AI 中文总结
针对能源消耗预测对专家特征工程的依赖，提出自动化特征工程算法 AutoEnergy，集成 AutoML 与决策聚焦学习，在多个真实数据集上显著降低预测误差和运营成本。
AI 中文摘要
能源成本的上升和需求的增长，加之环境可持续性目标，给能源管理带来了重大挑战。能源消耗预测（ECF）通过预测未来消耗来支持规划，但用于 ECF 的机器学习（ML）模型往往依赖于专家驱动的特征工程（FE）。本论文通过三项贡献来解决这一依赖问题。首先，它建立并评估了一个针对 ECF 的全面特征工程流水线，并研究了特定领域的特征。其次，它引入了 AutoEnergy，一种面向领域的自动化特征工程算法，该算法从时间戳和滞后消耗中生成可解释特征，并与 AutoML 集成以实现端到端的 ECF 建模。在涵盖住宅、商业、工业、可再生能源和电网领域的十八个真实世界能源数据集上，AutoEnergy 相对于基线 AutoML 和已建立的自动化特征工程方法，将预测误差降低了 19.52%-84.72%，同时运行速度提高了 1.31-4.41 倍，收益因数据集而异。第三，AutoEnergy 与决策聚焦学习（DFL）集成，用于电池储能系统问题，联合预测电价和需求，同时优化充电和放电决策。在一个真实世界的英国物业数据集上，与未使用自动化特征工程的相同 DFL 模型相比，该方法将运营成本降低了 22.9%-56.5%。总体而言，结果表明，特定领域的自动化特征工程可以减少对人工特征设计的依赖，提高预测准确性，并将预测收益转化为能源管理中可衡量的运营效益。
英文摘要
The rising cost and demand for energy, together with environmental sustainability goals, create major challenges for energy management. Energy Consumption Forecasting (ECF) supports planning by predicting future consumption, but Machine Learning (ML) models for ECF often depend on expert-driven Feature Engineering (FE). This thesis addresses that dependence through three contributions. First, it establishes and evaluates a comprehensive FE pipeline for ECF and investigates domain-specific features. Second, it introduces AutoEnergy, a domain-tailored automated FE algorithm that generates interpretable features from timestamps and lagged consumption and integrates with AutoML for end-to-end ECF modelling. Across eighteen real-world energy datasets spanning residential, commercial, industrial, renewable, and grid domains, AutoEnergy reduces forecasting error by 19.52%-84.72% relative to baseline AutoML and established automated FE methods, while running 1.31-4.41 times faster, with gains varying by dataset. Third, AutoEnergy is integrated with Decision-Focused Learning (DFL) for a Battery Energy Storage System problem, jointly forecasting electricity prices and demand while optimising charging and discharging decisions. On a real-world UK property dataset, this approach reduces operating costs by 22.9%-56.5% compared with the same DFL models without automated FE. Overall, the results show that domain-specific automated FE can reduce reliance on manual feature design, improve forecasting accuracy, and translate predictive gains into measurable operational benefits in energy management.
CommentsPhD thesis, School of Computer Science, University of Nottingha, United Kingdom
