Sergio Takeo Kofuji

A Palm Tree Antipodal Vivaldi Antenna With Exponential Slot Edge for Improved Radiation Pattern

This letter presents an Exponential Slot Edge Antipodal Vivaldi Antenna (ESE-AVA), with improved radiative features as compared to the conventional Antipodal Vivaldi Antenna (AVA) design. It extends the low-end bandwidth limitation, mitigates the side and back lobe levels, corrects squint effect, and increases its main lobe gain. In order to confirm those features, a comparative study among the ESE-AVA, the low directivity conventional AVA and two popular modifications, regular slot edge (RSE) and the tapered slot edge (TSE) AVA is performed. A comparison between AVA and the proposed ESE-AVA at 6 GHz shows an improved gain of 8.3 dB, -15.5 dB of Side Lobe Level (SLL), and 0 degrees of main lobe squint (MLS), in contrast with 5 dB of gain, - 5 dB of SLL, and 5 degrees of MLS in the conventional AVA. By comparing the ESE-AVA with RSE-AVA and TSE-AVA, it was observed that its notches in exponential shape, similar to open the main radiator, besides mitigating the SLL also directs the E-fields distributions towards the main lobe. It reflects into a main lobe gain improvement.

Using PARBIT to Implement Partial Run-Time Reconfigurable Systems

Field Programmable Gate Arrays (FPGAs) can be used to implement partial run-time reconfigurable (RTR) systems. A tool called PARBIT has been developed that transforms FPGA configuration bitstreams into partial bitstreams. With this tool it is possible to define a partial reconfigurable area inside the FPGA and download it into a specified region of the FPGA device. This paper presents PARBIT, the methodology used to design the partial RTR system, and three application examples.

Enabling Future Internet Architecture Research and Experimentation by Using Software Defined Networking

Internet core protocols were designed in the seventies and after four decades and a huge success, most of that initial design is still in place. As stated by Moores law, current digital devices offer a huge processing capacity when compared to the computational resources of the early Internet. Moreover, physical links, wired or not, offer great connectivity and high throughput capacity. New applications bring a new set of requirements that the Internet is not able to satisfy in a proper way. The Internet architecture must be reviewed and several research groups are engaged in this design. Software Defined Networking (SDN), currently materialized in OpenFlow, represents an extraordinary opportunity to rethink computer networks, enabling the design and deployment of a future Internet. This paper presents SDN based technologies available, describes some research initiatives and discusses how the research community can use them to shape future Internet architecture.

Overcoming the GPU memory limitation on FDTD through the use of overlapping subgrids

The method Finite Difference Time Domain (FDTD) is widely used in electromagnetic simulations. Since this method is a data intensive and computation intensive problem, there are a lot of initiatives to improve the scalability and the performance of the FDTD. Specifically the use of GPU to accelerate the FDTD is in focus, which has a good cost-benefit, offering a speedup of hundreds of times if compared to the traditional CPU computation. Nevertheless, the current implementations of FDTD in GPU need GPU devices with memory capacity to allocate the roll data needed for the simulation, which in many cases could require additional investments to increase the domain of the simulation. This work proposes a solution of FDTD over GPU that uses overlapping subgrids to increase the domain of the FDTD simulation through the use of CPU memory. The redundancy of the overlapping subgrids is used to minimize the memory traffic between GPU and CPU, increasing the performance. Tests of performance show that the solution combines the power of GPU with the memory facility of the CPU, allowing the accomplishment of simulations that require more memory than what is offered by the GPU device at a damaging performance cost lower than 10%.

Semantics-based grid resource management

Scheduling parallel and distributed applications efficiently onto grid environments is a difficult task and a great variety of scheduling heuristics have been developed aiming to address this issue. A successful grid resource allocation depends, among other things, on the quality of the available information about software artifacts and grid resources. In this paper, we propose a semantic approach to integrate selection of equivalent resources and selection of equivalent software artifacts in order to improve the schedule of resources suitable for a given set of application execution requirements. We also describe a prototype implementation of our approach based on the Integrade grid middleware and experimental results that indicate its benefits.

Defining and exploring a grid system ontology

This work introduces a generic and extensible grid system ontology and presents an approach to explore it in different grid scenarios.

On the analysis of multicast traffic over the Entity Title Architecture

New applications bring a new set of requirements that the Internet is not able to satisfy in a proper way. Internet architecture must be reviewed and researchers from all over the world are engaged in the design of a new Internet. Software Defined Networking (SDN), which is materialized in OpenFlow, represents an extraordinary opportunity to rethink computer networks. In this paper, taking advantage of SDN and the concepts of our previous work regarding the Entity Title Model, we present a proof of concept OpenFlow based implementation of the Entity Title Architecture. It is a clean slate network architecture for future networks where multicast and mobility are seamlessly provided. By using this implementation, we describe some experiments conducted and present a comparison between a video application implemented first, using the TCP/IP stack and then using our architecture focusing on its multicast capabilities and by consequently reducing bandwidth consumption. The results presented in this paper show that this consumption near the source by using our architecture remains constant while using TCP/IP it increases monotonically.

Horizontal Address Ontology in Internet Architecture

The ontology is used in different areas of computer systems for the explicit representation of conceptualizations, but there are few studies on the application of ontology in the intermediate and lower layers of computer networks. This paper extend the studies on ontology for the network and transport layers of the TCP/IP architecture, to address the human needs that demands technological requirements for the distributed systems. These systems have to address hosts, users and applications. This work presents one proposal to the horizontal addressing in the Internet architecture to collaborate in the improvement of distributed systems.

Distributed Systems Ontology

Applications in distributed systems, have increased their complexity and demands of new requirements, since the TCP/IP design, e.g. requirements for mobility, security, QoS and throughput. The access technologies also have a history of continuous development, with the increase of its capacity and new transmission medium. This evolution in applications and new access technologies have not been followed by significant development in the main protocols of the layers 3 and 4 in the Internet architecture, as the IP, TCP and UDP. This study shows ontological deficiencies in the Internet architecture in supporting new applications requirements and proposes improvements for the next generation Internet, based on the applications needs.

Horizontal Addressing by Title in a Next Generation Internet

In this work in progress, a new proposal is introduced for Internet horizontal addressing through the unification of application, host, and user addresses in entity title. With this unification it is possible the host addressing in Internet without IP use, as well as the routing of applications without the use of TCP, UDP, or SCTP ports. For so, it is proposed to create one Domain Title Service in Internet architecture to enable the addresses unification and that the network structure can receive information about the entities’ needs, and then meet them.