关键词： RIS   Mobile edge computing   Profit  

摘要： This paper focuses on the profit maximization problem in a reconfigurable intelligent surfaces (RIS) aided computing network, where multiple heterogeneous users offload their computational tasks to one computational access point (CAP) for seeking computing acceleration at the cost of profit. In particular, the CAP can also pre-store a part of the computing task to speed up computing, and the system has limited communication and computing resources, where heterogeneous users have different offloading requirements and the CAP can dynamically allocate the system resources to meet the requirements of users to earn profits. To maximize the system profit, we devise the system by proposing a resource allocation scheme which employs a genetic algorithm (GA), based on statistical channel state information (CSI) of wireless links. The proposed algorithm maximizes the long-term profit of the system by optimizing resource allocation among users. Finally, simulation results are provided to verify the proposed scheme. The results show that our proposed resource allocation scheme outperforms the conventional ones.

关键词： Remote sensing image analysis   Image fusion   Mobile edge computing   Forest tourism   Ubiquitous cloud   Prediction model  

摘要： With the development of society and the improvement of people's living standards, ecotourism based on forest ecological environment has become an urgent need of urban and rural people. Forest leisure tourism is different from traditional sightseeing tourism. The differences between them are not only reflected in consumption purpose, consumption behavior, consumption grade and consumption form, but also reflected in the differences between tourism products, service system and service quality demand. Therefore, in order to develop forest leisure tourism, we must first fully understand the objective status quo of the leisure tourism market and the real needs of the market, and correctly judge the basic characteristics of the current forest leisure tourism market. At present, the competition of tourism market is upgraded from the competition of tourism price and tourism product to the competition of tourism brand. However, the resource utilization efficiency of forest park tourism is insufficient, and the internal management and external marketing are difficult to adapt to the changes of the market, thus the image and attraction of forest park tourism need to be improved urgently. Therefore, based on remote sensing image analysis and neural computing model, this paper constructs a forest ecotourism evaluation scheme. We designed the novel cloud-based mobile edge computing model to construct the efficient scenario for the prediction. The experimental results show that the model proposed in this paper can effectively evaluate the development plan of forest eco-tourism.

关键词： Multi-Access Edge Computing   experimentation   edge computing   mobile edge computing  

摘要： Multi-Access Edge Computing (MEC) attracts much attention from the scientific community due to its scientific, technical, and commercial implications. In particular, the European Telecommunications Standards Institute (ETSI) standard convergence consolidates the discussions around MEC. Still, the existing MEC practical initiatives are incomplete in their majority, hardening or invalidating their effective deployment. To fill this gap, it is essential to understand a series of experimental prototypes, implementations, and deployments. The early implementations can reveal the potential, the limitations, the related technologies, and the development tools for MEC adoption. In this context, this work first brings a discussion on existing MEC initiatives regarding the use cases they target and their vision (i.e., whether they are more network-related or more distributed systems). Second, we survey MEC practical initiatives according to their strategies, including the ETSI MEC standard. Besides, we compare the strategies according to related limitations, impact, and deployment efforts. We also survey the existing tools making MEC systems a reality. Finally, we give hints to issues yet to be addressed in practice. By bringing a better comprehension of MEC initiatives, we believe this survey will help researchers and developers design their own MEC systems or improve and simplify the usability of existing ones.

关键词： Federated learning   model allocation   mobile edge computing  

摘要： Federated Learning (FL) is believed as a promising manner of distributed machine learning for 5G and future 6G networks in the context of mobile edge computing (MEC). From the worker's viewpoint, a problem is that no incentive drives them to participate in FL. Thus, different from the conventional server-centric model allocation methods, we study the worker-centric strategy in this paper. Because communicating with the FL server and training an FL model locally are energy-hungry, a dilemma for each worker is how to make the tradeoff between participating in FL training and the volume restriction of its battery. To address this issue, we formulate a WorkerFirst problem. Its NP-hardness is also proved. Next, we devise a DDQN algorithm and a DQL algorithm to strive for near-optimal decisions for each worker. These two algorithms are proposed by leveraging the deep reinforcement learning framework, while considering the energy consumption, training timespan, and the communication overheads of workers, simultaneously. The benefit of adopting such a DRL-based decision-making framework is that workers can execute the algorithms locally and dynamically adapt to the varying MEC environment. The evaluation results show that the proposed DDQN and DQL algorithms can learn good policies without knowing any prior knowledge of network conditions.

关键词： Mobile edge computing   Cooperative MEC   Multi-UAV flight trajectory optimization  

摘要： In this paper, a cooperative MEC system with multi-UAV and a ground access point (AP) is considered, in which UAVs can act as both a computing platform to help Internet of Things devices (IoTDs) deal with their computing tasks and a relay platform to offload some of the task data from IoTDs to the AP with higher computing ability. We aim to minimize the weighted overall energy consumption of UAVs and IoTDs by jointly optimizing connection scheduling, CPU frequency, task offloading bits and the flight trajectory of UAVs. The formulated problem is a Mixed-Integer Nonlinear Programming (MINLP) problem, which is hard to solve. To tackle this problem, we divided it into three sub-problems and resolved them iteratively by the Lagrangian dual method and succession convex approximation (SCA) technique. Finally, an alternately iterative optimization algorithm is proposed. The numerical results show that our proposed algorithm has better performance compared to other benchmark algorithms.& COPY;2023 Elsevier B.V. All rights reserved.

关键词： Task analysis   Energy consumption   Resource management   Collaboration   Servers   Optimization   Delays   Computation offloading   service caching   mobile edge computing   deep deterministic policy gradient  

摘要： Mobile Edge Computing (MEC) meets the delay requirements of emerging applications and reduces energy consumption by pushing cloud functions to the edge of the networks. Service caching is to cache application services and related databases at Edge Servers (ESs) in advance, and then ESs can process the relevant computation tasks. Due to the limited resources in the ESs, how to determine an effective service caching strategy is very crucial. In addition, the heterogeneity of ESs makes it impossible to make full use of the computing and caching resources without considering the collaboration among ESs. This paper considers a joint optimization of computation offloading, service caching, and resource allocation in a collaborative MEC system with multi-users, and formulates the problem as Mixed-Integer Non-Linear Programming (MINLP) which aims at minimizing the long-term energy consumption of the system. To solve the optimization problem, a Deep Deterministic Policy Gradient (DDPG) based algorithm is proposed for determining the strategies of computation offloading, service caching, and resource allocation. Simulation results demonstrate that the proposed DDPG based algorithm can reduce the long-term energy consumption of the system greatly, and can outperform some other benchmark algorithms under different scenarios.

关键词： Mobile edge computing   quality of experience   bisection searching   sub-channel matching  

摘要： Most of existing works related to mobile edge computing (MEC) focused on the total energy consumption or task completion time. However, for the applications with multiple players as a whole, the diverse battery levels of players should be considered to achieve better quality of experience (QoE), which is reflected in the metrics of task completion time and the lifespan of service. In this paper, we focus on QoE and diversity of devices. By jointly considering the individual battery level of different devices, we formulate an optimization problem to minimize the task completion time of the system. Firstly, we propose two necessary conditions to achieve the optimal solution of the formulated problem. In addition, we transform the formulated problem into another problem, which can be used to judge whether a given value is feasible for the formulated problem based on the proposed optimal conditions and bisection searching (BSS) algorithm. Then, we propose a method named sub-channel (SC) matching based on virtual computation resource (SMVCR) to solve the transformed problem with low computational complexity. Simulation results indicate that the BSS-SMVCR algorithm has a good performance in task completion time compared with some existing algorithms, and also can significantly extend the lifespan of the corresponding service, which is reflected in the supporting number of offloading tasks.

关键词： Task analysis   Delays   Vehicle dynamics   Computational modeling   Bandwidth   Heuristic algorithms   Roads   Cloud computing   computation offloading   deep reinforcement learning (DRL)   Internet of Vehicles (IoV)   mobile edge computing   resource allocation  

摘要： Mobile edge computing (MEC) and cloud computing (CC) have been considered as the key technologies to improve the task processing efficiency for Internet of Vehicles (IoV). In this article, we consider a random traffic flow and dynamic network environment scenario where MEC and CC are collaborated for processing delay-sensitive and computation-intensive tasks in IoV. We study the joint optimization of computation offloading and resource allocation (CORA) with the objective of minimizing the system cost of processing tasks subject to the processing delay and transmission rate constraints. To attack the challenges brought by the dynamic environment, we use the Markov decision process model for formulating the dynamic optimization problem, and apply a deep reinforcement learning (DRL) technique to deal with high-dimensional and continuous states and action spaces. Then, we design a CORA algorithm, which is able to effectively learn the optimal scheme by adapting to the network dynamics. Extensive simulation experiments are conducted, in which we compare the CORA algorithm with both non-DRL algorithms and DRL algorithms. The experimental results show that the CORA algorithm outperforms others with excellent training convergence and performance in processing delay and processing cost.

关键词： industrial internet   mobile edge computing   federated learning   deep reinforcement learning   computing offloading   resource allocation  

摘要： Industrial Internet mobile edge computing (MEC) deploys edge servers near base stations to bring computing resources to the edge of industrial networks to meet the energy-saving requirements of Industrial Internet terminal devices. This paper considers a wireless MEC system in an intelligent factory that has multiple edge servers and mobile smart industrial terminal devices. In this paper, the terminal device has the choice of either offloading the task in whole or in part to the edge server, or performing it locally. Through combined optimization of the task offload ratio, number of subcarriers, transmission power, and computing frequency, the system can achieve minimum total energy consumption. A computing offloading and resource allocation approach that combines federated learning (FL) and deep reinforcement learning (DRL) is suggested to address the optimization problem. According to the simulation results, the proposed algorithm displays fast convergence. Compared with baseline algorithms, this algorithm has significant advantages in optimizing the performance of energy consumption.

关键词： Mobile edge computing  

摘要： Mobile edge computing (MEC) integrated with radio frequency-based wireless power transfer (WPT) has became a promising trend to shorten task delay and achieve sustainable operations of computing system, as it continuously provides energy to wireless devices (WDs) and allows computation tasks offloading to a powerful edge server nearby. Furthermore, introducing the relay technique to WPT-MEC system could improve offloading capability and energy efficiency, especially when the condition of the wireless channels between server and WDs is poor. In this paper, we seek to maximize the energy efficiency (EE) for a multiuser relay-aided MEC network powered by WPT, where binary offloading policy is followed in WDs and partial offloading policy is adopted in the relay. We aim to jointly optimize the relay’s computing configurations, wireless charge time fraction and WDs offloading strategy, that faces great challenge due to the strong coupling of multi-user computing mode selection and hybrid offloading model among WDs and relay. To tackle the problem, we formulated it as a mixed integer nonlinear programming (MINLP) problem and design an iterative algorithm based on Dinkelbach’s method and alternating direction method of multipliers (ADMM) decomposition technique to solve it. We first transform the original fractional programming problem into a more tractable problem in a subtraction form based on Dinkelbach’s method. Then according to ADMM technique, we decompose the multi-user offloading problem into multiple subproblems which can be solved in a distributed model. For an iterative calculating step, we propose a Bi-Search algorithm for CPU frequency and transmission power optimization and a DAI-Based algorithm to choose the time fraction of wireless power charging. The simulation results show that our proposed algorithm convergence fast and derive a 15% higher energy efficiency than other benchmark methods. © 2023, CC BY-NC-SA.