UNIVERSITY OF JYVÄSKYLÄ Resource Discovery in P2P Networks Using Evolutionary Neural Networks Presentation for International Conference on Advances in.

Slides:



Advertisements
Similar presentations
Optimal Resource Discovery Paths of Gnutella2 The IEEE 22nd International Conference on Advanced Information Networking and Applications (AINA 2008)
Advertisements

Performance in Decentralized Filesharing Networks Theodore Hong Freenet Project.
UNIVERSITY OF JYVÄSKYLÄ Chedar: Peer-to-Peer Middleware Presentation for 8 th International Workshop on Java tm for Parallel and Distributed Computing.
UNIVERSITY OF JYVÄSKYLÄ P2PRealm – Peer-to-Peer Simulator Presentation for 11 th International Workshop on Computer- Aided Modeling, Analysis and Design.
UNIVERSITY OF JYVÄSKYLÄ P2PStudio – Monitoring, Controlling and Visualization Tool for Peer-to-Peer Networks Research Presentation for PM 2 HW 2 N on 2.
UNIVERSITY OF JYVÄSKYLÄ Mobile Chedar – A Peer-to-Peer Middleware for Mobile Devices Presentation for International Workshop on Mobile Peer-to- Peer Computing.
UNIVERSITY OF JYVÄSKYLÄ Mobile Encounter Networks and Their Applications 1 st IEEE International Peer-to-Peer for Handheld Devices Workshop IEEE CCNC,
UNIVERSITY OF JYVÄSKYLÄ P2PDisCo – Java Distributed Computing for Workstations Using Chedar Peer-to-Peer Middleware Presentation for 7 th International.
UNIVERSITY OF JYVÄSKYLÄ New Topology Management Algorithms for Unstructured P2P Networks Presentation for The Second International Workshop on P2P Systems.
Peer-to-Peer and Social Networks An overview of Gnutella.
NEURAL NETWORKS Backpropagation Algorithm
UNIVERSITY OF JYVÄSKYLÄ Building NeuroSearch – Intelligent Evolutionary Search Algorithm For Peer-to-Peer Environment Master’s Thesis by Joni Töyrylä
Sogang University ICC Lab Using Game Theory to Analyze Wireless Ad Hoc networks.
LightFlood: An Optimal Flooding Scheme for File Search in Unstructured P2P Systems Song Jiang, Lei Guo, and Xiaodong Zhang College of William and Mary.
PROMISE: Peer-to-Peer Media Streaming Using CollectCast Mohamed Hafeeda, Ahsan Habib et al. Presented By: Abhishek Gupta.
Effects of Applying Mobility Localization on Source Routing Algorithms for Mobile Ad Hoc Network Hridesh Rajan presented by Metin Tekkalmaz.
UNIVERSITY OF JYVÄSKYLÄ Yevgeniy Ivanchenko Yevgeniy Ivanchenko University of Jyväskylä
Prénom Nom Document Analysis: Artificial Neural Networks Prof. Rolf Ingold, University of Fribourg Master course, spring semester 2008.
UNIVERSITY OF JYVÄSKYLÄ Power-law Networks InBCT 3.2 Peer-to-Peer communication Cheese Factory -project Researcher.
UNIVERSITY OF JYVÄSKYLÄ Chedar P2P platform InBCT 3.2 Peer-to-Peer communication Cheese Factory -project Research Assistant.
Un Supervised Learning & Self Organizing Maps Learning From Examples
UNIVERSITY OF JYVÄSKYLÄ InBCT 3.2 Peer-to-Peer communication/computation Cheese Factory -project Prof., D.Sc. (EE)
UNIVERSITY OF JYVÄSKYLÄ Topology Management in Unstructured P2P Networks Using Neural Networks Presentation for IEEE Congress on Evolutionary Computing.
Prénom Nom Document Analysis: Artificial Neural Networks Prof. Rolf Ingold, University of Fribourg Master course, spring semester 2008.
1 Maximizing Remote Work in Flooding-based P2P Systems Qixiang Sun Neil Daswani Hector Garcia-Molina Stanford University.
UNIVERSITY OF JYVÄSKYLÄ Distributed computing in peer-to-peer environment InBCT 3.2 Peer-to-Peer communication Cheese Factory -project
Chapter 10 Introduction to Wide Area Networks Data Communications and Computer Networks: A Business User’s Approach.
UNIVERSITY OF JYVÄSKYLÄ Peer-to-Peer Algorithms and Prototypes in Jyväskylä Mikko Vapa, research student Department of Mathematical Information.
Enhancing TCP Fairness in Ad Hoc Wireless Networks Using Neighborhood RED Kaixin Xu, Mario Gerla University of California, Los Angeles {xkx,
UNIVERSITY OF JYVÄSKYLÄ Resource Discovery Using NeuroSearch Presentation for the Agora Center InBCT-seminar Mikko Vapa, researcher InBCT 3.2.
UNIVERSITY OF JYVÄSKYLÄ Resource Discovery in Unstructured P2P Networks Distributed Systems Research Seminar on Mikko Vapa, research student.
Information Fusion Yu Cai. Research Article “Comparative Analysis of Some Neural Network Architectures for Data Fusion”, Authors: Juan Cires, PA Romo,
UNIVERSITY OF JYVÄSKYLÄ Topology Management Algorithms in Chedar InBCT 3.2 Peer-to-Peer communication Cheese Factory -project
UNIVERSITY OF JYVÄSKYLÄ Topology Management in Unstructured P2P Networks Distributed Systems Research Seminar on Annemari Auvinen, Research Student.
November 21, 2012Introduction to Artificial Intelligence Lecture 16: Neural Network Paradigms III 1 Learning in the BPN Gradients of two-dimensional functions:
Marcus Gallagher and Mark Ledwich School of Information Technology and Electrical Engineering University of Queensland, Australia Sumaira Saeed Evolving.
Optimization of thermal processes2007/2008 Optimization of thermal processes Maciej Marek Czestochowa University of Technology Institute of Thermal Machinery.
 C. C. Hung, H. Ijaz, E. Jung, and B.-C. Kuo # School of Computing and Software Engineering Southern Polytechnic State University, Marietta, Georgia USA.
CHAPTER 12 ADVANCED INTELLIGENT SYSTEMS © 2005 Prentice Hall, Decision Support Systems and Intelligent Systems, 7th Edition, Turban, Aronson, and Liang.
COGNITIVE RADIO FOR NEXT-GENERATION WIRELESS NETWORKS: AN APPROACH TO OPPORTUNISTIC CHANNEL SELECTION IN IEEE BASED WIRELESS MESH Dusit Niyato,
IR Techniques For P2P Networks1 Information Retrieval Techniques For Peer-To-Peer Networks Demetrios Zeinalipour-Yazti, Vana Kalogeraki and Dimitrios Gunopulos.
A Genetic Algorithms Approach to Feature Subset Selection Problem by Hasan Doğu TAŞKIRAN CS 550 – Machine Learning Workshop Department of Computer Engineering.
Evolving a Sigma-Pi Network as a Network Simulator by Justin Basilico.
Integrating Neural Network and Genetic Algorithm to Solve Function Approximation Combined with Optimization Problem Term presentation for CSC7333 Machine.
Artificial Neural Network Theory and Application Ashish Venugopal Sriram Gollapalli Ulas Bardak.
1 Exploiting locality for scalable information retrieval in peer-to-peer networks D. Zeinalipour-Yazti, Vana Kalogeraki, Dimitrios Gunopulos Manos Moschous.
Artificial Intelligence Methods Neural Networks Lecture 4 Rakesh K. Bissoondeeal Rakesh K. Bissoondeeal.
ELeaRNT: Evolutionary Learning of Rich Neural Network Topologies Authors: Slobodan Miletic 3078/2010 Nikola Jovanovic 3077/2010
Intelligent Database Systems Lab N.Y.U.S.T. I. M. Externally growing self-organizing maps and its application to database visualization and exploration.
LightFlood: An Efficient Flooding Scheme for File Search in Unstructured P2P Systems Song Jiang, Lei Guo, and Xiaodong Zhang College of William and Mary.
CS 478 – Tools for Machine Learning and Data Mining Perceptron.
CSC321 Introduction to Neural Networks and Machine Learning Lecture 3: Learning in multi-layer networks Geoffrey Hinton.
Back-Propagation Algorithm AN INTRODUCTION TO LEARNING INTERNAL REPRESENTATIONS BY ERROR PROPAGATION Presented by: Kunal Parmar UHID:
UNIVERSITY OF JYVÄSKYLÄ UBIWARE Nokia Research Center Case Meeting on Mikko Vapa, research student P2P Computing Group Department of Mathematical.
Design of a Robust Search Algorithm for P2P Networks
School of Electrical Engineering &Telecommunications UNSW Cost-effective Broadcast for Fully Decentralized Peer-to-peer Networks Marius Portmann & Aruna.
Chapter 6 Neural Network.
Joe Bradish Parallel Neural Networks. Background  Deep Neural Networks (DNNs) have become one of the leading technologies in artificial intelligence.
Distributed Caching and Adaptive Search in Multilayer P2P Networks Chen Wang, Li Xiao, Yunhao Liu, Pei Zheng The 24th International Conference on Distributed.
An Evolutionary Algorithm for Neural Network Learning using Direct Encoding Paul Batchis Department of Computer Science Rutgers University.
A Presentation on Adaptive Neuro-Fuzzy Inference System using Particle Swarm Optimization and it’s Application By Sumanta Kundu (En.R.No.
Evolutionary Computation Evolving Neural Network Topologies.
Supervised Learning in ANNs
Fall 2004 Perceptron CS478 - Machine Learning.
Real Neurons Cell structures Cell body Dendrites Axon
On Growth of Limited Scale-free Overlay Network Topologies
Capabilities of Threshold Neurons
The Naïve Bayes (NB) Classifier
Javad Ghaderi, Tianxiong Ji and R. Srikant
复杂网络可控性 研究进展 汪秉宏 2014 北京 网络科学论坛.
Presentation transcript:

UNIVERSITY OF JYVÄSKYLÄ Resource Discovery in P2P Networks Using Evolutionary Neural Networks Presentation for International Conference on Advances in Intelligent Systems – Theory and Applications (AISTA 2004) Mikko Vapa, researcher student Agora Center With co-authors Niko Kotilainen, Annemari Auvinen, Heikki Kainulainen and Jarkko Vuori

UNIVERSITY OF JYVÄSKYLÄ 2004 Peer-to-Peer Networks Peer-to-Peer networks (P2P) are formed by Transmission Control Protocol (TCP) connections between workstations Workstations denoted as nodes can share their resources for example files ( ) or computing power Node 1 Node 2 Node 3 Node 4 TCP

UNIVERSITY OF JYVÄSKYLÄ 2004 Resource Discovery Problem In peer-to-peer resource discovery problem any node in the network can query resources from other nodes Node1: Where is ? Node 1 Node 2 Node 3 Node 4

UNIVERSITY OF JYVÄSKYLÄ 2004 A Simple Solution for the Problem Gnutella P2P network for example uses Breadth-First Search (BFS) flooding algorithm which sends query to all neighbors Problems: all resources in the network can be found, but network gets congested and there are lots of useless packets Node 1: Where is ? Node 1 Node 2 Node 3 Node 4 Query Node 4: I have it! Node 2: I have it! Node 4: Node 4 has it too! Reply

UNIVERSITY OF JYVÄSKYLÄ 2004 Our solution: NeuroSearch NeuroSearch resource discovery algorithm uses neural networks and evolution to adapt its behavior to given environment –neural network for deciding whether to pass the query further down the connection or not –evolution for breeding and finding out the best neural network in a large class of local search algorithms To authors knowledge this is the first time when neural networks are being applied to resource discovery problem Query Forward the query Neighbor Node

UNIVERSITY OF JYVÄSKYLÄ 2004 NeuroSearchs Inputs The internal structure of NeuroSearch algorithm Multiple layers enable the algorithm to express non-linear behavior With enough neurons the algorithm can universally approximate any decision function Tanh Threshold

UNIVERSITY OF JYVÄSKYLÄ 2004 NeuroSearchs Training Program The neural network weights define how neural network behaves so they must be adjusted to right values This is done using iterative optimization process based on evolution and Gaussian mutation Define the P2P network conditions Define the fitness requirements for the algorithm Create candidate algorithms randomly Select the best ones for next generation Breed a new population Finally select the best algorithm for these conditions Iterate thousands of generations Compare the best one against Breadth-First Search

UNIVERSITY OF JYVÄSKYLÄ 2004 Well How Good Is The Algorithm? We defined a peer-to-peer network scenario where: –100 nodes form a power-law distributed P2P network having few hubs and lots of low-connectivity nodes –Resources are distributed based on the number of connections the node has meaning that high-connectivity nodes are more likely to answer to the queries –Topology is static so the nodes are not moving Then we defined a fitness function for the algorithm stating that: –An algorithm that stops is always better than algorithm that does not –The algorithm should locate half of the available resources for each query –The algorithm should use as minimal number of packets as possible

UNIVERSITY OF JYVÄSKYLÄ 2004 Well How Good Is The Algorithm? After two weeks we were ready to compare NeuroSearchs invention against Breadth-First Search in 100-query test scenario The measurements indicate that the optimization process had developed an algorithm that: –finds half of the resources in the network with high probability –is more efficient than BFS with maximum number of three hops (BFS-3) and as efficient as BFS-2 while still locating the required 50% of resources –has stable performance regardless of where the querier is located Conclusion is that the approach is feasible, but not yet optimal AlgorithmPacketsResourcesResources/Packets (Efficiency) BFS (37,1%) BFS (66,7%) NeuroSearch (53,2%)0.2066

UNIVERSITY OF JYVÄSKYLÄ 2004 Evolution Of Neural Networks The best neural network of 85,736 th generation was selected for testing

UNIVERSITY OF JYVÄSKYLÄ 2004 Performance of NeuroSearch – Hit Rate NeuroSearch slightly misses the target of 50% resources in 8 queries

UNIVERSITY OF JYVÄSKYLÄ 2004 Performance of NeuroSearch - Resources BFS locates more resources when query starts from central nodes

UNIVERSITY OF JYVÄSKYLÄ 2004 Performance of NeuroSearch - Packets NeuroSearch is stable and the performance does not depend on where the query is started

UNIVERSITY OF JYVÄSKYLÄ 2004 Typical query pattern of NeuroSearch The maximum number of hops is 5

UNIVERSITY OF JYVÄSKYLÄ 2004 Future Work Now the first version of NeuroSearch is ready and analyzed The future work of NeuroSearch includes: –Analysis of the effects of varying neural networks structure New input types to feed NeuroSearch with more information Adjusting the number of neurons to allow NeuroSearch to make wiser decisions –Studying the scalability factors affecting NeuroSearch when the P2P network size grows –Developing an optimal resource discovery algorithm using global knowledge to be able to measure the best efficiency resource discovery algorithm can achieve –Speeding up the optimization process by parallelizing evolutionary algorithm using distributed computing

UNIVERSITY OF JYVÄSKYLÄ Thank You! Any questions?