Anthill is supported by:
|
Publications Page
The main ideas about Anthill have been published in a
few conferences and workshops. The original paper
presenting Anthill is Anthill: a Framework
for the Design and the Analysis of Peer-to-Peer Systems,
presented at the 4th European Research Seminar on Advances
in Distributed Systems (ERSADS '01), Bertinoro, Italy (May
2001). This workshop paper has been later expanded in
a conference paper ( Anthill: A
Framework for the Development of Agent-Based Peer-to-Peer
Systems), presented at the 22th International Conference
on Distributed Computing Systems (ICDCS '02), Vienna, Austria
(July 2002). An extended version of this paper has
also been published as a Technical Report of the University
of Bologna ( UBLCS-2001-09, revised August
2002).
So far, two different applications have been
implemented over Anthill:
- Gnutant is a file-sharing application.
In order to facilitate file searches, Gnutant builds
a distributed file index scattered across the nest network,
whose task is to store URLs for shared files, together with
routing information needed to navigate through the index.
The index is constructed at runtime by Gnutant ants, that
travel through the network collecting information about
new and existing files and insert this information
in the index. A short description of Gnutant is
provided in UBLCS-2001-09. A technical
report containing a complete description of Gnutant is in
preparation.
- Messor is a grid computing system aimed
at supporting the concurrent execution of highly-parallel,
time-intensive computations, in which the workload may be
decomposed into a large number of independent jobs. The computational
power offered by a network of Anthill nests is exploited
by Messor by assigning a set of jobs comprising a
computation to a dispersed set of nests. The Messor
algorithm has been described in Messor: Load-Balancing
through a Swarm of Autonomous Agents, presented at
the 1st International Workshop on Agents
and Peer-to-Peer Computing, Bologna, Italy, July
2002
The philosophy behind Anthill and its relation to the
complex adaptive system area are explained in two
workshop papers. The first paper ( Towards Self-Organizing,
Self-Repairing and Resilient Peer-to-Peer Systems,
in Proc. of the International Workshop on Peer-to-Peer
Computing, Networking 2002, Pisa, Italy, Maggio 2002)
contains the first description of Messor. The second paper
( Toward Self-Organizing, Self-Repairing
and Resilient Large-Scale Distributed Systems, in Proceedings
of the 1st International Workshop on Future Directions in
Distributed Computing, Bertinoro, Forlì,
Italy, June 2002) discusses how complex adaptive systems
may be one of the future trends of distributed computing.
JXTAnthill is discussed in Francesco Russo's master thesis. Francesco is (now a graduated)
student who developed the JXTA runtime environment.
Messor: Load-Balancing
through a Swarm of Autonomous Agents
|
Alberto
Montresor, Heing Meling and Ozalp Babaoglu
|
[pdf] [ps.gz]
|
In Proceedings of the 1st International
Workshop on Agents and Peer-to-Peer Computing, Bologna,
Italy, July 2002. Also appears as Technical Report UBLCS-2002-11,
University of Bologna, Italy.
|
Abstract: Peer-to-peer (P2P)
systems are characterized by decentralized control, large-scale
and extreme dynamism of their environment. Developing applications
that can cope with these characteristics requires a
paradigm shift that puts adaptation, resilience
and self-organization as primary concerns. Complex
adaptive systems (CAS), commonly used to explain the
behavior of many biological and social systems, could be
an appropriate response to these requirements. In order
to pursue these ideas, this paper
presents Messor, a decentralized load-balancing
algorithm based on techniques such as multi-agent
systems drawn from CAS. A novel P2P grid
computing system has been designed using the Messor algorithm,
allowing arbitrary users to initiate computational tasks.
|
Towards Self-Organizing,
Self-Repairing and Resilient Large-Scale Distributed Systems
|
Alberto
Montresor, Heing Meling, Ozalp Babaoglu
|
[pdf] [ps.gz]
|
In Proceedings of the 1st International
Workshop on Future Directions in Distributed Computing,
Bertinoro, Forlì (Italy), June 2002. Also appears
as Technical Report UBLCS-2002-10, University of
Bologna, Italy.
|
Abstract: The paper itself is an
extended abstract.
|
Towards Self-Organizing,
Self-Repairing and Resilient Peer-to-Peer Systems
|
Alberto
Montresor, Heing Meling, Ozalp Babaoglu
|
[pdf] [ps.gz]
|
In Proceedings of the International
Workshop on Peer-to-Peer Computing, Networking 2002,
Pisa, Italy, May 2002. Also appears as Technical Report
UBLCS-2002-09, University of Bologna, Italy.
|
Abstract: Peer-to-peer (P2P)
systems are characterized by decentralized control, large
scale and extreme dynamism of their operating environment.
Developing applications that can cope with these
characteristics requires a paradigm shift,
placing adaptation, resilience and self-organization as
primary concerns. In this note, we argue that complex
adaptive systems (CAS), which have been used to
explain certain biological, social and economical
phenomena, can be the basis of a programming
paradigm for P2P applications. In order to pursue this
idea, we are developing Anthill, a framework to support
the design, implementation and evaluation
of P2P applications based on ideas such as
multi-agent and evolutionary programming borrowed
from CAS.
|
Anthill: A
Framework for the Development of Agent-Based Peer-to-Peer
Systems
|
Ozalp
Babaoglu, Hein Meling and Alberto Montresor
|
[pdf] [ps.gz]
|
In Proceedings of the 22th International
Conference on Distributed Computing Systems (ICDCS '02),
Vienna, Austria, July 2002. Also appears as Technical Report
UBLCS-2001-09, University of Bologna, Italy.
|
Abstract: Recent peer-to-peer
(P2P) systems are characterized by decentralized control,
large scale and extreme dynamism of their operating environment.
As such, they can be seen as instances of complex adaptive
systems (CAS) typically found in biological
and social sciences. In this paper we
describe Anthill, a framework to support the design,
implementation and evaluation
of P2P applications based on ideas such as multi-agent
and evolutionary programming borrowed from CAS. An Anthill
system consists of a dynamic network of peer nodes;
societies of adaptive agents travel through this
network, interacting with nodes and cooperating
with other agents in order to solve complex problems.
Anthill can be used to construct different classes of P2P
services that exhibit resilience, adaptation and self-organization
properties. We also describe preliminary
experiences with Anthill in implementing a file sharing
application.
|
Anthill: a
Framework for the Design and Analysis of Peer-to-Peer
Systems
|
Alberto
Montresor
|
[pdf] [ps.gz]
|
In Proceedings of the 4th European
Research Seminar on Advances in Distributed Systems,
Bertinoro, Italy, May 2001.
|
Abstract: The peer-to-peer
(P2P) paradigm for building distributed applications
has recently attracted the attention of industry and media
primarily due to the enormous success of systems such as
Napster, Gnutella and Freenet. The multitude of projects
that have been proposed based on P2P all need to
confront common problems including security,
reliability and routing. Unfortunately, traditional techniques
for dealing with these issues are not directly applicable
to P2P systems in part due to the dimensions of their scale.
In this paper, we introduce a new approach for
designing P2P applications based on the biological
metaphor of ant colonies. Furthermore, we present Anthill,
a framework supporting the development and study of new
protocols based on the P2P approach.
|
|