A. R. Ashok Kumar

4-4, 1-4: Architecture for Data Center Network Based on IP Address Hierarchy for Efficient Routing

Architecture plays an important role in the design of Data Center Networks (DCN). Designs for DCN are to be scalable, robust and efficient. There are many designs proposed in recent years where routing is performed using location information of the server. These designs solve scalability problem of IP and Ethernet with additional overhead of determining and maintaining location information of the server. In this paper, we propose a new architecture named, four-four, one-four architecture (4-4, 1-4 Architecture) that has evolved from the format of IP address. Addressing and interconnection used in our design eliminate the complexities in the previous designs such as constructing addresses based on location information. Two major benefits - reduction of entries in routing table and routing based on location information - are achieved through our design with minimum complexity. The first advantage is due to the design combining servers with common prefixes at each level using hierarchical format of IP address. The second advantage is due to the IP address assigned to servers and switches acting as location indicator. This helps in faster routing where packet forwarding is done based on the bits of IP addresses. Further, the proposed architecture meets major design requirements for data center networks such as load balancing and energy conservation.

Recombinant Receptor-Binding Domain of Diphtheria Toxin Increases the Potency of Curcumin by Enhancing Cellular Uptake

Diphtheria toxin (DT) binds to a specific cell surface receptor, gets internalized, and causes cytotoxicity through its catalytic domain. The toxicity of DT is used in several therapeutic molecules. Here, we have exploited the receptor-binding ability of DT to increase cellular uptake of curcumin, a hydrophobic molecule with low bioavailability and cellular uptake. We have expressed only the receptor-binding domain of DT (RDT) in Escherichia coli. Purified RDT binds to the receptor with an affinity equivalent to that of full-length DT. It also binds to curcumin forming a curcumin-RDT complex, and this increases the fluorescence intensity and fluorescence lifetime of curcumin. The curcumin-RDT complex binds to the receptor and associates with human glioblastoma cells (U-87 MG) expressing the receptor. The cellular uptake of curcumin is higher for the curcumin-RDT complex than curcumin alone. This increase in uptake enhances the antiproliferative effect of curcumin and induces apoptosis of these cells even at a lower dose.

NS3 Simulator for a Study of Data Center Networks

The increasing complexity and sophistication of the applications deployed on Data Center Network (DCN) demanded new features and greater performance from the DCN. This resulted in many designs addressing various challenges such as cost, performance, reliability, scalability, security and energy. One major challenge a designer often faces is the realization of their proposed design or realization of the existing designs for comparison. Although proto-typing is a better choice but it does have certain limitation and is very complex and expensive. Hence, Simulation is considered as an alternative to the prototyping. In this paper, we present a case study of using Network Simulator 3 (NS3) for realization of various architectures for DCN and study their performance. The information we provide includes realization of the most popular designs for DCN and tools available with NS3 to study their performance. Our effort is to make it easy for a beginner to build popular designs for DCN and study their performance using NS3.

DCell-IP: DCell Emboldened with IP Address Hierarchy for Efficient Routing

The increasing complexity and sophistication of data center applications demands new features in the data center designs. With the deployment of large range of applications, there is a demand for low latency and high throughput from the underlying network infrastructure. This resulted in many Data Center Network (DCN) designs. There are class of designs for DCN called server-centric-networks, where routing is done by server rather than intermediate switches. BCube and DCell are two such designs. These designs use source routing for communication. The symmetry and hierarchy in their design enable source to compute the entire path to the destination. The current implementation of DCell uses addresses other than IP address for addressing the servers and switches. In this paper, we provide a new implementation for DCell called DCell-IP using IP address hierarchy. Since IP addresses are also symmetric and hierarchical, we eliminate the need for using new scheme for addressing servers and intermediate switches. This also eliminates the need for translating design specific addresses to IP addresses during the routing.

Experimental investigation of interface deformation in free surface flow of concentrated suspensions

It is well known that during the free surface flow of concentrated suspension of non-colloidal particles, the suspension-air interface becomes highly corrugated. This surface corrugation changes the interfacial area which could have important implications in various applications involving heat and mass transfer across the interface. Surface corrugation in free surface flow has been studied in the past, but its mechanism is not fully understood. We report detailed experiments on quantitative measurement of the surface deformation of concentrated suspension of non-colloidal particles in open channel flow. The motion and location of the interface and the velocity field of the bulk flow beneath the free surface were measured using the particle image velocimetry technique. Experiments were performed to study the effect of particle size, particle concentration, and viscosity of suspending fluid on the corrugation. The interface fluctuation was found to increase linearly with the flow rate. The deformation of th...

Simple, efficient location-based routing for data center network using IP address hierarchy

Summary Increasing demand and sophistication of applications deployed on data centers resulted in various designs for data center networks (DCNs). One of the major challenges in the design of DCNs is the design of routing protocol that scales to support millions of servers that a typical DCN hosts. Many alternative routing protocols are proposed to overcome the scalability problem of conventional routing protocols such as Open Shortest Path First and Routing Information Protocol. These alternative protocols that use topology characteristics of DCN are broadly classified as source routing and location-based routing. In the process of fixing the scalability problem, these protocols introduced additional complexities such as large network control overhead and reprogramming of network elements. The extra control overhead in these protocols is the result of their effort to determine the relative location of the end hosts in a given topology. Further, existing location-based routing is not entirely location based and covers only the latter half of a route. In our work, we present a new location-based routing based on IP address hierarchy that (a) does not need any additional network control plane and management planes, (b) deployable on proven network technologies, and (c) covers entire path of the route. We establish the correlation between topology design and address assignments that helps determining the location of an end host directly from the address assigned to it. We demonstrate our proposed location-based routing on an existing proven architecture for DCN, BCube-IP and on our proposed architecture 4-4, 1-4. We give proper justification for proposing 4-4, 1-4, a better design for our proposed location-based routing. Copyright

Greening 4-4, 1-4 Data Center Network: A Greedy Approach for Finding an Energy Efficient Sub-network

Data centers are over provisioned to handle traffic surges. However, various studies of data center traffic regarded this upsurge as a rare event and shown that the resources of data center are underutilized. Hence, there is a need to conserve energy by providing control knobs that turn the resources of data center on/off according to the traffic condition. In this paper, we study the ability of 4-4, 1-4 data center network design for energy conservation. Given a set of current flows, we propose a greedy approach to find sub-network that can accommodate current set of flows and switch off rest of the network to conserve energy. We simulated the proposed method using network-simulator (NS3) and compared the performance with Elastic Tree. The simulation results shown performance of 4-4, 1-4 design is better than Elastic Tree in terms of energy conservation, packet delivery ratio and delay. As an extension, we also compared the support from routing protocols: source routing and location based routing, in designing energy conservation methods.

BCube-IP: BCube with IP Address Hierarchy

BCube and DCell propose data transfer using source routing for data center networks (DCNs). One potential problem with their approach is the use of two different address spaces, one for identifying end hosts and another for routing. In this paper, we propose a variant of BCube called BCube-IP based on an IP address hierarchy. BCube-IP overcomes the limitations of using two different address spaces in BCube. Along with the improved performance of source routing, we demonstrate the use of location-based routing for data transfer in BCube-IP.