关键词： Mobile edge computing   network coding   wireless relay   intelligent cache   cooperative communications  

摘要： As an important technology in next-generation networks, mobile edge computing (MEC) can bring high-speed intelligent network services to users. However, planning MEC file transmission represents a problem to be urgently solved. In addition, network coding has been an emerging technology in recent years, and certain forms of cooperation with wireless relays can improve the transmission efficiency of network data. In this paper, we focus on cooperation in MEC intelligent cache with network coding. First, we built a MEC intelligent cache analysis platform that includes multiple algorithms;it can predetermine which streaming media files should be stored in the limited storage space of the MEC device to provide users the most efficient intelligent network experience. The platform's decision algorithm includes an innovative composite recommendation algorithm that is more comprehensive than the traditional recommendation algorithm. The MEC file extracted from the core network is then simultaneously transmitted to the edge with the real-time normal communication file using an innovative network coding and wireless relay cooperation method;with that, the files stored in the MEC can be cached to the edge. The normal network communication process does not require additional slot costs. The simulation results show that the proposed cooperation scheme can effectively improve network data transmission, improve users' average access rate, and offer users better intelligent network services.

关键词： Deep reinforcement learning   video quality selection   radio bearer control   short video applications   mobile edge computing  

摘要： With the rapid development of mobile communication technology, short video applications, which combine the features of both social and multimedia applications, have become more and more popular. However, the transmission of short videos poses great challenges to the existing mobile networks. In this paper, mobile edge computing is adopted to provide content caching of short videos close to end users. To improve the quality of service, we take both the quality level of the video and the long-term wireless network transmission performance into consideration. The joint video quality selection and radio bearer control optimization problem is formulated as a Markov decision process, aiming at maximizing the long-term video quality profit and minimizing the cost of bearers and the penalty of latency. Deep reinforcement learning is used as the solution and the policy gradient based quality selection and radio bearer control method is proposed. The REINFORCE algorithm with baseline is used to train the policy network, and the episodic simulations are built to obtain the training samples. Different weight coefficients of the objective function are configured. Training results show that the proposed method can achieve the best accumulated value among all the comparison methods. When the weight coefficients are changed, the training processes can lead the policy networks to obtain proper trade-off between different objective factors. Moreover, the performance of the trained policy network is evaluated with different short video request arriving rates. Testing results show that the proposed method performs well when the arriving rates vary in a certain range.

关键词： Green Internet of Vehicles   5G   mobile edge computing   deep reinforcement learning  

摘要： With the development of Internet of Vehicles (IoV) and the gradual maturity of 5th Generation Mobile Networks (5G) technology, the further development of the IoV highly relies on network energy and resources. However, basic methods of researching new energy or improving equipment result in high cost. This article focuses on researching how to minimize energy consumption and maximize resource utilization with the constraints of existing environment and equipment. We jointly discuss 5G technology, mobile edge computing and deep reinforcement learning in green IoV. We also discuss how to make rational use of resources to realize the sustainable development of IoV. By classifying and comparing the existing researches according to different emphases, the energy consumption can be managed effectively with the above-mentioned technologies. Finally, we analyze the possible research directions and challenges in the future.

关键词： Task analysis   Mobile handsets   Servers   Energy consumption   Computational modeling   Adaptation models   Mobile applications   Mobile edge computing   offloading   resource allocation   reinforcement learning   task dependency  

摘要： Mobile edge computing (MobEC) builds an Information Technology (IT) service environment to enable cloud-computing capabilities at the edge of mobile networks. To tackle the restrictions in the battery power and computation capability of mobile devices, task offloading for using MobEC is developed and used to reduce the service latency and to ensure high service efficiency. However, most of the existing schemes only focus on one-shot offloading, while taking less into consideration the task dependency. It is urgently needed a more comprehensive and adaptive way to take both the energy constraint and the inherent dependency of tasks into account, since modern communication networks have increasingly become complicated and dynamic. To this end, in this paper, we are motivated to study the problem of dependency-aware task offloading decision in MobEC, aiming at minimizing the execution time for mobile applications with constraints on energy consumption. To solve this problem, we propose a model-free approach based on reinforcement learning (RL), i.e., a Q-learning approach that adaptively learns to optimize the offloading decision and energy consumption jointly by interacting with the network environment. Simulation results show that our RL-based approach is able to achieve significant reduction on the total execution time with comparably less energy consumption.

关键词： Deep learning   Energy consumption   Servers   Decision making   Cost function   Mathematical model   Task analysis   Computational offloading   deep learning   energy efficient offloading   mobile edge computing   user equipment  

摘要： Mobile edge computing (MEC) has shown tremendous potential as a means for computationally intensive mobile applications by partially or entirely offloading computations to a nearby server to minimize the energy consumption of user equipment (UE). However, the task of selecting an optimal set of components to offload considering the amount of data transfer as well as the latency in communication is a complex problem. In this paper, we propose a novel energy-efficient deep learning based offloading scheme (EEDOS) to train a deep learning based smart decision-making algorithm that selects an optimal set of application components based on remaining energy of UEs, energy consumption by application components, network conditions, computational load, amount of data transfer, and delays in communication. We formulate the cost function involving all aforementioned factors, obtain the cost for all possible combinations of component offloading policies, select the optimal policies over an exhaustive dataset, and train a deep learning network as an alternative for the extensive computations involved. Simulation results show that our proposed model is promising in terms of accuracy and energy consumption of UEs.

关键词： Data offloading   energy aware   mobile edge computing   deep reinforcement learning  

摘要： A large number of connected sensors and devices in Internet of Things (IoT) can generate large amounts of computing data and increase massive energy consumption. Real-time states monitoring and data processing of IoT nodes are of great significance, but the processing power of IoT devices is limited. Using the emerging mobile edge computing (MEC), IoT devices can offload computing tasks to an MEC server associated with small or macro base stations. Moreover, the use of renewable energy harvesting capabilities in base stations or IoT nodes may reduce energy consumption. As wireless channel conditions vary with time and the arrival rates of renewable energy, computing tasks are stochastic, and data offloading and renewable energy aware for IoT devices under a dynamic and unknown environment are major challenges. In this work, we design a data offloading and renewable energy aware model considering an MEC server performing multiple stochastic computing tasks and involving time-varied wireless channels. To optimize data transmission delay, energy consumption, and bandwidth allocation jointly, and to avoid the curse of dimensionality caused by the complexity of the action space, we propose a joint optimization method for data offloading, renewable energy aware, and bandwidth allocation for IoT devices based on deep reinforcement learning (JODRBRL), which can handle the continuous action space. JODRBRL can minimize the total system cost(including data buffer delay cost, energy consumption cost, and bandwidth cost) and obtain an efficient solution by adaptively learning from the dynamic IoT environment. The numerical results demonstrate that JODRBRL can effectively learn the optimal policy, which outperforms Dueling DQN, Double DQN (DDQN), and greedy policy in stochastic environments.

关键词： Task analysis   Servers   Resource management   Mobile handsets   Computational modeling   Edge computing   Optimization   Mobile edge computing   resource allocation   optimization  

摘要： Due to explosive growth in mobile applications and services with different requirements, the concept of mobile edge computing (MEC) has emerged. For MEC, a mobile user (MU) and a MEC server need to exchange tasks using limited radio resources. Furthermore, when multiple MUs possess tasks, the MEC server has to handle multiple tasks simultaneously. Thus, the radio and computing resources need to be allocated to MUs by taking into account the wireless channel condition and the computing power of MUs and the MEC server. In this paper, a radio resource and computing resource allocation scheme is proposed to minimize the total processing completion time of all the tasks. Each task is assumed to be divided into local task and offload task. The local task is processed by each MU while the offload task is processed by a MEC server. We first formulate the optimization problem to minimize the total processing completion time of all tasks. To solve the formulated optimization problem, we propose a two-step radio and computing resources allocation scheme which iteratively performs bisection search method and Johnson's algorithm. The numerical results elucidate that the proposed scheme can reduce the total processing completion time by about 25% on average compared to the conventional schemes when multiple MUs have divisible tasks.

关键词： Unsaturated analysis model   real-time data self-organizing push   task collaborative scheduling model   mobile edge computing  

摘要： Wireless self-organizing networks have received extensive attention and research because they do not require fixed infrastructure support. Due to the complexity of data transmission in edge computing, the core cloud data center is very far away from the user, resulting in a very large delay in obtaining data from the mobile terminal. In view of this, this paper provides a nearby computing and processing service for user services by deploying multiple mobile edge computing servers on the base station side near the user's mobile core network edge. Firstly, this paper establishes an accurate DCF (Distributed Coordination Function) analysis model under unsaturated conditions. An analytical model for the statistical characteristics of service time is constructed. This model distinguishes the different effects of successfully transmitted packets and discarded packets. Secondly, this paper uses the maximum centrality theory of data aggregation transmission algorithm to determine the degree of influence of nodes by degree centrality theory to generate a fixed unbalanced spanning tree. On the basis of the spanning tree, a relatively large set of parallel nodes can be obtained, thereby reducing the delay time in the entire data transmission process. Finally, this paper studies two resource joint scheduling strategies of mobile terminals and MEC (Mobile Edge Computing) servers in mobile cellular networks based on MEC system. The performance of two collaborative scheduling strategies is verified by simulation. The simulation results show that the collaborative scheduling strategy proposed in this paper can effectively reduce the service cost of the system under the condition of ensuring the user service experience.

关键词： Task scheduling   smart city   mobile edge computing   Internet of Vehicle   alternating direction method of multipliers (ADMM) algorithm  

摘要： The smart city is increasingly gaining worldwide attention. It has the potential to improve the quality of life in convenience, at work, and in safety, among many others' utilizations. Nevertheless, some of the emerging applications in the smart city are computation-intensive and time-sensitive, such as real-time vision processing applications used for public safety and the virtual reality classroom application. Both of them are hard to handle due to the quick turnaround requirements of ultra-short time and large amounts of computation that are necessary. Fortunately, the abundant resource of the Internet of Vehicles (IoV) can help to address this issue and improve the development of the smart city. In this paper, we focus on the problem that how to schedule tasks for these computation-intensive and time-sensitive smart city applications with the assistance of IoV based on multi-server mobile edge computing. Task scheduling is a critical issue due to the limited computational power, storage, and energy of mobile devices. To handle tasks from the aforementioned applications in the shortest time, this paper introduces a cooperative strategy for IoV and formulates an optimization problem to minimize the completion time with a specified cost. Furthermore, we develop four evolving variants based on the alternating direction method of multipliers (ADMM) algorithm to solve the proposed problem: variable splitting ADMM, Gauss-Seidel ADMM, distributed Jacobi ADMM, and distributed improved Jacobi (DIJ)-ADMM algorithms. These algorithms incorporate an augmented Lagrangian function into the original objective function and divide the large problem into two sub-problems to iteratively solve each sub-problem. The theoretical analysis and simulation results show that the proposed algorithms have a better performance than the existing algorithms. In addition, the DIJ-ADMM algorithm demonstrates optimal performance, and it converges after approximately ten iterations and improves the

关键词： ID-PRS   integer factorization problem   mobile edge computing   free-pairing   non-interactive  

摘要： The Internet of Things (IoT) is the internetworking of terminal physical devices depends on application programming interfaces and sensors to be connected to the Internet for collecting and exchanging data. According to the characteristics of IoT, it can provide rich services for the terminal user. However, the centralized cloud computing-based storage architecture in IoT faces many challenges, such as data security, identity privacy, and high latency. To overcome these challenges, this paper introduces an IoT network storage architecture based on mobile edge computing, which not only achieves low-latency message response and computation offloading of the terminal user but also preserves identity-privacy of the terminal user. Afterward, we presented a novel non-interactive pairing-free ID-based proxy re-signature scheme (ID-PRS), which is a kernel technique to construct the aforementioned storage architecture. Compared with most of proxy re-signature schemes constructed based on traditional public-key-infrastructure, the proposed scheme avoids expensive pairing operation and intricate certificate-maintenance. And it is demonstrated to be provably secure under the classic security assumptions: integer factoring problem and the RSA assumption. Finally, in contrast to the other two ID-PRS schemes, the proposed ID-PRS scheme has more advantages in terms of security, functionability, and computation costs. Thus, it is very suitable to be applied to the resource-constrained mobile users.