As an important complement to cloud computing, edge computing can effectively reduce the workload of the backbone network. To reduce latency and energy consumption of edge computing, deep learning is used to learn the...As an important complement to cloud computing, edge computing can effectively reduce the workload of the backbone network. To reduce latency and energy consumption of edge computing, deep learning is used to learn the task offloading strategies by interacting with the entities. In actual application scenarios, users of edge computing are always changing dynamically. However, the existing task offloading strategies cannot be applied to such dynamic scenarios. To solve this problem, we propose a novel dynamic task offloading framework for distributed edge computing, leveraging the potential of meta-reinforcement learning (MRL). Our approach formulates a multi-objective optimization problem aimed at minimizing both delay and energy consumption. We model the task offloading strategy using a directed acyclic graph (DAG). Furthermore, we propose a distributed edge computing adaptive task offloading algorithm rooted in MRL. This algorithm integrates multiple Markov decision processes (MDP) with a sequence-to-sequence (seq2seq) network, enabling it to learn and adapt task offloading strategies responsively across diverse network environments. To achieve joint optimization of delay and energy consumption, we incorporate the non-dominated sorting genetic algorithm II (NSGA-II) into our framework. Simulation results demonstrate the superiority of our proposed solution, achieving a 21% reduction in time delay and a 19% decrease in energy consumption compared to alternative task offloading schemes. Moreover, our scheme exhibits remarkable adaptability, responding swiftly to changes in various network environments.展开更多
Cybertwin-enabled 6th Generation(6G)network is envisioned to support artificial intelligence-native management to meet changing demands of 6G applications.Multi-Agent Deep Reinforcement Learning(MADRL)technologies dri...Cybertwin-enabled 6th Generation(6G)network is envisioned to support artificial intelligence-native management to meet changing demands of 6G applications.Multi-Agent Deep Reinforcement Learning(MADRL)technologies driven by Cybertwins have been proposed for adaptive task offloading strategies.However,the existence of random transmission delay between Cybertwin-driven agents and underlying networks is not considered in related works,which destroys the standard Markov property and increases the decision reaction time to reduce the task offloading strategy performance.In order to address this problem,we propose a pipelining task offloading method to lower the decision reaction time and model it as a delay-aware Markov Decision Process(MDP).Then,we design a delay-aware MADRL algorithm to minimize the weighted sum of task execution latency and energy consumption.Firstly,the state space is augmented using the lastly-received state and historical actions to rebuild the Markov property.Secondly,Gate Transformer-XL is introduced to capture historical actions'importance and maintain the consistent input dimension dynamically changed due to random transmission delays.Thirdly,a sampling method and a new loss function with the difference between the current and target state value and the difference between real state-action value and augmented state-action value are designed to obtain state transition trajectories close to the real ones.Numerical results demonstrate that the proposed methods are effective in reducing reaction time and improving the task offloading performance in the random-delay Cybertwin-enabled 6G networks.展开更多
In task offloading,the movement of vehicles causes the switching of connected RSUs and servers,which may lead to task offloading failure or high service delay.In this paper,we analyze the impact of vehicle movements o...In task offloading,the movement of vehicles causes the switching of connected RSUs and servers,which may lead to task offloading failure or high service delay.In this paper,we analyze the impact of vehicle movements on task offloading and reveal that data preparation time for task execution can be minimized via forward-looking scheduling.Then,a Bi-LSTM-based model is proposed to predict the trajectories of vehicles.The service area is divided into several equal-sized grids.If the actual position of the vehicle and the predicted position by the model belong to the same grid,the prediction is considered correct,thereby reducing the difficulty of vehicle trajectory prediction.Moreover,we propose a scheduling strategy for delay optimization based on the vehicle trajectory prediction.Considering the inevitable prediction error,we take some edge servers around the predicted area as candidate execution servers and the data required for task execution are backed up to these candidate servers,thereby reducing the impact of prediction deviations on task offloading and converting the modest increase of resource overheads into delay reduction in task offloading.Simulation results show that,compared with other classical schemes,the proposed strategy has lower average task offloading delays.展开更多
Edge computing has transformed smart grids by lowering latency,reducing network congestion,and enabling real-time decision-making.Nevertheless,devising an optimal task-offloading strategy remains challenging,as it mus...Edge computing has transformed smart grids by lowering latency,reducing network congestion,and enabling real-time decision-making.Nevertheless,devising an optimal task-offloading strategy remains challenging,as it must jointly minimise energy consumption and response time under fluctuating workloads and volatile network conditions.We cast the offloading problem as aMarkov Decision Process(MDP)and solve it with Deep Reinforcement Learning(DRL).Specifically,we present a three-tier architecture—end devices,edge nodes,and a cloud server—and enhance Proximal Policy Optimization(PPO)to learn adaptive,energy-aware policies.A Convolutional Neural Network(CNN)extracts high-level features from system states,enabling the agent to respond continually to changing conditions.Extensive simulations show that the proposed method reduces task latency and energy consumption far more than several baseline algorithms,thereby improving overall system performance.These results demonstrate the effectiveness and robustness of the framework for real-time task offloading in dynamic smart-grid environments.展开更多
Fog computing is a key enabling technology of 6G systems as it provides quick and reliable computing,and data storage services which are required for several 6G applications.Artificial Intelligence(AI)algorithms will ...Fog computing is a key enabling technology of 6G systems as it provides quick and reliable computing,and data storage services which are required for several 6G applications.Artificial Intelligence(AI)algorithms will be an integral part of 6G systems and efficient task offloading techniques using fog computing will improve their performance and reliability.In this paper,the focus is on the scenario of Partial Offloading of a Task to Multiple Helpers(POMH)in which larger tasks are divided into smaller subtasks and processed in parallel,hence expediting task completion.However,using POMH presents challenges such as breaking tasks into subtasks and scaling these subtasks based on many interdependent factors to ensure that all subtasks of a task finish simultaneously,preventing resource wastage.Additionally,applying matching theory to POMH scenarios results in dynamic preference profiles of helping devices due to changing subtask sizes,resulting in a difficult-to-solve,externalities problem.This paper introduces a novel many-to-one matching-based algorithm,designed to address the externalities problem and optimize resource allocation within POMH scenarios.Additionally,we propose a new time-efficient preference profiling technique that further enhances time optimization in POMH scenarios.The performance of the proposed technique is thoroughly evaluated in comparison to alternate baseline schemes,revealing many advantages of the proposed approach.The simulation findings indisputably show that the proposed matching-based offloading technique outperforms existing methodologies in the literature,yielding a remarkable 52 reduction in task latency,particularly under high workloads.展开更多
Blockchain technology,based on decentralized data storage and distributed consensus design,has become a promising solution to address data security risks and provide privacy protection in the Internet-of-Things(IoT)du...Blockchain technology,based on decentralized data storage and distributed consensus design,has become a promising solution to address data security risks and provide privacy protection in the Internet-of-Things(IoT)due to its tamper-proof and non-repudiation features.Although blockchain typically does not require the endorsement of third-party trust organizations,it mostly needs to perform necessary mathematical calculations to prevent malicious attacks,which results in stricter requirements for computation resources on the participating devices.By offloading the computation tasks required to support blockchain consensus to edge service nodes or the cloud,while providing data privacy protection for IoT applications,it can effectively address the limitations of computation and energy resources in IoT devices.However,how to make reasonable offloading decisions for IoT devices remains an open issue.Due to the excellent self-learning ability of Reinforcement Learning(RL),this paper proposes a RL enabled Swarm Intelligence Optimization Algorithm(RLSIOA)that aims to improve the quality of initial solutions and achieve efficient optimization of computation task offloading decisions.The algorithm considers various factors that may affect the revenue obtained by IoT devices executing consensus algorithms(e.g.,Proof-of-Work),it optimizes the proportion of sub-tasks to be offloaded and the scale of computing resources to be rented from the edge and cloud to maximize the revenue of devices.Experimental results show that RLSIOA can obtain higher-quality offloading decision-making schemes at lower latency costs compared to representative benchmark algorithms.展开更多
With the rapid growth of connected devices,traditional edge-cloud systems are under overload pressure.Using mobile edge computing(MEC)to assist unmanned aerial vehicles(UAVs)as low altitude platform stations(LAPS)for ...With the rapid growth of connected devices,traditional edge-cloud systems are under overload pressure.Using mobile edge computing(MEC)to assist unmanned aerial vehicles(UAVs)as low altitude platform stations(LAPS)for communication and computation to build air-ground integrated networks(AGINs)offers a promising solution for seamless network coverage of remote internet of things(IoT)devices in the future.To address the performance demands of future mobile devices(MDs),we proposed an MEC-assisted AGIN system.The goal is to minimize the long-term computational overhead of MDs by jointly optimizing transmission power,flight trajecto-ries,resource allocation,and offloading ratios,while utilizing non-orthogonal multiple access(NOMA)to improve device connectivity of large-scale MDs and spectral efficiency.We first designed an adaptive clustering scheme based on K-Means to cluster MDs and established commu-nication links,improving efficiency and load balancing.Then,considering system dynamics,we introduced a partial computation offloading algorithm based on multi-agent deep deterministic pol-icy gradient(MADDPG),modeling the multi-UAV computation offloading problem as a Markov decision process(MDP).This algorithm optimizes resource allocation through centralized training and distributed execution,reducing computational overhead.Simulation results show that the pro-posed algorithm not only converges stably but also outperforms other benchmark algorithms in han-dling complex scenarios with multiple devices.展开更多
Multispectral low earth orbit(LEO)satel-lites are characterized by a large volume of captured data and high spatial resolution,which can provide rich image information and data support for a vari-ety of fields,but it ...Multispectral low earth orbit(LEO)satel-lites are characterized by a large volume of captured data and high spatial resolution,which can provide rich image information and data support for a vari-ety of fields,but it is difficult for them to satisfy low-delay and low-energy consumed task processing re-quirements due to their limited computing resources.To address the above problems,this paper presents the LEO satellites cooperative task offloading and computing resource allocation(LEOC-TC)algorithm.Firstly,a LEO satellites cooperative task offloading system was designed so that the multispectral LEO satellites in the system could leave their tasks locally or offload them to other LEO satellites with servers for processing,thus providing high-quality information-processing services for multispectral LEO satellites.Secondly,an optimization problem with the objective of minimizing the weighted sum of the total task pro-cessing delay and total energy consumed for multi-spectral LEO satellite is established,and the optimiza-tion problem is split into an offloading ratio subprob-lem and a computing resource subproblem.Finally,Bernoulli mapping tuna swarm optimization algorithm is used to solve the above two sub-problems separately in order to satisfy the demand of low delay and low energy consumed by the system.Simulation results show that the total task processing cost of the LEOCTC algorithm can be reduced by 63.32%,66.67%,and 80.72%compared to the random offloading ratio algorithm,the average resource offloading algorithm,and the local computing algorithm,respectively.展开更多
With the development of vehicle networks and the construction of roadside units,Vehicular Ad Hoc Networks(VANETs)are increasingly promoting cooperative computing patterns among vehicles.Vehicular edge computing(VEC)of...With the development of vehicle networks and the construction of roadside units,Vehicular Ad Hoc Networks(VANETs)are increasingly promoting cooperative computing patterns among vehicles.Vehicular edge computing(VEC)offers an effective solution to mitigate resource constraints by enabling task offloading to edge cloud infrastructure,thereby reducing the computational burden on connected vehicles.However,this sharing-based and distributed computing paradigm necessitates ensuring the credibility and reliability of various computation nodes.Existing vehicular edge computing platforms have not adequately considered themisbehavior of vehicles.We propose a practical task offloading algorithm based on reputation assessment to address the task offloading problem in vehicular edge computing under an unreliable environment.This approach integrates deep reinforcement learning and reputation management to address task offloading challenges.Simulation experiments conducted using Veins demonstrate the feasibility and effectiveness of the proposed method.展开更多
The Multi-access Edge Cloud(MEC) networks extend cloud computing services and capabilities to the edge of the networks. By bringing computation and storage capabilities closer to end-users and connected devices, MEC n...The Multi-access Edge Cloud(MEC) networks extend cloud computing services and capabilities to the edge of the networks. By bringing computation and storage capabilities closer to end-users and connected devices, MEC networks can support a wide range of applications. MEC networks can also leverage various types of resources, including computation resources, network resources, radio resources,and location-based resources, to provide multidimensional resources for intelligent applications in 5/6G.However, tasks generated by users often consist of multiple subtasks that require different types of resources. It is a challenging problem to offload multiresource task requests to the edge cloud aiming at maximizing benefits due to the heterogeneity of resources provided by devices. To address this issue,we mathematically model the task requests with multiple subtasks. Then, the problem of task offloading of multi-resource task requests is proved to be NP-hard. Furthermore, we propose a novel Dual-Agent Deep Reinforcement Learning algorithm with Node First and Link features(NF_L_DA_DRL) based on the policy network, to optimize the benefits generated by offloading multi-resource task requests in MEC networks. Finally, simulation results show that the proposed algorithm can effectively improve the benefit of task offloading with higher resource utilization compared with baseline algorithms.展开更多
Capable of flexibly supporting diverse applications and providing computation services,the Mobile Edge Computing(MEC)-assisted Unmanned Aerial Vehicle(UAV)network is emerging as an innovational paradigm.In this paradi...Capable of flexibly supporting diverse applications and providing computation services,the Mobile Edge Computing(MEC)-assisted Unmanned Aerial Vehicle(UAV)network is emerging as an innovational paradigm.In this paradigm,the heterogeneous resources of the network,including computing and communication resources,should be allocated properly to reduce computation and communication latency as well as energy consumption.However,most existing works solely focus on the optimization issues with global information,which is generally difficult to obtain in real-world scenarios.In this paper,fully considering the incomplete information resulting from diverse types of tasks,we study the joint task offloading and spectrum allocation problem in UAV network,where free UAV nodes serve as helpers for cooperative computation.The objective is to jointly optimize offloading mode,collaboration pairing,and channel allocation to minimize the weighted network cost.To achieve the purpose with only partial observation,an extensive-form game is introduced to reformulate the problem,and a regret learning-based scheme is proposed to achieve the equilibrium solution.With retrospective improvement property and information set concept,the designed algorithm is capable of combating incomplete information and obtaining more precise allocation patterns for diverse tasks.Numerical results show that our proposed algorithm outperforms the benchmarks across various settings.展开更多
With the advancement of technology and the continuous innovation of applications, low-latency applications such as drones, online games and virtual reality are gradually becoming popular demands in modern society. How...With the advancement of technology and the continuous innovation of applications, low-latency applications such as drones, online games and virtual reality are gradually becoming popular demands in modern society. However, these applications pose a great challenge to the traditional centralized mobile cloud computing paradigm, and it is obvious that the traditional cloud computing model is already struggling to meet such demands. To address the shortcomings of cloud computing, mobile edge computing has emerged. Mobile edge computing provides users with computing and storage resources by offloading computing tasks to servers at the edge of the network. However, most existing work only considers single-objective performance optimization in terms of latency or energy consumption, but not balanced optimization in terms of latency and energy consumption. To reduce task latency and device energy consumption, the problem of joint optimization of computation offloading and resource allocation in multi-cell, multi-user, multi-server MEC environments is investigated. In this paper, a dynamic computation offloading algorithm based on Multi-Agent Deep Deterministic Policy Gradient (MADDPG) is proposed to obtain the optimal policy. The experimental results show that the algorithm proposed in this paper reduces the delay by 5 ms compared to PPO, 1.5 ms compared to DDPG and 10.7 ms compared to DQN, and reduces the energy consumption by 300 compared to PPO, 760 compared to DDPG and 380 compared to DQN. This fully proves that the algorithm proposed in this paper has excellent performance.展开更多
This research is the first application of Unmanned Aerial Vehicles(UAVs)equipped with Multi-access Edge Computing(MEC)servers to offshore wind farms,providing a new task offloading solution to address the challenge of...This research is the first application of Unmanned Aerial Vehicles(UAVs)equipped with Multi-access Edge Computing(MEC)servers to offshore wind farms,providing a new task offloading solution to address the challenge of scarce edge servers in offshore wind farms.The proposed strategy is to offload the computational tasks in this scenario to other MEC servers and compute them proportionally,which effectively reduces the computational pressure on local MEC servers when wind turbine data are abnormal.Finally,the task offloading problem is modeled as a multi-intelligent deep reinforcement learning problem,and a task offloading model based on MultiAgent Deep Reinforcement Learning(MADRL)is established.The Adaptive Genetic Algorithm(AGA)is used to explore the action space of the Deep Deterministic Policy Gradient(DDPG),which effectively solves the problem of slow convergence of the DDPG algorithm in the high-dimensional action space.The simulation results show that the proposed algorithm,AGA-DDPG,saves approximately 61.8%,55%,21%,and 33%of the overall overhead compared to local MEC,random offloading,TD3,and DDPG,respectively.The proposed strategy is potentially important for improving real-time monitoring,big data analysis,and predictive maintenance of offshore wind farm operation and maintenance systems.展开更多
In recent years,task offloading and its scheduling optimization have emerged as widely discussed and signif-icant topics.The multi-objective optimization problems inherent in this domain,particularly those related to ...In recent years,task offloading and its scheduling optimization have emerged as widely discussed and signif-icant topics.The multi-objective optimization problems inherent in this domain,particularly those related to resource allocation,have been extensively investigated.However,existing studies predominantly focus on matching suitable computational resources for task offloading requests,often overlooking the optimization of the task data transmission process.This inefficiency in data transmission leads to delays in the arrival of task data at computational nodes within the edge network,resulting in increased service times due to elevated network transmission latencies and idle computational resources.To address this gap,we propose an Asynchronous Data Transmission Policy(ADTP)for optimizing data transmission for task offloading in edge-computing enabled ultra-dense IoT.ADTP dynamically generates data transmission scheduling strategies by jointly considering task offloading decisions and the fluctuating operational states of edge computing-enabled IoT networks.In contrast to existing methods,the Deep Deterministic Policy Gradient(DDPG)based task data transmission scheduling module works asynchronously with the Deep Q-Network(DQN)based Virtual Machine(VM)selection module in ADTP.This significantly reduces the computational space required for the scheduling algorithm.The continuous dynamic adjustment of data transmission bandwidth ensures timely delivery of task data and optimal utilization of network bandwidth resources.This reduces the task completion time and minimizes the failure rate caused by timeouts.Moreover,the VM selection module only performs the next inference step when a new task arrives or when a task finishes its computation.As a result,the wastage of computational resources is further reduced.The simulation results indicate that the proposed ADTP reduced average data transmission delay and service time by 7.11%and 8.09%,respectively.Furthermore,the task failure rate due to network congestion decreased by 68.73%.展开更多
Vehicular edge computing(VEC)is emerging as a promising solution paradigm to meet the requirements of compute-intensive applications in internet of vehicle(IoV).Non-orthogonal multiple access(NOMA)has advantages in im...Vehicular edge computing(VEC)is emerging as a promising solution paradigm to meet the requirements of compute-intensive applications in internet of vehicle(IoV).Non-orthogonal multiple access(NOMA)has advantages in improving spectrum efficiency and dealing with bandwidth scarcity and cost.It is an encouraging progress combining VEC and NOMA.In this paper,we jointly optimize task offloading decision and resource allocation to maximize the service utility of the NOMA-VEC system.To solve the optimization problem,we propose a multiagent deep graph reinforcement learning algorithm.The algorithm extracts the topological features and relationship information between agents from the system state as observations,outputs task offloading decision and resource allocation simultaneously with local policy network,which is updated by a local learner.Simulation results demonstrate that the proposed method achieves a 1.52%∼5.80%improvement compared with the benchmark algorithms in system service utility.展开更多
The rapid development of Internet of Things(IoT)technology has led to a significant increase in the computational task load of Terminal Devices(TDs).TDs reduce response latency and energy consumption with the support ...The rapid development of Internet of Things(IoT)technology has led to a significant increase in the computational task load of Terminal Devices(TDs).TDs reduce response latency and energy consumption with the support of task-offloading in Multi-access Edge Computing(MEC).However,existing task-offloading optimization methods typically assume that MEC’s computing resources are unlimited,and there is a lack of research on the optimization of task-offloading when MEC resources are exhausted.In addition,existing solutions only decide whether to accept the offloaded task request based on the single decision result of the current time slot,but lack support for multiple retry in subsequent time slots.It is resulting in TD missing potential offloading opportunities in the future.To fill this gap,we propose a Two-Stage Offloading Decision-making Framework(TSODF)with request holding and dynamic eviction.Long Short-Term Memory(LSTM)-based task-offloading request prediction and MEC resource release estimation are integrated to infer the probability of a request being accepted in the subsequent time slot.The framework learns optimized decision-making experiences continuously to increase the success rate of task offloading based on deep learning technology.Simulation results show that TSODF reduces total TD’s energy consumption and delay for task execution and improves task offloading rate and system resource utilization compared to the benchmark method.展开更多
In a network environment composed of different types of computing centers that can be divided into different layers(clod,edge layer,and others),the interconnection between them offers the possibility of peer-to-peer t...In a network environment composed of different types of computing centers that can be divided into different layers(clod,edge layer,and others),the interconnection between them offers the possibility of peer-to-peer task offloading.For many resource-constrained devices,the computation of many types of tasks is not feasible because they cannot support such computations as they do not have enough available memory and processing capacity.In this scenario,it is worth considering transferring these tasks to resource-rich platforms,such as Edge Data Centers or remote cloud servers.For different reasons,it is more exciting and appropriate to download various tasks to specific download destinations depending on the properties and state of the environment and the nature of the functions.At the same time,establishing an optimal offloading policy,which ensures that all tasks are executed within the required latency and avoids excessive workload on specific computing centers is not easy.This study presents two alternatives to solve the offloading decision paradigm by introducing two well-known algorithms,Graph Neural Networks(GNN)and Deep Q-Network(DQN).It applies the alternatives on a well-known Edge Computing simulator called PureEdgeSimand compares them with the two defaultmethods,Trade-Off and Round Robin.Experiments showed that variants offer a slight improvement in task success rate and workload distribution.In terms of energy efficiency,they provided similar results.Finally,the success rates of different computing centers are tested,and the lack of capacity of remote cloud servers to respond to applications in real-time is demonstrated.These novel ways of finding a download strategy in a local networking environment are unique as they emulate the state and structure of the environment innovatively,considering the quality of its connections and constant updates.The download score defined in this research is a crucial feature for determining the quality of a download path in the GNN training process and has not previously been proposed.Simultaneously,the suitability of Reinforcement Learning(RL)techniques is demonstrated due to the dynamism of the network environment,considering all the key factors that affect the decision to offload a given task,including the actual state of all devices.展开更多
With the growth of maritime activities,the number of computationally complex applications is growing exponentially.Mobile edge computing(MEC)is widely recognized as a viable option to address the substantial need for ...With the growth of maritime activities,the number of computationally complex applications is growing exponentially.Mobile edge computing(MEC)is widely recognized as a viable option to address the substantial need for wireless communications and compute-intensive operations in maritime environments.To reduce the processing load and meet the demands of mobile terminals for high bandwidth,low latency and multiple access,MEC systems with unmanned aerial vehicles(UAVs)have been proposed and extensively explored.In this paper,a maritime MEC network that employs a top-UAV(T-UAV)for task offloading supported by digital twin(DT)is considered.To explore the task offloading strategy employed by the edge server,the flight trajectory and resource allocation strategy of the T-UAV is studied in detail.The objective of this study is to minimize latency costs while ensuring that the energy of the T-UAV is sufficient to fulfill services.In order to accomplish this objective,the joint optimization problem is described as a Markov decision process(MDP).To overcome this problem,the priority-based reinforcement learning(RL)algorithm for computation offloading and trajectory planning(PRL-COTP)is developed.The simulation results demonstrate that the proposed approach can significantlyreduce the overall cost of the system in comparison to other benchmarks.展开更多
In this paper,the problem of computation offloading in the edge server is studied in a mobile edge computation(MEC)-enabled cell networks that consists of a base station(BS)integrating edge servers,several terminal de...In this paper,the problem of computation offloading in the edge server is studied in a mobile edge computation(MEC)-enabled cell networks that consists of a base station(BS)integrating edge servers,several terminal devices and collaborators.In the considered networks,we develop an intelligent task offloading and collaborative computation scheme to achieve the optimal computation offloading.First,a distance-based collaborator screening method is proposed to get collaborators within the distance threshold and with high power.Second,based on the Lyapunov stochastic optimization theory,the system stability problem is transformed into a queue stability issue,and the optimal computation offloading is obtained by solving these three sub-problems:task allocation control,task execution control and queue update,respectively.Moreover,rigorous experimental simulation shows that our proposed computation offloading algorithm can achieve the joint optimization among the system efficiency,energy consumption and time delay compared to the mobility-aware and migration-enabled approach,Full BS and Full local.展开更多
Unmanned Aerial Vehicle(UAV)has emerged as a promising technology for the support of human activities,such as target tracking,disaster rescue,and surveillance.However,these tasks require a large computation load of im...Unmanned Aerial Vehicle(UAV)has emerged as a promising technology for the support of human activities,such as target tracking,disaster rescue,and surveillance.However,these tasks require a large computation load of image or video processing,which imposes enormous pressure on the UAV computation platform.To solve this issue,in this work,we propose an intelligent Task Offloading Algorithm(iTOA)for UAV edge computing network.Compared with existing methods,iTOA is able to perceive the network’s environment intelligently to decide the offloading action based on deep Monte Calor Tree Search(MCTS),the core algorithm of Alpha Go.MCTS will simulate the offloading decision trajectories to acquire the best decision by maximizing the reward,such as lowest latency or power consumption.To accelerate the search convergence of MCTS,we also proposed a splitting Deep Neural Network(sDNN)to supply the prior probability for MCTS.The sDNN is trained by a self-supervised learning manager.Here,the training data set is obtained from iTOA itself as its own teacher.Compared with game theory and greedy search-based methods,the proposed iTOA improves service latency performance by 33%and 60%,respectively.展开更多
基金funded by the Fundamental Research Funds for the Central Universities(J2023-024,J2023-027).
文摘As an important complement to cloud computing, edge computing can effectively reduce the workload of the backbone network. To reduce latency and energy consumption of edge computing, deep learning is used to learn the task offloading strategies by interacting with the entities. In actual application scenarios, users of edge computing are always changing dynamically. However, the existing task offloading strategies cannot be applied to such dynamic scenarios. To solve this problem, we propose a novel dynamic task offloading framework for distributed edge computing, leveraging the potential of meta-reinforcement learning (MRL). Our approach formulates a multi-objective optimization problem aimed at minimizing both delay and energy consumption. We model the task offloading strategy using a directed acyclic graph (DAG). Furthermore, we propose a distributed edge computing adaptive task offloading algorithm rooted in MRL. This algorithm integrates multiple Markov decision processes (MDP) with a sequence-to-sequence (seq2seq) network, enabling it to learn and adapt task offloading strategies responsively across diverse network environments. To achieve joint optimization of delay and energy consumption, we incorporate the non-dominated sorting genetic algorithm II (NSGA-II) into our framework. Simulation results demonstrate the superiority of our proposed solution, achieving a 21% reduction in time delay and a 19% decrease in energy consumption compared to alternative task offloading schemes. Moreover, our scheme exhibits remarkable adaptability, responding swiftly to changes in various network environments.
基金funded by the National Key Research and Development Program of China under Grant 2019YFB1803301Beijing Natural Science Foundation (L202002)。
文摘Cybertwin-enabled 6th Generation(6G)network is envisioned to support artificial intelligence-native management to meet changing demands of 6G applications.Multi-Agent Deep Reinforcement Learning(MADRL)technologies driven by Cybertwins have been proposed for adaptive task offloading strategies.However,the existence of random transmission delay between Cybertwin-driven agents and underlying networks is not considered in related works,which destroys the standard Markov property and increases the decision reaction time to reduce the task offloading strategy performance.In order to address this problem,we propose a pipelining task offloading method to lower the decision reaction time and model it as a delay-aware Markov Decision Process(MDP).Then,we design a delay-aware MADRL algorithm to minimize the weighted sum of task execution latency and energy consumption.Firstly,the state space is augmented using the lastly-received state and historical actions to rebuild the Markov property.Secondly,Gate Transformer-XL is introduced to capture historical actions'importance and maintain the consistent input dimension dynamically changed due to random transmission delays.Thirdly,a sampling method and a new loss function with the difference between the current and target state value and the difference between real state-action value and augmented state-action value are designed to obtain state transition trajectories close to the real ones.Numerical results demonstrate that the proposed methods are effective in reducing reaction time and improving the task offloading performance in the random-delay Cybertwin-enabled 6G networks.
基金supported in part by the National Science Foundation of China(Grant No.62172450)the Key R&D Plan of Hunan Province(Grant No.2022GK2008)the Nature Science Foundation of Hunan Province(Grant No.2020JJ4756)。
文摘In task offloading,the movement of vehicles causes the switching of connected RSUs and servers,which may lead to task offloading failure or high service delay.In this paper,we analyze the impact of vehicle movements on task offloading and reveal that data preparation time for task execution can be minimized via forward-looking scheduling.Then,a Bi-LSTM-based model is proposed to predict the trajectories of vehicles.The service area is divided into several equal-sized grids.If the actual position of the vehicle and the predicted position by the model belong to the same grid,the prediction is considered correct,thereby reducing the difficulty of vehicle trajectory prediction.Moreover,we propose a scheduling strategy for delay optimization based on the vehicle trajectory prediction.Considering the inevitable prediction error,we take some edge servers around the predicted area as candidate execution servers and the data required for task execution are backed up to these candidate servers,thereby reducing the impact of prediction deviations on task offloading and converting the modest increase of resource overheads into delay reduction in task offloading.Simulation results show that,compared with other classical schemes,the proposed strategy has lower average task offloading delays.
基金supported by the National Natural Science Foundation of China(Grant No.62103349)the Henan Province Science and Technology Research Project(Grant No.232102210104).
文摘Edge computing has transformed smart grids by lowering latency,reducing network congestion,and enabling real-time decision-making.Nevertheless,devising an optimal task-offloading strategy remains challenging,as it must jointly minimise energy consumption and response time under fluctuating workloads and volatile network conditions.We cast the offloading problem as aMarkov Decision Process(MDP)and solve it with Deep Reinforcement Learning(DRL).Specifically,we present a three-tier architecture—end devices,edge nodes,and a cloud server—and enhance Proximal Policy Optimization(PPO)to learn adaptive,energy-aware policies.A Convolutional Neural Network(CNN)extracts high-level features from system states,enabling the agent to respond continually to changing conditions.Extensive simulations show that the proposed method reduces task latency and energy consumption far more than several baseline algorithms,thereby improving overall system performance.These results demonstrate the effectiveness and robustness of the framework for real-time task offloading in dynamic smart-grid environments.
基金supported and funded by theDeanship of Scientific Research at Imam Mohammad Ibn Saud Islamic University(IMSIU)(grant number IMSIU-RP23082).
文摘Fog computing is a key enabling technology of 6G systems as it provides quick and reliable computing,and data storage services which are required for several 6G applications.Artificial Intelligence(AI)algorithms will be an integral part of 6G systems and efficient task offloading techniques using fog computing will improve their performance and reliability.In this paper,the focus is on the scenario of Partial Offloading of a Task to Multiple Helpers(POMH)in which larger tasks are divided into smaller subtasks and processed in parallel,hence expediting task completion.However,using POMH presents challenges such as breaking tasks into subtasks and scaling these subtasks based on many interdependent factors to ensure that all subtasks of a task finish simultaneously,preventing resource wastage.Additionally,applying matching theory to POMH scenarios results in dynamic preference profiles of helping devices due to changing subtask sizes,resulting in a difficult-to-solve,externalities problem.This paper introduces a novel many-to-one matching-based algorithm,designed to address the externalities problem and optimize resource allocation within POMH scenarios.Additionally,we propose a new time-efficient preference profiling technique that further enhances time optimization in POMH scenarios.The performance of the proposed technique is thoroughly evaluated in comparison to alternate baseline schemes,revealing many advantages of the proposed approach.The simulation findings indisputably show that the proposed matching-based offloading technique outperforms existing methodologies in the literature,yielding a remarkable 52 reduction in task latency,particularly under high workloads.
基金supported by the Project of Science and Technology Research Program of Chongqing Education Commission of China(No.KJZD-K202401105)High-Quality Development Action Plan for Graduate Education at Chongqing University of Technology(No.gzljg2023308,No.gzljd2024204)+1 种基金the Graduate Innovation Program of Chongqing University of Technology(No.gzlcx20233197)Yunnan Provincial Key R&D Program(202203AA080006).
文摘Blockchain technology,based on decentralized data storage and distributed consensus design,has become a promising solution to address data security risks and provide privacy protection in the Internet-of-Things(IoT)due to its tamper-proof and non-repudiation features.Although blockchain typically does not require the endorsement of third-party trust organizations,it mostly needs to perform necessary mathematical calculations to prevent malicious attacks,which results in stricter requirements for computation resources on the participating devices.By offloading the computation tasks required to support blockchain consensus to edge service nodes or the cloud,while providing data privacy protection for IoT applications,it can effectively address the limitations of computation and energy resources in IoT devices.However,how to make reasonable offloading decisions for IoT devices remains an open issue.Due to the excellent self-learning ability of Reinforcement Learning(RL),this paper proposes a RL enabled Swarm Intelligence Optimization Algorithm(RLSIOA)that aims to improve the quality of initial solutions and achieve efficient optimization of computation task offloading decisions.The algorithm considers various factors that may affect the revenue obtained by IoT devices executing consensus algorithms(e.g.,Proof-of-Work),it optimizes the proportion of sub-tasks to be offloaded and the scale of computing resources to be rented from the edge and cloud to maximize the revenue of devices.Experimental results show that RLSIOA can obtain higher-quality offloading decision-making schemes at lower latency costs compared to representative benchmark algorithms.
基金supported by the Gansu Province Key Research and Development Plan(No.23YFGA0062)Gansu Provin-cial Innovation Fund(No.2022A-215).
文摘With the rapid growth of connected devices,traditional edge-cloud systems are under overload pressure.Using mobile edge computing(MEC)to assist unmanned aerial vehicles(UAVs)as low altitude platform stations(LAPS)for communication and computation to build air-ground integrated networks(AGINs)offers a promising solution for seamless network coverage of remote internet of things(IoT)devices in the future.To address the performance demands of future mobile devices(MDs),we proposed an MEC-assisted AGIN system.The goal is to minimize the long-term computational overhead of MDs by jointly optimizing transmission power,flight trajecto-ries,resource allocation,and offloading ratios,while utilizing non-orthogonal multiple access(NOMA)to improve device connectivity of large-scale MDs and spectral efficiency.We first designed an adaptive clustering scheme based on K-Means to cluster MDs and established commu-nication links,improving efficiency and load balancing.Then,considering system dynamics,we introduced a partial computation offloading algorithm based on multi-agent deep deterministic pol-icy gradient(MADDPG),modeling the multi-UAV computation offloading problem as a Markov decision process(MDP).This algorithm optimizes resource allocation through centralized training and distributed execution,reducing computational overhead.Simulation results show that the pro-posed algorithm not only converges stably but also outperforms other benchmark algorithms in han-dling complex scenarios with multiple devices.
基金supported in part by Sub Project of National Key Research and Development plan in 2020(No.2020YFC1511704)scientific research level improvement project to promote the colleges connotation development of Beijing Information Science&Technology University(No.2020KYNH212,No.2021CGZH302)in part by the National Natural Science Foundation of China(Grant No.61971048).
文摘Multispectral low earth orbit(LEO)satel-lites are characterized by a large volume of captured data and high spatial resolution,which can provide rich image information and data support for a vari-ety of fields,but it is difficult for them to satisfy low-delay and low-energy consumed task processing re-quirements due to their limited computing resources.To address the above problems,this paper presents the LEO satellites cooperative task offloading and computing resource allocation(LEOC-TC)algorithm.Firstly,a LEO satellites cooperative task offloading system was designed so that the multispectral LEO satellites in the system could leave their tasks locally or offload them to other LEO satellites with servers for processing,thus providing high-quality information-processing services for multispectral LEO satellites.Secondly,an optimization problem with the objective of minimizing the weighted sum of the total task pro-cessing delay and total energy consumed for multi-spectral LEO satellite is established,and the optimiza-tion problem is split into an offloading ratio subprob-lem and a computing resource subproblem.Finally,Bernoulli mapping tuna swarm optimization algorithm is used to solve the above two sub-problems separately in order to satisfy the demand of low delay and low energy consumed by the system.Simulation results show that the total task processing cost of the LEOCTC algorithm can be reduced by 63.32%,66.67%,and 80.72%compared to the random offloading ratio algorithm,the average resource offloading algorithm,and the local computing algorithm,respectively.
基金supported by the Open Foundation of Henan Key Laboratory of Cyberspace Situation Awareness(No.HNTS2022020)the Science and Technology Research Program of Henan Province of China(232102210134,182102210130)Key Research Projects of Henan Provincial Universities(25B520005).
文摘With the development of vehicle networks and the construction of roadside units,Vehicular Ad Hoc Networks(VANETs)are increasingly promoting cooperative computing patterns among vehicles.Vehicular edge computing(VEC)offers an effective solution to mitigate resource constraints by enabling task offloading to edge cloud infrastructure,thereby reducing the computational burden on connected vehicles.However,this sharing-based and distributed computing paradigm necessitates ensuring the credibility and reliability of various computation nodes.Existing vehicular edge computing platforms have not adequately considered themisbehavior of vehicles.We propose a practical task offloading algorithm based on reputation assessment to address the task offloading problem in vehicular edge computing under an unreliable environment.This approach integrates deep reinforcement learning and reputation management to address task offloading challenges.Simulation experiments conducted using Veins demonstrate the feasibility and effectiveness of the proposed method.
基金supported in part by the National Natural Science Foundation of China under Grants 62201105,62331017,and 62075024in part by the Natural Science Foundation of Chongqing under Grant cstc2021jcyj-msxmX0404+1 种基金in part by the Chongqing Municipal Education Commission under Grant KJQN202100643in part by Guangdong Basic and Applied Basic Research Foundation under Grant 2022A1515110056.
文摘The Multi-access Edge Cloud(MEC) networks extend cloud computing services and capabilities to the edge of the networks. By bringing computation and storage capabilities closer to end-users and connected devices, MEC networks can support a wide range of applications. MEC networks can also leverage various types of resources, including computation resources, network resources, radio resources,and location-based resources, to provide multidimensional resources for intelligent applications in 5/6G.However, tasks generated by users often consist of multiple subtasks that require different types of resources. It is a challenging problem to offload multiresource task requests to the edge cloud aiming at maximizing benefits due to the heterogeneity of resources provided by devices. To address this issue,we mathematically model the task requests with multiple subtasks. Then, the problem of task offloading of multi-resource task requests is proved to be NP-hard. Furthermore, we propose a novel Dual-Agent Deep Reinforcement Learning algorithm with Node First and Link features(NF_L_DA_DRL) based on the policy network, to optimize the benefits generated by offloading multi-resource task requests in MEC networks. Finally, simulation results show that the proposed algorithm can effectively improve the benefit of task offloading with higher resource utilization compared with baseline algorithms.
基金supported by the Natural Science Foundation of China(NSFC)under Grant 62101051the Guangdong Key Laboratory of Intelligent Information ProcessingShenzhen Key Laboratory of Media Security,Shenzhen 518060,China。
文摘Capable of flexibly supporting diverse applications and providing computation services,the Mobile Edge Computing(MEC)-assisted Unmanned Aerial Vehicle(UAV)network is emerging as an innovational paradigm.In this paradigm,the heterogeneous resources of the network,including computing and communication resources,should be allocated properly to reduce computation and communication latency as well as energy consumption.However,most existing works solely focus on the optimization issues with global information,which is generally difficult to obtain in real-world scenarios.In this paper,fully considering the incomplete information resulting from diverse types of tasks,we study the joint task offloading and spectrum allocation problem in UAV network,where free UAV nodes serve as helpers for cooperative computation.The objective is to jointly optimize offloading mode,collaboration pairing,and channel allocation to minimize the weighted network cost.To achieve the purpose with only partial observation,an extensive-form game is introduced to reformulate the problem,and a regret learning-based scheme is proposed to achieve the equilibrium solution.With retrospective improvement property and information set concept,the designed algorithm is capable of combating incomplete information and obtaining more precise allocation patterns for diverse tasks.Numerical results show that our proposed algorithm outperforms the benchmarks across various settings.
文摘With the advancement of technology and the continuous innovation of applications, low-latency applications such as drones, online games and virtual reality are gradually becoming popular demands in modern society. However, these applications pose a great challenge to the traditional centralized mobile cloud computing paradigm, and it is obvious that the traditional cloud computing model is already struggling to meet such demands. To address the shortcomings of cloud computing, mobile edge computing has emerged. Mobile edge computing provides users with computing and storage resources by offloading computing tasks to servers at the edge of the network. However, most existing work only considers single-objective performance optimization in terms of latency or energy consumption, but not balanced optimization in terms of latency and energy consumption. To reduce task latency and device energy consumption, the problem of joint optimization of computation offloading and resource allocation in multi-cell, multi-user, multi-server MEC environments is investigated. In this paper, a dynamic computation offloading algorithm based on Multi-Agent Deep Deterministic Policy Gradient (MADDPG) is proposed to obtain the optimal policy. The experimental results show that the algorithm proposed in this paper reduces the delay by 5 ms compared to PPO, 1.5 ms compared to DDPG and 10.7 ms compared to DQN, and reduces the energy consumption by 300 compared to PPO, 760 compared to DDPG and 380 compared to DQN. This fully proves that the algorithm proposed in this paper has excellent performance.
基金supported in part by the National Natural Science Foundation of China under grant 61861007the Guizhou Province Science and Technology Planning Project ZK[2021]303+2 种基金the Guizhou Province Science Technology Support Plan under grant[2022]264,[2023]096,[2023]409 and[2023]412the Science Technology Project of POWERCHINA Guizhou Engineering Co.,Ltd.(DJ-ZDXM-2022-44)the Project of POWERCHINA Guiyang Engineering Corporation Limited(YJ2022-12).
文摘This research is the first application of Unmanned Aerial Vehicles(UAVs)equipped with Multi-access Edge Computing(MEC)servers to offshore wind farms,providing a new task offloading solution to address the challenge of scarce edge servers in offshore wind farms.The proposed strategy is to offload the computational tasks in this scenario to other MEC servers and compute them proportionally,which effectively reduces the computational pressure on local MEC servers when wind turbine data are abnormal.Finally,the task offloading problem is modeled as a multi-intelligent deep reinforcement learning problem,and a task offloading model based on MultiAgent Deep Reinforcement Learning(MADRL)is established.The Adaptive Genetic Algorithm(AGA)is used to explore the action space of the Deep Deterministic Policy Gradient(DDPG),which effectively solves the problem of slow convergence of the DDPG algorithm in the high-dimensional action space.The simulation results show that the proposed algorithm,AGA-DDPG,saves approximately 61.8%,55%,21%,and 33%of the overall overhead compared to local MEC,random offloading,TD3,and DDPG,respectively.The proposed strategy is potentially important for improving real-time monitoring,big data analysis,and predictive maintenance of offshore wind farm operation and maintenance systems.
文摘In recent years,task offloading and its scheduling optimization have emerged as widely discussed and signif-icant topics.The multi-objective optimization problems inherent in this domain,particularly those related to resource allocation,have been extensively investigated.However,existing studies predominantly focus on matching suitable computational resources for task offloading requests,often overlooking the optimization of the task data transmission process.This inefficiency in data transmission leads to delays in the arrival of task data at computational nodes within the edge network,resulting in increased service times due to elevated network transmission latencies and idle computational resources.To address this gap,we propose an Asynchronous Data Transmission Policy(ADTP)for optimizing data transmission for task offloading in edge-computing enabled ultra-dense IoT.ADTP dynamically generates data transmission scheduling strategies by jointly considering task offloading decisions and the fluctuating operational states of edge computing-enabled IoT networks.In contrast to existing methods,the Deep Deterministic Policy Gradient(DDPG)based task data transmission scheduling module works asynchronously with the Deep Q-Network(DQN)based Virtual Machine(VM)selection module in ADTP.This significantly reduces the computational space required for the scheduling algorithm.The continuous dynamic adjustment of data transmission bandwidth ensures timely delivery of task data and optimal utilization of network bandwidth resources.This reduces the task completion time and minimizes the failure rate caused by timeouts.Moreover,the VM selection module only performs the next inference step when a new task arrives or when a task finishes its computation.As a result,the wastage of computational resources is further reduced.The simulation results indicate that the proposed ADTP reduced average data transmission delay and service time by 7.11%and 8.09%,respectively.Furthermore,the task failure rate due to network congestion decreased by 68.73%.
基金supported by the Talent Fund of Beijing Jiaotong University(No.2023XKRC028)CCFLenovo Blue Ocean Research Fund and Beijing Natural Science Foundation under Grant(No.L221003).
文摘Vehicular edge computing(VEC)is emerging as a promising solution paradigm to meet the requirements of compute-intensive applications in internet of vehicle(IoV).Non-orthogonal multiple access(NOMA)has advantages in improving spectrum efficiency and dealing with bandwidth scarcity and cost.It is an encouraging progress combining VEC and NOMA.In this paper,we jointly optimize task offloading decision and resource allocation to maximize the service utility of the NOMA-VEC system.To solve the optimization problem,we propose a multiagent deep graph reinforcement learning algorithm.The algorithm extracts the topological features and relationship information between agents from the system state as observations,outputs task offloading decision and resource allocation simultaneously with local policy network,which is updated by a local learner.Simulation results demonstrate that the proposed method achieves a 1.52%∼5.80%improvement compared with the benchmark algorithms in system service utility.
文摘The rapid development of Internet of Things(IoT)technology has led to a significant increase in the computational task load of Terminal Devices(TDs).TDs reduce response latency and energy consumption with the support of task-offloading in Multi-access Edge Computing(MEC).However,existing task-offloading optimization methods typically assume that MEC’s computing resources are unlimited,and there is a lack of research on the optimization of task-offloading when MEC resources are exhausted.In addition,existing solutions only decide whether to accept the offloaded task request based on the single decision result of the current time slot,but lack support for multiple retry in subsequent time slots.It is resulting in TD missing potential offloading opportunities in the future.To fill this gap,we propose a Two-Stage Offloading Decision-making Framework(TSODF)with request holding and dynamic eviction.Long Short-Term Memory(LSTM)-based task-offloading request prediction and MEC resource release estimation are integrated to infer the probability of a request being accepted in the subsequent time slot.The framework learns optimized decision-making experiences continuously to increase the success rate of task offloading based on deep learning technology.Simulation results show that TSODF reduces total TD’s energy consumption and delay for task execution and improves task offloading rate and system resource utilization compared to the benchmark method.
基金funding from TECNALIA,Basque Research and Technology Alliance(BRTA)supported by the project aOptimization of Deep Learning algorithms for Edge IoT devices for sensorization and control in Buildings and Infrastructures(EMBED)funded by the Gipuzkoa Provincial Council and approved under the 2023 call of the Guipuzcoan Network of Science,Technology and Innovation Program with File Number 2023-CIEN-000051-01.
文摘In a network environment composed of different types of computing centers that can be divided into different layers(clod,edge layer,and others),the interconnection between them offers the possibility of peer-to-peer task offloading.For many resource-constrained devices,the computation of many types of tasks is not feasible because they cannot support such computations as they do not have enough available memory and processing capacity.In this scenario,it is worth considering transferring these tasks to resource-rich platforms,such as Edge Data Centers or remote cloud servers.For different reasons,it is more exciting and appropriate to download various tasks to specific download destinations depending on the properties and state of the environment and the nature of the functions.At the same time,establishing an optimal offloading policy,which ensures that all tasks are executed within the required latency and avoids excessive workload on specific computing centers is not easy.This study presents two alternatives to solve the offloading decision paradigm by introducing two well-known algorithms,Graph Neural Networks(GNN)and Deep Q-Network(DQN).It applies the alternatives on a well-known Edge Computing simulator called PureEdgeSimand compares them with the two defaultmethods,Trade-Off and Round Robin.Experiments showed that variants offer a slight improvement in task success rate and workload distribution.In terms of energy efficiency,they provided similar results.Finally,the success rates of different computing centers are tested,and the lack of capacity of remote cloud servers to respond to applications in real-time is demonstrated.These novel ways of finding a download strategy in a local networking environment are unique as they emulate the state and structure of the environment innovatively,considering the quality of its connections and constant updates.The download score defined in this research is a crucial feature for determining the quality of a download path in the GNN training process and has not previously been proposed.Simultaneously,the suitability of Reinforcement Learning(RL)techniques is demonstrated due to the dynamism of the network environment,considering all the key factors that affect the decision to offload a given task,including the actual state of all devices.
基金Foundation items:National Natural Science Foundation of China(Nos.62301307 and 62072096)Shanghai Pujiang Program,China(No.23PJD041)Chenguang Program of Shanghai Education Development Foundation and Shanghai Municipal Education Commission,China(No.CGA60)。
文摘With the growth of maritime activities,the number of computationally complex applications is growing exponentially.Mobile edge computing(MEC)is widely recognized as a viable option to address the substantial need for wireless communications and compute-intensive operations in maritime environments.To reduce the processing load and meet the demands of mobile terminals for high bandwidth,low latency and multiple access,MEC systems with unmanned aerial vehicles(UAVs)have been proposed and extensively explored.In this paper,a maritime MEC network that employs a top-UAV(T-UAV)for task offloading supported by digital twin(DT)is considered.To explore the task offloading strategy employed by the edge server,the flight trajectory and resource allocation strategy of the T-UAV is studied in detail.The objective of this study is to minimize latency costs while ensuring that the energy of the T-UAV is sufficient to fulfill services.In order to accomplish this objective,the joint optimization problem is described as a Markov decision process(MDP).To overcome this problem,the priority-based reinforcement learning(RL)algorithm for computation offloading and trajectory planning(PRL-COTP)is developed.The simulation results demonstrate that the proposed approach can significantlyreduce the overall cost of the system in comparison to other benchmarks.
基金supported by Qinghai Natural Science Foundation under No.2020-ZJ-943Q.
文摘In this paper,the problem of computation offloading in the edge server is studied in a mobile edge computation(MEC)-enabled cell networks that consists of a base station(BS)integrating edge servers,several terminal devices and collaborators.In the considered networks,we develop an intelligent task offloading and collaborative computation scheme to achieve the optimal computation offloading.First,a distance-based collaborator screening method is proposed to get collaborators within the distance threshold and with high power.Second,based on the Lyapunov stochastic optimization theory,the system stability problem is transformed into a queue stability issue,and the optimal computation offloading is obtained by solving these three sub-problems:task allocation control,task execution control and queue update,respectively.Moreover,rigorous experimental simulation shows that our proposed computation offloading algorithm can achieve the joint optimization among the system efficiency,energy consumption and time delay compared to the mobility-aware and migration-enabled approach,Full BS and Full local.
基金the Artificial Intelligence Key Laboratory of Sichuan Province(Nos.2019RYJ05)National Natural Science Foundation of China(Nos.61971107).
文摘Unmanned Aerial Vehicle(UAV)has emerged as a promising technology for the support of human activities,such as target tracking,disaster rescue,and surveillance.However,these tasks require a large computation load of image or video processing,which imposes enormous pressure on the UAV computation platform.To solve this issue,in this work,we propose an intelligent Task Offloading Algorithm(iTOA)for UAV edge computing network.Compared with existing methods,iTOA is able to perceive the network’s environment intelligently to decide the offloading action based on deep Monte Calor Tree Search(MCTS),the core algorithm of Alpha Go.MCTS will simulate the offloading decision trajectories to acquire the best decision by maximizing the reward,such as lowest latency or power consumption.To accelerate the search convergence of MCTS,we also proposed a splitting Deep Neural Network(sDNN)to supply the prior probability for MCTS.The sDNN is trained by a self-supervised learning manager.Here,the training data set is obtained from iTOA itself as its own teacher.Compared with game theory and greedy search-based methods,the proposed iTOA improves service latency performance by 33%and 60%,respectively.
