Abstract: An energy optimization system for a building includes a processing circuit configured to provide a first bid including one or more first participation hours and a first load reduction amount for each of the one or more first participation hours to a computing system. The processing circuit is configured to operate one or more pieces of building equipment based on one or more first equipment loads and receive one or more awarded or rejected participation hours from the computing system responsive to the first bid. The processing circuit is configured to generate one or more second participation hours, a second load reduction amount for each of the one or more second participation hours, and one or more second equipment loads based on the one or more awarded or rejected participation hours and operate the one or more pieces of building equipment based on the one or more second equipment loads.

Abstract: A method for controlling production of one or more refined resources by an energy provider includes predicting a demand for the refined resources by one or more consumers of the refined resources as a function of an incentive offered by the energy provider. The method further includes performing an optimization of an objective function subject to a constraint based on the predicted demand for the refined resources to determine an amount of the refined resources for the energy provider to produce and a value of the incentive at multiple times within a time period. The method also includes providing setpoints for equipment of the energy provider that cause the equipment to produce the amount of the refined resources determined by performing the optimization.

Abstract: A building management system includes a controller configured to control building equipment by providing a control input to the building equipment for each of the plurality of time steps and generate a set of training data for a system model for the building. The training data includes input training data and output training data for each of the plurality of time steps. The controller is further configured to perform a system identification process to identify parameters of the system model. The system identification process includes predicting, for each time step, a predicted value for one or more of the output variables for each of a plurality of subsequent time steps, generating a prediction error function by comparing the output training data to the predicted values, and optimizing the prediction error function to determine values for the parameters of the system model that minimize the prediction error function.

Abstract: A building management system includes building equipment operable generate training data relating to behavior of a building system and a controller configured to perform a system identification process that includes generating a prediction error function based on the training data and a system model, generating initial guesses of one or more parameters of the system model, running an optimization problem of the prediction error function for a first group of iterations, discarding, after the first group of iterations, a portion of the initial guesses based on one or more criteria and ranking a remaining portion of the initial guesses, running the optimization problem of the prediction error function for a top-ranked initial guess of the remaining portion to local optimality to identify a first set of values of the one or more parameters, and identifying the one or more parameters as having the first set of values.

Abstract: A building system includes building equipment operable to consume one or more resources and a control system configured to generate, based on a prediction model, predictions of a load on the building equipment or a price of the one or more resources for a plurality of time steps in an optimization period, solve, based on the predictions, an optimization problem to generate control inputs for the equipment that minimize a predicted cost of consuming the resources over the optimization period, control the building equipment to operate in accordance with the control inputs, monitor an error metric that characterizes an error between the predictions and actual values of the at least one of the load on the building equipment or the price of the one or more resources during the optimization period, detect an occurrence of a trigger condition, and in response to detecting the trigger condition, update the prediction model.

Abstract: A central plant includes an asset allocator configured to determine an optimal allocation of energy loads across central plant equipment. The asset allocator identifies sources configured to supply input resources, subplants configured to convert the input resources to output resources, and sinks configured to consume the output resources. The asset allocator generates a cost function and a resource balance constraint. The resource balance constraint requires balance between a total amount of each resource supplied by the sources and the subplants and a total amount of each resource consumed by the subplants and the sinks. The asset allocator determines the optimal allocation of the energy loads across the central plant equipment by optimizing the cost function subject to the resource balance constraint. The asset allocator is configured to control the central plant equipment to achieve the optimal allocation of the energy loads.

Abstract: A predictive power control system includes a battery configured to store and discharge electric power, a battery power inverter configured to control an amount of the electric power stored or discharged from the battery, and a controller. The controller is configured to predict a power output of a photovoltaic field and use the predicted power output of the photovoltaic field to determine a setpoint for the battery power inverter.

Abstract: A method for determining a participation strategy for a load-following-block rate structure and controlling equipment in accordance with the participation strategy includes selecting a plurality of hedge percentages, running a simulation over a time period for each of the plurality of hedge percentages, determining, for each of the plurality of hedge percentages, a total cost for the time period based on the simulation for the hedge percentage, selecting a recommended hedge percentage based on the total costs, and controlling the equipment to consume a total amount of at least one of energy or power from a utility provider. The recommended hedge percentage of the total amount is priced at a fixed rate and a remainder of the total amount is priced at a variable rate.

Abstract: A building energy system includes equipment operable to consume, store, or generate one or more resources subject to a block-and-index rate structure. The building energy system includes a controller configured to obtain a cost function that represents a block of the resource(s) from the utility provider as being sourced from a first supplier at a fixed rate and a remainder of the resource(s) from the utility provider as being sourced from a second supplier at a variable rate. The controller is configured to optimize the cost function to generate values for one or more decision variables that indicate an amount of resource(s) to purchase, store, generate, or consume at each of a plurality of time steps, and control the equipment to achieve the values of the one or more decision variables at each of the time steps.

Abstract: A method includes operating equipment to consume energy resources including energy or power purchased from a utility, and obtaining a block-and-index rate profile for a future time period. The block-and-index rate profile includes a block rate and a block size for each of a plurality of sub-periods in the future time period. The block size for a sub-period identifies an amount of energy or power priced at the block rate for the sub-period. The method also includes applying the block-and-index rate profile in an optimization process for the equipment over the time period, running the optimization process, and allocating energy resources to the equipment over the time period in accordance with a result of the optimization process.

Abstract: A building management system includes building equipment operable generate training data relating to behavior of a building system and a controller configured to perform a system identification process that includes generating a prediction error function based on the training data and a system model, generating initial guesses of one or more parameters of the system model, running an optimization problem of the prediction error function for a first group of iterations, discarding, after the first group of iterations, a portion of the initial guesses based on one or more criteria and ranking a remaining portion of the initial guesses, running the optimization problem of the prediction error function for a top-ranked initial guess of the remaining portion to local optimality to identify a first set of values of the one or more parameters, and identifying the one or more parameters as having the first set of values.

Abstract: Systems and methods for implementing an economic model predictive control (EMPC) strategy in any resource-based system include an EMPC tool. The EMPC tool is configured to present user interfaces to a client device. The EMPC tool is further configured to receive first user input including resources and subplants associated with a central plant. The EMPC tool is also configured to receive second user input including sinks and connections between central plant equipment. The EMPC tool also includes a data model extender configured to extend a data model to define new entities and/or relationships specified by user input. The EMPC tool also includes a high level EMPC algorithm configured to generate an optimization problem and an asset allocator configured to solve the resource optimization problem in order to determine optimal control decisions used to operate the central plant.

Abstract: An energy storage system includes a photovoltaic energy field, a stationary energy storage device, an energy converter, and a controller. The photovoltaic energy field converts solar energy into electrical energy and charges the stationary energy storage device with the electrical energy. The energy converter converts the electrical energy stored in the stationary energy storage device into AC power at a discharge rate and supplies a campus with the AC power at the discharge rate. The controller generates a cost function of the energy consumption of the campus across a time horizon which relates a cost to operate the campus to the discharge rate of the AC power supplied by the stationary energy storage device. The controller applies constraints to the cost function, determines a minimizing solution to the cost function which satisfies the constraints, and controls the energy converter.

Abstract: A method for controlling HVAC equipment includes using a dynamic thermal model that describes heat transfer characteristics of a building to predict a temperature of the building as a function of control inputs to HVAC equipment that operate to affect the temperature of the building. The method includes obtaining time-varying utility prices and a predicted heating or cooling load for the building and performing a predictive control process using the dynamic thermal model, the time-varying utility prices, and the predicted heating or cooling load to generate the control inputs to the HVAC equipment subject to constraints on the temperature of the building.

Abstract: A building control system determines the uncertainty in a break even temperature parameter of an energy use model. The energy use model is used to predict energy consumption of a building site as a function of the break even temperature parameter and one or more predictor variables. The uncertainty in the break even temperature parameter is used to analyze energy performance of the building site.

Abstract: An energy storage system includes a photovoltaic energy field, a stationary energy storage device, an energy converter, and a controller. The photovoltaic energy field converts solar energy into electrical energy and charges the stationary energy storage device with the electrical energy. The energy converter converts the electrical energy stored in the stationary energy storage device into AC power at a discharge rate and supplies a campus with the AC power at the discharge rate. The controller generates a cost function of the energy consumption of the campus across a time horizon which relates a cost to operate the campus to the discharge rate of the AC power supplied by the stationary energy storage device. The controller applies constraints to the cost function, determines a minimizing solution to the cost function which satisfies the constraints, and controls the energy converter.

Abstract: An energy storage system includes a photovoltaic energy field, a stationary energy storage device, an energy converter, and a controller. The photovoltaic energy field converts solar energy into electrical energy and charges the stationary energy storage device with the electrical energy. The energy converter converts the electrical energy stored in the stationary energy storage device into AC power at a discharge rate and supplies a campus with the AC power at the discharge rate. The controller predicts a required load of the campus and an electrical generation of the photovoltaic energy field across a time horizon and optimizes a cost function subject to a set of constraints to determine a discharge rate of the AC power to achieve a desired power factor. At least one of the set of constraints applied to the cost function ensures that the energy converter can convert the electrical energy stored in the stationary energy storage device into AC power having the determined power factor and discharge rate.

Abstract: A model predictive maintenance system for building equipment that performs operations including obtaining an objective function defining a cost of operating and performing maintenance on the equipment as a function of operating and maintenance decisions for time steps within a time period of a life cycle horizon and including performing a first computation of the objective function under a first scenario where maintenance is performed on the equipment during the period, a result of the first computation indicating a first cost. The operations include performing a second computation under a second scenario in which maintenance is not performed during the period, a result indicating a second cost. The operations include initiating an automated action to perform maintenance on the equipment in accordance with decisions defined by the first scenario if the first cost is less than or equal to the second cost.

Abstract: A model predictive maintenance system for building equipment including one or more processing circuits including processors and memory storing instructions that, when executed by the processors, cause the processors to perform operations. The operations include obtaining an objective function that defines a cost of operating the building equipment and performing maintenance on the building equipment as a function of operating decisions and maintenance decisions for the building equipment for time steps within a time period. The operations include performing an optimization of the objective function to generate a maintenance and replacement strategy for the building equipment over a duration of an optimization period. The operations include estimating a savings loss predicted to result from a deviation from the maintenance and replacement strategy. The operations include adjusting an amount of savings expected to be achieved by energy conservation measures for the building equipment based on the savings loss.

Abstract: An energy storage system for a building includes a battery asset configured to store electricity and discharge the stored electricity for use in satisfying a building electric load. The system includes a planning tool configured to identify one or more selected functionalities of the energy storage system and generate a cost function defining a cost of operating the energy storage system over an optimization period. The cost function includes a term for each of the selected functionalities. The planning tool is configured to generate optimization constraints based on the selected functionalities, attributes of the battery asset, and the electric energy load to be satisfied. The planning tool is configured to optimize the cost function to determine optimal power setpoints for the battery asset at each of a plurality of time steps of the optimization period.