基于深度学习的节约型园林电能耗预测模型  

Prediction model of energy saving garden electric energy consumption based on deep learning

作　　者：龙征宇 孙琳[2] LONG Zheng-yu;SUN Lin(Tourism and Urban-Rural Planning College of CDUT,Chengdu 610059,China;Business School,Chengdu University of Technology,Chengdu 610059,China)

机构地区：[1]成都理工大学旅游与城乡规划学院,成都610059 [2]成都理工大学商学院,成都610059

出　　处：《信息技术》2021年第9期101-105,110,共6页Information Technology

摘　　要：为了精准预测节约型园林电能耗,提出了基于深度学习的节约型园林电能耗预测模型。该模型选取平均气温、最高气温、最低气温、霜点温度、平均湿度五个气候因素和历史电能耗作为输入变量,节约型园林电能耗作为输出变量,通过无监督预训练以及监督微调两部分实现电能耗预测。测试结果表明,该模型预测节约型园林短期、中期以及长期电能耗均具有较高精度,可以为节约型园林能源节约提供理论依据。In order to accurately predict the energy consumption of energy-saving garden,a prediction model of energy-saving garden based on deep learning is proposed.In this model,five climate factors including average temperature,maximum temperature,minimum temperature,frost point temperature and average humidity and historical power consumption are selected as input variables,while energy-saving garden power consumption is selected as output variable.Power consumption prediction is realized through unsupervised pre-training and supervised fine-tuning.The test results show that the model has high accuracy in predicting the short-term,medium-term and long-term energy consumption of energy-saving landscape,which can provide a theoretical basis for energy saving of energy-saving landscape.

关 键 词：深度学习 节约型园林 电能耗 预测模型 测试实验 

分 类 号：TP302[自动化与计算机技术—计算机系统结构]