deployment updation of stop points (SPs), the association of SPs with UDs and UAVs, and the optimal trajectories designing of UAVs. To tackle this problem, we propose a variable-length trajectory planning algorithm (VLTPA) consisting of three phases. In the first phase, the deployment of SPs is updated via presenting a genetic algorithm (GA) having variable -length individuals. Accordingly, the association between UDs and SPs is addressed by using a close rule. Finally, a multi-chrome GA is proposed to jointly handle the association of SPs with UAVs and their order for UAVs. The proposed VLTPA is tested via performing extensive experiments on eight instances ranging from 60 to 200 UDs, which reveal that the proposed VLTPA outperforms other compared state-of-the-art algorithms.(c) 2021 ISA. Published by Elsevier Ltd. All rights reserved.