关键词： Mobile edge computing   Deep learning   Application division   Energy conserving computation   Partial offloading   Energy efficient offloading  

摘要： In mobile edge computing networks, total or partial computational offloading of delay sensitive and compute intensive applications to the nearby edge servers is a promising solution to reduce transmission delay and energy consumption of mobile nodes (MNs). However, in computational offloading of an application to edge server, considerations of energy consumption and time delay are not sufficient for the decision of minimum cost of application. In this article, a novel battery dependent cost selection strategy for computational offloading of an application capable for sequential execution of dependent sub tasks is proposed. The strategy considers current battery level of MN in the cost function for optimal selection of offloading policy based on the amount of data, computational resources, and radio resources of the server. Our comprehensive cost function takes into account all the said parameters, calculates all the costs for possible offloading policies, and chooses the policy with minimum cost from a huge dataset. The cost selection is energy efficient for low battery level and prioritizes faster execution for full battery level of MNs. A deep neural network is trained on the generated dataset to minimize the overhead of computations. Simulation results reveal that our proposed strategy outperforms the benchmark strategies in terms of deep neural network accuracy for different sizes of dataset, energy consumption, time delay, and cost for different sizes of applications.

关键词： Internet of medical things   Mobile edge computing   Wireless body area network   Task offloading   Federated reinforcement learning   NOMA   SCHEME  

摘要： The exponential proliferation of wearable medical apparatus and healthcare information within the framework of the Internet of Medical Things (IoMT) introduces supplementary complexities pertaining to the elevated Quality of Service (QoS) of intelligent healthcare in the forthcoming 6G era. Healthcare services and applications need ultra-reliable data transfer and processing with ultra-low latency and energy usage. Wireless Body Area Network (WBAN) and Mobile Edge Computing (MEC) technologies enabled IoMT to handle large amounts of data sensing, transmission, and processing while maintaining good QoS. Traditional frame aggregation (FA) systems in WBAN, on the other hand, create an excessive number of control frames during data transmission, resulting in significant latency and energy consumption, as well as a lack of flexibility. A Federated Reinforcement Learning (FRL) based TO Approach is recommended in this research. In the beginning, different types of service-related information were separated into queues with equal QoS needs. The duration of the FA was then automatically determined by the aggregation vertex based on energy consumption, latency, and throughput using FRL. Finally, based on the existing status, the amount of tasks offloaded was determined. The simulation results demonstrate that, as compared to the baseline schemes, the suggested FRLTO efficiently reduces energy consumption and latency while enhancing throughput and total WBAN utilization. Numerical results show that the proposed scheme improves the throughput by 37.06% and reduced the energy consumption by around 69.84% and time delay by about 6.23%, as compared to the state-of-the-art existing baseline schemes.

关键词： Industry 5.0   Mobile edge computing   Joint optimization   Computational energy efficiency   Partial offloading   UPLINK NOMA   MOBILE  

摘要： Smart devices in Industry 5.0, such as sensors and robots, are often limited by low battery life and finite computational resources, hindering their ability to perform complex tasks. By offloading computation-intensive tasks to Mobile Edge Cloud Computing (MEC) servers at the network's edge, businesses can achieve real-time data processing and analysis, reducing communication latency, quicker response times, and improved system reliability. This work presents an integrated framework for MEC and Industry 5.0, aimed at enhancing the performance, efficiency, and flexibility of industrial processes. In particular, we propose a joint optimization problem that maximizes computational energy efficiency by optimally allocating resources, such as processing power and computational resources, as well as device association, in the most efficient manner possible. The problem is formulated as nonconvex/nonlinear, which is intractable and poses high complexity. To solve this challenging problem, we first transform and decouple the original optimization problem into a series of subproblems using the block coordinate descent method. Then, we iteratively obtain an efficient solution using convex optimization methods. In addition, our work sheds light on the fundamental trade-off between local computation and partial offloading schemes. The results show that for small data size requirements, the performance is comparable among different schemes. However, as data size increases, our proposed hybrid scheme, which includes a partial offloading scheme, outperforms others, highlighting the effectiveness of the proposed joint optimization scheme.

关键词： The Internet of unmanned aerial vehicles   mobile edge computing   machine learning   computation offloading   intelligent decision making   INTELLIGENT REFLECTING SURFACE   RESOURCE-ALLOCATION   TRAJECTORY OPTIMIZATION   COMMUNICATION   UAVS   DESIGN   MEC   NETWORKS   ACCELERATION   MANAGEMENT  

摘要： Unmanned Aerial Vehicles (UAVs) play an important role in the Internet of Things and form the paradigm of the Internet of UAVs, due to their characteristics of flexibility, mobility, and low costs. However, resource constraints such as dynamic wireless channels, limited battery capacities, and computation resources of UAVs make traditional methods inefficient in the Internet of UAVs. The thriving of Mobile Edge Computing (MEC) and Machine Learning (ML) is of great significance and is promising for real-time resource allocation, trajectory design, and intelligent decision making. This survey provides a comprehensive review of key technologies, applications, solutions, and challenges based on the integration of MEC and ML in the Internet of UAVs. First, key technologies of MEC and ML are presented. Then, their integration and major issues in the Internet of UAVs are presented. Furthermore, the applications of MEC and ML in the Internet of UAVs under urban, industrial, and emergency scenarios are discussed. After that, this survey summarizes the current solutions for MEC and ML in the Internet of UAVs based on the considered issues. Finally, some open problems and challenges are discussed.

关键词： Optical communication   Mobile edge computing   Channel allocation   Task scheduling   Machine learning   5G networks  

摘要： Edge computing enables even low-powered devices to move part of their processing work to the edges of the network, improving service quality for everyone. Though several studies have hinted that offloaded work's data volume might affect resource allocation, no comprehensive study has been undertaken on the issue. In this research, a new optical communication strategy for 5G networks is presented, one that makes use of a machine learning-based routing architecture for channel allocation and job scheduling. Within HDFS (Hadoop data file system) environment for Hadoop processing, the header controls the stimulated control. Edge fog networks communicate through optical tier networks, and resources are managed by a service reinforcement heterogeneous multi-objective architecture. In order to schedule jobs, a multi-node delay proximal strategy is used. This policy uses genetically competing objectives. Throughout the course of the experiment, data on things like throughput, delivery rate, efficiency, end-to-end latency, and collision probability will be collected and analyzed. By implementing the plan, we decreased the probability of a collision by 65%, increased efficiency by 95%, decreased latency to all nodes by 55%, increased throughput by 98%, and increased the delivery rate by 92%.

关键词： DenseNet   detection   mobile edge computing   parking spots   smart cities   OCCUPANCY DETECTION   SMART CITY   MANAGEMENT  

摘要： Internet of Things (IoT) and related applications have revolutionized most of our societal activities, enhancing the quality of human life. This study presents an IoT-based model that enables optimized parking space utilization. The paper implements a Hybrid Deep DenseNet Optimization (HDDNO) algorithm for predicting parking spot availability involving Machine Learning (ML) and deep learning techniques. The HDDNO-based ML model uses secondary data from the National Research Council Park (CNRPark) in Pisa, Italy. Different regression algorithms are employed to forecast parking lot availability for a given time as part of the prediction process. The DenseNet technique has generated promising results, whereas the HDDNO model yielded better accuracy. The use of five optimizers, namely, Adaptive Moment Estimation (Adam), Root Mean Squared Propagation (RMSprop), Adaptive Gradient (AdaGrad), AdaDelta, and Stochastic Gradient Descent (SGD), have played significant roles in minimizing the loss of the model. The part of Adam has enabled the HDDNO model to generate predictions with high accuracy 99.19% and low loss 0.0306%. This proposed methodology would significantly improve environmental safety and act as an initiative toward developing smart cities.

关键词： Mobile edge computing   Unmanned aerial vehicle   Service caching   Workload offloading   Deep reinforcement learning   RESOURCE-ALLOCATION  

摘要： Internet of Things devices generate a large number of heterogeneous workloads in real-time that require specific application to tackle, and the inability to communicate between devices and communication base stations due to complex scenarios is a thorny issue. Service caching play a key role in managing specific-request workload from devices, and unmanned aerial vehicles with computation and communication functions can effectively solve communication barrier between devices and ground base stations. In addition, the joint optimization of workload offloading and service cache placement is a key issue. Accordingly, we design an unmanned aerial vehicle-enabled mobile edge computing system with multiple devices, unmanned aerial vehicles and edge servers. The proposed framework takes into account the randomness of workload arrival, the time-varying nature of channel states, the limitations of the hosting service caching, and wireless communication blocking. Furthermore, we designed workload offloading and service caching hosting decision-making optimization problems to minimize the long-term weighted average latency and energy consumption costs. To tackle this joint optimization problem, we propose a request-specific workload offloading and service caching decision-making scheme based on the medley deep reinforcement learning scheme. To this end, the proposed scheme is decomposed into two-stage optimization subproblems: the workload offloading decision-making problem and the service caching hosting selection problem. In terms of the first subproblem, we model each device as a learning agent and propose the workloads offloading decision-making scheme based on multi-agent deep deterministic policy gradient. For the second subproblem, we present the decentralized double deep Q-learning scheme to tackle the service caching hosting policy. According to the comprehensive experimental results, the proposed scheme is able to converge rapidly on various parameter configurations and whose performance surpasses the other four ba

关键词： Edge server allocation   Mobile edge computing   Workload balance   Fitness dependent optimizer   Access delay   PARTICLE SWARM OPTIMIZATION   EFFICIENCY   PLACEMENT  

摘要： Due to the speedy development of mobile communication devices, the traditional cloudlet computing networks struggle to manipulate the huge collected data from these devices. Mobile computing has been developed to overcome the access delay (AD) and the workload balance (WB) in the traditional cloudlet networks by transferring the computing process from the remote servers in the cloudlet to the edge servers (ESs) allocated closer to the mobile users. The searching for the optimal place to allocate the ESs in mobile edge computing is the main challenge and it considers an NP-hard problem. In this work, we propose a new objective function with threefold objectives, the AD between base stations and ESs, the WB among various controlled ESs, and the energy consumption (EC) of ESs. Therefore, we formulate the edge server allocation problem as a multi-objective optimization problem that requires an efficient optimizer algorithm for solving it. To minimize the proposed objective function, we present an effective fitness-dependent optimizer (EFDO) algorithm and test it on Shanghai Telecom's BS dataset. To investigate the efficiency of the proposed EFDO algorithm, we compare it against seven algorithms taken from literature (e.g., K-means, Random, TopFirst, PSO, CSA, Jaya, and JS). The numerical results verified the superiority of the proposed algorithm in terms fitness function reached up to 14.84%, 18.56%, 17.28%, and 13.48% when compared with PSO, CSA, Jaya, and JS, respectively with various number of base stations and edge servers. Although k-means has been achieved the least average AD among compared algorithms which considered only the distance between the BS and ES, the proposed algorithm has achieved the superior results in WB ranged from 12 to 72% when compared against other algorithms. In addition, it has gained the least average EC among the compared algorithms.

关键词： Fog Computing   Mobile Edge Computing   Mobile Cloud Computing   ENERGY HARVESTING DEVICES   EDGE COMPUTING NETWORKS   RESOURCE-ALLOCATION   IOT NETWORKS   INTERNET   GAME   OPTIMIZATION   FRAMEWORK   AWARE   BLOCKCHAIN  

摘要： Today, cloud computation offloading may not be an appropriate solution for delay-sensitive applications due to the long distance between end-devices and remote datacenters. In addition, offloading to a remote cloud can consume bandwidth and dramatically increase costs. However, end-devices such as sensors, cameras, and smartphones have limited computing and storage capacity. Processing tasks on such battery-powered and energy-constrained devices becomes even more complex. To address these challenges, a new paradigm called Edge Computing (EC) emerged nearly a decade ago to bring computing resources closer to end-devices. Here, edge servers located between the end-device and the remote cloud perform user tasks. Recently, several new computing paradigms such as Mobile Edge Computing (MEC) and Fog Computing (FC) have emerged to complement Cloud Computing (CC) and EC. Although these paradigms are heterogeneous, they can further reduce energy consumption and task response time, especially for delay-sensitive applications. Computation offloading is a multi-objective, NP-hard optimization problem. A significant part of previous research in this field is devoted to Machine Learning (ML) methods. One of the essential types of ML is Reinforcement Learning (RL), in which an agent learns how to make the best decision using the experiences gained from the environment. This article provides a systematic review of the widely used RL approaches in computation offloading. It covers research in complementary paradigms such as mobile cloud computing, edge computing, fog computing, and the Internet of Things. We explain the reasons for using various RL methods in computation offloading from a technical point of view. This analysis includes both binary offloading and partial offloading techniques. For each method, the essential elements of RL and the characteristics of the environment are discussed regarding the most important criteria. Research challenges and Future trends are also mentioned.

关键词： Mobile edge computing   Emergency tasks   SDN   Collaborative computation offloading  

摘要： Due to the growing demand for time-intensive tasks, several tasks coexist, some of which last for a long time or only occur once in a while, such as emergencies. Emergencies such as natural disasters, accidents or medical emergencies require immediate attention and often demand real-time execution. Such tasks are the most difficult to plan for and foresee. Planning, resource allocation, and clear communication between all involved parties and network layers are crucial for scheduling emergency tasks. In the extensive literature, when an emergency task triggers, it will be handled like any other regular task. If the deadline is missed, a catastrophe will ensue. They ignored the impact of insufficient mobile edge computing (MEC) capacity and network congestion, which might result in execution delays. Collaborative offloading, which involves distributing computation tasks across multiple servers, shows promise in enhancing MEC network performance, particularly in emergency scenarios. In this context, efficient task scheduling plays a vital role in minimizing the total execution time of regular tasks while meeting the deadlines of emergency tasks. Our proposed scheme utilizes a collaborative offloading approach to schedule emergency tasks in MEC networks, leveraging the computing capacity of edge-deployed MEC servers. By utilizing the software-defined networking (SDN)'s global view of the network, task requests are collected and allocated to suitable MEC servers capable of meeting the demands. To address key challenges, our scheme propose four scheduling algorithms to address the following issues: (i) ensuring tasks are assigned to the nearest MEC server with sufficient computational resources, (ii) controlling a threshold to prevent network congestion, (iii) selecting an optimal collaborative MEC server for executing overloaded tasks based on collaborative offloading decisions, and (iv) allocating resources for emergency tasks when triggered to meet urgent deadlines by stealing resources from regular tasks without c