Machine learning of heat pump system water usage patterns for optimized heat pump performance
An air to water heat pump system is configured to minimize operating cost of the system utilizing one or more of hot water demand patterns, present or predicted ambient conditions, and/or electrical power cost. The system may be configured to reduce production and/or storage of hot water during periods of low demand, and increase production and storage of hot or hotter water immediately prior to a period of predicted high demand for hot water. The system may be configured to take into account ambient weather conditions to increase production and storage of hot water during favorable ambient conditions, and/or to increase production and storage of hot water prior to predicted cold ambient conditions.
1 . A method of controlling an air-to-water heat pump system for a building having an evaporator that, in use, is exposed to ambient air from outside the building, and a tank system that stores a volume of hot water that has been heated by the heat pump, the method comprising:
utilizing training data to train a machine learning program to generate a model that is capable of predicting periods of increased demand for hot water in a building;
utilizing the machine learning program to predict a period of low demand for hot water, predict a period of high demand for hot water that has a greater demand for hot water than the period of low demand for hot water, and monitor a volume of hot water stored in the tank system, wherein the volume of stored hot water in the tank system is determined utilizing at least six water temperature sensors that are configured such that each water temperature sensor has a unique volume of stored hot water associated therewith such that measured water temperatures from the at least six water temperature sensors can be utilized to measure the volume of hot water stored in the tank system to determine at least six non-equal volumes of stored hot water;
wherein the machine learning program predicts demand for hot water in the building based, at least in part, on data from the at least six water temperature sensors;
utilizing the machine learning program to implement a load up cycle prior to a predicted period of high demand, the load up cycle including:
1) reducing production of hot water by the heat pump to reduce the volume of hot water stored in the tank system; followed by:
2) increasing heat pump output to increase at least one of a temperature and a volume of hot water stored in the tank system prior to a predicted period of high demand for hot water in a building.
2 . The method of claim 1 , wherein:
training the machine learning program includes causing the machine learning program to track water temperature at each of the at least six water temperature sensors, and time stamp each significant change in water temperature, wherein significant changes in water temperature are determined according to predefined criteria.
3 . The method of claim 2 , wherein:
the predefined criteria comprises a change in water temperature of at least a predefined magnitude over a predefined time interval.
4 . The method of claim 3 , wherein:
the predefined criteria comprises a change in water temperature of at least 10° F. during a 12 hour period of time.
5 . The method of claim 2 , wherein:
the at least six water temperature sensors are arranged in a serial manner along a flow path of hot water through the tank system with a first sensor located adjacent to an inlet of the flow path that receives hot water from the heat pump, and a sixth sensor located adjacent to an exit of the flow path, such that a volume of stored hot water associated with each sensor comprises a volume of water above a predefined temperature stored in the tank system between the sensor and the tank system inlet that receives hot water from the heat pump.
6 . The method of claim 5 , wherein:
the system is configured to time stamp and store each ON and OFF at which the heat pump is turned on and off, respectively, and store heat pump run times for each ON and OFF time interval.
7 . The method of claim 6 , wherein:
the system is configured to store changes in water temperature measured by the at least six water temperature sensors and store the volumes of stored hot water associated with the stored changes in water temperature.
8 . The method of claim 7 , wherein:
the machine learning program is configured to determine a thermal output of the heat pump during each run time based, at least in part, on ambient air temperature.
9 . The method of claim 1 , wherein:
the machine learning program is configured to monitor ambient air temperature and adjust the volume of hot water stored in the tank system to reduce a cost of energy required to increase the volume of hot water stored in the tank system prior to a predicted demand for hot water in a building.
10 . The method of claim 9 , wherein:
the machine learning program is configured to receive predicted ambient temperature data and adjust a temperature and/or a volume of hot water stored in the tank system to reduce a cost of energy required to increase the temperature and/or volume of hot water stored in the tank system during a load up cycle.
11 . The method of claim 10 , wherein:
the heat pump utilizes electric power to produce hot water;
the machine learning program is configured to receive data concerning cost of electrical power and adjust the volume of hot water stored in the tank system to reduce a cost of energy required to increase the volume of hot water stored in the tank system during a load up cycle.
12 . The method of claim 11 , wherein:
the machine learning program is configured to utilize ambient temperature data and the cost of electrical power to predict the cost of electrical power required to implement a load up cycle prior to a predicted period of high demand for hot water in a building;
the machine learning program is configured to minimize the predicted cost of electrical power based, at least in part, on the ambient temperature data and the cost of electrical power.
13 . The method of claim 12 , including:
using a backup source of hot water to supply hot water if necessary to meet demand for hot water in a building.
14 . The method of claim 1 , including:
configuring the system to operate in a baseline mode and cause the heat pump to produce hot water at a baseline temperature between at least some periods of high demand for hot water, followed by causing the heat pump to produce water at a temperature that is greater than the baseline temperature during a load up cycle.
15 . The method of claim 14 , including:
configuring the system such that, in the baseline mode the system turns the heat pump ON and OFF when measured temperatures from a pair of temperature sensors drop to a first baseline set temperature and increase to a second baseline set temperature, respectively;
configuring the system to utilize first and second load up temperatures during a load up cycle, wherein the first and second load up temperatures are greater than the first and second baseline temperatures, respectively.