Incorporating Spatial and Temporal Correlations to Improve Aggregation of Decentralized Day-Ahead Wind Power Forecasts

In some electricity markets, individual wind farms are obliged to provide point forecasts to the power purchaser or system operator. These decentralized forecasts are usually based on on-site meteorological forecasts and measurements, and thus optimized for local conditions. Simply adding decentralized forecasts may not capture some of the spatial and temporal correlations of wind power, thereby lowering the potential accuracy of the aggregated forecast. This paper proposes the explanatory variables that are used to train the kernel density estimator and conditional kernel density estimator models to derive day-ahead aggregated point and probabilistic wind power forecasts from decentralized point forecasts of geographically distributed wind farms. The proposed explanatory variables include (a) decentralized point forecasts clustered using the clustering large applications algorithm to reduce the high-dimensional matrices, (b) hour of day and month of year to account for diurnal and seasonal cycles, respectively, and (c) atmospheric states derived from self-organizing maps to represent large-scale synoptic circulation climatology for a study area. The proposed methodology is tested using the day-ahead point forecast data obtained from 29 wind farms in South Africa. The results from the proposed methodology show a significant improvement as compared to simply adding the decentralized point forecasts. The derived predictive densities are shown to be non-Gaussian and time-varying, as expected given the time-varying nature of wind uncertainty. The proposed methodology provides system operators with a method of not only producing more accurate aggregated forecasts from decentralized forecasts, but also improving operational decisions such as dynamic operating reserve allocation and stochastic unit commitment.