The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Passive optical networks are the most promising solution for access networks. Nowadays, Gigabit passive optical networks are very popular for Internet services providers. These networks have currently been limited by transmission speeds (up to 2.5 Gbit/s in downstream) which is not sufficient for all services (such as 4k video transfer etc.) because this speed is shared with all users in the network...
HPC systems have shifted to burst buffer storage and high radix interconnect topologies in order to meet the challenges of large-scale, data-intensive scientific computing. Both of these technologies have been studied in detail independently, but the interaction between them is not well understood. I/O traffic and communication traffic from concurrently scheduled applications may interfere with each...
Task mapping is an important problem in parallel and distributed computing. The goal in task mapping is to find an optimal layout of the processes of an application (or a task) onto a given network topology. We target this problem in the context of staging applications. A staging application consists of two or more parallel applications (also referred to as staging tasks) which run concurrently and...
Stream processing applications continuously process large amounts of online streaming data in real-time or near real-time. They have strict latency constraints, but they are also vulnerable to failures. Failure recoveries may slow down the entire processing pipeline and break latency constraints. Upstream backup is one of the most widely applied fault-tolerant schemes for stream processing systems...
This paper presents the design foundations of an agile resource management (RM) framework for the fifth generation (5G) radio access network (RAN) by describing essential building blocks (BBs). Overall, the presented RM framework provides holistic RM solutions that consider and exploit the novel aspects of 5G systems, such as, diverse service requirements, co-existence of multiple air interface (AI)...
In a few years, ultrasound research platforms, also known as open scanners, have become a unique tool for the experimental activities of ultrasound labs. A number of advanced research platforms, designed according either to the software-or to the hardware-based approach, is now available. In this paper, the criteria followed in the recent development of ULA-OP 256, a 256-channel research scanner,...
This paper focuses on the resource allocation problem with equality and inequality constraints in a fixed weight-balanced directed or undirected network. Moreover, we propose a fully decentralized subgradient algorithm with event-triggered for solving above resource allocation problem based on first-order discrete-time multi-agent systems. Where each agent only communicates with its neighbors and...
In topology representations such as maps, carbon nanotubes, and cellular networks, neighboring cells are assigned different exclusive colors to represent different characteristics. In the previous research, based on the fourcolor theorem, an algorithm that can allocate exclusive channels among neighbors using only four channels in a polygonal cluster sensor network is proposed. The performance of...
This paper studies a distributed dynamic resource allocation problem for a multi-agent network with a strongly connected digraph, which has increased an equality constraint for individual node requirement from the point of dynamic prediction horizon. Each agent at each prediction horizon in the network is associated with a local resource and a quadratic convex cost function. The goal is to minimize...
This paper explores the potential of utilizing approximate system load information to enhance work stealing for dynamic load balancing in hierarchical multicore systems. Maintaining information about the load of a system has not been extensively researched since it is assumed to introduce performance overheads. We propose SWAS, a lightweight approximate scheme for retrieving and using such information,...
A resource allocation scheme consisting of joint assignment of routing, wavelength and time-slot is proposed to construct different channels in software-defined optical networks secured by quantum key distribution (QKD). Security level is considered by key-updating period.
The Abstraction and Control of Traffic Engineered Networks (ACTN) defines the requirements, use cases, and an SDN-based architecture, relying on the concepts of network and service abstraction, detaching the network and service control from the underlying data plane. The architecture encompasses Physical Network Controllers (PNCs), responsible for specific technology and administrative domains, orchestrated...
This work is focused on the characterization of the traffic allocated in Elastic Optical backbone networks when different dynamic traffic profiles are generated. Extensive simulations are done to statistically model the real-time traffic carried by this kind of networks. Well known topologies such as NSFNet and US_Backbone are considered as well as different parameters applied to the traffic generation...
Enterprise Networking (EN) services are source of high revenues for carriers. However, the traditional way of providing and selling those to enterprise and business customers is ossified and unsatisfactory for users. High prices, static connections and slow time to provision, make enterprise users doubtful about whether guaranteed connectivity is worth the price and push them to look for alternative...
Multi-path allocation has been proposed as a simple way to achieve traffic protection in different networking domains. In this work dual-path allocation is proposed for Elastic Optical Networks (EON) assuming dynamic offered traffic, and its performance is quantified by simulation. Indeed, dual-path allocation is compared with partial dedicated path protection assuming different scenarios. In addition...
Resonant switched capacitor dc-dc converter designs are commonly optimized based on flying capacitance constraints. However, for an actual circuit design, the total available capacitance is further constrained by the need for bypass capacitance at the input and output nodes. This work finds expressions for the voltage ripple and develops a method to optimize the allocation of bypass capacitance so...
Modern 5G network are becoming denser and more agile in terms of deployment options. The average throughput and overall capacity of 5G networks are continuously growing by using variety of new solutions. However, backhaul technologies for mobile network are either low capable or inconvenient for dense deployment. In this paper, we propose a new design for converged 5G backhaul based on improved passive...
Service chaining composed of several different virtual network functions (VNFs) constitutes a use case of Network Functions Virtualization (NFV). In a conventional method, the optimal allocation of VNFs and logical paths was resolved by using integer linear programming. However, because the approach did not consider that the required resources of each service differ, the residual resources of the...
This paper presents an architecture for digitally managing dc power distribution within a building using a network model, a system for simulating specific systems, and results from initial use of the model. The architecture implements the Local Power Distribution model [7] based on networks of nanogrids, with local prices as the mechanism for determining the direction, magnitude, and timing of power...
Orchestrating a service or resources across multiple administrative domains requires three main high level steps of operation: i) capability detection of other domains ii) placement of the service request across the domains iii) assurance that the service is functioning within the acceptable bounds of the service level agreement (SLA). This paper focuses on the assurance step; in particular, we present...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.