Performance Prediction Model Based on Multi-Task Learning and Co-Evolutionary Strategy for Ground Source Heat Pump System

In order to effectively predict the performance of ground source heat pump system, a performance prediction method is proposed in this paper. Based on the basic model of forward neural network, the algorithm predicts the performance data of ground source heat pump system by inputting the time series...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhaoyi Zhuang, Chen Wei, Bing Li, Peng Xu, Yifei Guo, Jiachang Ren
Format: Article
Language:English
Published: IEEE 2019-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/8807178/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850064896516947968
author Zhaoyi Zhuang
Chen Wei
Bing Li
Peng Xu
Yifei Guo
Jiachang Ren
author_facet Zhaoyi Zhuang
Chen Wei
Bing Li
Peng Xu
Yifei Guo
Jiachang Ren
author_sort Zhaoyi Zhuang
collection DOAJ
description In order to effectively predict the performance of ground source heat pump system, a performance prediction method is proposed in this paper. Based on the basic model of forward neural network, the algorithm predicts the performance data of ground source heat pump system by inputting the time series of system performance and 12 variables including 7 drilling parameters, 2 u-pipe parameters, 2 ground parameters and 1 circulating liquid parameter. The training of the model is divided into three subtasks by the strategy of multi-task learning and co-evolution, where CMA-ES is used as the evolutionary algorithm of the subtask. The experimental results show that the RMSE of the predicted results obtained by the proposed algorithm is less than 0.2, which verifies the effectiveness of the method. At the same time, this algorithm fully considers various influencing factors and has good versatility, which can be used as a reference for the design of ground source heat pump system.
format Article
id doaj-art-6a46d8d46c3b424ab2b344567cde73fc
institution DOAJ
issn 2169-3536
language English
publishDate 2019-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-6a46d8d46c3b424ab2b344567cde73fc2025-08-20T02:49:09ZengIEEEIEEE Access2169-35362019-01-01711792511793310.1109/ACCESS.2019.29365088807178Performance Prediction Model Based on Multi-Task Learning and Co-Evolutionary Strategy for Ground Source Heat Pump SystemZhaoyi Zhuang0https://orcid.org/0000-0002-7807-0207Chen Wei1Bing Li2Peng Xu3Yifei Guo4Jiachang Ren5School of Thermal Engineering, Shandong Jianzhu University, Jinan, ChinaShenzhen Graduate School, Peking University, Shenzhen, ChinaSchool of Information Science and Engineering, Shandong University, Qingdao, ChinaSchool of Information Science and Engineering, Shandong University, Qingdao, ChinaSchool of Information Science and Engineering, Shandong University, Qingdao, ChinaSchool of Information Science and Engineering, Shandong University, Qingdao, ChinaIn order to effectively predict the performance of ground source heat pump system, a performance prediction method is proposed in this paper. Based on the basic model of forward neural network, the algorithm predicts the performance data of ground source heat pump system by inputting the time series of system performance and 12 variables including 7 drilling parameters, 2 u-pipe parameters, 2 ground parameters and 1 circulating liquid parameter. The training of the model is divided into three subtasks by the strategy of multi-task learning and co-evolution, where CMA-ES is used as the evolutionary algorithm of the subtask. The experimental results show that the RMSE of the predicted results obtained by the proposed algorithm is less than 0.2, which verifies the effectiveness of the method. At the same time, this algorithm fully considers various influencing factors and has good versatility, which can be used as a reference for the design of ground source heat pump system.https://ieeexplore.ieee.org/document/8807178/Ground source heat pump systemdata miningcovariance matrix adaptation evolution strategymulti-task learningprediction model
spellingShingle Zhaoyi Zhuang
Chen Wei
Bing Li
Peng Xu
Yifei Guo
Jiachang Ren
Performance Prediction Model Based on Multi-Task Learning and Co-Evolutionary Strategy for Ground Source Heat Pump System
IEEE Access
Ground source heat pump system
data mining
covariance matrix adaptation evolution strategy
multi-task learning
prediction model
title Performance Prediction Model Based on Multi-Task Learning and Co-Evolutionary Strategy for Ground Source Heat Pump System
title_full Performance Prediction Model Based on Multi-Task Learning and Co-Evolutionary Strategy for Ground Source Heat Pump System
title_fullStr Performance Prediction Model Based on Multi-Task Learning and Co-Evolutionary Strategy for Ground Source Heat Pump System
title_full_unstemmed Performance Prediction Model Based on Multi-Task Learning and Co-Evolutionary Strategy for Ground Source Heat Pump System
title_short Performance Prediction Model Based on Multi-Task Learning and Co-Evolutionary Strategy for Ground Source Heat Pump System
title_sort performance prediction model based on multi task learning and co evolutionary strategy for ground source heat pump system
topic Ground source heat pump system
data mining
covariance matrix adaptation evolution strategy
multi-task learning
prediction model
url https://ieeexplore.ieee.org/document/8807178/
work_keys_str_mv AT zhaoyizhuang performancepredictionmodelbasedonmultitasklearningandcoevolutionarystrategyforgroundsourceheatpumpsystem
AT chenwei performancepredictionmodelbasedonmultitasklearningandcoevolutionarystrategyforgroundsourceheatpumpsystem
AT bingli performancepredictionmodelbasedonmultitasklearningandcoevolutionarystrategyforgroundsourceheatpumpsystem
AT pengxu performancepredictionmodelbasedonmultitasklearningandcoevolutionarystrategyforgroundsourceheatpumpsystem
AT yifeiguo performancepredictionmodelbasedonmultitasklearningandcoevolutionarystrategyforgroundsourceheatpumpsystem
AT jiachangren performancepredictionmodelbasedonmultitasklearningandcoevolutionarystrategyforgroundsourceheatpumpsystem