关键词： Mobile edge computing   Blockchain   Matching theory   Contract theory   Information scenario  

摘要： The application of blockchain technology on mobile devices requires significant computing resources. However, the limited capacity of mobile devices cannot meet the high computing power requirements of blockchain technology, which limits the development and implementation of blockchain application. Mobile Edge Computing (MEC) is capable of alleviate the limited computing capacity of IoT terminals. This paper introduces a MEC-enabled blockchain system consisting of an edge computing allocation center (ECAC), multiple edge service providers (ESPs), and multiple miners. To efficiently allocate resources between these ESPs and miners, a hierarchical computation offloading strategy based on contract theory and matching game is proposed. During contract design phase, ECAC makes a contribution-reward contract to attract ESPs to join the trading market, and provide services to miners. By analyzing the attributes and conditions of feasible contract, the optimal contract is devised using Lagrange multiplication. During matching phase, an iterative matching algorithm (IMA) is proposed to achieve the matching between ESPs and miners by constructing preference sets. Both the stability and convergence of IMA have been proved by theoretical analysis. Finally, we conduct experiments to validate the feasibility and effectiveness of the design contract, and the stability of IMA has also demonstrated by experimental results.

关键词： Mobile edge computing   Computation offloading   Task migration   Deep reinforcement learning  

摘要： The space-air-ground-sea integrated network (SAGSIN) integrates diverse heterogeneous networks, which makes the pervasive communication and computing service of maritime users possible. In SAGSIN, communication nodes are scarce and computing resources are tight. Tasks of users can be offloaded to the network edge, such as at surface ship, buoy and drone. However, some traditional task offloading decisions become inapplicable as users move or the topology of networks changes. Therefore, in order to ensure the continued effectiveness of the task offloading strategy in dynamic ocean scenarios, we need to design an efficient offloading method to improve the overall network performance. To address this issue, we propose a resource-aware deep reinforcement learning method to optimize task offloading decisions. In this scheme, the available resources of mobile users are perceived in real time, and efficient computation offloading and task migration decisions are made based on the results. Simulation results validate the effectiveness of the proposed algorithm. In addition, the simulation results show that the proposed algorithm can effectively reduce the system delay and energy consumption as the number of tasks increases, and reduce task migration.

关键词： Mobile edge computing   Internet of things   Deep reinforcement learning   Task offloading   Low carbon emission  

摘要： Mobile edge computing is an emerging computing paradigm in the Internet of Things. Task offloading is a critical method in mobile edge computing to alleviate computational resource constraints. Nowadays, the rising number of tasks is placing greater demands on computing resources. The increasing consumption of computing resources leads to high carbon emission. Achieving environmentally friendly mobile edge computing while effectively managing low-carbon task offloading poses a significant challenge. Recently, deep reinforcement learning has made certain progress in many research fields. However, there are few deep reinforcement learning methods that consider the carbon emission in task offloading. In this paper, we propose a deep reinforcement learning based low carbon emission task offloading algorithm for minimizing carbon emission in mobile edge computing. Firstly, since different base stations exist in the mobile edge computing environment, we consider the mobile edge computing environment with multiple heterogeneous agents. Secondly, to minimize carbon emission, we consider the carbon intensity of the base station as an optimization factor. We conclude the task offloading strategy to minimize carbon emission, consequently achieving the minimization of carbon emission. Moreover, our proposed algorithm allows user devices to decide their own preference for task offloading. Based on the specific requirements and preferences of user devices, our proposed algorithm can dynamically adjust the weights of delay, energy consumption, and carbon emission, respectively. Experiments indicate that the proposed algorithm can accurately and quickly conclude the task offloading strategy to minimize carbon emission.

关键词： Mobile edge computing   Task offloading   Independent task   Dependent task   Centralized/distributed decision-making  

摘要： With the rapid proliferation of mobile devices and the continuous emergence of new applications, the traffic on mobile networks has increased exponentially. The traditional cloud computing model has been inadequate in meeting the application service requirements for high traffic and large connections. Mobile Edge Computing (MEC) offers an efficient solution to achieve service localization by offloading tasks from mobile devices to the network edge for processing. While there have been numerous studies in this field from various perspectives, most of them overlook the impact of task independence on computation offloading decisions. This paper presents a comprehensive survey of computation offloading techniques focusing on task types, explores the decision-making problem for offloading under independent and dependent task conditions, and thoroughly covers strategies, algorithms, and challenges related to computation offloading in MEC.

关键词： Mobile edge computing   Multi-motion status   Lyapunov optimization   Deep reinforcement learning  

摘要： In mobile edge computing (MEC) networks, users can offload computational tasks from their devices to nearby mobile edge servers, reducing their computational loads and improving user experience quality. However, users exhibit various movement patterns with inherent random mobility in practice. Additionally, data that needs processing arrives randomly over continuous periods. To stabilize data and energy consumption in complex real-world environments and maximize the network system's data processing capacity, we propose a User Trajectory Prediction-Lyapunov-guided Deep Reinforcement Learning (UTP-LyDRL) algorithm. This algorithm first predicts the movement trajectories of mobile users (MUs) using a Mobility-aware Offloading (MO) mechanism. It then formulates the problem of both MUs and fixed users (FUs) as a Mixed Integer Nonlinear Programming (MINLP) problem. Through Lyapunov optimization, the multi-stage MINLP problem is decomposed into deterministic MINLP sub-problems for each time frame, ensuring long-term constraint satisfaction. Subsequently, combining model-free training with DRL, the algorithm addresses the binary offloading of FUs across sequential time frames and overall system resource allocation. Simulation results indicate that the proposed UTP-LyDRL algorithm optimizes computational performance and ensures the stability of all data and energy queues within the system.

关键词： Cellular heterogeneous networks   Non-orthogonal multiple access   Mobile edge computing   Task offloading   Resource allocation  

摘要： Mobile edge computing (MEC) is an effective strategy for real-time data processing and lowering data transmission latency between end devices and the cloud, which can minimize network congestion and improve user experience. This paper examines the problem of system energy consumption minimization in a cellular heterogeneous network (HetNets) MEC architecture with non-orthogonal multiple access (NOMA). The NOMA protocol is used by each base station to serve users within its small cell, and each base station is fitted with an edge computing server. Because of the parameter coupling, energy consumption minimization is a difficult non- convex optimization problem. Asa result, the problem is divided into three subproblems, the computational and communication resource allocation subproblem and the task offloading subproblem being optimally solved by their convexity, while the subchannel allocation and power control subproblems are solved by sequential convex programming. Then, for each of the three subproblems, an efficient iterative technique is presented. Simulation results show that the partial offloading strategy under NOMA (PO-NOMA) proposed in this paper outperforms several baseline strategy, including all local computation, complete offloading, random offloading strategy, and greedy offloading strategy, and outperforms Orthogonal Multiple Access (OMA)-based MEC in cellular heterogeneous networks in a cellular heterogeneous network scenario.

关键词： mobile edge computing   computation offloading   ultra-dense network   resource allocation  

摘要： Mobile edge computing (MEC) is a modern technique that has led to substantial progress in wireless networks. To address the challenge of efficient task implementation in resource-limited environments, this work strengthens system performance through resource allocation based on fairness and energy efficiency. Integration of energy-harvesting (EH) technology with MEC improves sustainability by optimizing the power consumption of mobile devices, which is crucial to the efficiency of task execution. The combination of MEC and an ultra-dense network (UDN) is essential in fifth-generation networks to fulfill the computing requirements of ultra-low-latency applications. In this study, issues related to computation offloading and resource allocation are addressed using the Lyapunov mixed-integer linear programming (MILP)-based optimal cost (LYMOC) technique. The optimization problem is solved using the Lyapunov drift-plus-penalty method. Subsequently, the MILP approach is employed to select the optimal offloading option while ensuring fairness-oriented resource allocation among users to improve overall system performance and user satisfaction. Unlike conventional approaches, which often overlook fairness in dense networks, the proposed method prioritizes fairness-oriented resource allocation, preventing service degradation and enhancing network efficiency. Overall, the results of simulation studies demonstrate that the LYMOC algorithm may considerably decrease the overall cost of system execution when compared with the Lyapunov-MILP-based short-distance complete local execution algorithm and the full offloading-computation method.

关键词： jellyfish search optimizer   kookaburra optimization algorithm   mobile edge computing   tasks offloading   unmanned aerial vehicles  

摘要： Mobile edge computing (MEC) is extensively utilized for supporting diverse mobile applications and the Internet of Things (IoT). One of MEC's prime operations is utilizing unmanned aerial vehicles (UAVs) included with the MEC servers for providing computational aids for offloaded tasks by mobile users in temporal hotspot regions or a few emerging situations like sports areas or environmental disaster regions. However, despite the various merits of UAVs executed with MEC servers, it is constrained by their insufficient sensible energy consumption and computational resources. Furthermore, owing to the complication of UAV-aided MEC systems, energy consumption optimizations and computation resource optimizations cannot be obtained better in conventional optimization schemes. In this research, the kookaburra jellyfish algorithm (KJA) is presented for task offloading in a UAV-enabled MEC network. The main objective is to enhance the efficiency of task offloading in UAV-enabled MEC networks by optimizing energy consumption, computational resources, and communication time using the KJA. Initially, the UAV-enabled MEC network model is simulated. Next, task computation is performed, and thereafter, task uploading is carried out. Then, task offloading is executed using KJA with consideration of multiobjective models, namely, energy consumption, communication time, and cost. Moreover, KJA is devised by integrating kookaburra optimization algorithm (KOA) with jellyfish search optimizer (JSO). Afterward, the task offloading process and data transmission are conducted. In addition, KJA obtained minimum energy, load, and time of 0.448 J, 0.122, and 1.036 s.

关键词： Mobile edge computing   Random task processing   Service loss   Service revenue   Partheno-genetic algorithm  

摘要： Mobile Edge Computing alleviates network congestion and reduces latency by offloading tasks to the network edge. However, fluctuating Quality of Service (QoS) and service compositions significantly challenge service reliability and utility optimization. To address these challenges, this paper proposes a novel virtual machine allocation framework designed to maximize the utility of edge cloud service provisioning under QoS constraints. First, the task processing mechanism is modeled as an M/M/m queuing system, with service loss and revenue functions defined to quantify the quality and profitability of edge services. Next, the framework dynamically reallocates virtual machines across sub-service centers, based on task arrival rates and varying QoS requirements, to optimize overall service utility. Finally, we develop a partheno-genetic algorithm based on integer coding to solve the service utility maximization (SOPGA) to determine the optimal virtual machine allocation strategy. Simulation results demonstrate that the proposed virtual machine allocation algorithm improves service utility by more than 20% compared to other virtual machine allocation algorithms, significantly enhancing service utility in edge cloud environments while maintaining robust QoS guarantees.

关键词： Mobile edge computing   Medical imaging   Collaborative inference   Feature compression   Reinforcement learning  

摘要： The popularity and convenience of mobile medical image analysis and diagnosis in mobile edge computing (MEC) environments have greatly improved the efficiency and quality of healthcare services, necessitating the use of deep neural networks (DNNs) for image analysis. However, DNNs face performance and energy constraints when operating on the mobile side, and are limited by communication costs and privacy issues when operating on the edge side, and previous edge-end collaborative approaches have shown unstable performance and low search efficiency when exploring classification strategies. To address these issues, we propose a DNN edge-optimized collaborative inference strategy (MOCI) for medical image diagnosis, which optimizes data transfer and computation allocation by combining compression techniques and multi-agent reinforcement learning (MARL) methods. The MOCI strategy first uses coding and quantization-based compression methods to reduce the redundancy of image data during transmission at the edge, and then dynamically segments the DNN model through MARL and executes it collaboratively between the edge and the mobile device. To improve policy stability and adaptability, MOCI introduces the optimal transmission distance (Wasserstein) to optimize the policy update process, and uses the long short-term memory (LSTM) network to improve the model's adaptability to dynamic task complexity. The experimental results show that the MOCI strategy can effectively solve the collaborative inference task of medical image diagnosis and significantly reduce the latency and energy consumption with less than a 2% loss in classification accuracy, with a maximum reduction of 38.5% in processing latency and 71% in energy consumption compared to other inference strategies. In real-world MEC scenarios, MOCI has a wide range of potential applications that can effectively promote the development and application of intelligent healthcare.