DOI: 10.11908/j.issn.0253-374x.21055

作者:

作者单位: 1.同济大学 机械与能源工程学院，上海 201804;2.广东美的暖通设备有限公司 美的全球创新中心，广东 佛山 528311;3.上海克来沃美的暖通设备有限公司，上海 200335


作者简介: 孟 华（1968—），女，副教授，工学博士，主要研究方向为建筑节能技术及区域供热。 E-mail： mengh@tongji.edu.cn


通讯作者: 王 海（1976—），男，副教授，工学博士，主要研究方向为区域供热、建筑节能、能源互联网。 E-mail： wanghai@tongji.edu.cn

中图分类号: TU119


基金项目: 国家重点研发计划（2017YFC0702907）




Air-Conditioning Load Prediction of Subway Station Based on Clustering and Optimization Algorithm Ensemble Neural Network
Author:

Affiliation: 1.School of Mechanical Engineering， Tongji University， Shanghai 201804， China;2.Midea Global Innovation Center， Guangdong Media HVAC Equipment Co.， Ltd.， Foshan 528311， China;3.Shanghai Kravomeid HVAC Equipment Co.， Ltd.， Shanghai 200335， China


Fund Project:




摘要
| 图/表
| 访问统计
| 参考文献
|相似文献
| 引证文献
| 资源附件

摘要:分别从优化算法集成神经网络及将数据聚类后按类建模两方面建立3种模型对地铁车站空调负荷进行逐时预测，结果表明：同一物理量对地铁车站空调负荷所产生的影响程度随时间呈现某种动态变化特征，根据历史数据定量分析这些特征，对精准筛选模型输入参数、提高模型预测精度大有裨益。在3种模型中，粒子群优化算法-神经网络（PSO-BPNN）和果蝇优化算法-神经网络（FOA-BPNN）预测的平均相对误差（MAPE）较单纯神经网络（BPNN）分别降低25.87%和40.08%，聚类-神经网络（Kmeans-BPNN）预测的MAPE比PSO-BPNN及FOA-BPNN分别降低61.12%和51.90%。说明在同等情况下，优化算法集成模型比单纯BPNN预测精度更高，而当区分实际负荷变化特点后，采用聚类后建模比优化集成建模效果更佳。



Abstract:Three models were developed to predict the air-conditioning hourly cooling load of a subway station from the aspects of optimization algorithm ensemble back propagation neural network （BPNN） and BPNN with data clustering pre-processing. The results show that the influence of the same physical parameters on the air-conditioning load of the subway station reflects a certain dynamic change characteristic over time. Quantitative analysis of these features based on historical data is of great benefit to precisely selecting the model input parameters and improving model prediction accuracy. In the three given models， the predicted mean absolute percentage error （MAPE） of particle swarm optimization （PSO）-BPNN and the fruit fly optimization algorithm （FOA）-BPNN decreases by 25.87% and 40.08% respectively compared with that of BPNN， while the MAPE of Kmeans-BPNN is reduced by 61.12% and 51.90% respectively compared with that of PSO-BPNN and FOA-BPNN， which means that the performance of optimization algorithm ensemble models is better than that of pure BPNN on even ground. Moreover， BPNN with data clustering is better than optimization algorithm ensemble BPNNs after distinguishing the characteristics of real load changes.





PDF全文下载地址:

点我下载PDF