EnsembleCI: Ensemble Learning for Carbon Intensity Forecasting

2025-05-04

AI Summary

Existing carbon intensity (CI) forecasting methods (e.g., CarbonCast) suffer from poor regional adaptability and limited flexibility, hindering precise low-carbon dispatch. To address this, we propose an end-to-end adaptive ensemble learning framework featuring a novel weighted sub-learner integration mechanism for region-specific modeling. The framework jointly incorporates temporal feature engineering and interpretable analysis to identify regionally dominant driving factors. It ensures robustness, long-horizon stability, and model transparency. Evaluated on real-world data from 11 regional power grids, our method achieves an average 19.58% reduction in mean absolute percentage error (MAPE) over baselines; it attains state-of-the-art accuracy across all regions, significantly improving both prediction stability and cross-regional generalization capability.

Technology Category

• Machine Learning: Ensemble Methods
• Intelligent Robots: Learning & Optimization for ROB
• Planning, Routing, and Scheduling: Model-Based Reasoning

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Sustainability and carbon-aware systems for Web, mobile, and WoT
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Carbon intensity (CI) measures the average carbon emissions generated per unit of electricity, making it a crucial metric for quantifying and managing the environmental impact. Accurate CI predictions are vital for minimizing carbon footprints, yet the state-of-the-art method (CarbonCast) falls short due to its inability to address regional variability and lack of adaptability. To address these limitations, we introduce EnsembleCI, an adaptive, end-to-end ensemble learning-based approach for CI forecasting. EnsembleCI combines weighted predictions from multiple sublearners, offering enhanced flexibility and regional adaptability. In evaluations across 11 regional grids, EnsembleCI consistently surpasses CarbonCast, achieving the lowest mean absolute percentage error (MAPE) in almost all grids and improving prediction accuracy by an average of 19.58%. While performance still varies across grids due to inherent regional diversity, EnsembleCI reduces variability and exhibits greater robustness in long-term forecasting compared to CarbonCast and identifies region-specific key features, underscoring its interpretability and practical relevance. These findings position EnsembleCI as a more accurate and reliable solution for CI forecasting. EnsembleCI source code and data used in this paper are available at https://github.com/emmayly/EnsembleCI.

Problem

• Accurate carbon intensity forecasting for environmental impact management
• Addressing regional variability in carbon intensity predictions
• Improving adaptability and robustness in long-term forecasting

Innovation

• Adaptive ensemble learning for CI forecasting
• Combines weighted predictions from multiple sublearners
• Enhances regional adaptability and accuracy