返回
Aggregated smart meter data driven occupant behavior analysis based on inverse problem optimization
DOI:10.1016/j.enbuild.2025.116074.png)
摘要
En 中文
本研究为自下而上的建筑能耗终端用途建模提供了创新性进展,这对住宅能源系统分析与规划至关重要。传统模型依赖来自不同来源的广泛人口统计、行为及设备数据,但这些方法常影响精度。为解决此问题,本研究引入了一种基于半小时间隔智能电表数据的参数校准新方法,尽管其分辨率受容量、管理及隐私约束而较低。纳入这些数据提升了能源需求估算的精度,并准确再现了 occupant behavior (OB)。该方法优化了模型精度并识别了不同家庭类型中的 OB,为制定针对气候目标实现至关重要的定向节能措施提供了宝贵见解。此外,它还能追踪随时间变化的OB,这是传统统计方法无法实现的,因而增强了其应用价值。然而,本研究认识到需通过整合其他数据源(如智能手机应用的运动数据及基于传感器的家庭测量数据)来进一步改进。这些改进有望革新能源系统分析,为建设更可持续、无碳的社会做出贡献。
Keyword:
Energy modeling
Smart meters
Residential sector
Occupant behavior
Parameter calibration
Energy demand estimation
Data-driven analysis
Sustainability
Climate goals
Data integration
期刊
IF:
7.1
论文数:
1.5W
被引数:
6.8W
机构
暂无机构信息
引用论文
The impact of occupants' behaviours on building energy analysis: A research review居住者行为对建筑能耗分析的影响: 研究综述
Enhancing building energy consumption prediction introducing novel occupant behavior models with sparrow search optimization and attention mechanisms: A case study for forty-five buildings in a university community
ENERGY
IF9.4
Analysis and modeling of air conditioner usage behavior in residential buildings using monitoring data during hot and humid season基于湿热季节监测数据的住宅空调使用行为分析与建模
ENERGY AND BUILDINGS
IF7.1
MARTINI: Smart meter driven estimation of HVAC schedules and energy savings based on Wi-Fi sensing and clustering
APPLIED ENERGY
IF11
Model predictive control for building loads connected with a residential distribution grid与住宅配电网连接的建筑物负荷的模型预测控制
APPLIED ENERGY
IF11

