摘要
如何合理安排水资源并减少水资源浪费是亟需解决的问题,精确预测供水量并为供水系统调度方案的制定提供必要的数据支持是目前重要研究方向之一。建立了一种基于CatBoost的城市供水量组合预测模型,该模型基于KNN算法对异常数据进行识别和校正,从而减少异常数据对模型精度的影响;随后采用SVR,XGBoost,LightGBM和CatBoost模型预测供水量数据;为了融合各模型的优点并提高模型的预测精度,将各单一模型的预测结果作为输入特征,采用CatBoost模型进一步预测供水量数据并得到最终的供水量预测结果。仿真实验结果表明:所提出的基于CatBoost的组合预测模型具有更好的预测精度,验证了该模型在城市供水量预测问题中的有效性。
How to reasonably arrange water resources and reduce the waste of water resources is a problem that need to be solved urgently.They are important research directions to accurately forecast water supply and provide necessary data support for the formulation of water supply system scheduling scheme.A combined forecasting model of water supply based on CatBoost is established.The model identifies and corrects abnormal data based on KNN algorithm to reduce the impact of abnormal data on the accuracy of the model;Then SVR,XGBoost,LightGBM and CatBoost models are used to forecast the water supply data;In order to integrate the advantages of each model and improve the accuracy of the model,the prediction results of each single model are taken as the inputting characteristics,and the CatBoost based model is used to further forecast the water supply data and obtain the final forecasting results.The simulation results show that the proposed combined prediction model based on CatBoost has better forecasting accuracy,which verifies the effectiveness of the model in the forecast of urban water supply.
作者
朱俊杰
叶文静
曹萃文
顾幸生
Zhu Junjie;Ye Wenjing;Cao Cuiwen;Gu Xingsheng(Shanghai Nanhui Tap Water Co.Ltd.,Shanghai,201399,China;Key Laboratory of Smart Manufacturing in Energy Chemical Processes,Ministry of Education,East China University of Science and Technology,Shanghai,200237,China)
出处
《石油化工自动化》
CAS
2023年第5期10-14,共5页
Automation in Petro-chemical Industry
基金
国家自然科学基金项目(61973120)。
