1,721,039 research outputs found
An Energy-Aware Offloading Clustering Approach (EAOCA) in fog computing
No full textFog computing is an interesting paradigm which has drawn attention recently, based on the presence of several Fog Nodes (FNs) able to interact among each other for sharing their tasks. To boost the interactions among FNs, an Energy-Aware Offloading Clustering Approach (EAOCA) is proposed for raising the network fairness in terms of FNs' energy level. In each cluster, there is a Fog Cluster Head (FCH) that aggregates the traffic from its Fog Cluster Members (FCMs) to be computed. EAOCA considers different policies for evaluating the impact of FCH and FCM selection and how the remained energy of the FNs influences the performance of the network in terms of fairness, delay and energy consumption. The simulation results later demonstrate how cluster updating frequency has a profound impact on the network lifetime
Deep Reinforcement Learning for Edge-DASH-Based Dynamic Video Streaming
Full text linkDynamic Adaptive Streaming over HTTP (DASH) is a promising solution to enhance the Quality of Experience (QoE) of mobile video services. In this paper, we consider an Edge-DASH scenario where two problems of Bitrate Allocation (BrA) and user-to-server allocation (USA) have been jointly formulated. Then, we exploit Deep Reinforcement Learning (DRL) algorithm to solve the USA problem and select the streaming point for users, which can be streaming from the Edge, Macro layer or cloud, and deliver the users the most appropriate bitrate respecting the QoE by solving the BrA problem. In the simulation results, we have demonstrated that our Deep Deterministic Policy Gradient (DDPG) outperforms the traditional solution in terms of bitrate allocation
Android-based Implementation of a Fog Computing and Networking Environment
Full text linkThe increasing number of devices and applications requesting external processing and storage facilities with reduced access latency has led to the introduction of edge computing solutions. Among others, Fog Computing can be considered as an edge computing solution enabling the edge devices to offer general-purpose processing and storage capabilities. Despite a huge research effort for proposing efficient Fog Computing solutions, their implementability is still under study. By resorting to the Cloud Computing service models, we propose here an Android-based proof-of-concept solution allowing to implement different Fog services in an edge scenario by using off-the-shelf end-user devices
Multiuser interference mitigation in multipath fading channels using a neural network based blind receiver
No full textIn order to enhance the bandwidth utilization, new advanced receivers for next generation mobile communications are developed. Adaptive blind multiuser detection has been widely proposed for applications in CDMA (Code Division Multiple Access) wireless communication systems for its principal advantage of eliminating training sequence to set-up receiver filter coefficients. Main drawback of this technique is that it reaches the optimum behavior after a certain number of bit times, which precludes its use in typical time-varying environments. In this paper, a new neural network approach is proposed in order to solve this drawback. In particular, this paper considers the use of a modified Kennedy-Chua neural network, based on the Hopfield model. Numerical results are given to demonstrate the effectiveness of the proposed approach in different time-varying application scenarios
A neural network for constrained optimization with application to CDMA communication systems
No full textThis brief proposes a neural network for the solution in real time of a class of quadratic optimization problems with equality and Inequality constraints arising in code-division multiple access (CDMA) communication systems. The network, which is derived via a nonobvious modification of the circuit for nonlinear programming introduced by Kennedy and Chua, is shown to be globally asymptotically stable, and as such is able to compute the global optimal solution in real time, without the risk of spurious responses. Computer simulations are presented to verify the neural network optimization capabilities and speed, and the performance in the application to CDMA communication systems
FORCH: An Orchestrator for Fog Computing service deployment
Full text linkIn scenarios where resource locality is the key, Fog Computing helps in bringing the potentialities of Everythingas-a-Service (XaaS) closer to the end user, reducing both service time and load on the Cloud infrastructure. We designed and developed FORCH, a service model-aware Fog Computing orchestrator to dynamically allocate services and manage resources available on Fog nodes, in order to provide for different needs of the end users. An experimental test bed to validate FORCH architecture has been implemented and will be the subject of our live demonstration, showing the feasibility of the proposed approach running on different Fog node types and with different service models
A cellular neural networks based DiffServ switch for satellite communication systems
No full textThe importance of DiffServ technique, based on cellular neural network (CNN), for satellite communication systems is discussed. In satellite communication systems, DiffServ policy computational capabilities are placed at the edge points. A CNN has been designed to maximize a cost functional, related to the on-board switch throughput and QoS constraints. The CNN make feasible to take the best decision for the packet to be delivered to each output satellite beam, in order to meet specific QoS constraints. The system is based on the Internet Engineering Task Force (IETE) recommendations
Next Generation Grids and Wireless Communication Networks: Towards a Novel Integrated Approach
No full textOne of the most promising trends for next generation networks is to consider an integrated approach to the communication infrastructure and the processing layer. In particular, the introduction of broadband and reliable wireless networks allows the interaction of a huge number of devices all creating a single network. On the other hand, the grid paradigm is considered as one of the most promising approach for pervasive and dynamic applications. Aim of this paper is to present a novel integrated approach between grid paradigm and wireless networks by highlighting the main advantages of their cooperation. In particular, it will be shown here how a wireless heterogeneous network can be exploited for implementing a pervasive and dynamic grid (mobile grid) and, on the other hand, a mobile grid allows the optimization of the communication infrastructure. The integrated approach can be an effective method for solving applications, such as emergency management, where a huge amount of data derived from a wireless infrastructure needs to be processed efficiently and adaptively, and the traffic flow in the wide area wireless networks needs to be coordinated and optimized
QoS provisioning in GEO satellite with onboard processing using predictor algorithms
No full textRecently, IP satellite networks have attracted considerable interest as a technology to deliver high-bandwidth IP-based multimedia services to nationwide areas. In particular, IP satellite networks seem to be one of the most promising technologies for connecting users in rural areas, where a wired high-speed network (e.g., xDSL) is not foreseen to be used. However, one of the main problems arising here is to guarantee specific quality of service constraints in order to have good performance for each traffic class. Among various QoS approaches used in the Internet, recently the DiffServ technique has become the most promising solution, mainly for its scalability with respect to the IntServ approach. Moreover, in satellite communication systems, DiffServ computational capabilities are placed at the edge points, reducing the implementation complexity of the satellite onboard equipment. This article deals with the problem of QPS provisioning for packet traffic by considering some resource allocation schemes, including bandwidth allocation techniques and priority-driven onboard switching algorithms. As to the first aim, the proposed technique takes advantage of proper statistical traffic modeling to predict future bandwidth requests. This approach,takes into consideration DiffServ-based traffic management to guarantee QoS priority among different users. Moreover, the satellite onboard switching problem has been addressed by considering a suitable implementation of the DiffServ policy based on a cellular neural network
- …
