Monitoring large computer networks often involves aggregation of various sorts of data that are distributed across network components. Finding extreme values, counting discrete observations or computing an average or a sum of some parameter values are typical examples of such "background" activities that provide input to monitoring systems. Another aspect of network management is fast and reliable information dissemination, like propagation of alarm signals.

This paper describes the recently released DREAM (Distributed Resource Evolutionary Algorithm Machine) framework for the automatic distribution of evolutionary algorithm (EA) processing through a virtual machine built from large numbers of individual machines linked by standard Internet protocols. The framework allows five different user entry points which depend on the knowledge and requirements of the user. At the highest level, users may specify and run distributed EAs simply by manipulating graphical displays. At the lowest level the framework turns becomes a P2P (Peer to Peer) mobile agent system, that may be used for the automatic distribution of a class of processes including, but not limited to, EAs. 1

In this paper we address the problem of maintaining integrity in the presence of malicious peers in a large class of epidemic-style protocols. This class includes membership management, information dissemination and proactive aggregation. We present solutions to the problems of identifying non-cooperating (malicious) nodes and removing them from the system. Our solutions are fully decentralized other than requiring an offline certificate authority to bind identity information to joining entities. We also present empirical evidence to illustrate the performance of our solutions.

This paper describes a novel tool for running distributed experiments on the Internet. The possible applications include simple load balancing, parallel evolutionary computation, agent-based simulation and artificial life. Our environment is based on cutting-edge peer-to-peer (P2P) technology. We demonstrate the potentials of the framework by analyzing a simple distributed multistart hillclimber application. We present theoretical and empirical evidence that our approach is scalable, effective and robust.

The Internet, which is becoming a more and more dynamic, extremely heterogeneous network has recently became a platform for huge fully distributed peer-to-peer overlay networks containing millions of nodes typically for the purpose of information dissemination and file sharing. This paper targets the problem of analyzing data which are scattered over a such huge and dynamic set of nodes, where each node is storing possibly very little data but where the total amount of data is immense due to the large number of nodes. We present distributed algorithms for effectively calculating basic statistics of data using the recently introduced newscast model of computation and we demonstrate how to implement basic data mining algorithms based on these techniques. We will argue that the suggested techniques are efficient, robust and scalable and that they preserve the privacy of data.

This paper describes a novel peer-to-peer (P2P) environment for running distributed Java applications on the Internet. The possible application areas include simple load balancing, parallel evolutionary computation, agent-based simulation and artificial life. Our environment is based on cutting-edge P2P technology. We introduce and analyze the concept of long term memory which provides protection against partitioning of the network. We demonstrate the potentials of our approach by analyzing a simple distributed application. We present theoretical and empirical evidence that our approach is scalable, effective and robust.

In addition to the popular structured peer-to-peer (P2P)

Networking solutions which do not depend on central services and where the components posses only partial information are robust and scalable but obtaining global information like e.g. the size of the network raises serious problems, especially in the case of very large systems. We consider a specific type of fully distributed peer-to-peer (P2P) environment with many interesting existing and potential applications. We suggest solutions for estimating network size and detecting partitioning, and we give estimations for the time complexity of global search in this environment. Our methods rely only on locally available (but continuously refreshed) partial information. Theoretical analysis and simulation results are also presented.

This paper describes a novel peer-to-peer (P2P) environment for running distributed Java applications on the Internet. The possible application areas include simple load balancing, parallel evolutionary computation, agent-based simulation and artificial life. Our environment is based on cutting-edge P2P technology. We introduce and analyze the concept of long term memory which provides protection against partitioning of the network. We demonstrate the potentials of our approach by analyzing a simple distributed application. We present theoretical and empirical evidence that our approach is scalable, effective and robust.