Electric power material prediction method and system based on weight distribution, medium and processor

Abstract

The invention provides an electric power material prediction method based on weight distribution, and the method comprises the steps: carrying out the statistics of the historical data of consumed materials of all power supply stations in a certain region in Y years, and solving the total consumption of the next year; according to the proportion data of the annual total amount of each month station in the historical data every year, the proportion of each month to the total consumption amount of the next year is solved; calculating a consumption predicted value of a certain month according to the total consumption of the next year and the proportion of each month; calculating the ratio of the operation quantity of the power equipment in a certain month of a certain power supply station in the region to the total operation quantity of the power equipment in the region, and calculating a material consumption predicted value of the certain month of the certain power supply station; counting and calculating the proportion of the consumption of various materials of the power supply station in the total consumption of the materials of the power supply station in the historical data of Y years, and calculating the consumption value prediction of a certain type of materials. The electric power material prediction calculation mode based on weight distribution is comprehensively suitable for power supply station material consumption calculation under various conditions, and the calculation mode is simple and reliable.

Description

Technical Field

[0001] The present invention relates to the technical field of power material consumption prediction, and in particular to a power material prediction method, system, medium and processor based on weight distribution. Background Art

[0002] In the operation and management of power companies, power material forecasting is a key link. As the middle point of procurement, arrival and distribution, only by accurately determining material consumption can the smooth operation of the power company's supply chain be guaranteed. Manual reporting is highly random and cannot guarantee the accuracy of the predicted consumption value. A low predicted value will lead to a shortage of supply and the grid cannot operate normally. When the predicted value is too high, it will cause inventory backlogs, restricting the efficiency of capital utilization of the company.

[0003] With the development of machine learning and deep learning technologies, the prediction methods of power materials have also made great progress. For example, (1) linear regression is easy to implement and has fast calculation speed, but it performs poorly for nonlinear relationships. (2) For complex data distribution and noise sensitivity, decision trees can handle nonlinear data and have strong explanatory power, but they are prone to overfitting and need to use pruning technology to prevent overfitting. They perform poorly for continuous variables. (3) LSTM can process time series data and capture long-term dependencies. It has a good prediction effect on time series data, especially for data with long-term dependencies. However, it takes a long time to train, consumes a lot of computing resources, and requires a large amount of data for training. (4) CNN can automatically extract features from data and effectively process long-term series data through convolution kernels and pooling layers, reduce data dimensions and extract key features, but it requires enough labeled data to support model training, and also requires high computing resources and time. Based on this, it can be seen that the current technical methods have poor overall performance and require more computing resources.

[0004] In view of this, a method, system, medium and processor for predicting electric power materials based on weight distribution are needed. Summary of the invention

[0005] In view of the poor overall performance and the large amount of computing resources required in the prior art, the present invention provides a method, system, medium and processor for predicting electric power materials based on weight distribution, which can start from the annual consumption and distribute the weights to each month, each unit and each type of materials one by one. It is suitable for calculating the material consumption of power supply stations in various situations, and the calculation method is simple and reliable, which can meet the annual forecast of procurement needs and the monthly forecast of arrival and delivery. The specific technical scheme is as follows:

[0006] A power material forecasting method based on weight distribution, comprising:

[0007] S1: Collect the historical data of material consumption of all power supply stations in a certain area for Y years, and use the linear mean of the historical data to calculate the total consumption X in the next year tl ;

[0008] S2: Based on the historical data, the proportion of each month in the total annual consumption is calculated by using the linear mean to calculate the proportion of each month in the total consumption in the next year. mo ;

[0009] S3: The total consumption in the next year is X tl and the proportion of each month mo , calculate the consumption forecast value X for a certain month mo ;

[0010] S4: Calculate the ratio of the number of power equipment in operation in a power supply station in the region in a certain month to the total number of power equipment in operation in the region. on,g , and according to the ratio r on,g Calculate the predicted material consumption value X of a power supply station in a certain month mo,g ;

[0011] S5: Count and calculate the proportion of the consumption value of various materials of the power supply station in the historical data of year Y to the total consumption of materials of the power supply station c , combined with the predicted material consumption value X of the power supply station in a certain month mo,g , calculate the consumption value forecast of a certain type of material in a certain month of the power supply station

[0012] Furthermore, the historical data is recorded by month.

[0013] Further, in step S3, the consumption forecast value X of a certain month mo The calculation formula is as follows:

[0014] X mo =X tl *r mo

[0016] Furthermore, the predicted value of material consumption of the power supply station in a certain month is calculated by the following formula:

[0017] X mo,g =X mo *r on,g .

[0018] Furthermore, the consumption value of a certain type of material of the power supply station in a certain month is predicted, and the calculation formula is as follows:

[0019]

[0020] Furthermore, the method further comprises the following steps:

[0021] If the proportion of a certain type of material in the power supply station is 0, search for the number of operating power equipment in each power supply station in the area, find the power supply station closest to the operating number of this power supply station, and use the predicted consumption value of this type of material in the closest power supply station to replace the predicted consumption value of this type of material in this power supply station.

[0022] Further, the replacement formula is as follows:

[0023]

[0024] In the above formula, r c 1 ,g 1 is the consumption ratio of a certain type of material in the power supply station; r on,g 1 is the proportion of the power equipment in operation in the power supply station; r on,g 2 The proportion of power equipment in operation closest to the power supply station; The consumption forecast value of a certain type of materials closest to the power supply station; It is the predicted value of consumption of a certain type of materials in the power supply station.

[0025] A power material forecasting system based on weight distribution, applied to the above method, comprises:

[0026] The annual forecast module is used to collect historical data on the consumption of materials in all power supply stations in a certain area for Y years, and use the linear mean of the historical data to calculate the total consumption X in the next year. tl ;

[0027] The monthly proportion forecast module is used to calculate the proportion of each month's annual total consumption in the future year using the linear mean based on the proportion of each month's annual total consumption in the historical data. mo ;

[0028] Monthly forecast module, which is used to calculate the total consumption X in the next year tl and the proportion of each month mo , calculate the consumption forecast value X for a certain month mo ;

[0029] The monthly forecast module of the power supply station is used to calculate the ratio of the number of power equipment in operation in a power supply station in a certain month to the total number of power equipment in operation in the region. on,g , and according to the ratio r on,g Calculate the predicted material consumption value X of a power supply station in a certain month mo,g ;

[0030] The monthly category forecasting module of the power supply station is used to count and calculate the proportion of the consumption value of each type of materials in the historical data of the power supply station in the Y year to the total consumption of materials in the power supply station. c , combined with the predicted material consumption value X of the power supply station in a certain month mo,g , calculate the consumption value forecast of a certain type of material in a certain month of the power supply station

[0031] A computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the above-mentioned power material prediction method based on weight distribution.

[0032] A processor is used to run a program, wherein the program executes the above-mentioned power material prediction method based on weight distribution when running.

[0033] Compared with the prior art, the present invention has the following beneficial effects:

[0034] 1. The power material forecast calculation method based on weight distribution is comprehensively applicable to the material consumption calculation of power supply stations under various circumstances, and the calculation method is simple and reliable.

[0035] 2. This method starts with the annual consumption and allocates it to each month, each unit, and each type of material according to the weight. It not only meets the annual forecast for procurement needs, but also allocates the monthly forecast to meet the arrival and delivery needs.

[0036] 3. This plan involves the field of power companies and data mining. By analyzing the historical data of power material consumption and combining it with the number of local power equipment in operation, a method from full to specific is adopted to predict the power material consumption of power supply stations. It aims to solve the problem of inaccurate power material predictions currently in power companies that rely on manual reporting. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following is a brief introduction to the drawings required for the specific embodiments or the description of the prior art. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn according to the actual scale.

[0038] Figure 1 It is a flow chart of a method for predicting power materials based on weight distribution;

[0039] Figure 2 This is a schematic diagram of the principle structure of an electric power material forecasting system based on weight distribution. DETAILED DESCRIPTION

[0040] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0041] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0042] It should also be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0043] It should be further understood that the term "and / or" used in the present description and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0044] Embodiment 1

[0045] like Figure 1 The figure shows a flow chart of a power material forecasting method based on weight distribution, including:

[0046] S1: Collect the historical data of material consumption of all power supply stations in a certain area for Y years, and use the linear mean of the historical data to calculate the total consumption X in the next year tl .

[0047] Furthermore, the historical data is recorded by month.

[0048] S2: Based on the historical data, the proportion of each month in the total annual consumption is calculated by using the linear mean to calculate the proportion of each month in the total consumption in the next year. mo .

[0049] S3: The total consumption in the next year is X tl and the proportion of each month mo , calculate the consumption forecast value X for a certain month mo .

[0050] Further, in step S3, the consumption forecast value X of a certain month mo The calculation formula is as follows:

[0051] X mo =X tl *r mo

[0053] S4: According to the relationship between the power material consumption characteristics and the number of power equipment in operation in the region, the greater the number of power equipment in operation, the greater the material consumption. Therefore, based on this characteristic, the ratio of the number of power equipment in operation in a certain power supply station in the region in a certain month to the total number of power equipment in operation in the region is calculated. on,g , and according to the ratio r on,g Calculate the predicted material consumption value X of a power supply station in a certain month mo,g .

[0054] Furthermore, the predicted value of material consumption of the power supply station in a certain month is calculated by the following formula:

[0055] X mo,g =X mo *r on,g .

[0056] S5: Count and calculate the proportion of the consumption value of various materials of the power supply station in the historical data of year Y to the total consumption of materials of the power supply station c , combined with the predicted material consumption value X of the power supply station in a certain month mo,g , calculate the consumption value forecast of a certain type of material in a certain month of the power supply station

[0057] Furthermore, the consumption value of a certain type of material of the power supply station in a certain month is predicted, and the calculation formula is as follows:

[0058]

[0059] The power material forecasting calculation method based on weight distribution can avoid the problems of poor performance of nonlinear relationships and poor performance of continuous variables encountered when using complex model calculations in the existing technology. At the same time, it eliminates the training and verification links and avoids the need for a large amount of data and computing resources. It is comprehensively applicable to the material consumption calculation of power supply stations in various situations, and the calculation method is simple and reliable. At the same time, this method starts from the annual consumption and distributes it to each month, each unit, and each type of material one by one according to the weights. It not only meets the annual forecast for procurement needs, but also allocates monthly forecasts to meet arrival and delivery needs. This solution involves the fields of power companies and data mining. By analyzing the historical data of power material consumption and combining the number of local power equipment in operation, a method from full to specific is adopted to realize the forecast of power material consumption of power supply stations, aiming to solve the problem of inaccurate forecasts of power materials currently reported by power companies.

[0060] When predicting the material category of a power supply station, it is necessary to obtain the proportion of the material in the power supply station. c , and when recording the consumption of power materials, it is inevitable that missing values ​​will appear, which will cause the proportion of a certain material in the power supply station to be 0. To solve this problem, considering the positive correlation between power material consumption and the number of power equipment in operation, when the proportion of a certain material in the power supply station is 0, search for the number of power supply stations in operation in the area, and use the predicted value of the consumption of this type of material in the power supply station that is closest to the number of power supply stations in operation to replace the predicted value of the consumption of this type of material in the power supply station. Therefore, the following steps are also included:

[0061] If the proportion of a certain type of material in the power supply station is 0, search for the number of operating power equipment in each power supply station in the area, find the power supply station closest to the operating number of this power supply station, and use the predicted consumption value of this type of material in the closest power supply station to replace the predicted consumption value of this type of material in this power supply station.

[0062] Further, the replacement formula is as follows:

[0063]

[0064] In the above formula, r c 1 ,g 1 is the consumption ratio of a certain type of material in the power supply station; r on,g 1 is the proportion of the power equipment in operation in the power supply station; r on,g 2 The proportion of power equipment in operation closest to the power supply station; The consumption forecast value of a certain type of materials closest to the power supply station; is the predicted value of a certain type of material consumption of the power supply station, and P is the specific consumption value of a certain type of material.

[0065] Furthermore, if the proportion of a certain type of material in the power station is 0, the number of operating power equipment in each power station in the area is searched to find the power station with the closest operating number to the power station. The consumption ratio of the closest power station can also be used to replace the consumption ratio of the same type of material in the power station, and then the specific consumption value is calculated based on the ratio. Compared with the direct consumption value replacement method, the predicted value obtained by replacing the consumption ratio will be more accurate.

[0066] This embodiment provides a method for predicting power materials from the entire quantity to each unit. Due to procurement needs, it is often necessary to predict the material consumption for the next year, and when the goods are delivered, it is necessary to predict the material consumption for the next month. Based on the analysis of power material consumption, it is found that its monthly consumption fluctuates greatly and is highly sudden. In order to avoid the gradual increase of errors in prediction, it is proposed as follows Figure 1The power material forecast framework shown in the figure. This framework starts with the annual consumption and allocates it to each month, each unit, and each type of material according to the weight. It not only meets the annual forecast for procurement needs, but also allocates the monthly forecast to meet the arrival and delivery needs, and can also prevent the problem of gradually increasing errors in each forecast.

[0067] Embodiment 2

[0068] like Figure 2 As shown, a power material prediction system based on weight distribution is applied to the method described above, comprising:

[0069] The annual forecast module is used to collect historical data on the consumption of materials in all power supply stations in a certain area for Y years, and use the linear mean of the historical data to calculate the total consumption X in the next year. tl ;

[0070] The monthly proportion forecast module is used to calculate the proportion of each month's annual total consumption in the future year using the linear mean based on the proportion of each month's annual total consumption in the historical data. mo ;

[0071] Monthly forecast module, which is used to calculate the total consumption X in the next year tl and the proportion of each month mo , calculate the consumption forecast value X for a certain month mo ;

[0072] The monthly forecast module of the power supply station is used to calculate the ratio of the number of power equipment in operation in a power supply station in a certain month to the total number of power equipment in operation in the region. on,g , and according to the ratio r on,g Calculate the predicted material consumption value X of a power supply station in a certain month mo,g ;

[0073] The monthly category forecasting module of the power supply station is used to count and calculate the proportion of the consumption value of each type of materials in the historical data of the power supply station in the Y year to the total consumption of materials in the power supply station. c , combined with the predicted material consumption value X of the power supply station in a certain month mo,g , calculate the consumption value forecast of a certain type of material in a certain month of the power supply station

[0074] Embodiment 3

[0075] A computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the above-mentioned power material prediction method based on weight distribution.

[0076] Embodiment 4

[0077] A processor is used to run a program, wherein the program executes the above-mentioned power material prediction method based on weight distribution when running.

[0078] The present application provides a power material prediction method based on weight distribution, including: S1: Counting the historical data of material consumption of all power supply stations in a certain area for Y years, and using the linear mean of the historical data to calculate the total consumption X in the next year tl ; S2: Based on the historical data, the proportion of each month in the total annual consumption of each station is calculated by using the linear mean to calculate the proportion of each month in the total consumption of the next year. mo ; S3: The total consumption in the next year X tl and the proportion of each month mo , calculate the consumption forecast value X for a certain month mo ; S4: Calculate the ratio of the number of power equipment in operation in a power supply station in the region in a certain month to the total number of power equipment in operation in the region on,g , and according to the ratio r on,g Calculate the predicted material consumption value X of a power supply station in a certain month mo,g ; S5: Statistics and calculation of the proportion of the consumption value of various materials of the power supply station in the historical data of year Y to the total consumption of materials of the power supply station c , combined with the predicted material consumption value X of the power supply station in a certain month mo,g , calculate the consumption value forecast of a certain type of material in a certain month of the power supply station The power material forecast calculation method based on weight distribution is comprehensively applicable to the material consumption calculation of power supply stations in various situations, and the calculation method is simple and reliable. This method starts from the annual consumption and allocates weights to each month, each unit, and each type of material one by one. It not only meets the annual forecast for procurement needs, but also allocates monthly forecasts to meet arrival and delivery needs. This solution involves the fields of power companies and data mining. By analyzing the historical data of power material consumption and combining the number of local power equipment in operation, a method from full to specific is adopted to realize the forecast of power material consumption of power supply stations, aiming to solve the problem of inaccurate power material forecasts currently relying on manual reporting in power companies.

[0079] Those of ordinary skill in the art will appreciate that the units of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition of each example has been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0080] In the embodiments provided by the present invention, it should be understood that the division of units is only a logical function division, and there may be other division methods in actual implementation, for example, multiple units can be combined into one unit, one unit can be split into multiple units, or some features can be ignored, etc.

[0081] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0082] If the integrated unit is implemented in the form of 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, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-0nlyMemory), random access memory (RAM, RandomAccessMemory), mobile hard disk, magnetic disk or optical disk, etc., which can store program code.

[0083] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and specification of the present invention.

Claims

1. A power material forecasting method based on weight distribution, characterized in that: include: S1: Collect the historical data of material consumption of all power supply stations in a certain area for Y years, and use the linear mean of the historical data to calculate the total consumption X in the next year tl ; S2: Based on the historical data, the proportion of each month in the total annual consumption is calculated by using the linear mean to calculate the proportion of each month in the total consumption in the next year. mo ; S3: The total consumption in the next year is X tl and the proportion of each month mo , calculate the consumption forecast value X for a certain month mo ; S4: Calculate the ratio of the number of power equipment in operation in a power supply station in the region in a certain month to the total number of power equipment in operation in the region. on,g , and according to the ratio r on,g Calculate the predicted material consumption value X of a power supply station in a certain month mo,g ; S5: Count and calculate the proportion of the consumption value of various materials of the power supply station in the historical data of year Y to the total consumption of materials of the power supply station c , combined with the predicted material consumption value X of the power supply station in a certain month mo,g , calculate the consumption value forecast of a certain type of material in a certain month of the power supply station 2. The power material forecasting method based on weight distribution according to claim 1 is characterized in that: The historical data is recorded on a monthly basis.

3. The power material forecasting method based on weight distribution according to claim 1 is characterized in that: In step S3, the consumption forecast value X of a certain month mo The calculation formula is as follows: X mo =X tl *r mo 。 4. The power material forecasting method based on weight distribution according to claim 1 is characterized in that: The material consumption forecast value of the power supply station in a certain month is calculated by the following formula: X mo,g =X mo *r on,g 。 5. The power material forecasting method based on weight distribution according to claim 1 is characterized in that: The consumption value forecast of a certain type of material of the power supply station in a certain month is calculated as follows:

6. The power material forecasting method based on weight distribution according to claim 1 is characterized in that: The following steps are also included: If the proportion of a certain type of material in the power supply station is 0, search for the number of operating power equipment in each power supply station in the area, find the power supply station closest to the operating number of this power supply station, and use the predicted consumption value of this type of material in the closest power supply station to replace the predicted consumption value of this type of material in this power supply station.

7. The power material forecasting method based on weight distribution according to claim 1 is characterized in that: The substitution formula is as follows: In the above formula, r c 1 ,g 1 is the consumption ratio of a certain type of material in the power supply station; r on,g 1 is the proportion of the power equipment in operation in the power supply station; r on,g 2 The proportion of power equipment in operation closest to the power supply station; The consumption forecast value of a certain type of materials closest to the power supply station; It is the predicted value of consumption of a certain type of materials in the power supply station.

8. A power material forecasting system based on weight distribution, characterized in that: The method applied to any one of claims 1 to 7, comprising: The annual forecast module is used to collect historical data on the consumption of materials in all power supply stations in a certain area for Y years, and use the linear mean of the historical data to calculate the total consumption X in the next year. tl ; The monthly proportion forecast module is used to calculate the proportion of each month's annual total consumption in the future year using the linear mean based on the proportion of each month's annual total consumption in the historical data. mo ; Monthly forecast module, which is used to calculate the total consumption X in the next year tl and the proportion of each month mo , calculate the consumption forecast value X for a certain month mo ; The monthly forecast module of the power supply station is used to calculate the ratio of the number of power equipment in operation in a power supply station in a certain month to the total number of power equipment in operation in the region. on,g , and according to the ratio r on,g Calculate the predicted material consumption value X of a power supply station in a certain month mo,g ; The monthly category forecasting module of the power supply station is used to count and calculate the proportion of the consumption value of each type of materials in the historical data of the power supply station in the Y year to the total consumption of materials in the power supply station. c , combined with the predicted material consumption value X of the power supply station in a certain month mo,g , calculate the consumption value forecast of a certain type of material in a certain month of the power supply station 9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the power material prediction method based on weight distribution as described in any one of claims 1 to 7.

10. A processor, characterized in that: The processor is used to run a program, wherein the program, when running, executes the power material prediction method based on weight distribution as described in any one of claims 1 to 7.

Images