一句话：通过受控实验评估五种降低 RAG 系统能耗的技术，发现其中两种可在不损准确率的情况下显著降低能耗与延迟。
随着 RAG 等机器学习系统能耗上升，其环境可持续性引发关注，但已有绿色策略在 RAG 系统中的实证评估仍很缺乏。本文开展受控实验，针对五种旨在降低 RAG 系统能耗的实用技术，在合作方 Software Improvement Group 的生产级 RAG 系统上评估其对能耗、延迟和准确率的影响。实验使用 CRAG 数据集，覆盖 9 种配置，总试验时长超过 200 小时。结果表明，提高相似度检索阈值、减小嵌入维度、应用向量索引以及使用 BM25S 重排序器等技术可显著降低能耗，部分情况下降幅达 60%。然而若干技术也导致不可接受的准确率下降，例如索引策略可使准确率降低达 30%。值得注意的是，找到最优检索阈值并减小嵌入维度能大幅降低能耗和延迟且不损失准确率，是真正能效较高的两项技术。本文提供了首个面向 RAG 系统的能效设计技术综合实证研究，为开发者与研究者构建可持续 RAG 应用提供指导。
The rising energy demands of machine learning (ML), e.g., implemented in popular variants like retrieval-augmented generation (RAG) systems, have raised significant concerns about their environmental sustainability. While previous research has proposed green tactics for ML-enabled systems, their empirical evaluation within RAG systems remains largely unexplored. This study presents a controlled experiment investigating five practical techniques aimed at reducing energy consumption in RAG systems. Using a production-like RAG system developed at our collaboration partner, the Software Improvement Group, we evaluated the impact of these techniques on energy consumption, latency, and accuracy. Through a total of 9 configurations spanning over 200 hours of trials using the CRAG dataset, we reveal that techniques such as increasing similarity retrieval thresholds, reducing embedding sizes, applying vector indexing, and using a BM25S reranker can significantly reduce energy usage, up to 60% in some cases. However, several techniques also led to unacceptable accuracy decreases, e.g., by up to 30% for the indexing strategies. Notably, finding an optimal retrieval threshold and reducing embedding size substantially reduced energy consumption and latency with no loss in accuracy, making these two techniques truly energy-efficient. We present the first comprehensive, empirical study on energy-efficient design techniques for RAG systems, providing guidance for developers and researchers aiming to build sustainable RAG applications.
@inproceedings{paperbot11974,
title = {On the Effectiveness of Proposed Techniques to Reduce Energy Consumption in RAG Systems: A Controlled Experiment},
author = {Zhinuan (Otto) Guo and Chushu Gao and Justus Bogner},
booktitle = {ICSE},
year = {2026},
doi = {10.1145/3786581.3786932}
}