基于人工神经网络的住宅新风系统负荷预测与运行优化
摘要：通过建立人工神经网络模型来预测溶液调湿新风系统的湿负荷及冷负荷，考虑使用热感区域划分来提高预测精度；引入了一种系统控制优化模型，并结合神经网络模型的负荷预测结果对新风系统的运行控制进行了优化，在潜能蓄能和分时电价情况下制定了优化控制策略，提高了系统灵活性。结果表明，分区神经网络模型具有较高的预测精度，湿负荷及冷负荷预测结果对应的均方根误差变异系数分别为8.72%和9.98%,优化结果可使系统在整个空调季的运行能耗和费用分别降低27.2%和29.2%。该结果可为住宅独立新风调湿系统的运行优化提供参考。
关键词：负荷预测新风分区人工神经网络溶液调湿蓄热
尊敬的用户，本篇文章需要2元，点击支付交费后阅读
限时优惠福利：领取VIP会员
全年期刊、VIP视频免费!
全年期刊、VIP视频免费!
参考文献[1] MAN Y,YANG H X,WANG J G.Study on hybrid ground-coupled heat pump system for air-conditioning in hot-weather areas like Hong Kong[J].Applied energy,2009,87(9):2826- 2833.
[2] 曾江月.地源热泵辐射空调系统后评估研究[D].南京：南京理工大学，2017:3- 5.
[3] RHEE K M,OLESEN B W,KIM K W.Ten questions about radiant heating and cooling systems[J].Building and environment,2017,112:367- 381.
[4] 清华大学，合肥通用机械研究所.热泵式热回收型溶液调湿新风机组：GB/T 27943—2011[S].北京：中国标准出版社，2011:1- 2.
[5] LUO X J,OYEDELE L O,AJAYI A O,et al.Comparative study of machine learning-based multi-objective prediction framework for multiple building energy loads[J].Sustainable cities and society,2020,61:102283.
[6] AHMAD A S,HASSAN M Y,ABDULLAH M P,et al.A review on applications of ANN and SVM for building electrical energy consumption forecasting[J].Renewable and sustainable energy reviews,2014,33:102- 109.
[7] GONZÁLEZ P A,ZAMARREÑO J M.Prediction of hourly energy consumption in buildings based on a feedback artificial neural network[J].Energy and buildings,2004,37(6):595- 601.
[8] LI Q,MENG Q L,CAI J J,et al.Predicting hourly cooling load in the building:a comparison of support vector machine and different artificial neural networks[J].Energy conversion and management,2008,50(1):90- 96.
[9] HU J F,ZHENG W D,ZHANG S R,et al.Thermal load prediction and operation optimization of office building with a zone-level artificial neural network and rule-based control[J].Applied energy,2021,300:117429.
[10] 徐新华，李骥，冯宇欣，等.基于灰色理论的建筑需求冷量预测研究[J].暖通空调，2021,51(8):64- 69.
[11] SONG K,KWON N,ANDERSON K,et al.Predicting hourly energy consumption in buildings using occupancy-related characteristics of end-user groups[J].Energy and buildings,2017,156:121- 133.
[12] LIU Z J,WU D F,LIU Y W,et al.Accuracy analyses and model comparison of machine learning adopted in building energy consumption prediction[J].Energy exploration & exploitation,2019,37(4):1426- 1451.
[13] BRANDI S,PISCITELLI M S,MARTELLACCI M,et al.Deep reinforcement learning to optimise indoor temperature control and heating energy consumption in buildings[J].Energy and buildings,2020,224:1110225.
[14] 黄巍，于震，李怀，等.近零能耗建筑空调负荷预测研究[J].建筑节能(中英文),2021,49(6):72- 78.
[15] DENG H,FANNON D,ECKELMAN M J.Predictive modeling for US commercial building energy use:a comparison of existing statistical and machine learning algorithms using CBECS microdata[J].Energy and buildings,2018,163:34- 43.
[16] ASHRAE.Measurement of energy,demand,and water savings:ASHRAE guideline 14-2014[S].Atlanta:ASHRAE Inc.,2014:94- 100.
[17] 蒋毅，张小松，殷勇高.溶液除湿的潜能蓄能技术及其应用研究[J].工程热物理学报，2006(增刊1):25- 28.
[2] 曾江月.地源热泵辐射空调系统后评估研究[D].南京：南京理工大学，2017:3- 5.
[3] RHEE K M,OLESEN B W,KIM K W.Ten questions about radiant heating and cooling systems[J].Building and environment,2017,112:367- 381.
[4] 清华大学，合肥通用机械研究所.热泵式热回收型溶液调湿新风机组：GB/T 27943—2011[S].北京：中国标准出版社，2011:1- 2.
[5] LUO X J,OYEDELE L O,AJAYI A O,et al.Comparative study of machine learning-based multi-objective prediction framework for multiple building energy loads[J].Sustainable cities and society,2020,61:102283.
[6] AHMAD A S,HASSAN M Y,ABDULLAH M P,et al.A review on applications of ANN and SVM for building electrical energy consumption forecasting[J].Renewable and sustainable energy reviews,2014,33:102- 109.
[7] GONZÁLEZ P A,ZAMARREÑO J M.Prediction of hourly energy consumption in buildings based on a feedback artificial neural network[J].Energy and buildings,2004,37(6):595- 601.
[8] LI Q,MENG Q L,CAI J J,et al.Predicting hourly cooling load in the building:a comparison of support vector machine and different artificial neural networks[J].Energy conversion and management,2008,50(1):90- 96.
[9] HU J F,ZHENG W D,ZHANG S R,et al.Thermal load prediction and operation optimization of office building with a zone-level artificial neural network and rule-based control[J].Applied energy,2021,300:117429.
[10] 徐新华，李骥，冯宇欣，等.基于灰色理论的建筑需求冷量预测研究[J].暖通空调，2021,51(8):64- 69.
[11] SONG K,KWON N,ANDERSON K,et al.Predicting hourly energy consumption in buildings using occupancy-related characteristics of end-user groups[J].Energy and buildings,2017,156:121- 133.
[12] LIU Z J,WU D F,LIU Y W,et al.Accuracy analyses and model comparison of machine learning adopted in building energy consumption prediction[J].Energy exploration & exploitation,2019,37(4):1426- 1451.
[13] BRANDI S,PISCITELLI M S,MARTELLACCI M,et al.Deep reinforcement learning to optimise indoor temperature control and heating energy consumption in buildings[J].Energy and buildings,2020,224:1110225.
[14] 黄巍，于震，李怀，等.近零能耗建筑空调负荷预测研究[J].建筑节能(中英文),2021,49(6):72- 78.
[15] DENG H,FANNON D,ECKELMAN M J.Predictive modeling for US commercial building energy use:a comparison of existing statistical and machine learning algorithms using CBECS microdata[J].Energy and buildings,2018,163:34- 43.
[16] ASHRAE.Measurement of energy,demand,and water savings:ASHRAE guideline 14-2014[S].Atlanta:ASHRAE Inc.,2014:94- 100.
[17] 蒋毅，张小松，殷勇高.溶液除湿的潜能蓄能技术及其应用研究[J].工程热物理学报，2006(增刊1):25- 28.
Load forecast and operation optimization of residential outdoor air system based on artificial neural network
Abstract: In this paper, an artificial neural network model is established to forecast the moisture load and cooling load of the solution humidification outdoor air system. In order to improve the forecast accuracy, the division of thermal area is considered. This paper also presents a system control optimization model, and optimizes the operation of the outdoor air system combined with the load forecast results of the neural network model. Under the scenario of potential energy storage and time-of-use tariff, the optimization control strategy is formulated to improve the flexibility of the system. The results show that the partition neural network model has high forecast accuracy. The root mean square error variation coefficients corresponding to the prediction results of moisture load and cooling load are 8.72% and 9.98% respectively. The optimization results can reduce the operation energy consumption and cost of the system by 27.2% and 29.2% in the whole air conditioning season respectively. The results provide a reference for the operation optimization of independent outdoor air humidification systems in residential buildings.
Keywords: load forecast; outdoor air; partition artificial neural network; solution humidification; heat storage;
498
0
0