Information processing system, heat pump type hot water supply system, information processing method, and program

Abstract

An information processing system (10) comprises: a first prediction unit (14) that predicts a power generation amount, for each unit time on a target date, of a solar power generation system (40) installed in a housing complex (100); a second prediction unit (15) that predicts a power consumption amount, for each unit time on the target date, for the housing complex (100) as a whole; and a control unit (16) that, on the basis of the predicted power generation amount and the predicted power consumption amount, sets a time period in which a boiling operation is performed by a target system, which constitutes a portion of heat pump type hot water supply systems (20) from among a plurality of the heat pump type hot water supply systems (20) installed in a plurality of residences (101) included in the housing complex (100), so as to be a first time period corresponding to at least a portion of a time period during the daytime of the target date.

Description

Information processing system, heat pump hot water supply system, information processing method, and program

[0001] The present disclosure relates to an information processing system, a heat pump hot water supply system, an information processing method, and a program.

[0002] Patent Document 1 discloses an operation planning method for a heat pump hot water supply system including a solar power generation device and a heat pump hot water supply device.

[0003] International Publication No. 2012 / 063409

[0004] The present disclosure provides an information processing system and the like that can suppress the occurrence of peak power consumption in an apartment building.

[0005] An information processing system according to one aspect of the present disclosure includes a first prediction unit that predicts the amount of power generated per unit time of a solar power generation system installed in an apartment building on a target day; a second prediction unit that predicts the amount of power consumed per unit time of the entire apartment building on the target day; and a control unit that sets, based on the predicted amount of power generated and the predicted amount of power consumed, a first time period corresponding to at least a portion of the daytime time period on the target day as the time period during which heating operation is performed by a target system, which is one of a plurality of heat pump hot water systems installed in a plurality of dwelling units included in the apartment building.

[0006] A heat pump hot water supply system according to one aspect of the present disclosure is a heat pump hot water supply system installed in an apartment building included in an apartment complex, and comprises a heat pump, a tank for storing hot water heated by the heat pump, and a hot water supply control device that receives a control command sent by an information processing system and controls the heat pump during a first time period specified in the received control command, thereby performing hot water supply operation during the first time period.The first time period is a time period determined by the information processing system based on the predicted power generation amount per unit time on a target day by a solar power generation system installed in the apartment complex and the predicted power consumption amount per unit time on the target day by the entire apartment complex.

[0007] An information processing method according to one aspect of the present disclosure is an information processing method executed by a computer system, and includes the steps of predicting the amount of power generated per unit time of a solar power generation system installed in an apartment building on a target day; predicting the amount of power consumed per unit time of the entire apartment building on the target day; and setting, based on the predicted amount of power generated and the predicted amount of power consumed, a first time period corresponding to at least a portion of the daytime hours on the target day as the time period during which heating operation is performed by a target system, which is one of a plurality of heat pump hot water systems installed in a plurality of dwelling units included in the apartment building.

[0008] A program according to one aspect of the present disclosure is a program for causing the computer system to execute the information processing method.

[0009] The information processing system etc. disclosed herein can prevent peak power consumption in apartment buildings.

[0010] Fig. 1 is a block diagram showing the functional configuration of an information processing system according to an embodiment. Fig. 2 is a diagram showing an example of a time period during which a plurality of heat pump hot water supply systems perform a heating operation. Fig. 3 is a flowchart of an operation example 1 of the information processing system according to an embodiment. Fig. 4 is a diagram showing a method for predicting the amount of power consumption of a heat pump hot water supply system. Fig. 5 is a diagram for explaining a shift in the time period during which a heating operation is performed. Fig. 6 is a diagram showing an example of a shift in the time period during which a target system performs a heating operation.

[0011] Hereinafter, the embodiments will be described in detail with reference to the drawings. Note that the embodiments described below are all comprehensive or specific examples. The numerical values, shapes, materials, components, component placement and connection forms, steps, and step order shown in the following embodiments are merely examples and are not intended to limit the present disclosure. Furthermore, among the components in the following embodiments, components not recited in independent claims will be described as optional components.

[0012] It should be noted that the drawings are schematic diagrams and are not necessarily strict illustrations. In addition, in the drawings, substantially the same components are denoted by the same reference numerals, and overlapping descriptions may be omitted or simplified.

[0013] (Embodiment) [Configuration] First, the configuration of an information processing system according to an embodiment will be described. Fig. 1 is a block diagram showing the functional configuration of an information processing system according to an embodiment.

[0014] The information processing system 10 is a system that can reduce peak power consumption caused by the operation of multiple heat pump hot water systems 20 in an apartment building 100. In addition to the information processing system 10, Fig. 1 illustrates multiple heat pump hot water systems 20, multiple power measurement devices 30, a solar power generation system 40, a power management system 50, and a weather information management system 60. These systems and devices will be described below.

[0015] The information processing system 10 is a system realized by one or more server devices located, for example, outside the apartment complex 100. Specifically, the information processing system 10 includes a communication unit 11, an information processing unit 12, and a storage unit 13.

[0016] The communication unit 11 is a communication module (communication circuit) that enables the information processing system 10 to communicate with a plurality of heat pump hot water supply systems 20, a power management system 50, a weather information management system 60, and the like, via a wide area communication network 90 such as the Internet. The communication performed by the communication unit 11 is, for example, wired communication, but may also be wireless communication. There are no particular limitations on the communication standard used for the communication.

[0017] The information processing unit 12 performs information processing for controlling the multiple heat pump hot water supply systems 20. The information processing unit 12 is realized, for example, by a microcontroller, but may also be realized by a processor. The information processing unit 12 includes, as functional components, a first prediction unit 14, a second prediction unit 15, and a control unit 16. The functions of the first prediction unit 14, the second prediction unit 15, and the control unit 16 are realized, for example, by the microcontroller or processor constituting the information processing unit 12 executing a computer program stored in the storage unit 13.

[0018] The storage unit 13 is a storage device that stores information necessary for the information processing, computer programs executed by the information processing unit 12, etc. The storage unit 13 is realized by, for example, a hard disk drive (HDD), but may also be realized by a semiconductor memory or the like.

[0019] The heat pump hot water supply system 20 is provided in each of the multiple dwelling units 101 included in the apartment building 100, and is a system for supplying hot water to the dwelling units 101. The hot water may be output from a faucet or may be used for heating such as floor heating. Specifically, the heat pump hot water supply system 20 includes a communication device 21, a hot water supply control device 22, a heat pump 23, and a tank 24.

[0020] The communication device 21 is, for example, a wireless router, and includes a communication module (communication circuit) that enables the heat pump hot water supply system 20 to communicate with the information processing system 10 via the wide area communication network 90. ​​The communication device 21, for example, communicates wirelessly with the hot water supply control device 22 and is connected to the wide area communication network 90 by wired communication. The communication standard for communication performed by the communication device 21 is not particularly limited.

[0021] The hot water supply control device 22 controls the heat pump 23 to heat water using the heat pump 23. The hot water supply control device 22 is realized by a communication unit that communicates with the communication device 21, an information processing unit realized by a microcontroller or a processor, a memory unit, a user interface that accepts user operations, and a display unit that displays an image showing the operating state of the heat pump hot water supply system 20.

[0022] The heat pump 23 absorbs heat from the atmosphere using a refrigerant and compresses the refrigerant using electric power to generate heat, which is then transferred to water via a heat exchanger. The tank 24 stores the water heated by the heat pump 23 (i.e., boiled hot water).

[0023] The power measurement device 30 is provided in each of the multiple dwelling units 101 included in the apartment building 100, and measures the amount of power consumed in the dwelling units 101. The power measurement device 30 also communicates with the power management system 50 via the wide area communication network 90, and transmits actual data of the time waveform of power consumption indicating the measured amount of power consumption to the power management system 50. The power measurement device 30 is, for example, a smart meter, but may also be a distribution board with a power measurement function.

[0024] The solar power generation system 40 is installed on the roof of the apartment building 100 or the like, and generates power by converting sunlight into electricity. Specifically, the solar power generation system 40 is realized by a solar cell module including a PV (PhotoVoltaic) panel, a power conditioner, and the like.

[0025] The power management system 50 is a system realized by one or more server devices located outside the apartment building 100. The power management system 50 receives power data from multiple power measurement devices 30, and thereby manages the amount of power consumed by each of the multiple dwelling units 101. The power management system 50 is used, for example, by a high-voltage bulk power purchasing company that has a bulk power purchasing contract with the apartment building 100.

[0026] The weather information management system 60 is a system realized by one or more server devices located outside the apartment building 100. The weather information management system 60 provides weather forecast information and past weather information to the information processing system 10 by communicating with the information processing system 10 via a wide area communication network 90. ​​The weather forecast information and the weather information each include solar radiation information, temperature information, etc.

[0027] [Overview of Operation] A bulk power receiving business operator purchases power from a power company. Here, a contract (demand contract) is known in which, if the peak of power supplied from the power grid to the apartment building 100 exceeds a certain threshold, the power purchase price will increase from the following year. Therefore, it is necessary to suppress the peak of power supplied from the power grid to the apartment building 100.

[0028] Each of the multiple heat pump hot water supply systems 20 installed in the apartment building 100 is optimized to perform a heating operation for the amount of hot water required per day during the late night hours based on past operation history information. Figure 2 is a diagram showing an example of a time period during which the multiple heat pump hot water supply systems 20 perform heating operation, and the vertical axis of the graph in Figure 2 represents the power consumption resulting from the heating operation, and the horizontal axis of the graph represents time (hour).

[0029] As shown in (a) of Figure 2, if all four heat pump hot water supply systems 20 installed in dwelling units A to D are operating in boiling mode late at night, there is a possibility that a peak in the amount of electricity supplied from the power grid to the apartment building 100 will occur during the time period surrounded by the dashed line.

[0030] Therefore, as shown in Figure 2 (b), the information processing system 10 shifts the time period during which some of the heat pump hot water systems 20 (the heat pump hot water systems 20 installed in dwelling units C and D) perform heating operations from late at night to daytime, thereby enabling the information processing system 10 to prevent peak power supply from the power grid to the apartment building 100 from occurring during late at night.

[0031] [Specific Example of Operation] The following describes a specific example of the operation of the information processing system 10. Fig. 3 is a flowchart of a specific example of the operation of the information processing system 10. The specific example of the operation below is performed in the evening (e.g., between 3:00 PM and 4:00 PM) of the day before the target day.

[0032] The first prediction unit 14 of the information processing system 10 acquires solar radiation information (weather forecast information) for the area to which the apartment building 100 belongs on a target day by communicating with the weather information management system 60 using the communication unit 11 (S11). The first prediction unit 14 predicts the amount of power generation on the target day based on the acquired solar radiation information and specification information (information indicating power generation efficiency, etc.) of the solar power generation system 40 pre-stored in the storage unit 13 (S12). The amount of power generation is predicted for each unit time. The unit time is, for example, 30 minutes, but is not particularly limited thereto.

[0033] The second prediction unit 15 communicates with the weather information management system 60 using the communication unit 11 to obtain temperature information (weather forecast information) for the area to which the apartment building 100 belongs on the target day (S13). More specifically, the temperature information is information indicating the predicted maximum temperature and minimum temperature on the target day. Note that the temperature information may be obtained together with the solar radiation information in step S11, in which case the processing of step S13 can be omitted.

[0034] The second prediction unit 15 predicts the amount of power consumption for each of the multiple dwelling units 101 included in the apartment building 100 on the target day based on the acquired temperature information and the baseline data previously stored in the storage unit 13 (S14). The amount of power consumption here refers to the time waveform of the total power consumption of the dwelling units 101. The amount of power consumption is predicted for each unit time. The unit time is, for example, 30 minutes, but is not particularly limited thereto.

[0035] Here, the baseline data will be described. The baseline data includes time waveforms (time series data) of power consumption in each of the multiple dwelling units 101 included in the apartment building 100. The time waveform of power consumption in a given dwelling unit 101 is actual data measured in the past by a power measurement device 30 installed in that dwelling unit 101, and indicates the total amount of power consumption in that dwelling unit 101 (in other words, the amount of power consumption in the main circuit of that dwelling unit 101). The time waveform of power consumption included in the baseline data is actual data covering a relatively long period of time, for example, several months to several years.

[0036] The baseline data is provided to the information processing system 10 from the power management system 50 (high-voltage bulk power receiving business operator), for example, by the information processing system 10 communicating with the power management system 50, but may be provided via any route.

[0037] In the baseline data, the time waveform of power consumption is linked to the month, date, day of the week, whether it is a holiday, time, and temperature information. In step S14, the second prediction unit 15, for example, refers to the baseline data to identify a day (approximate day) whose day of the week, holiday, and temperature information (temperature information acquired in step S13) are most similar to those of the target day. The second prediction unit 15 can predict the time waveform of power consumption of each of the multiple dwelling units 101 on the identified approximate day as the amount of power consumption of each of the multiple dwelling units 101 on the target day.

[0038] Next, the second prediction unit 15 estimates the past power consumption of each of the heat pump hot water supply systems 20 corresponding to the multiple dwelling units 101 (S15). Specifically, the second prediction unit 15 estimates the power consumption of each of the heat pump hot water supply systems 20 using a machine learning model stored in the storage unit 13.

[0039] This machine learning model is a trained model that uses as training data performance data for a dwelling unit that associates the following information (1) to (4) for a given day. The training data is performance data obtained for a dwelling unit in a housing complex other than the housing complex 100, but may also be performance data obtained for the dwelling unit 101 in the housing complex 100.

[0040] (1) Time waveform of the power consumption of the heat pump hot water system on that day (2) Time waveform of the power consumption of the entire dwelling unit on that day (3) Temperature information on that day (4) Date information on that day (month, day, day of the week, whether it is a holiday or not)

[0041] The second prediction unit 15 can acquire the time waveform of power consumption on a predetermined past day of the heat pump hot water supply system 20 installed in the dwelling unit 101 by inputting into the machine learning model the time waveform of power consumption of the dwelling unit 101 on a predetermined past day (for example, the previous day) from the baseline data stored in the memory unit 13, the temperature information on the predetermined past day, and the date information on the predetermined past day. The second prediction unit 15 can estimate the amount of power consumption of the heat pump hot water supply system 20 installed in the dwelling unit 101 from the acquired time waveform.

[0042] More specifically, three types of machine learning models are stored in the memory unit 13, and in step S14, for example, any one of the three types (for example, machine learning model M) is used.

[0043] Here, three types of machine learning models will be described. For example, the above-described learning data is divided into three types, learning data L, learning data M, and learning data S, according to the magnitude of the power consumption of the heat pump hot water supply system 20 included in the learning data (L (large), M (medium), S (small)). This allows three types of machine learning models, namely, a machine learning model L trained on the learning data L, a machine learning model M trained on the learning data M, and a machine learning model S trained on the learning data S, to be generated and stored in the storage unit 13. The three types of machine learning models are constructed based on mutually different learning data.

[0044] The second prediction unit 15 selects a machine learning model for each of the plurality of heat pump hot water supply systems 20 based on the estimated past power consumption of each of the plurality of heat pump hot water supply systems 20 (S16).

[0045] Specifically, the second prediction unit 15 selects one of three types of machine learning models for each of the multiple heat pump hot water systems 20. The second prediction unit 15 selects machine learning model L for a heat pump hot water system 20 with a large estimated amount of power consumption. The second prediction unit 15 selects machine learning model M for a heat pump hot water system 20 with a standard estimated amount of power consumption. The second prediction unit 15 selects machine learning model S for a heat pump hot water system 20 with a small estimated amount of power consumption. The magnitude of the power consumption is determined using, for example, a threshold value. The selection of the machine learning model may be based on the total power consumption of the dwelling unit 101.

[0046] The second prediction unit 15 then predicts the amount of power consumption on the target day for each of the heat pump hot water supply systems 20 corresponding to the dwelling units 101 (S17). Fig. 4 is a diagram showing a method for predicting the amount of power consumption of the heat pump hot water supply system 20.

[0047] FIG. 4A shows the time waveform of the power consumption of the entire dwelling unit 101 predicted in step S14. The second prediction unit 15 inputs the time waveform of the power consumption of the dwelling unit 101 on the target day predicted in step S14 (corresponding to FIG. 4A) along with the temperature information and date information for the target day acquired in step S13 into the machine learning model selected in step S16. As a result, the second prediction unit 15 acquires the time waveform of the power consumption of the heat pump hot water supply system 20 installed in the dwelling unit 101 on the target day. FIG. 4B shows the time waveform of the power consumption of the heat pump hot water supply system 20 predicted by the machine learning model. The second prediction unit 15 can predict the amount of power consumption of the heat pump hot water supply system 20 on the target day from the acquired time waveform. Note that in FIG. 4B, the actual measured value (correct data) of the time waveform of the power consumption of the heat pump hot water supply system 20 is indicated by a dotted line.

[0048] In this way, the second prediction unit 15 selectively uses three types of machine learning models to predict the time waveform of the power consumption of the heat pump hot water supply system 20 on the target day based on estimated values ​​of the past power consumption of the heat pump hot water supply system 20. This makes it possible to improve the prediction accuracy compared to predicting the time waveform of the power consumption of the heat pump hot water supply system 20 on the first target day by fixedly using one type of machine learning model. Note that two types of machine learning models may be prepared, or four or more types may be prepared.

[0049] To further improve the prediction accuracy, the second prediction unit 15 may correct the time waveform of the power consumption of the heat pump hot water supply system 20 predicted by the machine learning model using a predetermined algorithm. (c) of Fig. 4 shows the time waveform of the power consumption of the heat pump hot water supply system 20 corrected using the predetermined algorithm. (c) of Fig. 4 shows the actual measured value (correct data) of the time waveform of the power consumption of the heat pump hot water supply system 20 with a dotted line.

[0050] The waveform of the power consumption of the heat pump hot water supply system 20 has a characteristic shape (top hat shape), so prediction accuracy can be improved by correcting (waveform shaping) using a specified algorithm.

[0051] As described above, after the power consumption amounts for the plurality of heat pump hot water supply systems 20 corresponding to the plurality of dwelling units 101 on the target day are predicted in step S17, the control unit 16 creates a shift plan for shifting the time periods during which some of the plurality of heat pump hot water supply systems 20 perform the water heating operation (S18). In other words, the process of creating the shift plan is a process of determining the heat pump hot water supply systems 20 for which the time periods during which the water heating operation is to be shifted. Figure 5 is a diagram for explaining the shifting of the time periods during which the water heating operation is performed.

[0052] The bar graph shown in (a) of Fig. 5 shows the predicted total power consumption of the apartment building 100 on the target day, and is obtained by adding up the power consumption predicted in step S14 for each of the multiple dwelling units 101. The line graph shown in (a) of Fig. 5 shows the power generation amount of the photovoltaic power generation system 40 predicted in step S12.

[0053] If all of the power generated by the solar power generation system 40 is consumed in the apartment building 100 (self-consumption), in order to keep the power supplied to the apartment building 100 from the power grid below a threshold, the total power consumption of the apartment building 100 (bar graph) must fall within a range below the threshold in Figure 5(a).

[0054] Here, each of the multiple heat pump hot water supply systems 20 is typically optimized to perform water heating operation during the night hours based on the past operation history information of the heat pump hot water supply system 20. Therefore, the control unit 16 controls some of the multiple heat pump hot water supply systems 20 so that the water heating operation by these heat pump hot water supply systems 20 is performed during the daytime hours. In other words, the control unit 16 shifts (sets) the time period during which some of the multiple heat pump hot water supply systems 20 perform water heating operation from the night hours to the daytime hours. As a result, as shown in (b) of FIG. 5, the power supplied from the power grid to the apartment building 100 can be kept below a threshold.

[0055] Below, a method for determining the heat pump hot water supply system 20 (hereinafter also referred to as the target system) whose heating operation time period is to be shifted among the plurality of heat pump hot water supply systems 20 will be described. The plurality of dwelling units 101 included in the apartment building 100 are divided into n groups, group 1 to group n (n is a natural number of 2 or greater). In other words, the plurality of heat pump hot water supply systems 20 are divided into n groups. For example, if the total number of the plurality of dwelling units 101 is 120 and n = 8, eight groups each consisting of 15 dwelling units 101 will be obtained.

[0056] The control unit 16 selects, for example, m candidate groups (m is a natural number equal to or greater than 1) that are a part of the n groups based on the priority.

[0057] The control unit 16 performs a simulation to determine whether the goal of reducing the power supplied from the power grid to the apartment building 100 to a threshold or less on the target day will be achieved (whether the result will be as shown in FIG. 5(b)) if the time periods during which the water heating operations of the selected m candidate groups are performed are shifted to the daytime. The extent to which the power consumption can be shifted can be estimated using the power consumption of the heat pump hot water supply systems 20 on the target day predicted in step S15.

[0058] If the simulation results show that the target has been achieved, the control unit 16 determines m candidate groups and determines the heat pump hot water supply system 20 belonging to the determined candidate group (hereinafter also referred to as the target group) as the target system. If the simulation results show that the target has not been achieved, for example, the time period during which the heating operation is performed is not shifted, or the candidate group is changed (added, reduced, or replaced) and the simulation is performed again.

[0059] In determining the target system, in order to prevent the same group from being determined as the target group repeatedly, once a group has been determined as the target group, its priority for selection as one of the m candidate groups is lowered. In other words, once a group has been determined as the target group, it becomes less likely to be determined as the target group for a certain period of time.

[0060] Note that this method of determining the target system (target group) is one example. The information processing system 10 may employ other algorithms that can determine the target system so that the goal is achieved.

[0061] After the shift plan is generated in step S18 in this way, the control unit 16 transmits a control command to the target system indicated by the shift plan by communicating with the target system using the communication unit 11 based on the generated shift plan (S19). The control command specifies the first time slot set by the control unit 16, which is at least a part of the daytime time slot during which the heating operation should be performed.

[0062] The hot water supply control device 22 of the target system receives the control command via the communication device 21 and controls the heat pump 23 during the first time slot specified in the received control command, thereby performing the water heating operation during the first time slot. In other words, the hot water supply control device 22 of the target system shifts the time slot for the water heating operation from late night to daytime based on the received control command. In this way, the control unit 16 can set the time slot for the water heating operation of at least some of the multiple heat pump hot water supply systems 20 to the first time slot.

[0063] The hot water supply control devices 22 of the heat pump hot water supply systems 20 other than the target system that did not receive the control command perform the boiling operation during the night hours as usual based on the past operation history information.

[0064] As described above, the information processing system 10 includes a first prediction unit 14 that predicts the amount of power generated per unit time of the photovoltaic power generation system 40 installed in the apartment building 100 on a target day, a second prediction unit 15 that predicts the amount of power consumed per unit time of the entire apartment building 100 on the target day and that predicts the amount of power consumed per unit time of the multiple heat pump hot water supply systems 20 installed in the multiple dwelling units 101 included in the apartment building 100, and a control unit 16. Based on the predicted amount of power generated, the predicted amount of power consumed by the entire apartment building 100, and the predicted amount of power consumed by the multiple heat pump hot water supply systems 20, the control unit 16 sets a time period during which a target system, which is one of the multiple heat pump hot water supply systems 20, will perform a heating operation to a first time period that corresponds to at least a part of the daytime time period on the target day.

[0065] Such an information processing system 10 can prevent peaks in the amount of power supplied from the power grid to the apartment building 100 from occurring during late-night hours.

[0066] [Modification of Operation] In the specific example of the operation described above, the information processing system 10 shifts the time period during which the target system performs the heating operation to the daytime, but the time period may be shifted (divided) into the daytime and another time period. Figure 6 is a diagram showing an example of shifting the time period during which the target system performs the heating operation.

[0067] 6, the morning time zone, the daytime time zone, the evening time zone, and the late night time zone are defined. First, these definitions will be explained.

[0068] The late-night time period is a time period to which a late-night rate applies, as determined by the electric power company that supplies power from the power grid to the apartment building 100. In the example of Figure 6, the late-night time period is from 0:00 to 8:00. The late-night time period differs depending on the electric power company that supplies power from the power grid to the apartment building 100.

[0069] The morning time period is the latter half of the late night time period. If the late night time period is from 0:00 to 8:00, the morning time period is from 4:00 to 8:00. The night time period is from 18:00 to 8:00 the next day, including the late night time period (morning time period). The daytime period is from 8:00 to 18:00, excluding the night time period, and is the time period immediately following the morning time period.

[0070] 6, the "no shift" column shows hatched periods during which a normal heat pump hot water supply system 20 other than the target system performs the heating operation. Shift example 1 corresponds to a specific example of operation. That is, shift example 1 shows an example in which the period during which the target system performs the heating operation is shifted to a first period corresponding to at least a part of the daytime period.

[0071] Here, as shown in the column for Shift Example 2, the control unit 16 of the information processing system 10 may shift (divide) the time period during which the target system performs the water heating operation into a first time period and a second time period corresponding to at least a part of the morning time period. In other words, the control unit 16 may set the time period during which the target system performs the water heating operation to the first time period and the second time period, and in Operation Example 1, the first time period may be interpreted as the first time period and the second time period. The amount of hot water to be boiled in the first time period and the second time period is determined (distributed) using a predetermined algorithm.

[0072] Because the heating operation of heat pump hot water supply systems 20 other than the target system is typically performed between 11:00 PM and 4:00 AM, it is expected that the peak power consumption resulting from the heating operation of multiple heat pump hot water supply systems 20 will also occur between 11:00 PM and 4:00 AM. According to shift example 2, the target system performs heating operation during at least part of the daytime and at least part of the morning, avoiding the time periods when peak power consumption is likely to occur, thereby leveling out power consumption on the target day. Furthermore, shift example 2 can prevent hot water shortages from occurring when hot water is used during the morning hours.

[0073] Furthermore, as shown in the column for Shift Example 3, in Shift Example 2, the control unit 16 may set the second time slot to the end of the morning time slot. In other words, the end time of the second time slot may be the same time as the end time of the morning time slot or the time immediately before the end time of the morning time slot. The time immediately before the end time of the morning time slot is, for example, the time that belongs to the last of the four time slots obtained by dividing the morning time slot into four equal parts. For example, the control unit 16 calculates the boiling time operation backwards from the amount of water to be boiled in the second time slot and sends a control command to the target system to start boiling operation so that boiling will be completed by the end time of the morning time slot.

[0074] In this way, if the second time period is set at the end of the morning time period, the water will be heated just before the daytime time period when it is used, which prevents the water temperature from dropping during the period before it is used, making it more efficient.

[0075] Furthermore, as shown in the column for Shift Example 4, the control unit 16 may shift (divide) the time period during which the target system performs the heating operation into a first time period, a second time period, and a third time period corresponding to at least a portion of the nighttime period from the day before the target day through the target day. In other words, the control unit 16 may set the time period during which the target system performs the heating operation to the first time period, the second time period, and the third time period, and in the specific example of the operation, the first time period may be read as the first time period, the second time period, and the third time period. Note that the second time period and the third time period are, for example, time periods that do not overlap and are not consecutive.

[0076] As described above, the peak power consumption due to the heating operation of the multiple heat pump hot water supply systems 20 is thought to occur between 11:00 PM and 4:00 AM the next morning, and in Shift Example 4, if the target system performs heating operation during at least part of the daytime, at least part of the morning, and at least part of the evening, avoiding the time periods when peak power consumption is likely to occur, power consumption on the target day can be leveled out. Furthermore, Shift Example 4 can prevent hot water shortages from occurring when hot water is used in the first half of the late-night hours.

[0077] In addition, in shift example 4, if the third time slot belongs to the day before the target day, the power consumption of the apartment building 100 is predicted for at least the night time period of the day before the target day. The method for predicting the power consumption is the same as steps S13 to S15.

[0078] Furthermore, as shown in the column for Shift Example 5, the control unit 16 may set the second time period to the end of the morning time period in Shift Example 4. If the second time period is set to the end of the morning time period, the hot water is heated just before the daytime time period when the hot water is used, which prevents the hot water temperature from dropping during the period before it is used, and is therefore more efficient.

[0079] [Other Modifications] In the above embodiment, the information processing system 10 predicted the amount of power generated by the photovoltaic power generation system 40 on the target day, but if a photovoltaic power generation system 40 is not installed in the apartment building 100, the prediction of the amount of power generated by the photovoltaic power generation system 40 may be omitted. In other words, the information processing system 10 may shift the time period during which the heating operation is performed by the target system to the first time period, etc., based on the predicted power consumption of the entire apartment building 100 and the predicted power consumption of the multiple heat pump hot water supply systems 20.

[0080] In the above embodiment, it has been described that the machine learning model for predicting the time waveform of the power consumption of the heat pump hot water supply system 20 is selected based on the magnitude of the past power consumption of the heat pump hot water supply system 20. However, the machine learning model may be selected based on trends (parameters) obtained from the time waveform of the past power consumption of the heat pump hot water supply system 20, and it is not necessary to select the model based on the magnitude of the past power consumption. Furthermore, one machine learning model may be used in a fixed manner, and it is not necessary to select a machine learning model.

[0081] In the above embodiment, it has been explained that baseline data (actual data on the time waveform of power consumption in each of the multiple dwelling units 101 included in the apartment building 100) is stored in advance in the storage unit 13, but when the apartment building 100 is first used, for example, no baseline data exists. Below, a method for predicting the baseline data of the apartment building 100 in such a case will be described.

[0082] When actual data is obtained that associates baseline data (daily power consumption for each dwelling unit in the other apartment building) with the power consumption of the heat pump hot water supply system 20 for each dwelling unit in the other apartment building, the learning data is created by associating the actual data with daily temperature information, etc. In other words, the learning data is data that shows the relationship between the baseline data, the power consumption of the heat pump hot water supply system 20, and temperature information, etc.

[0083] The second prediction unit 15 of the information processing system 10 constructs a machine learning model for creating baseline data that has learned this learning data and is capable of creating baseline data. The second prediction unit 15 can create baseline data for the dwelling units included in the apartment building 100 by inputting temperature information, etc. in the apartment building 100 and the amount of power consumption of the heat pump hot water supply systems 20 installed in the dwelling units included in the apartment building 100 into the machine learning model for creating baseline data (hereinafter also referred to as the second machine learning model).

[0084] In order to obtain the power consumption of the heat pump hot water supply system 20 to be input into the machine learning model, for example, a machine learning model for predicting the power consumption of the heat pump hot water supply system 20 (hereinafter also referred to as the first machine learning model) described in the specific example of the above operation is used.

[0085] Therefore, if baseline data for the apartment building 100 does not exist, the second prediction unit 15 first uses the first machine learning model to predict the power consumption of the heat pump hot water system 20 installed in each dwelling unit 101 of the apartment building 100. Next, the second prediction unit 15 creates baseline data for the dwelling unit 101 by inputting the predicted power consumption of the heat pump hot water system 20 into the second machine learning model, and predicts the power consumption of the entire dwelling unit 101 on the target day based on the created baseline data. The second prediction unit 15 then predicts the power consumption of the entire dwelling unit 101 for each of the multiple dwelling units 101 and adds them up to predict the power consumption per unit time for the entire apartment building 100 on the target day.

[0086] In this way, the second prediction unit 15 uses a machine learning model to predict the power consumption of multiple heat pump hot water systems 20, and based on the predicted power consumption of multiple heat pump hot water systems 20, can predict the power consumption per unit time for the entire apartment building 100 on the target day.

[0087] [Effects, etc.] Hereinafter, examples of techniques that can be obtained from the disclosure of this specification will be given, and effects, etc. that can be obtained from the exemplified techniques will be described.

[0088] Technology 1 is an information processing system 10 including a first prediction unit 14 that predicts the amount of power generated per unit time of a solar power generation system 40 installed in an apartment building 100 on a target day; a second prediction unit 15 that predicts the amount of power consumed per unit time of the entire apartment building 100 on the target day; and a control unit 16 that sets, based on the predicted amount of power generated and the predicted amount of power consumed, a time period during which heating operation is performed by a target system that is one of a plurality of heat pump hot water systems 20 installed in a plurality of dwelling units 101 included in the apartment building 100, to a first time period that corresponds to at least a portion of the daytime time period on the target day.

[0089] Such an information processing system 10 can prevent peak power consumption in the apartment building 100 from occurring during the late night hours by shifting the time period during which the target system performs heating operation to the daytime hours of the target day.

[0090] Technology 2 is the information processing system 10 of Technology 1, in which the control unit 16 sets the time period during which the target system performs heating operation to a first time period and a second time period corresponding to at least a portion of the morning time period on the target day.

[0091] Such an information processing system 10 can level out the power consumption in the apartment building 100 by shifting the time period during which the target system performs the heating operation between two time periods.

[0092] Technology 3 is an information processing system 10 of Technology 2, in which the control unit 16 sets the time periods during which the target system performs heating operation to the first time period, the second time period, and a third time period corresponding to at least a part of the night time period from the day before the target day through the target day, and the second time period and the third time period do not overlap and are not consecutive.

[0093] Such an information processing system 10 can further equalize the power consumption in the apartment building 100 by shifting the time period during which the target system performs the heating operation to three time periods.

[0094] Technique 4 is the information processing system 10 of Technique 2 or 3, in which the end time of the second time slot is the same as the end time of the morning time slot or the time immediately before the end time of the morning time slot.

[0095] By setting the second time period at the end of the morning time period, the information processing system 10 can prevent the temperature of the hot water from dropping during the period up until the daytime when the hot water is used.

[0096] Technique 5 is the information processing system 10 of technique 3, in which the control unit 16 sets the second time slot and the third time slot so as to avoid a peak in the predicted power consumption amount.

[0097] Such an information processing system 10 can further level out the power consumption in the apartment building 100 by setting the second and third time periods so as to avoid peaks in the predicted power consumption.

[0098] Technique 6 is the information processing system 10 of any of Techniques 1 to 5, in which the second prediction unit 15 predicts the power consumption of a plurality of heat pump hot water systems 20 using a machine learning model, and predicts the power consumption per unit time on a target day for the entire apartment building 100 based on the predicted power consumption of the plurality of heat pump hot water systems 20. Technique 6 corresponds to a method (described in the "Other Modifications" section) for predicting the power consumption per unit time on a target day for the entire apartment building 100 when baseline data for the apartment building 100 does not exist.

[0099] Such an information processing system 10 can use a machine learning model to predict the amount of power consumption of multiple heat pump hot water systems 20 on a target day, thereby predicting the amount of power consumption per unit time for the entire apartment building 100 on a target day.

[0100] Technology 7 is the information processing system 10 of Technology 6, in which the machine learning model is a machine learning model selected from at least three machine learning models, and each of the at least three machine learning models takes the power consumption of the entire dwelling unit as input and outputs the power consumption of a heat pump hot water system installed in the dwelling unit.

[0101] Such an information processing system 10 can selectively use machine learning models constructed based on mutually different learning data to improve the accuracy of prediction of the amount of power consumption of a heat pump hot water supply system.

[0102] Technique 8 is an information processing system 10 of any of techniques 1 to 7, in which the second prediction unit 15 predicts the amount of power consumption per unit time for the entire apartment building 100 based on the day of the week of the target day and the predicted temperature for the target day.

[0103] Such an information processing system 10 can predict the amount of power consumption per unit time for the entire apartment building 100, taking into consideration the day of the week and predicted temperature, which have a large impact on the amount of power consumption.

[0104] Technology 9 is a heat pump hot water system 20 installed in a dwelling unit 101 included in an apartment building 100, and includes a heat pump 23, a tank 24 for storing hot water boiled by the heat pump 23, and a hot water control device 22 that receives a control command transmitted by an information processing system 10 and controls the heat pump during a first time period specified in the received control command, thereby performing boiling operation during the first time period, wherein the information processing system 10 predicts the amount of power generated per unit time on a target day by a solar power generation system 40 installed in the apartment building 100 and the amount of power consumed per unit time on a target day by the entire apartment building 100, and the heat pump hot water system 20 is a heat pump hot water system 20 that is determined based on the predicted amount of power generation and the predicted amount of power consumption.

[0105] Such a heat pump hot water supply system 20 can prevent peak power consumption in the apartment building 100 from occurring during the late night hours by shifting the time period during which heating operation is performed to the daytime on the target day.

[0106] Technology 10 is a heat pump hot water system 20 of Technology 9, in which the hot water control device 22 controls the heat pump 23 during a first time period and a second time period instructed by a received control command, thereby performing heating operation during the first time period and the second time period, the second time period being a time period corresponding to at least a part of the morning time period of the target day, and each of the first time period and the second time period being a time period determined by the information processing system 10 based on the predicted power generation amount and the predicted power consumption amount.

[0107] Such a heat pump hot water supply system 20 can level out the power consumption in the apartment building 100 by shifting the time period during which the water heating operation is performed between two time periods.

[0108] Technique 11 is an information processing method executed by a computer system, the information processing method including: step S12 of predicting the amount of power generated per unit time of solar power generation system 40 installed in apartment building 100 on a target day; step S14 of predicting the amount of power consumed per unit time of the entire apartment building 100 on the target day; and step S19 of setting, based on the predicted amount of power generation and the predicted amount of power consumption, a time period during which a heating operation is performed by a target system, which is one of multiple heat pump hot water supply systems 20 installed in multiple dwelling units 101 included in apartment building 100, to a first time period corresponding to at least a part of the daytime time period on the target day. The computer system here is, for example, information processing system 10.

[0109] This information processing method can prevent peak power consumption in the apartment building 100 from occurring during the late night hours by shifting the time period during which the target system performs heating operation to the daytime hours of the target day.

[0110] Technique 12 is a program for causing a computer system to execute the information processing method of technique 11.

[0111] According to such a program, the computer system can prevent peak power consumption in the apartment building 100 from occurring during the late night hours by shifting the time period during which the target system performs heating operation to the daytime hours of the target day.

[0112] (Other Embodiments) Although the embodiments have been described above, the present disclosure is not limited to the above-described embodiments.

[0113] For example, in the above-described embodiments, the information processing system may be realized by multiple devices or may be realized as a single device. Thus, the system in this specification may be configured by a single device or may be configured by multiple devices. When the system is realized by multiple devices, the components of the system may be distributed among the multiple devices in any manner.

[0114] Furthermore, the method of communication between the devices in the above-described embodiment is not particularly limited. Furthermore, a relay device (such as a broadband router, not shown) may be involved in the communication between the devices.

[0115] In the above-described embodiment, the processing performed by a specific processing unit may be performed by another processing unit. The order of multiple processing operations may be changed, or multiple processing operations may be performed in parallel.

[0116] In the above-described embodiments, each component may be realized by executing a software program suitable for that component, or by a program execution unit such as a CPU or processor reading and executing a software program recorded on a recording medium such as a hard disk or semiconductor memory.

[0117] Furthermore, each component may be realized by hardware. For example, each component may be a circuit (or integrated circuit). These circuits may form a single circuit as a whole, or each may be a separate circuit. Furthermore, each of these circuits may be a general-purpose circuit or a dedicated circuit.

[0118] Furthermore, the general or specific aspects of the present disclosure may be realized as a system, an apparatus, a method, an integrated circuit, a computer program, or a computer-readable recording medium such as a CD-ROM, or as any combination of a system, an apparatus, a method, an integrated circuit, a computer program, and a recording medium.

[0119] For example, the present disclosure may be realized as an information processing method executed by a computer system such as the information processing system of the above-described embodiment, or as a program (computer program product) for causing a computer system to execute the information processing method. Furthermore, the present disclosure may be realized as a computer-readable non-transitory recording medium on which such a program is recorded.

[0120] The present disclosure may be realized as a control method (operation method) for a heat pump hot water supply system executed by a computer system such as the heat pump hot water supply system of the above-described embodiment, or as a program (computer program product) for causing a computer system to execute the control method. Furthermore, the present disclosure may be realized as a computer-readable non-transitory recording medium on which such a program is recorded.

[0121] In addition, this disclosure also includes forms obtained by applying various modifications to each embodiment that a person skilled in the art would think of, or forms realized by arbitrarily combining the components and functions of each embodiment within the scope that does not deviate from the intent of this disclosure.

[0122] REFERENCE SIGNS LIST 10 Information processing system 11 Communication unit 12 Information processing unit 13 Memory unit 14 First prediction unit 15 Second prediction unit 16 Control unit 20 Heat pump hot water supply system 21 Communication device 22 Hot water supply control device 23 Heat pump 24 Tank 30 Power measurement device 40 Photovoltaic power generation system 50 Power management system 60 Weather information management system 90 Wide area communication network 100 Apartment building 101 Dwelling unit

Claims

1. A first prediction unit that predicts the power generation amount per unit time on a target day of a solar power generation system installed in an apartment house, a second prediction unit that predicts the power consumption amount per unit time on the target day of the entire apartment house, and based on the predicted power generation amount and the predicted power consumption amount, a control unit that sets a time period during which a boiling operation is performed by a target system, which is a part of a plurality of heat pump water heating systems installed in a plurality of dwelling units included in the apartment house, to a first time period corresponding to at least a part of the daytime time period of the target day. An information processing system.

2. The information processing system according to claim 1, wherein the control unit sets the time period during which the boiling operation is performed by the target system to a first time period and a second time period corresponding to at least a part of the morning time period of the target day.

3. The control unit sets the time period during which the boiling operation is performed by the target system to a first time period, a second time period, and a third time period corresponding to at least a part of the night time period from the day before the target day to the target day, and the second time period and the third time period do not overlap and are not continuous. The information processing system according to claim 2.

4. The information processing system according to claim 2, wherein the end time of the second time period is the same time as the end time of the morning time period or the time immediately before the end time of the morning time period.

5. The information processing system according to claim 3, wherein the control unit sets the second time period and the third time period so as to avoid the peak of the predicted power consumption amount.

6. The second prediction unit predicts the power consumption amount of the plurality of heat pump water heating systems using a machine learning model, and predicts the power consumption amount per unit time on the target day of the entire apartment house based on the predicted power consumption amount of the plurality of heat pump water heating systems. The information processing system according to claim 1.

7. The machine learning model is a machine learning model selected from at least three machine learning models constructed based on different learning data. Each of the at least three machine learning models takes the total power consumption of a household as input and outputs the power consumption of a heat pump water heating system installed in the household. The information processing system according to claim 6.

8. The second prediction unit predicts the power consumption per unit time of the entire apartment building based on the day of the week of the target day and the predicted temperature of the target day. The information processing system according to any one of claims 1 to 7.

9. A heat pump water heating system installed in a household included in an apartment building, comprising: a heat pump; a tank for storing hot water heated by the heat pump; and a water heating control device that receives a control command transmitted by an information processing system and controls the heat pump in a first time period specified in the received control command to perform a heating operation in the first time period. The first time period is a time period determined by the information processing system based on the power generation amount per unit time of a solar power generation system installed in the apartment building on the target day and the power consumption amount per unit time of the entire apartment building on the target day. Heat pump water heating system.

10. The water heating control device controls the heat pump in the first time period and the second time period commanded by the received control command to perform a heating operation in the first time period and the second time period. The second time period is a time period corresponding to at least a part of the morning time period of the target day. Each of the first time period and the second time period is a time period determined by the information processing system based on the predicted power generation amount and the predicted power consumption amount. The heat pump water heating system according to claim 9.

11. An information processing method executed by a computer system, the method including: predicting the power generation amount per unit time on a target day of a solar power generation system installed in an apartment house; predicting the power consumption amount per unit time on the target day of the entire apartment house; and based on the predicted power generation amount and the predicted power consumption amount, setting, for a target system that is a part of a plurality of heat pump water heating systems installed in a plurality of dwelling units included in the apartment house, a time period during which boiling operation is performed to a first time period corresponding to at least a part of the daytime time period of the target day.

12. A program for causing the computer system to execute the information processing method according to claim 11.

Images