MRPGA : An Extension of MapReduce for Parallelizing Genetic Algorithm Reporter :古乃卉.
-
Upload
claire-owen -
Category
Documents
-
view
220 -
download
6
Transcript of MRPGA : An Extension of MapReduce for Parallelizing Genetic Algorithm Reporter :古乃卉.
MRPGA : An Extension of MapReduce for Parallelizing Genetic Algorithm
Reporter:古乃卉
Outline
Abstract Introduction Related Work Architecture MRPGA Implementation Experiments Conclusion
Abstract
MapReduce Map and Reduce
Genetic Algorithm Iteration
MRPGA Extension of MapReduce for Parallelizing
Genetic Algorithm
Introduction
Problems of Parallelized Genetic Algorithm Communication, synchronization,
heterogeneity and frequent failures Why MapReduce?
Provides a parallel design pattern for simplify application developments
How to work? Add a phase for global selection at the end of
every iteration of PGAs and a coordinator
Related Work
PGAs Distributed, coarse grained and fine grained MPI : not flexible enough for handling
heterogeneity and failures MapReduce
Phoenix, Hadoop and MRPSO
Architecture
MRPGA
Map, Reduce and Reduce
Key : index of the individual Value : the individual Allows each of the reduce tasks to collect
dependent input without fetching data from a remote machine
Key : individual Value : just number
MRPGA(cont.)
MRPGA(cont.)
Select the global Optimum individual
Reproduction, mutationand submission ofoffspring to thescheduler of MRPGA, and collection optimumindividual
Implementation
Experiments
MRPGA runtime system with Aneka An enterprise Grid consisting of 33 nodes Pentium 4 processor 1GB of memory 160GB IDE disk 1 Gbps Ethernet Windows XP
300 individuals 100 generations
Simulated cost Avg. evaluation 10 sec. Standard deviation 0.2
500 individuals 10 times
Experiments(cont.)
MOAE
MOAE+MRPGA
Conclusion
This extension makes PGAs can benefit from the MapReduce model on handling heterogeneity and failures