Maestro: a self-organizing peer-to-peer dataflow framework using reinforcement learning Export

@inproceedings{citeulike:4921064, abstract = {In this paper we describe Maestro, a dataflow computation framework for Ibis, our Java-based grid middleware. The novelty of Maestro is that it is a self-organizing peer-to-peer system, meaning that it distributes the tasks in a flow over the available nodes based on local decisions on each node, without any central coordination. As a result, the computations are more scalable, more resilient against failing nodes, and less sensitive to communication latencies.}, address = {New York, NY, USA}, author = {van Reeuwijk, C.}, booktitle = {HPDC '09: Proceedings of the 18th ACM international symposium on High performance distributed computing}, citeulike-article-id = {4921064}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1551609.1551639}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/1551609.1551639}, doi = {10.1145/1551609.1551639}, isbn = {978-1-60558-587-1}, keywords = {algorithms, multicore, reasoning, semantic, theory, transactions}, location = {Garching, Germany}, pages = {187--196}, posted-at = {2009-06-22 08:49:33}, priority = {4}, publisher = {ACM}, title = {Maestro: a self-organizing peer-to-peer dataflow framework using reinforcement learning}, url = {http://dx.doi.org/10.1145/1551609.1551639}, year = {2009} }

TY - CONF ID - citeulike:4921064 L3 - citeulike-article-id:4921064 N2 - In this paper we describe Maestro, a dataflow computation framework for Ibis, our Java-based grid middleware. The novelty of Maestro is that it is a self-organizing peer-to-peer system, meaning that it distributes the tasks in a flow over the available nodes based on local decisions on each node, without any central coordination. As a result, the computations are more scalable, more resilient against failing nodes, and less sensitive to communication latencies. CY - Garching, Germany SN - 978-1-60558-587-1 AD - New York, NY, USA EP - 196 TI - Maestro: a self-organizing peer-to-peer dataflow framework using reinforcement learning PB - ACM T2 - HPDC '09: Proceedings of the 18th ACM international symposium on High performance distributed computing SP - 187 KW - algorithms KW - multicore KW - reasoning KW - semantic KW - theory KW - transactions AU - van Reeuwijk, C PY - 2009/// UR - http://dx.doi.org/10.1145/1551609.1551639 ER -