A method, system and computer-readable storage medium for predicting and tracking energy consumption parameters

Abstract

The present application provides an energy consumption parameter prediction and tracking method, system, and computer-readable storage medium. The method includes the following steps: obtaining first energy consumption parameters of a target institution within a preset time period uploaded in the current cycle; obtaining historical energy consumption parameters and historical weather data of the target institution in multiple cycles; obtaining first weather data of the elapsed time period of the current cycle of the target institution and predicted weather data of the unelapsed time period of the current cycle; calculating target energy consumption parameters of the unelapsed time period of the current cycle of the target institution according to the first energy consumption parameters, the historical energy consumption parameters, the historical weather data, the first weather data, and the predicted weather data. The present application can improve the accuracy of target energy consumption parameters.

Description

Technical Field

[0001] Embodiments of the present invention relate to the technical field of energy consumption prediction, and in particular to an energy consumption parameter prediction and tracking method, system, and computer-readable storage medium. Background Art

[0002] Currently, in the face of the tightening of global energy resources, serious environmental pollution, and the degradation of the ecological system, the construction of ecological civilization has risen to the national strategic height. The national five-year energy conservation plan clearly states that major sectors of society such as industry, construction, transportation, and public institutions should carry out energy conservation and emission reduction work to meet the binding target requirements of energy conservation and resource conservation. At present, each energy-consuming unit or institution in the country will receive the annual energy conservation task requirements issued by the superior competent department. Due to the lack of a scientific energy conservation target tracking method, the energy-consuming unit or institution cannot reasonably predict and judge whether the energy conservation target can be achieved as expected, or the prediction accuracy is not high, resulting in low enthusiasm for energy conservation work, and the energy conservation target tasks are often not completed.

[0003] Therefore, how to effectively track and predict the completion of the energy conservation target is the key issue in the current energy conservation work. Currently, when predicting energy consumption data, it is often only combined with historical data for energy consumption prediction, which is very rough, and the accuracy of the predicted energy consumption data is poor, which is not conducive to energy transmission and allocation.

[0004] Therefore, the existing technology has defects and needs to be improved urgently. Summary of the Invention

[0005] In order to solve at least one of the above technical problems, an energy consumption parameter prediction and tracking method, system, and computer-readable storage medium are provided, which can improve the prediction accuracy.

[0006] In a first aspect, an embodiment of the present application provides an energy consumption parameter prediction and tracking method, including:

[0007] Obtain the first energy consumption parameter within a preset time period uploaded by the target institution in the current cycle;

[0008] Obtain the historical energy consumption parameters and historical weather data of the target institution in multiple cycles;

[0009] Obtain the first weather data in the elapsed time period of the current cycle of the target institution and the predicted weather data in the unelapsed time period of the current cycle;

[0010] Calculate the target energy consumption parameter in the unelapsed time period of the current cycle of the target institution according to the first energy consumption parameter, the historical energy consumption parameters, the historical weather data, the first weather data, and the predicted weather data.

[0011] The energy consumption parameter prediction and tracking method provided by the embodiments of the present application can achieve the prediction of target energy consumption parameters and improve the accuracy of prediction.

[0012] Optionally, in the energy consumption parameter prediction and tracking method described in the embodiments of the present application, calculating the target energy consumption parameters of the target institution in the unexpired time period of the current cycle according to the first energy consumption parameter, the historical energy consumption parameter, the historical weather data, the first weather data, and the predicted weather data includes:

[0013] Inputting the first energy consumption parameter, the historical energy consumption parameter, the historical weather data, the first weather data, and the predicted weather data into a first preset neural network model to obtain the target energy consumption parameters of the target institution in the unexpired time period of the current cycle.

[0014] Optionally, in the energy consumption parameter prediction and tracking method described in the embodiments of the present application, calculating the target energy consumption parameters of the target institution in the unexpired time period of the current cycle according to the first energy consumption parameter, the historical energy consumption parameter, the historical weather data, the first weather data, and the predicted weather data includes:

[0015] Inputting the historical energy consumption parameter, the historical weather data, and the second weather data into a second preset neural network model to obtain the initial energy consumption parameters of the target institution in the unexpired time period;

[0016] Calculating a calibration coefficient according to the first energy consumption parameter, the first weather data, the historical energy consumption parameter, and the historical weather data;

[0017] Calibrating the initial energy consumption parameters according to the calibration coefficient to obtain the target energy consumption parameters.

[0018] Optionally, in the energy consumption parameter prediction and tracking method described in the embodiments of the present application, the preset time period includes multiple target time periods, the first weather data includes multiple first weather sub-data, and the first energy consumption parameter includes multiple first energy consumption sub-data; each target time period corresponds to a first weather sub-data and a first energy consumption sub-data respectively.

[0019] Optionally, in the energy consumption parameter prediction and tracking method described in the embodiments of the present application, calculating the calibration coefficient according to the first energy consumption parameter, the first weather data, the historical energy consumption parameter, and the historical weather data includes:

[0020] Screening out a preset time period with a weather data similarity greater than a preset threshold from the first weather data and the second weather data;

[0021] Obtain first energy consumption sub - data and historical energy consumption sub - data corresponding to the preset time period from the first energy consumption parameter and the historical energy consumption parameter;

[0022] Calculate the ratio of the current - week period to the period in the historical record under the same weather data according to the first energy consumption sub - data and the historical energy consumption sub - data, and set the ratio as the calibration coefficient.

[0023] Optionally, in the energy consumption parameter prediction and tracking method described in the embodiments of the present application, the method further includes:

[0024] Obtain a sample data set, the sample data set includes a plurality of sample data, and the sample data includes sample historical weather data corresponding to sample historical energy consumption parameters;

[0025] Train a preset network structure according to the plurality of sample data to obtain a second preset neural network structure.

[0026] Optionally, in the energy consumption parameter prediction and tracking method described in the embodiments of the present application, the calibrating the initial energy consumption parameter according to the calibration coefficient to obtain a target energy consumption parameter includes:

[0027] Multiply the initial energy consumption parameter by the calibration coefficient to obtain the target energy consumption parameter.

[0028] In a second aspect, the embodiments of the present application further provide an institutional energy consumption parameter prediction and tracking energy consumption parameter system, the system includes: a memory and a processor, the memory includes an energy consumption parameter prediction and tracking method program, and when the energy consumption parameter prediction and tracking method program is executed by the processor, the following steps are implemented:

[0029] Obtain the first energy consumption parameter within a preset time period uploaded by the target institution in the current period;

[0030] Obtain the historical energy consumption parameters and historical weather data of the target institution in multiple periods;

[0031] Obtain the first weather data of the elapsed time period of the target institution in the current period and the predicted weather data of the unelapsed time period in the current period;

[0032] Calculate the target energy consumption parameter of the unelapsed time period of the target institution in the current period according to the first energy consumption parameter, the historical energy consumption parameter, the historical weather data, the first weather data, and the predicted weather data.

[0033] Optionally, in the institutional energy consumption parameter prediction and tracking system described in the embodiments of the present application, when the energy consumption parameter prediction and tracking method program is executed by the processor, the following steps are implemented:

[0034] Input the first energy consumption parameter, the historical energy consumption parameter, the historical weather data, the first weather data, and the predicted weather data into a first preset neural network model to obtain the target energy consumption parameter of the target organization for the unpast period in the current cycle.

[0035] In a third aspect, an embodiment of the present application further provides a computer-readable storage medium, which includes an energy consumption parameter prediction and tracking method program. When the energy consumption parameter prediction and tracking method program is executed by a processor, the steps of an energy consumption parameter prediction and tracking method as described in any one of the above are implemented.

[0036] As can be seen from the above, the energy consumption parameter prediction and tracking method and system provided by the embodiments of the present application obtain the first energy consumption parameter within a preset period uploaded by the target organization in the current cycle; obtain the historical energy consumption parameters and historical weather data of the target organization in multiple cycles; obtain the first weather data of the past period of the target organization in the current cycle and the predicted weather data of the unpast period in the current cycle; calculate the target energy consumption parameter of the target organization for the unpast period in the current cycle according to the first energy consumption parameter, the historical energy consumption parameter, the historical weather data, the first weather data, and the predicted weather data, so as to predict the target energy consumption parameter, which can improve the accuracy of the prediction.

[0037] Additional aspects and advantages of the present invention will be given in the following description section, some will become obvious from the following description, or be learned through the practice of the present invention. Description of the Drawings

[0038] Figure 1 Shows a first flowchart of an energy consumption parameter prediction and tracking method of the present invention;

[0039] Figure 2 Shows a second flowchart of an energy consumption parameter prediction and tracking method of the present invention;

[0040] Figure 3 Shows a block diagram of an energy consumption parameter prediction and tracking system for the energy consumption parameter of an organization of the present invention. Detailed Embodiments

[0041] In order to be able to more clearly understand the above objects, features, and advantages of the present invention, the present invention will be further described in detail below with reference to the drawings and specific embodiments. It should be noted that, without conflict, the embodiments of the present application and the features in the embodiments can be combined with each other.

[0042] In the following description, many specific details are set forth in order to provide a thorough understanding of the present invention. However, the present invention may be practiced in other ways than those described herein. Therefore, the scope of the present invention is not limited by the specific embodiments disclosed below.

[0043] Figure 1 FIG. 1 shows a first flowchart of a method for predicting and tracking energy consumption parameters of the present invention. The method includes the following steps:

[0044] S101. Obtain first energy consumption parameters within a preset time period uploaded by a target institution in the current cycle;

[0045] S102. Obtain historical energy consumption parameters and historical weather data of the target institution in multiple cycles;

[0046] S103. Obtain first weather data for the elapsed time period of the current cycle of the target institution and predicted weather data for the unelapsed time period of the current cycle;

[0047] S104. Calculate target energy consumption parameters for the unelapsed time period of the current cycle of the target institution based on the first energy consumption parameters, the historical energy consumption parameters, the historical weather data, the first weather data, and the predicted weather data.

[0048] Wherein, in step S101, the cycle may be one year, one month, or any continuous period of time. The preset time period refers to the time that has elapsed in the current cycle, and the first energy consumption parameter may be power consumption. The target institution may be an enterprise, a factory, a school, a hospital, etc. It may be a building or a building complex engaged in a specific function. Of course, it can be understood that the first energy consumption parameter may also include consumption of institutional energy types such as power consumption, fuel consumption, gas consumption, heat supply, and cooling capacity.

[0049] Wherein, in step S102, the multiple cycles refer to 3 cycles or 4 cycles, or even more cycles before the current cycle. The historical energy consumption parameter refers to the energy consumption data of the target institution in each time period of the past multiple cycles, and the time period may be one day, one week, one month, or any time period less than the cycle time. The historical weather data refers to the weather data of the target institution in each time period of the past multiple cycles. The weather data includes, but is not limited to, temperature and humidity.

[0050] Wherein, in step S103, for example, if the cycle is one year and the time period is divided by month, if the current month is May, the elapsed time period is January, February, March, and April, and the unelapsed time period is May - December. The first weather data is the weather data for January - April, and the second weather data is the predicted weather data for May - December.

[0051] Among them, in this step S104, calculations can be performed based on a neural network model, or a pre-summarized formula can be used to calculate the target energy consumption parameter. Of course, it can be understood that other models or formulas summarized in advance can also be used to calculate the target energy consumption parameter. Or, a fitting function method can be used for calculation.

[0052] In some embodiments, this step S104 may include the following sub-steps: inputting the first energy consumption parameter, the historical energy consumption parameter, the historical weather data, the first weather data, and the predicted weather data into a first preset neural network model to obtain the target energy consumption parameter of the target institution in the unexpired time period of the current cycle. The first preset neural network model is pre-trained using sample data.

[0053] In some embodiments, as Figure 3 shown, this step S104 may include the following sub-steps: S1041. Inputting the historical energy consumption parameter, the historical weather data, and the second weather data into a second preset neural network model to obtain the initial energy consumption parameter of the target institution in the unexpired time period; S1042. Calculating a calibration coefficient according to the first energy consumption parameter, the first weather data, the historical energy consumption parameter, and the historical weather data; S1043. Calibrating the initial energy consumption parameter according to the calibration coefficient to obtain the target energy consumption parameter of the unexpired time period. Among them, the second preset neural network is pre-trained.

[0054] Among them, since there may be other differences in factors between the current cycle and other previous cycles, for example, differences in the number of people, working hours caused by changes in business conditions, etc., it is necessary to calculate a calibration coefficient based on the first energy consumption parameter, the first weather data, the historical energy consumption parameter, and the historical weather data. In some embodiments, this step S1042 includes: screening out a preset time period with a weather data similarity greater than a preset threshold from the first weather data and the second weather data; obtaining a first energy consumption sub-data and a historical energy consumption sub-data corresponding to the preset time period from the first energy consumption parameter and the historical energy consumption parameter; calculating the ratio of the current week cycle to the cycle in the historical record under the same weather data according to the first energy consumption sub-data and the historical energy consumption sub-data, and setting the ratio as the calibration coefficient.

[0055] Among them, the preset time period includes a plurality of target time periods, the first weather data includes a plurality of first weather sub-data, and the first energy consumption parameter includes a plurality of first energy consumption sub-data; each of the target time periods corresponds to a first weather sub-data and a first energy consumption sub-data respectively.

[0056] In some embodiments, the method further includes: obtaining a sample data set, where the sample data set includes a plurality of sample data, and the sample data includes sample historical weather data corresponding to sample historical energy consumption parameters; training a preset network structure according to the plurality of sample data to obtain a second preset neural network structure.

[0057] In some embodiments, step S1043 includes: calibrating the initial energy consumption parameter according to the calibration coefficient to obtain a target energy consumption parameter, including: multiplying the initial energy consumption parameter by the calibration coefficient to obtain the target energy consumption parameter. For example, if the initial energy consumption parameter is a1 and the calibration coefficient is q, then the target energy consumption parameter is a1×q.

[0058] Among them, in some embodiments, step S101 may be: obtaining the annual energy consumption data of a target organization within a preset range uploaded by a user terminal in the past N years. The ways for the user terminal to upload energy consumption data include, but are not limited to, entering and uploading data through mobile terminal software or platform software, or automatically uploading data using remote metering devices; the annual energy consumption data includes, but is not limited to, at least one of the following energy consumption data: water resource energy consumption data, electric energy consumption data, cooling / heating energy consumption data, fuel energy consumption data, and gas energy consumption data, etc.; obtaining information related to calculating energy consumption indicators such as building information, the first number of energy-consuming people information, and economic information of the target organization within a preset range uploaded by the user terminal in the past N years. The ways for the user terminal to upload information related to calculating energy consumption indicators include, but are not limited to, entering and uploading data through mobile terminal software or platform software.

[0059] Step S102 may include: obtaining the first energy consumption data and information related to calculating energy consumption indicators from January to the current month that have been statistically counted in the current year;

[0060] The method correspondingly further includes: S106. Calculating a calibration coefficient according to the first energy consumption data and the annual energy consumption data in the past N years; predicting the second energy consumption data from the current month to December in the current year according to the calibration coefficient; S107. Predicting the energy consumption indicators in the current year according to the first energy consumption data and the second energy consumption data. The energy consumption indicators include, but are not limited to, indicators related to the energy consumption intensity of the organization such as energy consumption per unit building area, per capita energy consumption, electricity consumption per unit building area, per capita electricity consumption, heating energy consumption per unit building, energy consumption per unit product, and energy consumption per unit GDP.

[0061] Among them, step S106 may include: selecting the target annual energy consumption data of the target year with the highest climate similarity to this year from the annual energy consumption data in the N years; obtaining the third energy consumption data from January to the corresponding month from the target annual energy consumption data; calculating the calibration coefficient according to the third energy consumption data and the first energy consumption data.

[0062] Among them, Wherein, i = 1, 2, 3…, 11, 12, and n = 1, 2, …, i, …, 12.

[0063] This step S106 may include: According to the formula: The second energy consumption data from the current month to December of the current year = The fourth energy consumption data from the corresponding month to December in the target annual energy consumption data * Calibration coefficient.

[0064] As can be seen from the above, the energy consumption parameter prediction and tracking method provided by the embodiments of the present application obtains the first energy consumption parameters within a preset time period uploaded by the target organization in the current cycle; obtains the historical energy consumption parameters and historical weather data of the target organization in multiple cycles; obtains the first weather data in the elapsed time period of the current cycle of the target organization and the predicted weather data in the unelapsed time period of the current cycle; calculates the target energy consumption parameters in the unelapsed time period of the current cycle of the target organization according to the first energy consumption parameters, the historical energy consumption parameters, the historical weather data, the first weather data, and the predicted weather data, so as to predict the target energy consumption parameters, thereby improving the accuracy of the prediction.

[0065] As Figure 3 shown, the embodiments of the present application also provide an energy consumption parameter prediction and tracking system for an organization. The system includes: a memory 201 and a processor 202. The memory 201 includes an energy consumption parameter prediction and tracking method program. When the energy consumption parameter prediction and tracking method program is executed by the processor, the following steps are implemented: obtaining the first energy consumption parameters within a preset time period uploaded by the target organization in the current cycle; obtaining the historical energy consumption parameters and historical weather data of the target organization in multiple cycles; obtaining the first weather data in the elapsed time period of the current cycle of the target organization and the predicted weather data in the unelapsed time period of the current cycle; calculating the target energy consumption parameters in the unelapsed time period of the current cycle of the target organization according to the first energy consumption parameters, the historical energy consumption parameters, the historical weather data, the first weather data, and the predicted weather data.

[0066] Wherein, the cycle may be one year, one month, or any continuous period of time. The preset time period refers to the time that has elapsed in the current cycle. The first energy consumption parameter is mainly the power consumption, and may also include the consumption of organization energy types such as power consumption, fuel consumption, gas consumption, heat supply, and cooling capacity.

[0067] Among them, multiple cycles refer to 3 cycles, 4 cycles, or even more cycles before the current cycle. The historical energy consumption parameter refers to the energy consumption data of the target structure in each time period of the past multiple cycles, and the time period can be one day, one week, one month, or any time period less than the cycle time. The historical weather data refers to the weather data of the target institution in each time period of the past multiple cycles. The weather data includes, but is not limited to, temperature and humidity.

[0068] Among them, if the cycle is one year and the time period is divided monthly, and if the current month is May, the passed time periods are January, February, March, and April, and the unpassed time periods are May - December. The first weather data is the weather data from January to April, and the second weather data is the predicted weather data from May to December.

[0069] Among them, the calculation can be based on a neural network model, or a pre - summarized formula can be used to calculate the target energy consumption parameter.

[0070] In some embodiments, when the energy consumption parameter prediction and tracking method program is executed by the processor, the following steps are implemented: input the first energy consumption parameter, the historical energy consumption parameter, the historical weather data, the first weather data, and the predicted weather data into a first preset neural network model to obtain the target energy consumption parameter of the target institution in the unpassed time period of the current cycle. The first preset neural network model is pre - trained using sample data.

[0071] In some embodiments, when the energy consumption parameter prediction and tracking method program is executed by the processor, the following steps are implemented: input the historical energy consumption parameter, the historical weather data, and the second weather data into a second preset neural network model to obtain the initial energy consumption parameter of the target institution in the unpassed time period; calculate a calibration coefficient according to the first energy consumption parameter, the first weather data, the historical energy consumption parameter, and the historical weather data; calibrate the initial energy consumption parameter according to the calibration coefficient to obtain the target energy consumption parameter. Among them, the second preset neural network is pre - trained.

[0072] Among them, since there may be other factors different between the current time period and other previous periods, for example, different numbers of people, different working hours due to changes in business conditions, etc., it is necessary to calculate a calibration coefficient based on the first energy consumption parameter, the first weather data, the historical energy consumption parameter, and the historical weather data. In some embodiments, when the energy consumption parameter prediction and tracking method program is executed by the processor, the following steps are implemented: screening out a preset time period with a weather data similarity greater than a preset threshold from the first weather data and the second weather data; obtaining a first energy consumption sub-data and a historical energy consumption sub-data corresponding to the preset time period from the first energy consumption parameter and the historical energy consumption parameter; calculating a ratio of the current week period to the period in the historical record under the same weather data according to the first energy consumption sub-data and the historical energy consumption sub-data, and setting the ratio as the calibration coefficient.

[0073] Among them, the preset time period includes a plurality of target time periods, the first weather data includes a plurality of first weather sub-data, and the first energy consumption parameter includes a plurality of first energy consumption sub-data; each of the target time periods corresponds to a first weather sub-data and a first energy consumption sub-data respectively.

[0074] In some embodiments, when the energy consumption parameter prediction and tracking method program is executed by the processor, the following steps are implemented: obtaining a sample data set, the sample data set including a plurality of sample data, and the sample data including sample historical weather data corresponding to sample historical energy consumption parameters; training a preset network structure according to the plurality of sample data to obtain a second preset neural network structure.

[0075] In some embodiments, when the energy consumption parameter prediction and tracking method program is executed by the processor, the following steps are implemented: calibrating the initial energy consumption parameter according to the calibration coefficient to obtain a target energy consumption parameter, including: multiplying the initial energy consumption parameter by the calibration coefficient to obtain the target energy consumption parameter for the unexpired time period.

[0076] As can be seen from the above, the institutional energy consumption parameter prediction and tracking system provided by the embodiments of the present application obtains the first energy consumption parameter within a preset time period uploaded by a target institution in the current period; obtains the historical energy consumption parameter and historical weather data of the target institution in a plurality of periods; obtains the first weather data of the expired time period of the target institution in the current period and the predicted weather data of the unexpired time period in the current period; calculates the target energy consumption parameter of the unexpired time period of the target institution in the current period according to the first energy consumption parameter, the historical energy consumption parameter, the historical weather data, the first weather data, and the predicted weather data, so as to predict the target energy consumption parameter, which can improve the accuracy of the prediction.

[0077] The embodiments of the present application also provide a computer-readable storage medium, which includes a program for the energy consumption parameter prediction and tracking method. When the program for the energy consumption parameter prediction and tracking method is executed by a processor, the steps of an energy consumption parameter prediction and tracking method described in any of the above embodiments are implemented. Specific implementation: Obtain the first energy consumption parameters within a preset time period uploaded by the target institution in the current cycle; obtain the historical energy consumption parameters and historical weather data of the target institution in multiple cycles; obtain the first weather data of the elapsed time period in the current cycle and the predicted weather data of the unelapsed time period in the current cycle; calculate the target energy consumption parameters of the unelapsed time period in the current cycle of the target institution according to the first energy consumption parameters, the historical energy consumption parameters, the historical weather data, the first weather data, and the predicted weather data.

[0078] As can be seen from the above, the computer-readable storage medium provided by the embodiments of the present application obtains the first energy consumption parameters within a preset time period uploaded by the target institution in the current cycle; obtains the historical energy consumption parameters and historical weather data of the target institution in multiple cycles; obtains the first weather data of the elapsed time period in the current cycle and the predicted weather data of the unelapsed time period in the current cycle; calculates the target energy consumption parameters of the unelapsed time period in the current cycle of the target institution according to the first energy consumption parameters, the historical energy consumption parameters, the historical weather data, the first weather data, and the predicted weather data, so as to predict the target energy consumption parameters, which can improve the accuracy of the prediction.

[0079] In several embodiments provided by the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined, or can be integrated into another system, or some features can be ignored, or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed with each other can be through some interfaces. The indirect coupling or communication connection of devices or units can be electrical or in other forms.

[0080] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units; they can be located in one place or distributed to multiple network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0081] In addition, each functional unit in the embodiments of the present invention may all be integrated into one processing unit, or each unit may be separately taken as one unit, or two or more units may be integrated into one unit; the above-mentioned integrated unit may be implemented in the form of hardware, or in the form of a hardware plus a software functional unit.

[0082] Those of ordinary skill in the art can understand that all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions. The foregoing program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps including the above method embodiments; and the foregoing storage medium includes: removable storage devices, read-only memory (ROM), random access memory (RAM), magnetic disks or optical discs and other various media that can store program codes.

[0083] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the embodiments of the present invention, in essence, or the part that contributes to the prior art, may be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the various embodiments of the present invention. And the foregoing storage medium includes: removable storage devices, ROM, RAM, magnetic disks or optical discs and other various media that can store program codes.

[0084] The above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A method for predicting and tracking energy consumption parameters, characterized in that Including: Obtain the first energy consumption parameter of the target institution within a preset time period uploaded in the current cycle; Obtain the historical energy consumption parameters and historical weather data of the target institution in multiple cycles; Obtain the first weather data of the target institution in the elapsed time period of the current cycle and the predicted weather data in the unelapsed time period of the current cycle; Calculate the target energy consumption parameter of the target institution in the unelapsed time period of the current cycle according to the first energy consumption parameter, the historical energy consumption parameter, the historical weather data, the first weather data, and the predicted weather data; The calculating the target energy consumption parameter of the target institution in the unelapsed time period of the current cycle according to the first energy consumption parameter, the historical energy consumption parameter, the historical weather data, the first weather data, and the predicted weather data includes: Input the historical energy consumption parameter, the historical weather data, and the second weather data into a second preset neural network model to obtain the initial energy consumption parameter of the target institution in the unelapsed time period; Calculate a calibration coefficient according to the first energy consumption parameter, the first weather data, the historical energy consumption parameter, and the historical weather data; Calibrate the initial energy consumption parameter according to the calibration coefficient to obtain the target energy consumption parameter; The calculating the calibration coefficient according to the first energy consumption parameter, the first weather data, the historical energy consumption parameter, and the historical weather data includes: Screen out a preset time period in which the weather data similarity between the first weather data and the second weather data is greater than a preset threshold; Obtain the first energy consumption sub-data and the historical energy consumption sub-data corresponding to the preset time period from the first energy consumption parameter and the historical energy consumption parameter; Calculate the ratio of the current week cycle to the cycle in the historical record under the same weather data according to the first energy consumption sub-data and the historical energy consumption sub-data, and set the ratio as the calibration coefficient.

2. The energy consumption parameter prediction and tracking method according to claim 1, wherein The preset time period includes multiple target time periods, the first weather data includes multiple first weather sub-data, and the first energy consumption parameter includes multiple first energy consumption sub-data; each target time period corresponds to a first weather sub-data and a first energy consumption sub-data respectively.

3. The energy consumption parameter prediction and tracking method according to claim 2, characterized in that, The method further includes: Obtain a sample data set, the sample data set includes multiple sample data, and the sample data includes the sample historical weather data corresponding to the sample historical energy consumption parameter; Train a preset network structure according to the multiple sample data to obtain a second preset neural network structure.

4. The energy consumption parameter prediction and tracking method according to claim 3, characterized in that The calibrating the initial energy consumption parameter according to the calibration coefficient to obtain the target energy consumption parameter includes: Multiply the initial energy consumption parameter by the calibration coefficient to obtain the target energy consumption parameter.

5. A system for predicting and tracking energy consumption parameters based on energy consumption parameters, characterized in that, The system includes: a memory and a processor, and the memory includes an energy consumption parameter prediction and tracking method program. When the energy consumption parameter prediction and tracking method program is executed by the processor, the following steps are implemented: Obtain the first energy consumption parameter of the target institution within a preset time period uploaded in the current cycle; Obtain the historical energy consumption parameters and historical weather data of the target institution in multiple cycles; Obtain the first weather data for the elapsed time period of the target institution in the current cycle and the predicted weather data for the unelapsed time period in the current cycle; Calculate the target energy consumption parameter for the unelapsed time period of the target institution in the current cycle according to the first energy consumption parameter, the historical energy consumption parameter, the historical weather data, the first weather data, and the predicted weather data; The calculating the target energy consumption parameter for the unelapsed time period of the target institution in the current cycle according to the first energy consumption parameter, the historical energy consumption parameter, the historical weather data, the first weather data, and the predicted weather data includes: Input the historical energy consumption parameter, the historical weather data, and the second weather data into a second preset neural network model to obtain the initial energy consumption parameter for the unelapsed time period of the target institution; Calculate a calibration coefficient according to the first energy consumption parameter, the first weather data, the historical energy consumption parameter, and the historical weather data; Calibrate the initial energy consumption parameter according to the calibration coefficient to obtain the target energy consumption parameter; The calculating the calibration coefficient according to the first energy consumption parameter, the first weather data, the historical energy consumption parameter, and the historical weather data includes: Screen out a preset time period with a weather data similarity greater than a preset threshold from the first weather data and the second weather data; Obtain the first energy consumption sub-data and the historical energy consumption sub-data corresponding to the preset time period from the first energy consumption parameter and the historical energy consumption parameter; Calculate the ratio of the current week's cycle to the cycle in the historical record under the same weather data according to the first energy consumption sub-data and the historical energy consumption sub-data, and set the ratio as the calibration coefficient.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes an energy consumption parameter prediction and tracking method program, and when the energy consumption parameter prediction and tracking method program is executed by a processor, the steps of an energy consumption parameter prediction and tracking method as described in any one of claims 1 to 4 are implemented.

Images