对比5种超参优化算法在电力负荷预测中的表现
Testing the Efficacy of Hyperparameter Optimization Algorithms in Short-Term Load Forecasting
- 用5种优化算法调XGBoost超参，测试其在短时负荷预测中的效果
- 贝叶斯优化运行快但精度最低，其他算法在不同样本量下各有优劣
- 适合能源预测与模型调优研究者参考
准确预测电力需求对维持电网稳定、优化资源配置和促进高效用电至关重要。本研究评估了五种超参数优化（HPO）算法——随机搜索、协方差矩阵自适应进化策略（CMA-ES）、贝叶斯优化、部分粒子群优化（PSO）和Nevergrad优化器（NGOpt）在单变量和多变量短时负荷预测（STLF）任务中的有效性。基于巴拿马电力数据集（n=48,049），在代理预测算法XGBoost上评估各算法的准确性（即MAPE、$R^2$）和运行时间。性能曲线展示了从1,000到20,000不同样本量下的指标表现，克鲁斯卡尔-沃利斯检验用于评估性能差异的统计显著性。结果表明，除贝叶斯优化外，其余算法均显著优于随机搜索。在单变量模型中，贝叶斯优化的准确率最低。本研究为在STLF场景下优化XGBoost提供了重要参考，并指出了未来研究方向。
原文摘要 · Abstract (English)
Accurate forecasting of electrical demand is essential for maintaining a stable and reliable power grid, optimizing the allocation of energy resources, and promoting efficient energy consumption practices. This study investigates the effectiveness of five hyperparameter optimization (HPO) algorithms -- Random Search, Covariance Matrix Adaptation Evolution Strategy (CMA--ES), Bayesian Optimization, Partial Swarm Optimization (PSO), and Nevergrad Optimizer (NGOpt) across univariate and multivariate Short-Term Load Forecasting (STLF) tasks. Using the Panama Electricity dataset (n=48,049), we evaluate HPO algorithms' performances on a surrogate forecasting algorithm, XGBoost, in terms of accuracy (i.e., MAPE, $R^2$) and runtime. Performance plots visualize these metrics across varying sample sizes from 1,000 to 20,000, and Kruskal--Wallis tests assess the statistical significance of the performance differences. Results reveal significant runtime advantages for HPO algorithms over Random Search. In univariate models, Bayesian optimization exhibited the lowest accuracy among the tested methods. This study provides valuable insights for optimizing XGBoost in the STLF context and identifies areas for future research.
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。