CarbonX用时间序列大模型实现全球碳强度预测，无需电网数据也能精准预报。
CarbonX: An Open-Source Tool for Computational Decarbonization Using Time Series Foundation Models
- 基于时间序列基础模型，仅需历史碳强度数据即可跨电网预测。
- 零样本预测平均误差15.82%，13个基准电网平均误差9.59%，且提供95%置信区间。
- 支持全球214个电网、最长21天预测，适合低碳应用开发与政策制定者使用。
计算去碳化旨在降低数据中心、交通和建筑环境等系统中的碳排放。这需要精确的细粒度碳强度预测，但现有工具存在三大局限：(i) 需要特定电网的电力结构数据，限制了在缺乏此类信息区域的应用；(ii) 依赖独立的电网特异性模型，难以实现全球覆盖；(iii) 缺乏不确定性估计，影响下游碳感知应用的可靠性。本文提出 CarbonX，一个开源工具，利用时间序列基础模型（TSFMs）完成多种去碳化任务。CarbonX 利用 TSFMs 的通用性，在多个任务和不同电网上均表现优异。仅使用历史碳强度数据和单一通用模型，该工具在全球214个电网上实现了零样本预测的平均绝对百分比误差（MAPE）为15.82%。在13个基准电网上，其平均MAPE为9.59%，尾部预测MAPE为16.54%，同时提供95%覆盖率的预测区间。预测可延伸至21天，精度下降极小。完全微调后，其在插补任务上性能优于统计基线1.2–3.9倍。结果表明，CarbonX 可在数据有限情况下于任意电网实现高性能，是面向全球去碳化的实用工具。
原文摘要 · Abstract (English)
Computational decarbonization aims to reduce carbon emissions in computing and societal systems such as data centers, transportation, and built environments. This requires accurate, fine-grained carbon intensity forecasts, yet existing tools have several key limitations: (i) they require grid-specific electricity mix data, restricting use where such information is unavailable; (ii) they depend on separate grid-specific models that make it challenging to provide global coverage; and (iii) they provide forecasts without uncertainty estimates, limiting reliability for downstream carbon-aware applications. In this paper, we present CarbonX, an open-source tool that leverages Time Series Foundation Models (TSFMs) for a range of decarbonization tasks. CarbonX utilizes the versatility of TSFMs to provide strong performance across multiple tasks, such as carbon intensity forecasting and imputation, and across diverse grids. Using only historical carbon intensity data and a single general model, our tool achieves a zero-shot forecasting Mean Absolute Percentage Error (MAPE) of 15.82% across 214 grids worldwide. Across 13 benchmark grids, CarbonX performance is comparable with the current state-of-the-art, with an average MAPE of 9.59% and tail forecasting MAPE of 16.54%, while also providing prediction intervals with 95% coverage. CarbonX can provide forecasts for up to 21 days with minimal accuracy degradation. Further, when fully fine-tuned, CarbonX outperforms the statistical baselines by 1.2--3.9X on the imputation task. Overall, these results demonstrate that CarbonX can be used easily on any grid with limited data and still deliver strong performance, making it a practical tool for global-scale decarbonization.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。