关键词： intelligent transportation system   short-term traffic state prediction   V2X communication   mobile edge computing   neural networks  

摘要： Real-time and reliable short-term traffic state prediction is one of the most critical technologies in intelligent transportation systems (ITS). However, the traffic state is generally perceived by single sensor in existing studies, which is difficult to satisfy the requirement of real-time prediction in complex traffic networks. In this paper, a short-term traffic prediction model based on complex neural network is proposed under the environment of vehicle-to-everything (V2X) communication systems. Firstly, a traffic perception system of multi-source sensors based on V2X communication is proposed and designed. A mobile edge computing (MEC)-assisted architecture is then introduced in a V2X network to facilitate perceptual and computational abilities of the system. Moreover, the graph convolutional network (GCN), the gated recurrent unit (GRU), and the soft-attention mechanism are combined to extract spatiotemporal features of traffic state and integrate them for future prediction. Finally, an intelligent roadside test platform is demonstrated for perception and computation of real-time traffic state. The comparison experiments show that the proposed method can significantly improve the prediction accuracy by comparing with the existing neural network models, which consider one of the spatiotemporal features. In particular, for comparison results of the traffic state prediction and the error value of root mean squared error (RMSE) is reduced by 39.53%, which is the greatest reduction in error occurrences by comparing with the GCN and GRU models in 5, 10, 15 and 30 min respectively.

关键词： Feature extraction   Servers   Wireless communication   Real-time systems   Monitoring   Resource management   Optimization   Machine learning   mobile edge computing   neurological mHealth systems   seizure detection and prediction  

摘要： Edge machine learning (Edge ML) is expected to serve as a key enabler for real-time mobile health (mHealth) applications. However, its reliability is governed by the limited energy and computing resources of user equipment (UE), along with the wireless channel variations and dynamic resource allocation at edge servers. In this letter, we incorporate both UE and edge server computing to satisfy the strict latency requirements of mHealth applications while efficiently utilizing the UE's energy resources. Specifically, we separate the feature extraction and classification processes of Edge ML inference and formulate an optimization problem to distribute them between the UE and the edge server while determining the optimal UE transmit power. We demonstrate the effectiveness of the proposed approach using an mHealth case study for predicting epileptic seizures using data from wearable health devices.

关键词： Heterogeneous networks   Energy consumption   Interference   Delays   Task analysis   Computational modeling   Uplink   Computation offloading   mobile edge computing   resource management   ultradense networks   heterogeneous networks  

摘要： To meet the demand of green communications of ultradense mobile devices (MDs), an energy-efficient mechanism, jointly considering the computation offloading and resource management, is designed to minimize the network-wide weighted energy consumption under the delay constraints of MDs for ultradense heterogeneous networks. Such a mechanism tightly integrates with the adjustment of computation capability and transmission power of MDs. Considering that the finally formulated problem is in a nonlinear and mixed-integer form, we design an effective algorithm to solve it. Specifically, by utilizing the powerful global searching capability of genetic algorithm (GA) and the accurate local searching capability of particle swarm optimization (PSO), the adaptive GA with diversity-guided is firstly used for coarse-grained search, and then adaptive PSO is utilized for fine-grained search. After that, some detailed analyses on the convergence, computation complexity and parallel implement are provided for algorithms. Simulation results show that the designed algorithm can achieve a lower network energy consumption than other offloading algorithms in general. At the same time, the numerical simulation also reveals that the designed algorithm may be more suitable for ultradense networks than existing algorithms.

关键词： Task analysis   Delays   Cloud computing   Computational modeling   Dynamic scheduling   Pricing   Costs   Mobile edge computing   profit maximization   task assignment   and resource management  

摘要： Mobile edge computing has been an important supplement for traditional cloud computing architecture to offer low-delay computing services to mobile users. However, it is in general impossible for edge service providers to overdeploy so much edge resources to satisfy the rapidly increasing while diverse user demands. In this paper, we study a mobile edge computing system consisting of a service platform, cloudlets joining the system, and mobile users. In this study, we focus on a profit-driven perspective such that the service platform purchases computation resource from the resource-rich cloudlets and makes profit by processing tasks from user side. The design objective is to maximize the platform profit subject to budget constraint and stringent delay requirements for task processing. We formulate this problem as a mixed integer programming problem. Due to the NP-hardness of the problem, we design a logic based Benders decomposition algorithm as the offline solution. We further study the scenario where the task arrivals from user side and resource availability at the cloudlets are both stochastic and unknown in advance. We accordingly propose a Multi-Armed Bandit learning based resource purchasing and greedy task scheduling algorithm for the online scenario. Simulations results show the high performance of our proposed algorithms.

关键词： Task analysis   Computational modeling   Costs   Resource management   Optimization   Artificial intelligence   Hardware   Computation offloading   Lyapunov Optimization   edge intelligence   mobile edge computing   deep learning  

摘要： With the rapid development of computing power and artificial intelligence, IoT devices equipped with ubiquitous sensors are gradually installed with intelligence. People can enjoy many conveniences with intelligent devices, such as face recognition, video understanding, and motion estimation. Currently, deep neural networks are the mainstream technology in intelligent mobile applications. Inspired by DNN model partition schemes, the paradigm of edge computing could be utilized collaboratively to improve the effectiveness of intelligent task execution in IoT devices. However, due to the dynamics of the wireless network environment and the increasing number of IoT devices, a DNN partition policy without adequate consideration would pose a significant challenge to the efficiency of task inference. Moreover, the shortage and high rental cost of edge computing resources make the optimization of DNN-based task execution more difficult. To cope with those situations, we propose a joint method by a self-adaptive DNN partition with cost-effective resource allocation to facilitate collaborative computation between IoT devices and edge servers. Our proposed online algorithm can be proved to ensure the overall rental cost within an upper bound above the optimal solution while guaranteeing the latency for DNN-based task inference. To evaluate the performance of our strategy, we conduct extensive trace-driven illustrative studies and show that the proposed method can achieve sub-optimal results and outperforms other alternative methods.

关键词： Task analysis   NOMA   Wireless communication   Servers   Resource management   5G mobile communication   Minimization   Network slicing   NOMA   mobile edge computing   latency minimization   optimization   energy efficiency  

摘要： With the rapid growth of traffic in current wireless networks, the management of heterogeneous and time-critical services with limited computing and communication resources has become a significant challenge. Edge computing (EC) is one of the key techniques in enabling 5G networks to reduce the latency of services while the network slicing (NS) technique aims to provide users with tailored services by taking advantage of virtualization of a physical network. Besides, non-orthogonal multiple access (NOMA), one of the key enablers of 5G networks, enables more users to share wireless resources. We propose to leverage these techniques to minimize the total latency of the computing tasks with energy constraints. The combination of NS with NOMA for EC can reduce the unnecessary allocation of resources and consequently enhance both the energy and spectral efficiencies of the system. We first propose a binary scheme for offloading computing tasks and formulate an optimization problem to minimize the total latency of completing the tasks. We then transform the optimization problem to facilitate a near-optimal solution. We also introduce a heuristic algorithm to reduce the computational complexity of solving the optimization problem. Finally, extensive simulation results have demonstrated the effectiveness of our proposed algorithm.

关键词： Servers   Costs   Computational modeling   Switches   Delays   Reinforcement learning   Vehicle dynamics   Mobile edge computing   edge server   user mobility   deep reinforcement learning  

摘要： With Mobile Edge Computing (MEC), computational intensive applications can be offloaded to the nearby edge servers to support latency-sensitive applications on mobile devices. Different from the cloud, edge servers usually have limited resources, and then selecting which edge server to run the offloaded computation becomes an important issue. Although server selection has received considerable attention, not much work has been done to consider the limited coverage of the edge server and the frequent user movement, which introduce many dynamic changing factors affecting the workload of the edge server and making it hard to achieve long-term optimum in the edge server selection. To deal with these challenges, we model the problem of continuous server selection as a Markov Decision Process (MDP). The difficulty of this problem is that achieving long-term optimum requires future knowledge, such as user mobility, server workload, etc, which is not known a priori. We do not have such knowledge and thus cannot find the optimal policy through traditional methods. To address this problem, we propose a Deep Reinforcement Learning (DRL) based algorithm to learn the selection policy based on the observed performance of past server selections. Specifically, a Long Short-Term Memory (LSTM) based neural network is exploited to encode the historical information which helps infer future knowledge of the dynamically changing factors. Then the DRL model selects the optimal server automatically based on the extracted system states. Extensive trace-driven evaluations demonstrate that the proposed DRL-based algorithm has the lowest overall cost compared to existing solutions.

关键词： Multimedia information system   Pattern recognition   Binocular vision   Social robot   Intelligent education   Mobile edge computing  

摘要： In recent years, artificial intelligence technology has gradually expanded its application scenarios in the field of education. Nevertheless, at present, most AI application scenarios are still difficult to really penetrate into the core links. Educational robot based on artificial intelligence technology can provide humanized interaction and personalized intelligent teaching in different links, thus it has attracted more attention and development than ever. For mobile robots, vision based target recognition technology is a very basic but challenging topic. The result of robot target recognition is directly related to the positioning, navigation and other work of the robot. Therefore, this paper studies the intelligent education information framework of social robot based on artificial intelligence-driven mobile edge computing. The pattern recognition framework is applied to the system and the proposed model is tested on the public database. Compared to the other state-of-the-art methodologies, the proposed idea performs better.

关键词： mobile edge computing   task offloading   game theory   Nash equilibrium  

摘要： Various types of service applications increase the amount of computing in vehicular networks. The lack of computing resources of the vehicle itself will hinder the improvement of network performance. Mobile edge computing (MEC) technology is an effective computing method that is used to solve this problem at the edge of network for multiple mobile users. In this paper, we propose the multi-user task offloading strategy based on game theory to reduce the computational complexity and improve system performance. The task offloading decision making as a multi-user task offloading game is formulated to demonstrate how to achieve the Nash equilibrium (NE). Additionally, a task offloading algorithm is designed to achieve a NE, which represents an optimal or sub-optimal system overhead. In addition, the vehicular communication simulation frameworks Veins, SUMO model and OMNeT++ are adopted to run the proposed task offloading strategy. Numerical results show that the system overhead of the proposed task offloading strategy can degrade about 24.19% and 33.76%, respectively, in different scenarios.

关键词： Task analysis   Resource management   Delays   Servers   Edge computing   Computer architecture   Reinforcement learning   Mobile edge computing   delay-constrained   constrained reinforcement learning   application-specific design  

摘要： We design a joint radio and computational resource allocation policy for a multi-user mobile edge computing system, such that the expected power consumption is minimized while satisfying long-term delay constraints. The problem is formulated as a constrained Markov decision process (CMDP) that is efficiently solved by the proposed constrained reinforcement learning (CRL) algorithm, called successive convex programming based policy optimization (SCPPO). SCPPO solves a convex objective/feasibility surrogate problem at each update and it can provably converge to a Karush-Kuhn-Tucker (KKT) point of the original CMDP problem almost surely under some mild conditions. Moreover, SCPPO adopts an application-specific policy architecture and employs a data-efficient estimation strategy that can reuse old experiences, such that SCPPO can realize fast learning with low computational complexity.