CN114992772B - Method, device and storage medium for evaluating adjustable potential of air conditioner temperature control load cluster - Google Patents
Method, device and storage medium for evaluating adjustable potential of air conditioner temperature control load cluster Download PDFInfo
- Publication number
- CN114992772B CN114992772B CN202210701408.6A CN202210701408A CN114992772B CN 114992772 B CN114992772 B CN 114992772B CN 202210701408 A CN202210701408 A CN 202210701408A CN 114992772 B CN114992772 B CN 114992772B
- Authority
- CN
- China
- Prior art keywords
- temperature
- air conditioner
- maximum
- average temperature
- indoor
- 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.)
- Active
Links
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
- F24F11/30—Control or safety arrangements for purposes related to the operation of the system, e.g. for safety or monitoring
-
- 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
- F24F11/50—Control or safety arrangements characterised by user interfaces or communication
- F24F11/61—Control or safety arrangements characterised by user interfaces or communication using timers
-
- 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
- F24F11/62—Control or safety arrangements characterised by the type of control or by internal processing, e.g. using fuzzy logic, adaptive control or estimation of values
- F24F11/63—Electronic processing
- F24F11/64—Electronic processing using pre-stored data
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F2110/00—Control inputs relating to air properties
- F24F2110/10—Temperature
- F24F2110/12—Temperature of the outside air
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S20/00—Management or operation of end-user stationary applications or the last stages of power distribution; Controlling, monitoring or operating thereof
- Y04S20/20—End-user application control systems
- Y04S20/222—Demand response systems, e.g. load shedding, peak shaving
Abstract
The application discloses an adjustable potential evaluation method, an adjustable potential evaluation device and a storage medium of an air conditioner temperature control load cluster, wherein the adjustable potential evaluation method comprises the following steps: acquiring outdoor temperature data and indoor temperature data of an area where a target air conditioner is located within a preset time period; according to the outdoor temperature data and the indoor temperature data in the preset time period, the outdoor average temperature and the indoor average temperature of the target air conditioner in the preset time period are obtained; performing pretreatment operation on the outdoor average temperature and the indoor average temperature in the preset time period; and in the on-line application, determining the maximum adjustable power and the sustainable time of the target air conditioner temperature control load cluster according to the outdoor average temperature and the indoor average temperature after the pretreatment operation through a pre-trained DBN adjustable potential evaluation model. The method can realize online evaluation, can obtain the maximum adjustable power and the sustainable time of the target air conditioner cluster, can enable the evaluation of the air conditioner control load to be more comprehensive, and can effectively ensure real-time performance, accuracy and rapidity.
Description
Technical Field
The invention relates to the technical field of smart grids, in particular to an air conditioner temperature control load cluster adjustable potential evaluation method, an air conditioner temperature control load cluster adjustable potential evaluation device and a storage medium.
Background
As the proportion of the photovoltaic power generation is gradually increased, the photovoltaic permeability of the medium-low voltage distribution network is also higher and higher, and the capacity overload of the photovoltaic grid-connected point can be possibly caused, so that the power supply stability is jeopardized; in addition, when the photovoltaic output is excessive and the power distribution network cannot be naturally consumed, the problem of power quality such as voltage out-of-limit and the like of the power grid is easily caused, and the normal operation of the power grid is influenced, so that the problem of photovoltaic consumption of the low-voltage power distribution network should be emphasized. And with popularization of rural high-power electrical appliances, the temperature-sensitive demand side response resources such as the air conditioner temperature control load have higher correlation with the photovoltaic, and are brought into the potential of system scheduling, and the power fluctuation of a connecting line can be reduced by evaluating the adjustment capability of the electric power used by the air conditioner temperature control load, so that the distributed photovoltaic energy consumption is promoted.
However, the current evaluation of the air conditioning load is not comprehensive enough, two layers of evaluation time or power are lacking, or bidirectional adjustable potential evaluation cannot be given, or a single result depending on a physical simulation model is lacking, the actual load parameter deviation is considered, the evaluation time is limited by the running time of the model, or the load reducing potential of the air conditioning cluster is optimized, so that the online evaluation of the adjustable potential of the air conditioning load cluster is difficult to ensure. For example, in the academic paper of central air conditioner load reduction potential modeling and influence factor analysis of pages 42-52 of volume 40 and 19 of electric power system automation, historical measurement data based on intelligent electric meters is provided, and the measurement data is classified by adopting a K-means algorithm, so that the evaluation of the controllable potential of the air conditioner load under different power utilization modes is realized. The method has the defects that the method is too dependent on the electricity consumption data of the user, can not effectively evaluate and predict the real-time adjustable potential of the air conditioner load on line, and can not meet the real-time requirement of evaluation. The academic paper of the electric power automation equipment, volume 38, phase 5, and pages 227-234, the central air conditioner load direct control strategy and the schedulable potential evaluation thereof propose a load adjustable potential evaluation method applicable to the proposed model by inducing the 3 layers of peak clipping and valley filling, load management and power saving potential. The method has the defects that the willingness degree of the user is expressed in a 0-1 variable form, the elasticity of the willingness of the user is limited, and the potential evaluation is influenced to a certain extent. The academic paper of 699-714 pages of 46 th edition 2 of the power grid technology in 2022 combines a day-ahead scheduling layer to obtain air-conditioning load aggregation power based on an approximate aggregation model, and establishes an air-conditioning load aggregation response potential evaluation model by considering multiple factors such as user thermal comfort and the like, and obtains aggregation response potential by Matlab programming simulation analysis. The method has the defects that the real-time performance and the rapidity of the adjustable potential prediction requirement cannot be met by utilizing Matlab programming simulation analysis only, and the requirement of online evaluation cannot be met. Academic conference paper Forecast of schedulable capacity for thermostatically controlled loads with big data analysis, pages 1-6 of international symposium on Power Electronics for Distributed Generation Systems 2017, predicts schedulable capacity using decision tree models in machine learning, enabling big data based assessment of adjustable potential. The method has the defects that the adopted model is too simple, the prediction capability for an actual sample is limited, and the precision is not high. The patent (Chinese patent publication No. CN 113297799A) of Cong Lin et al (a data-driven air conditioner cluster load demand response potential evaluation method) combines physical characteristics and excitation characteristics to provide a practical application air conditioner cluster demand response potential evaluation method. The disadvantage of this approach is that it is difficult to guarantee timeliness of online application demand response potential assessment, taking into account the time consumed by model operations in the process of physical and excitation properties. The patent (Chinese patent publication No. CN 109243547B) of Chen Xingying and the like (an air conditioner load group demand response potential quantitative evaluation method) propose to accurately evaluate the three of the air conditioner load group demand response quantity, the demand response duration and the indoor average temperature change quantity. The disadvantage of this method is also that in the practical application scenario, the time of the demand response potential evaluation process depends on the running time of the model, and it is difficult to ensure the rapidity of the evaluation result.
In summary, in the prior art, the evaluation of the adjustable potential of the air-conditioning temperature control load cluster is not comprehensive, and the real-time performance and rapidity of the evaluation cannot meet the corresponding requirements.
Disclosure of Invention
Therefore, the technical problem to be solved by the invention is to overcome the defects that the adjustable potential evaluation of the hollow temperature-control load cluster in the prior art is incomplete and the real-time performance and the rapidity do not meet the requirements, so as to provide the adjustable potential evaluation method, the device and the storage medium of the air-conditioning temperature-control load cluster.
In a first aspect, according to an embodiment of the present application, there is provided a method for evaluating adjustable potential of an air conditioner temperature control load cluster, including:
acquiring outdoor temperature data and indoor temperature data of an area where a target air conditioner is located within a preset time period;
according to the outdoor temperature data and the indoor temperature data in the preset time period, the outdoor average temperature and the indoor average temperature of the target air conditioner in the preset time period are obtained;
performing pretreatment operation on the outdoor average temperature and the indoor average temperature in the preset time period;
and in the on-line application, determining the maximum adjustable power and the sustainable time of the target air conditioner temperature control load cluster according to the outdoor average temperature and the indoor average temperature after the pretreatment operation through a pre-trained DBN adjustable potential evaluation model.
Preferably, the training method of the pre-trained DBN adjustable potential evaluation model comprises the following steps:
acquiring set outdoor temperature parameters and corresponding indoor temperature parameters, and acquiring adjustable potential samples of corresponding air conditioner temperature control load clusters by adopting a preset cluster simulation algorithm;
taking a first part of the adjustable potential samples as a training set, taking corresponding outdoor average temperature and indoor average temperature as inputs, taking adjustable power and sustainable time of a temperature control load cluster as outputs, selecting root mean square error and average absolute error as evaluation indexes, training a preset depth confidence network, and determining a corresponding DBN adjustable potential evaluation model as an adjustable potential evaluation model to be tested when the root mean square error and average absolute error meet corresponding requirements;
the second part of the adjustable potential samples is used as a test set, the corresponding outdoor average temperature and indoor average temperature are used as inputs, the adjustable power and the sustainable time of the temperature control load cluster are used as outputs, the decision coefficient is used as an evaluation index, the adjustable potential evaluation model to be tested is tested, and when the decision coefficient meets the corresponding decision coefficient requirement, the trained model is determined to be a pre-trained DBN adjustable potential evaluation model;
The adjustable potential samples of the air conditioner control load cluster comprise the maximum adjustable power of the target air conditioner and the maximum sustainable time of the target air conditioner.
Preferably, the maximum adjustable power includes an upward maximum adjustable power and a downward maximum adjustable power;
the maximum sustainable time includes an upward maximum sustainable time and a downward maximum sustainable time;
the preset cluster simulation algorithm is as follows:
when the indoor average temperature is smaller than the set temperature of the air conditioner (when the temperature of the air conditioner needs to be adjusted upwards), determining the maximum adjustable power of the target air conditioner by adopting a first mathematical model, and determining the maximum sustainable time of the target air conditioner by adopting a second mathematical model;
if the indoor average temperature is greater than the air conditioner set temperature (when the air conditioner temperature is adjusted downwards), determining the maximum adjustable power of the target air conditioner by adopting a third mathematical model, and determining the maximum sustainable time of the target air conditioner by adopting a fourth mathematical model:
the first mathematical model is:
P H ＝P t -P min ；
the second mathematical model is:
the third mathematical model is:
P L ＝P max -P t ；
the fourth mathematical model is:
wherein P is H ，P L The maximum adjustable power when the temperature of the air conditioner is adjusted upwards and the maximum adjustable power when the temperature of the air conditioner is adjusted downwards are respectively, Respectively, the maximum sustainable time when the temperature of the air conditioner is adjusted upwards and the maximum sustainable time when the temperature of the air conditioner is adjusted downwards, P max ，P min Respectively the maximum operating power and the minimum operating power of the air conditioner after temperature adjustment at the moment t, P t Stable running power before changing set temperature for air conditioner at time T t For the indoor average temperature at time T, T max Is the maximum threshold value of temperature regulation, T min Is the minimum threshold value of temperature regulation, T out For the outdoor average temperature, R and C are equivalent thermal resistance and equivalent heat capacity respectively, Q max ，Q min The maximum operation refrigerating capacity and the minimum operation refrigerating capacity of the air conditioner are respectively.
Preferably, the method further comprises:
adopting a sixth mathematical model to calculate the root mean square error between the predicted sample and the actual sample;
adopting a seventh mathematical model to calculate the average absolute error between the predicted sample and the actual sample;
the sixth mathematical model is:
the seventh mathematical model is:
preferably, the method further comprises:
obtaining the decision coefficient;
the determining the decision coefficient includes:
determining a decision coefficient by adopting a fifth mathematical model;
the fifth mathematical model is:
wherein m represents the total number of test set samples, P i Representing the value of the actual sample, Sample values predicted representing deep belief network, < >>Is the average value of the actual sample values.
Preferably, the preprocessing operation is performed on the outdoor average temperature and the indoor average temperature in the preset time period, and the preprocessing operation comprises the rational correction and normalization processing on the outdoor average temperature and the indoor average temperature; wherein:
the rationalizing and correcting the outdoor average temperature data and the indoor average temperature data comprises the following steps:
if the outdoor average temperature T out Less than or equal to the indoor average temperature T ss The sustainable time of the target air conditioner is adjusted to be 2 times of the normal data so as to display the sample specificity; wherein the normal data is the outdoor average temperature T out Is greater than the indoor average temperature T ss Maximum sustainable time of the target air conditioner;
the normalizing process for the outdoor average temperature and the indoor average temperature includes:
all the obtained initial sample data are normalized to be within the interval of 0 to 1, so that the training of a subsequent deep confidence network is facilitated.
Preferably, the pre-trained DBN tunable potential assessment model includes an input layer, a first limited boltzmann machine layer, a second limited boltzmann machine layer, a third limited boltzmann machine layer, a fourth limited boltzmann machine layer, and an output layer.
In a second aspect, according to an embodiment of the present application, there is provided an adjustable potential evaluation device for an air conditioner temperature control load cluster, including:
the acquisition module is used for acquiring outdoor temperature data and indoor temperature data of the area where the target air conditioner is located within a preset time period;
the computing module is used for solving the outdoor average temperature and the indoor average temperature of the target air conditioner in the preset time period according to the outdoor temperature data and the indoor temperature data in the preset time period;
the pretreatment operation module is used for carrying out pretreatment operation on the outdoor average temperature and the indoor average temperature in the preset time period;
and the evaluation module is used for determining the maximum adjustable power and the sustainable time of the target air conditioner according to the pre-trained DBN adjustable potential evaluation model aiming at the outdoor average temperature and the indoor average temperature after the pretreatment operation.
In a third aspect, according to an embodiment of the present application, there is provided an adjustable potential assessment device for an air conditioner temperature control load cluster, including a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program is loaded and executed by the processor to implement the adjustable potential assessment for an air conditioner temperature control load cluster according to any one of the preceding claims.
In a fourth aspect, according to an embodiment of the present application, there is provided a computer readable storage medium storing a computer program, wherein the computer program, when executed by a processor, is configured to implement an adjustable potential assessment of an air conditioner temperature control load cluster according to any one of the preceding claims.
The technical scheme of the invention has the following advantages:
in the embodiment of the application, the outdoor average temperature and the indoor average temperature after the pretreatment operation are used as the input of a pre-trained DBN adjustable potential evaluation model, and the maximum adjustable power and the sustainable time of the target air conditioner are used as the output of the pre-trained DBN adjustable potential evaluation model, so that the maximum adjustable power and the sustainable time of the target air conditioner temperature control load cluster can be obtained directly through the pre-trained DBN adjustable potential evaluation model. According to the scheme, the maximum adjustable power and the sustainable time of the target air conditioner cluster can be obtained through online evaluation, so that the evaluation of the air conditioner control load is comprehensive, and meanwhile, the instantaneity, the accuracy and the rapidity can be effectively ensured.
Further, in the embodiment of the application, a training sample is obtained by performing simulation calculation on the target air-conditioning load cluster in the area, an outdoor average temperature and an indoor average temperature are taken as input, adjustable potential and sustainable time are taken as output, and a deep belief network DBN is trained to obtain a temperature-conditioning load cluster adjustable potential evaluation model based on the DBN; and in the on-line application, determining the maximum adjustable power and the sustainable time of the target air conditioner temperature control load cluster according to the outdoor average temperature and the indoor average temperature after the pretreatment operation through a pre-trained DBN adjustable potential evaluation model. The method can realize online evaluation, can obtain the maximum adjustable power and the sustainable time of the target air conditioner cluster, can enable the evaluation of the air conditioner control load to be comprehensive, and can effectively ensure real-time performance, accuracy and rapidity.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the description of the embodiments or the prior art will be briefly described, and it is obvious that the drawings in the description below are some embodiments of the present invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of an adjustable potential evaluation method of an air conditioner temperature control load cluster according to an embodiment of the present application;
FIG. 2 is a flow chart of a training method of a pre-trained DBN adjustable potential assessment model employed in an embodiment of the present application;
FIG. 3 is a flowchart of a preset cluster simulation algorithm used in an embodiment of the present application;
FIG. 4 is a flow chart of another training method of a pre-trained DBN adjustable potential assessment model used in an embodiment of the present application;
FIG. 5 is a flow chart of yet another training method of a pre-trained DBN adjustable potential assessment model employed in an embodiment of the present application;
FIG. 6 is a schematic structural diagram of a trained DBN adjustable potential assessment model employed in an embodiment of the present application;
FIG. 7 is a waveform diagram of clustering simulation under 1000 air conditioners under one of the temperature conditions in one embodiment of the present application;
FIG. 8 is a graph of online evaluation of the adjustable potential of a corresponding air conditioner temperature control load cluster in one embodiment of the present application;
fig. 9 is a block diagram of an adjustable potential evaluation device of an air conditioner temperature control load cluster according to an embodiment of the present application;
fig. 10 is a block diagram of an adjustable potential evaluation device for an air conditioner temperature control load cluster according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present invention will be made apparent and fully in view of the accompanying drawings, in which some, but not all embodiments of the invention are shown. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. are based on the directions or positional relationships shown in the drawings, are merely for convenience of describing the present invention and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and thus should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
In the description of the present invention, it should be noted that, unless explicitly specified and limited otherwise, the terms "mounted," "connected," and "connected" are to be construed broadly, and may be either fixedly connected, detachably connected, or integrally connected, for example; can be mechanically or electrically connected; the two components can be directly connected or indirectly connected through an intermediate medium, or can be communicated inside the two components, or can be connected wirelessly or in a wired way. The specific meaning of the above terms in the present invention will be understood in specific cases by those of ordinary skill in the art.
In addition, the technical features of the different embodiments of the present invention described below may be combined with each other as long as they do not collide with each other.
Example 1
The embodiment provides an adjustable potential evaluation method for an air conditioner temperature control load cluster, as shown in fig. 1, comprising the following steps:
step S12, acquiring outdoor temperature data and indoor temperature data of a region where a target air conditioner is located within a preset time period;
in this embodiment of the present application, the area where the target air conditioner is located includes an area where the indoor unit is located and an area where the outdoor unit is located, and the temperature data may be collected by using a temperature sensor. It is noted here that the frequency at which the sensor collects temperature data may be set according to actual requirements.
Step S14, according to the outdoor temperature data and the indoor temperature data in a preset time period, the outdoor average temperature and the indoor average temperature of the target air conditioner in the preset time period are obtained;
in the embodiment of the application, after outdoor temperature data and indoor temperature data of a target air conditioner in a preset time period are obtained by adopting a temperature sensor, the outdoor average temperature is obtained according to the outdoor temperature data in the preset time period, and the indoor average temperature is obtained according to the indoor temperature data in the preset time period. Specifically, the outdoor average temperature may be obtained by directly averaging the collected outdoor temperature data, or may be obtained by removing a highest outdoor temperature data and a lowest outdoor temperature data from the collected outdoor temperature data and then averaging the obtained outdoor temperature data. Here, the method for obtaining the indoor average temperature according to the temperature data in the inner chamber in the preset time period is similar to the algorithm for obtaining the outdoor average temperature, and will not be described herein.
S16, preprocessing the outdoor average temperature and the indoor average temperature in the preset time period;
in the embodiment of the application, after the outdoor average temperature and the indoor average temperature are obtained, a preprocessing operation is performed on the outdoor average temperature, wherein the preprocessing operation can be, but is not limited to, and rationalizes correction and normalization. In the application, the pretreatment operation is performed on the indoor average temperature, so that the outdoor average temperature and the indoor average temperature after the pretreatment operation can be directly used as the input of a pre-trained DBN adjustable potential evaluation model.
And S18, determining the maximum adjustable power and the sustainable time of the target air conditioner according to the outdoor average temperature and the indoor average temperature after the pretreatment operation through a pre-trained DBN adjustable potential evaluation model.
In the embodiment of the application, the outdoor average temperature and the indoor average temperature after the pretreatment operation are used as the input of the pre-trained DBN adjustable potential evaluation model, and the maximum adjustable power and the sustainable time of the target air conditioner are used as the output of the pre-trained DBN adjustable potential evaluation model, so that the maximum adjustable power and the sustainable time of the target air conditioner can be obtained directly through the pre-trained DBN adjustable potential evaluation model. The maximum adjustable power and the sustainable time of the target air conditioner can be obtained through online evaluation, so that the evaluation of the air conditioner control load is comprehensive, and the instantaneity and the rapidity can be effectively ensured.
Preferably, the training method of the pre-trained DBN adjustable potential assessment model adopted in step S18 includes:
s22, acquiring set outdoor temperature parameters and corresponding indoor temperature parameters, and acquiring adjustable potential samples of corresponding air conditioner temperature control load clusters by adopting a preset cluster simulation algorithm;
In this embodiment of the present application, the set outdoor temperature parameter and the corresponding indoor temperature parameter may be set according to actual requirements, for example, may be set at equal intervals, that is, the intervals between two adjacent outdoor temperature values are the same, or different temperature intervals may be set, and similarly, the indoor temperature values are the same.
Step S24, taking a first part of the adjustable potential samples as a training set, taking corresponding outdoor average temperature and indoor average temperature as inputs, taking adjustable power and sustainable time of a temperature control load cluster as outputs, selecting root mean square error and average absolute error as evaluation indexes, training a preset depth confidence network, and determining a corresponding DBN adjustable potential evaluation model as an adjustable potential evaluation model to be tested when the root mean square error and average absolute error meet corresponding requirements;
in an embodiment of the present application, three-quarters of samples are selected from the adjustable potential samples as a training set, and mean square error and average absolute error between the measured samples and the actual samples are selected as training indexes, wherein the predicted samples refer to samples obtained through a preset deep confidence network, and the actual samples are samples obtained through a preset simulation algorithm.
Step S26, a second part in the adjustable potential sample is adopted as a test set, corresponding outdoor average temperature and indoor average temperature are adopted as inputs, adjustable power and sustainable time of a temperature control load cluster are adopted as outputs, a decision coefficient is adopted as an evaluation index, the adjustable potential evaluation model to be tested is tested, and when the decision coefficient meets the corresponding decision coefficient requirement, the adjustable potential evaluation model to be tested is determined to be a pre-trained DBN adjustable potential evaluation model;
the adjustable potential samples of the air conditioner control load cluster comprise the maximum adjustable power of the target air conditioner and the maximum sustainable time of the target air conditioner.
In the embodiment of the application, a training sample is obtained by performing simulation calculation on a target air-conditioning control load cluster in the area, an outdoor average temperature and an indoor average temperature are taken as input, adjustable potential and sustainable time are taken as output, and a deep belief network DBN is trained to obtain a pre-trained DBN adjustable potential evaluation model; specifically, a second part of the adjustable potential samples, corresponding set outdoor temperature parameters and corresponding indoor temperature parameters are selected as a test set, the decision coefficients are used as evaluation indexes for testing, and when the decision coefficients meet the corresponding decision coefficient requirements, the corresponding adjustable potential evaluation model to be tested is determined to be a pre-trained DBN adjustable potential evaluation model. In the present application, the remaining quarter samples in the adjustable potential samples and their corresponding set outdoor temperature parameters, and the corresponding indoor temperature parameters are test sets.
In the embodiment of the application, aiming at the set outdoor temperature parameter and the corresponding indoor temperature parameter, a preset cluster simulation algorithm is adopted to obtain an adjustable potential sample of a corresponding air conditioner temperature control load cluster, then three-quarter adjustable potential sample, the corresponding outdoor temperature parameter and the corresponding indoor temperature parameter are selected as test sets, and offline and test is performed on a preset depth confidence network, so that a pre-trained DBN adjustable potential evaluation model meeting requirements is obtained.
Preferably, referring to fig. 3, the preset cluster simulation algorithm involved in step S12 is:
step S121, when the indoor average temperature is smaller than the set temperature of the air conditioner (when the temperature of the air conditioner needs to be adjusted upwards), determining the maximum adjustable power of the target air conditioner by adopting a first mathematical model, and determining the maximum sustainable time of the target air conditioner by adopting a second mathematical model;
step S122, if the indoor average temperature is greater than the air conditioner set temperature (when the air conditioner temperature is adjusted downward), determining the maximum adjustable power of the target air conditioner by using the third mathematical model, and determining the maximum sustainable time of the target air conditioner by using the fourth mathematical model:
the first mathematical model is:
P H ＝P t -P min ；
the second mathematical model is:
The third mathematical model is:
P L ＝P max -P t ；
the fourth mathematical model is:
wherein P is H ，P L The maximum adjustable power when the temperature of the air conditioner is adjusted upwards and the maximum adjustable power when the temperature of the air conditioner is adjusted downwards are respectively,respectively, the maximum sustainable time when the temperature of the air conditioner is adjusted upwards and the maximum sustainable time when the temperature of the air conditioner is adjusted downwards, P max ，P min Respectively the maximum operating power and the minimum operating power of the air conditioner after temperature adjustment at the moment t, P t Stable running power before changing set temperature for air conditioner at time T t For the indoor average temperature at time T, T max Is the maximum threshold value of temperature regulation, T min Is the minimum threshold value of temperature regulation, T out For the outdoor average temperature, R and C are equivalent thermal resistance and equivalent heat capacity respectively, Q max ，Q min The maximum operation refrigerating capacity and the minimum operation refrigerating capacity of the air conditioner are respectively.
In an embodiment of the present application, referring to fig. 4, the method further includes:
step S231, adopting a sixth mathematical model to calculate the root mean square error between the predicted sample and the actual sample;
s232, adopting a seventh mathematical model to calculate the average absolute error between the predicted sample and the actual sample;
further, the sixth mathematical model is:
the seventh mathematical model is:
Preferably, referring to fig. 5, the method further includes:
step S25, obtaining the determination coefficient;
in the embodiment of the application, after the adjustable potential evaluation model to be tested is obtained through training, a preset training set is required to be adopted to test the adjustable potential evaluation model to be tested, so that the maximum adjustable power and the sustainable time of the target air conditioner obtained according to the adjustable potential evaluation model to be tested obtained through training are determined to meet corresponding requirements, and the target air conditioner can be used as the DBN adjustable potential evaluation model to be trained.
Further, in the embodiment of the present application, the outdoor average temperature and the indoor average temperature in the training set are substituted into the adjustable potential evaluation model to be tested to obtain a test sample, then, whether the test sample meets the corresponding requirement is measured by the decision coefficient, and when the probability that the decision coefficients of the test sample set obtained by the sample in the test set and the corresponding sample in the original sample set meet the corresponding requirement meet the preset requirement, the adjustable potential evaluation model to be tested is determined to be the DBN adjustable potential evaluation model trained in advance.
Further, the determining the decision coefficient includes:
determining a decision coefficient by adopting a fifth mathematical model;
Still further, in an embodiment of the present application, the fifth mathematical model is:
wherein m represents the total number of test set samples, P i Representing the value of the actual sample,sample values predicted representing deep belief network, < >>Is the average value of the actual sample values.
The method provided by the embodiment of the application adopts the mathematical model to calculate the decision coefficient, and is quick, accurate and efficient. Meanwhile, the method adopts the decision coefficient collocation test set to measure whether the adjustable potential evaluation model to be tested meets the requirements, the decision coefficient is calculated according to the predicted sample value, the actual sample value and the predicted sample mean value, and the method not only calculates according to the difference between the predicted sample value and the actual sample value, but also more accurately characterizes the proximity degree of the whole sample of the predicted sample and the actual sample, so that the adjustable potential evaluation model to be tested is effectively tested, and further, a more accurate pre-trained DBN adjustable potential evaluation model is determined.
Preferably, in step S16 in the embodiment of the present application, a pretreatment operation is performed on the outdoor average temperature and the indoor average temperature in the preset time period, which specifically means that a rational correction and normalization process are performed on the outdoor average temperature and the indoor average temperature.
Further, the rationalizing the outdoor average temperature data and the indoor average temperature data includes:
if the outdoor average temperature T out Less than or equal to the indoor average temperature T ss The sustainable time of the target air conditioner is adjusted to be 2 times of the normal data so as to display the sample specificity; wherein the normal data is the outdoor average temperature T out Is greater than the indoor average temperature T ss Maximum sustainable time of the target air conditioner; the maximum sustainable time is calculated according to the second mathematical model and the fourth mathematical model, and the specific method can be as follows: if the temperature of the air conditioner is adjusted upwards, bringing the values of the outdoor temperature, the indoor temperature, the set temperature, the refrigerating capacity, the equivalent thermal resistance and the equivalent heat capacity into a second mathematical model for solving; and if the temperature of the air conditioner is adjusted downwards, bringing the values of the outdoor temperature, the indoor temperature, the set temperature, the refrigerating capacity, the equivalent thermal resistance and the equivalent heat capacity into a fourth mathematical model for solving.
Meanwhile, the normalizing the outdoor average temperature and the indoor average temperature includes:
all the obtained initial sample data are normalized to be within the interval of 0 to 1, so that the training of a subsequent deep confidence network is facilitated.
In an embodiment of the present application, referring to fig. 6, the trained DBN adjustable potential assessment model includes an INPUT layer (INPUT), a first boltzmann limited machine layer (RBM 1), a second boltzmann limited machine layer (RBM 2), a third boltzmann limited machine layer (RBM 3), a fourth boltzmann limited machine layer (RBM 4), and an OUTPUT layer (OUTPUT).
The following describes a specific example to determine the beneficial effects of the methods of the present application:
in order to verify the effectiveness of the method, according to an equivalent thermal parameter model of the air conditioner temperature control load, an upward maximum adjustable power of the air conditioner temperature control load and a corresponding upward maximum sustainable time, a downward maximum adjustable power and a corresponding downward maximum sustainable time are obtained, and a simulation algorithm of the aggregate air conditioner temperature control load cluster is obtained.
Taking 1000 air conditioner temperature control load clusters as an example, setting outdoor temperature data to be from 20 ℃ to 45 ℃ and taking 0.2 ℃ as a temperature interval; setting the indoor average temperature to be from 20 ℃ to 28 ℃ and taking 0.5 ℃ as a temperature interval;
assume that the outdoor temperature T is set out Indoor average temperature t=35℃ in Using the first-order equivalent thermal parameter model, samples were collected in 10 hours as the total time scale and one minute as the sample collection time step, i.e., 600 time dimensions. Two temperature thresholds of 28 ℃ and 20 ℃ are selected, the air conditioner set temperature is respectively changed to 28 ℃ and 20 ℃ in t=350 minutes, and the corresponding maximum adjustable power and the corresponding maximum sustainable time of the air conditioner load cluster are calculated. The clustering simulation waveforms of 1000 air conditioners under one temperature condition can be obtained, as shown in fig. 7, and meanwhile the upward maximum adjustable power, the upward sustainable time, the downward maximum adjustable power and the downward maximum sustainable time of the air conditioner cluster under the temperature condition can be calculated. And by analogy, the upward maximum adjustable power, the upward sustainable time, the downward maximum adjustable power and the downward sustainable time of the air conditioning cluster under the combination of different outdoor average temperatures and different indoor average temperatures can be calculated, and 2142 groups of simulation data are finally obtained.
The resulting simulation data is then pre-processed, involving pre-processing operations including, but not limited to, rationalizing modifications to the selected samples and normalization. Wherein, rationalization correction can be: when the outdoor temperature is less than or equal to the set temperature of the air conditioner, the upward sustainable time of the air conditioner tends to infinity at the moment, and when a data sample is processed, the sustainable time of the air conditioner under the condition is adjusted to be 2 times of the normal sustainable time so as to display the specificity of the sample; the normalization process may be: all the obtained initial sample data are normalized to be within the interval of 0 to 1, so that the subsequent deep confidence network training is facilitated. And the integrity and the accuracy of sample data are ensured.
The preprocessed data are divided into training sets and testing sets according to the proportion of 3:1, wherein the training set samples are 1600 groups, and the verification data are 542 groups. The constructed sample data is put into a deep belief network as shown in fig. 6 for offline training.
In order to measure the potential evaluation effect of the deep learning algorithm on the air conditioner temperature control load cluster, defining the RMSE as the root mean square error between a predicted sample and an actual sample, wherein the mathematical model for solving the RMSE is as follows:
defining MAE as the average absolute error between the predicted sample and the actual sample, wherein a mathematical model of MAE is calculated:
Defining R2 as a determination coefficient of a model, wherein a mathematical model of R2 is obtained:
/>
wherein m represents the total number of samples in the test set, P i Representing the value of the actual sample,sample values predicted representing deep belief network, < >>Is practically theAverage of sample values.
And when the two error rates and the decision coefficients meet the corresponding threshold requirements, model training is finished, and the optimal model parameters at the moment can be obtained, so that a pre-trained DBN adjustable potential evaluation model is determined for subsequent use.
The estimated error rate and the decision coefficient are finally obtained as shown in table 1, and satisfy the requirement of the preset threshold value:
table 1 test results of 1000 air conditioner load aggregation models
As can be seen from Table 1, the Root Mean Square Error (RMSE) between the predicted sample and the actual sample and the Mean Absolute Error (MAE) between the predicted sample and the actual sample obtained by training under the DBN model all reach the 10-3 level, and the result accuracy is accurate. Meanwhile, the R2 parameter for measuring the good fitting effect of the model is close to 1, which indicates that the fitting effect of the DBN adjustable potential evaluation model is good.
In order to verify that the DBN adjustable potential evaluation model in the application has better effect, a centralized model is selected for comparison test as follows, and specific test results are shown in the following table:
Table 2 test results of load aggregation of 1000 air conditioners under different training models
/>
Table 2 gives a comparison of the results under the different training models. By comparison, the evaluation performance of the DBN is obviously higher than that of two machine learning models, namely a Support Vector Machine (SVM) and a Decision Tree (DT).
According to the training, the optimal deep confidence model is obtained, and the load aggregator can realize the online evaluation of the adjustable potential of the corresponding air conditioner temperature control load cluster by inputting the current real-time outdoor temperature and indoor average temperature data, as shown in fig. 8.
Example 2
The embodiment of the application also provides an adjustable potential evaluation device of an air conditioner temperature control load cluster, as shown in fig. 9, the device comprises:
an acquiring module 91, configured to acquire outdoor temperature data and indoor temperature data within a preset time period of an area where a target air conditioner is located;
the calculating module 92 is configured to calculate an outdoor average temperature and an indoor average temperature of the target air conditioner in a preset time period according to the outdoor temperature data and the indoor temperature data in the preset time period;
a preprocessing operation module 93, configured to perform a preprocessing operation on an outdoor average temperature and an indoor average temperature within the preset period of time;
The evaluation module 94 is configured to determine, for the outdoor average temperature and the indoor average temperature after the preprocessing operation, the maximum adjustable power and the sustainable time of the target air conditioner through a pre-trained DBN adjustable potential evaluation model.
Example 3
Fig. 10 is a block diagram of an adjustable potential evaluation device of an air-conditioning load cluster according to an embodiment of the present application, where the adjustable potential evaluation device of the air-conditioning load cluster may be a computing device such as a desktop computer, a notebook computer, a palmtop computer, and a cloud server, and the device may include, but is not limited to, a processor and a memory. The adjustable potential evaluation device of the air conditioner temperature control load cluster according to the present embodiment at least includes a processor and a memory, where the memory stores a computer program, and the computer program can be run on the processor, and when the processor executes the computer program, the steps in embodiment 1 are implemented.
The computer program may be divided into one or more modules, which are stored in the memory and executed by a processor to accomplish the present invention, for example. The one or more modules may be a series of computer program instruction segments capable of performing a specific function for describing the execution of the computer program in an adjustable potential assessment device of an air conditioner temperature control load cluster. For example, the computer program may be divided into an acquisition module, a calculation module, a preprocessing operation module and an evaluation module, and the specific functions of each module are as follows:
The acquisition module is used for acquiring outdoor temperature data and indoor temperature data of the area where the target air conditioner is located within a preset time period;
the computing module is used for solving the outdoor average temperature and the indoor average temperature of the target air conditioner in the preset time period according to the outdoor temperature data and the indoor temperature data in the preset time period;
the pretreatment operation module is used for carrying out pretreatment operation on the outdoor average temperature and the indoor average temperature in the preset time period;
and the evaluation module is used for determining the maximum adjustable power and the sustainable time of the target air conditioner according to the pre-trained DBN adjustable potential evaluation model aiming at the outdoor average temperature and the indoor average temperature after the pretreatment operation.
The processor may include one or more processing cores, such as: 4 core processor, 6 core processor, etc. The processor may be implemented in at least one hardware form of DSP (Digital Signal Processing ), FPGA (Field-Programmable Gate Array, field programmable gate array), PLA (Programmable Logic Array ). The processor may also include a main processor, which is a processor for processing data in an awake state, also called a CPU (Central Processing Unit ), and a coprocessor; a coprocessor is a low-power processor for processing data in a standby state. In some embodiments, the processor may also include an AI (Artificial Intelligence ) processor for processing computing operations related to machine learning. The processor is a control center of the adjustable potential evaluation device of the air conditioner temperature control load cluster, and various interfaces and lines are utilized to connect various parts of the adjustable potential evaluation device of the air conditioner temperature control load cluster.
The memory may be used to store the computer program and/or module, and the processor may implement various functions of the adjustable potential assessment device of the air conditioner temperature control load cluster by running or executing the computer program and/or module stored in the memory and invoking data stored in the memory. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data (such as audio data, phonebook, etc.) created according to the use of the handset, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as a hard disk, memory, plug-in hard disk, smart Media Card (SMC), secure Digital (SD) Card, flash Card (Flash Card), at least one disk storage device, memory device, or other volatile solid-state storage device.
It will be understood by those skilled in the art that the apparatus described in this embodiment is merely an example of the adjustable potential evaluation apparatus of the air conditioner temperature control load cluster, and does not constitute a limitation of the adjustable potential evaluation apparatus of the air conditioner temperature control load cluster, and in other embodiments, more or fewer components may be included, or some components may be combined, or different components, for example, the adjustable potential evaluation apparatus of the air conditioner temperature control load cluster may further include an input/output device, a network access device, a bus, and so on. The processor, memory, and peripheral interfaces may be connected by buses or signal lines. The individual peripheral devices may be connected to the peripheral device interface via buses, signal lines or circuit boards. Illustratively, peripheral devices include, but are not limited to: radio frequency circuitry, touch display screens, audio circuitry, and power supplies, among others.
Of course, the adjustable potential assessment device of the air conditioner temperature control load cluster may also include fewer or more components, which is not limited in this embodiment.
Optionally, the present application further provides a computer readable storage medium storing a computer program, which when executed by a processor is configured to implement the steps of the adjustable potential assessment method of the air conditioner temperature control load cluster.
The technical features of the above-described embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above-described embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples merely represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the invention. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application is to be determined by the claims appended hereto.
Claims (8)
1. An adjustable potential evaluation method for an air conditioner temperature control load cluster is characterized by comprising the following steps:
acquiring outdoor temperature data and indoor temperature data of an area where a target air conditioner is located within a preset time period;
according to the outdoor temperature data and the indoor temperature data in the preset time period, the outdoor average temperature and the indoor average temperature of the target air conditioner in the preset time period are obtained;
performing pretreatment operation on the outdoor average temperature and the indoor average temperature in the preset time period;
when the method is applied online, according to the outdoor average temperature and the indoor average temperature after pretreatment operation, the maximum adjustable power and the sustainable time of the target air conditioner temperature control load cluster are determined through a pre-trained DBN adjustable potential evaluation model;
the training method of the pre-trained DBN adjustable potential evaluation model comprises the following steps:
acquiring set outdoor temperature parameters and corresponding indoor temperature parameters, and acquiring adjustable potential samples of corresponding air conditioner temperature control load clusters by adopting a preset cluster simulation algorithm;
taking a first part of the adjustable potential samples as a training set, taking corresponding outdoor average temperature and indoor average temperature as inputs, taking adjustable power and sustainable time of a temperature control load cluster as outputs, selecting root mean square error and average absolute error as evaluation indexes, training a preset depth confidence network, and determining a corresponding DBN adjustable potential evaluation model as an adjustable potential evaluation model to be tested when the root mean square error and average absolute error meet corresponding requirements;
The second part of the adjustable potential samples is used as a test set, the corresponding outdoor average temperature and indoor average temperature are used as inputs, the adjustable power and the sustainable time of the temperature control load cluster are used as outputs, the decision coefficient is used as an evaluation index, the adjustable potential evaluation model to be tested is tested, and when the decision coefficient meets the corresponding decision coefficient requirement, the trained model is determined to be a pre-trained DBN adjustable potential evaluation model;
the adjustable potential samples of the air conditioner control load clusters comprise the maximum adjustable power of a target air conditioner and the maximum sustainable time of the target air conditioner;
the maximum adjustable power includes an upward maximum adjustable power and a downward maximum adjustable power;
the maximum sustainable time includes an upward maximum sustainable time and a downward maximum sustainable time;
the preset cluster simulation algorithm is as follows:
when the indoor average temperature is smaller than the set temperature of the air conditioner and the temperature of the air conditioner needs to be adjusted upwards, determining the maximum adjustable power of the target air conditioner by adopting a first mathematical model, and determining the maximum sustainable time of the target air conditioner by adopting a second mathematical model;
If the indoor average temperature is greater than the set temperature of the air conditioner, and the temperature of the air conditioner is adjusted downwards, determining the maximum adjustable power of the target air conditioner by adopting a third mathematical model, and determining the maximum sustainable time of the target air conditioner by adopting a fourth mathematical model:
the first mathematical model is:
；
the second mathematical model is:
；
the third mathematical model is:
；
the fourth mathematical model is:
；
wherein, the liquid crystal display device comprises a liquid crystal display device,，/>the maximum adjustable power when the temperature of the air conditioner is adjusted upwards and the maximum adjustable power when the temperature of the air conditioner is adjusted downwards are respectively +.>，/>Maximum sustainable time when the temperature of the air conditioner is adjusted upwards and maximum sustainable time when the temperature of the air conditioner is adjusted downwards respectively,/->，/>The maximum operating power and the minimum operating power of the air conditioner after temperature adjustment at the moment t are respectively +.>Stable operating power before changing the set temperature for the air conditioner at time t, +.>For the mean indoor temperature at time t>For maximum threshold value of temperature regulation, +.>Is the minimum threshold for temperature regulation, +.>Is the outdoor average temperature>，/>Equivalent thermal resistance and equivalent heat capacity respectively, +.>，/>The maximum operation refrigerating capacity and the minimum operation refrigerating capacity of the air conditioner are respectively.
2. The method according to claim 1, characterized in that the method further comprises:
Adopting a sixth mathematical model to calculate the root mean square error between the predicted sample and the actual sample;
adopting a seventh mathematical model to calculate the average absolute error between the predicted sample and the actual sample;
the sixth mathematical model is:
；
the seventh mathematical model is:
；
where m represents the total number of test set samples,representing the actual sample value, +.>Sample values predicted representing deep belief network, < >>Is the average value of the actual sample values.
3. The method according to claim 1, characterized in that the method further comprises:
obtaining the decision coefficient;
the determining the decision coefficient includes:
determining a decision coefficient by adopting a fifth mathematical model;
the fifth mathematical model is:
where m represents the total number of test set samples,representing the actual sample value, +.>Sample values predicted representing deep belief network, < >>Is the average value of the actual sample values.
4. The method according to claim 1, wherein the preprocessing operation is performed on the outdoor average temperature and the indoor average temperature in the preset time period, and the preprocessing operation comprises the rational correction and normalization processing on the outdoor average temperature and the indoor average temperature; wherein:
the rationalizing and correcting the outdoor average temperature data and the indoor average temperature data comprises the following steps:
If the outdoor average temperature isLess than or equal to the indoor average temperature->The sustainable time of the target air conditioner is adjusted to be 2 times of the normal data so as to display the sample specificity; wherein the normal data is outdoor average temperature +.>Is greater than the indoor average temperature->Maximum sustainable time of the target air conditioner;
the normalizing process for the outdoor average temperature and the indoor average temperature includes:
all the obtained initial sample data are normalized to be within the interval of 0 to 1, so that the training of a subsequent deep confidence network is facilitated.
5. The method of claim 1, wherein the pre-trained DBN tunable potential assessment model comprises an input layer, a first restricted boltzmann machine layer, a second restricted boltzmann machine layer, a third restricted boltzmann machine layer, a fourth restricted boltzmann machine layer, and an output layer.
6. An adjustable potential evaluation device for an air conditioner temperature control load cluster, comprising:
the acquisition module is used for acquiring outdoor temperature data and indoor temperature data of the area where the target air conditioner is located within a preset time period;
the computing module is used for solving the outdoor average temperature and the indoor average temperature of the target air conditioner in the preset time period according to the outdoor temperature data and the indoor temperature data in the preset time period;
The pretreatment operation module is used for carrying out pretreatment operation on the outdoor average temperature and the indoor average temperature in the preset time period;
the evaluation module is used for determining the maximum adjustable power and the sustainable time of the target air conditioner according to the outdoor average temperature and the indoor average temperature after the pretreatment operation through a pre-trained DBN adjustable potential evaluation model;
the training method of the pre-trained DBN adjustable potential evaluation model comprises the following steps:
acquiring set outdoor temperature parameters and corresponding indoor temperature parameters, and acquiring adjustable potential samples of corresponding air conditioner temperature control load clusters by adopting a preset cluster simulation algorithm;
taking a first part of the adjustable potential samples as a training set, taking corresponding outdoor average temperature and indoor average temperature as inputs, taking adjustable power and sustainable time of a temperature control load cluster as outputs, selecting root mean square error and average absolute error as evaluation indexes, training a preset depth confidence network, and determining a corresponding DBN adjustable potential evaluation model as an adjustable potential evaluation model to be tested when the root mean square error and average absolute error meet corresponding requirements;
The second part of the adjustable potential samples is used as a test set, the corresponding outdoor average temperature and indoor average temperature are used as inputs, the adjustable power and the sustainable time of the temperature control load cluster are used as outputs, the decision coefficient is used as an evaluation index, the adjustable potential evaluation model to be tested is tested, and when the decision coefficient meets the corresponding decision coefficient requirement, the trained model is determined to be a pre-trained DBN adjustable potential evaluation model;
the adjustable potential samples of the air conditioner control load clusters comprise the maximum adjustable power of a target air conditioner and the maximum sustainable time of the target air conditioner;
the maximum adjustable power includes an upward maximum adjustable power and a downward maximum adjustable power;
the maximum sustainable time includes an upward maximum sustainable time and a downward maximum sustainable time;
the preset cluster simulation algorithm is as follows:
when the indoor average temperature is smaller than the set temperature of the air conditioner and the temperature of the air conditioner needs to be adjusted upwards, determining the maximum adjustable power of the target air conditioner by adopting a first mathematical model, and determining the maximum sustainable time of the target air conditioner by adopting a second mathematical model;
If the indoor average temperature is greater than the set temperature of the air conditioner, and the temperature of the air conditioner is adjusted downwards, determining the maximum adjustable power of the target air conditioner by adopting a third mathematical model, and determining the maximum sustainable time of the target air conditioner by adopting a fourth mathematical model:
the first mathematical model is:
；
the second mathematical model is:
；
the third mathematical model is:
；
the fourth mathematical model is:
；
wherein, the liquid crystal display device comprises a liquid crystal display device,，/>the maximum adjustable power when the temperature of the air conditioner is adjusted upwards and the maximum adjustable power when the temperature of the air conditioner is adjusted downwards are respectively +.>，/>Maximum sustainable time when the temperature of the air conditioner is adjusted upwards and maximum sustainable time when the temperature of the air conditioner is adjusted downwards respectively,/->，/>The maximum operating power and the minimum operating power of the air conditioner after temperature adjustment at the moment t are respectively +.>Stable operating power before changing the set temperature for the air conditioner at time t, +.>For the mean indoor temperature at time t>For maximum threshold value of temperature regulation, +.>Is the minimum threshold for temperature regulation, +.>Is the outdoor average temperature>，/>Equivalent thermal resistance and equivalent heat capacity respectively, +.>，/>The maximum operation refrigerating capacity and the minimum operation refrigerating capacity of the air conditioner are respectively.
7. An adjustable potential evaluation device of an air conditioner temperature control load cluster, comprising a processor, a memory and a computer program stored in the memory and executable on the processor, characterized in that the computer program is loaded and executed by the processor to implement the adjustable potential evaluation method of an air conditioner temperature control load cluster according to any one of claims 1-5.
8. A computer readable storage medium storing a computer program, characterized in that the computer program, when executed by a processor, is adapted to implement the adjustable potential assessment method of an air conditioner temperature controlled load cluster according to any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210701408.6A CN114992772B (en) | 2022-06-20 | 2022-06-20 | Method, device and storage medium for evaluating adjustable potential of air conditioner temperature control load cluster |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210701408.6A CN114992772B (en) | 2022-06-20 | 2022-06-20 | Method, device and storage medium for evaluating adjustable potential of air conditioner temperature control load cluster |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114992772A CN114992772A (en) | 2022-09-02 |
| CN114992772B true CN114992772B (en) | 2023-07-28 |
Family
ID=83037452
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210701408.6A Active CN114992772B (en) | 2022-06-20 | 2022-06-20 | Method, device and storage medium for evaluating adjustable potential of air conditioner temperature control load cluster |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114992772B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115829786B (en) * | 2023-02-16 | 2023-04-28 | 国网浙江省电力有限公司金华供电公司 | Power grid response adjusting method based on air conditioner load |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105841300A (en) * | 2016-03-31 | 2016-08-10 | 东南大学 | Modeling and controlling strategy for central air conditioner with fresh air system |
| KR101875488B1 (en) * | 2018-03-22 | 2018-07-06 | 윤홍익 | Method and system for automatic controlling of air conditioner by using an artificial intelligence |
| CN108361927A (en) * | 2018-02-08 | 2018-08-03 | 广东美的暖通设备有限公司 | A kind of air-conditioner control method, device and air conditioner based on machine learning |
| CN109695944A (en) * | 2018-11-29 | 2019-04-30 | 中国汽车工业工程有限公司 | A kind of control method of the coating fresh air conditioner based on multi-model deep learning |
| CN111832593A (en) * | 2019-04-23 | 2020-10-27 | 中国电力科学研究院有限公司 | Response potential evaluation method and system for cluster variable frequency air conditioner |
| CN112628956A (en) * | 2020-12-24 | 2021-04-09 | 华中科技大学 | Water chilling unit load prediction control method and system based on edge cloud cooperative framework |
| CN113991655A (en) * | 2021-10-28 | 2022-01-28 | 国网上海市电力公司 | Method, device and medium for evaluating load aggregation demand response potential of fixed-frequency air conditioner |
| WO2022039400A1 (en) * | 2020-08-20 | 2022-02-24 | 삼성전자주식회사 | Electronic device and control method therefor |
| CN114186393A (en) * | 2021-11-12 | 2022-03-15 | 国网浙江省电力有限公司营销服务中心 | Variable frequency air conditioner cluster response capability assessment method and system |
-
2022
- 2022-06-20 CN CN202210701408.6A patent/CN114992772B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105841300A (en) * | 2016-03-31 | 2016-08-10 | 东南大学 | Modeling and controlling strategy for central air conditioner with fresh air system |
| CN108361927A (en) * | 2018-02-08 | 2018-08-03 | 广东美的暖通设备有限公司 | A kind of air-conditioner control method, device and air conditioner based on machine learning |
| KR101875488B1 (en) * | 2018-03-22 | 2018-07-06 | 윤홍익 | Method and system for automatic controlling of air conditioner by using an artificial intelligence |
| CN109695944A (en) * | 2018-11-29 | 2019-04-30 | 中国汽车工业工程有限公司 | A kind of control method of the coating fresh air conditioner based on multi-model deep learning |
| CN111832593A (en) * | 2019-04-23 | 2020-10-27 | 中国电力科学研究院有限公司 | Response potential evaluation method and system for cluster variable frequency air conditioner |
| WO2022039400A1 (en) * | 2020-08-20 | 2022-02-24 | 삼성전자주식회사 | Electronic device and control method therefor |
| CN112628956A (en) * | 2020-12-24 | 2021-04-09 | 华中科技大学 | Water chilling unit load prediction control method and system based on edge cloud cooperative framework |
| CN113991655A (en) * | 2021-10-28 | 2022-01-28 | 国网上海市电力公司 | Method, device and medium for evaluating load aggregation demand response potential of fixed-frequency air conditioner |
| CN114186393A (en) * | 2021-11-12 | 2022-03-15 | 国网浙江省电力有限公司营销服务中心 | Variable frequency air conditioner cluster response capability assessment method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114992772A (en) | 2022-09-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Sanandaji et al. | Improved battery models of an aggregation of thermostatically controlled loads for frequency regulation | |
| Luo et al. | Demand flexibility of residential buildings: definitions, flexible loads, and quantification methods | |
| CN103017290A (en) | Air conditioner electric energy control device and air conditioner electric energy management method | |
| CN110380444B (en) | Capacity planning method for distributed wind power orderly access to power grid under multiple scenes based on variable structure Copula | |
| CN107525964B (en) | Non-invasive load identification method and device based on fusion decision | |
| CN112182720B (en) | Building energy consumption model evaluation method based on building energy management application scene | |
| CN114992772B (en) | Method, device and storage medium for evaluating adjustable potential of air conditioner temperature control load cluster | |
| Li et al. | Coordinated state‐estimation method for air‐conditioning loads to provide primary frequency regulation service | |
| Alden et al. | Artificial intelligence method for the forecast and separation of total and hvac loads with application to energy management of smart and nze homes | |
| CN110969306A (en) | Power distribution low-voltage distribution area load prediction method and device based on deep learning | |
| CN107516902B (en) | Real-time coordination control method for multiple interruptible loads considering market operation rules | |
| Ding et al. | Individual nonparametric load estimation model for power distribution network planning | |
| CN116544934B (en) | Power scheduling method and system based on power load prediction | |
| AU2016324351B2 (en) | Power analyser and method for the use thereof | |
| CN105739308B (en) | Power optimization control method and system applied to temperature control electric appliance | |
| CN117091242A (en) | Evaluation method, temperature setting method and system for air conditioner temperature control load cluster | |
| CN109586309B (en) | Power distribution network reactive power optimization method based on big data free entropy theory and scene matching | |
| CN116937569A (en) | Intelligent energy storage method and device for photovoltaic power generation and electronic equipment | |
| CN111476400A (en) | Circuit fault prediction method, device, equipment and computer readable medium | |
| CN116595383A (en) | Intelligent cooling method for storage unit of data center | |
| CN115051374A (en) | Control method and device for electric heating equipment to participate in electric power peak regulation and storage medium | |
| CN108917134A (en) | A kind of body-sensing air quantity adjusting method, device and air conditioner | |
| Wang et al. | Control strategies of large-scale residential air conditioning loads participating in demand response programs | |
| CN110322063A (en) | A kind of power consumption simulated prediction method and storage medium | |
| Ma et al. | Controller design and parameter optimization of aggregated thermostatically controlled loads for frequency regulation |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |