Method and system for modifying hot water usage

Abstract

The present disclosure relates to a computer-implemented method for regulating utility usage of a water supply system, the water supply system comprising a heat pump configured to transfer thermal energy from an ambient environment to a thermal energy storage medium and a control module configured to control the operation of the heat pump, the water supply system being configured to provide water heated by the thermal energy storage medium to a user at one or more water outlets, the method being performed by the control module and comprising: determining a water usage event when the water outlet is opened to provide water at a first temperature, the first temperature being set by a user; determining whether the water usage event is a short duration event based on at least one indication; and deploying one or more utility reduction strategies when it is determined that the water usage event is a short duration event.

Description

Technical Field

[0001] The present disclosure relates generally to utility management. In particular, the present disclosure relates to methods and systems that can be used to help change a user's hot water usage habits. Background Art

[0002] Whether in a commercial or domestic setting, hot water is needed all day, all year round. It goes without saying that providing hot water requires clean water and a heat source. To provide hot water, a heating system is provided to a water supply system, which is usually centralized, to heat the water to a predetermined temperature, for example, set by the user, and the heat source used is usually one or more electric heating elements or natural gas combustion. Typically, during periods of high energy (e.g., natural gas or electricity) demand, the utility supplier will implement a peak electricity price that increases the unit energy cost, partly to make up for the additional cost of having to purchase more energy to supply to consumers, and partly to discourage unnecessary energy use. Then, during periods of low energy demand, the utility supplier will implement an off-peak electricity price that reduces the unit energy cost to encourage customers to use energy during these off-peak periods rather than during peak periods, thereby achieving an overall more balanced energy consumption over time. However, this strategy is only effective if users are always aware of price changes and additionally make a conscious effort to change their energy consumption habits.

[0003] Clean water as a public utility is currently receiving a lot of attention. As clean water becomes increasingly scarce, many efforts have been made to educate the public on conserving clean water as well as developing systems and devices that reduce water consumption, such as aerated showers and faucets that reduce water flow, showers and faucets equipped with motion sensors that stop the flow of water when no motion is detected, etc. However, these systems and devices are limited to a single specific purpose and have only a limited impact on problematic water usage habits.

[0004] With increasing concern about the environmental impact of energy consumption, there has been a growing interest in using heat pump technology as a way to provide domestic hot water recently. A heat pump is a device that transfers thermal energy from a heat source to a heat reservoir. Although a heat pump requires electricity to do the job of transferring thermal energy from a heat source to a heat reservoir, it is generally more efficient than a resistance heater (electric heating element) because it typically has a coefficient of performance of at least 3 or 4. This means that, for the same amount of electricity, a heat pump can provide up to 3 or 4 times more heat to a user than a resistance heater.

[0005] The heat transfer medium that carries the thermal energy is called a refrigerant. Thermal energy from the air (e.g., outside air, or air from a hot room in the room) or from a ground source (e.g., a ground loop or a water-filled borehole) is transferred to the contained refrigerant, for example, via a heat exchanger. The now higher energy refrigerant is compressed, causing its temperature to rise significantly, and the now hotter refrigerant then exchanges the thermal energy to the hot water supply circuit via a heat exchanger. In the case of providing hot water, the heat extracted by the heat pump can be transferred to water in an insulated water tank, which serves as a thermal energy storage device, and the hot water can be used later when needed. As needed, the hot water can be transferred to one or more water outlets, such as a faucet, a shower, a radiator. However, compared to electric resistance heaters, heat pumps usually require more time for the water to reach the desired temperature, partly because heat pumps usually start slowly.

[0006] Since different homes, workplaces and commercial spaces have different requirements and preferences for hot water use, new ways of hot water supply are needed to make heat pumps a practical alternative to electric heaters. In addition, energy and clean water consumption may need to be regulated to save energy and water; however, regulating utility consumption cannot simply be a blanket restriction on usage.

[0007] It would therefore be desirable to provide improved methods and systems for supplying hot water. Summary of the invention

[0008] One aspect of the present technology provides a computer-implemented method for regulating utility usage of a water supply system, the water supply system comprising a heat pump configured to transfer thermal energy from an ambient environment to a thermal energy storage medium, and a control module configured to control the operation of the heat pump, the water supply system being configured to provide water heated by the thermal energy storage medium to a user at one or more water outlets, the method being performed by the control module and comprising: determining a water usage event when a water outlet is opened to provide water at a first temperature, the first temperature being set by the user; determining whether the water usage event is a short duration event based on at least one indication; and deploying one or more utility reduction strategies when it is determined that the water usage event is a short duration event.

[0009] According to an embodiment, in the event that a user has opened the water outlet for a short duration, where it is not possible for the hot water required by the user to reach the desired temperature before the water outlet is closed, the control module deploys one or more strategies to reduce utility consumption. This is particularly relevant because there may be situations when a heat pump is used to provide hot water, and when the heat pump is started, the energy extracted by the heat pump must first heat the thermal energy storage medium to the desired operating temperature before the thermal energy storage medium can fully heat the water. In the event that the heat pump is started in response to a demand for hot water, but the water outlet is closed before the water is heated to the desired temperature, the energy (electricity) used to operate the heat pump is wasted because the user does not actually receive hot water. Therefore, when such a short duration event is determined, utility consumption can be reduced by deploying one or more utility reduction strategies when the consumption is deemed unnecessary (the user does not benefit from the energy consumption).

[0010] In some embodiments, the method is performed by a machine learning algorithm MLA executing on the control module, the MLA being trained to associate the at least one indication with a short duration event based on sensor data obtained from the water supply system.

[0011] In some embodiments, the sensor data includes time of day, day of the week, date, water flow detection at the one or more water outlets, time elapsed since the water outlet was opened, main water temperature and / or water temperature at the one or more water outlets.

[0012] In some embodiments, the method may further include identifying, by the MLA algorithm, the at least one indication based on a utility usage pattern, wherein the MLA is trained to establish the utility usage pattern of the water supply system based on sensor data obtained from the water supply system.

[0013] In some embodiments, the utility usage pattern includes expected cooling water usage with respect to a time, day and / or date, expected heating water usage with respect to a time, day and / or date, expected energy usage with respect to a time, day and / or date, expected occupancy level with respect to a time, day and / or date, or a combination thereof.

[0014] In some embodiments, the at least one indication comprises a location of a water outlet, a time of a water usage event, a determination of cold water usage within a predetermined time prior to the water usage event, or a combination thereof.

[0015] In some embodiments, one or more utility reduction strategies may include the control module generating a prompt signal to prompt the user to set the water temperature to a second temperature lower than the first temperature. Optionally, the prompt signal may include a light signal at or near the water outlet, a flashing signal at or near the water outlet, a predetermined sound or tone generated at or near the water outlet, a verbal or multimedia prompt, or a combination thereof.

[0016] According to an embodiment, users of the water supply system are aware of situations where they need hot water but have not used the water long enough to heat the water to a certain temperature. In addition, when the hot water may last for a short time, the user is prompted to use lower temperature water or cold water instead of hot water next time, so that the user can choose to avoid wasting energy by requesting hot water from the water supply system when it is not necessary. Therefore, the present embodiment can interactively change the hot water usage habits of the occupants to reduce energy usage.

[0017] In some embodiments, one or more utility reduction strategies may include the control module setting the water temperature to a second temperature that is lower than the first temperature.

[0018] Therefore, according to an embodiment, when a short duration event is determined, the control module can actively reduce the water temperature. By reducing the water temperature, less energy is required to heat the water. In this way, energy consumption can be reduced when hot water is not needed.

[0019] In some embodiments, one or more utility reduction strategies may include the control module reducing the flow rate of water provided to the water outlet.

[0020] Therefore, the control module according to the embodiment shown can actively reduce the water flow when a short duration event is determined. This embodiment is particularly relevant when the water is heated, for example, by an electric heating element, because by reducing the water flow, less water needs to be heated and less energy is required to heat the amount of water used. Doing so can reduce water and energy consumption.

[0021] In some embodiments, one or more utility reduction strategies may include a control module bypassing activation of a heat pump in response to a water usage event.

[0022] This embodiment is particularly relevant when the water is heated by a thermal energy storage medium that stores energy extracted by a heat pump, because a certain amount of time is required to operate the heat pump to transfer a sufficient amount of heat to the thermal energy storage medium before the thermal energy storage medium reaches an operating temperature, so for short-term use, the thermal energy storage medium may not have sufficient time to reach a temperature that allows it to heat the water to the first temperature set by the user. Therefore, by actively bypassing the activation of the heat pump when a short-term event is determined by the control module, the heat pump is not operated unnecessarily, thereby wasting energy.

[0023] Another aspect of the present technology provides a control module configured to communicate and control a water supply system via a communication channel, the control module comprising a processor having a machine learning algorithm executed thereon, the algorithm being trained to perform the method as described above.

[0024] Another aspect of the present technology provides a method for training a machine learning algorithm (MLA) to regulate utility usage of a water supply system, the water supply system comprising a heat pump configured to transfer thermal energy from an ambient environment to a thermal energy storage medium, and a control module configured to control the operation of the heat pump, the water supply system being configured to provide water heated by the thermal energy storage medium to a user at one or more water outlets, the MLA executed on the control module being trained to establish a utility usage pattern based on sensor data from the water supply system, the method comprising: receiving a first signal by the control module, the first signal indicating that the water outlet is open to provide water at a first temperature set by a user; monitoring changes in the water temperature at the water outlet by the control module; subsequently receiving a second signal by the control module indicating that the water outlet is closed; and when the second signal is received, if the water temperature at the water outlet is lower than the first temperature, training the MLA to determine a short duration event.

[0025] In some embodiments, the sensor data may include time of day, day of the week, date, water flow detection at one or more outlets, time elapsed since the outlet was opened, main water temperature and / or water temperature at one or more outlets.

[0026] In some embodiments, the method may further include monitoring, by the control module, an elapsed time when the first signal is received.

[0027] In some embodiments, the method may further include the MLA recording short duration events, including recording the time, day and / or date of water usage, the first temperature, the water temperature when the second signal is received, the total elapsed time, the location of the water outlet, or a combination thereof.

[0028] In some embodiments, the method may further include training the MLA to recognize at least one indication based on sensor data and utility usage patterns received during the short duration event, and training the MLA to predict the short duration event when the at least one indication is recognized.

[0029] In some embodiments, the at least one indication may include a location of a water outlet, a time of a water usage event, a determination of cold water usage within a predetermined time prior to a water usage event, or a combination thereof.

[0030] In some embodiments, the method may further include training the MLA to deploy one or more utility reduction strategies when predicting a short duration event.

[0031] In some embodiments, one or more utility reduction strategies may include generating a prompt signal to prompt a user to set the water temperature to a reduced second temperature that is lower than the first temperature.

[0032] In some embodiments, the prompt signal may include a light signal at or near the water outlet, a flashing signal at or near the water outlet, a predetermined sound or tone generated at or near the water outlet, a verbal or multimedia prompt, or a combination thereof.

[0033] In some embodiments, one or more utility reduction strategies may include the control module setting the water temperature to a second temperature that is lower than the first temperature.

[0034] In some embodiments, one or more utility reduction strategies may include the control module reducing the flow rate of water provided to the water outlet.

[0035] In some embodiments, one or more utility reduction strategies may include a control module bypassing activation of a heat pump in response to a water usage event.

[0036] Another aspect of the present technology provides a computer readable medium including machine readable code, which, when executed by a processor, causes the processor to perform the above method.

[0037] Each embodiment of the present technology has at least one of the above-mentioned purposes and / or aspects, but does not necessarily have all of the purposes and / or aspects. It should be understood that some aspects of the present technology resulting from attempts to achieve the above-mentioned purposes may not satisfy the purposes and / or may satisfy other purposes not specifically listed herein.

[0038] Additional and / or alternative features, aspects, and advantages of embodiments of the present technology will become apparent from the following description, drawings, and appended claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Embodiments of the present disclosure will now be described with reference to the accompanying drawings, in which:

[0040] FIG1 is a schematic system overview of an exemplary water supply system;

[0041] FIG2 schematically illustrates an exemplary training phase of an MLA to establish a usage pattern;

[0042] FIG3 schematically illustrates exemplary data processing of occupancy predictions output by an MLA;

[0043] FIG4 schematically illustrates an exemplary data process for precharging a thermal storage device via MLA;

[0044] FIG5 schematically illustrates exemplary data processing for starting a heat pump by MLA;

[0045] FIG6 schematically illustrates an exemplary data process for starting a heat pump for a defrost cycle via an MLA;

[0046] 7 is a flow chart of an exemplary method of changing a user's water usage habits according to an embodiment;

[0047] 8 is a flow chart of an exemplary method of regulating water usage according to an embodiment;

[0048] FIG. 9 is a flow chart of another exemplary method of regulating water usage according to an embodiment; and

[0049] FIG. 10 schematically illustrates exemplary data processing for outputting a leak warning by an MLA. DETAILED DESCRIPTION

[0050] In view of the foregoing, the present disclosure provides various methods for providing hot water using a heat pump or assisted by a heat pump, and in some cases, the method is used to regulate the use of utilities including water and energy to reduce the waste of water and energy. The method can be implemented by using one or more machine learning algorithms (MLA), which are trained to control and regulate the water supply of the water supply system via a control module based on sensor data received from the water supply system. For example, during the training phase, the MLA can monitor the hot water use of the family in a home environment and establish a normal usage pattern. Based on many different inputs, such as the time of day, the day of the week, the date, the weather, etc., the MLA can be trained to recognize different types of water use (e.g., showering, washing hands, heating, etc.). In some embodiments, the MLA can collect additional data, such as the time when the water outlet of the system is opened and closed, the duration of use, the water temperature set by the user, and the actual water temperature when the hot water is provided to the user. In use, the MLA can use the learned usage patterns in a variety of different ways to improve the efficiency and effectiveness of hot water supply using a heat pump or assisted by a heat pump.

[0051] In some embodiments, the MLA may be trained to implement one or more energy conservation strategies at or before the water outlet is opened, and optionally implement one or more interactive strategies to help change water and energy usage habits, such as gradually reducing water and / or energy usage.

[0052] A brief overview of many different types of machine learning algorithms for embodiments using one or more MLAs is given below. However, it should be noted that using an MLA to establish normal usage patterns is only one way to implement the present technology, but it is not required; in some embodiments, the control module can be programmed with appropriate software functions to target specific hot water usage, such as excessive water flow, and respond in a predetermined manner.

[0053] MLA Overview

[0054] In general, there are three types of MLA: supervised learning-based MLA, unsupervised learning-based MLA, and reinforcement learning-based MLA.

[0055] The supervised learning MLA process is based on a target outcome variable (or dependent variable) which is to be predicted from a given set of predictor variables (independent variables). Using this set of variables, MLA (during training) generates a function that maps the input to the desired output. The training process continues until the MLA achieves the desired level of accuracy on the validation data. Examples of supervised learning based MLA include: regression, decision trees, random forests, logistic regression, etc.

[0056] Unsupervised learning MLA itself does not involve predicting the target or outcome variable. This type of MLA is used to cluster a bunch of values ​​into different groups, which is widely used to segment customers into different groups for specific interventions. Examples of unsupervised learning MLA include: Apriori algorithm, K-means.

[0057] A reinforcement learning MLA is trained to make specific decisions. During training, the MLA is exposed to a training environment where it continuously trains itself using a trial and error method. The MLA learns from past experiences and tries to acquire the best knowledge to make accurate decisions. An example of a reinforcement learning MLA is a Markov decision process.

[0058] It should be understood that different types of MLAs with different structures or topologies may be used for various tasks.One specific type of MLA includes an artificial neural network (ANN), also known as a neural network (NN).

[0059] Neural Network (NN)

[0060] In general, a given neural network consists of a set of interconnected artificial "neurons" that process information using a connectionist computational approach. Neural networks are used to model complex relationships between inputs and outputs (without actually knowing such relationships) or to discover patterns in data. The neural network is first conditioned in a training phase, in which the neural network is provided with a set of known "inputs" and information that is used to adapt the neural network to generate appropriate outputs (for the given situation it is trying to model). During this training phase, the given neural network adapts to the situation being learned and changes its structure so that the given neural network will be able to provide reasonable predicted outputs for given inputs in new situations (based on what it has learned). Therefore, instead of trying to determine a complex statistical arrangement or mathematical algorithm for a given situation, the given NN aims to provide an "intuitive" answer based on a "feeling" of the situation. Therefore, the given NN is considered a trained "black box" that can be used to determine reasonable answers for a given set of inputs in situations where what happens in the "black box" is unimportant.

[0061] NNs are often used in many situations where it is important to know the output based on a given input, but how exactly the output was obtained is of little or no importance. For example, neural networks are often used to optimize the distribution of network traffic between servers and in data processing, including filtering, clustering, signal separation, compression, vector generation, etc.

[0062] Deep Neural Networks

[0063] In some non-limiting embodiments of the present technology, the neural network can be implemented as a deep neural network. It should be understood that neural networks can be classified into various neural network categories, and these categories include recurrent neural networks (RNNs).

[0064] Recurrent Neural Networks (RNNs)

[0065] RNNs are adapted to process input sequences using their "internal states" (stored memories). This makes RNNs well suited for tasks such as unsegmented handwriting recognition and speech recognition. These internal states of RNNs can be controlled and are called "gated" states or "gated" memories.

[0066] It should also be noted that RNN itself can also be classified into various subclasses of RNN. For example, RNN includes Long Short-Term Memory (LSTM) network, Gated Recurrent Unit (GRU), Bidirectional RNN (BRNN), etc.

[0067] LSTM networks are deep learning systems that can learn tasks that in a sense require "memorizing" events that occurred in very short and discrete time steps. The topology of LSTM networks can vary depending on the specific task they are "learning" to perform. For example, LSTM networks can learn to perform tasks in situations where relatively long delays occur between events or where events occur together at both low and high frequencies. RNNs with specific gating mechanisms are called GRUs. Unlike LSTM networks, GRUs do not have an "output gate" and therefore have fewer parameters than LSTM networks. BRNNs may have "hidden layers" of neurons that are connected in reverse order, which may allow the use of information from past as well as future states.

[0068] Residual Neural Network (ResNet)

[0069] Another example of a NN that can be used to implement non-limiting embodiments of the present technology is a residual neural network (ResNet).

[0070] Deep networks naturally integrate low / mid / high-level features and classifiers in an end-to-end multi-layer manner, and the “level” of features can be enriched by the number of stacked layers (depth).

[0071] In summary, in the context of the present technology, the implementation of at least a portion of one or more MLAs can be roughly divided into two phases - a training phase and an in-use phase. First, a given MLA is trained using one or more appropriate training data sets in the training phase. Then, once the given MLA has learned what data to expect as input and what data to provide as output, the given MLA is run using the in-use data in the in-use phase.

[0072] Water supply system

[0073] In an embodiment of the present technology, a centralized water supply system provides cold and hot water to multiple water outlets, including faucets, showers, radiators, etc., to buildings suitable for use in residential or commercial environments. FIG. 1 shows an exemplary water supply system according to one embodiment. In this embodiment, the water supply system 100 includes a control module 110. The control module 110 is communicatively coupled to and configured to control various elements of the water supply system, including: a flow controller 130, for example in the form of one or more valves, arranged to control the flow of water inside and outside the system; a (ground source or air source) heat pump 140, configured to extract heat from the surrounding environment and store the extracted heat in a thermal energy storage 150 for heating water; and one or more electric heating elements 160, which are configured to directly heat cold water to a desired temperature by controlling the energy provided to the electric heating element 160. The heated water, whether heated by the thermal energy storage 150 or by the electric heating element 160, is then directed to one or more water outlets when needed. In an embodiment, the heat pump 140 extracts heat from the environment (e.g., ambient air for an air source heat pump, geothermal energy for a ground source heat pump, or a body of water for a water source heat pump), which is absorbed by the refrigerant and then transferred from the refrigerant to the working fluid, which in turn transfers the heat to a thermal energy storage medium within the thermal energy storage 150, where the heat is preferably stored as latent heat. The energy from the thermal energy storage medium can then be used to heat cooler water, such as cold water from a water supply system (which may be a tap water system), to a desired temperature. The hot water can then be supplied to various water outlets in the system.

[0074] In the present embodiment, the control module 110 is configured to receive inputs from a plurality of sensors 170-1, 170-2, 170-3, ... 170-n, which may include, for example, one or more air temperature sensors, one or more water temperature sensors, one or more water pressure sensors, one or more timers, one or more motion sensors disposed indoors and / or outdoors, and may include other sensors not directly connected to the water supply system 100, such as a GPS signal receiver, a calendar, a weather forecast application on a smartphone carried by a resident, and communicate with the control module via a communication channel. In the present embodiment, the control module 110 is configured to use the received inputs to perform various control functions, such as controlling the flow of water through the flow controller 130 to the thermal energy storage 150 or the electric heating element 160 to heat the water. In the present embodiment, a machine learning algorithm (MLA) 120 is used, which may be executed on a processor (not shown) of the control module 110, or executed on a server communicating with the processor of the control module 110 via a communication channel. The MLA 120 may be trained using input sensor data received by the control module 110 to establish baseline water and energy usage patterns based on, for example, time of day, day of the week, date (e.g., seasonal changes, public holidays), occupancy, etc. The learned usage patterns may then be used to determine, and in some cases improve, various control functions performed by the control module 110 .

[0075] Although heat pumps are generally more energy efficient in heating water than resistance heaters, it takes time to start the heat pump (usually a minute or more), and it also takes time to transfer a sufficient amount of thermal energy to the thermal energy storage medium so that the storage medium reaches the desired operating temperature before being used to heat water. Therefore, compared to resistance heaters, heat pumps generally take longer to heat the same amount of water to the same temperature from an initial starting point. In addition, in some embodiments, the heat pump 140 may, for example, use a phase change material (PCM) as a thermal energy storage medium, which changes from a solid to a liquid when heated. In this case, additional time may be required to change the PCM from a solid to a liquid (if it has been allowed to solidify) before the thermal energy extracted by the heat pump has the effect of raising the temperature of the thermal energy storage medium (until then the energy is stored as latent heat). Although this method of heating water is slower than electric heating elements, it consumes less energy to heat the water, so overall, energy is saved and the cost of providing hot water is reduced.

[0076] Phase change materials

[0077] In this embodiment, the phase change material can be used as a thermal energy storage medium for a heat pump. One class of suitable phase change materials is paraffin wax, which has a solid-liquid phase transition at temperatures relevant to domestic hot water supply and use in conjunction with a heat pump. Of particular interest are paraffin waxes that melt in the range of 40 to 60 degrees Celsius (°C), and within this range waxes can be found melting at different temperatures to suit specific applications. Typical latent heat capacities are between about 180 kJ / kg and 230 kJ / kg, and the specific heat capacity of the liquid phase is about 2.27 Jg -1 K -1 , the solid relative heat capacity is about 2.1 Jg -1 K -1 As can be seen, considerable energy can be stored using the latent heat of fusion. Even more energy can also be stored by heating the phase change liquid above its melting point. For example, when electricity rates are relatively low during off-peak hours, a heat pump can be operated to "charge" the thermal energy storage to a higher than normal temperature, thereby "superheating" the thermal energy storage.

[0078] A suitable choice of wax may be a wax having a melting point of about 48°C, such as n-tricosane C 23 or paraffin C 20 -C 33 , which requires the heat pump to operate at a temperature of about 51°C and be able to heat the water to a satisfactory temperature of about 45°C, which is sufficient for ordinary domestic hot water, such as kitchen taps, shower / bathroom taps. If necessary, cold water can be added to the water flow to reduce the water temperature. Considering the temperature performance of the heat pump, the maximum difference between the input and output temperatures of the fluid heated by the heat pump is preferably kept in the range of 5°C to 7°C, although it can be as high as 10°C.

[0079] Although paraffin is a preferred material for use as a thermal energy storage medium, other suitable materials may also be used. For example, salt hydrates are also suitable for latent heat energy storage systems, such as the latent heat energy storage system of the present invention. In this case, the salt hydrate is a mixture of an inorganic salt and water, and its phase change involves the loss of all or most of the water. During the phase change, the hydrate crystals decompose into anhydrous (or less water-containing) salts and water. The advantage of salt hydrates is that they have a much higher thermal conductivity (2 to 5 times higher) than paraffin, and a much smaller phase change volume. The suitable salt hydrate of the present application is Na2S2O3-5H2O, which has a melting point of about 48°C to 49°C and a latent heat of 200-220kJ / kg.

[0080] Usage Mode

[0081] FIG. 2 illustrates a training phase of an MLA 2200 (eg, MLA 120 ) to establish a baseline utility usage pattern, according to an embodiment.

[0082] In this embodiment, MLA2200 receives inputs from multiple sensors and other sources over a period of time to learn, for example, usage patterns of occupants of a house. For example, a control module (e.g., control module 110) on which MLA2200 executes may include a clock, and MLA2200 may receive the time of day 2101 and the date and day of the week 2102 from the clock. The house may be installed with multiple motion sensors, and MLA2200 may receive occupancy data 2103 from the motion sensors. In another embodiment described below, occupancy may also be predicted based on multiple factors. The control module may communicate with one or more outdoor temperature sensors of MLA2200 to receive input of current weather 2104. The control module may also communicate with one or more indoor temperature sensors of MLA2200 to receive indoor temperature 2105. A plurality of water temperature, pressure and flow sensors may be provided at different locations of the water supply system, such as at the tap water inlet, to measure the tap water inlet temperature 2106, the tap water flow rate 2107 and the tap water flow pressure 2108, which may be input to the MLA 2200. A sensor may be provided at one or more or each water outlet (or a valve controlling the flow of water to the water outlet) to detect when the corresponding water outlet is opened and when it is closed, and the water temperature at the water outlet, and data related to the hot / cold water usage time and temperature 2109 and the hot / cold water usage volume 2110 may be input to the MLA 2200. The MLA 2200 may also collect data on energy usage 2111 through the water supply system, such as usage time, amount of energy used, and current prices if the control module communicates with an energy supplier. The MLA 2200 may also collect data on heat pump usage 2112, such as usage time, usage length, etc. It should be noted that it is not necessary for the MLA to receive, collect and / or use all of the input sensor data described herein, and the list of input sensor data described herein is not exhaustive, and the MLA may also receive, collect and / or use other input data as needed. In particular, in embodiments where the control module communicates with one or more smart devices (e.g., smartphones) or personal computers of one or more occupants, the MLA may receive and use other personal or public data obtained from these devices.

[0083] During the training phase, the MLA 2200 establishes water and energy usage patterns for the occupants based on the received input data. For example, the usage patterns 2300 may include hot water usage patterns, cold water usage patterns, energy usage patterns, heat pump usage patterns, occupancy patterns, which provide a baseline for expected usage based on, for example, time of day, day of the week, date, occupancy level, etc.

[0084] Occupancy prediction

[0085] 3 schematically illustrates an embodiment of an MLA 3200 executed on a control module (e.g., control module 110) that processes a set of input data to output, for example, an occupancy prediction for a house. MLA 3200 may be the same MLA as MLA 2200, or it may be a different MLA. MLA 3200 may be trained using an appropriate training data set, for example based on occupancy levels and a schedule of occupants arriving at the house throughout the year.

[0086] The MLA 3200 receives input data specific to the house and its occupants from a number of sources through the control module, including one or more sensors arranged around the house, one or more user interfaces (e.g., control panels around the house that communicate with the control module, smart devices, personal computers, etc.), one or more software programs, one or more public and private databases, etc. In this embodiment, the MLA 3200 receives inputs of the current time 3101, date 3102, and day of the week 3103, for example, from a clock and calendar function running on the control module or remotely through a communication network. The MLA 3200 also receives inputs of any special events or public holidays 3104, for example, from the occupants of the house through the user interface, automatically obtained from a calendar application on the occupants' smart devices, or obtained from the public domain through the communication network. The MLA 3200 then determines the expected occupancy level based on the input data and outputs an occupancy forecast 3300. By determining the expected occupancy level of the building, the likely utility (e.g., energy and water) demand can be estimated or predicted.

[0087] In a further embodiment, when it is determined that one or more occupants are not in the house, the MLA 3200 receives input of the occupant's current location 3105. For example, the occupant may register one or more smart devices (e.g., smartphones) with the control module or a server in communication with the control module, and then the MLA 3200 may receive the current location of each occupant by obtaining a GPS signal received on the registered smart device corresponding to each occupant through the communication network. Then based on the occupant's current location 3105 and optionally other information such as traffic conditions obtained from the public domain, the MLA 3200 determines an expected arrival time 3106 for each occupant at the house. The expected arrival time 3106 for each occupant may also be determined based on other inputs, such as the current time 3101, date 3102, day of the week 3103, and event day 3104. The MLA 3200 may then use the expected arrival time 3106 to output an occupancy prediction 3300 (future occupancy level rather than current occupancy level) for the house.

[0088] The occupancy prediction 3300 is a useful indication to the control module when performing various control functions of the water supply system. For example, hot water can be directed to the radiators of a central heating system installed in the house before the occupant is expected to arrive. Another example is to start a heat pump before the occupant is expected to arrive to begin storing thermal energy in the thermal energy storage. In addition, the heat pump can be started at a time based on the occupant's expected arrival time 3106 so that the thermal energy storage is "filled" (to a certain degree of liquefaction) before the occupant is expected to arrive.

[0089] Pre-charged thermal energy storage

[0090] In the conventional method, heat extracted by the heat pump from the environment (e.g., the outside air) and from the compression of the refrigerant is transferred directly from the working fluid of the heat pump to water (e.g., from a water main), for example, stored in an insulated storage tank, and then hot water from the storage tank is supplied to the various water outlets when needed. One disadvantage of this conventional method is that it takes time for the heat pump to transfer a sufficient amount of heat from the outside air to the water in the water tank to bring the water to the desired temperature. Therefore, heat pump water heaters are often installed together with conventional electric resistance type water heaters, which heat the water to the desired temperature when the water is not sufficiently heated by the heat pump.

[0091] According to an embodiment of the present technology, a thermal energy storage medium in the thermal energy storage 150 is provided for storing heat extracted by the heat pump 140, and the stored heat can be used to heat water when needed. In this embodiment, the thermal energy storage medium can be pre-charged by operating the heat pump to transfer heat to the thermal energy storage before the demand for hot water occurs. This may be desirable in situations where the demand for hot water and / or the demand for electricity fluctuates throughout the day, such that, for example, operating the heat pump and / or the electric resistance water heater when the demand for hot water is high may not be cost-effective and may place additional pressure on the energy network at times of high demand.

[0092] 4 schematically illustrates an embodiment of an MLA 4200 executed on a control module (e.g., control module 110) that processes a set of input data to output a decision to precharge a thermal energy storage medium to raise its temperature to a desired operating temperature. MLA 4200 may be the same MLA as MLA 2200 and / or MLA 3200, or it may be a different MLA. MLA 4200 may be trained using an appropriate training data set, such as based on a house's hot water demand.

[0093] The MLA 4200 receives input data specific to the house and its occupants from a plurality of sources through the control module, including one or more sensors arranged around the house, one or more user interfaces (e.g., control panels around the house that communicate with the control module, smart devices, personal computers, etc.), one or more software programs, one or more public and private databases, etc. In this embodiment, the MLA 4200 receives inputs such as the current time and date 4101 from a clock and / or calendar on the control module, and energy demand data such as a current rate 4102 that specifies the unit energy cost obtained from an energy supplier supplying energy to the house during off-peak periods, such as periods when the unit energy cost is lower.

[0094] Alternatively or additionally, the MLA 4200 may derive energy demand data from the utility usage patterns 2300 and occupancy forecasts 3300 established as described above. For example, if the current energy usage of the house is below, for example, an average level for a day, the current energy usage may be considered low; conversely, if the current energy usage of the house is above the average level, the current energy usage may be considered high.

[0095] Then, based on the received rate information 4102 obtained from the energy supplier (and any other energy demand data), the MLA 4200 can determine the current energy demand level and, if the current energy demand is deemed to be low, start the heat pump to pre-charge the thermal energy storage 4300, thereby preparing a supply of hot water in advance of an increased demand for hot water, such as when occupants are expected to arrive at the house and / or when demand for hot water is expected to increase in the evening.

[0096] In addition, using the received time / date 4101 in conjunction with the utility usage pattern 2300 and the occupancy forecast 3300, the MLA 4200 can predict one or more parameters, such as an expected level of hot water usage and an expected level of energy usage. The MLA 4200 can then determine an amount of thermal energy to be stored in the thermal energy storage medium based on the predicted parameters. For example, if the expected level of hot water usage is expected to be high and remain high for an extended period of time, the MLA 4200 can operate the heat pump long enough in advance of the expected rise in demand to pre-charge the thermal energy storage medium to a temperature above the normal operating temperature set, for example, by the occupant who installed the device, thereby storing a sufficient amount of energy for continued hot water usage.

[0097] By enabling the water supply system to predict the expected demand for hot water so that a stored heat source is prepared before demand rises, this embodiment enables the heat pump to be utilized in situations where it may not be able to respond adequately if activated only when needed. In addition, by using the current rate as an input, the heat pump can be operated during low energy demand periods when the unit energy cost is low to pre-charge the thermal energy storage, and reduce the pressure on the energy network by shifting energy use from high demand times to low demand times. This embodiment is also suitable for self-sustaining homes because the demand for hot water and electricity often rises and falls in parallel during the day. Therefore, shifting the use of electricity for running the heat pump to times of low electricity demand enables self-sustaining homes to operate more smoothly. In general, this embodiment is able to provide hot water at a lower cost using a more efficient form (i.e., a heat pump) and with almost no disadvantages caused by delays in heating the water to the desired temperature.

[0098] Hot water demand forecasting

[0099] 5 schematically illustrates an embodiment of an MLA 5200 executed on a control module (e.g., control module 110) that is trained to determine whether to start a heat pump based on chilled water usage. MLA 5200 may be the same MLA as MLA 2200 and / or MLA 3200 and / or MLA 4200, or it may be a different MLA.

[0100] The MLA5200 receives house-specific input data from a plurality of inputs through a control module, including one or more sensors arranged around the house, one or more user interfaces (e.g., control panels around the house that communicate with the control module, smart devices, personal computers, etc.), one or more software programs, one or more public and private databases, etc. During the training phase, the MLA5200 can be trained to recognize the correlation between hot water usage and cold water usage. For example, the MLA5200 can be trained to recognize the correlation between the cold water usage demand in the bathroom (e.g., a water tank to fill a toilet) and the hot water demand of the faucet in the bathroom (e.g., for washing hands). Thus, during the training phase, the MLA5200 can use sensor data related to cold water usage to establish the correlation between the two events. The sensor data can, for example, include the elapsed time between receiving the first sensor data and receiving the second sensor data, the position of the second water outlet relative to the first water outlet, the frequency of receiving the second sensor data after receiving the first sensor data, the time of day, the day of the week, but this list is not exhaustive.

[0101] In this embodiment, the MLA 5200 receives an input of a chilled water activation 5101, and based on the current chilled water usage associated with the established utility usage pattern 2300 and occupancy forecast 3300, the MLA 5200 can determine the probability of a demand for hot water that may result from the current chilled water usage based on the relevance of the current chilled water usage. If an expected demand for hot water is determined, the MLA 5200 can instruct the control module to start the heat pump 5300 when the demand is expected.

[0102] To determine whether the probability of a demand for hot water is high enough to warrant expending energy to operate a heat pump to pre-charge the thermal energy storage medium, the MLA 5200 may establish a threshold during a training phase that indicates when it is worth activating the heat pump. In one embodiment, the threshold may be manually established by manual input by an occupant or installer when such predictive activation of the heat pump is desired. In another embodiment, the threshold may be established by the MLA 5200 based on utility usage patterns 2300 and / or occupancy predictions 3300.

[0103] In another embodiment, the MLA5200's determination of whether to activate the heat pump may also be based on input such as a current rate 5102 obtained from an energy supplier. In this embodiment, the threshold may be determined based on rate information obtained from the energy supplier during a training phase. Alternatively or additionally, the threshold may be modified during runtime based on the current rate. For example, if the current rate 5102 indicates an off-peak electricity price, meaning that the electric heating element 160 may operate at a low cost, and the MLA5200 determines a low correlation between the current cold water usage and the expected demand for hot water, the MLA5200 may determine that there is no need to activate the heat pump to preheat the thermal energy storage medium because there is unlikely to be a demand for hot water; if hot water is required, the electric heating element 160 may be used to heat the water. On the other hand, if the current rate 5102 indicates a peak electricity price when the unit energy cost is high, meaning that heating water using the electric heating element 160 will be expensive, and if the MLA 5200 determines that there is only a low correlation between the current cold water usage and the expected demand for hot water, the MLA 5200 may determine that, despite the low correlation, it is more cost-effective to activate the heat pump to pre-charge the thermal energy storage in preparation for the demand for hot water, thereby avoiding the more expensive option of providing hot water using the electric heating element 160. In the latter example, the MLA 5200 may modify the threshold so that it is lower than the threshold in the former example, so that the heat pump may be activated in the latter example even though the probability values ​​in both cases are the same.

[0104] By preparing the water supply system in advance of the need for hot water, delays in hot water delivery can be reduced, thereby reducing the waste of clean water by reducing the time that the water outlet remains open while occupants wait for the water to be heated. In addition, by predicting the expected demand for hot water and predictively preparing the storage heat source by running the heat pump in advance of the need for hot water, the heat pump can be utilized as a reliable form of hot water delivery, reducing or even eliminating the inherent delays.

[0105] Defrost prediction

[0106] As described above, a heat pump such as heat pump 140 includes an outdoor unit having a heat exchanger coil that extracts heat from the air or outdoor ground and transfers it to an indoor unit, either directly to the interior of a building to warm it, or to a thermal energy storage medium to store it for later use. The process of extracting thermal energy from the outside air cools the heat exchanger coil in the outdoor unit, and moisture in the air condenses on the cold outdoor coil. In cold outdoor conditions, such as when the outdoor air is 5°C, the outdoor coil may cool below freezing and frost may form on the outdoor coil. When frost forms on the outdoor coil, the efficiency of the heat pump decreases, requiring a greater temperature difference with the outside air to output the same power compared to a frost-free coil. Therefore, it is desirable to run the heat pump regularly in a defrost cycle and when frosting occurs to remove frost from the heat exchanger coil in the outdoor unit of the heat pump.

[0107] Many factors affect when a heat pump needs a defrost cycle, such as the outdoor temperature and humidity, the heat pump's power output, and the condition of the heat pump (for example, older systems may be less efficient and require more frequent defrosts). Typically, a heat pump runs a defrost cycle whenever frost forms on the outdoor heat exchanger coil.

[0108] During the defrost cycle, the heat pump operates in reverse because hot refrigerant is sent to the outdoor unit to thaw the heat exchanger coil. The heat pump can run the defrost cycle until, for example, the coil reaches approximately 15°C. Once the heat exchanger coil is thawed, the heat pump can resume the normal heating cycle. Obviously, when the heat pump is running a defrost cycle, it will not be able to perform its normal function of transferring heat to the indoor unit (e.g., to the thermal energy storage 150) until the defrost cycle is completed. Therefore, it may be desirable to prepare the thermal storage in the building before the heat pump defrost cycle begins.

[0109] 6 schematically illustrates an embodiment of an MLA 6200 executed on a control module (e.g., control module 110) that processes a set of input data to predict the next defrost cycle of a heat pump (e.g., heat pump 140). MLA 6200 may be the same MLA as MLA 2200 and / or MLA 3200 and / or MLA 4200 and / or MLA 5200, or it may be a different MLA.

[0110] The MLA 6200 receives house-specific input data from a plurality of inputs through a control module, including one or more sensors arranged around the house, one or more user interfaces (e.g., control panels around the house that communicate with the control module, smart devices, personal computers, etc.), one or more software programs, and one or more public and private databases, etc. During a training phase, the MLA 6200 can be trained to recognize when a defrost cycle is required and establish the length of time and average energy requirements for operating the heat pump in a defrost cycle based on, for example, weather forecasts, current weather conditions, indoor temperature, and data collected from previous defrost cycles, using knowledge of the heat pump's performance (e.g., the heat pump's average thermal energy output, the heat pump's efficiency or coefficient of performance, and any other information or quantity related to the heat pump's performance).

[0111] In this embodiment, the MLA 6200 receives input of a weather forecast 6101, such as obtained from a public domain or a weather application on a smart device registered with the control module, current weather conditions 6102, such as temperature and humidity, such as obtained from a public domain or one or more sensors arranged around the house, indoor temperature 6103, such as obtained from one or more temperature sensors arranged in the house, and data related to the last defrost cycle 6104 when the heat pump was last defrosted. Based on the weather forecast, current weather conditions, and indoor temperature, the MLA 6200 can predict when the next defrost cycle may be expected 6301, for example, when there is a long period of low temperature and high humidity, a faster defrost cycle may be required, and can estimate the length of time required to defrost the heat pump. In addition, using established utility usage patterns 2300 and occupancy forecasts 3300, the MLA 6200 can estimate expected energy and hot water requirements during the time of the predicted defrost cycle and prepare the water supply system prior to the predicted defrost cycle 6302, such as by storing additional thermal energy in a thermal energy storage device (by storing energy as sensible heat in addition to latent heat in the PCM), heating the house to a temperature above a preset temperature, and the like.

[0112] Additionally or alternatively, the MLA 6200 may also predict when demand for energy and hot water (e.g., for faucets, showers, and / or central heating) is low and determine an appropriate time to defrost the heat pump, e.g., when there is less disruption to providing hot water to occupants. Using these inputs, the MLA 6200 may determine time periods when water and energy demand is low (e.g., at night) and / or occupancy levels are low (e.g., during school and work hours) and adjust the expected start time of the next defrost cycle to the determined time of low demand and / or time of low occupancy levels. The MLA 6200 may then instruct the control module to activate the heat pump to begin a defrost cycle at the adjusted start time 6301. For example, if the MLA 6200 predicts that a defrost cycle may be required in the evening when demand for energy and hot water is expected to be high, the MLA 6200 may preheat the thermal energy storage medium by operating the heat pump to store more heat, such as by raising the temperature of the thermal energy storage medium to a higher operating temperature, and diverting some of the heat to heat the building before the predicted defrost cycle, and / or the MLA 6200 may adjust the defrost cycle start time to a time in the evening when demand is expected to be lower. In another example, if a defrost cycle is expected to occur during the day, the MLA 6200 may determine based on occupancy forecasts and / or usage patterns that the next defrost cycle is during a time period when energy and hot water demand are low, such as when occupancy forecasts are low or zero, and when no preparation or adjustment is determined.

[0113] By predicting the next defrost cycle of the heat pump based on, for example, the performance of the heat pump, weather forecast, current weather conditions, current indoor temperature, expected occupancy, and hot water demand, and predictively preparing the water supply system before the defrost cycle begins, the present embodiment allows the necessary heat pump defrost cycle to be performed in a manner that is less disruptive to the hot water supply, thereby enabling the heat pump to be used as an efficient way to provide hot water.

[0114] Cold water recommendations

[0115] In one embodiment, methods and systems for monitoring and interactively modifying occupants' water usage habits are provided. These methods can be implemented by MLA7200. MLA7200 can be the same MLA as MLA2200 and / or MLA3200 and / or MLA4200 and / or MLA5200 and / or MLA6200, or it can be a different MLA. During a training phase, data related to water usage, such as provided by the occupants of the house, is provided to MLA7200 to establish a normal water usage pattern, as described above. In addition, MLA7200 can be trained to confirm or recognize a situation in normal usage mode when the water outlet is opened to provide hot water at a temperature T1 set by the occupant but the water outlet is subsequently closed before the water is heated to T1. This is particularly relevant when starting a heat pump, as the energy extracted by the heat pump must first heat the thermal energy storage medium to the desired operating temperature before the thermal energy storage medium can sufficiently heat the water. Thus, in the event that the heat pump is activated in response to a demand for hot water but the water outlet is closed before the water is heated to the desired temperature, the energy (electricity) used to operate the heat pump is wasted because the user does not actually receive hot water. In view of the foregoing, when such a short-term instance is determined, the MLA 7200 can be trained to employ one or more energy reduction strategies.

[0116] 7 , at S7001, the occupant sets the water temperature at the water outlet to T1 and opens the water outlet. At S7002, the control module determines that the water outlet is opened, for example, by using one or more sensors to detect changes in water pressure or water flow at a water source supplying water to the water supply system, and at S7003, the control module runs MLA7200 to monitor changes in water temperature at the water outlet. Subsequently, the control module determines at S7004 that the water outlet is closed, and MLA7200 determines at S7005 whether the water temperature has reached T1 set by the user during the time period when the water outlet is opened. If so, the algorithm ends and no further action is taken.

[0117] If it is determined at S7005 that the water temperature did not reach T1 during the period of time when the water outlet was open, the MLA 7200 may employ one or more energy saving strategies. In one embodiment, at S7006, the MLA 7200 initiates a software function to generate a notification to notify the occupant that the water did not reach the preset temperature before the water outlet was closed. At S7007, the MLA 7200 may optionally record the event.

[0118] At a later time, the occupant may again set the water temperature at the same water outlet to T1 and open the water outlet. Before or after determining that the water outlet is open, in this embodiment, MLA7200 identifies the water usage as a short-duration situation in which the water temperature cannot reach T1 before the user closes the water outlet, and then initiates a software function to generate a prompt signal to prompt the user to set the water temperature to a lower temperature T2 or use cold water instead of hot water. The prompt signal may be, for example, a flash at or near the water outlet, the generation of a predetermined sound or tone, a verbal and / or visual prompt (e.g., a played message or image), etc. MLA7200 may determine such short-term instances based on established usage patterns, or use one or more indications to identify such short-term instances. For example, MLA7200 may use the location of the water outlet or the time when hot water is needed as an indication. As another example, MLA7200 may predetermine the correlation between the instance of cold water use before such a short-term hot water use instance and the subsequent hot water demand for hand washing, and use such cold water use as an indication, such as when the toilet is flushed and then refilled.

[0119] Therefore, according to the present embodiment, the occupants are made aware of situations when they need heated water but have not used the water long enough to heat the water to a certain temperature. In addition, when the hot water is likely to last for a short time, the user is prompted to use lower temperature water or cold water instead of hot water next time, so that the user can choose to avoid wasting energy by requesting hot water from the water supply system when it is not necessary. Therefore, the present embodiment can interactively modify the hot water usage habits of the occupants to reduce energy usage.

[0120] In another supplementary or alternative embodiment shown in FIG8 , at S8001, the occupant again sets the water temperature to T1 and opens the water outlet. Before or after the control module determines that the water outlet is open at S8002, the MLA7200 identifies the water usage as a short-term situation and adopts an additional or alternative energy saving strategy by causing the control module to change the temperature setting of the water outlet from T1 to a lower temperature T2. Temperature T2 may be lower than temperature T1, but still represents a heated water temperature, or T2 may represent an unheated cold water temperature from the main water pipe. Under the control of the control module, at S8003, the water supply system outputs water at a temperature of T2 to the water outlet.

[0121] Therefore, according to this embodiment, when the MLA7200 identifies a short duration situation, the control module actively lowers the water temperature. By lowering the water temperature, less energy is required to heat the water. In this way, this embodiment reduces energy consumption when hot water is not needed.

[0122] In another supplementary or alternative embodiment shown in FIG. 9 , at S9001, the occupant sets the water temperature to T1 again and opens the water outlet. Before or after the control module determines that the water outlet is opened at S9002, the MLA 7200 identifies the water usage as a short-term situation and adopts an additional or alternative energy-saving strategy by causing the control module to adjust the flow rate of the water outlet to a lower flow rate. Under the control of the control module, at S9003, the water supply system outputs water to the water outlet at a lower flow rate.

[0123] Therefore, according to this embodiment, when the MLA identifies a short duration condition, the control module proactively reduces the water flow. When heating water, this embodiment is particularly relevant to heating water, such as by an electric heating element, so that by reducing the water flow, less water needs to be heated and less energy is required to heat the amount of water used. In this way, this embodiment reduces water and energy consumption.

[0124] Leakage warning

[0125] 10 schematically illustrates an embodiment of an MLA 1200 executed on a control module (e.g., control module 110) that processes a set of sensor data to output a leak alarm for a given building. MLA 1200 may be the same MLA as MLA 2200 and / or MLA 3200 and / or MLA 4200 and / or MLA 5200 and / or MLA 6200 and / or MLA 7200, or it may be a different MLA.

[0126] The MLA 1200 receives house-specific input data from a plurality of inputs through the control module, including one or more sensors arranged around the house, one or more user interfaces (e.g., control panels around the house that communicate with the control module, smart devices, personal computers, etc.), one or more software programs, one or more public and private databases, etc. In this embodiment, the MLA 1200 receives the current time and date 1101, for example, from a clock and calendar function running on the control module or remotely through a communication network, and then using the established utility usage pattern 2300 and occupancy forecast 3300, the MLA 1200 can estimate the expected water consumption for the current time and date. In addition, the MLA 1200 receives inputs of the main water inlet temperature 1102, the main water flow rate 1103, and the main water pressure 1104, and determines the real-time water consumption, which is measured, for example, by appropriate sensors at the main water inlet of the house. The MLA 1200 can then determine whether the current water consumption is as expected based on the expected consumption and the real-time consumption, and if the current water consumption exceeds the expected consumption, the MLA 1200 outputs a water leak warning 1300. The MLA 1200 may be pre-trained to recognize whether current water usage exceeding expected usage is associated with a leak in the system or an unexpected increase in demand, such as a change in weather or an increase in occupancy. In some embodiments, the MLA 1200 may be provided with a threshold above which water usage levels exceeding expected usage are considered leaks. Optionally, the MLA 1200 may establish such a threshold during a training phase, or adjust the threshold while in use, for example based on user feedback.

[0127] By establishing utility usage patterns and monitoring current water usage against that pattern, potential water leaks in the system can be detected and early warnings given to occupants to take remedial or corrective action before the leak becomes more severe.

[0128] The various MLAs described above may refer to the same or different MLAs. If multiple MLAs are implemented, one or some or all of the MLAs may be executed on the control module 110, and one or some or all of the MLAs may be executed on a server (e.g., a cloud server) that communicates with the control module 110 via a suitable communication channel. Those skilled in the art will appreciate that the above embodiments may be implemented in any combination, in parallel, or as an alternative strategy as desired.

[0129] As will be appreciated by those skilled in the art, the present technology may be embodied as a system, method or computer program product.Therefore, the present technology may take the form of an all-hardware embodiment, an all-software embodiment or an embodiment combining software and hardware.

[0130] Furthermore, the present technology may take the form of a computer program product embodied in a computer-readable medium having computer-readable program code embodied thereon. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared or semiconductor system, apparatus or device, or any suitable combination of the foregoing.

[0131] Computer program code for carrying out operations of the present technology may be written in any combination of one or more programming languages, including object oriented programming languages ​​and traditional procedural programming languages.

[0132] For example, program code for performing operations of the present technology may include source, object, or executable code in a conventional programming language (interpreted or compiled) such as C, or assembly code, code for setting up or controlling an ASIC (application-specific integrated circuit) or FPGA (field programmable gate array), or code for a hardware description language such as VerilogTM or VHDL (very high speed integrated circuit hardware description language).

[0133] The program code may execute entirely on the user's computer, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server. In the latter case, the remote computer may be connected to the user's computer through any type of network. Code components may be embodied as procedures, methods, etc., and may include subcomponents that may take the form of instructions or sequences of instructions at any level of abstraction, from direct machine instructions of the native instruction set to high-level compiled or interpreted language structures.

[0134] It will also be clear to those skilled in the art that all or part of the logic method according to the preferred embodiment of the present technology can be appropriately embodied in a logic device including logic elements that perform the steps of the method, and such logic elements can include components such as logic gates in a programmable logic array or an application-specific integrated circuit. Such a logic arrangement can also be embodied in an enabling element for temporarily or permanently establishing a logic structure in such an array or circuit using, for example, a virtual hardware descriptor language, which can be stored and transmitted using a fixed or transmittable carrier medium.

[0135] The examples and conditional language cited herein are intended to help the reader understand the principles of the present technology, rather than to limit its scope to these specifically cited examples and conditions. It should be understood that a person skilled in the art can design various arrangements that, although not explicitly described or shown herein, embody the principles of the present technology and are included within the scope defined by the appended claims.

[0136] In addition, as an aid to understanding, the above description may describe a relatively simplified implementation of the present technology. As will be appreciated by those skilled in the art, various implementations of the present technology may be more complex.

[0137] In some cases, useful examples that are considered to be modifications to the present technology may also be set forth. This is done solely to aid understanding and is not intended to limit the scope of the present technology or set the boundaries of the present technology. These modifications are not exhaustive, and those skilled in the art may make other modifications while still remaining within the scope of the present technology. In addition, where examples of modifications are not set forth, it should not be interpreted that no modifications are possible and / or that what is described is the only way to implement that element of the present technology.

[0138] In addition, all statements describing the principles, aspects, and implementations of the technology herein and specific examples thereof are intended to cover structural and functional equivalents thereof, whether currently known or developed in the future. Thus, for example, it will be understood by those skilled in the art that any block diagram herein represents a conceptual diagram of an illustrative circuit embodying the principles of the technology. Similarly, it will be understood that any flow chart, flowchart, state transition diagram, pseudocode, etc., represents various processes that can be substantially represented in a computer-readable medium and executed by a computer or processor, whether or not such a computer or processor is explicitly shown.

[0139] The functions of the various elements shown in the drawings, including any functional blocks marked as "processors", may be provided using dedicated hardware as well as hardware capable of executing software associated with appropriate software. When provided by a processor, these functions may be provided by a single dedicated processor, a single shared processor, or multiple separate processors, some of which may be shared. In addition, the explicit use of the term "processor" or "controller" should not be interpreted as referring exclusively to hardware capable of executing software, and may implicitly include, but is not limited to, digital signal processor (DSP) hardware, network processors, application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), read-only memory (ROM), random access memory (RAM), and non-volatile memory for storing software. Other hardware, conventional and / or customized, may also be included.

[0140] Software modules, or simply implied modules of software, may be represented herein as any combination of flow chart elements or other elements indicating the execution of process steps and / or textual descriptions. Such modules may be executed by hardware shown explicitly or implicitly.

[0141] It will be apparent to those skilled in the art that many improvements and modifications can be made to the foregoing exemplary embodiments without departing from the scope of the present technology.

Claims

1. A computer-implemented method of regulating utility use of a water supply system, the water supply system comprising a heat pump configured to transfer thermal energy from an ambient environment to a thermal energy storage medium, and a control module configured to control the operation of the heat pump, the control module having a machine learning algorithm (MLA) executed thereon, the MLA pre-trained to associate indications with short duration events based on sensor data obtained from the water supply system, the water supply system being configured to provide water heated by a thermal energy storage medium to a user at one or more water outlets, the method being performed by the control module and comprising: determining a water usage event when a water outlet is opened to provide water at a first temperature, the first temperature being set by the user; Determining whether the water usage event is a short duration event based on at least one indication by inputting sensor data received from the water supply system into the MLA, wherein the short duration event is an event in which the water outlet is opened for such a short time that the water temperature cannot reach the first temperature before the water outlet is closed; and Upon determining that the water usage event is a short duration event, one or more utility reduction strategies are deployed.

2. The method according to claim 1, wherein: The sensor data includes time of day, day of the week, date, water flow detection at the one or more water outlets, time elapsed since the water outlet was opened, mains water temperature and / or water temperature at the one or more water outlets.

3. The method of claim 2, further comprising identifying, by the MLA, the at least one indication based on utility usage patterns, wherein the MLA is trained to establish utility usage patterns for the water supply system based on sensor data obtained from the water supply system.

4. The method according to claim 3, wherein: The utility usage pattern includes expected cooling water usage with respect to a time, day and / or date, expected heating water usage with respect to a time, day and / or date, expected energy usage with respect to a time, day and / or date, expected occupancy level with respect to a time, day and / or date, or a combination thereof.

5. A method according to any one of the preceding claims, wherein: The at least one indication includes a location of a water outlet, a time of a water usage event, a determination of cold water usage within a predetermined time prior to the water usage event, or a combination thereof.

6. The method according to claim 1, wherein: The one or more utility reduction strategies include the control module generating a prompt signal to prompt a user to set the water temperature to a second temperature that is lower than the first temperature.

7. The method according to claim 6, wherein: The prompt signal includes a light signal at or near the water outlet, a flashing signal at or near the water outlet, a predetermined sound or tone generated at or near the water outlet, a verbal or multimedia prompt, or a combination thereof.

8. The method according to claim 1, wherein: The one or more utility reduction strategies include the control module setting a water temperature at a second temperature that is lower than the first temperature.

9. The method according to claim 1, wherein: The one or more utility reduction strategies include the control module reducing a flow rate of water provided to the water outlet.

10. The method according to claim 1, wherein: The one or more utility reduction strategies include the control module bypassing activation of the heat pump in response to the water usage event.

11. A control module configured to communicate and control a water supply system via a communication channel, the control module comprising a processor having a machine learning algorithm MLA executed on the control module, the machine learning algorithm being trained to perform the method of any of the preceding claims.

12. A method of training a machine learning algorithm (MLA) to regulate utility usage of a water supply system, the water supply system comprising a heat pump configured to transfer thermal energy from an ambient environment to a thermal energy storage medium, and a control module configured to control the operation of the heat pump, the water supply system being configured to provide water heated by the thermal energy storage medium to a user at one or more water outlets, the MLA executing on the control module and trained to establish utility usage patterns based on sensor data from the water supply system, the method comprising: The control module receives a first signal, the first signal indicating that the water outlet is opened to provide water at a first temperature, the first temperature being set by a user; The control module monitors the change of water temperature at the water outlet; Then, the control module receives a second signal indicating that the water outlet is closed; and When the second signal is received, if the water temperature at the water outlet is lower than the first temperature, the MLA is trained to determine a short duration event, where the water outlet is open for such a short time that the water temperature cannot reach the first temperature before the water outlet is closed.

13. The method according to claim 12, wherein: The sensor data includes time of day, day of the week, date, water flow detection at the one or more water outlets, time elapsed since the water outlet was opened, mains water temperature and / or water temperature at the one or more water outlets.

14. The method of claim 12, further comprising monitoring, by the control module, an elapsed time when the first signal is received.

15. The method of claim 12, further comprising training the MLA to record short duration events, including recording the time, day and / or date of water usage, the first temperature, the water temperature when the second signal is received, the total elapsed time, the location of the water outlet, or a combination thereof.

16. The method of any one of claims 12 to 15, further comprising training the MLA to recognize at least one indication based on sensor data received during the short duration event and the utility usage pattern, and training the MLA to predict a short duration event when the at least one indication is recognized.

17. The method according to claim 16, wherein: The at least one indication includes a location of a water outlet, a time of a water usage event, a determination of cold water usage within a predetermined time prior to the water usage event, or a combination thereof.

18. The method of claim 17, further comprising training the MLA to deploy one or more utility reduction strategies when predicting a short duration event.

19. The method according to claim 18, wherein: The one or more utility reduction strategies include generating a prompt signal to prompt the user to set the water temperature to a reduced second temperature that is lower than the first temperature.

20. The method according to claim 19, wherein: The prompt signal includes a light signal at or near the water outlet, a flashing signal at or near the water outlet, a predetermined sound or tone generated at or near the water outlet, a verbal or multimedia prompt, or a combination thereof.

21. The method according to claim 18, wherein: The one or more utility reduction strategies include the control module setting a water temperature at a second temperature that is lower than the first temperature.

22. The method according to claim 18, wherein: The one or more utility reduction strategies include the control module reducing a flow rate of water provided to the water outlet.

23. The method according to claim 18, wherein: The one or more utility reduction strategies include the control module bypassing activation of a heat pump in response to the water usage event.

Images