基于灰色理论的建筑需求冷量预测研究
Prediction of building demand cooling based on grey theory
摘要：
建筑需求冷量预测能够帮助建筑运行人员提前了解建筑的需求冷量，制定最优的空调系统运行策略，以实现系统安全节能运行。针对某综合大楼的间歇制冷空调系统，基于其历史运行数据，应用灰色预测对该系统早晨的需求冷量进行了研究。建立了多个等维度新陈代谢灰色模型，预测了不同工作日的早晨需求冷量。对比分析了仅以历史冷量建模的GM(1,1)模型和考虑室外气温对冷量影响的GM(1,2)模型的预测准确性。结果表明，GM(1,2)模型较GM(1,1)模型预测精度更高，即考虑到室外气温对冷量的影响时，能够更准确地预测建筑需求冷量。灰色预测模型简单、计算量小，易于集成到建筑设备管理系统中，预测得到的需求冷量可以为空调系统运行优化提供参考。
Abstract：
The prediction of building demand cooling can help building operators understand the demand cooling of the building in advance, and make the optimal operation strategy of the air conditioning system for safe and energy saving operation. Based on the historical operation data of the intermittent air conditioning system of a complex building, studies the demand cooling prediction of the building in the morning using the grey prediction. Establishes several equal-dimension-new-information grey models to predict the morning demand cooling of different working days. Compares the predication accuracy of the GM(1,1) model only based on historical cooling capacity and the GM(1,2) model considering the effect of outdoor air temperature on demand cooling. The results show that the GM(1,2) model has a higher prediction accuracy than the GM(1,1) model by using the average outdoor air temperature as an independent variable. The grey prediction model can be integrated into the building management system (BMS) easily due to the simple model and less computation demand, and the predicted demand cooling can be used as a reference for the operation of the air conditioning system.
Keywords:grey prediction, grey modeling, intermittent air conditioning system, demand cooling prediction, data mining