Variable air volume modeling for an HVAC system
Using information available from the controller or controllers of air-handling units, a remote server uses a heuristic model to determine settings for the air-handling units. Rather than just using rules for each air-handling unit, a model-based solution determines the settings. The model is used to optimize operation of the air distribution. In additional or alternative embodiments, measurements are gathered and used to derive analytics. The measurements may include data not otherwise used for rule-based control of the air handling unit. The analytics are used to predict needs, as inputs to the modeling, identify problems, and/or identify opportunities.
1. A control system for heating, ventilation, and air conditioning (HVAC), the control system comprising:
an air-handling unit having a plurality of sensors from the group of temperature, relative humidity, fan speed, pressure, input power, and fan flow for a variable speed drive of a fan of the air-handling unit;
a network connected with a controller of the air-handling unit;
a memory configured to store measurements from the plurality of the sensors of the air-handling unit and a heuristic model of the air-handling unit; and
a cloud server remote from the air-handling unit and connected with the network, the cloud server configured to receive the measurements, to identify a setting of an operational parameter for the air-handling unit solving the heuristic model using the measurements, the setting identified from an iterative test based on the heuristic model with different values of the operational parameter, and output the setting of the operational parameter;
wherein the air-handling unit is controlled by the output setting of the operational parameter, and
wherein the cloud server determines a diversity from a fan flow set point of the fan and a fan designed maximum flow, and wherein the cloud server is configured to indicate a mismatch of the fan with a space based on the diversity.
2. The control system of claim 1 wherein the heuristic model comprises a machine-learnt classifier, and wherein the cloud server is configured to solve by input of the measurements to the machine-learnt classifier.
3. The control system of claim 2 wherein the machine-learnt classifier comprises an on-going machine learning classifier.
4. The control system of claim 1 the cloud server is configured to derive a characteristic from the measurements and is configured to solve the heuristic model using the characteristic.
5. The control system of claim 1 wherein the operational parameter comprises control parameters for operating the aft-handling unit, the cloud server configured to provide the control parameters to the controller.
6. The control system of claim 1 wherein the plurality of the sensors comprise sensors for the fan flow, the pressure, fan speed, and the input power, and wherein the cloud server is configured to determine efficiency of the fan, a demand curve, energy consumption, load, or capacity trend.
7. The control system of claim 6 wherein the cloud server is configured to indicate a problem for the fan.
8. A control system for heating, ventilation, and air conditioning (HVAC), the control system comprising:
an air-handling unit having a plurality of sensors from the group of temperature, relative humidity, fan speed, pressure, input power, and fan flow for a variable speed drive of a fan of the air-handling unit;
a network connected with a controller of the air-handling unit;
a memory configured to store measurements from the plurality of the sensors of the air-handling unit and a heuristic model of the air-handling unit; and
a cloud server remote from the air-handling unit and connected with the network the cloud server configured to receive the measurements to identify a setting of an operational parameter for the air-handling unit solving the heuristic model using the measurements, the setting identified from an iterative test based on the heuristic model with different values of the operational parameter, and output the setting of the operational parameter;
wherein the air-handling unit is controlled by the output setting of the operational parameter, and wherein the air-handling unit is one of a plurality of air-dandling units, wherein the cloud server identifies a rogue zone or a critical zone of the plurality of air-handling units based on a number of actuator re-positioning, box pressures, and box flow.