关键词： Mobile edge computing  

摘要： With the rapid development of internet of everything, current Mobile Consumer Electronics (MCEs) can support complex computing due to their specialized data-handling capacity. Thus, federated Machine Learning (ML) and edge computing are integrated to leverage such capacity of MCEs to enhance large model training. This paper studies motivations of all participants that take part in large model collaborative optimization from a global perspective, and proposes the positive promotion pattern that collaborates MCEs, Edge Computing Servers (ECSs), and the centralized computing center to support large model collaborative optimization by introducing the idea of computing economic. We firstly propose the novel three-layered framework for large model collaboratively optimizing based on MCEs constructed federated ML. Secondly, we introduce the economic factor into the large model optimization by devising algorithms to assess consumptions of all participants and dynamically adjust incentive benefits according to the qualities of trained models. Finally, we design the scheme to encourage more MCEs to train local models by adaptively adjusting the ECS pricing strategy with the ECS future economic benefit trend considered. Experimental results validate that our proposed approach is able to optimize the global accuracy and improve the economic benefit more efficiently than the state of the art. © 1975-2011 IEEE.

关键词： Autonomous aerial vehicles   Task analysis   Training   Trajectory   Optimization   Approximation algorithms   Trajectory planning   Multi-access edge computing   Edge computing   Mobile edge computing   spiking neural network   deep reinforcement learning   unmanned aerial vehicle   trajectory planning  

摘要： This study aims to minimize the energy consumption of user equipments (UE) and unmanned aerial vehicles (UAV) in UAV-assisted mobile edge computing (MEC) systems through the optimization of UAV flight trajectories, user associations, and resource allocations. The problem is formally articulated as a mixed integer nonlinear programming (MINLP) problem. However, employing deep reinforcement learning (DRL) to address this challenge introduces computational complexity and convergence obstacles. In response to these challenges, we propose an efficient and robust approach known as spiking reinforcement trajectory planning (SRTP), which uniquely integrates spiking neural networks (SNN) with DRL. SRTP utilizes a Poisson encoding mechanism to seamlessly convert between spike and continuous signals, enabling collaborative learning between spike actor networks and deep critic networks. Additionally, a pseudo-spacetime backpropagation method is employed for accelerated training of the spike actor network. Experimental findings distinctly highlight SRTP's advantages, demonstrating a more streamlined network structure and faster convergence compared to conventional methodologies. This innovative methodology holds promise in addressing the computational complexities and convergence challenges associated with implementing DRL in UAV-assisted MEC systems.

关键词： Disasters   Sensors   Satellites   Processor scheduling   Resource management   Autonomous aerial vehicles   Internet of Things   Edge information hub   latency   mobile edge computing   non-terrestrial network   resource orchestration  

摘要： Quick response to disasters is crucial for saving lives and reducing loss. This requires low-latency uploading of situation information to the remote command center. Since terrestrial infrastructures are often damaged in disaster areas, non-terrestrial networks (NTNs) are preferable to provide network coverage, and mobile edge computing (MEC) could be integrated to improve the latency performance. Nevertheless, the communications and computing in MEC-enabled NTNs are strongly coupled, which complicates the system design. In this paper, an edge information hub (EIH) that incorporates communication, computing and storage capabilities is proposed to synergize communication and computing and enable systematic design. We first address the joint data scheduling and resource orchestration problem to minimize the latency for uploading sensing data. The problem is solved using an optimal resource orchestration algorithm. On that basis, we propose the principles for resource configuration of the EIH considering payload constraints on size, weight and energy supply. Simulation results demonstrate the superiority of our proposed scheme in reducing the overall upload latency, thus enabling quick emergency rescue.

关键词： semiring   centralizer   discrete logarithm problem   factor problem   undeniable signature   mobile edge computing  

摘要： The Undeniable Signature Scheme ( USS ) was first introduced by chaum and van in 1989. The advantage of the ( USS ) scheme is the signer's co-operation during the verification process. In this paper, the Discrete Logarithm Problem with Factor Problem ( DLFP ) is introduced. It's security and complexity is analyzed. Then, based on ( DLFP ) , a key exchange protocol is given. An undeniable signature scheme based on DLFP over semiring is proposed along with illustration we have also given application of the proposed USS in Mobile Edge Computing ( MEC ) . Then the proposed scheme's security and complexity is examined.

关键词： Task offloading   vehicular networks   matching algorithm   matching algorithm   genetic algorithm   genetic algorithm   mobile edge computing   mobile edge computing   mobile edge computing  

摘要： With the developments of the intelligent vehicles, the most significant contradiction is coming to the limited computing resource and the unlimited requirements. Task offloading has been proposed to overcome this. Most of the existing task offloading methods aim to optimize the global delay. However, from the user's point of view, different in-vehicle applications (such as entertainment and autonomous driving) have different importance and delay requirements. Therefore, simply minimizing the latency of all tasks does not meet the QoS (Quality of Service) of each user. Unfortunately, very few people discuss this practical issue. In this paper, the problem of vehicular task offloading in resource-constrained scenarios is studied, and a two-stage task offloading scheme MAT-IGA based on multi-node collaboration is proposed. In the first stage, the complex tasks are pre-segmented adaptively, and the optimal matching set is solved by combining the improved multi-round deferred-acceptance algorithm, which prioritizes the resource requirements of emergency tasks and improves the reliability of the strategy. In the second stage, a chaotic genetic algorithm based on opposition-based learning is used to optimize resource allocation, and the global delay and cost are optimized on the basis of ensuring the success rate. The simulation results show that the proposed method is superior to the common baseline algorithm in different vehicle numbers and task characteristics.

关键词： mobile edge computing   intelligent finance   data sharing   blockchain   non-separable task  

摘要： The intelligent financial sharing platform in the online realm is capable of collecting, storing, processing, analysing and sharing financial data through the integration of AI and big data processing technologies. However, as data volume grows exponentially, the cost of financial data storage and processing increases, and the asset accounting and financial profit data sharing analysis structure in financial sharing platforms is inadequate. To address the issue of data security sharing in the intelligent financial digital sharing platform, this paper proposes a data-sharing framework based on blockchain and edge computing. Building upon this framework, a non-separable task distribution algorithm based on data sharing is developed, which employs multiple nodes for cooperative data storage, reducing the pressure on the central server for data storage and solving the problem of non-separable task distribution. Multiple sets of comparative experiments confirm the proposed scheme has good feasibility in improving algorithm performance and reducing energy consumption and latency.

关键词： Mobile edge computing  

摘要： E dge computing is a distributed computing paradigm that moves processing and data closer to the consumer. The main benefi ts of edge computing include decreased latency, higher bandwidth availability, and fi ne-grained control of quality of service (QoS).

关键词： Task analysis   Servers   Games   Cyber-physical systems   Nash equilibrium   Costs   Computational modeling   mobile edge computing   multi-agent systems   potential game   task offloading  

摘要： The intelligentization of cyber-physical systems has led to an influx of computational tasks, placing substantial strain on the systems' computational and storage resources. High-speed railway (HSR), as a representative cyber-physical system, requires increased task completion rates and reduced energy consumption within defined timeframes. Effectively managing the surge in computational tasks within cyber-physical systems has become an urgent issue requiring resolution. This paper introduces a game-based task offloading strategy that addresses dynamic latency and energy consumption. Specifically, the study employs Stochastic Network Calculus (SNC) to capture the impact of transmission latency on system performance and obtain the bounds and probability distribution of transmission latency. Subsequently, the task offloading problem is formulated as a potential game, with each task acting as a player optimizing its objective, which includes the task completion rate and energy consumption. The Nash Equilibrium state is derived to ensure the existence of a task offloading strategy. Additionally, a reinforcement learning algorithm, Multi-Agent Deep Deterministic Policy Gradient (MADDPG), is proposed to achieve the Nash Equilibrium and optimize the task offloading strategy. Finally, extensive simulations demonstrate that the MADDPG algorithm outperforms other algorithms and exhibits fast convergence. Moreover, an appropriate violation probability derived from SNC can reduce system costs.

关键词： Internet of Vehicles   mobile edge computing   resource allocation   reinforcement learning   task offloading  

摘要： Edge computing plays a crucial role in the field of the Internet of Vehicles (IoV), meeting the resource and latency requirements of time-sensitive vehicle applications. However, the emergence of numerous compute-intensive and latency-sensitive applications, such as augmented reality and autonomous driving, has led to a situation where traditional edge computing architectures cannot meet the increasing application demands of the IoV. This paper extends the paradigm of vehicular edge computing to a collaborative cloud-edge cluster resource provisioning framework. Integrating compute resources from multiple Edge Service Providers (ESP) and the cloud enables horizontal and vertical collaborative computation offloading among service nodes. To facilitate resource sharing among different ESPs, we introduce a dynamic pricing model and utilize software-defined networking (SDN) to tackle this scenario's complex resource management challenges. Furthermore, with the optimization objectives of minimizing task computation latency and maximizing the profits of ESPs, we establish a mathematical model. Before resource allocation, we employ a clustering algorithm to determine initial offloading decisions, reducing the dimensionality of the action space. Subsequently, we employ the Double Deep Q-Network (DDQN) algorithm to achieve a rational allocation of compute resources. Simulation results demonstrate that compared to the Deep Q-Network (DQN) algorithm and greedy strategy, the proposed approach reduces latency by 18.18% and 34.85%, respectively, while increasing the profits of edge service providers by 16.25% and 33.33%, respectively.

关键词： Mobile edge computing  

摘要： This paper considers an aerial edge computing (AEC) paradigm, where unmanned aerial vehicles (UAVs) are deployed as edge servers to provide computing services to mobile devices (MDs) in remote and hard-to-reach regions. Although offloading compute-intensive tasks to edge servers can improve the quality of experience and reduce energy consumption of MDs, it poses challenges in efficient system management due to the limitation in energy and bandwidth resources of the servers. To address this issue, we propose a green AEC architecture where servers can harvest energy from renewable resources such as solar power. We formulate an optimization problem that aims to maximize the MDs' long-term satisfaction while guaranteeing sustainable operation for the UAVs by controlling computation offloading and resource allocation decisions. We leverage the Lyapunov optimization theory to handle long-term energy constraints in the formulated problem and then develop a deep deterministic policy gradient (DDPG) algorithm to solve the problem considering a dynamic network environment. We also integrate prioritized experience replay and weighted importance sampling techniques into the DDPG algorithm to improve learning performance. Experimental results demonstrate that the proposed solution achieves high performance and adapts well to network variations. © 2017 IEEE.