关键词： unmanned aerial vehicle   mobile edge computing   anarchic federated learning   artificial intelligence   cooperative dynamic resource allocation  

摘要： Providing robust communication services to mobile users (MUs) is a challenging task due to the dynamicity of MUs. Unmanned aerial vehicles (UAVs) and mobile edge computing (MEC) are used to improve connectivity by allocating resources to MUs more efficiently in a dynamic environment. However, energy consumption and lifetime issues in UAVs severely limit the resources and communication services. In this paper, we propose a dynamic cooperative resource allocation scheme for MEC-UAV-enabled wireless networks called joint optimization of trajectory, altitude, delay, and power (JO-TADP) using anarchic federated learning (AFL) and other learning algorithms to enhance data rate, use rate, and resource allocation efficiency. Initially, the MEC-UAVs are optimally positioned based on the MU density using the beluga whale optimization (BLWO) algorithm. Optimal clustering is performed in terms of splitting and merging using the triple-mode density peak clustering (TM-DPC) algorithm based on user mobility. Moreover, the trajectory, altitude, and hovering time of MEC-UAVs are predicted and optimized using the self-simulated inner attention long short-term memory (SSIA-LSTM) algorithm. Finally, the MUs and MEC-UAVs play auction games based on the classified requests, using an AFL-based cross-scale attention feature pyramid network (CSAFPN) and enhanced deep Q-learning (EDQN) algorithms for dynamic resource allocation. To validate the proposed approach, our system model has been simulated in Network Simulator 3.26 (NS-3.26). The results demonstrate that the proposed work outperforms the existing works in terms of connectivity, energy efficiency, resource allocation, and data rate.

关键词： Mobile edge computing   Wireless power transfer   Particle swarm optimization   Multi-source data stream  

摘要： Due to its low latency and energy consumption, edge computing technology is essential in processing multi-source data streams from intelligent devices. This article investigates a mobile edge computing network aided by wireless power transfer (WPT) for multi-source data streams, where the wireless channel parameters and the characteristic of the data stream are varied. Moreover, we consider a practical communication scenario, where the devices with limited battery capacity cannot support the executing and transmitting of computational data streams under a given latency. Thus, WPT technology is adopted for this considered network to enable the devices to harvest energy from the power beacon. In further, by considering the device's energy consumption and latency constraints, we propose an optimization problem under energy constraints. To solve this problem, we design a customized particle swarm optimization-based algorithm, which aims at minimizing the latency of the device processing computational data stream by jointly optimizing the charging and offloading strategies. Furthermore, simulation results illustrate that the proposed method outperforms other benchmark schemes in minimizing latency, which shows the proposed method's superiority in processing the multi-source data stream.

关键词： Mobile edge computing  

摘要： Federated learning (FL) is a collaborative learning paradigm for decentralized private data from mobile terminals (MTs). However, it suffers from issues in terms of communication, resource of MTs, and privacy. Existing privacy-preserving FL methods usually adopt the instance-level differential privacy (DP), which provides a rigorous privacy guarantee but with several bottlenecks: severe performance degradation, transmission overhead, and resource constraints of edge devices such as MTs. To overcome these drawbacks, we propose Fed-LTP, an efficient and privacy-enhanced FL framework with Lottery Ticket Hypothesis (LTH) and zero-concentrated DP (zCDP). It generates a pruned global model on the server side and conducts sparse-to-sparse training from scratch with zCDP on the client side. On the server side, two pruning schemes are proposed: (i) the weight-based pruning (LTH) determines the pruned global model structure;(ii) the iterative pruning further shrinks the size of the pruned model's parameters. Meanwhile, the performance of Fed-LTP is also boosted via model validation based on the Laplace mechanism. On the client side, we use sparse-to-sparse training to solve the resource-constraints issue and provide tighter privacy analysis to reduce the privacy budget. We evaluate the effectiveness of Fed-LTP on several real-world datasets in both independent and identically distributed (IID) and non-IID settings. The results clearly confirm the superiority of Fed-LTP over state-of-the-art (SOTA) methods in communication, computation, and memory efficiencies while realizing a better utility-privacy trade-off. Copyright © 2023, The Authors. All rights reserved.

关键词： 5G   6G   mobile edge computing   migration   offloading   quality of service  

摘要： Next-generation cellular networks are expected to provide users with innovative gigabits and terabits per second speeds and achieve ultra-high reliability,availability,and ultra-low *** requirements of such networks are the main challenges that can be handled using a range of recent technologies,including multi-access edge computing(MEC),artificial intelligence(AI),millimeterwave communications(mmWave),and software-defined *** aspects and design challenges associated with the MEC-based 5G/6G networks should be solved to ensure the required quality of service(QoS).This article considers developing a complex MEC structure for fifth and sixth-generation(5G/6G)cellular ***,we propose a seamless migration technique for complex edge computing *** developed migration scheme enables services to adapt to the required load on the radio *** proposed algorithm is analyzed for various use cases,and a test bench has been developed to emulate the operator’s *** obtained results are introduced and discussed.

关键词： Mobile edge computing   Deep neural network (DNN)   DNN partitioning and offloading   Heterogeneous edge computing  

摘要： Mobile edge computing is conducive to artificial intelligence computing near terminals, in which Deep Neural Networks (DNNs) should be partitioned to allocate tasks partially to the edge for execution to reduce latency and save energy. Most of the existing studies assume that the tasks are of the same type or the computing resources of the server are the same. In real life, Mobile Devices (MDs) and Edge Servers (ESs) are heterogeneous in type and computing resources, it is challenging to find the optimal partition point for each DNN and offload it to an appropriate ES. To fill this gap, we propose a partitioning-and-offloading scheme for the heterogeneous tasks-server system to reduce the overall system latency and energy consumption on DNN inference. The scheme has four steps. First, it establishes a partitioning and task offloading model for adaptive DNN model. Second, to reduce the solution space, the scheme designs a Partition Point Retain (PPR) algorithm. After that, the scheme gives an Optimal Partition Point (OPP) Algorithm to find the optimal partition point with the minimum cost for each ES corresponding to each MD. Based on the partition points, an offloading of DNN tasks for each MD is presented to finish the whole scheme. Simulations show that the proposed scheme reduces the total cost by 77.9% and 59.9% on average compared to Only-Local and Only-Server respectively in the heterogeneous edge computing environment.

关键词： cost optimization   dual optimization   IoT system   mobile edge computing   relay selection   zero latency  

摘要： The evolution of IoT, 5G and 6G aims to provide almost zero latency. Computation tasks size is different for different users. A framework for task computation achieving almost zero latency for stochastic demand is a challenge. A relay-based D2D mobile edge computing (MEC) system is proposed. The idle device present in the networks is used as relay resources (RS). Mobile devices (MDs) communicate task to relay resources (RS) using D2D communication link. The RS perform computation and offloaded to edge server (ES). It aims to minimize total cost, energy expenditure and overall latency. Problem is formulated as mixed-integer nonlinear-constrained problem (MINCP). A three-step algorithm to optimize relay selection, power allocation and computation resource allocation is proposed. In the initial step optimal relay selection is obtained by the Kuhn-Munkres (KM) algorithm. In the next step, power allocation is obtained using Q-learning. In the last step, the main problem is converted into a cost optimization problem deciphered by the proposed algorithm. The substantial simulation results indicate the relay-based MEC system to achieve an astounding outcome in terms of latency, energy consumption and cost. Compared with other baseline methods, the proposed algorithm can achieve reduced energy consumption and cost for almost zero latency.

关键词： Task analysis   Servers   Batteries   Optimization   Internet of Things   Schedules   Resource management   Mobile edge computing   wireless power transfer   energy-efficient   resource allocation   deep Q-network   convex optimization  

摘要： Mobile edge computing (MEC) offers an opportunity for devices relying on wireless power transfer (WPT), to accomplish computationally demanding tasks. Such WPT-powered MEC systems have yet to be optimized for long-term efficiency, due to random and changing task demands and wireless channel states of the devices. This paper presents an augmented two-staged deep Q-network (DQN), referred to as "TS-DQN," for online optimization of WPT-powered MEC systems, where the WPT, offloading schedule, channel allocation, and the CPU configurations of the edge server and devices are jointly optimized to minimize the long-term average energy requirement of the systems. The key idea is to design a DQN for learning the channel allocation and task admission, while the WPT, offloading time and CPU configurations are efficiently optimized to precisely evaluate the reward of the DQN and substantially reduce its action space. Another important aspect is that a new action generation method is developed to expand and diversify the actions of the DQN, further accelerating its convergence. As validated by simulations, the proposed TS-DQN is much more energy efficient and converges much faster, than its potential alternative directly using the state-of-the-art Deep Deterministic Policy Gradient algorithm to learn all decision variables.

关键词： Robots   Task analysis   Servers   Resource management   Delays   Robot kinematics   Processor scheduling   Robot team   multi-robot system   mobile edge computing   interdependent computing   user association   resource allocation   multi-agent deep reinforcement learning  

摘要： A group of robots can be assigned with different roles to collaboratively conduct interdependent tasks. The robots form a multi-robot system (MRS), where one robot's decision or action relies on the others'. This paper addresses the sequential decision problem of user association and resource allocation in a mobile edge computing (MEC)-enabled, wirelessly-connected MRS to maximize the time-averaged completion rate of interdependent computing tasks. The problem is challenging due to the partial observability of the network environment, and the delicate delay requirements of interdependent computing tasks. A new decentralized partially observable Markov decision process (Dec-POMDP) problem is reformulated, where edge servers act as intelligent agents and can make decentralized decisions about user association and resource management with their local information of the network state. By leveraging the multi-agent deep deterministic policy gradient (MADDPG) theory, a new cooperative multi-agent deep reinforcement learning (MADRL) model is developed to enable interdependent computing. Simulations show the merits of our approach in terms of task completion rate compared to existing techniques.

关键词： Blockchain   industrial internet   mobile edge computing   task scheduling   reinforcement learning  

摘要： With the rapid development of the Internet of Things (IoT) and Internet technology, the product of the combination of the two, the Industrial Internet, has also received extensive attention and there are more and more research achievements related to the Industrial Internet. In the industrial Internet system, the communication network system composed of sensors, communication nodes, controllers and other intelligent devices can realize efficient and convenient data interaction between people and machines, providing an important infrastructure and technical support for industrial big data analysis and intelligent production. However, in the current industrial Internet system, industrial equipment users generally have the problem of low computing energy efficiency, and the collected industrial data has a high-security risk in the transmission, processing and other processes. At the same time, the size and scale of the industrial Internet equipment group is huge, and the lack of rational resource allocation leads to excessive waste of computing resources in the system, which is also a prominent problem of the current industrial Internet *** response to the above questions, this paper, on the basis of reading a large number of documents, integrates the improved DRL algorithm, End-Edge-Cloud architecture and blockchain to form a new industrial Internet architecture. The architecture realizes computing offload through the three-tier structure of terminal layer, edge layer and cloud layer, and guarantees the security of industrial data through the decentralized feature of blockchain, ultimately achieving the goal of reducing energy consumption, computing overhead and trusted computing. In the architecture proposed in this paper, the dynamic unloading of industrial data and computing tasks is achieved through a three-tier architecture. The MDP is used to build an optimization problem model, and the improved DRL algorithm is used to iteratively solve the optimal comput

关键词： Task analysis   Servers   Resource management   Device-to-device communication   Wireless communication   Mobile handsets   Energy consumption   Computation offloading   deep reinforcement learning   Index Terms   device-to-device   mobile edge computing   resource allocation  

摘要： Computation offloading via device-to-device communications can improve the performance of mobile edge computing by exploiting the computing resources of user devices. However, most proposed optimization-based computation offloading schemes lack self-adaptive abilities in dynamic environments due to time-varying wireless environment, continuous-discrete mixed actions, and coordination among devices. The conventional reinforcement learning based approaches are not effective for solving an optimal sequential decision problem with continuous-discrete mixed actions. In this paper, we propose a hierarchical deep reinforcement learning (HDRL) framework to solve the joint computation offloading and resource allocation problem. The proposed HDRL framework has a hierarchical actor-critic architecture with a meta critic, multiple basic critics and actors. Specifically, a combination of deep Q-network (DQN) and deep deterministic policy gradient (DDPG) is exploited to cope with the continuous-discrete mixed action spaces. Furthermore, to handle the coordination among devices, the meta critic acts as a DQN to output the joint discrete action of all devices and each basic critic acts as the critic part of DDPG to evaluate the output of the corresponding actor. Simulation results show that the proposed HDRL algorithm can significantly reduce the task computation latency compared with baseline offloading schemes.