An optimized autoregressive forecast error generator for wind and load uncertainty study

摘要

This paper presents a first-order autoregressive algorithm used to generate real-time (RT), hour-ahead (HA) and day-ahead (DA) wind and load forecast errors in time series. The modeled error time series preserve the characteristics of the historical forecast data sets. Four statistical characteristics are considered: the means, the standard deviations, the autocorrelations and the cross-correlations. A stochastic optimization routine was used to find an optimal set of parameters that minimize the differences of the four characteristics between the generated error series and the targeted ones. The obtained parameters were then in due order of succession used to produce the RT, HA and DA forecasts. This method, although implemented as a first-order regressive random forecast error generator, can be extended to higher orders. Simulation results have shown that the methodology produces random forecast error series that have statistics similar to those derived from real data sets. The wind and load forecast error generator can be used in wind integration studies to produce wind and load forecast in time series for stochastic planning processes. Our future studies will focus on reflecting the diurnal and seasonal differences of the wind and load statistics and on implementing them in the random forecast generator.