Проект Templet

акторный фреймворк для запуска задач
на множестве ядер, кластерах и в облаках
templet.ssau.ru

Инструменты пользователя

Инструменты сайта


science:разработка_методов_прогнозирования_доступных_вычислительных_ресурсов_в_кластерных_системах

Разработка методов прогнозирования доступных вычислительных ресурсов в кластерных системах

Аспирант СГАУ: Артамонов Юрий

Постановка задачи

Актуальность

Методы решения

  • Модель EMMSP
  • Нейросетевые модели
  • Модели адаптивной селекции и композиции

Список литературы

  1. How Effective are Neural Networks at Forecasting and Prediction? - Journal of Forecasting J. Forecast. 17, 481-495 (1998)
  2. Evaluation of a Workflow Scheduler Using Integrated Performance Modelling and Batch Queue Wait Time Prediction - SC '06 Proceedings of the 2006 ACM/IEEE conference on Supercomputing Article No. 119 (2006)
  3. Predicting Bounds on Queuing Delay for Batch-scheduled Parallel Machines - PPoPP '06 Proceedings of the eleventh ACM SIGPLAN symposium on Principles and practice of parallel programming (2006)
  4. QBETS: Queue Bounds Estimation from Time Series - Job Scheduling Strategies for Parallel Processing, 13th InternationalWorkshop, JSSPP 2007 Seattle,WA, USA, June 17, (2007)
  5. Probabilistic Advanced Reservations for Batch-scheduled Parallel Machines - PPoPP '08 Proceedings of the 13th ACM SIGPLAN Symposium on Principles and practice of parallel programming (2008)
  6. An Architecture for Resource Behavior Prediction to Improve Scheduling Systems Performance on Enterprise Desktop Grids, Advances in New Technologies, Interactive Interfaces and Communicability, Lecture Notes in Computer Science Volume 7547, 186-196 (2012)
  7. Identifying Quick Starters: Towards an Integrated Framework for Efficient Predictions of Queue Waiting Times of Batch Parallel Jobs - Job Scheduling Strategies for Parallel Processing, 16th InternationalWorkshop, JSSPP 2012 Shanghai, China, May 25, (2012)
  8. Web-Scale Job Scheduling - Job Scheduling Strategies for Parallel Processing, 16th InternationalWorkshop, JSSPP 2012 Shanghai, China, May 25, (2012)
  9. Maximizing Utilization in Private IaaS Clouds with Heterogenous Load through Time Series Forecasting - International Journal on Advances in Systems and Measurements, vol 6 no 1 & 2 (2013)
science/разработка_методов_прогнозирования_доступных_вычислительных_ресурсов_в_кластерных_системах.txt · Последнее изменение: 2017/01/10 19:00 — 127.0.0.1