摘要
采用人工神经网络建立建筑负荷预测模型,采用粒子群算法进行空调系统设备运行参数寻优。结合工程实例,对某办公建筑的负荷进行预测,对设备运行参数进行寻优。建筑负荷预测结果与实际负荷的平均相对误差为7.7%,预测模型具有较好的预测能力。采用TRNSYS软件建立该办公楼空调系统仿真模型,按优化后的设备运行参数,对空调系统耗电量进行模拟,模拟耗电量比实际耗电量低9.9%。
The artificial neural network is used to establish a building load forecasting model,and the particle swarm algorithm is used to optimize the operating parameters of the air-conditioning system equipment.Combined with an engineering example,the load of an office building is predicted and the equipment operation parameters are optimized.The average relative error between the building load forecasting result and the actual load is 7.7%,and the forecasting model has good forecasting ability.The TRNSYS software is used to establish a simulation model of the air-conditioning system in the office building,and the power consumption of the air-conditioning system is simulated according to the optimized equipment operating parameters.The simulated power consumption is 9.9%lower than the actual power consumption.
作者
杨滨
崔红社
孙锐
马倩倩
牛梦涵
YANG Bin;CUI Hongshe;SUN Rui;MA Qianqian;NIU Menghan
出处
《煤气与热力》
2022年第3期19-21,共3页
Gas & Heat
关键词
负荷预测
神经网络
粒子群算法
设备运行参数
load forecasting
neural network
particle swarm algorithm
equipment operating parameters
