用协同集成学习+SHAP分析，精准预测高校未来12个月用电量。
Electricity Consumption Forecasting: An Approach Using Cooperative Ensemble Learning with SHapley Additive exPlanations
- 构建WSB集成模型，融合LSTM、RF等多算法并优化参数。
- 帕尔马斯校区预测误差sMAPE仅13.90%，梅特里达校区为18.72%。
- 发现历史用电数据最关键，气候因素影响较小，适合能源管理决策者。
电力费用管理面临诸多挑战，因该资源受多种因素影响。在高校中，随着机构扩张，用电需求快速增长，并带来显著环境影响。本研究基于巴西巴拉那联邦学院（IFPR）过去七年的历史用电数据及气象变量，训练长短期记忆网络（LSTM）、随机森林（RF）、支持向量回归（SVR）和极端梯度提升（XGBoost）等机器学习模型，预测未来12个月的用电量。采用两个校区的数据集。为提升性能，使用SHapley加性解释（SHAP）进行特征选择，并通过遗传算法（GA）与粒子群优化（PSO）进行超参数优化。结果表明，所提出的协同集成学习方法——弱分离增强器（WSB）表现最佳：在帕尔马斯校区达到sMAPE 13.90%、MAE 1990.87 kWh；在科罗内尔·维维达校区为sMAPE 18.72%、MAE 465.02 kWh。SHAP分析显示，两校区特征重要性模式不同，但滞后时间序列值影响显著，而气象变量影响较小。
原文摘要 · Abstract (English)
Electricity expense management presents significant challenges, as this resource is susceptible to various influencing factors. In universities, the demand for this resource is rapidly growing with institutional expansion and has a significant environmental impact. In this study, the machine learning models long short-term memory (LSTM), random forest (RF), support vector regression (SVR), and extreme gradient boosting (XGBoost) were trained with historical consumption data from the Federal Institute of Paraná (IFPR) over the last seven years and climatic variables to forecast electricity consumption 12 months ahead. Datasets from two campuses were adopted. To improve model performance, feature selection was performed using Shapley additive explanations (SHAP), and hyperparameter optimization was carried out using genetic algorithm (GA) and particle swarm optimization (PSO). The results indicate that the proposed cooperative ensemble learning approach named Weaker Separator Booster (WSB) exhibited the best performance for datasets. Specifically, it achieved an sMAPE of 13.90% and MAE of 1990.87 kWh for the IFPR-Palmas Campus and an sMAPE of 18.72% and MAE of 465.02 kWh for the Coronel Vivida Campus. The SHAP analysis revealed distinct feature importance patterns across the two IFPR campuses. A commonality that emerged was the strong influence of lagged time-series values and a minimal influence of climatic variables.
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。