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： Quality of service   Streaming media   Delays   Multimedia systems   Scheduling algorithms   Heuristic algorithms   Optimization   Deep-Q-network   deep reinforcement learning   mobile edge computing   multimedia   quality of service  

摘要： By offloading storage and computing resources to the edge of networks, mobile edge computing (MEC) is emerged as a promising architecture to reduce the transmission delay and bandwidth waste for mobile multimedia services. This paper focuses on a multi-service scenario in the MEC systems, where the MEC server can provide three multimedia services including live streaming, buffered streaming and low latency enhanced mobile broadband applications for edge users at the same time. In order to satisfy various quality of service (QoS) requirements for different multimedia applications, the 5G QoS model is applied. Notably, the packets from the multimedia applications with the same or similar requirements are mapped into the same QoS flow, and each QoS flow is processed individually. Therefore, how to effectively schedule the limited radio resource for QoS flows is an intractable problem. To address the problem above, a QoS evaluation model is designed, and a QoS maximization problem is formulated. Furthermore, a deep reinforcement learning method, deep-Q-network, is adopted to make decisions to allocate radio resource dynamically. Compared with round-robin and priority-based scheduling algorithms, the simulation results validate that the proposed algorithm outperforms other resource scheduling algorithms for multi-service scenario.

关键词： Mobile edge computing   energy harvesting   device-to-device (D2D) communication   computation offloading  

摘要： Mobile edge computing (MEC) is envisioned as a new paradigm by integrating the mobile computing functionality into 5G wireless networks, aiming at empowering communication networks with low-latency services. In general, mobile devices have finite battery lifetime (e.g., machine-type devices) and the energy harvesting is advocated to provide perpetual energy supply for achieving sustainable operation, which is very important for facilitating sustainable computing in future applications. In this paper, we propose a wireless powered MEC network architecture that employs device-to-device (D2D) communications underlaying heterogeneous networks (HetNets) to enable the computational tasks offloading to resource-rich edge servers. A dynamic offloading decision is made to execute the computation tasks. Then, we focus on the energy-efficient offloading scheme, and joint offloading and user association scheme. From the illustrative results, we provide insights for the design of this new network architecture. Furthermore, several open research topics are discussed.

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.

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： 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： Energy Internet   mobile edge computing   wind turbine   unmanned aerial vehicle   task offloading  

摘要： As a promising choice of alternative energy, wind power will account for a major part of energy generation in future Energy Internet. With the exploitation of wind power, multiple wind turbines (WTs) are deployed at remote and harsh areas, in which the adverse working environment may lead to enormous WT operating and maintenance costs. Deploying unmanned aerial vehicles (UAVs) for WT detection and sensory data processing in wind farms has been considered as a promising technology to reduce the costs and improve inspection efficiency. In this paper, a mobile edge computing (MEC) driven UAV routine inspection scheme is proposed, in which the UAV not only detects WTs in multiple sorties, but also provides computing and offloading services. To provide seamless communication service, UAV can offload the sensory data to the ground station or satellite optimally. In order to minimize the total completion time, we jointly optimize the UAV trajectory and computation operations, while guaranteeing the data processing accuracy. In the proposed scheme, in order to overcome the influence of wind on UAV trajectory planning, a low complexity WT routine inspection trajectory and UAV scheduling approach is designed firstly. Then, we present an iterative optimization solution to minimize the energy consumption of computation processing, via finding the optimal offloading trajectory and computation offloading parameters. Finally, simulation results show that the proposed scheme can effectively improve the efficiency of UAV routine inspection system performance.

关键词： Information-centric network   Internet of Things   mobile edge computing   joint optimization   deep Q-learning  

摘要： With the rapid development of the Internet of Things (IoT) network, the IoT devices need to perform the artificial intelligence (AI) model to make decisions according to the specific service requirement under a dynamic environment. However, the generation and usage of AI model typically requires a huge amount of communication, computing, and caching resource. Thus, the construction of the network and the scheduling of the limited network resources to realize the rapid generation and propagation of AI models are critical. Therefore, we propose a software-defined Information Centric-Internet of Things (IC-IoT) architecture to bring caching and computing capabilities to the IoT network. Based on the proposed IC-IoT architecture, we design a joint resource scheduling scheme to uniformly manage the computing and caching resources. The objective is to maximize the reward which consists not only short-term reward but also long-term reward brought by caching popular AI models. The resource scheduling problem is formulated into a multi-dimensional optimization problem. A new deep Q-learning method is proposed due to the complexity and high dimension of this problem. The simulation results verify the effectiveness of the software-defined IC-IoT architecture and the joint resource allocation strategy.

关键词： Opportunistic mobile social networks   mobile edge computing   routing-forwarding algorithm   mobile device similarity   fuzzy reasoning system  

摘要： The arrival of 5G is accompanied by massive data transmission between mobile devices (MDs) and huge transmission energy consumption in the wireless networks. Therefore, how message applications select the appropriate relay MDs to complete the efficient data transmission process in the opportunistic mobile social networks (OMSNs)? At present, designing an efficient routing-forwarding algorithm is extremely challenging. Some routing-forwarding algorithms choose appropriate nodes as relay nodes based on the similarity between nodes, but most existing routing-forwarding algorithms only consider a few similar factors and even completely ignore the importance of movement similarity in data transmission of the node. In particular, existing routing-forwarding algorithms will bring extra energy consumption to the nodes in the wireless networks, and excessive energy consumption will further affect the delay and data transmission efficiency. In order to solve the problems in the existing strategies, we apply the mobile edge computing (MEC) to OMSNs, and we propose the fuzzy reasoning routing-forwarding (FRRF) algorithm that integrates the movement and social similarity in the MEC-based OMSNs. In detail, the fuzzy evaluation of the movement and social similarity is integrated to determine the transmission priority value between MDs, and finally, the transmission priority between MDs is compared to make transmission decision. Through simulation experiment and comparison with other algorithms, the correctness of the theoretical analysis and the efficiency of the FRRF algorithm in energy consumption, delay, and transmission efficiency are verified.

关键词： Service migration   service functions virtualization   mobile edge computing   QoS-awareness  

摘要： 5G systems are envisioned to support numerous delay-sensitive applications such as the tactile Internet, mobile gaming, and augmented reality. Such applications impose new demands on service providers in terms of the quality of service (QoS) provided to the end-users. Achieving these demands in mobile 5G-enabled networks represent a technical and administrative challenge. One of the solutions proposed is to provide cloud computing capabilities at the edge of the network. In such vision, services are cloudified and encapsulated within the virtual machines or containers placed in cloud hosts at the network access layer. To enable ultrashort processing times and immediate service response, fast instantiation, and migration of service instances between edge nodes are mandatory to cope with the consequences of user's mobility. This paper surveys the techniques proposed for service migration at the edge of the network. We focus on QoS-aware service instantiation and migration approaches, comparing the mechanisms followed and emphasizing their advantages and disadvantages. Then, we highlight the open research challenges still left unhandled.