关键词： Task analysis   Internet of Things   Autonomous aerial vehicles   Delays   Costs   Resource management   Disasters   Aerial computing   mobile edge computing   deep reinforcement learning   computation offloading  

摘要： The exponential growth of Internet of Things (IoT) devices and emerging applications have significantly increased the requirements for ubiquitous connectivity and efficient computing paradigms. Traditional terrestrial edge computing architectures cannot provide massive IoT connectivity worldwide. In this article, we propose an aerial hierarchical mobile edge computing system composed of high-altitude platforms (HAPs) and unmanned aerial vehicles (UAVs). In particular, we consider non-divisible tasks and formulate a task offloading problem to minimize the long-term processing cost of tasks while satisfying the queueing mechanism in the offloading procedure and processing procedure of tasks. We propose a multi-agent deep reinforcement learning (DRL) based computation offloading algorithm in which each device can make its offloading decision according to local observations. Due to the limited computing resources of UAVs, high task loads of UAVs will increase the ratio of abandoning offloaded tasks. To increase the success ratio of completing tasks, the convolutional LSTM (ConvLSTM) network is utilized to estimate the future task loads of UAVs. In addition, a prioritized experience replay (PER) method is proposed to increase the convergence speed and improve the training stability. The experimental results demonstrate that the proposed computation offloading algorithm outperforms other benchmark methods.

关键词： Task analysis   Servers   Processor scheduling   Resource management   Cloud computing   Schedules   Job shop scheduling   Mobile edge computing   online combinatorial optimization   resource management  

摘要： The paradigm of mobile edge computing (MEC) has emerged as a promising solution to the increasing demand of time-sensitive applications, where tasks generated by users are offloaded to proximate edge clouds for low-latency execution. Due to the online nature of task generation and edge capacity bottleneck, a fundamental challenge for the MEC network is how to optimally schedule the tasks and resources in face of uncertain future arrivals. To this end, we propose a competitive algorithm named EdgeOPT for online parallel task scheduling aiming to maximize the cumulative reward of completed tasks subject to their hard deadlines. The algorithm leverages an adaptive threshold structure at each server to schedule tasks with different demand patterns based on the status of the system and all active users, while incorporating a subroutine for efficient resource allocations. We prove a bounded competitive ratio for EdgeOPT when scheduling monolithic tasks, and propose its extended version to schedule chains of dependent functions. We conduct extensive experiments to demonstrate the effectiveness and superiority of our proposal compared to all the baselines.

关键词： Autonomous aerial vehicles   Task analysis   Computational modeling   Data models   Vehicle dynamics   Training   Heuristic algorithms   Computational offloading   data caching   federated deep reinforcement learning   Internet of Vehicle   mobile edge computing   unmanned aerial vehicles  

摘要： Due to the dense buildings around the macro base stations (MBSes) and the hotspot requests within particular area (e.g., traffic intersections), it is a challenging task for Quality of Service (QoS) guarantee in Internet of Vehicle (IoV). To address these challenges, unmanned aerial vehicles (UAVs) can be integrated into mobile edge computing (MEC) for IoV by leveraging their advantages of mobile flexibility, low price, and line-of-sight (LoS) communication links. In this paper, we establish a joint UAV-assisted IoV scenario, where both UAVs and MBSes can provide computation and data caching services for smart vehicles. Then, we formulate a joint optimization problem for dynamic data caching and computation offloading, aiming to minimize the average task processing delay and maximize the UAV cache hit ratio. By applying deep reinforcement learning (DRL) techniques, we design an intelligent data caching and computation offloading (IDCCO) algorithm to deal with large-scale and continuous state and action spaces. Furthermore, in order to accelerate the convergence speed of DRL model training while protecting the privacy of original user data in IoV, we propose a distributed training mechanism based on Federated Learning (FL), where the DRL model training is performed locally on UAV and global parameter aggregation is performed on MBS. Finally, extensive experiments are conducted, and the experimental results demonstrate the superiority of our approach over several comparative algorithms in shortening the training time, reducing the task processing delay, and maximizing the cache hit ratio.

关键词： Smarter home systems   Federated learning   Mobile edge computing   Blockchain  

摘要： Home appliance manufacturers are increasingly focusing on building smarter home systems by incorporating user feedback to enhance products and services. To support this, we designed a federated learning (FL) system that includes a reputation mechanism to help manufacturers leverage customer data to train machine learning models. First, it downloads the initial model provided by the manufacturer and trains it with local data. Then, it asks customers to sign their models and upload them to the blockchain. To protect customer privacy, we implemented differential privacy and introduced a new normalization technique. In addition, we also attract more customers to participate in crowdsourced FL tasks by rewarding their contributions, thereby ensuring that the datasets for model training are robust and diverse. This system not only promotes collaboration between customers and manufacturers, but also facilitates the development of more responsive and smarter home appliance systems through advanced FL and blockchain technologies.

关键词： Performance evaluation   Edge computing   Optimization   Dynamic scheduling   Costs   Servers   Collaboration   Internet of Things   Device-to-device communication   Delays   Edge resource probing   mobile edge computing   optimal stopping   online learning   UCB  

摘要： To meet the stringent requirement of edge intelligence applications, resource-constrained devices can offload their task to nearby resource-rich devices. Resource awareness, as a prime prerequisite for offloading decision-making, is critical for achieving efficient collaborative computation performance. Although major works have explored computation offloading in dynamic edge environments, the impact of fresh resource information perception has not been formally investigated. To bridge the gap, we design a cost-aware edge resource probing (CERP) framework for infrastructure-free edge computing, where a task device self-organizes its resource probing to enable informed computation offloading. We first formulate the joint optimization of device probing and offloading as a multi-stage optimal stopping problem and derive a multi-threshold-based optimal strategy with theoretical guarantees. Accordingly, we devise a data-driven layered learning mechanism to handle more complex real-world scenarios. The layered learning enables the task device to adaptively learn the optimal probing sequence and decision thresholds on the fly, aiming to strike a good balance between the gain of choosing the best edge device and the accumulated cost of deep resource probing. To further boost its learning efficiency, we replace the $\epsilon$epsilon-greedy method with a tailored UCB-based adaptive exploration scheme in layered learning, thus better navigating the exploration and exploitation trade-off during probing processes. Finally, we conduct a thorough performance evaluation of the proposed CERP schemes using both extensive numerical simulations and realistic system prototype implementation, which demonstrate the superior performance of CERP in diverse application scenarios.

关键词： Autonomous aerial vehicles   Energy consumption   Task analysis   Resource management   Consumer electronics   Servers   Batteries   Mobile edge computing   computation offloading   resource allocation   trajectory optimization   deep reinforcement learning  

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.

关键词： Task analysis   Eavesdropping   Energy consumption   Autonomous aerial vehicles   Servers   Resource management   Resists   Unmanned aerial vehicle   mobile edge computing   active aerial eavesdropping   collaborative communication and computation   deep reinforcement learning  

摘要： Unmanned aerial vehicle (UAV)-enabled mobile edge computing (MEC) can provide flexible computing service for terminal-devices (TDs). However, malicious active aerial eavesdroppers can perform air-to-ground eavesdropping and air-to-air attacking, which makes TDs' tasks offloading computation more vulnerable, posing significantly secure threats to UAV-enabled MEC. To overcome this challenge, we aim to design collaborative communication and computation schemes for the secure UAV-enabled MEC system, where an active aerial eavesdropper is capable of wiretapping the tasks information offloaded from TDs and transmitting attack signals to the legitimate network. The total weighted energy consumption of the system is minimized via optimizing time allocation, transmit power, local and offloading computation bits, as well as UAV trajectory. First, considering the given number of computational tasks of TDs, a block coordinate descent (BCD)-based scheme is proposed to decompose the original multi-variables-coupling and close-form-lacking problem into several tractable subproblems that can be addressed by iterations. Next, considering that there are dynamic and random tasks arriving to TDs' original tasks, a deep reinforcement learning (DRL)-based scheme is proposed to maintain the stability of tasks, where the solution of computation, communication and trajectory optimization is intelligently obtained by adopting double-deep Q-learning (DDQN). Simulation results demonstrate that the proposed schemes outperform the respective benchmarks for secure UAV-enabled MEC against active aerial eavesdropping.

关键词： Task analysis   Autonomous aerial vehicles   Optimization   Resource management   Statistics   Sociology   Green computing   Evolutionary algorithm   mobile edge computing   multiobjective optimization   unmanned aerial vehicles  

摘要： With the development of technology, unmanned aerial vehicles (UAVs) and Internet of Things devices are widely used in smart agriculture, resulting in significant energy consumption. In this paper, the optimization problem for UAV-assisted mobile computing in smart agriculture is modeled as a constrained multiobjective optimization problem. By jointly optimizing the deployment position of UAVs, the offloading location of the tasks, the transmit power of the devices, and the resource allocation of the UAVs, two optimization objectives (total delay and energy consumption) are minimized simultaneously. In view of the complex constraints, a constrained multiobjective algorithm named JO-DPTS is proposed. The algorithm adopts dual-population and two-stage approach to improve population convergence and diversity. The simulation results substantiate that JO-DPTS exhibits superior performance compared to the other three state-of-the-art constrained multiobjective evolutionary algorithms.

关键词： Task analysis   Resource management   Servers   Uncertainty   Optimization   Dynamic scheduling   Heuristic algorithms   Chance-constrained program   mobile edge computing   online resource management   probabilistic deadline guarantee   uncertain demands  

摘要： With the proliferation of resource-hungry applications, a common paradigm to quickly respond to the ever-increasing demands of tasks is mobile edge computing (MEC), which deploys resources on the premise of grasping task information (including time and quantity of task release, etc). Actually, task generation is dynamic in many practical scenarios, and it is unrealistic for MEC servers to acquire a task's demand for computing resources beforehand until task execution is completed. It is also challenging to ensure all tasks can be processed before their deadlines. In this paper, we characterize task generation as a dynamic process, implying that MEC servers only obtain the task information in the current time slot. Also, we assume the task's demand for computing resources is uncertain with only knowledge of its mean and variance. To eliminate this uncertainty, we leverage the chance-constrained program (CCP) method, which also offers a probabilistic guarantee to the task deadline. Moreover, we formulate a long-term time-averaged task processing power minimization problem, which is transformed into a series of per-slot deterministic optimization problems utilizing the Lyapunov algorithm. Given that the transformed problem is a mixed-integer non-linear programming (MINLP) problem, a joint optimization algorithm considering UE access, power control, and resource allocation (JUPR) is proposed to decouple the MINLP problem into three sub-problems. Finally, simulation results demonstrate the JUPR algorithm can consume 22% less power per task than the average resource allocation algorithm and 12% less power per task than the random resource allocation algorithm.

关键词： Task analysis   Optimization   NOMA   Resource management   Energy consumption   Servers   Wireless communication   Mobile edge computing   wireless power transfer   deep reinforcement learning   system computation completion time  

摘要： Wireless powered mobile edge computing (WP-MEC), which combines mobile edge computing (MEC) and wireless power transfer (WPT), is a promising paradigm for coping with the computing power and energy constraints of wireless devices. However, how to realize the online optimal offloading decision and resource allocation in the WP-MEC system is very challenging. This paper studies the system computation completion time (SCCT) minimization problems for WP-MEC networks using non-orthogonal multiple access (NOMA) communication under binary and partial offloading modes. Due to the complexity of the optimization problems and the time-varying nature of the channel state information, we decouple the original problems into a top-problem of optimizing WPT duration and a sub-problem of optimizing resource allocation, and then propose a convolutional deep reinforcement learning online (CDRO) algorithm. For the top-problem, a deep reinforcement learning framework is used to obtain the near-optimal WPT duration, and an incremental exploration policy is designed to balance the exploration accuracy and exploration range to improve the convergence performance of the CDRO algorithm. For the sub-problems, we propose their corresponding low-complexity algorithms based on in-depth analysis and derivation of the optimal offloading decision's properties. Finally, numerical results show that the proposed CDRO algorithm achieves near-optimal SCCT with low computational complexity, enabling online decision-making in time-varying channel environments.