Guillermo Terrén-Serrano

The increasing penetration of solar energy leaves power grids vulnerable to fluctuations in the solar radiation that reaches the surface of the Earth due to the projection of cloud shadows. Therefore, an intra-hour solar forecasting algorithm is necessary to reduce power instabilities caused by the impact of moving clouds on energy generation. The most accurate intra-hour solar forecasting methods apply convolutional neural networks to a series of visible light sky images. Instead, this investigation uses data acquired by a novel infrared sky imager on a solar tracker, which is capable of maintaining the Sun in the center of the images throughout the day and, at the same time, reducing the scattering effect produced by the Sun’s direct radiation. In addition, infrared sky images allow the derivation and extraction of physical cloud features. The cloud dynamics are analyzed in sequences of images to compute the probability of the Sun intercepting air parcels in the sky images (i.e., voxels). The method introduced in this investigation fuses sky condition information from multiple sensors (i.e., pyranometer, sky imager, solar tracker, weather station) and feature sources using a multi-task deep learning architecture based on recurrent neural networks. The proposed deterministic and Bayesian architectures reduce computation time by avoiding convolutional filters. The proposed intra-hour solar forecasting algorithm reached a forecast skill of 18.6% with a forecasting horizon of 8 min. Consequently, the proposed intra-hour solar forecasting method can potentially reduce the operational costs of power grids with high participation of solar energy.

We propose and analyze the application of statistical functional depth metrics for the selection of extreme scenarios for realized electric load, as well as solar and wind generation in day-ahead grid planning. Our primary motivation is screening probabilistic scenarios to identify those most relevant for operational risk mitigation. To handle the high-dimensionality of the scenarios across asset classes and intra-day periods, we employ functional measures of depth to sub-select outlying scenarios that are most likely to be the riskiest for the grid operation. We investigate a range of functional depth measures, as well as a range of operational risks, including load shedding, operational costs, reserve shortfalls, and variable renewable energy curtailment. The effectiveness of the proposed screening approach is demonstrated through a case study on the realistic Texas-7k grid.

Increasing shares of wind and solar generation, together with rising electricity demand, introduce growing uncertainty into power system operations. Accurate day-ahead forecasts of electricity demand and renewable generation are essential for system operators to coordinate electricity markets and maintain reliability at low cost. Here, we show that forecasting based on joint probability distributions of demand and renewable supply can substantially improve system-level forecasting performance using publicly available weather data. We develop multiple day-ahead forecasting models that combine machine learning methods to identify relevant weather variables with probabilistic approaches to quantify forecast uncertainty, and we evaluate these models using proper scoring rules. Applied to the three zones of the California Independent System Operator, the best-performing model improves forecast skill by 25% relative to current benchmarks. We further show that forecasts based on joint probability distributions enable a more effective allocation of operating reserves than conventional deterministic approaches, highlighting the potential of probabilistic machine learning to enhance market efficiency and grid stability in increasingly decarbonized power systems.