The Ninja architecture for robust Internet-scale systems and services

This paper provide provide wide range of services and mechanism for access those mechanism via heterogeneous devices. The services set include: robustness, scalability, distributed Internet services. The architecture assumes the four basic components:
* powerful workstation cluster environments with a software platform that simplifies scalable service construction;
* units, which are the devices by which users access the services;
* active proxies, which are transformational elements that are used for unit- or service-speci®c adaptation;
* and paths, which are an abstraction through which units, services, and active proxies are composed.

Resilient Workload Manager Framework

"In data centers hosting scaling Internet applications, operators face the tradeoff dilemma between resource efficiency and Quality of Service (QoS), and the root cause lies in workload dynamics. In this paper, we address the problem with the design of Resilient Workload Manager (ROM). ROM explicitly segregates base workload and trespassing workload, the two naturally different components in application workload, and manages them separately in two resource zones with specialized optimization techniques.

As a comprehensive workload management framework, ROM covers workload, data, resource, and Quality of Service of the target applications. It features a fast workload factoring algorithm for distributing incoming application requests, not only on volume but also on content, between the two resource zones; integrated two-dimensional workload shaping, resource planning, and request dispatching schemes for efficient utilization of base workload zone resource; and a simple and high-performance system architecture for dynamic provisioning in trespassing workload zone. Through extensive evaluation, we showed ROM can achieve resource efficiency (e.g., 54.9% server saving) guarantee QoS (based on client-side perceived service quality), reduce data access overhead in the trespassing workload zone during peak load (up to two orders of magnitude), and be adaptive at processing speed (running faster at peak load periods than at regular periods)."

Amazon distriburted services

Amazon is one of the largest e-commerce companies which provide different services for various website around the world using its distributed servers. These servers are proven to errors, faults, and failures which necessitates reliability, consistency and flexibility to reconfigure and keep persistent state for the data hosted by those servers. Dynamo, incrementally scalable depend upon the current workloads, provide reliability and availability for major Amazon services. Although versioning and conflict resolutions mechanism are used to provide consistency still it undermines it in some scenarios. From developer point of view, porting and new development a bit more complex because of Dynamo's consistency model and reconciliation logic. Also, it uses Full Membership model where each peers have knowledge of every other peer as for as stored component is concerned. This Full membership model limit scalability because the routing tables are developed by continue gossiping which produce overhead. The problem could be solved by extending it with Distributed DHTs or P2P Systems (which is under consideration of our research).

Location aware DHT

"Place Lab: Device Positioning Using Radio Beacons in the Wild" - is an application API which allows any wireless device to listen to fixed beacon provider for her position estimation. Leveraging this API with Peer could be helpful in making location aware DHTs. Prefix Hash Three (PHT) used Place lab in building location aware DHT. The case study from Sylvia decouples application developed from DHT. A good point to note for while most of applications demand refined and optimized overlay for its QoS and performance requirements.

Information dessimnation in Social Nets

The Java applet shows the self-managed information dessimination in social net with monitoring metrics (at the right). This could be a good idea to implement a online-benchmarking application with user input to determine different quality and performance parameters. Since, information are disseminated in self-configured way, it could be used for monitoring resources, services including security, etc. The interesting question could be how the collect or disseminate information for productive activity.

PageRank, LinkRank, ComRank, WikiFactor, PageFactor, ComFact

PageRank: This is an algorithm which ranks a web-page among set of web-page on WWW by considering a large set of different variables.
LinkRank: is a method of quantifying the modularity of social links in directed network. The original paper assumes modularities in un-directed networks and optimizes it for directed networks.
WikiFactor: "A new metric is introduced, inspired by the Hirsch {\it h-index}, to measure the impact of a wiki site. A table of wikiFactors is presented for a number of wikis, in particular those oriented towards scientific topics. The wikiFactor is defined as the number of web pages, wF, that have had $\ge 1000$wF visits."

Referring to these links one reasonable question would be haw to rank communities, services, privacy settings in sub-graphs or along the whole graph. But what one could buy out of this? Well, considering services provisions and service management, one should provide provide load balancing, some what deterministically routing, or have surgically prune out bad guys (cheaters in MMOG, attackers, or selfish guys).

@ LinkRank: One can predict link, LinkPrdict, by predicting previously un-observed relationship and hence behavior. There are many exciting applications of this particular area of network science. Most research in the area of link prediction has been restricted to scoring based on a single measure within network topologies. While the research considers new measure and placing existing measures in the context of a machine learning task. "We are also casting the problem as a high class imbalance task."

CFP: Cloud Computing

Call for Papers

IEEE Network magazine - Special Issue on Cloud Computing

http://dl.comsoc.org/livepubs/ni/info/cfp/cfpnetwork711.htm

Background

Cloud Computing is a recent trend in information technology
and scientific computing that moves computing and data away
from desktop and portable PCs into large Data Centers.
Cloud computing is based on a model for enabling convenient,
on-demand network access to a shared pool of configurable
computing resources (e.g., networks, servers, storage,
applications, and services) that can be rapidly provisioned
and released with minimal management effort or service
provider interaction. Cloud Computing opens new perspectives
in internetworking technologies, raising new issues in the
architecture, design and implementation of existing networks
and data centers. The relevant research has just recently
gained momentum and the space of potential ideas
and solutions is still far from being widely explored.


Scope

This special issue of the IEEE Network Magazine will feature
articles that discuss networking aspects of cloud computing.
Specifically, it aims at delivering the state-of-the-art
research on current cloud computing networking topics, and
at promoting the networking discipline by bringing to the
attention of the community novel problems that must be
investigated.
Areas of interest include, but are not limited to:

Data center architecture
Server interconnection
Routers (switching technology) for data center deployment
Centralization of network administration/routing
Energy-efficient cloud networking
Low energy routing
Green data centers
Measurement-based network management
Traffic engineering
Network anomaly detection
Usage-based pricing
Security issues in clouds
Secure routing
Security threats and countermeasures
Virtual network security
Virtual Networking
Virtualized network resource management
Virtual cloud storage
Futuristic topics
Interclouds
Cloud computing support for mobile users


Manuscript Submission

Authors should submit their manuscript electronically in PDF
format by email to all the guest editors according to the
timetable. Authors are encouraged to register their papers by
submitting the paper abstract, the paper title, authors and
keywords by the corresponding deadline. Prospective authors
must prepare their original submissions in accordance with
the IEEE Network guidelines to authors,
http://dl.comsoc.org/livepubs/ni/info/authors.html. Articles
should not exceed 4500 words, be tutorial in nature, and
should be written in a style comprehensible to readers
outside the specialty of the article. The title page should
include the paper title, authors and keywords. Figures
and tables should be limited to a combined total of six.
All submissions will be reviewed based on
technical merit and relevance.

Schedule

Abstract submission: January 9, 2011
Deadline for paper submission: January 15, 2011
First round of reviews: February 28, 2011
Revisions due: March 15, 2011
Author notification: March 26, 2011
Publication materials due: May 1, 2011
Publication date: July, 2011


Guest Editors

Swami Sivasubramanian
Amazon, USA
swami@amazon.com

Dimitrios Katsaros
University of Thessaly, Greece
dkatsar@inf.uth.gr

George Pallis
University of Cyprus, Cyprus
gpallis@cs.ucy.ac.cy

Athena Vakali
Aristotle University of Thessaloniki, Greece
avakali@csd.auth.gr

Freenet Installation Error

Freenet source code can be build with '> ant -f freenet_ext/build.xml' or 'sudo ant -f freenet_ext/build.xml'.

P2P and applications

Some applications of interest and could be tested for P2P application and service layer:

Open source code available in Ubuntu - resource monitoring, etc
> Ping6
> V4Ping

> RadvD - Router advertisement daemon and could be configured for new peer advertisements, etc

> UdpEchoClient/Server - Echo protocol (see http://en.wikipedia.org/wiki/Echo_protocol
for a brief overview
> UdpClient/Server

> UdpTraceClient - ns3 OnOffApplication which implements UDP based application, :)
> OnOffApplication

Parallelizing overlay-routing or parallelizing unicast messages for improving FreeNet performance?

How to reduce messages and improve performance? Is it possible to improve by parallelizing a variety of overlay routing? What could be the gain (for MMOG and FreeNet, for instance) over parallel multicast messages?

"that parallelizing a variety of overlay routing algorithms using multi-destination multicasting instead of parallel unicast messages results in significantly reduced message traffic on both edge and internal links. In structured overlays, this message reduction occurs for a variety of operations such as joins, routing table maintenance, and application lookups. In general, latency behavior and operational semantics are retained." Further information about the study could be found at this link.

GC10 NGN and Services

[GC10 - CSSMA] CFP - IEEE Globecom 2010 - Communications Software, Services and Multimedia

IEEE Globecom 2010 - Communications Software, Services and Multimedia Applications Symposium
Dec 6 - 10, 2010
Miami, FL USA
http://www.ieee-globecom.org/2010

The Communications Software, Services and Multimedia Applications
Symposium covers challenges and advances for service delivery and
management in fixed and mobile communication networks. These topics
are particularly relevant for researchers, developers and industries
in the areas of networking and services covered by many Technical
Committees. The symposium will follow GC2010 instructions for
paper submission, review, and session construction. Papers offering
novel research contributions in any aspect of Communications Software
and Services are solicited for submission to the symposium.

Topics of Interest

* Next Generation Services and Service Platforms
o Mobile Services and Service Platforms including IMS
o Home Network Service Platform
o VoP2P and P2P-SIP Services
o Converged Application/Communication Servers and Services
o Location-based Services
o Social Networking Communication Services
o Advanced Communication Services and Feature Interaction
* Multimedia applications and services including VoIP, IPTV, Gaming
o Multimedia delivery over wired and wireless networks
o Cross-layer optimization for multimedia service support
o Multicast, Broadcast and IPTV
o Media streaming
o Peer-to-Peer services
* Software and Protocol Technologies for advanced service support
o Web Services and distributed SW technology
o Distributed systems and applications, including Grid Services
o Peer-to-Peer technologies for communication services
o Service overlay networks
o Context Awareness and Personalization
* Network and Service Management and Provisioning
o Multimedia QoS provisioning
o Quality of Experience for End-to-End Communications
o End-to-End Quality of Service Routing algorithms
o Service Creation, Delivery, Management
o Network Management
o Virtual Home Environment
o Charging, Pricing, Business Models
o Triple Play Services
o Security and Privacy in Network and Service Management
o Service Overlay Networks
o Cooperative Networking for Streaming Media Content

Submission deadline: March 15, 2010
Notifications due: July 1, 2010
Final version due: Aug 1, 2010

For more information about IEEE Globecom 2010, please see
http://www.ieee-globecom.org/2010

Symposium Co-Chairs

John Buford, Avaya Labs Research, USA (buford at avaya.com)
Mohammad S. Obaidat, Monmouth university, USA (obaidat at monmouth.edu)
Joel Rodrigues, University of Beira Interior, Portugal (joelr at
ieee.org)
Bin Wei, AT&T Research, USA (bw at research.att.com)

Darwin: Resource Management for Application-Aware Networks

"Sophisticated multi-party applications will use many traffic streams with very different characteristics and will be network-aware so they can perform well on a variety of networks. At the same time, we see the emergence of an electronic service industry that is eager to deliver a wide variety of services to end-users. Services will range from low-level "bearer" services that transport bit streams over the network infrastructure to value-added services such as video conferencing, computing services, and data mining. Complex applications will support cooperation among multiple parties by combining video conferencing with access to large amounts of archived data, real time data streams, and distributed computing tasks. Supporting this service model and this emerging class of complex services requires innovation in a number of areas, including support for application-specific handling of traffic, sharing of resources between cooperating traffic streams, adapting quickly to changes in the network conditions and application requirements, systematic methods for balancing the constraints and priorities of services competing for network resources, and reliability and security. The CMU application-aware networking project will develop a comprehensive suite of resource management mechanisms in support of such "application-aware" networks. The project is headed by Peter Steenkiste, Allan Fisher, and Hui Zhang."