空调系统负荷分段预测与研究
|
摘要
为了改善空调系统的能源消耗,根据空调系统实际运行时的环境数据和负荷数据,采用神经网络的方式建立空调系统的负荷预测模型,通过负荷预测得到博物馆所需的空调负荷,以此作为空调系统节能优化的基础。根据BP神经网络具有的非线性特性以及强大的自学习自适应能力,对博物馆的空调负荷进行预测,建立基于BP神经网络的负荷预测模型,分析研究仿真得到结果,发现其不足之处主要体现在准确性上,之后对神经网络后改进进行分段预测,将通过仿真实验预测的结果与实际运行的负荷进行对比,结果表明改进后预测的结果具有较好的准确性。
In order to improve the energy consumption of air conditioning system, this paper established the load forecasting model of air conditioning system by using neural network, according to the environmental data and load data of the actual operation of the air conditioning system. The air conditioning load of the museum is obtained by the load forecasting, which is the basis of the energy saving optimization of the air conditioning system. According to the nonlinear characteristics and strong self learning and adaptive ability of the BP neural network, the air conditioning load of the museum is forecasted. Then the load forecasting model based on BP neural network is established, and the simulation results are also obtained, we can find that the deficiency is mainly reflected in the accuracy. Finally, the neural network is improved by subsection prediction, and the results of simulation experiment are compared with the actual load. It shows that the improved prediction results have good accuracy.
In order to improve the energy consumption of air conditioning system, this paper established the load forecasting model of air conditioning system by using neural network, according to the environmental data and load data of the actual operation of the air conditioning system. The air conditioning load of the museum is obtained by the load forecasting, which is the basis of the energy saving optimization of the air conditioning system. According to the nonlinear characteristics and strong self learning and adaptive ability of the BP neural network, the air conditioning load of the museum is forecasted. Then the load forecasting model based on BP neural network is established, and the simulation results are also obtained, we can find that the deficiency is mainly reflected in the accuracy. Finally, the neural network is improved by subsection prediction, and the results of simulation experiment are compared with the actual load. It shows that the improved prediction results have good accuracy.
引文
[1]郑慧凡,阎秀英,范晓伟.建筑物空调负荷计算方法研究进展[J].中原工学院学报,2007,18(5):1-5.
[2]温权,李敬如,赵静.空调负荷计算方法及应用[J].电力需求侧管理,2005,7(4):16-18.
[3]赵君有.基于灰色理论的中长期电力负荷的预测[D].沈阳:沈阳工业大学,2007.
[4]陈娟,吉培荣,卢丰.指数平滑法及其在负荷预测中的应用[J].三峡大学学报(自然科学版),2010,32(3):37-41.
[5]Wang H,Chang W L.Load forecasting for electrical power system based on BP neural network[C]//International Workshop on Education Technology and Computer Science.IEEE,2009:702-705.
[6]赵波峰,文远高,杨恒.四种空调负荷预测方法分析比较[J].建筑热能通风空调,2012,30(6):65-67.
[7]康重庆,周安石,王鹏.短期负荷预测中实时气象因素的影响分析及其处理策略[J].电网技术,2006,30(7):5-10.
[8]郑慧凡,白静,李安桂.BP神经网络在建筑物空调负荷预测中的应用评述[J].计算机应用与软件,2007,24(6):103-105.
[9]柳小桐.BP神经网络输入层数据归一化研究[J].机械工程与自动化,2010,(3):122-123.
[10]程玉桂,黎明,林明玉.基于遗传算法和BP神经网络的城区中长期电力负荷预测与分析[J].计算机应用,2010,30(1):224-226.
[2]温权,李敬如,赵静.空调负荷计算方法及应用[J].电力需求侧管理,2005,7(4):16-18.
[3]赵君有.基于灰色理论的中长期电力负荷的预测[D].沈阳:沈阳工业大学,2007.
[4]陈娟,吉培荣,卢丰.指数平滑法及其在负荷预测中的应用[J].三峡大学学报(自然科学版),2010,32(3):37-41.
[5]Wang H,Chang W L.Load forecasting for electrical power system based on BP neural network[C]//International Workshop on Education Technology and Computer Science.IEEE,2009:702-705.
[6]赵波峰,文远高,杨恒.四种空调负荷预测方法分析比较[J].建筑热能通风空调,2012,30(6):65-67.
[7]康重庆,周安石,王鹏.短期负荷预测中实时气象因素的影响分析及其处理策略[J].电网技术,2006,30(7):5-10.
[8]郑慧凡,白静,李安桂.BP神经网络在建筑物空调负荷预测中的应用评述[J].计算机应用与软件,2007,24(6):103-105.
[9]柳小桐.BP神经网络输入层数据归一化研究[J].机械工程与自动化,2010,(3):122-123.
[10]程玉桂,黎明,林明玉.基于遗传算法和BP神经网络的城区中长期电力负荷预测与分析[J].计算机应用,2010,30(1):224-226.