Systems, methods, and computer program products for staging chillers in a chiller group. Operational data is collected on chillers in a chiller group, and performance curves indicative of chiller efficiency generated for each chiller based on the operational data. During operation, a current thermal load and a current group efficiency is determined for the chiller group. Estimated group efficiencies are also determined for the chiller group for one or more scenarios in which one or more offline chillers are brought online, online chillers are taken offline, or both online chillers are taken offline and offline chillers are brought online. If the estimated efficiency of the chiller group is higher than the current efficiency for any of the scenarios, chillers in the chiller group are brought online or taken offline so that the chiller group operates in accordance with the most efficient scenario.

Systems, methods, and computer program products for staging chillers in a chiller group. Operational data is collected on chillers in a chiller group, and performance curves indicative of chiller efficiency generated for each chiller based on the operational data. During operation, a current thermal load and a current group efficiency is determined for the chiller group. Estimated group efficiencies are also determined for the chiller group for one or more scenarios in which one or more offline chillers are brought online, online chillers are taken offline, or both online chillers are taken offline and offline chillers are brought online. If the estimated efficiency of the chiller group is higher than the current efficiency for any of the scenarios, chillers in the chiller group are brought online or taken offline so that the chiller group operates in accordance with the most efficient scenario.

Environmental data of an environment of the building and cooling load demand data are received as first training data, which are used for training a first machine learning model to predict a cooling load demand from environmental data. Furthermore, control signals for the chiller plant and cooling power data resulting from applying the control signals to the chiller plant are received as second training data which are used for training a second machine learning model to predict a cooling power from control signals. Actual environmental data are received, from which a cooling load demand is predicted by the trained first machine learning model. Furthermore, candidate control signals for the chiller plant are generated, and from which a resulting cooling power is predicted by the trained second machine learning model. From the candidate control signals, applicable control signals are selected for which a predicted cooling power fulfills the predicted cooling load demand.

Techniques for providing an adaptive energy management system for responding to extreme weather conditions are described herein. In an embodiment, a server computer stores multiple policy datasets each representing HVAC control policy for different structure locations and one or more extreme weather conditions. The server computer receives weather condition data comprising a condition identifier of a then-current extreme weather condition in association with a location identifier specifying a particular geographical region. Based on the location identifier, a particular structure location, being within the particular geographic region, is identified. Based on the particular structure location, a particular policy dataset from among the policy datasets is identified. The particular policy dataset is transformed into HVAC equipment instructions, which the server computer transmits, over a network, to HVAC equipment at the particular structure location which, when executed, cause the HVAC equipment to execute an action in accordance with the particular policy dataset.

A thermostat of an HVAC system receives active event parameters from a utility provider. The active event parameters include a start time, a stop time, and a predefined temperature setpoint for the active event, which is associated with a requirement to decrease energy consumption between the start time and the stop time. Following the start time, the thermostat adjusts a setpoint temperature of the HVAC system to the predefined setpoint temperature.

An air conditioning system control device 10 includes: a switching unit 11 that, when a parameter relating to the indoor environment in which the air conditioning system operates does not satisfy a first condition while the air conditioning system is operating in a first operation mode that is an operation mode in which setting values computed on the basis of a prediction model are used as the setting values for the air conditioning system, switches the operation mode of the air conditioning system to a second operation mode that is an operation mode in which the computed setting values are not used as the setting values for the air conditioning system.

A HVAC controller includes a housing and one or more heat-generating components contained within the housing. The heat-generating components cause a temperature inside the housing to exceed a temperature outside the housing. The controller includes a temperature sensor configured to measure the temperature inside the housing and a controller event detector configured to detect, for at least one of the heat-generating components, a controller event that generates heat inside the housing. The controller further includes a temperature compensation module configured to identify a steady-state temperature gain associated with the detected controller event, to calculate a temperature offset using a summation of the steady-state temperature gain, to determine the temperature of the building zone outside the housing by subtracting the temperature offset from the temperature measured inside the housing, and to store the temperature offset.

A fault prediction system for building equipment includes one or more memory devices configured to store instructions that, when executed on one or more processors, cause the one or more processors to receive device data for a plurality of devices of the building equipment, the device data indicating performance of the plurality of devices; generate, based on the received device data, a plurality of prediction models comprising at least one of single device prediction models generated for each of the plurality of devices or cluster prediction models generated for device clusters of the plurality of devices; label each of the plurality of prediction models as an accurately predicting model or an inaccurately predicting model based on a performance of each of the plurality of prediction models; and predict a device fault with each of the plurality of prediction models labeled as an accurately predicting model.

An HVAC system is disclosed. The HVAC system includes at least one heat exchanger unit disposed within a predefined area. The HVAC system further includes at least one frame cooperating with each of the at least one heat exchanger unit. The at least one frame includes a guiding assembly configured to move each of the at least one heat exchanger unit across the predefined area. The guiding assembly includes a guiding rail. The guiding assembly further includes at least one slider cooperating with the guiding rail to enable movement of the at least one heat exchanger unit. Each of the at least one slider comprises a fastening unit configured to attach a heat exchanger unit to an associated slider. The guiding assembly includes at least one actuator, wherein each of the at least one actuator is configured to move an associated slider from the at least one slider.

An information processing apparatus includes a memory storing equipment information, an equipment characteristics table, and an energy saving control menu, a receiver configured to receive energy saving control and a condition and acquire operation data and measurement data from a controller of equipment, a processor, and a display outputting a result. The processor obtains an actual load factor based on the operation data and the measurement data, obtains a control characteristics correction parameter regarding control characteristics of the equipment, estimates a load factor distribution for an estimation target period according to the actual load factor. Further, the processor corrects the control characteristics, calculates, according to the load factor distribution and the corrected control characteristics, a power consumption of the equipment for each of a case where the energy saving control is performed and a case where the energy saving control is not performed, and calculates the energy saving effect.