Air conditioning system can respond to quantity prediction method, device, cloud platform and storage medium

Abstract

An air conditioning system can respond to the method, device, cloud platform and storage medium, the method comprises: obtaining the current operation data and prediction data of air conditioning system; The current operation data comprises the indoor temperature, outdoor temperature and system operation power of air conditioning system in the response period before this response, and the prediction data comprises the indoor predicted temperature and outdoor predicted temperature of air conditioning system in the response period of this response; According to the current operation data, prediction data and response amount correction coefficient of this response, the system operation power of air conditioning system in the response period of this response is predicted; According to the baseline load of air conditioning system and the predicted system operation power, the predicted air conditioning system can respond to the amount of this response; The response amount correction coefficient of this response is calculated by inputting at least part of the data in the current operation data and the prediction data into the calculation model of the response amount correction coefficient, which can improve the prediction accuracy of the response amount while taking into account the indoor temperature comfort.

Description

Technical Field

[0001] This article relates to the field of power demand response control, and in particular to a method, device, cloud platform, and storage medium for predicting the responsiveness of an air conditioning system. Background Technology

[0002] Building energy consumption accounts for a large proportion of electricity consumption, and central air conditioning systems account for almost one-third of that. Especially during peak summer electricity demand, the energy consumption contributed by air conditioning load can even reach more than half of the total building energy consumption. Although peak electricity loads are high, their duration is short. Allocating additional power generation resources to meet peak demand is not economical and violates the principle of reducing energy consumption. Air conditioning systems are thermal systems and inherently possess a margin for flexible control, thus enabling demand response actions during peak electricity periods. These demand response actions refer to adjusting the electricity consumption behavior of electrical equipment when wholesale electricity prices rise or the reliability of the power system is threatened, thereby reducing or shifting peak loads, ensuring grid stability, reducing user electricity costs, or helping users obtain subsidies.

[0003] Multi-split air conditioning systems account for about half of the domestic central air conditioning market. They typically consist of one outdoor unit and multiple indoor units. The outdoor unit supplies refrigerant to the connected indoor units via piping to meet indoor cooling and heating load requirements, offering advantages such as high energy efficiency and simple installation. Currently, multi-split air conditioning systems are connected and controlled by load aggregators. When multi-split air conditioning systems participate in electricity demand response, the load aggregator first predicts the potential response amount (also known as responsive quantity) of each multi-split air conditioning system it controls within a specified response period. The predicted potential response amounts of all multi-split air conditioning systems are then aggregated and reported to the power grid.

[0004] When the actual settlement is carried out after the response is completed, the relative ratio between the actual response volume of all multi-split air conditioning systems and the responsive volume reported by the load aggregator directly affects the response subsidy coefficient. Figure 1 This is an example graph of a response subsidy coefficient. The horizontal axis represents the ratio of the actual response amount to the reported responsive amount, and the vertical axis represents the subsidy coefficient. Figure 1As can be seen, if the reported responsiveness is too high relative to the actual response, it may result in a smaller subsidy coefficient or even an invalid response. Conversely, if the multi-split air conditioning system is controlled with an excessively high reported response, the indoor temperature may exceed the comfortable range, reducing the user experience. Conversely, if the reported responsiveness is too low relative to the actual response, the subsidy coefficient will also be low, preventing subsidies for a large amount of excess response. Furthermore, if the multi-split air conditioning system is controlled with an excessively low reported response, it will hinder the achievement of peak shaving control objectives for the power grid. Therefore, accurately predicting the responsiveness of the air conditioning system is a crucial part of the entire demand response operation. Summary of the Invention

[0005] This application provides a method, apparatus, cloud platform, and storage medium for predicting the responsiveness of an air conditioning system.

[0006] The method for predicting the responsiveness of air conditioning systems for electricity demand response provided in this application includes:

[0007] Obtain current operating data and predicted data of the air conditioning system; the current operating data includes the indoor temperature, outdoor temperature and system operating power of the air conditioning system in the period before the response of this response, and the predicted data includes the indoor predicted temperature and outdoor predicted temperature of the air conditioning system in the response period of this response.

[0008] The system operating power of the air conditioning system during the response period of this response is predicted based on the current operating data, the predicted data, and the response quantity correction coefficient of this response.

[0009] The predicted responsiveness of the air conditioning system in this response is obtained based on the baseline load of the air conditioning system and the predicted operating power of the system.

[0010] The response quantity correction coefficient for this response is calculated by inputting at least a portion of the current running data and the predicted data into the calculation model of the response quantity correction coefficient.

[0011] Compared with related technologies, the prediction method described in this application comprehensively considers various temperature and power data that affect the responsiveness of the air conditioning system when predicting the responsiveness, which is more comprehensive and helps to improve the prediction accuracy of the responsiveness. Moreover, the temperature data includes not only the actual temperature data before the response, but also the predicted temperature data during the response period with controllable prediction deviation, so that the predicted responsiveness during the response period is more in line with the actual response under the indoor temperature comfort requirements.

[0012] Other features and advantages of this application will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing the application. Other advantages of this application can be realized and obtained by means of the solutions described in the description and the accompanying drawings. Attached Figure Description

[0013] The accompanying drawings are used to provide an understanding of the technical solutions of this application and constitute a part of the specification. They are used together with the embodiments of this application to explain the technical solutions of this application and do not constitute a limitation on the technical solutions of this application.

[0014] Figure 1 This is an example diagram of an existing response subsidy policy;

[0015] Figure 2 A flowchart of a method for predicting the responsiveness of an air conditioning system for electricity demand response, provided in an embodiment of this application.

[0016] Figure 3 An example diagram illustrating a historical response to electricity demand, provided as an embodiment of this application;

[0017] Figure 4 A flowchart illustrating the method for predicting aggregate responsive quantities of multiple air conditioning systems for power demand response, as provided in this application embodiment;

[0018] Figure 5 A structural diagram of a predictive device for the responsive quantity of an air conditioning system for power demand response, provided in an embodiment of this application.

[0019] Figure 6 This is a cloud platform structure diagram of a load aggregator provided in an embodiment of this application. Detailed Implementation

[0020] This application describes several embodiments, but these descriptions are exemplary and not restrictive, and it will be apparent to those skilled in the art that many more embodiments and implementations are possible within the scope of the embodiments described herein. Although many possible combinations of features are shown in the drawings and discussed in the detailed description, many other combinations of the disclosed features are also possible. Unless specifically limited, any feature or element of any embodiment may be used in combination with, or may replace, any feature or element of any other embodiment.

[0021] This application includes and contemplates combinations of features and elements known to those skilled in the art. The embodiments, features, and elements disclosed in this application may also be combined with any conventional features or elements to form a unique inventive scheme as defined by the claims. Any feature or element of any embodiment may also be combined with features or elements from other inventive schemes to form another unique inventive scheme as defined by the claims. Therefore, it should be understood that any feature shown and / or discussed in this application may be implemented individually or in any suitable combination. Therefore, the embodiments are not limited except by the limitations imposed by the appended claims and their equivalents. Furthermore, various modifications and changes may be made within the scope of the appended claims.

[0022] Furthermore, in describing representative embodiments, the specification may have presented methods and / or processes as a specific sequence of steps. However, the method or process should not be limited to the specific order of steps described herein, to the extent that it does not depend on such a specific order. As will be understood by those skilled in the art, other sequences of steps are also possible. Therefore, the specific order of steps set forth in the specification should not be construed as a limitation of the claims. Moreover, the claims concerning the method and / or process should not be limited to the steps performed in the written order, and those skilled in the art will readily understand that these orders can be varied and still remain within the spirit and scope of the embodiments of this application.

[0023] In a demand response (DR) scheme, the response quantity refers to the reduction or delay in the use of electricity by a user or participating facility during a demand response event. In other words, it is the actual reduction in electricity consumption by a user compared to their normal electricity consumption pattern when a demand response event occurs. The response quantity can be measured in several ways, such as: absolute value: directly representing the total reduction in electricity or energy, expressed in kilowatts (kW) or kilowatt-hours (kWh); or percentage: the percentage of a participant's total electricity consumption that is reduced.

[0024] The response of an air conditioning system is affected by a variety of factors, such as the operating power of the air conditioning system, the ambient temperature where the air conditioning system is located, the thermal characteristics of the building, and the changes in the heat load of the room. The heat load of the room refers to the load caused by complex factors such as electrical equipment, people, outdoor air infiltration, and solar radiation in the room.

[0025] Demand response schemes typically define a responsive quantity (also known as a target responsive quantity), which is jointly predicted based on the grid operator's demand and the participants' capabilities. Achieving this responsive quantity usually provides participants with economic incentives, such as electricity bill reductions or additional rewards.

[0026] Currently, there are two main methods for predicting the responsiveness of air conditioning systems: one method is to calculate the responsiveness by taking a certain proportion of the pre-response load or baseline load of the air conditioning system. This method does not consider the issue of matching the output capacity of the air conditioning system with the total cooling and heating load of the room after the response action. As a result, it may not be able to uncover more of the responsiveness of the air conditioning system, and there is also a risk that the indoor temperature may no longer be within the comfortable temperature range, reducing the user's comfort experience. The other method is to predict the responsiveness based on models. This method requires the establishment of separate thermophysical models of the building rooms and energy consumption models of the air conditioning system. The model construction is complex, the amount of calculation is large and time-consuming, which restricts its widespread application in the current minute-level response tasks or real-time response tasks.

[0027] This application provides a method for predicting the responsiveness of an air conditioning system based on electricity demand response, such as... Figure 2 As shown, the method includes:

[0028] Step S201: Obtain the current operating data and forecast data of the air conditioning system;

[0029] A response typically includes a pre-response period and a response period. The response period, also known as the response time, can be determined according to the regulations and arrangements of the grid operator or relevant institutions. A specific response period is defined by the start and end times of the response period. The response period can be adjusted according to different factors, such as actual electricity demand, power supply capacity, and market demand. It is common to use peak electricity consumption periods as the response period, such as the morning peak of 9:00-11:00, the afternoon peak of 15:00-17:00, and the evening peak of 18:00-20:00, or a specific time period determined by the grid operator's response invitation.

[0030] The following conditions may be met, in part or in all of them, between the pre-response period and the response period of the same response:

[0031] The end time of the pre-response period is the start time of the response period; or, the ratio of the duration of the pre-response period to the duration of the response period is greater than 0.9 and less than 1.1; or the ratio of the duration of the pre-response period to the duration of the response period is equal to 0.9; or the ratio of the duration of the pre-response period to the duration of the response period is equal to 1.1.

[0032] The current operating data includes: the indoor temperature, outdoor temperature, and system operating power of the air conditioning system during the period prior to the current response; the indoor temperature during the period prior to the response may be the average indoor temperature during that period, the outdoor temperature during the period prior to the response may be the average outdoor temperature during that period, and the system operating power during the period prior to the response may be the average operating power of the system during that period; the current operating data can be data that can be measured by relevant technical means.

[0033] The predicted data includes: the indoor and outdoor predicted temperatures of the air conditioning system during the response period of this response; since the response period of this response has not yet begun when this method is implemented, the indoor and outdoor temperatures during the response period are predicted data.

[0034] Step S202 predicts the system operating power of the air conditioning system during the response period of this response based on the current operating data, the predicted data, and the response quantity correction coefficient of this response;

[0035] The response quantity correction coefficient for this response is calculated by inputting at least a portion of the current running data and the predicted data into the calculation model of the response quantity correction coefficient;

[0036] Step S203: Based on the baseline load of the air conditioning system and the predicted operating power of the system, the predicted responsiveness of the air conditioning system in this response is obtained; for example, the difference between the baseline load of the air conditioning system and the predicted operating power of the system can be used as the predicted responsiveness of the air conditioning system in this response.

[0037] The baseline load refers to the predicted load on electricity users without participation in demand response projects, and it can be determined by participants such as power companies, power system management agencies, energy service providers, or load aggregators.

[0038] The method for predicting the responsiveness of an air conditioning system for power demand response described in this application comprehensively considers various temperature and power data that affect the responsiveness when predicting the responsiveness of the air conditioning system. This comprehensive consideration of factors helps to improve the prediction accuracy of the responsiveness. Furthermore, the temperature data includes not only the actual temperature data before the response but also the predicted temperature data during the response period with controllable prediction deviation, making the predicted responsiveness during the response period more closely match the actual response under indoor temperature comfort requirements.

[0039] In an exemplary embodiment, the outdoor and indoor temperatures of the air conditioning system during the period prior to the current response, and the outdoor and indoor temperatures during the response period, can be determined in the following manner:

[0040] The outdoor temperature of the air conditioning system during the pre-response period can be determined based on Tb1, and the predicted outdoor temperature Ta2' of the air conditioning system during the response period can be determined based on Tb2. Here, Tb1 is the real-time temperature of the area where the air conditioning system is located, as published by the meteorological station, during the pre-response period; and Tb2 is the forecast temperature of the area where the air conditioning system is located, as published by the meteorological station, during the response period. For example, the average of the real-time temperatures at multiple moments during the pre-response period can be used as the outdoor temperature during the pre-response period; and the average of the forecast temperatures at multiple moments during the response period can be used as the predicted outdoor temperature during the response period.

[0041] The outdoor temperature of the air conditioning system in the period before the response of this response can be determined according to Ts. The outdoor predicted temperature Ta2' of the air conditioning system in the response period of this response can be obtained according to the following formula: Ta2'=Ts+(Tb2-Tb1); Ts is the ambient temperature detected at the outdoor unit of the air conditioning system in the period before the response of this response. Since there is a difference between the ambient temperature at the outdoor unit of the air conditioning system and the ambient temperature of the area published by the meteorological station, the outdoor predicted temperature Ta2' obtained by correcting the ambient temperature detected at the outdoor unit of the air conditioning system in the period before the response (which can be the average of the ambient temperatures detected at multiple times) is more accurate.

[0042] The indoor temperature of the air conditioning system in the period prior to the response of this response can be measured in a variety of ways, such as by using instruments such as thermometers, infrared thermometers, and smart thermostats to measure the room temperature or return air temperature.

[0043] The predicted indoor temperature of the air conditioning system during the response period can be any temperature within the indoor comfort temperature range to ensure that the predicted responsiveness takes into account the user's temperature comfort experience. For example, the predicted indoor temperature can be equal to the upper or lower limit of the comfort temperature of the air conditioning system. In cooling mode, the predicted indoor temperature is equal to the upper limit of the comfort temperature; in heating mode, the predicted indoor temperature is equal to the lower limit of the comfort temperature. This maximizes the responsiveness of the air conditioning system during the response period while taking into account the user's comfort experience. The comfort temperature range of the air conditioning system can be set, obtained from user feedback statistics, or calculated based on relevant models.

[0044] In an exemplary embodiment, the calculation model for the response correction coefficient can be a regression model obtained by performing regression analysis on the historical response data of the air conditioning system. The regression analysis is a predictive modeling technique that studies the relationship between the dependent variable (also known as the target or the variable to be regressed) and the independent variables. In this embodiment, the variable to be regressed in the regression model is the response correction coefficient, and the independent variables in the regression model include: the indoor temperature of the air conditioning system before the response period, the outdoor temperature before the response period, the indoor temperature during the response period, and the outdoor temperature during the response period.

[0045] The historical response data includes the indoor temperature, outdoor temperature, and system operating power of the air conditioning system during the period before each response in the past multiple responses, as well as the indoor temperature, outdoor temperature, and system operating power during the response period in the past multiple responses.

[0046] The calculation principle of the response correction coefficient described in the embodiments of this application is explained below.

[0047] Figure 3 As an example of a historical response to electricity demand, a historical response is divided into two periods: a pre-response period and a response period. The length of the pre-response period and the response period is the same, both being dt. Time t1 represents the start time of the response period; Ta represents the outdoor temperature, Ti represents the indoor temperature, and Pac represents the operating power of the air conditioning system. During the response period, due to the increase in indoor temperature, the air conditioning system may enter the temperature-reaching shutdown phase, i.e., phase ② in the diagram; or it may not enter phase ② and maintain continuous operation at a lower power. Therefore, phase ② does not necessarily exist. Figure 3 The stage division shown is only a schematic diagram of air conditioner power control during the response period.

[0048] Before the response period, based on the principle that the output heat of the air conditioning system and the heat load of the room must be conserved, formula (1) is established:

[0049] Cop1*Pac_1=K*A*(Ta1-Ti1)+Q1 (1)

[0050] Cop1 represents the energy efficiency ratio of the air conditioning system before the response period, Pac_1 represents the system operating power of the air conditioning system before the response period, K represents the overall heat transfer coefficient of the room, A represents the overall heat transfer area of ​​the room, K*A represents the total indoor and outdoor thermal conductivity, Ta1 represents the outdoor temperature of the air conditioning system before the response period, Ti1 represents the indoor temperature of the air conditioning system before the response period, and Q1 represents the collective term for other heat gain before the response period, including heat gain of people in the room, heat gain of equipment, heat gain from solar radiation, and heat gain from indoor and outdoor air infiltration.

[0051] Since Q1 can be converted into a certain proportion of K*A*(Ta1-Ti1), by transforming formula (1), we can obtain formula (2):

[0052] Cop1*Pac_1=a1*K*A*(Ta1-Ti1) (2)

[0053] During the response period, based on the principle that the output heat of the air conditioning system and the heat load of the room must be conserved, formula (3) is established:

[0054] Cop2*Pac_2=K*A*(Ta2-Ti2)+Q2 (3)

[0055] Cop2 represents the energy efficiency ratio of the air conditioning system during the response period, Pac_2 represents the system operating power of the air conditioning system during the response period, Ta2 represents the outdoor temperature of the air conditioning system during the response period, Ti2 represents the indoor temperature of the air conditioning system during the response period, and Q2 represents the collective term for other heat gain during the response period.

[0056] Transforming formula (3), we obtain formula (4):

[0057] Cop2*Pac_2=a2*K*A*(Ta2-Ti2) (4)

[0058] After entering the response period, the decrease in system power dPac can be expressed as:

[0059] dPac=Pac_1-Pac_2=a1*K*A*(Ta1-Ti1) / Cop1-a2*K*A*(Ta2-Ti2) / Cop2 (5)

[0060] Let Cop2 = a3 * Cop1, then formula (5) can be transformed into:

[0061] dPac=Pac_1-Pac_2=a1*K*A*(Ta1-Ti1) / Cop1*{1-a2 / a3 / a1*[(Ta2-Ti2) / (Ta1-Ti1)]}

[0062] That is, dPac=Pac_1*{1-a2 / a3 / a1*[(Ta2-Ti2) / (Ta1-Ti1)]} (6)

[0063] Let a = a2 / a3 / a1 = f(Ta1,Ti1,Ta2,Ti2), then formula (6) can be transformed into:

[0064] dPac=Pac_1*{1-a*[(Ta2-Ti2) / (Ta1-Ti1)]} (7)

[0065] In formula (7), except for parameter a, all other parameters can be obtained based on historical response data. Therefore, based on the statistical results of historical response data, the correspondence between a and Ta1, Ti1, Ta2, and Ti2 can be obtained through regression, which is expressed as a = f(Ta1, Ti1, Ta2, Ti2). Parameter a is the response correction coefficient recorded in the embodiments of this application.

[0066] For example, the calculation model for the response correction coefficient obtained through regression is as follows:

[0067] a = k1*(Ta1-Ti1)+k2*(Ta2-Ti2)+k3*(Ta2-Ta1)+k4*(Ti2-Ti1); k1, k2, k3 and k4 are coefficients.

[0068] In an exemplary embodiment, for this response, when the current operating data, the predicted data, and the response quantity correction coefficient for this response are all known, the step of predicting the system operating power of the air conditioning system during the response period of this response based on the current operating data, the predicted data, and the response quantity correction coefficient for this response includes:

[0069] The system power reduction dPac is calculated according to formula (8):

[0070] dPac=Pac_1*{1-a*[(Ta2'-Ti2') / (Ta1-Ti1)]} (8)

[0071] The difference between formula (8) and formula (7) is that the indoor temperature Ti2' and outdoor temperature Ta2' during the response period in formula (8) are predicted quantities, while the indoor temperature Ti2 and outdoor temperature Ta2 during the response period in formula (7) are historical data, which are actual measurements.

[0072] After obtaining the system power reduction dPac, the predicted system operating power Pac_2' during the response period of this response is calculated according to formula (9):

[0073] Pac_2'=Pac_1-dPac (9)

[0074] In one exemplary embodiment, the method may further include:

[0075] After entering the response period, the operating data of the air conditioning system during the response period of this response are obtained. The operating data of the air conditioning system during the response period of this response includes indoor temperature, outdoor temperature and system operating power.

[0076] After this response is completed, the calculation model of the response quantity correction coefficient is updated based on the operating data of the air conditioning system during the response period of this response.

[0077] In this embodiment, the method of obtaining the operating data of the air conditioning system during the response period of this response can be the same as the method of obtaining the operating data of the air conditioning system during the period before the response of this response; the update refers to using the operating data of the response period of this response as historical data, and re-performing regression analysis to update the calculation model of the response correction coefficient, which helps the model to more accurately reflect the real-time characteristic changes of the air conditioning system and improve the accuracy of the prediction results made by the model.

[0078] The air conditioning system described in this embodiment can be a multi-split air conditioning system, a unit air conditioning system, or other types of air conditioning systems.

[0079] When the air conditioning system is a multi-split air conditioning system, the method for obtaining the indoor temperature of the multi-split air conditioning system in the period before each response includes: periodically acquiring the indoor temperature of the room where each indoor unit of the multi-split air conditioning system is located during the period before the response; and taking the average or weighted average of the indoor temperatures of all the acquired rooms as the indoor temperature of the period before the response. When taking the weighted average, the weighted value of the indoor temperature of all the rooms acquired in each period can be the same, or the weighted value of the indoor temperature of all the rooms acquired from the period closer to the response period is larger. The indoor temperature of the room where an indoor unit is located can be the return air temperature of that indoor unit, or the room temperature detected by a temperature detection instrument installed in the room where the indoor unit is located.

[0080] During the response period, the method for obtaining the indoor temperature of the multi-split air conditioning system during the response period of each response includes: predicting the indoor temperature of the room where each indoor unit of the multi-split air conditioning system is located; and using the average or weighted average of the predicted indoor temperatures of all rooms as the predicted indoor temperature for the response period.

[0081] Typically, a multi-split air conditioning system has only one outdoor unit. If the system has multiple outdoor units, the outdoor temperature before each response can be obtained by periodically acquiring the ambient temperature of each outdoor unit and using the average or weighted average of all acquired ambient temperatures as the outdoor temperature before the response. When the temperature of the area where the outdoor unit is located is used as the ambient temperature of the outdoor unit, the ambient temperatures of multiple outdoor units are almost the same. In this case, only the ambient temperature of one outdoor unit can be measured as the outdoor temperature before the response.

[0082] This application also provides a method for predicting the aggregated responsiveness of multiple air conditioning systems for electricity demand response, such as... Figure 4 As shown, the method includes:

[0083] Step S401 involves predicting the responsive quantities for each of the multiple air conditioning systems participating in this response.

[0084] The method for predicting the responsive quantity of each air conditioning system in this response can be the air conditioning system responsive quantity prediction method for power demand response as described in any of the previous embodiments.

[0085] Step S402 involves summing up all the obtained responsive quantities to obtain the aggregate responsive quantity of the multiple air conditioning systems in this response;

[0086] When summing up all the available responsive quantities, simply sum them up algebraically to obtain the aggregate available responsive quantity for this response.

[0087] In the embodiments of this application, each air conditioning system may be a multi-split air conditioning system, a unit air conditioning system, or other types of air conditioning systems.

[0088] The method for predicting the aggregate responsiveness of multiple air conditioning systems for power demand response as described in this application embodiment can achieve the method for predicting the responsiveness of air conditioning systems for power demand response as described in any of the previous embodiments. Therefore, this method for predicting the aggregate responsiveness of multiple air conditioning systems for power demand response can have the technical effects of the method for predicting the responsiveness of air conditioning systems for power demand response as described in any of the previous embodiments.

[0089] This application also provides a computer-readable storage medium storing one or more programs that can be executed by one or more processors to implement the method for predicting the responsiveness of an air conditioning system for power demand response as described in any of the preceding embodiments.

[0090] This application also provides a predictive device for the responsiveness of an air conditioning system for electricity demand response, such as... Figure 5 As shown, the prediction device includes:

[0091] Memory 501 is configured to store computer-executable instructions;

[0092] Processor 502 is configured to execute the computer-executable instructions to implement the method for predicting the responsiveness of an air conditioning system for power demand response as described in the previous embodiment.

[0093] The air conditioning system aggregate responsiveness prediction device described in this embodiment can realize the air conditioning system responsiveness prediction method for power demand response as described in any of the previous embodiments. Therefore, the air conditioning system aggregate responsiveness prediction device can have the technical effects of the air conditioning system responsiveness prediction method for power demand response as described in any of the previous embodiments.

[0094] This application embodiment also provides a cloud platform for a load aggregator, which is used to send response commands to the air conditioning systems participating in the aggregation and to obtain the operating data of the air conditioning systems, such as... Figure 6 As shown, the cloud platform includes a predictive device 601 for the responsiveness of an air conditioning system to power demand, as described in the previous embodiment; the operating data may include operating power, outdoor temperature, indoor temperature, electricity consumption, etc.

[0095] In this embodiment of the application, the air conditioning system participating in the aggregation may be a multi-split air conditioning system, a unit air conditioning system, or other types of air conditioning systems.

[0096] The cloud platform of the load aggregator described in this application includes a predictive device for the responsiveness of air conditioning systems for power demand response as described in the previous embodiment. Therefore, the cloud platform of the load aggregator can have the technical effects of the predictive device for the responsiveness of air conditioning systems for power demand response as described in the previous embodiment.

[0097] It will be understood by those skilled in the art that all or some of the steps, systems, or apparatuses disclosed above, and their functional modules / units, can be implemented as software, firmware, hardware, or suitable combinations thereof. In hardware implementations, the division between functional modules / units mentioned above does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed collaboratively by several physical components. Some or all components may be implemented as software executed by a processor, such as a digital signal processor or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit (ASIC). Such software may be distributed on a computer-readable medium, which may include computer storage media (or non-transitory media) and communication media (or transient media). As is known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and can be accessed by a computer. Furthermore, it is well known to those skilled in the art that communication media typically contain computer-readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

Claims

1. A method for predicting the responsiveness of an air conditioning system for electricity demand response, comprising: Obtain current and forecast data for the air conditioning system; The current operating data includes the indoor temperature, outdoor temperature, and system operating power of the air conditioning system during the period before the response of this response; the predicted data includes the predicted indoor temperature and outdoor temperature of the air conditioning system during the response period of this response. The system operating power of the air conditioning system during the response period of this response is predicted based on the current operating data, the predicted data, and the response quantity correction coefficient of this response. The predicted responsiveness of the air conditioning system in this response is obtained based on the baseline load of the air conditioning system and the predicted operating power of the system. The response quantity correction coefficient for this response is calculated by inputting at least a portion of the current running data and the predicted data into the calculation model of the response quantity correction coefficient. The indoor predicted temperature is any temperature within the indoor comfort temperature range; The outdoor predicted temperature is determined based on the forecast temperature of the area where the air conditioning system is located during the response period of this response, issued by the meteorological station; or, based on the ambient temperature detected at the outdoor unit of the air conditioning system during the period before the response of this response, and the difference between the forecast temperature of the area where the air conditioning system is located during the response period of this response and the real-time temperature of the area where the air conditioning system is located during the period before the response of this response. The baseline load is the predicted load of the air conditioning system when it is not participating in demand response.

2. The method according to claim 1, characterized in that, In cooling mode, the predicted indoor temperature is equal to the upper limit of the indoor comfort temperature of the air conditioning system; in heating mode, the predicted indoor temperature is equal to the lower limit of the indoor comfort temperature of the air conditioning system.

3. The method according to claim 1, characterized in that, The pre-response period and the response period of the same response must meet some or all of the following conditions: The end time of the pre-response period is the start time of the response period; and The ratio of the duration of the pre-response period to the duration of the response period is greater than or equal to 0.9 and less than or equal to 1.

1.

4. The method according to claim 1, characterized in that, The outdoor temperature of the air conditioning system during the period before the response is determined according to Tb1, and the predicted outdoor temperature Ta2' of the air conditioning system during the response period is determined according to Tb2. or The outdoor temperature of the air conditioning system in the period before the response of this response is determined according to Ts, and the outdoor predicted temperature Ta2' of the air conditioning system in the response period of this response is obtained according to the following formula: Ta2'= Ts+( Tb2 -Tb1); Wherein, Tb1 is the real-time temperature of the area where the air conditioning system is located, as released by the meteorological station, during the period before the response of this response; Tb2 is the forecast temperature of the area where the air conditioning system is located, as released by the meteorological station, during the response period of this response; and Ts is the ambient temperature detected at the outdoor unit of the air conditioning system during the period before the response of this response.

5. The method according to claim 1, characterized in that, The calculation model for the response correction coefficient is a regression model obtained by performing regression analysis on the historical response data of the air conditioning system. The variable to be regressed in the regression model is the response correction coefficient. The independent variables in the regression model include the indoor and outdoor temperatures of the air conditioning system before the response period and the indoor and outdoor temperatures during the response period. The historical response data includes the indoor and outdoor temperatures and system operating power of the air conditioning system before the response period in multiple historical responses, as well as the indoor and outdoor temperatures and system operating power during the response period in multiple historical responses.

6. The method according to claim 5, characterized in that, The step of predicting the system operating power of the air conditioning system during the response period of this response based on the current operating data, the predicted data, and the response quantity correction coefficient of this response includes: Calculate according to the following formula : ; Calculate according to the following formula : ; in, This represents the reduction in system power. The predicted system operating power of the air conditioning system during the response period of this response. , , These are the indoor temperature, outdoor temperature, and system operating power of the air conditioning system during the period prior to this response. , These are the indoor and outdoor predicted temperatures of the air conditioning system during the response period of this response, respectively. This is the response quantity correction factor for this response.

7. The method according to claim 5, characterized in that, The method further includes: The operating data of the air conditioning system during the response period of this response is obtained, including indoor temperature, outdoor temperature and system operating power. After this response is completed, the calculation model of the response quantity correction coefficient is updated based on the operating data of the air conditioning system during the response period of this response.

8. The method according to claim 1, characterized in that, The air conditioning system is a multi-split air conditioning system; The indoor temperature of the multi-split air conditioning system before each response is obtained in the following manner: during the period before response, the indoor temperature of the room where each indoor unit of the multi-split air conditioning system is located is periodically obtained; and the average or weighted average of all obtained indoor temperatures is taken as the indoor temperature before response.

9. A method for predicting aggregate responsiveness of an air conditioning system, comprising: For the multiple air conditioning systems participating in this response, predictions are made according to any one of the methods described in claims 1 to 8 to obtain the responsiveness of each of the multiple air conditioning systems in this response; All the obtained responsive quantities are summed to obtain the aggregate responsive quantity of the multiple air conditioning systems in this response.

10. A computer-readable storage medium storing one or more programs that can be executed by one or more processors to implement the method for predicting the responsiveness of an air conditioning system for power demand response as described in any one of claims 1 to 8.

11. A predictive device for the responsiveness of an air conditioning system for electricity demand response, characterized in that, The prediction device includes: Memory, configured to store computer-executable instructions; A processor configured to execute the computer-executable instructions to implement a method for predicting the responsiveness of an air conditioning system for power demand response as described in any one of claims 1 to 8.

12. A cloud platform for a load aggregator, the cloud platform being used to issue response commands to air conditioning systems participating in the aggregation and to acquire operating data of the air conditioning systems, characterized in that, The cloud platform includes a predictive device for the responsiveness of an air conditioning system as described in claim 11.

Images