Partitioning and Multi-core Parallelization of Multi-equation Forecast Models

  • Lars Dannecker
  • Matthias Böehm
  • Wolfgang Lehner
  • Gregor Hackenbroich
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7338)


Forecasting is an important analysis technique used in many application domains such as electricity management, sales and retail and, traffic predictions. The employed statistical models already provide very accurate predictions, but recent developments in these domains pose new requirements on the calculation speed of the forecast models. Especially, the often used multi-equation models tend to be very complex and their estimation is very time consuming. To still allow the use of these highly accurate forecast models, it is necessary to improve the data processing capabilities of the involved data management systems. For this purpose, we introduce a partitioning approach for multi-equation forecast models that considers the specific data access pattern of these models to optimize the data storage and memory access. With the help of our approach we avoid the redundant reading of unnecessary values and improve the utilization of the CPU cache. Furthermore, we utilize the capabilities of modern multi-core hardware and parallelize the model estimation. Our experimental results on real-world data show speedups of up to 73x for the initial model estimation. Thus, our partitioning and parallelization approach significantly increases the efficiency of multi-equation models.


Forecasting Multi-Equation Partitioning Parallelization 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    MIRABEL Project (2011),
  2. 2.
    MeRegio Project (2011),
  3. 3.
    Box, G.E.P., Jenkins, G.M., Reinsel, G.C.: Time Series Analysis: Forecasting and Control. John Wiley & Sons Inc. (1970)Google Scholar
  4. 4.
    Winters, P.R.: Forecasting sales by exponentially weighted moving averages. Management Science, 324–342 (April 1960)Google Scholar
  5. 5.
    Bunnoon, P., Chalermyanont, K., Limsakul, C.: A computing model of artificial intelligent approaches to mid-term load forecasting: a state-of-the-art- survey for the researcher. Int. Journal of Engineering and Technology 2(1), 94–100 (2010)Google Scholar
  6. 6.
    Ramanathan, R., Engle, R., Granger, C.W., Vahid-Araghi, F., Brace, C.: Short-run forecasts of electricity loads and peaks. International Journal of Forecasting 13(2), 161–174 (1997)CrossRefGoogle Scholar
  7. 7.
    Cottet, R., Smith, M.: Bayesian modeling and forecasting of intraday electricity load. Journal of the American Statistical Association 98, 839–849 (2003)MathSciNetCrossRefGoogle Scholar
  8. 8.
    Taylor, J.W., de Menezes, L.M., McSharry, P.E.: A comparison of univariate methods for forecasting electricity demand up to a day ahead. International Journal of Forecasting 22, 1–16 (2006)CrossRefGoogle Scholar
  9. 9.
    Soares, L.J., Medeiros, M.C.: Modeling and forecasting short-term electricity load: A comparison of methods with an application to brazilian data. International Journal of Forecasting 24(4), 630–644 (2008)CrossRefGoogle Scholar
  10. 10.
    Wulf, W.A., McKee, S.A.: Hitting the memory wall: Implications of the obvious. Computer Architecture News 23(1), 20–24 (1995)CrossRefGoogle Scholar
  11. 11.
    Borkar, S.Y., Mulder, H., Dubey, P., Pawlowski, S.S., Kahn, K.C., Rattner, J.R., Kuck, D.J.: Platform 2015: Intel processor and platform evolution for the next decade. Technical report, Intel Corporation (2005)Google Scholar
  12. 12.
    Kim, C., Chhugani, J., Satish, N., Sedlar, E., Nguyen, A.D., Kaldewey, T., Lee, V.W., Brandt, S.A., Dubey, P.: Fast: Fast architecture sensitive tree search on modern cpus and gpus. In: Proceeding of the SIGMOD 2010 (2010)Google Scholar
  13. 13.
    Taylor, J.W.: Triple seasonal methods for short-term electricity demand forecasting. European Journal of Operational Research 204, 139–152 (2009)CrossRefGoogle Scholar
  14. 14.
    Nelder, J., Mead, R.: A simplex method for function minimization. The Computer Journal 7(4), 308–313 (1965)MATHGoogle Scholar
  15. 15.
    Nationalgrid UK: Metered half-hourly electricity demands (2010),
  16. 16.
    Ge, T., Zdonik, S.: A skip-list approach for efficiently processing forecasting queries. In: Proceeding of the VLDB 2008 (2008)Google Scholar
  17. 17.
    Agrawal, D., Chen, D., Ji Lin, L., Shanmugasundaram, J., Vee, E.: Forecasting high-dimensional data. In: Proceeding of the SIGMOD 2010 (2010)Google Scholar
  18. 18.
    Cannas, B., Fanni, A., See, L., Sias, G.: Data preprocessing for river flow forecasting using neural networks: Wavelet transforms and data partitioning. Physics and Chemistry of the Earth 31(18), 1164–1171 (2006)CrossRefGoogle Scholar
  19. 19.
    Kalaitzakis, K., Stavrakakis, G., Anagnostakis, E.: Short-term load forecasting based on artificial neural networks parallel implementation. Electric Power Systems Research 63, 185–196 (2002)CrossRefGoogle Scholar
  20. 20.
    Shimokawabe, T., Aoki, T., Muroi, C., Ishida, J., Kawano, K., Endo, T., Nukada, A., Maruyama, N., Matsuoka, S.: An 80-fold speedup, 15.0 tflops full gpu acceleration of non-hydrostatic weather model asuca production code. In: Proceedings of Super Computing 2010 (2010)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Lars Dannecker
    • 1
  • Matthias Böehm
    • 2
  • Wolfgang Lehner
    • 2
  • Gregor Hackenbroich
    • 1
  1. 1.SAP Research DresdenSAP AGDresdenGermany
  2. 2.Database Technology GroupTechnische Universität DresdenDresdenGermany

Personalised recommendations