Cap-Aware Boosting for Green Day-Ahead Electricity Price Forecasting

Forecasting 15-minute Market Clearing Prices in the Indian Energy Exchange Green Day-Ahead Market (GDAM) is complicated by pronounced diurnal renewable cycles and frequent upper price-cap events ($10,000\text{ Rs/MWh}$). We propose a leak-safe, cap-aware LightGBM architecture that blends an $L_1$ log-price regressor with an upper-price classifier alongside nine rolling-calibrated quantile heads. Across 257 delivery days (January–September 2026; 24,672 blocks), our baseline model achieves $397.9\text{ Rs/MWh}$ MAE and $171.6\text{ Rs/MWh}$ mean pinball loss, cutting MAE by $31.8\%$ relative to a zero-shot univariate Chronos-2 model ($583.3\text{ Rs/MWh}$) and $32.5\%$ over persistence ($589.1\text{ Rs/MWh}$). On a volatile October–November 2026 holdout, decoupling uncapped price regression from cap classification while adding pre-gate covariates—same-morning real-time prices, prior-day unmatched sell volumes, and capacity-weighted clear-sky solar irradiance—further reduces MAE to $716.0\text{ Rs/MWh}$ versus $2,000.4\text{ Rs/MWh}$ for Chronos-2. Domain-informed covariates within cap-aware boosting drive accuracy gains far more effectively than replacing tabular ensembles with univariate foundation models.

Authors

Publication Details

Published
2026-11-19
DOI
https://doi.org/10.66977/xsci.2611.003a
Primary Topic
Energy Load and Power Forecasting
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Cap-Aware Boosting for Green Day-Ahead Electricity Price Forecasting

Shubham Pratap
1 links
Energy Load and Power Forecasting
preprint

Cap-Aware Boosting for Green Day-Ahead Electricity Price Forecasting

Shubham Pratap
preprint en

Abstract

Forecasting 15-minute Market Clearing Prices in the Indian Energy Exchange Green Day-Ahead Market (GDAM) is complicated by pronounced diurnal renewable cycles and frequent upper price-cap events ($10,000\text{ Rs/MWh}$). We propose a leak-safe, cap-aware LightGBM architecture that blends an $L_1$ log-price regressor with an upper-price classifier alongside nine rolling-calibrated quantile heads. Across 257 delivery days (January–September 2026; 24,672 blocks), our baseline model achieves $397.9\text{ Rs/MWh}$ MAE and $171.6\text{ Rs/MWh}$ mean pinball loss, cutting MAE by $31.8\%$ relative to a zero-shot univariate Chronos-2 model ($583.3\text{ Rs/MWh}$) and $32.5\%$ over persistence ($589.1\text{ Rs/MWh}$). On a volatile October–November 2026 holdout, decoupling uncapped price regression from cap classification while adding pre-gate covariates—same-morning real-time prices, prior-day unmatched sell volumes, and capacity-weighted clear-sky solar irradiance—further reduces MAE to $716.0\text{ Rs/MWh}$ versus $2,000.4\text{ Rs/MWh}$ for Chronos-2. Domain-informed covariates within cap-aware boosting drive accuracy gains far more effectively than replacing tabular ensembles with univariate foundation models.

Affordable and clean energy, Climate action, Industry, innovation and infrastructure
Energy Load and Power Forecasting
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon