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.

关键词： Mobile edge computing  

摘要： The impending 6G network is envisioned to seamlessly interconnect a myriad of consumer electronics (CEs), facilitating a wide array of applications accessible from any location and at any time. To advance this objective, our paper proposes the integration of Mobile Edge Computing (MEC) with a multi-rotor Unmanned Aerial Vehicle (UAV), aiming to furnish computation offloading services for CEs of Ground Devices (GDs). Additionally, charging stations (CSs) are utilized to wirelessly charge the UAVs. Our objective is to minimize the UAV’s energy consumption for the entire mission by jointly optimizing both resource allocation and the UAV’s trajectory simultaneously. This entails solving a mixed-integer nonlinear programming (MINLP) optimization problem. Initially, we decompose the UAV’s trajectory into discrete offloading and charging locations, guided by a decision matrix. we decompose the optimization problem into two sub-problems. The first one determines offloading locations and resource allocation using Particle Swarm Optimization (PSO). The second one optimizes the decision matrix by incorporating PSO outputs and employing Double Deep Q-Network (DDQN), a form of deep reinforcement learning. Simulation results demonstrate that the proposed solution significantly reduces energy consumption compared to baseline schemes. IEEE

关键词： Task analysis   Cloud computing   Delays   Simulated annealing   Optimization   Computer architecture   Servers   Scheduling   Online services   Online task scheduling   simulated annealing   mobile edge computing   task offloading  

摘要： This paper introduces SATS, an innovative online task scheduling strategy tailored for hierarchical Mobile Edge Computing (MEC) architectures. Leveraging a Simulated Annealing-based approach, SATS extends the applicability of this method beyond offline scheduling, demonstrating its efficacy in real-time task allocation. Crucially, the paper underscores the pivotal role of accurate service request predictions in enhancing SATS' performance. Through a comparative analysis of three prediction models, neutral, conservative, and optimistic, the paper reveals that SATS achieves optimal outcomes when paired with a conservative predictor, which deliberately overestimates service request volumes. In fact, employing this predictor yields significantly higher acceptance rates and reduced processing times. Remarkably, SATS, coupled with a conservative predictor, achieves an acceptance ratio within a mere 5% deviation from an ideal scenario where the frequency of service request arrivals is known in advance, maintaining consistency across various experimental scenarios.

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： Distributed Denial of Service   EtherCAT   Inter Planetary File System   Mobile Edge Computing   Netlink   NSLKDD dataset   SoftRouter   Software-Defined Networking  

摘要： The advent of Software-Defined Networking (SDN) has ushered in a new era in network architecture, providing unprecedented levels of flexibility and adaptability. However, this advanced flexibility exposes SDN to security risks, particularly Distributed Denial of Service (DDoS) attacks. Detecting and mitigating DDoS attacks in SDN environments poses a critical challenge. This study introduces an innovative DDoS detection approach leveraging Echo State Networks (ESN) tailored specifically for SDN. This approach is based on two core assumptions: firstly, routine network operations primarily exhibit normal behavior, and secondly, there are discernible differences in data characteristics between normal and abnormal network conditions. These assumptions hold true in the realm of everyday network dynamics. To validate the efficacy of the ESN algorithm, we augment this approach by incorporating flow features to enhance DDoS detection capabilities. This study underscores the effectiveness of ESN in identifying and mitigating Distributed Denial of Service (DDoS) attacks, DDoS threats, achieving an impressive average success rate of 97.78%. By harnessing the potential of Echo State Networks, this work makes a substantial contribution to ongoing efforts in fortifying network security, providing a proactive defense against disruptive DDoS attacks. © (2024), (Research Institute of Intelligent Computer Systems). All rights reserved.

关键词： Servers   Training   Optimization   Computational modeling   Data privacy   Privacy   Data models   Federated learning   Multi-access edge computing   centralized learning   mobile edge computing  

摘要： To alleviate the substantial local training burden on clients in the federated learning (FL) process, this paper proposes a more efficient approach based on hybrid federated and centralized learning (HFCL), leveraging the Mobile Edge Computing (MEC) environment within wireless communication networks. Considering the existence of heterogeneous data types with different privacy levels -such as 1) sensitive data, which can not be exposed, and 2) less-sensitive data, which can be exposed for centralized learning (CL)-we formulate an optimization problem aimed at achieving a balance between 1) total latency, including computation and communication, and 2) the training burden on the MEC server. This balance is achieved by adjusting the set of participants in FL, taking into account client selection under different privacy levels. A multi-objective optimization problem is designed using mixed-integer nonlinear programming, which is generally recognized as NP-hard. We employ relaxation techniques in combination with the Mutas & Simulated Annealing Heuristic algorithm to develop a near-optimal yet practical algorithm. Our numerical and simulation results reveal that the proposed scheme effectively achieves a global model by striking a balance between the total time required for model convergence and the computational load on the MEC server. Furthermore, experimental results on three well-known real-world datasets demonstrate that the proposed scheme maintains an acceptable level of accuracy and loss.

关键词： Mobile edge computing  

摘要： With the development of artificial intelligence, there is an increasing demand for edged computing visual sensors, particularly those integrated with visual object detection capability. However, the deployment of object detection models in edge computing environments faces technical challenges in many aspects, such as model size, inference speed, accuracy, and deployment optimization. This paper systematically summarizes the knowledge related to the deployment of object detection at the edge computing side, including mainstream models, deployment optimization methods, edge computing deployment frameworks, and deployment devices, based on practical technical experience. The strengths and weaknesses of the various models and their applicability are analyzed, and the optimization and deployment of models on edge devices are explored in depth, with a focus on adapting them to the specific characteristics of edge computing environments. This paper is intended to provide valuable reference and insight to researchers and developers in the field, we provide deployment code for reference at repository https://***/shouxieai/tensorRT Pro. © 2001-2012 IEEE.

关键词： Mobile edge computing  

摘要： While improving network performance, Mobile Edge Computing (MEC) faces significant security threats due to User Equipment (UE) vulnerabilities and insecure communication protocols. This enables attackers to insert malicious nodes into the entire system and propagate worms such as the Mirai, enabling activities like DDoS attacks and cryptocurrency mining. To reduce security risks, it is necessary to identify worm sources and predict their propagation accurately. However, in practice, there exist a large number of stealthy worms (nodes that infect stealthy worms work without exhibiting any abnormal behavior), making it challenging to accurately analyze their source and predict their propagation. To address this problem, our paper introduces a prediction scheme designed to analyze the propagation of stealthy worms originating from unknown sources. First, a Bayes rule-based observation algorithm is designed to correct false-negative nodes and increase the accuracy of identifying the propagation sources. Then, we design a branch-and-bound algorithm to effectively reduce the traversal space and improve the efficiency of calculating the upper and lower bounds. Finally, a series of experiments in four real networks are conducted to show the accuracy and efficiency of our scheme. © 1975-2011 IEEE.

关键词： Mobile edge computing  

摘要： The ever-increasing scale and more stringent latency requirements of mobile computing tasks have driven the recent development of distributed edge computing. In distributed edge computing, a large-scale computing task is partitioned into multiple small subtasks and executed in parallel on multiple edge nodes (ENs) to reduce computation delay. In early works of this area, the computation results of the subtasks are often transmitted back in a non-cooperative manner, which may lead to suboptimal downlink communication delay. Replicated edge computing can alleviate this issue by replicating the computing task over multiple ENs to enable cooperative transmission in the downlink. However, this will inevitably entail multi-fold increase of computation costs. To bridge the gap between the conventional distributed edge computing and the replicated edge computing, a novel partial replication based distributed edge computing scheme is proposed in this work. In particular, by judiciously determining the portion of task to be replicated at the ENs, the proposed scheme can harvest cooperative transmission gains while avoiding excessive computational replication costs. Accordingly, a partial replication based delay minimization problem is formulated. By leveraging the generic alternating optimization framework, this problem can be divided into two subproblems of power allocation and task partitioning. Through analysis, a semi-closed form solution is derived for the former non-convex subproblem, while the latter subproblem turns out to be linear. Simulation results are presented to corroborate the effectiveness of the proposed scheme. © 1972-2012 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.