Industrial park energy consumption prediction method, device, equipment and storage medium

Abstract

The present invention belongs to the field of energy technology, and discloses an industrial park energy consumption prediction method, device, equipment and storage medium; the method comprises: obtaining historical energy consumption and historical initial parameters of a target park, analyzing the energy consumption correlation of each historical initial parameter, and obtaining historical reference parameters; diagnosing the collinearity of the historical reference parameters, eliminating the strongly correlated parameters in the historical reference parameters, and obtaining historical target parameters; constructing a basic building energy consumption model according to the historical target parameters to perform energy consumption simulation, and obtain an electricity energy consumption coefficient; predicting the fixed energy consumption and variable energy consumption of the park according to the electricity energy consumption coefficient, and obtaining the predicted energy consumption of the target park; the present invention analyzes the factors affecting the energy consumption of the industrial park, predicts the future energy consumption from the basic electricity consumption and the variable electricity consumption based on the factors with the highest correlation, and controls the energy consumption of the industrial park according to the predicted energy consumption, thereby avoiding unnecessary energy waste, realizing lean control and more environmentally friendly energy use.

Description

Technical Field

[0001] The present invention relates to the field of energy technology, and in particular to an industrial park energy consumption prediction method, device, equipment and storage medium. Background Art

[0002] With the development of the internet and the Internet of Things, the construction, planning, scheduling, and economic operation of integrated industrial park energy systems are trending toward intelligent management. Smart parks can control energy consumption within industrial parks and are a key strategy for managing carbon emissions within them. However, current industrial park areas are large and complex, making energy consumption monitoring ineffective and hindering improvements in energy efficiency.

[0003] In an environment where energy supply is becoming increasingly tight and environmental pollution is becoming increasingly serious, research on energy consumption prediction systems for the purpose of energy conservation and consumption reduction is of great significance. Industrial building energy conservation also requires further control and regulation of energy consumption, and lean management of energy use to avoid unnecessary energy waste.

[0004] The above content is only used to assist in understanding the technical solution of the present invention and does not constitute an admission that the above content is prior art. Summary of the Invention

[0005] The main purpose of the present invention is to provide an industrial park energy consumption prediction method, device, equipment and storage medium, aiming to solve the technical problem that the existing technology of industrial building energy consumption has no clear target requirements and specific regulations, resulting in the inability to timely control and adjust energy use according to industrial energy consumption.

[0006] To achieve the above object, the present invention provides a method for predicting energy consumption in an industrial park, the method comprising the following steps:

[0007] Obtain the historical energy consumption and multiple historical initial parameters of the target park, perform energy consumption correlation analysis on each historical initial parameter, and obtain historical reference parameters;

[0008] Performing collinearity diagnosis on the historical reference parameters, and eliminating strongly correlated parameters from the historical reference parameters based on the diagnosis results to obtain historical target parameters;

[0009] Constructing a basic building energy consumption model according to the historical target parameters, performing energy consumption simulation based on the basic building energy consumption model, and obtaining an electricity consumption coefficient;

[0010] The fixed energy consumption and variable energy consumption of the park are predicted according to the electricity energy consumption coefficient, and the predicted energy consumption of the target park is obtained according to the fixed energy consumption and variable energy consumption.

[0011] Optionally, the acquiring of the historical energy consumption of the target park and a plurality of historical initial parameters, performing energy consumption correlation analysis on each historical initial parameter, and obtaining historical reference parameters may include:

[0012] Obtaining historical energy consumption and multiple historical initial parameters of the target park, wherein the historical initial parameters include building area, number of windows, number of air conditioners, number of employees, and per capita income;

[0013] constructing an original sequence based on the historical energy consumption of the target park and a plurality of historical initial parameters, and performing dimensionless processing on the original sequence to obtain a reference sequence;

[0014] Calculating the correlation coefficient between each historical initial parameter and the historical energy consumption in the reference sequence according to a preset resolution coefficient;

[0015] An energy consumption correlation analysis is performed based on the correlation coefficient to obtain historical reference parameters.

[0016] Optionally, performing energy consumption correlation analysis according to the correlation coefficient to obtain historical reference parameters includes:

[0017] Smoothing the historical initial parameters and the historical energy consumption to obtain smoothed historical initial parameters and historical energy consumption;

[0018] Calculating the correlation between each historical initial parameter and the historical energy consumption according to the correlation coefficient, the smoothed historical initial parameter and the historical energy consumption;

[0019] The historical initial parameters are sorted according to the correlation, and a preset number of historical initial parameters after sorting are selected as historical reference parameters.

[0020] Optionally, performing collinearity diagnosis on the historical reference parameters and eliminating strongly correlated parameters in the historical reference parameters according to the diagnosis results to obtain historical target parameters includes:

[0021] constructing a whitening differential equation according to the historical reference parameters, and calculating a whitening parameter according to the historical reference parameters;

[0022] Solving the whitening differential equation according to the whitening parameter to obtain a prediction model;

[0023] Verifying the historical reference parameters according to the prediction model to obtain a verification result, and performing collinearity diagnosis according to the verification result;

[0024] A strong correlation parameter is obtained according to the diagnosis result, and the strong correlation parameter in the historical reference parameter is eliminated to obtain a historical target parameter.

[0025] Optionally, constructing a basic building energy consumption model according to the historical target parameters, performing energy consumption simulation based on the basic building energy consumption model, and obtaining an electricity consumption coefficient include:

[0026] Obtain historical meteorological data of the target park;

[0027] constructing a plurality of initial models according to the historical meteorological data and the historical target parameters, and obtaining simulated energy consumption corresponding to each initial model by simulating each initial model;

[0028] Calculate the energy consumption error between the simulated energy consumption corresponding to each initial model and the historical energy consumption, and use the initial model corresponding to the minimum energy consumption error as the basic building energy consumption model;

[0029] Energy consumption simulation is performed based on the basic building energy consumption model to obtain the electricity consumption coefficient.

[0030] Optionally, the electricity energy consumption coefficient includes a basic electricity energy consumption coefficient, a variable electricity energy consumption coefficient, and a park energy consumption distribution factor;

[0031] The energy consumption simulation based on the basic building energy consumption model is performed to obtain the electricity consumption coefficient, including:

[0032] Simulate the building energy consumption model to obtain the building electricity consumption, lighting electricity consumption, and air conditioning electricity consumption;

[0033] Calculate the basic electricity consumption coefficient based on the building electricity and lighting electricity, and calculate the variable electricity consumption coefficient based on the air conditioning electricity;

[0034] A park energy consumption distribution factor is constructed based on the basic electricity energy consumption coefficient and the variable electricity energy consumption coefficient.

[0035] Optionally, predicting the fixed energy consumption and variable energy consumption of the park according to the electricity energy consumption coefficient, and obtaining the predicted energy consumption of the target park according to the fixed energy consumption and the variable energy consumption, includes:

[0036] Obtain the current energy consumption of the park, and make a prediction based on the current energy consumption of the park, the energy consumption distribution factor of the park, and the basic electricity consumption coefficient to obtain a fixed energy consumption;

[0037] Predicting the variable energy consumption based on the current energy consumption of the park, the energy consumption distribution factor of the park, and the variable electricity consumption coefficient;

[0038] The fixed energy consumption and the variable energy consumption are added together to obtain the predicted energy consumption of the target park.

[0039] In addition, to achieve the above-mentioned purpose, the present invention further proposes a park energy consumption prediction device, which includes:

[0040] The parameter acquisition module is used to obtain the historical energy consumption and multiple historical initial parameters of the target park, perform energy consumption correlation analysis on each historical initial parameter, and obtain historical reference parameters;

[0041] The parameter acquisition module is further configured to perform collinearity diagnosis on the historical reference parameters, and eliminate strongly correlated parameters from the historical reference parameters according to the diagnosis results to obtain historical target parameters;

[0042] An energy consumption prediction module is used to construct a basic building energy consumption model according to the historical target parameters, perform energy consumption simulation based on the basic building energy consumption model, and obtain an electricity consumption coefficient;

[0043] The energy consumption prediction module is further used to predict the fixed energy consumption and variable energy consumption of the park based on the electricity consumption coefficient, and obtain the predicted energy consumption of the target park based on the fixed energy consumption and variable energy consumption.

[0044] In addition, to achieve the above-mentioned purpose, the present invention also proposes a park energy consumption prediction device, which includes: a memory, a processor, and a park energy consumption prediction program stored on the memory and runnable on the processor, and the park energy consumption prediction program is configured to implement the steps of the park energy consumption prediction method described above.

[0045] In addition, to achieve the above-mentioned purpose, the present invention also proposes a storage medium, on which a park energy consumption prediction program is stored. When the park energy consumption prediction program is executed by a processor, the steps of the park energy consumption prediction method described above are implemented.

[0046] The present invention analyzes the factors that affect the energy consumption of industrial parks, predicts future energy consumption from basic electricity consumption and variable electricity consumption based on the factors with the highest correlation, and manages and adjusts the energy consumption of industrial parks according to the predicted energy consumption. The more accurate the prediction, the more lean management and control can be achieved, thereby avoiding unnecessary energy waste and achieving more environmentally friendly energy use. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 It is a structural diagram of a campus energy consumption prediction device in a hardware operating environment involved in an embodiment of the present invention;

[0048] Figure 2 This is a flow chart of a first embodiment of a method for predicting energy consumption in a park according to the present invention;

[0049] Figure 3 This is a flow chart of a second embodiment of the method for predicting energy consumption in a park according to the present invention;

[0050] Figure 4 This is a flow chart of a third embodiment of the method for predicting energy consumption in a park according to the present invention;

[0051] Figure 5 A schematic diagram of meteorological data of an embodiment of a method for predicting energy consumption in a park according to the present invention;

[0052] Figure 6 This is a structural block diagram of the first embodiment of the park energy consumption prediction device of the present invention.

[0053] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0054] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0055] Reference Figure 1 , Figure 1 This is a schematic diagram of the structure of a campus energy consumption prediction device in the hardware operating environment involved in the embodiment of the present invention.

[0056] like Figure 1 As shown, the campus energy consumption prediction device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display and an input unit, such as a keyboard. Optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wireless Fidelity (Wi-Fi) interface). The memory 1005 may be a high-speed random access memory (RAM) or a stable non-volatile memory (NVM), such as a disk drive. Optionally, the memory 1005 may be a storage device independent of the processor 1001.

[0057] Those skilled in the art will understand that Figure 1 The structure shown in does not constitute a limitation on the park energy consumption prediction device, and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0058] like Figure 1 As shown, the memory 1005 as a storage medium may include an operating system, a network communication module, a user interface module, and a campus energy consumption prediction program.

[0059] exist Figure 1 In the park energy consumption prediction device shown, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the park energy consumption prediction device of the present invention can be set in the park energy consumption prediction device, and the park energy consumption prediction device calls the park energy consumption prediction program stored in the memory 1005 through the processor 1001, and executes the park energy consumption prediction method provided by the embodiment of the present invention.

[0060] The embodiment of the present invention provides a method for predicting energy consumption in a park, referring to Figure 2 , Figure 2 This is a flow chart of a first embodiment of a method for predicting energy consumption in a park according to the present invention.

[0061] In this embodiment, the park energy consumption prediction method includes the following steps:

[0062] Step S10: Obtain the historical energy consumption and multiple historical initial parameters of the target park, perform energy consumption correlation analysis on each historical initial parameter, and obtain historical reference parameters.

[0063] It is understandable that the target park can be a park for which energy consumption forecasting is desired, wherein the historical energy consumption can be the energy consumption of the target park in the past month, week or day; this embodiment here uses the energy consumption of each month as the historical energy consumption for illustration.

[0064] It should be understood that the historical initial parameters may be factors that may affect the energy consumption of the target park, such as the park area, the number of people in the park, the number of windows in the park, the number of air conditioners in the park, the weather in the area where the park is located, and even the output value of the park, etc. can all be used as historical initial parameters.

[0065] It should be noted that the energy consumption correlation analysis of each historical initial parameter can be used to analyze the degree of influence of each historical initial parameter on the energy consumption of the park. For example, the correlation between the number of people in the park and the energy consumption of the park is 0.56, and the correlation between the number of air conditioners in the park and the energy consumption of the park is 0.87.

[0066] It should be emphasized that after analyzing the correlation between each historical initial parameter and the park's energy consumption, the correlation between each historical initial parameter and the park's energy consumption can be obtained. Based on the magnitude of the correlation, the parameter with the highest correlation, or the parameter whose correlation meets a threshold, is selected from the multiple historical initial parameters as the historical reference parameter. The correlation threshold can be 0.6, 0.66, etc., and can be adjusted according to actual conditions. This embodiment does not limit this.

[0067] It should be further emphasized that the correlation analysis of each historical initial parameter can be performed through principal component analysis, partial correlation analysis, etc. This embodiment uses grey correlation analysis as an example for description.

[0068] Step S20: performing collinearity diagnosis on the historical reference parameters, and eliminating strongly correlated parameters in the historical reference parameters according to the diagnosis results to obtain historical target parameters.

[0069] It is understandable that collinearity diagnosis can be a diagnostic method for whether there is a mutual influence relationship between various historical reference parameters. Simply put, when predicting the energy consumption of a park based on historical reference parameters, there is a mutual influence between two or more historical reference parameters, which may lead to inaccurate energy consumption prediction of the park.

[0070] It should be noted that collinearity diagnosis can be performed using software specifically for parameter analysis, such as statistical analysis software (SPSS, the full name of which is Statistical Product and Service Solutions), or by constructing a multiple linear regression equation for parameter analysis.

[0071] It is worth noting that the specific calculation steps of the historical target parameters can be to construct a whitened differential equation based on the historical reference parameters, and calculate the whitened parameters based on the historical reference parameters; solve the whitened differential equation based on the whitened parameters to obtain a prediction model; verify the historical reference parameters based on the prediction model to obtain a verification result, and perform collinearity diagnosis based on the verification result; obtain strong correlation parameters based on the diagnosis result, eliminate the strong correlation parameters in the historical reference parameters, and obtain historical target parameters.

[0072] Wherein, constructing the whitening differential equation according to the historical reference parameters, and calculating the whitening parameters according to the historical reference parameters may be to establish a parameter sequence according to the historical reference parameter line, and the parameter sequence may refer to a series of formulas:

[0073]

[0074] In the formula, l is the total number of historical reference parameters, N is the reference sequence, and n is the total number of historical reference parameters. 1 1 indicates that the first historical energy consumption of the park corresponds to each historical reference parameter.

[0075] The following formula can be used to construct the whitening differential equation based on the above parameter sequence:

[0076]

[0077] Furthermore,

[0078]

[0079] Where a~ represents the whitening parameter. Based on the above historical reference parameters, the above whitening differential equation can be substituted into the above equation to obtain the prediction model:

[0080]

[0081] Among them, k represents the number of predictions, and k+1 represents the next prediction result.

[0082] Furthermore, the historical reference parameters are verified according to the prediction model to obtain verification results, and collinearity diagnosis is performed based on the verification results. This can be understood as predicting each historical reference parameter based on the prediction model, drawing a prediction result curve based on each prediction result, and performing collinearity diagnosis based on the prediction result curve.

[0083] Among them, strong correlation parameters are obtained according to the diagnosis results, and the strong correlation parameters in the historical reference parameters are eliminated to obtain historical target parameters. Historical reference parameters that are strongly correlated with each other can be obtained according to the diagnosis results. Only one representative or the historical reference parameter with the highest correlation degree is retained among the strongly correlated historical reference parameters, and other strongly correlated historical reference parameters are eliminated.

[0084] Step S30: constructing a basic building energy consumption model according to the historical target parameters, performing energy consumption simulation based on the basic building energy consumption model, and obtaining an electricity consumption coefficient.

[0085] It is understandable that the building energy consumption model can be a model constructed based on the current park buildings and the park's historical target parameters, while adding the temperature changes of the target park to the model, and performing dynamic simulation based on the park's temperature changes.

[0086] It should be understood that the energy consumption building model based on the target park may have a variety of different structures and building compositions. At the same time, different structures and different buildings may have different simulation results during the energy consumption simulation process. Based on historical energy consumption and simulated energy consumption, a more accurate basic building energy consumption model can be screened from multiple building energy consumption models.

[0087] It should be noted that the energy consumption coefficient is further obtained by making predictions through the basic building energy consumption model and calculating based on the prediction results and historical energy consumption.

[0088] Step S40: predicting the fixed energy consumption and variable energy consumption of the park according to the electricity consumption coefficient, and obtaining the predicted energy consumption of the target park according to the fixed energy consumption and variable energy consumption.

[0089] It should be noted that the electricity energy consumption coefficient includes the basic electricity energy consumption coefficient, the variable electricity energy consumption coefficient and the park energy consumption distribution factor.

[0090] It is understandable that the energy consumption of a park can be divided into fixed energy consumption and variable energy consumption. Fixed energy consumption can be understood as energy consumption that does not change significantly due to other factors, such as lighting energy consumption and building energy consumption; variable energy consumption can be understood as energy consumption that will change due to other factors, such as air conditioning energy consumption, which will change with temperature or season.

[0091] This embodiment analyzes the factors that affect the energy consumption of the industrial park, predicts future energy consumption from the basic electricity consumption and variable electricity consumption based on the factors with the highest correlation, and manages and adjusts the energy consumption of the industrial park according to the predicted energy consumption. The more accurate the prediction, the more lean management and control can be achieved, thereby avoiding unnecessary energy waste and achieving more environmentally friendly energy use.

[0092] refer to Figure 3 , Figure 3 This is a flow chart of a second embodiment of a method for predicting energy consumption in a park according to the present invention.

[0093] Based on the first embodiment described above, the park energy consumption prediction method of this embodiment includes, in step S10:

[0094] Step S11: Obtain the historical energy consumption and multiple historical initial parameters of the target park, where the historical initial parameters include building area, number of windows, number of air conditioners, number of staff, and per capita income.

[0095] It is understandable that the multiple historical initial parameters may be parameters that may affect the energy consumption of the park determined when the historical data of the park is collected.

[0096] It should be understood that the historical energy consumption may be the energy consumption of the target park in the past months or years, or may be more specific to the energy consumption per day or per hour. This embodiment is described using the energy consumption per month and per hour as examples.

[0097] It should be noted that each historical energy consumption has corresponding multiple historical initial parameters.

[0098] Step S12: constructing an original sequence according to the historical energy consumption of the target park and a plurality of historical initial parameters, and performing dimensionless processing on the original sequence to obtain a reference sequence.

[0099] It should be noted that the original sequence constructed according to the historical energy consumption of the target park and multiple historical initial parameters may be the original sequence of historical energy consumption and the original sequence of historical initial parameters corresponding to each historical energy consumption.

[0100] It should be further explained that the construction of the original sequence can refer to the following formula:

[0101]

[0102] Where l represents the historical energy consumption of l target parks; X l (i) represents the i-th historical initial parameter corresponding to the l-th historical energy consumption.

[0103] It is worth noting that the dimensionless processing of the original sequence may be normalization, standardization, least square method, etc. This embodiment does not limit this and can be adjusted according to actual conditions.

[0104] Step S13: Calculating the correlation coefficient between each historical initial parameter and the historical energy consumption in the reference sequence according to a preset resolution coefficient.

[0105] It is understandable that the preset resolution coefficient may be a parameter that is set based on experience to facilitate the calculation of the relationship between the original sequence of historical energy consumption and the original sequence of historical initial parameters corresponding to each historical energy consumption.

[0106] It should be noted that the correlation coefficient between each historical initial parameter and historical energy consumption in the reference sequence can be calculated according to the preset resolution coefficient by referring to the following formula:

[0107]

[0108] Wherein, ρ represents the preset resolution coefficient.

[0109] Step S14: performing energy consumption correlation analysis according to the correlation coefficient to obtain historical reference parameters.

[0110] It is understandable that performing energy consumption correlation analysis based on the correlation coefficient may be calculating the correlation between each historical initial parameter and the historical energy consumption based on the correlation coefficient, and screening each historical initial parameter based on the correlation to obtain the historical reference parameter.

[0111] It should be noted that the energy consumption correlation analysis based on the correlation coefficient to obtain the historical reference parameters may be performed by smoothing the various historical initial parameters and the historical energy consumption to obtain the smoothed historical initial parameters and historical energy consumption.

[0112] Among them, it is understandable that smoothing can weaken the fluctuation of data series, reduce its randomness, and adjust the changing trend of data series, so as to meet or approach the needs of decision-making. After smoothing the data, the fitting accuracy of the model can be further improved.

[0113] The correlation between each historical initial parameter and the historical energy consumption is calculated according to the correlation coefficient, the smoothed historical initial parameter and the historical energy consumption.

[0114] The correlation between each historical initial parameter and the historical energy consumption can be calculated by referring to the following formula:

[0115]

[0116] In the formula, Indicates the correlation between each historical initial parameter and historical energy consumption.

[0117] Then, the historical initial parameters are sorted according to the correlation degree, and a preset number of historical initial parameters after sorting are selected as historical reference parameters.

[0118] This example uses a grey correlation algorithm to initially identify the relationship between historical energy consumption and various influencing factors, obtaining correlation coefficients between each historical initial parameter and historical energy consumption. The correlation coefficients are then used to calculate the correlation between each historical initial parameter and historical energy consumption. Parameter screening of the historical initial parameters based on the correlation coefficients effectively identifies the parameters that most significantly impact park energy consumption, eliminating other factors and reducing the workload for energy consumption forecasting. This allows for more accurate simulation of park energy consumption and prediction of energy consumption when subsequently constructing a prediction model based on these parameters.

[0119] refer to Figure 4 , Figure 4 This is a flow chart of a second embodiment of a method for predicting energy consumption in a park according to the present invention.

[0120] Based on the first embodiment described above, the park energy consumption prediction method of this embodiment includes, in step S30:

[0121] Step S31: Obtain historical meteorological data of the target park.

[0122] It is understandable that the historical meteorological data of the target park may be the average temperature, the maximum temperature, and the minimum temperature of each day in the historical period.

[0123] It should be noted that if the energy consumption of the park at different times needs to be dynamically simulated through the model, the meteorological data of the target park should be used as the simulation basis. Detailed meteorological data can be found in Figure 5 .

[0124] Step S32: constructing multiple initial models according to the historical meteorological data and the historical target parameters, and simulating each initial model to obtain the simulated energy consumption corresponding to each initial model.

[0125] It is understandable that there are various situations in which multiple initial models are constructed based on the historical meteorological data and the historical target parameters. The historical meteorological data referenced in the initial model may include the daily average temperature, the daily maximum temperature, and the daily minimum temperature. The building models that can be obtained by the historical target parameters correspond to different model structures and different building structures, thereby constituting multiple initial models.

[0126] It should be understood that the simulated energy consumption obtained by simulating different models is not the same, and the simulated energy consumption is obtained by simulating the historical reference parameters corresponding to the historical energy consumption of each model.

[0127] It should be noted that the historical reference parameters are simulated through model simulation to obtain simulated energy consumption. Calculating the simulated energy consumption and the historical energy consumption corresponding to each historical reference parameter can further optimize the model or screen the model.

[0128] It should be further explained that, multiple energy consumption simulations can be performed on each model based on historical reference parameters corresponding to multiple historical energy consumptions.

[0129] Step S33: Calculate the energy consumption errors between the simulated energy consumption corresponding to each initial model and the historical energy consumption, and use the initial model corresponding to the minimum energy consumption error as the basic building energy consumption model.

[0130] It is understandable that multiple simulated energy consumptions can be obtained by simulating the reference parameters corresponding to each historical energy consumption through each model, and the absolute value of the difference between each simulated energy consumption and the historical energy consumption is calculated, and the mean square error of the difference is calculated based on the absolute value.

[0131] Furthermore, the model with the smallest mean energy variance is used as the basic building energy consumption model for the next step of energy consumption prediction.

[0132] Step S34: performing energy consumption simulation based on the basic building energy consumption model to obtain an electricity consumption coefficient.

[0133] It can be understood that according to the selected basic building energy consumption model, energy consumption prediction (energy consumption simulation) is carried out from the meteorological data of the month and the energy consumption already consumed in the month to obtain the electricity consumption coefficient.

[0134] In a specific implementation, the energy consumption simulation is performed based on the basic building energy consumption model to obtain the electricity energy consumption coefficient. The simulation can be performed based on the basic building energy consumption model to obtain building electricity, lighting electricity, and air-conditioning electricity; the basic electricity energy consumption coefficient is calculated based on the building electricity and lighting electricity, and the variable electricity energy consumption coefficient is calculated based on the air-conditioning electricity; and the park energy consumption distribution factor is constructed based on the basic electricity energy consumption coefficient and the variable electricity energy consumption coefficient.

[0135] Among them, the model can obtain building electricity, lighting electricity, and air-conditioning electricity respectively during simulation. Among them, building electricity and lighting electricity are relatively basic energy consumption and will not change much. The basic electricity energy consumption coefficient can be further calculated based on building electricity and lighting electricity.

[0136] Furthermore, the electricity consumption of air conditioners will vary greatly according to meteorological data (weather, temperature), and there are also certain interference factors in the changes. The variable electricity consumption coefficient can be calculated based on the electricity consumption of air conditioners.

[0137] In specific implementation, the calculation formulas for the basic electricity energy consumption coefficient, variable electricity energy consumption coefficient, and campus energy consumption distribution factor can refer to the following formulas:

[0138]

[0139] in, Indicates the basic electricity energy consumption coefficient, represents the energy consumption distribution factor of the park, Indicates the variable power consumption coefficient, X i Indicates the energy consumption in the current month, i indicates the i-th month, and n indicates the n-th hour in a year.

[0140] Furthermore, step S40: predicting the fixed energy consumption and variable energy consumption of the park according to the power consumption coefficient, and obtaining the predicted energy consumption of the target park according to the fixed energy consumption and the variable energy consumption, includes:

[0141] Obtain the current energy consumption of the park, make a prediction based on the current energy consumption of the park, the park energy consumption distribution factor and the basic electricity consumption coefficient to obtain a fixed energy consumption; make a prediction based on the current energy consumption of the park, the park energy consumption distribution factor and the variable electricity consumption coefficient to obtain a variable energy consumption; add the fixed energy consumption and the variable energy consumption to obtain the predicted energy consumption of the target park.

[0142] It should be noted that the calculation formulas for fixed energy consumption and variable energy consumption can refer to the following formulas:

[0143]

[0144] in, Indicates the basic electricity energy consumption coefficient, represents the energy consumption distribution factor of the park, Indicates the variable power consumption coefficient, X i Indicates the energy consumption in the current month, i indicates the i-th month, and n indicates the n-th hour in a year.

[0145] It is understandable that the energy consumption of the park is divided into fixed energy consumption and variable energy consumption. After predicting the fixed energy consumption and variable energy consumption respectively, the result of the two is used as the predicted energy consumption of the target park.

[0146] This embodiment uses the basic electricity consumption coefficient, variable electricity consumption coefficient and park energy consumption distribution factor, combined with the actual energy consumption model of the building, to quickly and accurately predict the hourly energy consumption data of this type of building, draw an energy consumption curve, and provide a basis for enterprises to monitor dynamic energy consumption and guide energy management. The energy consumption of industrial buildings also needs to further control and adjust energy consumption, and carry out lean management of energy use to avoid unnecessary energy waste.

[0147] In addition, an embodiment of the present invention further proposes a storage medium, on which a campus energy consumption prediction program is stored. When the campus energy consumption prediction program is executed by a processor, the steps of the campus energy consumption prediction method described above are implemented.

[0148] Reference Figure 6 , Figure 6 This is a structural block diagram of the first embodiment of the park energy consumption prediction device of the present invention.

[0149] like Figure 6 As shown, the park energy consumption prediction device proposed in the embodiment of the present invention includes:

[0150] The parameter acquisition module 10 is used to obtain the historical energy consumption and multiple historical initial parameters of the target park, perform energy consumption correlation analysis on each historical initial parameter, and obtain historical reference parameters;

[0151] The parameter acquisition module 10 is further configured to perform collinearity diagnosis on the historical reference parameters, and remove strongly correlated parameters from the historical reference parameters according to the diagnosis results to obtain historical target parameters;

[0152] An energy consumption prediction module 20 is configured to construct a basic building energy consumption model according to the historical target parameters, perform energy consumption simulation based on the basic building energy consumption model, and obtain an electricity consumption coefficient;

[0153] The energy consumption prediction module 20 is further configured to predict the fixed energy consumption and variable energy consumption of the park according to the electricity consumption coefficient, and obtain the predicted energy consumption of the target park according to the fixed energy consumption and variable energy consumption.

[0154] This embodiment analyzes the factors that affect the energy consumption of industrial parks, predicts future energy consumption from basic electricity consumption and variable electricity consumption based on the factors with the highest correlation, and manages and adjusts the energy consumption of the industrial park according to the predicted energy consumption. The more accurate the prediction, the more lean management and control can be achieved, thereby avoiding unnecessary energy waste and achieving more environmentally friendly energy use.

[0155] In one embodiment, the parameter acquisition module 10 is further configured to acquire historical energy consumption and a plurality of historical initial parameters of the target park, wherein the historical initial parameters include building area, number of windows, number of air conditioners, number of staff, and per capita income;

[0156] constructing an original sequence based on the historical energy consumption of the target park and a plurality of historical initial parameters, and performing dimensionless processing on the original sequence to obtain a reference sequence;

[0157] Calculating the correlation coefficient between each historical initial parameter and the historical energy consumption in the reference sequence according to a preset resolution coefficient;

[0158] An energy consumption correlation analysis is performed based on the correlation coefficient to obtain historical reference parameters.

[0159] In one embodiment, the parameter acquisition module 10 is further configured to perform smoothing on the historical initial parameters and the historical energy consumption to obtain smoothed historical initial parameters and historical energy consumption.

[0160] Calculating the correlation between each historical initial parameter and the historical energy consumption according to the correlation coefficient, the smoothed historical initial parameter and the historical energy consumption;

[0161] The historical initial parameters are sorted according to the correlation, and a preset number of historical initial parameters after sorting are selected as historical reference parameters.

[0162] In one embodiment, the parameter acquisition module 10 is further configured to construct a whitening differential equation based on the historical reference parameters, and calculate the whitening parameters based on the historical reference parameters;

[0163] Solving the whitening differential equation according to the whitening parameter to obtain a prediction model;

[0164] Verifying the historical reference parameters according to the prediction model to obtain a verification result, and performing collinearity diagnosis according to the verification result;

[0165] A strong correlation parameter is obtained according to the diagnosis result, and the strong correlation parameter in the historical reference parameter is eliminated to obtain a historical target parameter.

[0166] In one embodiment, the energy consumption prediction module 20 is further configured to obtain historical meteorological data of the target park;

[0167] constructing a plurality of initial models according to the historical meteorological data and the historical target parameters, and obtaining simulated energy consumption corresponding to each initial model by simulating each initial model;

[0168] Calculate the energy consumption error between the simulated energy consumption corresponding to each initial model and the historical energy consumption, and use the initial model corresponding to the minimum energy consumption error as the basic building energy consumption model;

[0169] Energy consumption simulation is performed based on the basic building energy consumption model to obtain the electricity consumption coefficient.

[0170] In one embodiment, the energy consumption prediction module 20 is further configured to perform simulation based on the basic building energy consumption model to obtain building electricity consumption, lighting electricity consumption, and air conditioning electricity consumption;

[0171] Calculate the basic electricity consumption coefficient based on the building electricity and lighting electricity, and calculate the variable electricity consumption coefficient based on the air conditioning electricity;

[0172] A park energy consumption distribution factor is constructed based on the basic electricity energy consumption coefficient and the variable electricity energy consumption coefficient.

[0173] In one embodiment, the energy consumption prediction module 20 is further configured to obtain the current energy consumption of the park, and perform prediction based on the current energy consumption of the park, the energy consumption distribution factor of the park, and the basic power consumption coefficient to obtain a fixed energy consumption;

[0174] Predicting the variable energy consumption based on the current energy consumption of the park, the energy consumption distribution factor of the park, and the variable electricity consumption coefficient;

[0175] The fixed energy consumption and the variable energy consumption are added together to obtain the predicted energy consumption of the target park.

[0176] It should be understood that the above is only an example and does not constitute any limitation to the technical solution of the present invention. In specific applications, those skilled in the art can make settings as needed, and the present invention does not impose any limitation on this.

[0177] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of the present invention. In practical applications, technicians in this field can select part or all of it according to actual needs to achieve the purpose of the embodiment scheme, and no limitation is made here.

[0178] In addition, it should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or system comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or system. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or system comprising the element.

[0179] The serial numbers of the above embodiments of the present invention are for description only and do not represent the advantages or disadvantages of the embodiments.

[0180] Through the above description of the embodiments, those skilled in the art will clearly understand that the methods of the above embodiments can be implemented using software plus the necessary general-purpose hardware platform. Of course, hardware can also be used, but in many cases the former is the more preferred implementation method. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as read-only memory (ROM) / RAM, a magnetic disk, or an optical disk) and includes a number of instructions for enabling a terminal device (such as a mobile phone, computer, server, or network device) to execute the methods described in the various embodiments of the present invention.

[0181] The above are only preferred embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for predicting energy consumption in a park, characterized in that: The park energy consumption prediction method comprises: Obtain the historical energy consumption and multiple historical initial parameters of the target park, perform energy consumption correlation analysis on each historical initial parameter, and obtain historical reference parameters; Performing collinearity diagnosis on the historical reference parameters, and eliminating strongly correlated parameters in the historical reference parameters according to the diagnosis results to obtain historical target parameters; Constructing a basic building energy consumption model according to the historical target parameters, performing energy consumption simulation based on the basic building energy consumption model, and obtaining an electricity consumption coefficient; Predicting the fixed energy consumption and variable energy consumption of the park according to the power consumption coefficient, and obtaining the predicted energy consumption of the target park according to the fixed energy consumption and variable energy consumption; The historical energy consumption and multiple historical initial parameters of the target park are obtained, and the energy consumption correlation analysis of each historical initial parameter is performed to obtain the historical reference parameters, including: Obtaining historical energy consumption and multiple historical initial parameters of the target park, wherein the historical initial parameters include building area, number of windows, number of air conditioners, number of personnel, and per capita income; constructing an original sequence according to the historical energy consumption of the target park and a plurality of historical initial parameters, and performing dimensionless processing on the original sequence to obtain a reference sequence; Calculating the correlation coefficient between each historical initial parameter and the historical energy consumption in the reference sequence according to a preset resolution coefficient; Perform energy consumption correlation analysis according to the correlation coefficient to obtain historical reference parameters; The energy consumption correlation analysis is performed according to the correlation coefficient to obtain historical reference parameters, including: Smoothing the various historical initial parameters and the historical energy consumption to obtain smoothed historical initial parameters and historical energy consumption; Calculate the correlation between each historical initial parameter and the historical energy consumption according to the correlation coefficient, the smoothed historical initial parameter and the historical energy consumption; Sorting the historical initial parameters according to the correlation, and selecting a preset number of historical initial parameters after the sorting as historical reference parameters; The performing collinearity diagnosis on the historical reference parameters and eliminating strongly correlated parameters in the historical reference parameters according to the diagnosis results to obtain historical target parameters includes: constructing a whitening differential equation according to the historical reference parameters, and calculating a whitening parameter according to the historical reference parameters; Solving the whitening differential equation according to the whitening parameter to obtain a prediction model; Verifying the historical reference parameters according to the prediction model to obtain verification results, and performing collinearity diagnosis according to the verification results; Obtaining a strongly correlated parameter according to the diagnosis result, eliminating the strongly correlated parameters in the historical reference parameters, and obtaining a historical target parameter; The step of constructing a basic building energy consumption model according to the historical target parameters, performing energy consumption simulation based on the basic building energy consumption model, and obtaining an electricity consumption coefficient includes: Obtain historical meteorological data of the target park; Constructing a plurality of initial models according to the historical meteorological data and the historical target parameters, and obtaining simulated energy consumption corresponding to each initial model by simulating each initial model; Calculate the energy consumption errors between the simulated energy consumption corresponding to each initial model and the historical energy consumption respectively, and use the initial model corresponding to the minimum energy consumption error as the basic building energy consumption model; Energy consumption simulation is performed based on the basic building energy consumption model to obtain the electricity consumption coefficient.

2. The method for predicting park energy consumption according to claim 1, characterized in that: The electricity consumption coefficient includes a basic electricity consumption coefficient, a variable electricity consumption coefficient and a park energy consumption distribution factor; The energy consumption simulation is performed based on the basic building energy consumption model to obtain the electricity consumption coefficient, including: Based on the basic building energy consumption model, simulation is performed to obtain building electricity, lighting electricity, and air conditioning electricity; Calculate the basic electricity consumption coefficient based on the building electricity and lighting electricity, and calculate the variable electricity consumption coefficient based on the air conditioning electricity; A park energy consumption distribution factor is constructed according to the basic electricity energy consumption coefficient and the variable electricity energy consumption coefficient.

3. The method for predicting park energy consumption according to claim 2, characterized in that: The step of predicting the fixed energy consumption and the variable energy consumption of the park according to the power consumption coefficient, and obtaining the predicted energy consumption of the target park according to the fixed energy consumption and the variable energy consumption, includes: Obtain the current energy consumption of the park, and make a prediction based on the current energy consumption of the park, the energy consumption distribution factor of the park, and the basic electricity consumption coefficient to obtain a fixed energy consumption; Predicting based on the current energy consumption of the park, the energy consumption distribution factor of the park and the variable power consumption coefficient to obtain variable energy consumption; The fixed energy consumption and the variable energy consumption are added together to obtain the predicted energy consumption of the target park.

4. A park energy consumption prediction device, characterized in that: The park energy consumption prediction device comprises: A parameter acquisition module is used to obtain the historical energy consumption and multiple historical initial parameters of the target park, perform energy consumption correlation analysis on each historical initial parameter, and obtain historical reference parameters; The parameter acquisition module is further used to perform collinearity diagnosis on the historical reference parameters, and remove strongly correlated parameters from the historical reference parameters according to the diagnosis results to obtain historical target parameters; An energy consumption prediction module is used to construct a basic building energy consumption model according to the historical target parameters, perform energy consumption simulation based on the basic building energy consumption model, and obtain an electricity consumption coefficient; The energy consumption prediction module is further used to predict the fixed energy consumption and variable energy consumption of the park according to the power consumption coefficient, and obtain the predicted energy consumption of the target park according to the fixed energy consumption and variable energy consumption; The parameter acquisition module is further used to acquire the historical energy consumption and multiple historical initial parameters of the target park, wherein the historical initial parameters include building area, number of windows, number of air conditioners, number of personnel, and per capita income; construct an original sequence according to the historical energy consumption and multiple historical initial parameters of the target park, perform dimensionless processing on the original sequence, and obtain a reference sequence; calculate the correlation coefficient between each historical initial parameter and the historical energy consumption in the reference sequence according to a preset resolution coefficient; perform energy consumption correlation analysis according to the correlation coefficient to obtain historical reference parameters; The parameter acquisition module is further used to smooth the various historical initial parameters and the historical energy consumption to obtain the smoothed historical initial parameters and historical energy consumption; calculate the correlation between the various historical initial parameters and the historical energy consumption according to the correlation coefficient, the smoothed historical initial parameters and the historical energy consumption; sort the various historical initial parameters according to the correlation, and select a preset number of historical initial parameters after sorting as historical reference parameters; The parameter acquisition module is further used to construct a whitened differential equation according to the historical reference parameters, calculate the whitened parameters according to the historical reference parameters; solve the whitened differential equation according to the whitened parameters to obtain a prediction model; verify the historical reference parameters according to the prediction model to obtain a verification result, and perform collinearity diagnosis according to the verification result; obtain a strongly correlated parameter according to the diagnosis result, eliminate the strongly correlated parameters in the historical reference parameters, and obtain a historical target parameter; The energy consumption prediction module is also used to obtain historical meteorological data of the target park; construct multiple initial models according to the historical meteorological data and the historical target parameters, and obtain the simulated energy consumption corresponding to each initial model by simulating each initial model; calculate the energy consumption error between the simulated energy consumption corresponding to each initial model and the historical energy consumption, and use the initial model corresponding to the minimum energy consumption error as the basic building energy consumption model; perform energy consumption simulation based on the basic building energy consumption model to obtain the electricity energy consumption coefficient.

5. A park energy consumption prediction device, characterized in that: The device includes: a memory, a processor, and a campus energy consumption prediction program stored in the memory and executable on the processor, wherein the campus energy consumption prediction program is configured to implement the campus energy consumption prediction method as described in any one of claims 1 to 3.

6. A storage medium, characterized in that: The storage medium stores a campus energy consumption prediction program, which, when executed by a processor, implements the campus energy consumption prediction method as described in any one of claims 1 to 3.

Images