Abstract:
A frequency response controller includes a high level controller configured to receive a regulation signal from an incentive provider, determine statistics of the regulation signal, and use the statistics of the regulation signal to generate a frequency response midpoint. The controller further includes a low level controller configured to use the frequency response midpoint to determine optimal battery power setpoints and use the optimal battery power setpoints to control an amount of electric power stored or discharged from a battery during a frequency response period.
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:
In one aspect, a system for operations an energy plant obtains thermal energy load allocation data indicating time dependent thermal energy load of the energy plant. The system determines, for a time period, an operating state of the energy plant from a plurality of predefined operating states based on the thermal energy load allocation data. The system determines operating parameters of the energy plant according to the determined operating state. The system operates the energy plant according to the determined operating parameters.
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.
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.
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.
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.
Abstract:
A building energy system includes a controller configured to obtain representative loads and rates for a plurality of scenarios and generate a cost function comprising a risk attribute and multiple demand charges. Each of the demand charges corresponds to a demand charge period and defines a cost based on a maximum amount of at least one of the energy resources purchased within the corresponding demand charge period. The controller is configured to determine, for each of the multiple demand charges, a peak demand target for the corresponding demand charge period by performing a first optimization of the risk attribute over the plurality of the scenarios, allocate an amount of the one or more energy resources to be consumed, produced, stored, or discharged by the building equipment by performing a second optimization subject to one or more constraints based on the peak demand target for each of the multiple demand charges.
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.
Abstract:
A frequency response optimization system includes a battery configured to store and discharge electric power, a power inverter configured to control an amount of the electric power stored or discharged from the battery, and a frequency response controller. The frequency response controller includes receiving a regulation signal from an incentive provider, determining statistics of the regulation signal, using the statistics of the regulation signal to generate a frequency response midpoint, and using the frequency response midpoint to determine optimal battery power setpoints for the power inverter. The power inverter is configured to use the optimal battery power setpoints to control the amount of the electric power stored or discharged from the battery.