CN113825955A - Method, apparatus, system, storage medium, and processor for determining a temperature setting - Google Patents

Method, apparatus, system, storage medium, and processor for determining a temperature setting Download PDF

Info

Publication number
CN113825955A
CN113825955A CN201980096481.1A CN201980096481A CN113825955A CN 113825955 A CN113825955 A CN 113825955A CN 201980096481 A CN201980096481 A CN 201980096481A CN 113825955 A CN113825955 A CN 113825955A
Authority
CN
China
Prior art keywords
temperature value
temperature
sub
cooling system
time period
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201980096481.1A
Other languages
Chinese (zh)
Inventor
汤琦
曲颖
罗章维
王焦剑
李聪超
刘晓南
鲁雷
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Siemens Ltd China
Original Assignee
Siemens Ltd China
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Siemens Ltd China filed Critical Siemens Ltd China
Publication of CN113825955A publication Critical patent/CN113825955A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F11/00—Control or safety arrangements

Landscapes

  • Engineering & Computer Science (AREA)
  • Chemical & Material Sciences (AREA)
  • Combustion & Propulsion (AREA)
  • Mechanical Engineering (AREA)
  • General Engineering & Computer Science (AREA)
  • Air Conditioning Control Device (AREA)

Abstract

The present application relates to methods, apparatuses, systems, storage media, and processors for determining a temperature setting. The method comprises the following steps: acquiring a comfort zone temperature range of each sub-period in a plurality of sub-periods included in a future predetermined period; obtaining a plurality of first temperature value combinations, wherein each first temperature value combination comprises a plurality of temperature values, each temperature value in the plurality of temperature values corresponds to one sub-time period in the plurality of sub-time periods, and each temperature value is in a comfort zone temperature range corresponding to the sub-time period; and determining a target temperature value combination from the plurality of first temperature value combinations, so that the temperature setting value of each of the plurality of sub-time periods is set according to the target temperature value combination, and the running state of the air-conditioning cooling system in a future preset time period is optimal. The technical scheme of the application can effectively reduce the energy consumption of the air-conditioning cooling system in the building while ensuring the comfort of personnel in the building.

Description

Method, apparatus, system, storage medium, and processor for determining a temperature setting Technical Field
The present application relates to the field of temperature control. In particular, the present application relates to methods, devices, systems, storage media, and processors for determining temperature settings for air conditioning cooling systems.
Background
The on-demand control specification is very useful when considering the minimization of Heating Ventilation Air Conditioning (HVAC) systems and associated energy consumption and costs for buildings and buildings. In current practice, demand control strategy decisions including peak demand limiting (peak demand limiting), night and day mode control (night burst control) and temperature compensated duty cycle (temperature-compensated duty cycle) are typically applied to facilitate the supply and demand balancing of building electricity. In general, the existing cooling demand control strategy is to input expert experience, calendar events into the programmable logic controller in advance. In this case, these strategies lack flexibility and do not dynamically reflect real-time changes in building cooling demand, and therefore belong to passive hysteresis control strategies. Furthermore, computational complexity issues arise when trying to find an optimized demand control strategy. Some control strategies may take into account the optimum value of building temperature setting per hour for a predetermined period of time of day, but in this case the amount of calculation may be very large. For example, considering ten adjustable temperatures for an hour, there may be 10^24 possibilities for temperature settings for a predetermined period of time a day. With such a large computing context, it is not practical to calculate and update every hour a set of temperature value combinations that are optimal for a future predetermined time period.
Many buildings use high performance modular Direct Digital Control (DDC) monitoring field panels, such as PXC modular line of products, to perform complex control, monitoring and energy management functions. Applications associated with demand control strategies are programmed to apply such modularity and are implemented by entering the required parameters. By utilizing built-in applications (e.g., peak demand limiting and temperature compensation duty cycles), the user can adjust cooling balance load demand and supply, reducing overall energy usage. Since the demand control strategies for these modular families are designed specifically, the control strategies under these strategies are static and cannot dynamically update the cooling load demand based on real-time data (e.g., cooling side data, such as chiller and pump operating parameters and dynamic electricity rates).
Disclosure of Invention
Embodiments of the present application provide a method, apparatus, system, storage medium, and processor for determining a temperature setting value of an air conditioning cooling system to at least solve the problem of how to determine an optimal temperature setting value for an air conditioning cooling system within a building.
According to one aspect of an embodiment of the present application, there is provided a method of determining a temperature setting value of an air conditioning and cooling system within a building, comprising: acquiring a comfortable zone temperature range of each sub-time period in a plurality of sub-time periods in a future preset time period, wherein the comfortable zone temperature range is a temperature range enabling people in a building to feel comfortable in the corresponding sub-time period, and each comfortable zone temperature range is smaller than a temperature adjustment range of an air conditioning and cooling system; obtaining a plurality of first temperature value combinations, wherein each first temperature value combination comprises a plurality of temperature values, each temperature value in the plurality of temperature values corresponds to one sub-time period in the plurality of sub-time periods, and each temperature value is in a comfort zone temperature range corresponding to the sub-time period; and determining a target temperature value combination from the plurality of first temperature value combinations, so that the temperature setting value of each of the plurality of sub-time periods is set according to the target temperature value combination, and the running state of the air-conditioning cooling system in a future preset time period is optimal.
According to another aspect of the embodiments of the present application, there is also provided an apparatus for determining a temperature setting value of an air conditioning and cooling system in a building, including: the comfortable zone module is configured to execute the step of acquiring the temperature range of the comfortable zone of each sub-time period in a plurality of sub-time periods included in the future preset time period, wherein the temperature range of the comfortable zone is the temperature range enabling people in the building to feel comfortable in the corresponding sub-time period, and each temperature range of the comfortable zone is smaller than the temperature adjustment range of the air conditioning and cooling system; a temperature value combination obtaining module configured to perform a step of obtaining a plurality of first temperature value combinations, wherein each first temperature value combination comprises a plurality of temperature values, each temperature value in the plurality of temperature values corresponds to one sub-time period in the plurality of sub-time periods, and each temperature value is in a comfort zone temperature range corresponding to the sub-time period; and the target temperature value combination determining module is configured to execute the step of determining one target temperature value combination from the plurality of first temperature value combinations, so that the temperature setting value of each of the plurality of sub-time periods is set according to the target temperature value combination, and the running state of the air-conditioning cooling system in a future preset time period is optimal.
According to another aspect of the embodiments of the present application, there is also provided a system for determining a temperature setting value of an air conditioning and cooling system in a building, the system comprising: an air conditioning cooling system; and means for determining a temperature setting for an air conditioning and cooling system within a building, the means comprising: the comfortable zone module is configured to execute the step of acquiring the temperature range of the comfortable zone of each sub-time period in a plurality of sub-time periods included in the future preset time period, wherein the temperature range of the comfortable zone is the temperature range enabling people in the building to feel comfortable in the corresponding sub-time period, and each temperature range of the comfortable zone is smaller than the temperature adjustment range of the air conditioning and cooling system; a temperature value combination obtaining module configured to perform a step of obtaining a plurality of first temperature value combinations, wherein each first temperature value combination comprises a plurality of temperature values, each temperature value in the plurality of temperature values corresponds to one sub-time period in the plurality of sub-time periods, and each temperature value is in a comfort zone temperature range corresponding to the sub-time period; and the target temperature value combination determining module is configured to execute the step of determining one target temperature value combination from the plurality of first temperature value combinations, so that the temperature setting value of each of the plurality of sub-time periods is set according to the target temperature value combination, and the running state of the air-conditioning cooling system in a future preset time period is optimal.
According to another aspect of embodiments of the present application, there is also provided a storage medium having a program stored thereon, the program, when executed by a computer including the storage medium, causing the computer to perform the foregoing method.
According to another aspect of the embodiments of the present application, there is also provided a processor for executing a program stored on a memory, wherein the processor executes the program to perform the foregoing method.
In this way, the optimal temperature setting value for each sub-period in the future predetermined period can be provided to the user, and determining the comfort zone temperature range reduces the amount of calculation to determine the optimal temperature setting value.
In exemplary embodiments of the method, apparatus, system and storage medium according to the foregoing, the step of determining a target temperature value combination from among a plurality of first temperature value combinations comprises: acquiring a temperature setting value-cooling amount corresponding relation between a temperature setting value of an air conditioner cooling system and the cooling amount provided by the air conditioner cooling system and a cooling amount-power consumption corresponding relation between the cooling amount provided by the air conditioner cooling system and the power consumption required by the cooling amount provided by the air conditioner cooling system; and taking the first temperature value combination with the minimum sum of the power consumption corresponding to the plurality of included temperature setting values as a target temperature value combination.
In this way, a temperature setting value that minimizes the amount of electricity used to make the occupants in the building comfortable in each sub-time period in a future predetermined time period can be determined for the air conditioning cooling system.
In exemplary embodiments of the method, apparatus, system and storage medium according to the foregoing, the step of determining a target temperature value combination from among a plurality of first temperature value combinations comprises: acquiring a temperature setting value-cooling amount corresponding relation between a temperature setting value of an air conditioner cooling system and cooling amount provided by the air conditioner cooling system, a cooling amount-power consumption corresponding relation between the cooling amount provided by the air conditioner cooling system and power consumption required by the air conditioner cooling system for providing the cooling amount, and rates of all sub-time periods associated with the air conditioner cooling system; determining the electric charge corresponding to the temperature setting value of each sub-time period according to the temperature setting value-cooling amount corresponding relation, the cooling amount-electricity consumption corresponding relation and the rate; and using the first temperature value combination with the minimum sum of the electric charges corresponding to the plurality of included temperature setting values as a target temperature value combination.
In this way, it is possible to determine the temperature setting value for the air conditioning cooling system that minimizes the electricity rate that makes the person in the building comfortable in each sub-period in the future predetermined period.
In exemplary embodiments of the method, apparatus, system, and storage medium according to the foregoing, further comprising: acquiring historical data, wherein the historical data comprises an actual temperature setting value and an actual cooling capacity of each sub-time period in a historical time period of the air-conditioning cooling system; acquiring prediction data, wherein the prediction data comprises predicted cooling capacity according to the temperature setting value-cooling capacity corresponding relation; establishing a loss function according to the historical data and the prediction data, and determining a prediction error between the predicted cooling capacity and the actual cooling capacity; adjusting the corresponding relation between the temperature setting value and the cooling capacity according to the prediction error; and/or acquiring historical data, wherein the historical data comprises the actual cooling amount and the actual power consumption of the air conditioner cooling system in each sub-time period included in a historical time period; acquiring prediction data, wherein the prediction data comprises power consumption predicted according to the corresponding relation between the cooling capacity and the power consumption; establishing a loss function according to the historical data and the predicted data, and determining a prediction error between the predicted power consumption and the actual power consumption; and adjusting the corresponding relation between the cooling capacity and the power consumption according to the prediction error.
In this way, the parameters of the optimization algorithm can be updated according to the error between the historical data and the predicted value, so that the temperature setting value of the air conditioner cooling system determined in the future is more accurate.
In exemplary embodiments of the method, apparatus, system, and storage medium according to the foregoing, further comprising obtaining a time duration for the adjusted target temperature value combination, and determining the adjusted target temperature value combination over the time duration, the determining the adjusted target temperature value combination over the time duration comprising: after the step of obtaining a plurality of first temperature value combinations, for at least one first temperature value combination in the first temperature value combinations, for each sub-time period in a part or all of the sub-time periods, adjusting the temperature value of the sub-time period based on a preset step length to obtain at least one second temperature value combination, wherein the temperature value of each sub-time period in the at least one second temperature value combination is in a comfort zone temperature range corresponding to the sub-time period; and after the step of determining a target temperature value combination from the plurality of first temperature value combinations, determining an adjusted target temperature value combination from the first temperature value combination and the second temperature value combination, so that the temperature setting value of each of the plurality of sub-time periods is set according to the adjusted target temperature value combination, and the running state of the air-conditioning cooling system in a future preset time period is optimal.
In this manner, the determination of the temperature setting value of the air conditioning cooling system is completed within a prescribed period of time within which the optimization calculation is repeated to update the temperature setting value to the optimum value.
In exemplary embodiments of the method, apparatus, system and storage medium according to the foregoing, the step of determining an adjusted target temperature value combination from the first temperature value combination and the second temperature value combination comprises: acquiring a temperature setting value-cooling amount corresponding relation between a temperature setting value of an air conditioner cooling system and cooling amount provided by the air conditioner cooling system, a cooling amount-power consumption corresponding relation between the cooling amount provided by the air conditioner cooling system and power consumption required by the air conditioner cooling system for providing the cooling amount, and rates of all sub-time periods associated with the air conditioner cooling system; determining the electric charge corresponding to the temperature setting value of each sub-time period according to the temperature setting value-cooling amount corresponding relation, the cooling amount-electricity consumption corresponding relation and the rate; and using the first temperature value combination or the second temperature value combination with the minimum sum of the electric charges corresponding to the plurality of temperature setting values as a target temperature value combination.
In this manner, an updated temperature setting can be determined for the air conditioning cooling system that will make the occupants of the building comfortable and least-charged per sub-time period in the future predetermined time period.
In exemplary embodiments of the method, apparatus, system and storage medium according to the foregoing, the step of determining an adjusted target temperature value combination from the first temperature value combination and the second temperature value combination comprises: acquiring a temperature setting value-cooling amount corresponding relation between a temperature setting value of an air conditioner cooling system and the cooling amount provided by the air conditioner cooling system and a cooling amount-power consumption corresponding relation between the cooling amount provided by the air conditioner cooling system and the power consumption required by the cooling amount provided by the air conditioner cooling system; and taking the first temperature value combination or the second temperature value combination with the minimum sum of the power consumption corresponding to the plurality of temperature setting values as the target temperature value combination.
In this manner, an updated temperature setting can be determined for the air conditioning cooling system that will make the occupants of the building comfortable and minimize power usage for each of the sub-time periods in the future.
In exemplary embodiments of the method, apparatus, system, and storage medium according to the foregoing, further comprising: acquiring historical data, wherein the historical data comprises an actual temperature setting value and an actual cooling capacity of each sub-time period in a historical time period of the air-conditioning cooling system; acquiring prediction data, wherein the prediction data comprises predicted cooling capacity according to the temperature setting value-cooling capacity corresponding relation; establishing a loss function according to the historical data and the prediction data, and determining a prediction error between the predicted cooling capacity and the actual cooling capacity; adjusting the corresponding relation between the temperature setting value and the cooling capacity according to the prediction error; and/or acquiring historical data, wherein the historical data comprises the actual cooling amount and the actual power consumption of the air conditioner cooling system in each sub-time period included in a historical time period; acquiring prediction data, wherein the prediction data comprises power consumption predicted according to the corresponding relation between the cooling capacity and the power consumption; establishing a loss function according to the historical data and the predicted data, and determining a prediction error between the predicted power consumption and the actual power consumption; and adjusting the corresponding relation between the cooling capacity and the power consumption according to the prediction error.
In this manner, the parameters of the optimization algorithm can be updated based on the error between the historical data and the predicted values, making future determinations of updated temperature settings for the air conditioning cooling system more accurate.
In exemplary embodiments of the method, apparatus, system, and storage medium according to the foregoing, further comprising: acquiring prediction errors of a plurality of historical time periods; if the prediction error increases over time in the plurality of historical time periods, performing at least one of the following in the step of adjusting the combination of target temperature values for a length of time over which the combination of target temperature values is adjusted: extending the length of the time length, decreasing the preset step size, and increasing the number of times of adjusting the temperature value of the sub-time period based on the preset step size to obtain at least one second temperature value combination.
In this manner, the optimization algorithm that updates the temperature setting is adjusted by calculating the prediction error, resulting in more accurate results in the subsequent determination of the updated temperature setting for the air conditioning cooling system.
In exemplary embodiments of the method, apparatus, system, and storage medium according to the foregoing, further comprising, at each new sub-period: executing the steps of obtaining a comfort zone temperature range of each sub-time period in a plurality of sub-time periods included in a future preset time period, obtaining a plurality of first temperature value combinations and determining a target temperature value combination from the plurality of first temperature value combinations; and taking the temperature values of the plurality of sub-time periods in the determined target temperature value combination as the temperature values of the corresponding plurality of sub-time periods in one temperature value combination in the plurality of first temperature value combinations to be acquired in the next future preset time period.
In this manner, the temperature setting of the air conditioning cooling system is redetermined at each new sub-period, resulting in a more accurate temperature setting for each sub-period.
In exemplary embodiments of the method, apparatus, system, and storage medium according to the foregoing, further comprising, at each new sub-period: executing the steps of obtaining a comfortable zone temperature range of each sub-time period in a plurality of sub-time periods included in a future preset time period, obtaining a plurality of first temperature value combinations and determining a target temperature value combination from the plurality of first temperature value combinations; executing the steps of obtaining a time length for adjusting the target temperature value combination, and determining the adjusted target temperature value combination in the time length; and taking the temperature values of the plurality of sub-time periods in the determined adjusted target temperature value combination as the temperature values of the corresponding plurality of sub-time periods in one temperature value combination in the plurality of first temperature value combinations to be acquired in the next future preset time period.
In this manner, the temperature setting value of the air conditioning cooling system is re-determined every new sub-period and the optimization calculation is repeated for a prescribed period of time to update the temperature setting value to an optimal value, resulting in a more accurate temperature setting value.
In exemplary embodiments of the method, apparatus, system, and storage medium according to the foregoing, the step of determining the adjusted combination of target temperature values over the duration of time is repeated periodically over the duration of time; and the length of each sub-time period is equal, and the duration of the target temperature value combination is adjusted to be smaller than the length of the sub-time period.
In this way, the updating process of optimizing the calculation result to update the temperature setting value to the optimum value is repeatedly performed for a prescribed period of time, and sufficient operating time is allowed for the air conditioning cooling system to adjust the temperature.
In exemplary embodiments of the method, apparatus, system, and storage medium according to the foregoing, the acquiring the comfort zone temperature range includes: acquiring one or more pieces of information of outdoor temperature, humidity and people flow rate associated with a building; the comfort zone temperature range for each of a plurality of sub-periods included in the future predetermined period is determined based on the one or more information.
In this way, the value range of the temperature setting value of the air conditioning and cooling system which enables people in the building to be comfortable is determined, and the calculation amount of the determined temperature setting value is reduced.
The technical scheme of the application provides the best temperature setting value (enabling indoor personnel to feel comfortable and minimizing energy consumption) of the air conditioner cooling system in each sub-time period in the future preset time period, and in addition, the technical scheme of the application provides a data driving model, and an algorithm capable of dynamically updating the temperature setting value according to prediction errors is provided, so that the accuracy of calculation is ensured. In addition, the user can adjust the model parameter values to explore energy saving opportunities. The data driving type building cold demand optimization solution has the characteristics of high flexibility and modular design. The solution is suitable for different building types, such as single or multi-zone buildings, commercial buildings or office buildings. The scheme is also suitable for buildings provided with different air-conditioning cooling systems, such as a full water system or an air-water system. The optimization scheme of the demand side (for example, the control end of the air conditioner cooling system of the building) can be matched with the corresponding optimization scheme of the cooling system (the air conditioner cooling system of the building) for use, so that the total energy usage amount of the building is further reduced.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
FIG. 1 is a flow chart of a method of determining a temperature setting for an air conditioning and cooling system within a building according to an embodiment of the present application;
FIG. 2 is a schematic diagram of an exemplary comfort zone temperature range;
FIG. 3 is a schematic diagram of a method of determining a target temperature value combination according to an exemplary embodiment of the present application;
FIG. 4 is a schematic diagram of another method of determining a combination of target temperature values according to an exemplary embodiment of the present application;
FIG. 5 is a schematic diagram of exemplary electricity rates;
FIG. 6 is a schematic diagram of an adjustment algorithm based on prediction error according to an exemplary embodiment of the present application;
FIG. 7 is a schematic diagram of an adjustment algorithm based on prediction error according to an exemplary embodiment of the present application;
FIG. 8 is a schematic illustration of a method of optimizing temperature settings according to an exemplary embodiment of the present application;
FIG. 9 is a flowchart of a method of determining a combination of a future 24-hour electricity fee and a minimum temperature value according to an exemplary embodiment of the present application;
FIG. 10 is a performance curve of a chiller according to an exemplary embodiment of the present application;
FIG. 11 is a diagram illustrating determination of an optimal temperature value combination according to an exemplary embodiment of the present application;
FIG. 12 is a diagram illustrating determination of an optimal temperature value combination according to an exemplary embodiment of the present application;
FIG. 13 is a schematic diagram of a comfort zone temperature range according to an embodiment of the present application;
FIG. 14 is a schematic diagram of a modified comfort zone temperature range according to an embodiment of the present application;
FIG. 15 is a schematic diagram of an apparatus for determining a temperature setting for an air conditioning and cooling system within a building in accordance with an embodiment of the present application;
FIG. 16 is a schematic view of an apparatus according to an exemplary embodiment of the present application;
FIG. 17 is a schematic diagram of a system for determining a temperature setting for an air conditioning and cooling system within a building in accordance with an embodiment of the present application;
FIG. 18 is a schematic diagram of a system according to an exemplary embodiment of the present application.
The reference numbers illustrate:
s102, S104 and S106: a step of;
s302, S304: a step of;
s402, S404 and S406: a step of;
s602, S604, S606: a step of;
s702, S704, S706: a step of;
s802, S804 and S806: a step of;
s902, S904, S906, S908, S910, S912, S914, S916, S918: a step of;
1: a device;
102: a comfort zone module;
104: a temperature value combination acquisition module;
106: a target temperature value combination determination module;
108: a corresponding relation adjusting module;
110: a target temperature value combination adjusting module;
112: adjusting an optimization module;
114: a target temperature value combination updating module;
3: an air conditioning cooling system;
302: a sensor;
304: a control feedback module;
5: provided is a system.
Detailed Description
In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only partial embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or modules or elements is not necessarily limited to those steps or modules or elements expressly listed, but may include other steps or modules or elements not expressly listed or inherent to such process, method, article, or apparatus.
According to an embodiment of the present application, a method of determining a temperature setting for an air conditioning and cooling system within a building is provided. FIG. 1 is a flow chart of a method of determining a temperature setting for an air conditioning and cooling system within a building according to an embodiment of the present application. As shown in fig. 1, a method of determining a temperature setting value of an air conditioning and cooling system in a building according to an embodiment of the present application includes the following steps.
Step S102, a step of obtaining a comfortable zone temperature range of each sub-time period in a plurality of sub-time periods in a future preset time period, wherein the comfortable zone temperature range is a temperature range enabling people in the building to feel comfortable in the corresponding sub-time period, and each comfortable zone temperature range is smaller than a temperature adjustment range of the air conditioning and cooling system.
The goal of introducing a comfort zone temperature range is to search the space hourly in order to set the optimum temperature, thereby providing an optimization algorithm. When the temperature value of the air-conditioning cooling system of the building is set within the temperature range of the comfortable area, people in the building feel comfortable. More specifically, the comfort zone temperature range provides upper and lower limits of the temperature set point per hour of the air conditioning cooling system, and in this application, the optimum temperature set point is found from within the comfort zone temperature range, so that the amount of electricity used for cooling is minimized or the required electricity rate is minimized while the person in the building feels comfortable. The computational cost of the optimization algorithm may also be minimized by considering the comfort zone temperature range (e.g., on-time versus off-time) which must be narrower than the full adjustable temperature range of the air conditioning cooling system, rather than the full adjustable temperature range of the air conditioning cooling system. In practice, the user may set the comfort zone temperature range according to the comfort zone temperature range set by the user, or according to other commonly used thermal comfort zone models (e.g., those conforming to the ASHRAE standard), such as a Predictive Mean Vote (PMV) index. Fig. 2 is a schematic diagram of an exemplary comfort zone temperature range. As can be seen from the exemplary comfort zone temperature range shown in fig. 2, the comfort zone temperature range (the range of values of temperature at which the indoor person feels comfortable) is wider in the non-operating time interval than in the operating time interval. In addition, the comfort zone temperature range should be dynamically updated according to the changing values of, for example, the outdoor ambient temperature, the room occupancy, and the room relative humidity to obtain accurate results. In a predetermined time period, such as the next 24 hours, as shown in fig. 2, the comfort zone temperature range is varied for each sub-time period, such as each hour, so that the temperature setting of the air conditioning cooling system can be selected from the comfort zone temperature range for each hour, rather than from the entire temperature setting range of the air conditioning cooling system, thereby reducing the amount of calculation of the selected temperature value.
In addition, the user can also customize the comfort zone temperature range per hour. Regardless of the method used, the comfort zone temperature range should be updated in real time (e.g., every sub-period of time or every hour) to ensure a reasonable and accurate calculation of the temperature setting of the air conditioning cooling system.
After obtaining the comfort zone temperature range of the future predetermined time period, step S104 is performed to obtain a plurality of first temperature value combinations, where each of the plurality of first temperature value combinations includes a plurality of temperature values, each of the plurality of temperature values corresponds to one of the plurality of sub-time periods, and each of the plurality of temperature values is in the comfort zone temperature range corresponding to the sub-time period. For example, in the next 24 hours, corresponding to the comfort zone temperature range for each hour, a temperature value is selected from the comfort zone temperature range, so that 24 temperature values are obtained to constitute a temperature value combination. Such a combination of temperature values represents the temperature setting of the air conditioning cooling system for each of the 24 hours in the future 24 hours. And acquiring a plurality of temperature value combinations as a selection range for selecting the temperature value of the air-conditioning cooling system in the next 24 hours. For example, a desired temperature value combination is selected from the plurality of such temperature value combinations.
Step S106 is performed, namely, a step of determining a target temperature value combination from the plurality of first temperature value combinations is performed, so that the temperature setting value of each of the plurality of sub-time periods is set according to the target temperature value combination, and the operating state of the air conditioning cooling system in a future predetermined time period is optimal.
The optimal determination mode of the operation state of the air conditioner cooling system in the future preset time period can be set according to requirements. The present exemplary embodiments consider the total heat output of a building, which includes heat generated by infrastructure, such as IT equipment and lighting, and power for air conditioning systems, such as chiller, chilled water pump, condenser water pump, secondary chilled water pump, PAU, AHU, and cooling towers. The data driven solution presented here allows flexibility in considering any configuration. The optimal operation state of the air conditioner cooling system is determined according to the following embodiments of the present application, for example.
FIG. 3 is a schematic diagram of a method of determining a combination of target temperature values according to an exemplary embodiment of the present application. As shown in fig. 3, the step of determining a target temperature value combination from a plurality of first temperature value combinations according to an exemplary embodiment of the present application includes: step S302, obtaining the temperature setting value-cooling amount corresponding relation between the temperature setting value of the air-conditioning cooling system and the cooling amount provided by the air-conditioning cooling system and the cooling amount-power consumption corresponding relation between the cooling amount provided by the air-conditioning cooling system and the power consumption required by the cooling amount provided by the air-conditioning cooling system, and step S304, using the first temperature value combination with the minimum sum of the power consumption corresponding to the plurality of temperature setting values as the target temperature value combination.
The temperature setting value-cooling amount correspondence is determined based on the temperature setting value of the air conditioning cooling system and the corresponding cooling amount. The corresponding relation between the cooling capacity and the electricity consumption is determined based on the performance curve of the air-conditioning cooling system. According to the technical solution of the exemplary embodiment of the present application, it is an object to calculate a combination of temperature values at which the amount of electricity used by the air-conditioning cooling system is the least in the next predetermined period of time, for example, in the next 24 hours. And setting the temperature of the air-conditioning cooling system in each sub-time period in the preset time period according to a plurality of temperature values included in the temperature value combination, wherein the power consumption in the preset time period is minimum, so that the running state of the air-conditioning cooling system is optimal.
FIG. 4 is a schematic diagram of another method of determining a combination of target temperature values according to an exemplary embodiment of the present application. As shown in fig. 4, according to an exemplary embodiment of the present application, the step of determining a target temperature value combination from a plurality of first temperature value combinations comprises: step S402, acquiring a temperature setting value-cooling amount corresponding relation between a temperature setting value of an air conditioner cooling system and cooling amount provided by the air conditioner cooling system, a cooling amount-power consumption corresponding relation between the cooling amount provided by the air conditioner cooling system and power consumption required by the air conditioner cooling system for providing the cooling amount, and rates of each sub-time period associated with the air conditioner cooling system; step S404, determining the electric charge corresponding to the temperature setting value of each sub-time period according to the temperature setting value-cooling amount corresponding relation, the cooling amount-electricity consumption corresponding relation and the charge rate; and step S406, using the first temperature value combination with the minimum sum of the electric charges corresponding to the plurality of included temperature setting values as the target temperature value combination.
The temperature setting value-cooling amount correspondence is determined based on the temperature setting value of the air conditioning cooling system and the corresponding cooling amount. The corresponding relation between the cooling capacity and the electricity consumption is determined based on the performance curve of the air-conditioning cooling system. The rates are building-related and the rates are different at different times, so that the electricity rates corresponding to the electricity consumption consumed by the building are varied according to the rates at different time periods. According to a solution of another exemplary embodiment of the present application, the objective is to calculate a combination of temperature values for which the electricity costs for the cooling needs are minimal during the next predetermined period of time, for example the next 24 hours.
Typically, the rate of electricity charges for a city is fluctuating, time-shared (e.g., peak-to-valley electricity rates). Therefore, a reasonable time-sharing or component electric charge pricing model is constructed in consideration of the electric charge metering mode applied to the city or the region. The rate of electricity charges of any kind of power consumers may also vary depending on the time-of-use (TOU) because the rate of electricity charges is set to be high during peak periods of power use and to be low when power demand is low. Fig. 5 is a schematic diagram of an exemplary electricity rate. As shown in fig. 5, the rate is higher during peak periods of electricity usage, such as working periods, while the demand for electricity is small and the rate for electricity charges is lower during the latter periods. According to the corresponding relation between the rate and the time and the power consumption of the air-conditioning cooling system in each sub-period, such as each hour, the power rate of the air-conditioning cooling system in each hour can be determined, and further the power rate in a preset period, such as 24 hours in the future, can be determined. And setting the temperature of the air-conditioning cooling system in each sub-time period in the preset time period according to a plurality of temperature values included in the temperature value combination, wherein the electricity fee in the preset time period is minimum, so that the running state of the air-conditioning cooling system is optimal.
In the method according to the exemplary embodiment of the present application, the cooling amount and the power consumption amount associated with the air conditioning cooling system are determined according to the temperature setting value-cooling amount corresponding relationship and the cooling amount-power consumption amount corresponding relationship, and there may be an error with the actual cooling amount and power consumption amount of the air conditioning cooling system. In order to determine the error and to optimize the method according to the embodiments of the present application in terms of the error, the following technical solutions may be adopted.
Fig. 6 and 7 are schematic diagrams of an adjustment algorithm according to a prediction error according to an exemplary embodiment of the present application.
As shown in fig. 6, the method according to an exemplary embodiment of the present application further includes: step S602, acquiring historical data, wherein the historical data comprises an actual temperature setting value and an actual cooling capacity of each sub-time period in a historical time period of the air conditioner cooling system; step S604, obtaining prediction data, wherein the prediction data comprises predicted cooling capacity according to the corresponding relation between the temperature setting value and the cooling capacity; step S606, establishing a loss function according to the historical data and the prediction data, and determining a prediction error between the predicted cooling capacity and the actual cooling capacity; and adjusting the corresponding relation between the temperature setting value and the cooling capacity according to the prediction error.
As shown in fig. 7, the method according to an exemplary embodiment of the present application further includes: step S702, acquiring historical data, wherein the historical data comprises the actual cooling amount and the actual power consumption of each sub-time period in a historical time period of the air conditioner cooling system; step S704, obtaining prediction data, wherein the prediction data comprises predicted electricity consumption according to the corresponding relation between cooling capacity and electricity consumption; step S706, establishing a loss function according to the historical data and the predicted data, and determining a prediction error between the predicted power consumption and the actual power consumption; and adjusting the corresponding relation between the cooling capacity and the power consumption according to the prediction error.
According to the method of the exemplary embodiment of the present application, the method of calculating the combination of the optimal temperature settings for a predetermined period of time in the future, for example 24 hours in the future, is based on a dynamically updated optimization algorithm, and the error can be automatically corrected to improve the accuracy of the prediction of the temperature settings per hour. And, the optimization algorithm is time-constrained, that is, the optimal temperature value combination of the air conditioner cooling system is found in the given calculation time, so as to minimize the total electricity consumption or electricity charge of the future target building.
FIG. 8 is a schematic diagram of a method of optimizing temperature settings according to an exemplary embodiment of the present application. As shown in fig. 8, the method according to the exemplary embodiment of the present application further includes step S802, obtaining a time length for adjusting the target temperature value combination, and determining the adjusted target temperature value combination within the time length, where determining the adjusted target temperature value combination within the time length includes: step S804, after the step of obtaining the plurality of first temperature value combinations, for at least one first temperature value combination in the first temperature value combinations, for each sub-time period in a part or all of the sub-time periods, adjusting the temperature value of the sub-time period based on a preset step size to obtain at least one second temperature value combination, wherein the temperature value of each sub-time period in the at least one second temperature value combination is within the comfort zone temperature range corresponding to the sub-time period; and step S806, after the step of determining a target temperature value combination from the plurality of first temperature value combinations, determining an adjusted target temperature value combination from the first temperature value combination and the second temperature value combination, so that the temperature setting value of each of the plurality of sub-time periods is set according to the adjusted target temperature value combination, and the operation state of the air-conditioning cooling system in a future predetermined time period is optimal.
For example, at each of the 24 hours in the future, a time period is obtained in which the combination of target temperature values is determined for each hour. And after obtaining the first plurality of first temperature value combinations, at least one second temperature value combination is obtained, wherein the second temperature value combination is obtained on the basis of the first temperature value combinations. For example, the first temperature value combination includes 24 temperature values corresponding to 24 hours in the future, and for the 24 temperature values, at least one of the temperature values may be adjusted, for example, the at least one temperature value is added to the preset step size, so as to obtain a new second temperature value combination. It should be understood that one of the 24 temperature values may be added to the preset step size to obtain a new second temperature value combination, multiple of the 24 temperature values may be added to the preset step size, or all 24 temperature values may be added to the preset step size. In practical application, the preset step length may be an integral multiple of the temperature adjustment step length of the air conditioning cooling system. For example, the air conditioner may adjust the step size by using 0.1 degree celsius as the temperature, and the preset step size may be ± 0.1 degree celsius, ± 0.2 degree celsius, or ± N degree celsius, etc. Assuming that the temperature value of one hour added with the preset step length is 20 degrees and the preset step length is 1 degree centigrade among the plurality of temperature values included in the first temperature value combination, the temperature value corresponding to the hour is 21 degrees centigrade among the plurality of temperature values included in the second temperature value combination. And if the preset step length is-1 ℃, the temperature value corresponding to the hour is 19 ℃ in the plurality of temperature values included in the second temperature value combination. If the preset step length is 2 ℃, the temperature value corresponding to the hour is 22 ℃ in the plurality of temperature values included in the second temperature value combination. The 24 temperature values of the second combination of temperature values are also within the corresponding comfort zone temperature range per hour. And after at least one second temperature value combination is obtained, determining a temperature value combination which enables the air conditioner cooling system to have the best operation state in a future preset time period from the first temperature value combination and the second temperature value combination. In this way, the calculation result is further optimized for each hour of the acquired duration.
According to the embodiment of the application, a Particle Swarm Optimization (PSO) in a heuristic algorithm is used for completing the optimization process of the calculation result. Because the PSO algorithm can simultaneously calculate a plurality of potential optimal temperature value combinations, the convergence rate is higher and the calculation time is shorter compared with other traditional heuristic algorithms. Each particle in the PSO algorithm represents one possible optimal combination of temperature values for the next 24 hours, and the fitness of these possible combinations is evaluated by an objective function (total electricity usage for 24 hours, total electricity charge). Each particle should be located in a preset search space, i.e. within the comfort zone temperature range per hour. The PSO algorithm generates new particles by updating the flight speed (i.e., search step size such as 0.1 or 1 degree celsius) and position (i.e., different 24 hour combination of potentially optimal temperature values) of each particle, updating the local and global optimal solutions based on the objective function. The algorithm stops and outputs the result of the optimum temperature value combination in two cases: 1, the fitness is not increased (namely the total electricity consumption and the total electricity charge are not reduced or reduced); and 2, calculating time by the optimization algorithm, namely, the time consumed by the optimization algorithm exceeds a preset value.
The manner in which the results of the temperature value combinations are optimized in the calculation time of the optimization algorithm can also be based on the cooling capacity, the electricity usage or the rate, as is the case with the determination of the target temperature value combination from the first temperature value combination.
For example, according to an exemplary embodiment of the present application, the step of determining an adjusted target temperature value combination from the first temperature value combination and the second temperature value combination comprises: acquiring a temperature setting value-cooling amount corresponding relation between a temperature setting value of an air conditioner cooling system and cooling amount provided by the air conditioner cooling system, a cooling amount-power consumption corresponding relation between the cooling amount provided by the air conditioner cooling system and power consumption required by the air conditioner cooling system for providing the cooling amount, and rates of all sub-time periods associated with the air conditioner cooling system; determining the electric charge corresponding to the temperature setting value of each sub-time period according to the temperature setting value-cooling amount corresponding relation, the cooling amount-electricity consumption corresponding relation and the rate; and using the first temperature value combination or the second temperature value combination with the minimum sum of the electric charges corresponding to the plurality of temperature setting values as a target temperature value combination.
For example, according to an exemplary embodiment of the present application, the step of determining one adjusted target temperature value combination from the first temperature value combination and the second temperature value combination comprises: acquiring a temperature setting value-cooling amount corresponding relation between a temperature setting value of an air conditioner cooling system and the cooling amount provided by the air conditioner cooling system and a cooling amount-power consumption corresponding relation between the cooling amount provided by the air conditioner cooling system and the power consumption required by the cooling amount provided by the air conditioner cooling system; and taking the first temperature value combination or the second temperature value combination with the minimum sum of the power consumption corresponding to the plurality of temperature setting values as the target temperature value combination.
The prediction error can also be applied to make the optimization algorithm accurate, for the way the result of the combination of temperature values is optimized in the calculation time of the optimization algorithm. The method according to an exemplary embodiment of the present application further includes: acquiring historical data, wherein the historical data comprises an actual temperature setting value and an actual cooling capacity of each sub-time period in a historical time period of the air-conditioning cooling system; acquiring prediction data, wherein the prediction data comprises predicted cooling capacity according to the temperature setting value-cooling capacity corresponding relation; establishing a loss function according to the historical data and the prediction data, and determining a prediction error between the predicted cooling capacity and the actual cooling capacity; adjusting the corresponding relation between the temperature setting value and the cooling capacity according to the prediction error; and/or acquiring historical data, wherein the historical data comprises the actual cooling amount and the actual power consumption of the air conditioner cooling system in each sub-time period included in a historical time period; acquiring prediction data, wherein the prediction data comprises power consumption predicted according to the corresponding relation between the cooling capacity and the power consumption; establishing a loss function according to the historical data and the predicted data, and determining a prediction error between the predicted power consumption and the actual power consumption; and adjusting the corresponding relation between the cooling capacity and the power consumption according to the prediction error.
The method according to an exemplary embodiment of the present application further includes: acquiring prediction errors of a plurality of historical time periods; if the prediction error increases over time in the plurality of historical time periods, performing at least one of the following in the step of adjusting the combination of target temperature values for a length of time over which the combination of target temperature values is adjusted: extending the length of the time length, decreasing the preset step size, and increasing the number of times of adjusting the temperature value of the sub-time period based on the preset step size to obtain at least one second temperature value combination.
In the method, a loss function (for example, a function of a mean square error) is set, and a prediction error of each variable (power consumption, cooling capacity, electricity charge, and the like) is calculated for each hour based on a historical time period, for example, actual data of each elapsed hour and prediction data of the time period, so that the accuracy of a current prediction model is reflected. And calculating a loss function value of each hour in history, and if the function value tends to converge (namely, the value is increased along with the increase of time and is smaller and smaller), proving that the performance of the current optimization algorithm is better and stable, and the method is suitable for predicting the temperature setting value of the air conditioner cooling system in the current scene. On the contrary, if the function value tends to diverge (i.e., the value increases more and more with time), it proves that the performance of the optimization function is poor and unstable, and the optimization function is not suitable for the current scenario. At this point, the parameters of the optimization algorithm will be adjusted, for example:
1. and increasing the running time of the optimization algorithm. The optimization algorithm is time-limited, for example, in fifteen minutes every hour, the operation needs to be forcibly stopped, and the optimal temperature value combination found in 15 minutes is output. In this case, it may be advisable to extend the algorithm run time, for example to 20 minutes, so that the algorithm has more time to find a better combination of temperature values. And if the later optimization algorithm is stable, the operation time can be gradually reduced.
2. The iteration times of the optimization algorithm are increased, namely the optimization running time of the algorithm is indirectly increased. The second temperature value combination is determined a plurality of times and the optimum temperature value combination is determined a plurality of times by a plurality of iterations of the optimization algorithm.
3. If the optimization algorithm adopts the PS0 algorithm, the inertia factor and the learning factor are adjusted.
The method according to an exemplary embodiment of the present application, further comprising, at each new sub-period: executing the steps of obtaining a comfort zone temperature range of each sub-time period in a plurality of sub-time periods included in a future preset time period, obtaining a plurality of first temperature value combinations and determining a target temperature value combination from the plurality of first temperature value combinations; and taking the temperature values of the plurality of sub-time periods in the determined target temperature value combination as the temperature values of the corresponding plurality of sub-time periods in one temperature value combination in the plurality of first temperature value combinations to be acquired in the next future preset time period. That is, the method of determining the optimum temperature value combination is repeatedly performed every new sub-period of time, for example every hour, so that the optimum temperature value combination is updated every hour.
The method according to an exemplary embodiment of the present application, further comprising, at each new sub-period: executing the steps of obtaining a comfort zone temperature range of each sub-time period in a plurality of sub-time periods included in a future preset time period, obtaining a plurality of first temperature value combinations and determining a target temperature value combination from the plurality of first temperature value combinations; executing the steps of obtaining a time length for adjusting the target temperature value combination, and determining the adjusted target temperature value combination in the time length; and taking the temperature values of the plurality of sub-time periods in the determined adjusted target temperature value combination as the temperature values of the corresponding plurality of sub-time periods in one temperature value combination in the plurality of first temperature value combinations to be acquired in the next future preset time period. That is, the method of optimizing the optimum temperature value combination is repeatedly performed during the runtime of the optimization algorithm at every new sub-period of time, for example every hour, so that the optimized optimum temperature value combination (adjusted target temperature value combination) is updated every hour.
According to the method of an exemplary embodiment of the present application, the step of determining the adjusted combination of target temperature values over the duration of time is repeated periodically over the duration of time; and the length of each sub-time period is equal, and the duration of the target temperature value combination is adjusted to be smaller than the length of the sub-time period. The result of optimizing the combination of optimum temperature values is repeated, for example every hour, within for example 15 minutes of the optimization algorithm. The time of the optimization algorithm does not exceed one hour, and the time of the optimization algorithm does not exceed one hour after adjustment, and enough setting time for the air conditioner cooling system is guaranteed.
The method of determining a combination of a future 24-hour electricity rate and a minimum temperature value according to an exemplary embodiment of the present application is further described below.
First, an initial comfort zone temperature range C is set for each hour (i.e., each sub-period) of the next 24 hoursi(using a classical comfort zone model, such as a PMV model, or a user-defined comfort zone temperature range), the comfort zone temperature range should be updated in real-time (hourly) to ensure a reasonable and accurate calculation of the optimal temperature value combination. Based on the comfort zone temperature range, an hourly initial temperature value for the next 24 hours is set as an initial temperature value combination, and a plurality of such initial temperature value combinations are set as inputs to the following steps.
The algorithm of the proposed solution of the exemplary embodiment of the present application aims to determine a combination of a future 24-hour electricity rate and a minimum temperature value. The next several steps are aimed at constructing a mapping function (i.e., an objective function) from the temperature set by the air conditioning cooling system to the amount of electricity used. A mapping relation D between the temperature set by the air-conditioning cooling system and the cooling capacity is firstly constructed (a model of temperature set value-cooling capacity), and the method is to utilize historical data of the temperature corresponding to the cooling capacity in a database related to the air-conditioning cooling system to construct a model of temperature set value-cooling capacity, such as a linear/nonlinear regression model or other machine learning regression models. Setting the temperature T at the ith houriThe amount of cooling d in the houriThe associated mapping is as follows:
d＝D(T)。
then, a mapping E of the cooling capacity to the electricity consumption amount is constructed (a "cooling capacity-electricity consumption amount" model). The generation of cooling capacity comes from the air-conditioning and cooling system of the target building, so the total power consumption and the cooling capacity of the air-conditioning and cooling system have corresponding mapping relation. When the mapping relation is constructed, the performance curve of each cooler of the air-conditioning cooling system of the building represents the relation between the performance (COP) of the cooler and the cooling capacity, and the performance curve is closely related to the model, parameter design and the like of the cooler. The data can be obtained from a factory design specification of the refrigerator, and historical data can be collected to predict a relation curve of COP and cooling capacity. After the performance curve is obtained, a relation function of cold machine performance COP and cold supply capacity is constructed by using an image identification point-taking method:
cop＝F(d)。
different models of chillers have different performance curves. Fig. 10 is a performance curve of a chiller according to an exemplary embodiment of the present application. As shown in fig. 10, the performance of the chiller varies with the amount of cooling supplied. Reuse formula: and the power consumption E is the cooling capacity/COP, and the relation between the cooling capacity and the power consumption is obtained:
e ═ cooling capacity/cop ═ d/f (d).
Next, a "temperature setting value-cooling amount" model, a "cooling amount-power consumption" model, and a peak-valley power rate model P (for example, a peak-valley power rate as shown in fig. 5) representing rate fluctuation are combined: electric charge p ═ p (e). Based on the rate (the "electricity usage E-electricity rate P" model), a final objective function (representing the future 24-hour electricity rate sum) is constructed.
And combining three mapping function models from the temperature setting value to the cooling amount, from the cooling amount to the power consumption and from the power consumption to the electric charge (through rate calculation) to obtain the mapping relation from the temperature setting value to the electric charge. An object of the exemplary embodiments of the present application is to consider that the electricity charge accumulated value (sum) per hour is minimum for 24 hours in the future, and thus the following formula is adopted:
Figure PCTCN2019088598-APPB-000001
left part of the formula
Figure PCTCN2019088598-APPB-000002
Refers to the optimal solution output by the optimization algorithm: the optimal temperature value combination of the temperature setting values (optimized temperature setting) of 24 hours per hour in the future, the right side is an objective function, argmin is the minimum value, Σ x is the summation, i ═ current time +1, which means that the summation algorithm starts from the next hour, current time +25 means the summation to the 24 th hour calculated from the current hour, and the last P () is the mapping relation from the temperature setting value to the electricity charge of the "temperature setting value-cooling capacity" model, the "cooling capacity-electricity consumption" model and the rate, and is the optimization algorithm for finding the optimal temperature setting value of 24 hours per hour in the future.
The method for determining the combination of the electricity fee and the minimum temperature value for the 24 hours in the future according to the embodiment of the present application is further described below with reference to the accompanying drawings. Fig. 9 is a flowchart of a method of determining a combination of a future 24-hour electricity rate and a minimum temperature value according to an exemplary embodiment of the present application. As shown in fig. 9, the optimization algorithm for finding the optimal temperature setting for the next 24 hours per hour is time constrained, thereby ensuring that the search calculation of the optimal temperature setting is completed within the user-specified time period, and also allowing time for the system deployment to be completed.
To achieve the above objective, a heuristic algorithm may be used to complete the calculation of the optimal temperature value combination, and it should be understood that the modular design is flexible and that other optimization algorithms may be deployed by the user. The search space for the objective function of the optimization algorithm is large, with over billions of possible combinations available to try to find the optimum temperature setting. However, the run time of the optimization algorithm should be limited to ensure that there is sufficient time to change the temperature settings of the air conditioning cooling system in view of updating the optimum temperature value combination every hour. In other words, the calculation time of the optimization algorithm should be shorter than one hour.
As shown in fig. 9, previously determined models, such as a "temperature setting value-cooling capacity" model, a "cooling capacity-power consumption" model, and a peak-to-valley electricity rate model representing rate fluctuation, are input at step S902, and an objective function is determined as described above at step S904. Parameters of the optimization algorithm (e.g., run time of the optimization algorithm, number of iterations of the optimization algorithm, etc.) are input at step S906 and the optimization algorithm is executed at step S908 (as previously described). It is determined whether the optimization algorithm is overtime in step S901, if the algorithm is not overtime, the step S908 is continued to execute the optimization algorithm, and if the algorithm is overtime, the predicted optimal temperature value combination, which is used for setting the temperature value of the air conditioner cooling system for the 24 hours in the future, the cooling amount, the power consumption amount and the electricity fee are output in step S912. In step S914, the number of hours of the algorithm is increased by 1, so that the optimization of the optimum temperature value combination for the next hour is performed. The historical data of the amount of used cooling power and the electricity rate is acquired at step S916, and then at step S918, the parameters of the optimization algorithm, such as adjusting the operation time of the optimization algorithm, adjusting the number of iterations of the optimization algorithm, adjusting the inertia factor of the PSO algorithm, the magnitude of the learning factor, etc., are updated based on the loss functions of the historical data and the predicted data, and the updated parameters are used as the parameters of the optimization algorithm of step S906, so as to be used for the optimization algorithm of the next hour (the current hour for the historical period of time). By providing a reasonable initial value of the optimization algorithm, the calculation efficiency of the optimization algorithm is improved.
The following should be noted in the optimization procedure given in fig. 9:
1. if the preset time of the optimization algorithm is not reached, the optimization algorithm is updated circularly, and the optimal temperature value combination is found out iteratively according to different algorithm characteristics.
2. When the calculation time reaches the time upper limit of the optimization algorithm, the optimization algorithm stops and outputs the optimal result of the current calculated temperature value combination.
3. After each calculation, the optimization algorithm updates the temperature value combination used for searching in the current hour according to the loss function between the predicted value and the actual value (historical data) of the model in the previous hours, so as to improve the calculation efficiency of the optimization algorithm.
The objective function of the PSO algorithm is to minimize the total electricity charge in the next 24 hours. Each particle in the algorithm represents a solution to one possible combination of temperature values for the next 24 hours, to be evaluated by an objective function to determine its fitness with the optimal combination of temperature values. In addition, each particle is located within a search space, which in the exemplary embodiment of the present application is a comfort zone temperature range per hour. In the next step, the PSO algorithm updates the velocity and position of each particle. The formula for updating the velocity of each particle is as follows:
Figure PCTCN2019088598-APPB-000003
there are three parameters that need to be updated for speed:
1、wv i(t): called the inertial component, which keeps the particle in its original direction of motion. The parameter w determines the convergence speed, with higher values of w encouraging exploration of the search space.
2、
Figure PCTCN2019088598-APPB-000004
Called cognitive components, serve as a memory for the particles, returning them to the respective best regions of the search space. Parameter c1Limiting the size of the step size of the particles traveling towards the individual optimum value, and r1Is a unit random value that is regenerated every time a speed update occurs.
3、c 2r 2[g(t)-x i(t)]: called social component, moves the particles to the best region found by the cluster of particles so far. Parameter c2The size of the step size for the particle to travel towards the global optimum is limited, while r2Is a unit random value that is regenerated every time a speed update occurs.
The position of each particle is then updated using the following formula:
x i(t+1)＝x i(t)+v i(t+1)。
after the above procedure, new particles are generated and the individual and global optimal solutions will be updated according to the objective function. This iterative optimization will terminate when the quality of the new particle converges, i.e. the maximum adaptation value (electricity charge and min) among the current particles no longer increases, or when the calculation time expires. In both cases, the particle with the largest adaptation value represents the optimum temperature value combination for the next 24 hours. Fig. 11 and 12 show determination results of an optimum temperature value combination according to an exemplary embodiment of the present application.
According to the method of the exemplary embodiment of the present application, acquiring the comfort zone temperature range includes: acquiring one or more pieces of information of outdoor temperature, humidity and people flow rate associated with a building; the comfort zone temperature range for each of a plurality of sub-periods included in the future predetermined period is determined based on the one or more information.
Further, according to another embodiment of the present application, the user can adjust the model parameter values to explore energy saving opportunities. For example, the user may manually adjust the calculation parameters (based on the PMV model) of the comfort zone temperature range to change the search space of the algorithm to obtain different results.
Fig. 13 is a schematic view of a comfort zone temperature range according to an embodiment of the present application. Fig. 14 is a schematic view of a modified comfort zone temperature range according to an embodiment of the present application.
In comparison with fig. 13, in fig. 14, the parameter values (wind speed, relative humidity, and ambient temperature) at the lower portion of the graph change, and the optimum temperature setting curve (optimum temperature value combination) calculated based on the change in the comfort zone temperature range calculated based on the change changes.
According to another embodiment of the present application, an apparatus for determining a temperature setting for an air conditioning and cooling system within a building is also provided. Fig. 15 is a schematic diagram of an apparatus for determining a temperature setting value of an air conditioning and cooling system in a building according to an embodiment of the present application. As shown in fig. 15, the apparatus 1 for determining a temperature setting value of an air conditioning and cooling system in a building according to an embodiment of the present application includes: a comfort zone module 102 configured to perform a step of obtaining a comfort zone temperature range of each sub-time period of a plurality of sub-time periods included in a future predetermined time period, wherein the comfort zone temperature range is a temperature range enabling persons in a building to feel comfortable in the corresponding sub-time period, and each comfort zone temperature range is smaller than a temperature adjustment range of an air conditioning and cooling system; a temperature value combination obtaining module 104 configured to perform a step of obtaining a plurality of first temperature value combinations, wherein each first temperature value combination comprises a plurality of temperature values, each temperature value of the plurality of temperature values corresponds to one sub-period of the plurality of sub-periods, and each temperature value is in a comfort zone temperature range corresponding to the sub-period; and a target temperature value combination determining module 106 configured to execute the step of determining one target temperature value combination from the plurality of first temperature value combinations, so that the temperature setting value of each of the plurality of sub-time periods is set according to the target temperature value combination, and the operating state of the air conditioner cooling system in a future predetermined time period is optimal.
According to an exemplary embodiment of the present application, the step of determining a target temperature value combination from a plurality of first temperature value combinations performed by the target temperature value combination determination module 106 comprises: acquiring a temperature setting value-cooling amount corresponding relation between a temperature setting value of an air conditioner cooling system and the cooling amount provided by the air conditioner cooling system and a cooling amount-power consumption corresponding relation between the cooling amount provided by the air conditioner cooling system and the power consumption required by the cooling amount provided by the air conditioner cooling system; and taking the first temperature value combination with the minimum sum of the power consumption corresponding to the plurality of included temperature setting values as a target temperature value combination.
According to another exemplary embodiment of the present application, the target temperature value combination determination module 106 performs the step of determining one target temperature value combination from the plurality of first temperature value combinations, including: acquiring a temperature setting value-cooling amount corresponding relation between a temperature setting value of an air conditioner cooling system and cooling amount provided by the air conditioner cooling system, a cooling amount-power consumption corresponding relation between the cooling amount provided by the air conditioner cooling system and power consumption required by the air conditioner cooling system for providing the cooling amount, and rates of all sub-time periods associated with the air conditioner cooling system; determining the electric charge corresponding to the temperature setting value of each sub-time period according to the temperature setting value-cooling amount corresponding relation, the cooling amount-electricity consumption corresponding relation and the rate; and using the first temperature value combination with the minimum sum of the electric charges corresponding to the plurality of included temperature setting values as a target temperature value combination.
Fig. 16 is a schematic diagram of an apparatus according to an exemplary embodiment of the present application. As shown in fig. 16, the apparatus 1 according to the exemplary embodiment of the present application further includes a correspondence adjusting module 108 configured to: acquiring historical data, wherein the historical data comprises an actual temperature setting value and an actual cooling capacity of each sub-time period in a historical time period of the air-conditioning cooling system; acquiring prediction data, wherein the prediction data comprises predicted cooling capacity according to the temperature setting value-cooling capacity corresponding relation; establishing a loss function according to the historical data and the prediction data, and determining a prediction error between the predicted cooling capacity and the actual cooling capacity; adjusting the corresponding relation between the temperature setting value and the cooling capacity according to the prediction error; and/or acquiring historical data, wherein the historical data comprises the actual cooling amount and the actual power consumption of the air conditioner cooling system in each sub-time period included in a historical time period; acquiring prediction data, wherein the prediction data comprises power consumption predicted according to the corresponding relation between the cooling capacity and the power consumption; establishing a loss function according to the historical data and the predicted data, and determining a prediction error between the predicted power consumption and the actual power consumption; and adjusting the corresponding relation between the cooling capacity and the power consumption according to the prediction error.
The apparatus 1 according to an exemplary embodiment of the present application further includes a target temperature value combination adjustment module 110 configured to obtain a time duration for adjusting the target temperature value combination, and determine an adjusted target temperature value combination within the time duration, the determining the adjusted target temperature value combination within the time duration including: after the step of obtaining a plurality of first temperature value combinations, for at least one first temperature value combination in the first temperature value combinations, for each sub-time period in a part or all of the sub-time periods, adjusting the temperature value of the sub-time period based on a preset step length to obtain at least one second temperature value combination, wherein the temperature value of each sub-time period in the at least one second temperature value combination is in a comfort zone temperature range corresponding to the sub-time period; and after the step of determining a target temperature value combination from the plurality of first temperature value combinations, determining an adjusted target temperature value combination from the first temperature value combination and the second temperature value combination, so that the temperature setting value of each of the plurality of sub-time periods is set according to the adjusted target temperature value combination, and the running state of the air-conditioning cooling system in a future preset time period is optimal.
According to an exemplary embodiment of the present application, the step of the target temperature value combination adjustment module 110 performing the step of determining an adjusted target temperature value combination from the first temperature value combination and the second temperature value combination includes: acquiring a temperature setting value-cooling amount corresponding relation between a temperature setting value of an air conditioner cooling system and cooling amount provided by the air conditioner cooling system, a cooling amount-power consumption corresponding relation between the cooling amount provided by the air conditioner cooling system and power consumption required by the air conditioner cooling system for providing the cooling amount, and rates of all sub-time periods associated with the air conditioner cooling system; determining the electric charge corresponding to the temperature setting value of each sub-time period according to the temperature setting value-cooling amount corresponding relation, the cooling amount-electricity consumption corresponding relation and the rate; and using the first temperature value combination or the second temperature value combination with the minimum sum of the electric charges corresponding to the plurality of temperature setting values as a target temperature value combination.
According to another exemplary embodiment of the present application, the step of the target temperature value combination adjustment module 110 performing the determination of an adjusted target temperature value combination from the first temperature value combination and the second temperature value combination comprises: acquiring a temperature setting value-cooling amount corresponding relation between a temperature setting value of an air conditioner cooling system and the cooling amount provided by the air conditioner cooling system and a cooling amount-power consumption corresponding relation between the cooling amount provided by the air conditioner cooling system and the power consumption required by the cooling amount provided by the air conditioner cooling system; and taking the first temperature value combination or the second temperature value combination with the minimum sum of the power consumption corresponding to the plurality of temperature setting values as the target temperature value combination.
The apparatus 1 according to an exemplary embodiment of the present application further comprises an adjustment optimization module 112 configured to: acquiring prediction errors of a plurality of historical time periods; if the prediction error increases over time in the plurality of historical time periods, performing at least one of the following in the step of adjusting the combination of target temperature values for a length of time over which the combination of target temperature values is adjusted: extending the length of the time length, decreasing the preset step size, and increasing the number of times of adjusting the temperature value of the sub-time period based on the preset step size to obtain at least one second temperature value combination.
The apparatus 1 according to the exemplary embodiment of the present application further comprises a target temperature value combination update module 114 configured to, at each new sub-period: executing the steps of obtaining a comfort zone temperature range of each sub-time period in a plurality of sub-time periods included in a future preset time period, obtaining a plurality of first temperature value combinations and determining a target temperature value combination from the plurality of first temperature value combinations; and taking the temperature values of the plurality of sub-time periods in the determined target temperature value combination as the temperature values of the corresponding plurality of sub-time periods in one temperature value combination in the plurality of first temperature value combinations to be acquired in the next future preset time period.
According to the apparatus 1 of another exemplary embodiment of the present application, the target temperature value combination update module 114 is further configured to, at each new sub-period: executing the steps of obtaining a comfort zone temperature range of each sub-time period in a plurality of sub-time periods included in a future preset time period, obtaining a plurality of first temperature value combinations and determining a target temperature value combination from the plurality of first temperature value combinations; executing the steps of obtaining a time length for adjusting the target temperature value combination, and determining the adjusted target temperature value combination in the time length; and taking the temperature values of the plurality of sub-time periods in the determined adjusted target temperature value combination as the temperature values of the corresponding plurality of sub-time periods in one temperature value combination in the plurality of first temperature value combinations to be acquired in the next future preset time period.
According to an exemplary embodiment of the application, the step of determining the adjusted combination of target temperature values over the time period is repeated periodically over the time period; and the length of each sub-time period is equal, and the duration of the target temperature value combination is adjusted to be smaller than the length of the sub-time period.
According to an exemplary embodiment of the present application, the comfort zone module acquiring the comfort zone temperature range includes: acquiring one or more pieces of information of outdoor temperature, humidity and people flow rate associated with a building; the comfort zone temperature range for each of a plurality of sub-periods included in the future predetermined period is determined based on the one or more information.
In accordance with another embodiment of the present application, a system for determining a temperature setting for an air conditioning and cooling system within a building is provided. FIG. 17 is a schematic diagram of a system for determining a temperature setting for an air conditioning and cooling system within a building in accordance with an embodiment of the present application.
As shown in fig. 17, the system 5 includes: an air conditioning and cooling system 3; and an apparatus 1 for determining a temperature setting for an air conditioning and cooling system within a building, the apparatus 1 comprising: a comfort zone module 102 configured to perform a step of obtaining a comfort zone temperature range of each sub-time period of a plurality of sub-time periods included in a future predetermined time period, wherein the comfort zone temperature range is a temperature range enabling persons in a building to feel comfortable in the corresponding sub-time period, and each comfort zone temperature range is smaller than a temperature adjustment range of an air conditioning and cooling system; a temperature value combination obtaining module 104 configured to perform a step of obtaining a plurality of first temperature value combinations, wherein each first temperature value combination comprises a plurality of temperature values, each temperature value of the plurality of temperature values corresponds to one sub-period of the plurality of sub-periods, and each temperature value is in a comfort zone temperature range corresponding to the sub-period; and a target temperature value combination determining module 106 configured to execute the step of determining one target temperature value combination from the plurality of first temperature value combinations, so that the temperature setting value of each of the plurality of sub-time periods is set according to the target temperature value combination, and the operating state of the air conditioner cooling system in a future predetermined time period is optimal.
The system 5 shown in fig. 17 comprises two main parts: an air conditioning and cooling system 3 (e.g. HVAC) on the cooling side and a data driven device 1 for determining the temperature setting of the air conditioning and cooling system. The whole system is flexible in design, modular and applicable to different air-conditioning cooling systems, for example, the facility for providing cooling capacity on the cooling side can be freely added or removed from the air-conditioning cooling system 3, and the facility is equipped with the relevant sensor 302 for collecting data. Furthermore, any supplier-related control strategy may be applied, such as chiller control and optimization of operating parameters. The air conditioning and cooling system 3 further comprises a control feedback module 304 for feeding back data collected from the air conditioning and cooling system 3 to the device 1, such as historical data, and performing data interaction with the device 1.
According to an exemplary embodiment of the present application, the step of determining a target temperature value combination from a plurality of first temperature value combinations performed by the target temperature value combination determination module 106 of the apparatus 1 comprises: acquiring a temperature setting value-cooling amount corresponding relation between a temperature setting value of an air conditioner cooling system and the cooling amount provided by the air conditioner cooling system and a cooling amount-power consumption corresponding relation between the cooling amount provided by the air conditioner cooling system and the power consumption required by the cooling amount provided by the air conditioner cooling system; and taking the first temperature value combination with the minimum sum of the power consumption corresponding to the plurality of included temperature setting values as a target temperature value combination.
According to another exemplary embodiment of the present application, the step of determining a target temperature value combination from a plurality of first temperature value combinations performed by the target temperature value combination determination module 106 of the apparatus 1 comprises: acquiring a temperature setting value-cooling amount corresponding relation between a temperature setting value of an air conditioner cooling system and cooling amount provided by the air conditioner cooling system, a cooling amount-power consumption corresponding relation between the cooling amount provided by the air conditioner cooling system and power consumption required by the air conditioner cooling system for providing the cooling amount, and rates of all sub-time periods associated with the air conditioner cooling system; determining the electric charge corresponding to the temperature setting value of each sub-time period according to the temperature setting value-cooling amount corresponding relation, the cooling amount-electricity consumption corresponding relation and the rate; and combining the first temperature values with the minimum sum of the electric charges corresponding to the plurality of included temperature setting values into a target temperature value combination.
Further, the system 5 according to the embodiment of the present application includes all the modules of the apparatus 1 as shown above. FIG. 18 is a schematic diagram of a system according to an exemplary embodiment of the present application.
According to an exemplary embodiment of the present application, the apparatus 1 further includes a correspondence adjusting module 108 configured to: acquiring historical data, wherein the historical data comprises an actual temperature setting value and an actual cooling capacity of each sub-time period in a historical time period of the air-conditioning cooling system; acquiring prediction data, wherein the prediction data comprises predicted cooling capacity according to the temperature setting value-cooling capacity corresponding relation; establishing a loss function according to the historical data and the prediction data, and determining a prediction error between the predicted cooling capacity and the actual cooling capacity; adjusting the corresponding relation between the temperature setting value and the cooling capacity according to the prediction error; and/or acquiring historical data, wherein the historical data comprises the actual cooling amount and the actual power consumption of the air conditioner cooling system in each sub-time period included in a historical time period; acquiring prediction data, wherein the prediction data comprises power consumption predicted according to the corresponding relation between the cooling capacity and the power consumption; establishing a loss function according to the historical data and the predicted data, and determining a prediction error between the predicted power consumption and the actual power consumption; and adjusting the corresponding relation between the cooling capacity and the power consumption according to the prediction error.
According to an exemplary embodiment of the present application, the apparatus 1 further comprises a target temperature value combination adjustment module 110 configured to obtain a time duration for adjusting the target temperature value combination, and determine an adjusted target temperature value combination within the time duration, the determining the adjusted target temperature value combination within the time duration comprising: after the step of obtaining a plurality of first temperature value combinations, for at least one first temperature value combination in the first temperature value combinations, for each sub-time period in a part or all of the sub-time periods, adjusting the temperature value of the sub-time period based on a preset step length to obtain at least one second temperature value combination, wherein the temperature value of each sub-time period in the at least one second temperature value combination is in a comfort zone temperature range corresponding to the sub-time period; and after the step of determining a target temperature value combination from the plurality of first temperature value combinations, determining an adjusted target temperature value combination from the first temperature value combination and the second temperature value combination, so that the temperature setting value of each of the plurality of sub-time periods is set according to the adjusted target temperature value combination, and the running state of the air-conditioning cooling system in a future preset time period is optimal.
According to an exemplary embodiment of the present application, the step of determining an adjusted target temperature value combination from the first temperature value combination and the second temperature value combination by the target temperature value combination adjustment module 110 of the apparatus 1 comprises: acquiring a temperature setting value-cooling amount corresponding relation between a temperature setting value of an air conditioner cooling system and cooling amount provided by the air conditioner cooling system, a cooling amount-power consumption corresponding relation between the cooling amount provided by the air conditioner cooling system and power consumption required by the air conditioner cooling system for providing the cooling amount, and rates of all sub-time periods associated with the air conditioner cooling system; determining the electric charge corresponding to the temperature setting value of each sub-time period according to the temperature setting value-cooling amount corresponding relation, the cooling amount-electricity consumption corresponding relation and the rate; and using the first temperature value combination or the second temperature value combination with the minimum sum of the electric charges corresponding to the plurality of temperature setting values as a target temperature value combination.
According to another exemplary embodiment of the present application, the step of determining an adjusted target temperature value combination from the first temperature value combination and the second temperature value combination by the target temperature value combination adjustment module 110 of the apparatus 1 comprises: acquiring a temperature setting value-cooling amount corresponding relation between a temperature setting value of an air conditioner cooling system and the cooling amount provided by the air conditioner cooling system and a cooling amount-power consumption corresponding relation between the cooling amount provided by the air conditioner cooling system and the power consumption required by the cooling amount provided by the air conditioner cooling system; and taking the first temperature value combination or the second temperature value combination with the minimum sum of the power consumption corresponding to the plurality of temperature setting values as the target temperature value combination.
According to an exemplary embodiment of the application, the apparatus 1 further comprises an adjustment optimization module 112 configured to: acquiring prediction errors of a plurality of historical time periods; if the prediction error increases over time in the plurality of historical time periods, performing at least one of the following in the step of adjusting the combination of target temperature values for a length of time over which the combination of target temperature values is adjusted: extending the length of the time length, decreasing the preset step size, and increasing the number of times of adjusting the temperature value of the sub-time period based on the preset step size to obtain at least one second temperature value combination.
According to an exemplary embodiment of the application, the target temperature value combination update module 114 of the apparatus 1 is configured to, at each new sub-period: executing the steps of obtaining a comfort zone temperature range of each sub-time period in a plurality of sub-time periods included in a future preset time period, obtaining a plurality of first temperature value combinations and determining a target temperature value combination from the plurality of first temperature value combinations; and taking the temperature values of the plurality of sub-time periods in the determined target temperature value combination as the temperature values of the corresponding plurality of sub-time periods in one temperature value combination in the plurality of first temperature value combinations to be acquired in the next future preset time period.
According to another exemplary embodiment of the present application, the target temperature value combination update module 114 of the apparatus 1 is further configured to, at each new sub-period: executing the steps of obtaining a comfort zone temperature range of each sub-time period in a plurality of sub-time periods included in a future preset time period, obtaining a plurality of first temperature value combinations and determining a target temperature value combination from the plurality of first temperature value combinations; executing the steps of obtaining a time length for adjusting the target temperature value combination, and determining the adjusted target temperature value combination in the time length; and taking the temperature values of the plurality of sub-time periods in the determined adjusted target temperature value combination as the temperature values of the corresponding plurality of sub-time periods in one temperature value combination in the plurality of first temperature value combinations to be acquired in the next future preset time period.
According to an exemplary embodiment of the application, the step of determining the adjusted combination of target temperature values over the time period is repeated periodically over the time period; and the length of each sub-time period is equal, and the duration of the target temperature value combination is adjusted to be smaller than the length of the sub-time period.
According to an exemplary embodiment of the present application, the comfort zone module acquiring the comfort zone temperature range includes: acquiring one or more pieces of information of outdoor temperature, humidity and people flow rate associated with a building; the comfort zone temperature range for each of a plurality of sub-periods included in the future predetermined period is determined based on the one or more information.
A system according to an embodiment of the present application may operate as follows.
Step 1: the cold side utilities and sensors are properly selected and set 302.
Step 2.1: the cooling side continuously sends sensor data to the device 1 determining the temperature setting of the air conditioning cooling system 3 to reflect the operating conditions of the system. The apparatus 1 updates the parameters of the data optimization algorithm based on history.
Step 2.2: the apparatus 1 builds an optimization model (objective function) that provides inputs and constraints for the optimization algorithm.
And step 3: the device 1 outputs the optimal solution (optimal temperature value combination) predicted within the calculation time length to the air-conditioning cooling system 3 of the cooling side once per hour according to the optimization algorithm. The optimum temperature value combination includes the temperature setting for the next 24 hours per hour in the building, as well as the amount of cooling, electricity usage and electricity charges.
And 4, step 4: the device 1 adjusts the temperature setting value of the air-conditioning cooling system 3 to the temperature setting value per hour of the optimal temperature value combination, and sends the predicted cooling capacity, power consumption and electricity fee to the control feedback module 304 of the air-conditioning cooling system 3.
And 5: the cooling side of the air conditioning cooling system 3 checks the advice of the temperature setting value in the control feedback module 304, makes an adjustment and sends the real-time historical data back to the control feedback module 304, and the control feedback module 304 sends the historical data to the apparatus 1.
Step 6: the apparatus 1 updates the optimization algorithm parameters based on an error analysis of the prediction data and the historical data. Finally, a new hourly temperature setting is proposed.
The system according to the present application provides the user with a combination of optimal temperature settings for a predetermined period of time in the future, e.g. 24 hours per hour in the future (optimal temperature value combination, i.e. 24 temperatures in total, optimal meaning that the sum of the electricity charges is minimal for 24 hours in the future at the setting of this set of temperature values). And providing predictions of the corresponding hourly cooling capacity, power usage, and hourly electricity rates for the set of optimal temperature values. In addition, the data-driven model of the system according to the present application corrects the error of the predicted value at the current hour according to the deviation of the predicted value at the past hour, thereby improving the accuracy of the predicted optimal temperature value combination.
According to another embodiment of the present application, there is provided a storage medium having a program stored thereon, the program causing a computer to execute the method according to the above-described embodiment when executed by the computer including the storage medium.
According to another embodiment of the present application, a processor for executing a program stored on a memory is provided, wherein the processor executes the program to perform the method according to the above embodiment.
The solution proposed by the present application is flexible and modular in design and can be adapted to buildings with different air conditioning and cooling systems. The optimization module and algorithm of the present application are flexible: various optimization algorithms can be used as the core algorithm. The error analysis of the present application helps to ensure the reliability of the prediction results and improve the computational efficiency. The solution of the present application allows to optimize both the cooling demand and the cooling side of the target building. The application considers sub-models such as the temperature range of a comfortable area, and the like, so that the air conditioner cooling system can ensure the minimum electricity consumption or the minimum total electricity charge in the next 24 hours, and meanwhile, the comfort of indoor personnel is ensured. The data-driven cooling optimization process of the present application is based on dynamically updated real-time data (e.g., cooling measurement data, such as chiller and pump operating parameters, peak-to-valley power rates). Therefore, the technical scheme of the application can reflect the real situation of the system when in use and can optimize at any time.
In the above embodiments of the present application, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
In the embodiments provided in the present application, it should be understood that the disclosed technology can be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units or modules is only one logical division, and there may be other divisions when the actual implementation is performed, for example, a plurality of units or modules or components may be combined or integrated with another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of modules or units through some interfaces, and may be in an electrical or other form.
The units or modules described as separate parts may or may not be physically separate, and parts displayed as units or modules may or may not be physical units or modules, may be located in one place, or may be distributed on a plurality of network units or modules. Some or all of the units or modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
In addition, functional units or modules in the embodiments of the present application may be integrated into one processing unit or module, or each unit or module may exist alone physically, or two or more units or modules are integrated into one unit or module. The integrated unit or module may be implemented in the form of hardware, or may be implemented in the form of a software functional unit or module.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.
The foregoing is only a preferred embodiment of the present application and it should be noted that those skilled in the art can make several improvements and modifications without departing from the principle of the present application, and these improvements and modifications should also be considered as the protection scope of the present application.

Claims (13)

  1. A method of determining a temperature setting for an air conditioning cooling system within a building, comprising:
    a step of obtaining a comfortable zone temperature range of each sub-time period in a plurality of sub-time periods in a future preset time period, wherein the comfortable zone temperature range is a temperature range enabling people in the building to feel comfortable in the corresponding sub-time period, and each comfortable zone temperature range is smaller than a temperature adjustment range of the air-conditioning and cooling system;
    obtaining a plurality of first temperature value combinations, wherein each first temperature value combination comprises a plurality of temperature values, each temperature value in the plurality of temperature values corresponds to one sub-time period in the plurality of sub-time periods, and each temperature value is in the temperature range of the comfort zone corresponding to the sub-time period; and
    and determining a target temperature value combination from a plurality of first temperature value combinations, so that the temperature setting value of each of the plurality of sub-time periods is set according to the target temperature value combination, and the running state of the air-conditioning cooling system in the future preset time period is optimal.
  2. The method of claim 1, wherein the step of determining a target temperature value combination from the plurality of first temperature value combinations comprises:
    acquiring a temperature setting value-cooling amount corresponding relation between a temperature setting value of the air-conditioning cooling system and the cooling amount provided by the air-conditioning cooling system and a cooling amount-power consumption corresponding relation between the cooling amount provided by the air-conditioning cooling system and the power consumption required by the air-conditioning cooling system for providing the cooling amount;
    and taking the first temperature value combination with the minimum sum of the power consumption corresponding to the plurality of included temperature setting values as the target temperature value combination.
  3. The method of claim 1, wherein the step of determining a target temperature value combination from the plurality of first temperature value combinations comprises:
    acquiring a temperature setting value-cooling amount corresponding relation between a temperature setting value of the air-conditioning cooling system and the cooling amount provided by the air-conditioning cooling system, a cooling amount-power consumption corresponding relation between the cooling amount provided by the air-conditioning cooling system and the power consumption required by the air-conditioning cooling system for providing the cooling amount, and rates of the sub-time periods associated with the air-conditioning cooling system;
    determining the electric charge corresponding to the temperature setting value of each sub-time period according to the temperature setting value-cooling capacity corresponding relation, the cooling capacity-electricity consumption corresponding relation and the rate; and
    and using the first temperature value combination with the minimum sum of the electric charges corresponding to the plurality of included temperature setting values as the target temperature value combination.
  4. The method of claim 2 or 3, further comprising:
    acquiring historical data, wherein the historical data comprises an actual temperature setting value and an actual cooling capacity of each sub-time period included in a historical time period of the air-conditioning cooling system; acquiring prediction data, wherein the prediction data comprises the predicted cooling capacity according to the temperature setting value-cooling capacity corresponding relation; establishing a loss function according to the historical data and the prediction data, and determining a prediction error between the predicted cooling capacity and the actual cooling capacity; adjusting the corresponding relation between the temperature setting value and the cooling capacity according to the prediction error; and/or
    Acquiring historical data, wherein the historical data comprises the actual cooling amount and the actual power consumption of the air conditioner cooling system in each sub-time period included in a historical time period; acquiring predicted data, wherein the predicted data comprises the predicted power consumption according to the corresponding relation between the cooling capacity and the power consumption; establishing a loss function according to the historical data and the predicted data, and determining a prediction error between predicted power consumption and actual power consumption; and adjusting the corresponding relation between the cooling capacity and the power consumption according to the prediction error.
  5. The method of claim 1, further comprising obtaining a time duration for adjusting the target temperature value combination, and determining the adjusted target temperature value combination over the time duration, wherein determining the adjusted target temperature value combination over the time duration comprises:
    after the step of obtaining a plurality of first temperature value combinations, for at least one first temperature value combination in the first temperature value combinations, for each sub-time period in a part or all of the sub-time periods, adjusting the temperature value of the sub-time period based on a preset step length to obtain at least one second temperature value combination, wherein the temperature value of each sub-time period in the at least one second temperature value combination is within the comfort zone temperature range corresponding to the sub-time period; and
    after the step of determining a target temperature value combination from the plurality of first temperature value combinations, determining an adjusted target temperature value combination from the first temperature value combination and the second temperature value combination, so that the operating state of the air-conditioning cooling system in the future predetermined time period is optimal by setting the temperature setting value of each of the plurality of sub-time periods according to the adjusted target temperature value combination.
  6. The method of claim 1, further comprising, at each new sub-period:
    executing the steps of obtaining a comfort zone temperature range of each sub-time period in a plurality of sub-time periods included in a future preset time period, obtaining a plurality of first temperature value combinations and determining a target temperature value combination from the plurality of first temperature value combinations; and
    and taking the temperature value of the plurality of sub-time periods in the determined target temperature value combination as the temperature value of the corresponding plurality of sub-time periods in one temperature value combination in the plurality of first temperature value combinations to be acquired in the next future preset time period.
  7. The method of claim 1, wherein obtaining the comfort zone temperature range comprises:
    acquiring one or more pieces of information of outdoor temperature, humidity and people flow rate associated with the building;
    determining the comfort zone temperature range for each of a plurality of sub-periods included in a future predetermined period of time based on the one or more information.
  8. Apparatus for determining a temperature setting for an air conditioning cooling system within a building, comprising:
    a comfort zone module (102) configured to perform the step of obtaining a comfort zone temperature range for each of a plurality of sub-time periods included in a future predetermined time period, wherein the comfort zone temperature range is a temperature range enabling persons in the building to feel comfortable in the corresponding sub-time period, and each comfort zone temperature range is smaller than a temperature adjustment range of the air-conditioning cooling system;
    a temperature value combination obtaining module (104) configured to perform the step of obtaining a plurality of first temperature value combinations, wherein each of the first temperature value combinations comprises a plurality of temperature values, each of the plurality of temperature values corresponds to one of the plurality of sub-periods, and each temperature value is in the comfort zone temperature range corresponding to the sub-period;
    a target temperature value combination determination module (106) configured to perform the step of determining a target temperature value combination from a plurality of first temperature value combinations, so that the temperature setting value of each of the plurality of sub-time periods is set according to the target temperature value combination, and the operation state of the air conditioner cooling system in the future predetermined time period is optimal.
  9. The apparatus of claim 8, wherein the target temperature value combination determining module (106) performs the step of determining a target temperature value combination from a plurality of the first temperature value combinations, comprising:
    acquiring a temperature setting value-cooling amount corresponding relation between a temperature setting value of the air-conditioning cooling system and the cooling amount provided by the air-conditioning cooling system and a cooling amount-power consumption corresponding relation between the cooling amount provided by the air-conditioning cooling system and the power consumption required by the air-conditioning cooling system for providing the cooling amount;
    and taking the first temperature value combination with the minimum sum of the power consumption corresponding to the plurality of included temperature setting values as the target temperature value combination.
  10. The apparatus of claim 8, wherein the target temperature value combination determining module (106) performs the step of determining a target temperature value combination from a plurality of the first temperature value combinations, comprising:
    acquiring a temperature setting value-cooling amount corresponding relation between a temperature setting value of the air-conditioning cooling system and the cooling amount provided by the air-conditioning cooling system, a cooling amount-power consumption corresponding relation between the cooling amount provided by the air-conditioning cooling system and the power consumption required by the air-conditioning cooling system for providing the cooling amount, and rates of the sub-time periods associated with the air-conditioning cooling system;
    determining the electric charge corresponding to the temperature setting value of each sub-time period according to the temperature setting value-cooling capacity corresponding relation, the cooling capacity-electricity consumption corresponding relation and the rate; and
    and using the first temperature value combination with the minimum sum of the electric charges corresponding to the plurality of included temperature setting values as the target temperature value combination.
  11. A system for determining a temperature setting for an air conditioning and cooling system within a building, said system comprising:
    the air-conditioning cooling system (3); and
    apparatus (1) for determining a temperature setting for an air conditioning and cooling system within a building, said apparatus (1) comprising:
    a comfort zone module (102) configured to perform the step of obtaining a comfort zone temperature range for each of a plurality of sub-time periods included in a future predetermined time period, wherein the comfort zone temperature range is a temperature range enabling persons in the building to feel comfortable in the corresponding sub-time period, and each comfort zone temperature range is smaller than a temperature adjustment range of the air-conditioning cooling system;
    a temperature value combination obtaining module (104) configured to perform the step of obtaining a plurality of first temperature value combinations, wherein each of the first temperature value combinations comprises a plurality of temperature values, each of the plurality of temperature values corresponds to one of the plurality of sub-periods, and each temperature value is in the comfort zone temperature range corresponding to the sub-period;
    a target temperature value combination determination module (106) configured to perform the step of determining a target temperature value combination from a plurality of first temperature value combinations, so that the temperature setting value of each of the plurality of sub-time periods is set according to the target temperature value combination, and the operation state of the air conditioner cooling system in the future predetermined time period is optimal.
  12. A storage medium characterized in that the storage medium has stored thereon a program which, when executed by a computer including the storage medium, causes the computer to execute the method according to any one of claims 1 to 7.
  13. A processor for executing a program stored on a memory, wherein the processor executes the program to perform the method according to any one of claims 1 to 7.
CN201980096481.1A 2019-05-27 2019-05-27 Method, apparatus, system, storage medium, and processor for determining a temperature setting Pending CN113825955A (en)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2019/088598 WO2020237468A1 (en) 2019-05-27 2019-05-27 Method, apparatus and system for determining temperature setting value, and storage medium and processor

Publications (1)

Publication Number Publication Date
CN113825955A true CN113825955A (en) 2021-12-21

Family

ID=73553565

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201980096481.1A Pending CN113825955A (en) 2019-05-27 2019-05-27 Method, apparatus, system, storage medium, and processor for determining a temperature setting

Country Status (2)

Country Link
CN (1) CN113825955A (en)
WO (1) WO2020237468A1 (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113283056B8 (en) * 2021-04-28 2024-02-23 长安大学 Method for calculating adaptability of evaporative cooling air conditioning technology in different areas
CN114608187B (en) * 2022-03-01 2023-09-26 博锐尚格科技股份有限公司 Method, device, equipment and storage medium for determining cooling machine adjusting mode

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107763799A (en) * 2017-11-27 2018-03-06 中山路得斯空调有限公司 A kind of building air conditioning flexible control system
CN109323419A (en) * 2018-09-30 2019-02-12 广东美的制冷设备有限公司 The method and apparatus and air-conditioning system and equipment of peak of power consumption control air-conditioning
CN109612034A (en) * 2018-11-30 2019-04-12 广东美的制冷设备有限公司 Temprature control method, device and storage medium
US20210080915A1 (en) * 2017-10-02 2021-03-18 Hitachi, Ltd. System and method for controlling an hvac system or an acmv system of a building

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101430546A (en) * 2007-11-09 2009-05-13 苏州三星电子有限公司 Operation control method for sleep mode of air conditioner
CN103245033B (en) * 2012-02-10 2016-04-20 珠海格力电器股份有限公司 Air conditioner and control method and device thereof
CN103512151A (en) * 2012-06-29 2014-01-15 株式会社日立制作所 Method and device for having control over air conditioner installed in area
CN104791963A (en) * 2015-05-08 2015-07-22 天津汇西尔制冷设备有限公司 Variable air volume (VAV) energy-saving control system for central air-conditioner
CN106958913A (en) * 2017-02-16 2017-07-18 中节能城市节能研究院有限公司 A kind of weather compensation type building air-conditioner energy-storage system

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20210080915A1 (en) * 2017-10-02 2021-03-18 Hitachi, Ltd. System and method for controlling an hvac system or an acmv system of a building
CN107763799A (en) * 2017-11-27 2018-03-06 中山路得斯空调有限公司 A kind of building air conditioning flexible control system
CN109323419A (en) * 2018-09-30 2019-02-12 广东美的制冷设备有限公司 The method and apparatus and air-conditioning system and equipment of peak of power consumption control air-conditioning
CN109612034A (en) * 2018-11-30 2019-04-12 广东美的制冷设备有限公司 Temprature control method, device and storage medium

Also Published As

Publication number Publication date
WO2020237468A1 (en) 2020-12-03

Similar Documents

Publication Publication Date Title
JP6976976B2 (en) Multilevel model predictive control system and method
Korkas et al. Grid-connected microgrids: Demand management via distributed control and human-in-the-loop optimization
US9429961B2 (en) Data-driven HVAC optimization
CN103398451B (en) Based on the multidimensional comfort level indoor environmental condition control method and system of study user behavior
CN102812303B (en) HVAC control system and method
Rajasekhar et al. A survey of computational intelligence techniques for air-conditioners energy management
US20150310461A1 (en) Operating method and apparatus of smart system for power consumption optimization
Abdulaal et al. Two-stage discrete-continuous multi-objective load optimization: An industrial consumer utility approach to demand response
EP1729223A2 (en) Demand control apparatus, electric power consumption prediction method, and program therefor
CN110736227A (en) Building management system with online configurable system identification
WO2010098083A1 (en) Energy usage control system and method
CN105143781A (en) Air-conditioning control system and method
US20130151013A1 (en) Method for Controlling HVAC Systems Using Set-Point Trajectories
US11578889B2 (en) Information processing apparatus and air-conditioning system provided with the same
US11215375B2 (en) Building control system with heat disturbance estimation and prediction
CN111609534A (en) Temperature control method and device and central temperature control system
US10830474B2 (en) Systems and methods of predicting energy usage
CN113825955A (en) Method, apparatus, system, storage medium, and processor for determining a temperature setting
CN110398029A (en) Control method and computer readable storage medium
Kircher et al. Distributed peak shaving for small aggregations of cyclic loads
JP6589227B1 (en) Control device, air conditioning control system, control information calculation method and program
EP3352027B1 (en) Method and system of smart climatization management
CN115793478A (en) Control method and device for household appliance and household appliance
Shi et al. Adaptive Data-Driven Predictive Control as a Module in Building Control Hierarchy: A Case Study of Demand Response in Switzerland
JP2022053418A (en) Optimum regulator

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20211221

WD01 Invention patent application deemed withdrawn after publication