| 引用本文: | 胡诗苑,高金良,钟丹,郭文娟,何军军,王学森.基于异常值识别的计量小区短期需水量预测[J].哈尔滨工业大学学报,2022,54(8):43.DOI:10.11918/202107031 |
| HU Shiyuan,GAO Jinliang,ZHONG Dan,GUO Wenjuan,HE Junjun,WANG Xuesen.A short-term water demand forecasting method combined with abnormal detection for district metered area[J].Journal of Harbin Institute of Technology,2022,54(8):43.DOI:10.11918/202107031 |
|
| |
|
|
| 本文已被：浏览 687次 下载 928次 |
码上扫一扫！ |
|
|
| 基于异常值识别的计量小区短期需水量预测 |
|
胡诗苑1,高金良1,钟丹1,郭文娟2,何军军3,王学森3
|
|
(1.哈尔滨工业大学 环境学院,哈尔滨 150090;2.北京首创股份有限公司,北京 100044; 3.哈尔滨凯纳科技股份有限公司,哈尔滨 150028)
|
|
| 摘要: |
| 需水量预测是进行水资源调配、节能降耗和降低管网水龄的关键问题。现有需水量预测研究主要对预测模型进行改进,而忽视了对预测准确性至关重要的预处理步骤,如异常值处理,限制了预测模型的精度。为此,建立基于密度的局部离群因子模型（local outlier factor,LOF）对需水量数据中的异常值进行识别及矫正,并将其与一种新兴的高精度、高效率梯度提升树算法（light gradient boosting machine,LightGBM）结合,形成组合需水量预测模型（LOF+LightGBM）。通过实际案例进行模型性能测试,结果表明,相比基于原始数据的预测模型,基于经过LOF模型处理后的需水量数据进行预测的模型均方根误差平均降低10%。LightGBM模型在不同数据集上的绝对平均误差比人工神经网络和支持向量机平均降低了24.7%。整体上,LOF+LightGBM表现最佳预测性能,3个计量小区（district metered area,DMA）的纳什效率系数分别为0.886、0.951、0.942。所有模型训练及预测时间均小于0.7 s。无论是LOF模型、LightGBM模型还是LOF+LightGBM模型,均有利于提升需水量预测模型的预测准确性。 |
| 关键词: 需水量预测 异常值识别 局部离群因子模型 LightGBM 人工神经网络 支持向量机 |
| DOI：10.11918/202107031 |
| 分类号:TU991 |
| 文献标识码:A |
| 基金项目:国家重点研发计划项目(2018YFC0406200)；国家自然科学基金(8,3)；黑龙江省自然科学基金联合引导项目(LH2019E044)；哈尔滨市校所信誉担保推荐项目(2017FF1XJ001) |
|
| A short-term water demand forecasting method combined with abnormal detection for district metered area |
|
HU Shiyuan1,GAO Jinliang1,ZHONG Dan1,GUO Wenjuan2,HE Junjun3,WANG Xuesen3
|
|
(1.School of Environment, Harbin Institute of Technology, Harbin 150090, China; 2. Beijing Capital Co., Ltd., Beijing 100044, China; 3.Harbin Corner Science & Technology Inc., Harbin 150028, China)
|
| Abstract: |
| Water demand forecasting is the key to allocating water resources, saving energy, and reducing water age of water distribution network. Existing research focuses on the forecasting models but ignores the pre-processing steps such as abnormal detection, which restricts the accuracy of the models. A local outlier factor (LOF) model based on density was proposed to identify abnormal values of water demand data. The LOF was then combined with light gradient boosting machine (LightGBM) to form a hybrid water demand forecasting model LOF+LightGBM. The model was tested through actual cases. Results show that the root-mean-square error of the forecasting model based on data processed by LOF reduced by about 10% on average, compared with the forecasting model based on raw data. The mean absolute error of LightGBM on different datasets was 24.7% lower than artificial neural network (ANN) and support vector machine (SVR) on average. Overall, LOF+LightGBM showed the best prediction performance and the Nash-Sutcliffe model efficiency coefficients for three district metered areas (DMAs) were 0.6,0.951, and 0.942, respectively. The training and computational time of all the models was less than 0.7 s. In conclusion, LOF model, LightGBM model, and LOF+LightGBM model are conducive to improving the accuracy of the water demand forecasting model. |
| Key words: water demand forecasting abnormal detection local outlier factor LightGBM artificial neural network support vector machine |
|
|
|
|
