← Back to all news
arXiv Machine Learning

The Operational Value of Spatial Dependence in Renewable Forecast Scenarios for Single-Period Economic Dispatch: A Controlled Ablation Study

Related stories

arXiv Machine Learning
Oct 16

CoCopula: Conformal Calibration and Copula Aggregation for Reliable Renewable Energy Forecasting

CoCopula is a framework that transforms site-level probabilistic forecasts into reliable fleet-level forecasts by combining Copula-based dependence modeling with Context-Aware Conformal Prediction. It captures cross-site correlations and mitigates aggregation-induced miscalibration, producing sharp prediction intervals with near-nominal empirical coverage. Experiments on large-scale solar generation data from MISO, ERCOT, and SPP show lower Winkler scores than competing baselines and performance comparable to directly calibrated system-level forecasts.

By Alireza Moradi, Mathieu Tanneau, Reza Zandehshahvar, Pascal Van Hentenryck
More like this →
arXiv Machine Learning
2d ago

EnergyBench: a live, gate-aligned benchmark of day-ahead forecasts for European power markets

EnergyBench is a live, gate‑aligned benchmark that evaluates day‑ahead forecasts for European power markets every day at 11:30 CET/CEST, just before the SDAC gate closes. It runs models on a single, frozen information set—including three numerical weather prediction models—and publishes forecasts for price, wind, solar generation, and load across six bidding zones. Models are ranked using a Bradley‑Terry Elo system, with errors pooled against a seasonal‑naive baseline, allowing comparison of baselines, linear and gradient‑boosted models, foundation models, ensembles, and grid operators’ forecasts. Why it matters: By evaluating models live on a fixed, publicly released information set, EnergyBench eliminates overfitting to static test sets and provides a realistic, deadline‑aligned assessment of forecasting performance across multiple market variables.

By Evgenii Genov, Ander Martinez Alonso, Christoph Bergmeir
benchmarks
More like this →
arXiv Machine Learning
Jul 3

Probabilistic Low-Voltage Peak Load Forecasting with Time Series Foundation Models Evaluated on Application-Oriented Metrics

arXiv:2607. 01966v1 Announce Type: new Abstract: Low-voltage load forecasting is an important component in current and future energy systems with a high degree of electrification and decentralized generation.

By Benedikt Kaas, Manuel Treutlein, Hannes Benedikt Gerber, Oliver Neumann, Cheewan Phatthanakhuha, Oliver Resch, Ralf Mikut, Veit Hagenmeyer
benchmarks
More like this →
arXiv Machine Learning
Oct 8

Evaluating Sequence Assembly Strategies for Differentially Private Synthetic Time-Series Forecasting

The paper investigates how post‑generation assembly of fixed‑length synthetic windows affects downstream forecasting performance. By varying overlap rates and window‑weighting schemes, the authors evaluate boundary continuity, statistical and temporal fidelity, and TSTR utility across four public datasets and five forecasting models. Results show that optimal assembly depends on the forecaster, with increased overlap improving continuity but not always reducing forecasting error, and provide assembly grids and TRTR references to quantify these effects.

By Guoxiong Long, Huizhen Huang, Qikun Cai, Tao Huang, Chen Hou
More like this →
arXiv Machine Learning
Jun 5

Electricity price forecasting across Norway's five bidding zones in the post-crisis era

arXiv:2604. 26634v2 Announce Type: replace Abstract: Norway's electricity market is heavily dominated by hydropower, but the 2021-2022 energy crisis and stronger integration with Continental Europe have fundamentally altered price formation, reducing the reliability of forecasting models calibrated on historical data.

By My Thi Diem Phan, Trung Tuyen Truong, Hoai Phuong Ha, Dat Thanh Nguyen
multimodalbenchmarkssafety
More like this →