Method and device for affirming electric quantity of electric energy alternative project
By constructing a transformation matrix using dimensionality reduction and replication techniques, and combining it with a deviation analysis model, the problem of high resource input in the electricity consumption identification method for electricity substitution projects was solved, achieving efficient and accurate electricity consumption identification.
Patent Information
- Application Number
- CN202511849274.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-09
- Publication Date
- 2026-03-20
AI Technical Summary
Existing methods for determining the amount of electricity required for electricity substitution projects require a large amount of preliminary data and resource investment, and the models lack generalization ability, resulting in inaccurate assessments.
By acquiring the electricity consumption data queue and influencing factors of alternative projects, a transformation matrix is constructed using dimensionality reduction and reproduction techniques. The deviation is calculated and standardized, and the reliability of the electricity consumption data is determined by combining the deviation analysis model.
It reduces reliance on massive amounts of data, simplifies model building and application processes, reduces resource consumption, and improves the accuracy and efficiency of electricity consumption identification for electricity substitution projects.
Smart Images
Figure CN121707046A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of power metering technology, and in particular to a method and device for determining the amount of electricity used in electricity substitution projects. Background Technology
[0002] Electricity substitution, as a key measure to promote energy structure optimization and green and low-carbon transformation, is crucial for reducing dependence on fossil fuels, lowering carbon emissions, and achieving the "dual carbon" goals. However, electricity substitution faces many challenges, such as increased difficulty in technology promotion and inaccurate evaluation of project effectiveness.
[0003] The determination of electricity consumption for electricity substitution projects is an important factor in evaluating the return on investment of these projects. Currently, some projects use generative artificial intelligence models to simulate energy supply and demand relationships under different scenarios to assist in the dynamic optimization of solutions. However, in practical applications, issues such as data fusion and model generalization capabilities still need to be addressed.
[0004] Some projects that are already in operation have also tried to use artificial intelligence to analyze the credibility of the electricity consumption of electricity substitution projects. However, these technologies require a large amount of preliminary data, as well as a lot of preliminary modeling and subsequent operation and maintenance work, resulting in a large investment of resources.
[0005] Therefore, it is necessary to develop a method for determining the amount of electricity used in electricity substitution projects. Summary of the Invention
[0006] The present invention provides a method and apparatus for determining the amount of electricity required for electricity substitution projects, which addresses the problem that existing methods for determining the amount of electricity required for electricity substitution projects involve significant manpower and material resources.
[0007] In a first aspect, embodiments of the present invention provide a method for determining the amount of electricity required for an electricity substitution project, including: Obtain the first electricity consumption data queue of the alternative projects and the first factor affecting the electricity consumption of the alternative projects; Based on the first factor, a first dimension transformation matrix is selected. The first power consumption data queue is then dimensionality-reduced and reproduced using the first dimension transformation matrix to obtain a second power consumption data queue. The power consumption data queue is dimensionality-reduced using the first dimension transformation matrix to obtain the main feature dimension. Calculate the deviation between the first electricity consumption data queue and the second electricity consumption data queue, and standardize the obtained deviation to obtain the first deviation queue; The first deviation queue is input into the deviation analysis model, and the reliability of the first electricity consumption data queue is determined based on the output of the deviation analysis model.
[0008] In one possible implementation, the first transformation matrix is obtained based on multiple historical first electricity consumption data queues, including: Multiple second transformation matrices and multiple historical first electricity consumption data queues are obtained, wherein the first factor affects the fluctuation characteristics of historical first electricity consumption; For each second transformation matrix, dimensionality reduction and reproduction are performed on each of the plurality of historical first electricity consumption data queues according to the second transformation matrix, and the first transformation deviation is determined based on the obtained plurality of historical second electricity consumption data queues; If the predetermined number of iterations is reached, the second transformation matrix with the smallest first transformation deviation is taken as the first transformation matrix; Otherwise, the plurality of second conversion matrices are adjusted according to the plurality of first conversion deviations, and the process jumps to the step of performing dimensionality reduction and reproduction on each of the plurality of historical first electricity consumption data queues for each second conversion matrix, and determining the first conversion deviation based on the obtained plurality of historical second electricity consumption data.
[0009] In one possible implementation, the step of performing dimensionality reduction and replication on each of the plurality of historical first electricity consumption data queues according to the second transformation matrix, and determining the first transformation deviation based on the obtained plurality of historical second electricity consumption data queues, includes: Based on the second transformation matrix and the first formula, each of the multiple historical first electricity consumption data queues is subjected to dimensionality reduction and reproduction to obtain multiple historical second electricity consumption data queues, wherein the first formula is:
[0010] In the formula, This is the second-highest historical electricity consumption data queue. This is the first queue for electricity consumption data. This is the second transformation matrix; The first conversion deviation is determined according to the second formula, whereby the second formula is:
[0011] In the formula, This is the first conversion bias. For the first The second historical electricity consumption data queue One data point, For the first The first historical electricity consumption data queue One data point, This represents the total number of electricity consumption data queues in history. This represents the total number of data points in the historical first electricity consumption data queue. This is the average of data from multiple historical first electricity consumption data queues.
[0012] In one possible implementation, adjusting the plurality of second transformation matrices according to the plurality of first transformation deviations includes: The second transformation matrix corresponding to the first transformation deviation with the smallest value is used as the global matrix; Based on the correspondence between the first conversion deviation and the second conversion matrix, the plurality of first conversion deviations are added to a plurality of first deviation queues respectively, wherein each second conversion matrix corresponds to a first deviation queue; For each first deviation queue, the historical second transformation matrix corresponding to the minimum value in the queue is used as the historical matrix; For each second transformation matrix, adjustments are made according to the third formula, the global matrix, and the corresponding historical matrix, wherein the third formula is:
[0013] In the formula, For the adjusted second matrix, the first... Line number Column elements, For the second matrix before adjustment, the first... Line number Column elements, The first in the global matrix Line number Column elements, The first in the history matrix Line number Column elements, For global coefficients, Historical coefficients This is the bias coefficient.
[0014] In one possible implementation, the step of calculating the deviation between the first electricity consumption data queue and the second electricity consumption data queue, and standardizing the obtained deviation to obtain a first deviation queue, includes: Perform a subtraction operation on the first power consumption data queue and the second power consumption data queue bit by bit to obtain the difference queue; The difference queue is normalized to obtain the first deviation queue.
[0015] In one possible implementation, the deviation analysis model is constructed based on multiple historical first deviation queues, including: Multiple historical first deviation queues and multiple credibility labels are obtained. Each historical first deviation queue corresponds to a credibility label. The historical first deviation queues are obtained by performing deviation calculations and standardization based on the historical first electricity consumption data queue and the reproduction queue of the historical first electricity consumption data queue. Substitute the multiple historical first deviation queues into the process model to obtain multiple first confidence levels; The prediction loss of the model is determined based on the plurality of first confidence levels and the plurality of confidence level labels; If the predicted loss is greater than the loss threshold, then the multiple coefficients of the process model are optimized by an optimization algorithm based on the predicted loss, and the process jumps to the step of substituting the multiple historical first deviation queues into the process model to obtain multiple first confidence levels. Otherwise, the process model is used as the deviation analysis model.
[0016] In one possible implementation, the process model is as follows:
[0017] In the formula, The first confidence level of the model output. It is a natural constant. As joint variables, For the first Each model coefficient For the deviation queue One data point, The bias constant is This represents the total number of data items in the deviation queue.
[0018] In one possible implementation, determining the model's prediction loss based on the plurality of first confidence levels and the plurality of confidence level labels includes: The prediction loss of the model is determined based on the fourth formula, the plurality of first confidence levels, and the plurality of confidence level labels, wherein the fourth formula is:
[0019] In the formula, To predict losses, The number of credibility tags, For the first A credibility tag, For the first Firstly, credibility.
[0020] In one possible implementation, optimizing multiple coefficients of the process model using an optimization algorithm based on the predicted loss includes: The predicted loss is used to optimize multiple coefficients of the process model using a fifth formula, wherein the fifth formula is:
[0021] In the formula, For the optimized first Each model coefficient For the first time before optimization Each model coefficient As the first optimization coefficient, The optimized bias constant. This is the bias constant before optimization.
[0022] In a second aspect, embodiments of the present invention provide an energy consumption determination device for electricity substitution projects, used to implement the energy consumption determination method for electricity substitution projects as described in the first aspect or any possible implementation thereof, the energy consumption determination device for electricity substitution projects comprising: The data acquisition module is used to acquire the first electricity consumption data queue of the alternative project and the first factor affecting the electricity consumption of the alternative project; The queue reconstruction module is used to select a first dimension transformation matrix based on the first factor, and to perform dimensionality reduction and reproduction on the first electricity consumption data queue through the first dimension transformation matrix to obtain a second electricity consumption data queue. The electricity consumption data queue obtains the main feature dimension through dimensionality reduction of the first dimension transformation matrix. The deviation calculation module is used to calculate the deviation between the first electricity consumption data queue and the second electricity consumption data queue, and to standardize the obtained deviation to obtain the first deviation queue. as well as, The data credibility determination module is used to input the first deviation queue into the deviation analysis model and determine the credibility of the first electricity consumption data queue based on the output of the deviation analysis model.
[0023] The beneficial effects of the embodiments of the present invention compared with the prior art are as follows: This invention discloses a method for determining the electricity consumption of electricity substitution projects. First, it obtains a first electricity consumption data queue for the substitution project and a first factor influencing the electricity consumption of the substitution project. Then, based on the first factor, it selects a first dimension transformation matrix and performs dimensionality reduction and replication on the first electricity consumption data queue using the first dimension transformation matrix to obtain a second electricity consumption data queue. The electricity consumption data queue is dimensionality reduced using the first dimension transformation matrix to obtain the main feature dimension. Next, it calculates the deviation between the first and second electricity consumption data queues and standardizes the obtained deviation to obtain a first deviation queue. Finally, it inputs the first deviation queue into a deviation analysis model, and determines the credibility of the first electricity consumption data queue based on the output of the deviation analysis model. This invention achieves the transformation of the first electricity consumption data queue through dimensionality reduction and replication, and then performs deviation calculations between the obtained data queue and the first electricity consumption data queue. Based on the results of the deviation calculations, credibility analysis is performed using a deviation analysis model. The above process does not require massive amounts of preliminary data, and the deviation analysis model is relatively simple. Therefore, the construction and application processes consume fewer resources and are suitable for widespread application. Attached Figure Description
[0024] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0025] Figure 1 This is a flowchart of the method for determining the amount of electricity used in an electricity substitution project provided by an embodiment of the present invention; Figure 2 This is a schematic diagram of the first transformation matrix construction process provided by an embodiment of the present invention; Figure 3 This is a functional block diagram of the electricity consumption determination device for electricity substitution projects provided in the embodiments of the present invention. Detailed Implementation
[0026] In the following description, specific details such as particular system structures and techniques are set forth for illustrative purposes and not for limitation, so as to provide a thorough understanding of embodiments of the invention. However, those skilled in the art will understand that the invention can be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, and methods are omitted so as not to obscure the description of the invention with unnecessary detail.
[0027] To make the objectives, technical solutions, and advantages of the present invention clearer, specific embodiments will be described below in conjunction with the accompanying drawings.
[0028] The embodiments of the present invention will be described in detail below. This example is implemented based on the technical solution of the present invention, and provides detailed implementation methods and specific operation processes. However, the protection scope of the present invention is not limited to the following embodiments.
[0029] Figure 1 A flowchart illustrating the method for determining the amount of electricity used in an energy substitution project, as provided in an embodiment of the present invention.
[0030] like Figure 1 As shown, it illustrates the implementation flowchart of the electricity consumption determination method for electricity substitution projects provided by the embodiments of the present invention, which is described in detail below: In step 101, the first electricity consumption data queue of the alternative project and the first factor affecting the electricity consumption of the alternative project are obtained.
[0031] In step 102, a first dimension transformation matrix is selected based on the first factor. The first dimension transformation matrix is used to reduce the dimensionality of the first electricity consumption data queue and reproduce it to obtain a second electricity consumption data queue. The electricity consumption data queue is reduced in dimensionality by the first dimension transformation matrix to obtain the main feature dimension.
[0032] In some implementations, the first conversion matrix is obtained based on multiple historical first electricity consumption data queues, including: Multiple second transformation matrices and multiple historical first electricity consumption data queues are obtained, wherein the first factor affects the fluctuation characteristics of historical first electricity consumption; For each second transformation matrix, dimensionality reduction and reproduction are performed on each of the plurality of historical first electricity consumption data queues according to the second transformation matrix, and the first transformation deviation is determined based on the obtained plurality of historical second electricity consumption data queues; If the predetermined number of iterations is reached, the second transformation matrix with the smallest first transformation deviation is taken as the first transformation matrix; Otherwise, the plurality of second conversion matrices are adjusted according to the plurality of first conversion deviations, and the process jumps to the step of performing dimensionality reduction and reproduction on each of the plurality of historical first electricity consumption data queues for each second conversion matrix, and determining the first conversion deviation based on the obtained plurality of historical second electricity consumption data.
[0033] In some implementations, the step of performing dimensionality reduction and reproduction on each of the plurality of historical first electricity consumption data queues according to the second transformation matrix, and determining the first transformation deviation based on the obtained plurality of historical second electricity consumption data queues, includes: Based on the second transformation matrix and the first formula, each of the multiple historical first electricity consumption data queues is subjected to dimensionality reduction and reproduction to obtain multiple historical second electricity consumption data queues, wherein the first formula is:
[0034] In the formula, This is the second-highest historical electricity consumption data queue. This is the first queue for electricity consumption data. This is the second transformation matrix; The first conversion deviation is determined according to the second formula, whereby the second formula is:
[0035] In the formula, This is the first conversion bias. For the first The second historical electricity consumption data queue One data point, For the first The first historical electricity consumption data queue One data point, This represents the total number of electricity consumption data queues in history. This represents the total number of data points in the historical first electricity consumption data queue. This is the average of data from multiple historical first electricity consumption data queues.
[0036] In some embodiments, adjusting the plurality of second transformation matrices according to the plurality of first transformation deviations includes: The second transformation matrix corresponding to the first transformation deviation with the smallest value is used as the global matrix; Based on the correspondence between the first conversion deviation and the second conversion matrix, the plurality of first conversion deviations are added to a plurality of first deviation queues respectively, wherein each second conversion matrix corresponds to a first deviation queue; For each first deviation queue, the historical second transformation matrix corresponding to the minimum value in the queue is used as the historical matrix; For each second transformation matrix, adjustments are made according to the third formula, the global matrix, and the corresponding historical matrix, wherein the third formula is:
[0037] In the formula, For the adjusted second matrix, the first... Line number Column elements, For the second matrix before adjustment, the first... Line number Column elements, The first in the global matrix Line number Column elements, The first in the history matrix Line number Column elements, For global coefficients, Historical coefficients This is the bias coefficient.
[0038] For example, the present invention aims to provide a relatively simple method for determining the electricity consumption of electricity substitution projects without requiring massive amounts of data. This method involves first reducing and reproducing the acquired first electricity data queue using a pre-constructed first transformation matrix, then performing a deviation calculation between the resulting first deviation queue and the original queue, and finally analyzing the credibility of the electricity consumption of electricity substitution projects based on the first deviation queue.
[0039] In this data, the first electricity consumption data queue is obtained by arranging the electricity consumption of replacement projects in chronological order. Because the characteristics of the replacement project data queue are affected by external factors, such as the seasonality of residential projects, this invention extracts the factors affecting the characteristics of the first electricity consumption data queue before analysis. Based on these factors, a first-dimensional transformation matrix is selected. Using this first-dimensional transformation matrix, dimensionality reduction and reproduction are performed using the following formula to obtain the reproduced second electricity consumption data queue:
[0040] In the formula, This is the second electricity consumption data queue. This is the first queue for electricity consumption data. This is the first transformation matrix.
[0041] As we can see, the first transformation matrix is key to achieving reproduction. In fact, this invention constructs this matrix using multiple historical first-time electricity consumption data queues.
[0042] like Figure 2 As shown, specifically, when constructing the first transformation matrix, multiple second transformation matrices 202 and multiple historical first electricity consumption data queues 201 are first obtained. Note that the fluctuation characteristics of historical first electricity consumption are also affected by the first factor. Then, for each historical first electricity consumption data queue 201 in the multiple historical first electricity consumption data queues 201 according to each second transformation matrix 202, dimensionality reduction and reproduction are performed respectively. In one scenario, the first formula is applied:
[0043] In the formula, This is the second highest historical electricity consumption data queue, number 203. This is the first historical electricity consumption data queue 201. This is the second transformation matrix 202.
[0044] After obtaining multiple second historical electricity consumptions based on each second conversion matrix 202, we then calculate the conversion deviation based on the second formula to obtain the first conversion deviation 204:
[0045] In the formula, The first conversion deviation is 204. For the first The second historical electricity consumption data queue One data point, For the first The first historical electricity consumption data queue One data point, This represents the total number of electricity consumption data queues in history. This represents the total number of data points in the historical first electricity consumption data queue. This is the average of data from multiple historical first electricity consumption data queues.
[0046] The above transformation deviation is the formula for verifying the accuracy of the reproduction of the second transformation matrix 202.
[0047] After obtaining the first transformation deviation 204, if a predetermined number of iterations is reached, the second transformation matrix 202 with the smallest first transformation deviation 204 is taken as the first transformation matrix. If the predetermined number of iterations is not reached, multiple second transformation matrices 202 need to be adjusted based on multiple first transformation deviations 204.
[0048] During adjustment, the second transformation matrix 202 corresponding to the smallest first transformation deviation 204 is firstly used as the global matrix. Then, multiple first transformation deviations 204 are added to multiple first deviation queues respectively. Note that each first deviation queue corresponds to a second transformation matrix 202. After adding them, the historical second transformation matrix 202 corresponding to the minimum value in each first deviation queue is used as the historical matrix.
[0049] Finally, each second transformation matrix 202 is adjusted according to the third formula, the global matrix, and the corresponding historical matrix, wherein the third formula is:
[0050] In the formula, For the adjusted second matrix, the first... Line number Column elements, For the second matrix before adjustment, the first... Line number Column elements, The first in the global matrix Line number Column elements, The first in the history matrix Line number Column elements, For global coefficients, Historical coefficients This is the bias coefficient.
[0051] After the adjustment is completed, repeat the above steps of dimensionality reduction and reproduction for each of the multiple historical first electricity consumption data queues 201 according to each second transformation matrix 202.
[0052] After the above steps, a transformation matrix can be obtained that ensures the deviation between the reproduced queue and the original queue.
[0053] In step 103, the deviation between the first electricity consumption data queue and the second electricity consumption data queue is calculated, and the obtained deviation is standardized to obtain the first deviation queue.
[0054] In some implementations, calculating the deviation between the first electricity consumption data queue and the second electricity consumption data queue, and standardizing the obtained deviation to obtain a first deviation queue, includes: Perform a subtraction operation on the first power consumption data queue and the second power consumption data queue bit by bit to obtain the difference queue; The difference queue is normalized to obtain the first deviation queue.
[0055] In step 104, the first deviation queue is input into the deviation analysis model, and the reliability of the first electricity consumption data queue is determined based on the output of the deviation analysis model.
[0056] In some implementations, the deviation analysis model is constructed based on multiple historical first deviation queues, including: Multiple historical first deviation queues and multiple credibility labels are obtained. Each historical first deviation queue corresponds to a credibility label. The historical first deviation queues are obtained by performing deviation calculations and standardization based on the historical first electricity consumption data queue and the reproduction queue of the historical first electricity consumption data queue. Substitute the multiple historical first deviation queues into the process model to obtain multiple first confidence levels; The prediction loss of the model is determined based on the plurality of first confidence levels and the plurality of confidence level labels; If the predicted loss is greater than the loss threshold, then the multiple coefficients of the process model are optimized by an optimization algorithm based on the predicted loss, and the process jumps to the step of substituting the multiple historical first deviation queues into the process model to obtain multiple first confidence levels. Otherwise, the process model is used as the deviation analysis model.
[0057] In some implementations, the process model is as follows:
[0058] In the formula, The first confidence level of the model output. It is a natural constant. As joint variables, For the first Each model coefficient For the deviation queue One data point, The bias constant is This represents the total number of data items in the deviation queue.
[0059] In some implementations, determining the model's prediction loss based on the plurality of first confidence levels and the plurality of confidence level labels includes: The prediction loss of the model is determined based on the fourth formula, the plurality of first confidence levels, and the plurality of confidence level labels, wherein the fourth formula is:
[0060] In the formula, To predict losses, The number of credibility tags, For the first A credibility tag, For the first Firstly, credibility.
[0061] In some implementations, optimizing multiple coefficients of the process model using an optimization algorithm based on the predicted loss includes: The predicted loss is used to optimize multiple coefficients of the process model using a fifth formula, wherein the fifth formula is:
[0062] In the formula, For the optimized first Each model coefficient For the first time before optimization Each model coefficient As the first optimization coefficient, The optimized bias constant. This is the bias constant before optimization.
[0063] For example, after obtaining the second electricity consumption data queue, the data in the first electricity consumption data queue and the data in the second electricity consumption data queue can be subtracted to obtain the difference queue. The difference queue is then normalized to obtain the first deviation queue.
[0064] The first deviation queue is substituted into the deviation analysis model, which will give a value between 0 and 1. A value greater than 0.5 indicates high confidence, and the confidence is proportional to the value. A value less than 0.5 indicates low confidence, and the smaller the value, the lower the confidence.
[0065] In fact, the model is constructed based on multiple historical first deviation queues. Each historical first deviation queue corresponds to a confidence label. The process of obtaining the historical first deviation queue is the same as that of obtaining the first deviation queue. It is obtained by performing deviation calculations and standardization based on the historical first electricity consumption data queue and the reproduction queue of the historical first electricity consumption data queue.
[0066] When constructing the model, multiple historical first deviation queues are first substituted into the process model to obtain multiple first confidence levels. Here, the process model is:
[0067] In the formula, The first confidence level of the model output. It is a natural constant. As joint variables, For the first Each model coefficient For the deviation queue One data point, The bias constant is This represents the total number of data items in the deviation queue.
[0068] Then, based on the fourth formula, multiple first confidence levels, and multiple confidence level labels, the model's prediction loss is determined:
[0069] In the formula, To predict losses, The number of credibility tags, For the first A credibility tag, For the first Firstly, credibility.
[0070] If the predicted loss is greater than the loss threshold, the process model's multiple coefficients are optimized using an optimization algorithm based on the predicted loss. Specifically, in one scenario, the fifth formula is used for optimization:
[0071] In the formula, For the optimized first Each model coefficient For the first time before optimization Each model coefficient As the first optimization coefficient, The optimized bias constant. This is the bias constant before optimization.
[0072] After optimization, repeat the above steps of substituting multiple historical first deviation queues into the process model to obtain multiple first confidence levels.
[0073] After multiple iterations, when the predicted loss is less than the loss threshold, the process model can be used as the deviation analysis model.
[0074] The present invention discloses an implementation method for determining the electricity consumption of electricity substitution projects. First, it acquires a first electricity consumption data queue for the substitution project and a first factor influencing the electricity consumption of the substitution project. Then, based on the first factor, it selects a first dimension transformation matrix and performs dimensionality reduction and replication on the first electricity consumption data queue using the first dimension transformation matrix to obtain a second electricity consumption data queue. The electricity consumption data queue is dimensionality reduced using the first dimension transformation matrix to obtain the main feature dimension. Next, it calculates the deviation between the first and second electricity consumption data queues and standardizes the obtained deviation to obtain a first deviation queue. Finally, it inputs the first deviation queue into a deviation analysis model, and determines the credibility of the first electricity consumption data queue based on the output of the deviation analysis model. This invention achieves the transformation of the first electricity consumption data queue through dimensionality reduction and replication, and then performs deviation calculations between the obtained data queue and the first electricity consumption data queue. Based on the results of the deviation calculations, a credibility analysis is performed using a deviation analysis model. The above process does not require massive amounts of preliminary data, and the deviation analysis model is relatively simple. Therefore, the construction and application processes consume fewer resources and are suitable for widespread application.
[0075] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.
[0076] The following are embodiments of the apparatus of the present invention. For details not described in detail, please refer to the corresponding method embodiments described above.
[0077] Figure 3 This is a functional block diagram of the electricity consumption determination device for electricity substitution projects provided in the embodiments of the present invention, with reference to... Figure 3 The electricity consumption verification device for the electricity substitution project includes: a data acquisition module 301, a queue reconstruction module 302, a deviation calculation module 303, and a data reliability determination module 304, wherein: Data acquisition module 301 is used to acquire the first power consumption data queue of the alternative project and the first factor affecting the power consumption of the alternative project; The queue reconstruction module 302 is used to select a dimension first transformation matrix according to the first factor, and to perform dimensionality reduction and reproduction on the first electricity consumption data queue through the first dimension transformation matrix to obtain a second electricity consumption data queue, wherein the electricity consumption data queue obtains the main feature dimension through dimensionality reduction of the first dimension transformation matrix; The deviation calculation module 303 is used to calculate the deviation between the first electricity consumption data queue and the second electricity consumption data queue, and to standardize the obtained deviation to obtain the first deviation queue. The data credibility determination module 304 is used to input the first deviation queue into the deviation analysis model and determine the credibility of the first electricity consumption data queue based on the output of the deviation analysis model.
[0078] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the aforementioned method embodiments, and will not be repeated here.
[0079] In the above embodiments, the descriptions of each embodiment have their own emphasis. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.
[0080] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.
[0081] In the embodiments provided by this invention, it should be understood that the disclosed devices / electronic devices and methods can be implemented in other ways. For example, the device / electronic device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.
[0082] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.
[0083] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.
[0084] If the integrated module / unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the above-described embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various methods and apparatus embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.
[0085] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.
Claims
1. A method for determining the amount of electricity required for an electricity substitution project, characterized in that, include: Obtain the first electricity consumption data queue of the alternative projects and the first factor affecting the electricity consumption of the alternative projects; Based on the first factor, a first dimension transformation matrix is selected. The first power consumption data queue is then dimensionality-reduced and reproduced using the first dimension transformation matrix to obtain a second power consumption data queue. The power consumption data queue is dimensionality-reduced using the first dimension transformation matrix to obtain the main feature dimension. Calculate the deviation between the first electricity consumption data queue and the second electricity consumption data queue, and standardize the obtained deviation to obtain the first deviation queue; The first deviation queue is input into the deviation analysis model, and the reliability of the first electricity consumption data queue is determined based on the output of the deviation analysis model.
2. The method for determining the amount of electricity used in electricity substitution projects according to claim 1, characterized in that, The first conversion matrix is obtained based on multiple historical first electricity consumption data queues, including: Multiple second transformation matrices and multiple historical first electricity consumption data queues are obtained, wherein the first factor affects the fluctuation characteristics of historical first electricity consumption; For each second transformation matrix, dimensionality reduction and reproduction are performed on each of the plurality of historical first electricity consumption data queues according to the second transformation matrix, and the first transformation deviation is determined based on the obtained plurality of historical second electricity consumption data queues; If the predetermined number of iterations is reached, the second transformation matrix with the smallest first transformation deviation is taken as the first transformation matrix; Otherwise, the plurality of second conversion matrices are adjusted according to the plurality of first conversion deviations, and the process jumps to the step of performing dimensionality reduction and reproduction on each of the plurality of historical first electricity consumption data queues for each second conversion matrix, and determining the first conversion deviation based on the obtained plurality of historical second electricity consumption data.
3. The method for determining the amount of electricity used in electricity substitution projects according to claim 1, characterized in that, The step of performing dimensionality reduction and reproduction on each of the plurality of historical first electricity consumption data queues according to the second transformation matrix, and determining the first transformation deviation based on the obtained plurality of historical second electricity consumption data queues, includes: Based on the second transformation matrix and the first formula, each of the multiple historical first electricity consumption data queues is subjected to dimensionality reduction and reproduction to obtain multiple historical second electricity consumption data queues, wherein the first formula is: In the formula, This is the second-highest historical electricity consumption data queue. This is the highest-ever electricity consumption data queue. This is the second transformation matrix; The first conversion deviation is determined according to the second formula, whereby the second formula is: In the formula, This is the first conversion bias. For the first The second historical electricity consumption data queue One data point, For the first The first historical electricity consumption data queue One data point, This represents the total number of electricity consumption data queues in history. This represents the total number of data points in the historical first electricity consumption data queue. This is the average of data from multiple historical first electricity consumption data queues.
4. The method for determining the amount of electricity used in an electricity substitution project according to claim 3, characterized in that, The adjustment of the plurality of second transformation matrices based on the plurality of first transformation deviations includes: The second transformation matrix corresponding to the first transformation deviation with the smallest value is used as the global matrix; Based on the correspondence between the first conversion deviation and the second conversion matrix, the plurality of first conversion deviations are added to a plurality of first deviation queues respectively, wherein each second conversion matrix corresponds to a first deviation queue; For each first deviation queue, the historical second transformation matrix corresponding to the minimum value in the queue is used as the historical matrix; For each second transformation matrix, adjustments are made according to the third formula, the global matrix, and the corresponding historical matrix, wherein the third formula is: In the formula, For the adjusted second matrix, the first... Line number Column elements, For the second matrix before adjustment, the first... Line number Column elements, The first in the global matrix Line number Column elements, The first in the history matrix Line number Column elements, For global coefficients, Historical coefficients This is the bias coefficient.
5. The method for determining the amount of electricity used in electricity substitution projects according to claim 1, characterized in that, The step of calculating the deviation between the first electricity consumption data queue and the second electricity consumption data queue, and standardizing the obtained deviation to obtain the first deviation queue, includes: Perform a subtraction operation on the first power consumption data queue and the second power consumption data queue bit by bit to obtain the difference queue; The difference queue is normalized to obtain the first deviation queue.
6. The method for determining the amount of electricity used in an electricity substitution project according to any one of claims 1-5, characterized in that, The deviation analysis model is constructed based on multiple historical first deviation queues, including: Multiple historical first deviation queues and multiple credibility labels are obtained. Each historical first deviation queue corresponds to a credibility label. The historical first deviation queues are obtained by performing deviation calculations and standardization based on the historical first electricity consumption data queue and the reproduction queue of the historical first electricity consumption data queue. Substitute the multiple historical first deviation queues into the process model to obtain multiple first confidence levels; The prediction loss of the model is determined based on the plurality of first confidence levels and the plurality of confidence level labels; If the predicted loss is greater than the loss threshold, then the multiple coefficients of the process model are optimized by an optimization algorithm based on the predicted loss, and the process jumps to the step of substituting the multiple historical first deviation queues into the process model to obtain multiple first confidence levels. Otherwise, the process model is used as the deviation analysis model.
7. The method for determining the amount of electricity used in electricity substitution projects according to claim 6, characterized in that, The process model is as follows: In the formula, The first confidence level of the model output. It is a natural constant. As joint variables, For the first Each model coefficient For the deviation queue One data point, The bias constant is This represents the total number of data items in the deviation queue.
8. The method for determining the amount of electricity used in an electricity substitution project according to claim 6, characterized in that, The step of determining the model's prediction loss based on the plurality of first confidence levels and the plurality of confidence level labels includes: The prediction loss of the model is determined based on the fourth formula, the plurality of first confidence levels, and the plurality of confidence level labels, wherein the fourth formula is: In the formula, To predict losses, The number of credibility tags, For the first A credibility tag, For the first Firstly, credibility.
9. The method for determining the amount of electricity used in an electricity substitution project according to claim 8, characterized in that, The optimization of multiple coefficients of the process model based on the predicted loss using an optimization algorithm includes: The predicted loss is used to optimize multiple coefficients of the process model using a fifth formula, wherein the fifth formula is: In the formula, For the optimized first Each model coefficient For the first time before optimization Each model coefficient As the first optimization coefficient, The optimized bias constant. This is the bias constant before optimization.
10. A device for determining the amount of electricity used in an electricity substitution project, characterized in that, For implementing the method for determining the electricity consumption of electricity substitution projects as described in any one of claims 1-9, the electricity consumption determination device for electricity substitution projects includes: The data acquisition module is used to acquire the first electricity consumption data queue of the alternative project and the first factor affecting the electricity consumption of the alternative project; The queue reconstruction module is used to select a first dimension transformation matrix based on the first factor, and to perform dimensionality reduction and reproduction on the first electricity consumption data queue through the first dimension transformation matrix to obtain a second electricity consumption data queue. The electricity consumption data queue obtains the main feature dimension through dimensionality reduction of the first dimension transformation matrix. The deviation calculation module is used to calculate the deviation between the first electricity consumption data queue and the second electricity consumption data queue, and to standardize the obtained deviation to obtain the first deviation queue. as well as, The data credibility determination module is used to input the first deviation queue into the deviation analysis model and determine the credibility of the first electricity consumption data queue based on the output of the deviation analysis model.