摘要 针对空调为二次泵变流量系统时，考虑分区域供冷工况下，采用多目标回归方式解决负荷预测问题将有利于提高负荷预测准确性的情况，提出了两种多目标回归的中央空调负荷预测模型，即多目标支持向量回归(support vector regression, SVR）负荷预测模型和多目标长短期记忆（long short term memory，LSTM）神经网络负荷预测模型，利用上海市某医院的二次泵变流量系统数据对两个模型进行训练和预测，并与单目标回归预测模型进行比较.研究结果表明：相较单目标回归预测模型，两种多目标预测模型的预测精度更高；多目标SVR负荷预测模型较多目标LSTM负荷预测模型的预测准确性更高.
Abstract：For the air conditioning with secondary pump variable flow system, considering the regional cooling situation, the multi-objective regression method was used to solve the load forecasting problem for improving the accuracy of load forecasting. For the central air conditioning, two multi-objective regression load forecasting models of multi-objective support vector regression（SVR） and multi-objective long short-term memory（LSTM）neural network were proposed. The two models were used to train and predict on the data of the secondary pump variable flow system of the hospital in Shanghai, and the results were compared with those of the single objective regression prediction model. The results show that the prediction accuracies of the two multi-objective prediction models are higher than that of the single objective regression prediction model, and the multi-objective SVR load forecasting model has higher prediction accuracy than the multi-objective LSTM load forecasting model.
ZHOU X, FAN Z B,LIU G Q, et al. Cooling load prediction of shopping mall air conditioning based on multivariate nonlinear regression method[J]. Heating Ventilating & Air Conditioning, 2018,48(3):120-125.（in Chinese）
LI T T, BI H Q, WANG H L, et al. Prediction of air-conditioning load in metro station hall based on BP neutral network[J]. Computer Science, 2019,46(Sup2):590-594.（in Chinese）
GUO H, LI Z J. Comparisonand analysis of several load forecasting methods based on central air conditioning[J]. Building Energy & Environment, 2020,39(9):1-5.（in Chinese）
MO M, ZHAO L Z, GONG Y W, et al. Short-term prediction of air-conditioning cooling load based on particle swarm neural network[J]. Building Energy & Environment, 2018,37(5):6-8. （in Chinese）
DENG X, CHEN W J, DENG S Y. Short-term building cooling load predication based on the deep learning mo-del of LSTM[J]. Building Energy & Environment, 2021,40(11):25-27,51. （in Chinese）
FU C B, CHEN Y H, YANG G Y, et al. Research on energy consumption prediction of air-conditioning system using long-short term memory neural network[J]. Refrigeration and Air-Conditioning, 2021,21(8):36-39. （in Chinese）
GU C F, LUO Q H, XI P F, et al. Research on load forecasting method of building air conditioning based on PCA-LSTM neural network[J]. Modern Architecture Electric, 2021,12(10):1-7. （in Chinese）
LI Z R, LI C J, ZHU H. Parameter optimization of HVAC load forecasting model based on support vector regression[J]. Building Energy Efficiency, 2021,49(2):43-48. （in Chinese）
［10］
MASMOUDI S, ELGHAZEL H, TAIEB D, et al. A machine-learning framework for predicting multiple air pollutants′ concentrations via multi-target regression and feature selection[J]. Science of the Total Environment, DOI:/10.1016/j.scitotenv.2020.136991.
［11］
NAKANO F K, PLIAKOS K, VENS C. Deep tree-ensembles for multi-output prediction[J]. Pattern Recognition, DOI:10.1016/j.patcog.2021.108211.
［12］
SPYROMITROS-XIOUFIS E, TSOUMAKAS G, GROVES W, et al. Multi-target regression via input space expansion: treating targets as inputs[J]. Machine Learning, 2016,104(1):55-98.
［13］
ZHANG W, LIU X H, DING Y, et al. Multi-output LS-SVR machine in extended feature space[C]∥2012 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications (CIMSA) Proceedings. New York, USA:IEEE,2012:1-25.
［14］
WANG J, CHEN Z L, SUN K W, et al. Multi-target regression via target specific features[J]. Knowledge-Based Systems, 2019,170:70-78.
［15］
李航. 基于标签特定特征的多目标回归集成算法及应用[D]. 重庆：重庆邮电大学, 2019.
［16］
PLIAKOS K, VENS C. Network representation with clustering tree features[J]. Journal of Intelligent Information Systems， 2018,51(2):341-365.
［17］
MIHELCˇIC＇ M, DEROSKI S, LAVRACˇ N, et al. Redescription mining augmented with random forest of multi-target predictive clustering trees[J]. Journal of Intelligent Information Systems， 2018,50(1):63-96.
［18］
AHO T, ENKO B, DEROSKI S. Rule Ensembles for multi-target regression[C]∥2009 Ninth IEEE International Conference on Data Mining. New York, USA:IEEE,2009:21-30.
［19］
TANG Z H, LI Y Y, KUSIAK A. A deep learning mo-del for measuring oxygen content of boiler flue gas[J]. IEEE Access， 2020,8:12268-12278.
［20］
TANG Z H, WU X Y, CAO S X. Adaptive nonlinear model predictive control of the combustion efficiency under the NOx emissions and load constraints[J]. Energies, DOI:10.3390/en12091738.
