关键词： Internet of things devices   Mobile edge computing   Energy-saving service management   Long short-term memory model   Reinforcement learning   Dynamic power management  

摘要： The purpose is to solve the problems of high transmission rate and low delay in the deployment of mobile edge computing network, ensure the security and effectiveness of the Internet of things (IoT), and save resources. Dynamic power management is adopted to control the working state transition of Edge Data Center (EDC) servers. A load prediction model based on long-short term memory (LSTM) is creatively proposed. The innovation of the model is to shut down the server in idle state or low utilization in EDC, consider user mobility and EDC location information, learn the global optimal dynamic timeout threshold strategy and N-policy through trial and error reinforcement learning method, reasonably control the working state switching of the server, and realize load prediction and analysis. The results show that the performance of AdaGrad optimization solver is the best when the feature dimension is 3, the number of LSTM network layers is 6, the time series length is 30-45, the batch size is 128, the training time is 788 s, the number of units is 250, and the number of times is 350. Compared with the traditional methods, the proposed load prediction model and power management mechanism improve the prediction accuracy by 4.21%. Compared with autoregressive integrated moving average (ARIMA) load prediction, the dynamic power management method of LSTM load prediction can reduce energy consumption by 12.5% and realize the balance between EDC system performance and energy consumption. The system can effectively meet the requirements of multi-access edge computing (MEC) for low delay, high bandwidth and high reliability, reduce unnecessary energy consumption and waste, and reduce the cost of MEC service providers in actual operation. This exploration has important reference value for promoting the energy-saving development of Internet-related industries.

关键词： Servers   Visual analytics   Delays   Optimization   Streaming media   Bayes methods   Wireless communication   Mobile edge computing   video analytics   offloading   online learning   Bayesian optimization  

摘要： Video analytics demand intensive computation resources, which means long processing delay when running on mobile devices. Although offloading computation to the cloud can partially solve the problem, transferring videos to the cloud introduces high transmission delay. With mobile edge computing, computation can be offloaded to the nearby edge servers to reduce the delay. However, the computation resources of the edge servers are usually limited and highly dynamic, and then server selection should be adaptive in order to improve the performance of video analytics. Also, frame resolution should be selected to achieve a better tradeoff between accuracy and frame processing rate. In this paper, we study the server resource-aware offloading problem for video analytics, where the goal is to maximize the utility which is a weighted function of accuracy and frame processing rate. The major challenge to solve this problem is the lack of server and network knowledge and the dynamic system environment. To overcome these challenges, we formulate the problem as a contextual Multi-armed Bandit problem, and propose a Bayesian Optimization based online learning algorithm to gradually learn the server status and the optimal solution, and make it adaptable for time-varying environments. Both theoretical analysis and evaluation results demonstrate the superior performance of our proposed algorithm.

关键词： Sensors   Radar   Performance evaluation   Wireless sensor networks   Servers   OFDM   Computational modeling   Radio resource allocation   integrated sensing and communication   mobile edge computing   network externality   matching theory  

摘要： Integrated sensing, communication, and computation (ISCC) will become a key enabler for automation applications. However, since the performance region of ISCC has a higher dimension than those of traditional wireless networks, existing schedulers typically fail to simultaneously meet the heterogeneous requests in ISCC. In this work, we propose a novel wireless scheduling architecture to explore the coordination gains of sensing, communication, and computation from a perspective of joint optimization. Specifically, we first construct an implementation framework of ISCC by combining the mobile edge computing paradigm with the integrated sensing and communication technology, where the inherent tradeoff between sensing, communication, and computation performance is characterized. Next, a joint device association and subchannel assignment problem is formulated to capture the network externalities induced by resource competition among mobile devices with multi-functional requirements. Due to its intractability, we then reformulate it in the matching theoretical manner. To obtain a mutually satisfactory solution under externalities, an iterative matching algorithm is developed by introducing pairwise stability and proved to be convergent and stable. The extensive simulations elucidate the significant superiority of our proposed scheme over those externality-unaware wireless schedulers.

关键词： Task analysis   Autonomous aerial vehicles   Energy consumption   Digital twins   Trajectory   Servers   Resource management   Digital twin   unmanned aerial vehicle   mobile edge computing   user mobility   deep reinforcement learning  

摘要： Considering the user mobility and unpredictable mobile edge computing (MEC) environments, this paper studies the intelligent task offloading problem in unmanned aerial vehicle (UAV)-enabled MEC with the assistance of digital twin (DT). We aim at minimizing the energy consumption of the entire MEC system by jointly optimizing mobile terminal users (MTUs) association, UAV trajectory, transmission power distribution and computation capacity allocation while respecting the constraints of mission maximum processing delays. Specifically, double deep Q-network (DDQN) algorithm stemming from deep reinforcement learning is first proposed to effectively solve the problem of MTUs association and UAV trajectory. Then, the closed-form expression is employed to handle the problem of transmission power distribution and the computation capacity allocation problem is further addressed via an iterative algorithm. Numerical results show that our proposed scheme is able to converge and significantly reduce the total energy consumption of the MEC system compared to the benchmark schemes.

关键词： total consumed task communication time   MEC   mobile edge computing   DQN-SN   moving direction-based adaptive task migration   multiple edge servers   MDP   reinforcement learning   resource allocation   training process   deep learning (artificial intelligence)   edge computing   Markov processes   credit-based scheme   telecommunication scheduling   resource-limited users   mobility process   Markov decision process   greedy algorithms   trusted edge environment   mobile computing   low-latency services   vehicle network   deep Q network   moving process   telecommunication computing  

摘要： Edge computing is expected to be a promising paradigm to provide low-latency services. Tasks from resource-limited users can be offloaded to edge servers for efficient execution within a limit time. This innovative technique has attracted widespread attention. Task migration is one of the important problems in mobile edge computing (MEC). Taking vehicle network as an example, during the moving process, a vehicle passes through multiple edge servers and decisions about where to migrate the task need to be made. The moving direction should be emphasized since it directly determines a vehicle's trajectory. Nevertheless, few existing works take the moving direction into consideration. In this paper, task migration issue during the vehicle's mobility process is investigated and the moving direction is specifically considered. The direction helps exclude meaningless selections. The moving process can be formulated as a Markov decision process (MDP) and effort is made to design an adaptive algorithm with direction consideration, aiming at minimizing the total communication time while satisfying the deadline of each task. Based on deep Q network (DQN), we devise a Soft update and parameter Noise applied algorithm DQN-SN, trying to enlarge action exploration space and stabilize the target network's parameter placement in training process. Besides, with the goal of building credible MEC, a credit-based scheme is also introduced to establish a trusted edge environment. Extensive experiments are conducted to evaluate the performance of our proposed algorithm. Compared to Greedy algorithm and DQN, the total consumed task communication time of DQN-SN shows 10-20% reduction. Furthermore, the algorithms with the direction factor always outperform the algorithms without direction consideration.

关键词： Mobile blockchain   Mobile edge computing   5G   Mining-as-a-Service   Data offloading  

摘要： In this paper, we propose a mobile blockchain (MB) based mining-as-a-service (MaaS) scheme, MBMaaS for resource-constrained industrial internet-of-things (IIoT) environments. The scheme addresses the research gaps of fixed static allocation for miners to perform computationally intensive mining tasks through a multi-hop computational offloading (CO) scheme and addresses an auction mechanism for a fair bidding process among the miner nodes. The scheme operates in three phases. In the first phase, a multi-hop CO scheme with a fair incentive policy is formulated for miners. The CO schemes offer guaranteed offloading services to mobile devices from far-edge systems through a chain of neighbor nodes. Then, in the second phase, MaaS is proposed to leverage expensive mining tasks through 5Genabled pico/femtocells. Integration of 5G allows massive end-to-end device and service connectivity. As IIoT ecosystems have limited memory and compute requirements, MaaS assures that the proposed consensus has a responsive validation and mining time. To make the data exchange in the consensus process lightweight, and allow a large number of sensors to share the data in a lightweight manner, an effective consensus mechanism Lightweight Proof-of-Proximity (LPoP), is proposed that forms group validations instead of single block validation. The data is exchanged through javascript object notation (JSON) format, maintaining a steady transaction rate. MB-MaaS is compared against the existing scheme for parameters bid thresholds and request servicing times, and mining and consensus formation. For example, the request serving time at 12 requests is improved by 56.78%, and a significant improvement of 26.47% is observed for processed blocks;parsing time on average is improved by 7.89%. The comparative analysis suggests that the scheme is more efficient than other competing approaches. (c) 2022 Elsevier Inc. All rights reserved.

关键词： Multi-period vehicular task offloading   Mobile edge computing   5G HetNets   Transmission method   Task completion rate   Timely rate of task completion  

摘要： Task offloading is one of the important research directions in Internet of Vehicles. Mobile edge computing and 5G heterogeneous network frameworks bring new opportunities for task offloading research. Most research works propose resource scheduling schemes and offloading strategies for task offloading within the same period. However, the allocation of resources for offloading tasks at different periods cannot be planned uniformly. The utilization and release of resources in previous periods affect the scheduling of resource allocations in later periods. To address the task offloading problem at different periods, this paper proposes the MPTO-MT algorithm. Specifically, the algorithm first determines whether the task can be offloaded in time at a certain period according to the number of candidate offloading nodes of the task in this period. Secondly, the algorithm selects the offloading node and the task transmission method. In order to select the appropriate offloading node and transmission method, we introduce the service utility and propose three heuristics of selecting the offloading node. Finally, the algorithm updates the resource information of nodes at the next period based on the utilization and release of node resources at the period, and the service time of the nodes. Comparative experiments with other baseline algorithms show that the proposed MPTO-MT algorithm improves the task completion rate by 4.55%, the timely rate of task completion by 3.57%, and shorter average service time.

关键词： Mobile edge computing   Machine learning   Virtual machine placement   Bat Algorithm  

摘要： Mobile edge computing requires more and more high-performance servers, resulting in increasing energy consumption. As a well-established way to reduce energy consumption, virtual machine placement can be utilized to optimize the cost of wide-deployment of servers. However, traditional strategies tend to focus on single indicators, there are few existing research taking time delay limitation into account while solving energy consumption problems. In this paper, we propose a brand new method to settle the problems listed above, which is able to reduce the placement time of virtual machine and energy consumption. First, considering the excellent performance of bat swarm algorithm in NP-hard problem, we introduced the second order oscillation factor to avoid premature convergence, and combined the order exchange and migration local search technology. we proposed the OEMBA algorithm, which integrates underutilized servers to save energy. Subsequently, an improved Long Short-Term Memory model is utilized to fasten the placement of virtual machines and reduce latency based on historical data. Our results indicate that the improved learning model can save energy consumption and reduce placement latency.

关键词： mobile edge computing   task offloading   deep Q-learning   optimization  

摘要： Even though small portable devices are becoming increasingly more powerful in terms of processing power and power efficiency, there are still workloads that require more computational capacity than these devices offer. Examples of such workloads are real-time sensory input processing, video game streaming, and workloads relating to IoT devices. Some of these workloads such as virtual reality, however, require very small latency;hence, the workload cannot be offloaded to a cloud service. To tackle this issue, edge devices, which are closer to the user, are used instead of cloud servers. In this study, we explore the problem of assigning tasks from mobile devices to edge devices in order to minimize the task response latency and the power consumption of mobile devices, as they have limited power capacity. A deep Q-learning model is used to handle the task offloading decision process in mobile and edge devices. This study has two main contributions. Firstly, training a deep Q-learning model in mobile devices is a computational burden for a mobile device;hence, a solution is proposed to move the computation to the connected edge devices. Secondly, a routing protocol is proposed to deliver task results to mobile devices when a mobile device connects to a new edge device and therefore is no longer connected to the edge device to which previous tasks were offloaded.

关键词： Task analysis   Servers   Autonomous aerial vehicles   Wireless communication   Resource management   Energy consumption   Performance evaluation   Mobile edge computing   resource allocation   service caching   task offloading   UAV communications  

摘要： Service caching refers to caching the necessary programs or/and the related databases for performing computational tasks at edge servers, which has been considered to save both computation and communication resources in mobile edge computing (MEC) systems. In this paper, we investigate computation service caching in a multi-unmanned aerial vehicle (UAV) enabled MEC system, where each UAV equipped with an edge server acts as an aerial computing platform to serve the ground devices. Furthermore, the UAVs can serve the devices cooperatively through the provided computing and caching resources. Aiming at minimizing the maximum task completion latency among all devices, we formulate a joint service caching, task offloading, communication and computation resource allocation, as well as UAV placement optimization problem, while guaranteeing the energy budget of all devices and UAVs. The problem is a mixed integer non-linear programming problem, and we decompose it into four sub-problems, and then propose an iterative algorithm based on block coordinate descent (BCD) and successive convex approximation (SCA) techniques to obtain near-optimal solution. Numerical results show that our proposed algorithm can achieve lower task completion latency than other baselines while guaranteeing better fairness among all devices.