CN111179108A - Method and device for predicting power consumption - Google Patents
Method and device for predicting power consumption Download PDFInfo
- Publication number
- CN111179108A CN111179108A CN201811339840.5A CN201811339840A CN111179108A CN 111179108 A CN111179108 A CN 111179108A CN 201811339840 A CN201811339840 A CN 201811339840A CN 111179108 A CN111179108 A CN 111179108A
- Authority
- CN
- China
- Prior art keywords
- data
- power consumption
- training
- factor
- prediction model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
Abstract
The invention discloses a method and a device for predicting power consumption. Wherein, the method comprises the following steps: acquiring factor data of a target type, wherein the factor data is used for expressing data influencing the electricity consumption of the target air-conditioning system, and the target type is determined according to the influence degree of various types of factor data on the electricity consumption of the target air-conditioning system; acquiring a power consumption prediction model; and predicting the power consumption of the target air conditioning system based on the power consumption prediction model according to the factor parameters of the target type. The invention solves the technical problem that the accurate prediction of the electric energy consumption for the air conditioner of the building is difficult in the prior art.
Description
Technical Field
The invention relates to the field of air conditioners, in particular to a method and a device for predicting power consumption.
Background
With the continuous increase of global economy, energy shortage and environmental pressure are increasingly serious, the problems of reducing energy waste and protecting the environment become important, the unit area energy consumption of large public buildings is more than 10 times higher than that of residential buildings, and the research on an energy consumption prediction system aiming at energy conservation and consumption reduction is carried out under the environment of increasingly tense energy supply and increasingly serious environmental pollution, so that the important significance is achieved. In order to improve the energy consumption management efficiency of large public buildings, not only historical energy consumption data need to be monitored and analyzed, but also future energy consumption of the buildings need to be predicted, energy consumption prediction results are analyzed, abnormal energy consumption data are found in time, and guidance directions are provided for building energy conservation.
During the working operation of large public buildings, the pre-estimation of energy consumption data in a certain period of time in the future is very important for the energy consumption supervision and analysis of the whole building. However, the factors influencing the energy consumption of the large public buildings are many, and the future energy consumption is difficult to predict accurately.
Aiming at the problem that the electric energy consumption for the air conditioner of the building is difficult to accurately predict in the prior art, no effective solution is provided at present.
Disclosure of Invention
The embodiment of the invention provides a method and a device for predicting power consumption, which are used for at least solving the technical problem that the power consumption for air conditioning of a building is difficult to predict accurately in the prior art.
According to an aspect of an embodiment of the present invention, there is provided a method for predicting power consumption, including: acquiring factor data of a target type, wherein the factor data is used for expressing data influencing the electricity consumption of the target air-conditioning system, and the target type is determined according to the influence degree of various types of factor data on the electricity consumption of the target air-conditioning system; acquiring a power consumption prediction model; and predicting the power consumption of the target air conditioning system based on the power consumption prediction model according to the factor parameters of the target type.
Further, before obtaining factor data of the target type, determining the target type, wherein the step of determining the target type includes: acquiring historical electricity consumption data and various factor data of a target air conditioning system; sorting the influence degrees of various types on the electricity consumption energy data of the target air conditioning system according to various types of factor data through historical electricity consumption energy data and various types of factor data; under the condition of sorting according to the influence degree from big to small, determining the first N types as target types, wherein N is an integer greater than 1; and under the condition of sorting according to the influence degrees from small to large, determining the last M types as target types, wherein M is an integer larger than 1.
Further, before obtaining the factor data of the target type, constructing a power consumption prediction model, wherein the constructing of the power consumption prediction model comprises: acquiring sample data, wherein the sample data comprises historical factor data of a target type and power consumption data corresponding to the historical factor data; and training the preset initial model through the sample data to obtain the power consumption prediction model.
Further, the initial model is preset to be a radial basis function neural network model.
Further, after the sample data is acquired, preprocessing the sample data, wherein the preprocessing includes any one or more of the following: data cleaning, data integration, data conversion and data reduction; training a preset initial model through sample data to obtain a power consumption prediction model, comprising: and training the preset initial model through the preprocessed sample data to obtain the power consumption prediction model.
Further, the sample data includes: training sample data and test sample data, and training a preset initial model through the training sample data to obtain a training result; testing the training result through the test sample data; and if the test is passed, determining the training result as a power consumption prediction model, and if the test is not passed, continuing training on the basis of the training result.
Further, inputting historical factor data in the test sample data to a training result to obtain a prediction result output by the training result; acquiring a root mean square error of the power consumption data corresponding to the prediction result and the test sample data; and determining whether the training result passes the test according to the root mean square error.
Further, correcting the network parameters in the training result through the root mean square error; and determining the corrected training result as a power consumption prediction model.
According to an aspect of an embodiment of the present invention, there is provided an apparatus for predicting power consumption, including: the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring factor data of a target type, the factor data is used for representing data influencing the power consumption of the target air conditioning system, and the target type is determined according to the influence degree of various types of factor data on the power consumption of the target air conditioning system; the second acquisition module is used for acquiring the power consumption prediction model; and the prediction module is used for predicting the power consumption of the target air conditioning system based on the power consumption prediction model according to the factor parameters of the target type.
According to an aspect of the embodiments of the present invention, there is provided a storage medium including a stored program, wherein when the program is executed, a device in which the storage medium is located is controlled to execute the power consumption prediction method according to any one of claims 1 to 8.
According to an aspect of the embodiments of the present invention, there is provided a processor for executing a program, wherein the program executes the prediction method of power consumption according to any one of claims 1 to 8.
In the embodiment of the invention, factor data of a target type corresponding to the power consumption of the target air-conditioning system is obtained, wherein the target type determines the influence degree of the target type on the power consumption of the target air-conditioning system according to various types of factor data, a power consumption prediction model is obtained, and the power consumption of the target air-conditioning system is predicted based on the power consumption prediction model according to the factor parameters of the target type. In the above scheme, the factor data for predicting the power consumption is the factor data of the target type, and the target type is determined according to the influence degree of the various types of factor data on the power consumption of the target air conditioning system, so that the types of the factor data for operation can be reduced on the basis of ensuring the accuracy degree of prediction, thereby reducing the operation resources used in operation, improving the operation speed, and further solving the technical problem that the accurate prediction on the power consumption for air conditioning of the building is difficult in the prior art.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:
fig. 1 is a flowchart of a prediction method of power consumption according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a power consumption prediction model constructed according to an embodiment of the present application; and
fig. 3 is a schematic diagram of a prediction apparatus of power consumption according to an embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Example 1
In accordance with an embodiment of the present invention, there is provided an embodiment of a method for predicting power consumption, it is noted that the steps illustrated in the flowchart of the drawings may be performed in a computer system such as a set of computer executable instructions and that, although a logical order is illustrated in the flowchart, in some cases the steps illustrated or described may be performed in an order different than that illustrated herein.
Fig. 1 is a flowchart of a prediction method of power consumption according to an embodiment of the present invention, as shown in fig. 1, the method including the steps of:
and S102, acquiring factor data of a target type, wherein the factor data is used for expressing data influencing the electricity consumption of the target air conditioning system, and the target type determines the influence degree of the various types of factor data on the electricity consumption of the target air conditioning system.
Specifically, the target air conditioning system may be a central air conditioning system applied to a large building, the factor data may be of various types, and the target type may be one or more types having a large influence on power consumption of the target air conditioning system.
In an alternative embodiment, the factor data types may include: the building system comprises a building factor, an environmental factor and an artificial factor, wherein the building factor can comprise parameters such as building area and building height, the environmental factor can comprise parameters such as indoor and outdoor ambient temperature, ambient humidity and outdoor wind power, and the artificial factor can comprise the number of people or the density of people in the building.
The target type may be set empirically, for example, the user considers that the construction factor and the environmental factor have a relatively important influence on the power consumption of the target air conditioning system, and thus the construction factor and the environmental factor may be set as the target type; for another example, the user considers that the building area in the building factor and the person density in the human factor have a significant influence on the power consumption of the target air conditioning system, and thus can set the building area in the building factor and the person density in the human factor as the target types.
In an alternative embodiment, the target type may also be analyzed from historical data.
And step S104, acquiring a power consumption prediction model.
The power consumption prediction model may be a neural network model for predicting power consumption of the target air conditioning system in a future preset time period. In an alternative embodiment, the power consumption prediction model may be obtained by training a neural network model using historical data.
And S106, predicting the power consumption of the target air conditioning system based on the power consumption prediction model according to the factor parameters of the target type.
Specifically, the power consumption may be represented by parameters such as unit power consumption, total power consumption in a preset time period, or power consumption. In the above steps, the factor parameters of the target type are used as input data of the power consumption prediction model, and an output result of the power consumption prediction model is obtained and used for the power consumption of the target air conditioning system.
In an optional embodiment, a user determines a target type building parameter and an environmental parameter, and when power consumption prediction is performed, the building parameter and the environmental parameter are collected and input into the power consumption prediction model, so that a prediction result of the power consumption prediction model is obtained.
The obtained prediction result of the power consumption and energy consumption can guide the subsequent energy-saving work of the air conditioner, and the abnormity of the energy consumption can be found in time by analyzing the prediction result of the power consumption and energy consumption.
As can be seen from the above, in the embodiment of the present application, the factor data of the target type corresponding to the power consumption of the target air conditioning system is obtained, wherein the influence degree of the target type on the power consumption of the target air conditioning system is determined according to the multiple types of factor data, the power consumption prediction model is obtained, and the power consumption of the target air conditioning system is predicted based on the power consumption prediction model according to the factor parameters of the target type. In the above scheme, the factor data for predicting the power consumption is the factor data of the target type, and the target type is determined according to the influence degree of the various types of factor data on the power consumption of the target air conditioning system, so that the types of the factor data for operation can be reduced on the basis of ensuring the accuracy degree of prediction, thereby reducing the operation resources used in operation, improving the operation speed, and further solving the technical problem that the accurate prediction on the power consumption for air conditioning of the building is difficult in the prior art.
As an alternative embodiment, before obtaining the factor data of the target type, the method further comprises: determining a target type, wherein the step of determining the target type comprises: acquiring historical electricity consumption data and various factor data of a target air conditioning system; sorting the influence degrees of various types on the electricity consumption energy data of the target air conditioning system according to various types of factor data through historical electricity consumption energy data and various types of factor data; under the condition of sorting according to the influence degree from big to small, determining the first N types as target types, wherein N is an integer greater than 1; and under the condition of sorting according to the influence degrees from small to large, determining the last M types as target types, wherein M is an integer larger than 1.
Specifically, the historical electricity consumption energy consumption data may be electricity consumption energy consumption data in the last year, and taking the current date of 2018, 5, month and 1 as an example, a time period from 2017, 4, month and 30 to 2018, 4, month and 30 may be selected as the historical time period, and the electricity consumption energy consumption data in the time period is the historical electricity consumption energy data.
Besides the electricity consumption data, the scheme also acquires various types of factor data in the same historical time period. The target type of factor data is one or more of the above-described types of factor data.
The M can be equal to N, namely M or N types with the largest influence degree are selected no matter the types are sorted from large to small or from small to large according to the influence degree.
In an optional embodiment, the number of the target types is set to be L, and the influence magnitude ordering can be performed on the factor data of each type through an intelligent orthogonal experiment, so that an analysis result of the factor data of each type is obtained. The top L types are taken from the sorted results as the target types described above.
As an alternative embodiment, before obtaining the factor data of the target type, the method further comprises: the method comprises the following steps of constructing a power consumption prediction model, wherein the construction of the power consumption prediction model comprises the following steps: acquiring sample data, wherein the sample data comprises historical factor data of a target type of a target air conditioning system and power consumption data corresponding to the historical factor data; and training the preset initial model through the sample data to obtain the power consumption prediction model.
In an alternative embodiment, the historical factor data may also be historical factor data in the last year, and since one or more target types having the greatest influence on the power consumption of the target air conditioning system have been determined, the sample data may be constructed only with the historical factor data of the target type. For example, taking an office building as an example, the time periods from 30 days 4 and 30 days 2017 to 30 days 4 and 30 days 2018 can be classified according to the working time period and the rest time period, historical factor data of the target type and power consumption data in the working time period and power consumption data in the hour in each hour in the working time period are acquired, historical factor data of the target type and power consumption data in the hour in each hour in the rest time period are acquired, the two data are used as sample data, the initial model is trained, network parameters in the model are adjusted, and therefore the power consumption prediction model is obtained.
As an alternative embodiment, the initial model is a radial basis function neural network model.
The Radial Basis Function neural network model is an RBF (Radial Basis Function) neural network model, the RBF neural network model is used as an initial neural network model, the initial neural network model has the optimal approximation performance and the global optimal characteristic which are not possessed by other forward networks, the structure is simple, the training speed is high, and the efficiency of the training model can be improved.
As an optional embodiment, after obtaining the sample data, the method further includes: preprocessing the sample data, wherein the preprocessing comprises any one or more of the following steps: data cleaning, data integration, data conversion and data reduction; training a preset initial model through sample data to obtain a power consumption prediction model, comprising: and training the preset initial model through the preprocessed sample data to obtain the power consumption prediction model.
In the scheme, the data which are directly collected are preprocessed to arrange the data, and the cleaning data are used for eliminating the data which do not accord with the preset rule in the sample data; the data reduction is used for reducing part of data according to a preset reduction mode under the condition that the data is more; the data integration is used for combining various directly acquired data to obtain data required by the training model; data conversion is used for converting directly acquired data into data required in sample data, for example, directly acquired artificial data is the flow of people per hour, and the flow of people may need to be converted into the density of people through data conversion.
As an alternative embodiment, the sample data includes: training sample data and test sample data, training a preset initial model through the sample data to obtain a power consumption prediction model, and the method comprises the following steps: training a preset initial model through training sample data to obtain a training result; testing the training result through the test sample data; and if the test is passed, determining the training result as a power consumption prediction model, and if the test is not passed, continuing training on the basis of the training result.
In the scheme, a power consumption prediction model is established according to sample data obtained after preprocessing, the sample data is divided into a training data set (namely the training sample data) and a test data set (test sample data) based on an RBF neural network artificial intelligence algorithm, the model is trained by the training set data, and the test set data is subjected to result testing, so that the final power consumption prediction model is obtained.
If the training passes the test, the error of the prediction result is small when the training result is used for prediction, and if the training result does not pass the test, the error of the prediction result is still large when the training result is used for prediction, so that a more accurate result is difficult to obtain.
The reason that the training result is failed to pass the test is that the accuracy of the network parameters of the training result is low, so that training is performed on the basis of the training result to obtain a more accurate power consumption prediction model.
In continuing training based on the training result, the training sample data used may be different from the training sample data used in the previous training.
As an alternative embodiment, the testing the training result obtained by training through the test sample data includes: inputting historical factor data in the test sample data into the training result to obtain a prediction result output by the training result; acquiring a root mean square error of the power consumption data corresponding to the prediction result and the test sample data; and determining whether the training result passes the test according to the root mean square error.
Specifically, the above scheme judges the effect of the model according to the magnitude of RMSE (Mean Square Error). In an optional embodiment, if the root mean square error between the prediction result and the actual power consumption data is greater than a preset value, it indicates that the prediction effect of the current training result is not accurate enough, and therefore the test is determined not to pass; if the root mean square error between the prediction result and the actual power consumption data is smaller than or equal to the preset value, the current training prediction effect is more accurate, and therefore the test can be determined to be passed.
As an alternative embodiment, if the test passes, the training result is determined to be the power consumption prediction model, including: correcting the network parameters in the training result through the root mean square error; and determining the corrected training result as a power consumption prediction model.
And on the basis, in order to further improve the accuracy of the training result, network parameters in the training result can be corrected through a root mean square error, so that a predicted value of the training result can continuously approach an expected value, and a final power consumption prediction model is obtained.
After the power consumption and energy consumption of the target air conditioning system are predicted based on the power consumption and energy consumption prediction model according to the factor parameters of the power consumption and energy consumption, the prediction results can be displayed on a preset display interface in various modes such as a chart and the like, and comments or explanations can be artificially added to the prediction results so as to improve the readability of data.
Fig. 2 is a schematic diagram of a power consumption prediction model constructed according to an embodiment of the present application, and with reference to fig. 2, data collection is first performed, where the collected data are historical factor data and historical power consumption data; and judging whether the acquired data needs to be preprocessed or not, if so, carrying out cleaning, integration, conversion or reduction processing, and entering a step of factor analysis after preprocessing, and if not, directly entering a step of factor analysis.
In the process of factor analysis, influence of each type of factor data on the power consumption and energy consumption of the target air-conditioning system is sequenced through an intelligent orthogonal experiment, and the first L types of factor data in the sequence of the influence degree of the power consumption and energy consumption of the target air-conditioning system from large to small are obtained.
And training the model based on the factor data obtained by the factor analysis, testing the effect of the model after obtaining the model, determining that the obtained model is the power consumption prediction model under the condition of successful test, and continuing training under the condition of failed test.
Example 2
According to an embodiment of the present invention, there is provided an embodiment of an apparatus for predicting power consumption, and fig. 3 is a schematic diagram of an apparatus for predicting power consumption according to an embodiment of the present invention, as shown in fig. 3, the apparatus includes:
the first obtaining module 30 is configured to obtain factor data of a target type, where the factor data is used to represent data that affects power consumption of the target air conditioning system, and a degree of the target type is determined according to a plurality of types of factor data that affect the power consumption of the target air conditioning system.
And the second obtaining module 32 is configured to obtain the power consumption prediction model.
And the prediction module 34 is used for predicting the power consumption of the target air conditioning system based on the power consumption prediction model according to the factor parameter of the target type.
As an alternative embodiment, the apparatus further comprises: a determining module, configured to determine the target type before obtaining the factor data of the target type, where the determining module includes: the acquisition submodule is used for acquiring historical electricity consumption data and various types of factor data of the target air conditioning system; the sequencing submodule is used for sequencing the influence degree of various types on the electricity consumption energy data of the target air-conditioning system according to various types of factor data through historical electricity consumption energy data and various types of factor data; the first determining submodule is used for determining the first N types as target types under the condition of sorting according to the influence degrees from large to small, wherein N is an integer larger than 1; and the first determining submodule is used for determining the M types as target types under the condition of sorting according to the influence degrees from small to large, wherein M is an integer larger than 1.
As an alternative embodiment, the apparatus further comprises: the construction module is used for constructing the power consumption prediction model before acquiring the factor data of the target type, wherein the construction comprises the following steps: the acquisition submodule is used for acquiring sample data, wherein the sample data comprises historical factor data of a target type and power consumption data corresponding to the historical factor data; and the training submodule is used for training the preset initial model through the sample data to obtain the power consumption prediction model.
As an alternative embodiment, the initial model is a radial basis function neural network model.
As an alternative embodiment, the apparatus further comprises: the device comprises a preprocessing module and a processing module, wherein the preprocessing module is used for preprocessing the sample data after the sample data is acquired, and the preprocessing comprises any one or more of the following steps: data cleaning, data integration, data conversion and data reduction; the training submodule includes: and the first training unit is used for training the preset initial model through the preprocessed sample data to obtain the power consumption prediction model.
As an alternative embodiment, the sample data includes: training sample data and test sample data, the training submodule includes: the second training unit is used for training the preset initial model through training sample data to obtain a training result; the test unit is used for testing the training result through the test sample data; and the determining unit is used for determining that the training result is the power consumption prediction model if the test is passed, and continuing training on the basis of the training result if the test is not passed.
As an alternative embodiment, the test unit comprises: the input subunit is used for inputting the historical factor data in the test sample data to the training result to obtain a prediction result output by the training result; the obtaining subunit is used for obtaining the root mean square error of the power consumption data corresponding to the prediction result and the test sample data; and the first determining subunit is used for determining whether the training result passes the test according to the root mean square error.
As an alternative embodiment, the determining unit includes: the correcting subunit is used for correcting the network parameters in the training result through the root mean square error; and the first determining subunit is used for determining the corrected training result as a power consumption prediction model.
Example 3
According to an embodiment of the present invention, there is provided a storage medium, wherein the storage medium includes a stored program, and wherein, when the program runs, a device in which the storage medium is located is controlled to execute the prediction method of power consumption of embodiment 1.
Example 4
According to an embodiment of the present invention, there is provided a processor, wherein the processor is configured to execute a program, and the program executes a prediction method of power consumption in the embodiment.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
In the above embodiments of the present invention, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
In the embodiments provided in the present application, it should be understood that the disclosed technology can be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units may be a logical division, and in actual implementation, there may be another division, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or modules, and may be in an electrical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (11)
1. A method for predicting power consumption, comprising:
acquiring factor data of a target type, wherein the factor data is used for representing data influencing the electricity consumption of a target air conditioning system, and the target type is determined according to the influence degree of various types of factor data on the electricity consumption of the target air conditioning system;
acquiring a power consumption prediction model;
and predicting the power consumption of the target air conditioning system based on the power consumption prediction model according to the factor parameters of the target type.
2. The method of claim 1, wherein prior to obtaining factor data for a target type, the method further comprises: determining the target type, wherein determining the target type comprises:
acquiring historical electricity consumption data and various types of factor data of the target air conditioning system;
sorting the plurality of types according to the influence degree of the plurality of types of factor data on the electricity consumption energy data of the target air conditioning system through the historical electricity consumption energy data and the plurality of types of factor data;
under the condition of sorting according to the influence degrees from big to small, determining the first N types as the target types, wherein N is an integer greater than 1;
and under the condition of sorting according to the influence degrees from small to large, determining the last M types as the target types, wherein M is an integer larger than 1.
3. The method of claim 1, wherein prior to obtaining factor data for a target type, the method further comprises: the power consumption energy consumption prediction model is constructed, wherein the construction of the power consumption energy consumption prediction model comprises the following steps:
acquiring sample data, wherein the sample data comprises historical factor data of the target type and power consumption data corresponding to the historical factor data;
and training a preset initial model through the sample data to obtain the power consumption prediction model.
4. The method of claim 3, wherein the predetermined initial model is a radial basis function neural network model.
5. The method of claim 2, wherein after obtaining sample data, the method further comprises:
preprocessing the sample data, wherein the preprocessing comprises any one or more of the following: data cleaning, data integration, data conversion and data reduction;
training a preset initial model through the sample data to obtain the power consumption prediction model, wherein the power consumption prediction model comprises the following steps: and training a preset initial model through the preprocessed sample data to obtain the power consumption and energy consumption prediction model.
6. The method of claim 3, wherein the sample data comprises: training sample data and test sample data, training a preset initial model through the sample data to obtain the power consumption prediction model, and the method comprises the following steps:
training the preset initial model through the training sample data to obtain a training result;
testing the training result through the test sample data;
and if the test is passed, determining the training result as the power consumption prediction model, and if the test is not passed, continuing training on the basis of the training result.
7. The method of claim 6, wherein testing the training result with the test sample data comprises:
inputting historical factor data in the test sample data to the training result to obtain a prediction result output by the training result;
obtaining a root mean square error of the prediction result and the power consumption data corresponding to the test sample data;
and determining whether the training result passes the test according to the root mean square error.
8. The method of claim 7, wherein determining the training result as the power consumption prediction model if the test passes comprises:
correcting the network parameters in the training result through the root mean square error;
and determining the corrected training result as the power consumption prediction model.
9. An apparatus for predicting power consumption, comprising:
the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring factor data of a target type, the factor data is used for representing data influencing the electricity consumption of a target air conditioning system, and the target type is determined according to the influence degree of various types of factor data on the electricity consumption of the target air conditioning system;
the second acquisition module is used for acquiring the power consumption prediction model;
and the prediction module is used for predicting the power consumption of the target air conditioning system based on the power consumption prediction model according to the factor parameters of the target type.
10. A storage medium, characterized in that the storage medium includes a stored program, and when the program runs, the storage medium is controlled to execute the method for predicting power consumption according to any one of claims 1 to 8.
11. A processor configured to execute a program, wherein the program executes the method for predicting power consumption according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811339840.5A CN111179108A (en) | 2018-11-12 | 2018-11-12 | Method and device for predicting power consumption |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811339840.5A CN111179108A (en) | 2018-11-12 | 2018-11-12 | Method and device for predicting power consumption |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111179108A true CN111179108A (en) | 2020-05-19 |
Family
ID=70655561
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811339840.5A Pending CN111179108A (en) | 2018-11-12 | 2018-11-12 | Method and device for predicting power consumption |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111179108A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112283889A (en) * | 2020-10-10 | 2021-01-29 | 广东美的暖通设备有限公司 | Method, device and equipment for controlling pre-starting time of air conditioner and storage medium |
| CN112669171A (en) * | 2020-12-22 | 2021-04-16 | 深圳市康必达控制技术有限公司 | Energy management method and device |
| CN113550872A (en) * | 2021-09-22 | 2021-10-26 | 深圳市特发信息数据科技有限公司 | Energy consumption monitoring system of wind power data center |
| US11468375B2 (en) * | 2015-10-13 | 2022-10-11 | British Gas Trading Limited | System for energy consumption prediction |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103853106A (en) * | 2012-11-28 | 2014-06-11 | 同济大学 | Energy consumption prediction parameter optimization method of building energy supply device |
| CN106600026A (en) * | 2016-10-21 | 2017-04-26 | 金斯科 | Residential building energy consumption prediction method suitable for hilly area in east part of Zhejiang province |
| CN106874581A (en) * | 2016-12-30 | 2017-06-20 | 浙江大学 | A kind of energy consumption of air conditioning system in buildings Forecasting Methodology based on BP neural network model |
| CN107590565A (en) * | 2017-09-08 | 2018-01-16 | 北京首钢自动化信息技术有限公司 | A kind of method and device for building building energy consumption forecast model |
-
2018
- 2018-11-12 CN CN201811339840.5A patent/CN111179108A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103853106A (en) * | 2012-11-28 | 2014-06-11 | 同济大学 | Energy consumption prediction parameter optimization method of building energy supply device |
| CN106600026A (en) * | 2016-10-21 | 2017-04-26 | 金斯科 | Residential building energy consumption prediction method suitable for hilly area in east part of Zhejiang province |
| CN106874581A (en) * | 2016-12-30 | 2017-06-20 | 浙江大学 | A kind of energy consumption of air conditioning system in buildings Forecasting Methodology based on BP neural network model |
| CN107590565A (en) * | 2017-09-08 | 2018-01-16 | 北京首钢自动化信息技术有限公司 | A kind of method and device for building building energy consumption forecast model |
Non-Patent Citations (1)
| Title |
|---|
| 宋蒙: ""大型公共建筑用电能耗预测模型及预测数据分析"", 《中国优秀硕士学位论文全文数据库 工程科技II辑》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11468375B2 (en) * | 2015-10-13 | 2022-10-11 | British Gas Trading Limited | System for energy consumption prediction |
| CN112283889A (en) * | 2020-10-10 | 2021-01-29 | 广东美的暖通设备有限公司 | Method, device and equipment for controlling pre-starting time of air conditioner and storage medium |
| CN112669171A (en) * | 2020-12-22 | 2021-04-16 | 深圳市康必达控制技术有限公司 | Energy management method and device |
| CN113550872A (en) * | 2021-09-22 | 2021-10-26 | 深圳市特发信息数据科技有限公司 | Energy consumption monitoring system of wind power data center |
| CN113550872B (en) * | 2021-09-22 | 2021-12-07 | 深圳市特发信息数据科技有限公司 | Energy consumption monitoring system of wind power data center |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103853106B (en) | A kind of energy consumption Prediction Parameters optimization method of building energy supplied equipment | |
| CN111179108A (en) | Method and device for predicting power consumption | |
| CN108154258B (en) | Method and device for predicting load of air source heat pump, storage medium and processor | |
| CN115796393B (en) | Energy management optimization method, system and storage medium based on multi-energy interaction | |
| CN111754026A (en) | Photovoltaic power station group power prediction method and device, computer equipment and storage medium | |
| CN111680841B (en) | Short-term load prediction method, system and terminal equipment based on principal component analysis | |
| CN107730097B (en) | Bus load prediction method and device and computing equipment | |
| CN111861023A (en) | Statistical-based hybrid wind power prediction method and device | |
| CN114372360A (en) | Method, terminal and storage medium for power load prediction | |
| CN115759467A (en) | Time-division integrated learning photovoltaic prediction method for error correction | |
| CN112365056A (en) | Electrical load joint prediction method and device, terminal and storage medium | |
| CN115660225A (en) | Electricity load prediction management method and system based on ammeter communication module | |
| KR20170106686A (en) | Method and apparatus for predicting home energy usage | |
| CN111815060A (en) | Short-term load prediction method and device for power utilization area | |
| CN112801357B (en) | Solar radiation quantity prediction method, device, equipment and storage medium | |
| CN112365082A (en) | Public energy consumption prediction method based on machine learning | |
| CN108446783A (en) | A kind of prediction of new fan operation power and monitoring method | |
| CN116706992A (en) | Self-adaptive power prediction method, device and equipment for distributed photovoltaic cluster | |
| CN117033923A (en) | Method and system for predicting crime quantity based on interpretable machine learning | |
| CN106897771B (en) | New energy sample board machine selection method and system based on chaotic genetic algorithm | |
| CN110889465B (en) | Power demand side equipment identification method and system based on self-adaptive resonant network | |
| CN201717634U (en) | Failure set handling system for multilayer power network | |
| CN110322063A (en) | A kind of power consumption simulated prediction method and storage medium | |
| CN110991519A (en) | Intelligent switch state analysis and adjustment method and system | |
| CN110648248A (en) | Control method, device and equipment for power station |
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 |