Using the ensemble Kalman filter for electricity load forecasting and analysis

作者：Takeda Hisashi^*; Tamura Yoshiyasu; Sato Seisho

来源：Energy, 2016, 104: 184-198.

DOI：10.1016/j.energy.2016.03.070

• Short-term load forecasting
• Electricity load
• State-space models
• Lasso

This paper proposes a novel framework for modeling electricity loads; it can be used for both forecasting and analysis. The framework combines the EnKF (ensemble Kalman filter) technique with shrinkage/multiple regression methods. First, SSMs (state-space models) are used to model the load structure, and then the EnKF is used for the estimation. Next, shrinkage/multiple linear regression methods are used to further enhance accuracy. The EnKF allows for the modeling of nonlinear systems in the SSMs, and this gives it great flexibility and detailed analytical information, such as the temperature response rate. We show that the forecasting accuracy of the proposed models is significantly better than that of the current state-of-the-art models, and this method also provides detailed analytical information.

• 出版日期2016-6-1