The probabilistic model and forecasting of power load based on JMAP-ML and Gaussian process
- 34 Downloads
The power load is a significant and important factor to the power system which can provide secure power supply and reliable power system. In this paper, we focus on the approximation and forecasting of the power load profiles based on the Gaussian mixture model. In order to infer the parameters of each component of GMM, we employ the joint maximum a posterior and maximum likelihood algorithm (JMAP-ML). Given the approximation of the power load, the Gaussian process regression method are utilized to forecast the power load in the time sequence. The simulation results show that the proposed algorithms can closely approximate the power load profiles and forecast the power load with lower errors.
KeywordsPower load Approximation and forecasting Gaussian mixture model (GMM) JMAP-ML Gaussian process regression
The work is supported by the Natural Science Foundation of China (61572032), Key Natural Science Research Project of Anhui Province (KJ2017A107).
- 6.Seppãlã, A.: Statistical distribution of customer load profiles. In: Proceedings of EMPD’95, 1995 International Conference on Energy Management and Power Delivery, vol. 2, pp. 696–701. IEEE (1995)Google Scholar
- 11.Blei, D.M., Kucukelbir, A., McAuliffe, J.D.: Variational inference: a review for statisticians. J. Am. Stat. Assoc. 112, 859–877 (2017)Google Scholar
- 25.Bar-Shalom, Y., Li, X.R., Kirubarajan, T.: Estimation with Applications to Tracking and Navigation: Theory Algorithms and Software. Wiley, New York (2004)Google Scholar