Systems and methods for determining the uncertainty in parameters of an energy use model
    42.
    发明授权
    Systems and methods for determining the uncertainty in parameters of an energy use model 有权
    确定能源使用模型参数不确定度的系统和方法

    公开(公告)号:US09355069B2

    公开(公告)日:2016-05-31

    申请号:US14137627

    申请日:2013-12-20

    Abstract: Systems and methods for determining the uncertainty in parameters of a building energy use model are provided. A disclosed method includes receiving an energy use model for a building site. The energy use model includes one or more predictor variables and one or more model parameters. The method further includes calculating a gradient of an output of the energy use model with respect to the model parameters, determining a covariance matrix using the calculated gradient, and using the covariance matrix to identify an uncertainty of the model parameters. The uncertainty of the model parameters may correspond to entries in the covariance matrix.

    Abstract translation: 提供了用于确定建筑物能量使用模型参数不确定度的系统和方法。 公开的方法包括接收建筑工地的能量使用模型。 能量使用模型包括一个或多个预测变量和一个或多个模型参数。 该方法还包括相对于模型参数计算能量使用模型的输出的梯度,使用所计算的梯度来确定协方差矩阵,以及使用协方差矩阵来识别模型参数的不确定性。 模型参数的不确定性可以对应于协方差矩阵中的条目。

    BUILDING CONTROL SYSTEM WITH HEAT LOAD ESTIMATION USING DETERMINISTIC AND STOCHASTIC MODELS

    公开(公告)号:US20200371482A1

    公开(公告)日:2020-11-26

    申请号:US16418715

    申请日:2019-05-21

    Abstract: An environmental control system for a building including building equipment operable to affect a variable state or condition of the building. The system includes a controller including a processing circuit. The processing circuit can obtain training data relating to operation of the building equipment and can perform a system identification process to identify parameters of a system model using the training data. The processing circuit can augment the system model with a disturbance model and estimate values of a historical heat disturbance in the training data based on the augmented system model. The processing circuit can train one or more heat disturbance models based on the training data and the estimated values. The processing circuit can predict a heat disturbance using the augmented system model along with the one or more heat disturbance models and can control the building equipment based on the predicted heat disturbance.

    MODEL PREDICTIVE MAINTENANCE SYSTEM WITH AUTOMATIC SERVICE WORK ORDER GENERATION

    公开(公告)号:US20190271978A1

    公开(公告)日:2019-09-05

    申请号:US16418686

    申请日:2019-05-21

    Abstract: An automatic work order generation system for model predictive maintenance (MPM) of building equipment including an MPM system including an equipment controller to operate the building equipment to affect an environmental condition of a building. The MPM system can perform a predictive optimization to determine a service time at which to service the building equipment. The automatic work order generation system includes an equipment service scheduler that can determine whether any service providers are available to perform equipment service within a predetermined time range of the service time. In response to determining that service providers are available to perform the equipment service, the equipment service scheduler can select a service provider and an appointment time based on one or more service provider attributes. The equipment service scheduler can generate a service work order and transmit the service work order to the service provider to schedule a service appointment.

    Systems and methods for monetizing and prioritizing building faults

    公开(公告)号:US10402767B2

    公开(公告)日:2019-09-03

    申请号:US14179672

    申请日:2014-02-13

    Abstract: A fault parameter of an energy consumption model is modulated. The energy consumption model is used to estimate an amount of energy consumption at various values of the fault parameter. A first set of variables is generated including differences between a target value of the fault parameter and the various values of the fault parameter. A second set of variables is generated including differences between an estimated amount of energy consumption with the fault parameter at the target value and the estimated amounts of energy consumption with the fault parameter at the various values. The first set of variables and second set of variables are used to develop a regression model for the fault parameter. The regression model estimates a change in energy consumption based on a change in the fault parameter. Regression models are developed for multiple fault parameters and used to prioritize faults.

    SYSTEMS AND METHODS FOR DETECTING CHANGES IN ENERGY USAGE IN A BUILDING

    公开(公告)号:US20190212712A1

    公开(公告)日:2019-07-11

    申请号:US16352536

    申请日:2019-03-13

    Abstract: A method for operating HVAC equipment includes obtaining building data for each of a plurality of time steps. The building data relates to resource usage of HVAC equipment. The method also includes calculating a recursive residual for each of a plurality of overlapping time periods using the building data. Each overlapping time period includes a subset of the plurality of time steps. The method also includes, for each of the plurality of time steps, calculating a metric based on the recursive residuals for overlapping time periods that end on or before the time step and automatically detecting a change in static factors for one or more buildings served by the HVAC equipment by comparing the metrics for the plurality of time steps based on a statistical property of the metrics.

    Building energy storage system with peak load contribution cost optimization

    公开(公告)号:US10324483B2

    公开(公告)日:2019-06-18

    申请号:US15405234

    申请日:2017-01-12

    Abstract: An energy storage system for a building includes a battery and an energy storage controller. The battery is configured to store electrical energy purchased from a utility and to discharge stored electrical energy for use in satisfying a building energy load. The energy storage controller is configured to generate a cost function including a peak load contribution (PLC) term. The PLC term represents a cost based on electrical energy purchased from the utility during coincidental peak hours in an optimization period. The controller is configured to modify the cost function by applying a peak hours mask to the PLC term. The peak hours mask identifies one or more hours in the optimization period as projected peak hours and causes the energy storage controller to disregard the electrical energy purchased from the utility during any hours not identified as projected peak hours when calculating a value for the PLC term.

Patent Agency Ranking