>> I'd like to reuse some old desktop computers to create a cluster for > heavy duty optimization jobs, do you know if JBTWebOptimizer could be > used in a cluster using ParallelKnoppix?
Interesting idea :-) JBTWebOptimizer in its current state is just another frontend for JBookTrader. This means that JBTWO is utilizing the JBT code base including a slightliy adopted version of the strategy optimizer. So JBTWO is not capable for clustered computing. An architecture for using JBT in a clustered environment could follow the MapReduce approach (http://en.wikipedia.org/wiki/MapReduce). I think in the Map step the parameter sets for the strategies should be determined and distributed to the available computing nodes. On these nodes the data file with the back testing data should reside because transfering 100MB of data file contents to each node would be a bottleneck. I think there are two possibilities to enable JBT for clustered computing: - develop an adoption to the Hadoop framework. Then you can run it directly in the Amazon cloud, it uses the hadoop framework in its Amazon Elestic MapReduce service - using GridGain as framework for clustering. By using this approach you have more manual work to do but also you have more control. For your scenario this would be an intersting option -- You received this message because you are subscribed to the Google Groups "JBookTrader" group. To post to this group, send email to [email protected]. To unsubscribe from this group, send email to [email protected]. For more options, visit this group at http://groups.google.com/group/jbooktrader?hl=en.
