CN112434430A - Method and device for predicting cell capacity - Google Patents

Abstract

The present application discloses a method and device for predicting the capacity of a station area. The method includes: determining the time series data of the power load, wherein the time series data is the power load corresponding to each time point in the historical time period; establishing an autoregressive moving average model according to the time series data, wherein the autoregressive moving average The model is used to predict the power load; the target power load of the target station area in the target time period is determined according to the autoregressive moving average model; the capacity of the target station area is determined at least according to the target power load, wherein the larger the target power load, the greater the capacity. . The present application solves the technical problems of high distribution network construction cost and low power expansion and connection efficiency caused by the inability to predict the capacity of the station area in the related art.

Description

Method and device for predicting station capacity

technical field

The present application relates to the field of electric power, and in particular, to a method and device for predicting the capacity of a station area.

Background technique

The social and economic reform and development and the adjustment of the industrial structure have led to the continuous changes in the demand for electricity and the structure of electricity consumption. The distribution network is not designed based on the maximum load of users, but is based on the principle of open capacity sharing of equipment to meet the needs of users and industry expansion. In order to further optimize the power business environment and reduce the construction cost of the distribution network, it is necessary to analyze the correlation between the open capacity of the power grid and the limited expansion of the industry, and to give early warnings to areas with limited expansion of the industry.

At present, the related technology does not use big data analysis technology to predict the future capacity of the station area according to the changing trend of historical industry expansion and installation demand. Therefore, in the related technology, it is impossible to predict the capacity of the station area. Therefore, there is a power distribution The cost of network construction is high, which may not match the actual demand, and the efficiency of power expansion is low.

For the above problems, no effective solution has been proposed yet.

SUMMARY OF THE INVENTION

The embodiments of the present application provide a method and device for predicting the capacity of a station area, so as to at least solve the high cost of construction of the distribution network and the low efficiency of industrial expansion and connection caused by the inability to predict the capacity of the station area in the related art. question.

According to an aspect of the embodiments of the present application, a method for predicting the capacity of a station area is provided, including: determining time series data of power loads, wherein the time series data are power loads corresponding to various time points in a historical time period; Sequence data, establish an autoregressive moving average model, wherein the autoregressive moving average model is used to predict the power load; according to the autoregressive moving average model, determine the target power load of the target station area in the target time period; at least determine the target power load according to the target power load The capacity of the station area, in which the larger the target power load, the larger the capacity.

Optionally, before establishing the autoregressive moving average model, it includes: comparing the power loads corresponding to each time point with the preset parameter range one by one, and when the power load does not belong to the preset parameter range, determine that the power load data is wild. value and remove outliers.

Optionally, before establishing the autoregressive moving average model according to the time series data, the method further includes: when the power load corresponding to each time point has an increasing or decreasing trend in the historical time period, performing differential processing on the time series data.

Optionally, after performing differential processing on the time series data, the method further includes: judging whether there is heteroscedasticity in the time series data; not significantly different from zero.

Optionally, establishing an autoregressive moving average model according to the time series data includes: determining the type of the partial autocorrelation function and the autocorrelation function of the time series data; establishing an autoregressive moving average model for power load forecasting according to the type.

Optionally, establishing an autoregressive moving average model for power load forecasting according to the type, including: when the partial autocorrelation function is a truncation type, and the autocorrelation function is a tailing type, establishing a power load forecasting AR model according to the time series data, according to The AR model determines the autoregressive moving average model; when the partial autocorrelation function is of the tail type and the autocorrelation function is of the truncation type, the power load forecasting MA model is established according to the time series data, and the autoregressive moving average model is determined according to the MA model; When the partial autocorrelation function is a tailing type, and the autocorrelation function is a tailing type, an autoregressive moving average model of power load forecasting is established according to the time series data.

Optionally, determining the time series data of the power load includes: acquiring historical data of the power load from the power GIS system and/or the power management system PMS; and determining the time series data of the power load according to the historical data.

According to another aspect of the embodiments of the present application, there is also provided an apparatus for predicting the capacity of a station area, including: a first determination module configured to determine time series data of electric power loads, wherein the time series data is each The power load corresponding to the time point; the establishment module is used to establish an autoregressive moving average model according to the time series data, wherein the autoregressive moving average model is used to predict the power load; the second determination module is used for according to the autoregressive moving average model Determine the target power load of the target station area in the target time period; the third determination module is used to determine the capacity of the target station area at least according to the target power load, wherein the larger the target power load, the greater the capacity.

According to another aspect of the embodiments of the present application, a non-volatile storage medium is also provided, where the non-volatile storage medium includes a stored program, wherein when the program runs, the device where the non-volatile storage medium is located is controlled to execute any arbitrary program. A method for predicting the capacity of a station area.

According to another aspect of the embodiments of the present application, a processor is also provided, and the processor is configured to run a program, wherein when the program runs, any method for predicting the capacity of a station area is executed.

In the embodiment of the present application, the autoregressive moving average model is used to predict the power load, and the time series data of the power load is determined, wherein the time series data is the power load corresponding to each time point in the historical time period; according to the time series data , establish an autoregressive moving average model, in which the autoregressive moving average model is used to predict the power load; according to the autoregressive moving average model, the target power load of the target station area in the target time period is determined, and the prediction of the autoregressive moving average model is achieved. The purpose of the power load of the station area, so as to realize the technical effect of predicting the capacity of the station area according to the prediction result, and then providing a data reference for the construction of the distribution network and the business expansion business according to the prediction result, and then solve the problem due to the related technology. The high cost of construction of the distribution network caused by the prediction of the capacity of the station area, as well as the technical problems of low efficiency of industrial expansion and connection.

Description of drawings

The drawings described herein are used to provide further understanding of the present application and constitute a part of the present application. The schematic embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation of the present application. In the attached image:

1 is a schematic flowchart of an optional method for predicting station capacity according to an embodiment of the present application;

FIG. 2 is a schematic structural diagram of an optional apparatus for predicting station capacity according to an embodiment of the present application.

Detailed ways

In order to make those skilled in the art better understand the solutions of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only The embodiments are part of the present application, but not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the scope of protection of the present application.

It should be noted that the terms "first", "second", etc. in the description and claims of the present application and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific sequence or sequence. It is to be understood that data so used may be interchanged under appropriate circumstances so that the embodiments of the application described herein can be practiced in sequences other than those illustrated or described herein. Furthermore, the terms "comprising" and "having" and any variations thereof, are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those expressly listed Rather, those steps or units may include other steps or units not expressly listed or inherent to these processes, methods, products or devices.

For those skilled in the art to better understand the embodiments of the present application, the technical terms or some terms that may be involved in the embodiments of the present application are now explained as follows:

Power GIS is a comprehensive information system of production management that connects power equipment, substations, transmission and distribution networks, power users and power loads of power companies to form power informatization. It provides power equipment information, power grid operation status information, power technology information, production management information, power market information and natural environment information such as mountains, topography, towns, roads, and meteorology, hydrology, geology, and resources in a unified system. Through GIS, relevant data, pictures, images, maps, technical materials, management knowledge, etc. can be inquired.

Power management system (Power Management System, referred to as PMS), the role of the power management system are: plant power switch status monitoring, electricity, three-phase voltage, three-phase current, frequency and power factor monitoring. When an abnormality occurs in the power system of the plant area, resulting in insufficient or excess power, it can quickly respond to perform functions such as automatic unloading (Load Shedding) or dynamic braking (Dynamic Breaking) to prevent the occurrence of complete darkness in the plant area and improve the power system of the entire plant area. stability and quality.

According to an embodiment of the present application, an embodiment of a method for predicting station capacity is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings may be executed in a computer system such as a set of computer-executable instructions, and , although a logical order is shown in the flowcharts, in some cases steps shown or described may be performed in an order different from that herein.

FIG. 1 is a method for predicting station capacity according to an embodiment of the present application. As shown in FIG. 1 , the method includes the following steps:

Step S102, determining the time series data of the power load, wherein the time series data is the power load corresponding to each time point in the historical time period;

Step S104, establishing an autoregressive moving average model according to the time series data, wherein the autoregressive moving average model is used to predict the power load;

Step S106, determining the target power load of the target station area within the target time period according to the autoregressive moving average model;

In step S108, the capacity of the target station area is determined at least according to the target electric power load, wherein the larger the target electric power load, the larger the capacity.

In the method for predicting the capacity of the station area, first, the time series data of the power load is determined, wherein the time series data is the power load corresponding to each time point in the historical time period; then, an autoregressive moving average model is established according to the time series data, Among them, the autoregressive moving average model is used to predict the power load; then the target power load of the target station area in the target time period is determined according to the autoregressive moving average model; finally, the capacity of the target station area is determined at least according to the target power load, wherein, The larger the target power load, the larger the capacity, which achieves the purpose of using the autoregressive moving average model to predict the power load of the station area, thereby realizing the prediction of the station area capacity according to the prediction results, and then according to the prediction results for the construction of the distribution network and The technical effect of providing data reference for the industry expansion business, thereby solving the technical problems of high distribution network construction cost and low efficiency of industry expansion due to the inability to predict the capacity of the station area in related technologies.

In some embodiments of the present application, before establishing the autoregressive moving average model, the outliers in the power load data may be eliminated by the following methods: comparing the power loads corresponding to each time point with the preset parameter range one by one, when the power load does not When it falls within the preset parameter range, the power load data is determined to be an outlier, and the outlier is deleted.

In some optional embodiments of the present application, before establishing the autoregressive moving average model according to the time series data, when the power load corresponding to each time point has a trend of increasing or decreasing in the historical time period, the time series data are analyzed for Differential processing.

In some embodiments of the present application, after performing differential processing on the time series data, it can be determined whether the time series data has heteroscedasticity; when the time series data has heteroscedasticity, the autocorrelation function value and the partial correlation function value of the time series data are set. not significantly different from zero.

In some optional embodiments of the present application, an autoregressive moving average model may be established according to time series data, specifically: determining the type of partial autocorrelation function and autocorrelation function of the time series data; establishing an autoregressive power load forecasting autoregressive function according to the type moving average model.

It should be noted that the autoregressive moving average model ARIMA has three parameters: p, d, and q.

p represents the lags of the time series data itself used in the prediction model, which is also called AR/Auto-Regressive item.

d represents that the time series data needs to be differentiated in several orders to be stable, also called the Integrated item.

q represents the number of lags in the forecast error used in the forecast model, also known as the MA/Moving Average term. ARIMA's prediction model can be expressed as: predicted value of Y = constant c and/or weighted sum of Y at one or more recent times and/or prediction error at one or more recent times.

After determining p, q, d, ARIMA can be expressed in mathematical form as:

表示目标电力负荷，μ表示电力负荷的误差值，为常数，y_t-p表示p阶自回归模型中历史时间各个时间点的电力负荷，e_t-q表示q阶移动平均模型中历史时间各个时间点的电力负荷，t表示历史时间各个时间点,

表示p阶自回归模型的系数，θ_q表示q阶移动平均模型的系数，AR代表p阶自回归过程，MA代表q阶移动平均过程。in,

represents the target power load, μ represents the error value of the power load, which is a constant, y _tp represents the power load at each time point in the historical time in the p-order autoregressive model, and e _tq represents the power at each time point in the historical time in the q-order moving average model. load, t represents each time point in historical time,

represents the coefficient of the p-order autoregressive model, θ _q represents the coefficient of the q-order moving average model, AR represents the p-order autoregressive process, and MA represents the q-order moving average process.

The specific model implementation process is as follows:

1) Data collection: The selected data set comes from the industry expansion data of a certain region from 2007 to 2018. It should be noted that the industry expansion data includes but is not limited to: load data.

2) Data preprocessing: Eliminate missing and abnormal data in the data, and perform Z-Scroe normalization preprocessing on the processed data to eliminate the influence of dimensions, so that the features extracted from all samples can be in the same dimension. for comparison.

3) Model construction: extract the load data, and obtain the parameters p, d, and q of the time series model, which are 1, 1, and 2, respectively. That is, the model is finally fitted to ARIMA(1,1,2). Substitute the 2007-2017 data into the load forecasting model. The monthly load forecast data and actual data in 2018 are shown in the following table. It can be seen that the load forecast value is relatively close to the actual value, and the relative error is within 6%. The overall average relative error is 2.4%. Therefore, the time series load forecast is established. The model can effectively predict future load values with high accuracy. As shown in Table 1-1, it is an analysis of the predicted value, the actual value and the error:

In some embodiments of the present application, the power load prediction autoregressive moving average model can be established according to the type. Specifically: when the partial autocorrelation function is of the truncation type and the autocorrelation function is of the tail type, then the power load is established according to the time series data. The AR model is predicted, and the autoregressive moving average model is determined according to the AR model; when the partial autocorrelation function is of the tail type and the autocorrelation function is of the truncation type, the power load forecasting MA model is established based on the time series data, and the autocorrelation function is determined according to the MA model. Regression moving average model; when the partial autocorrelation function is a tailing type and the autocorrelation function is a tailing type, an autoregressive moving average model for power load forecasting is established based on the time series data.

It should be noted that the time series data of the power load can be determined by the following methods: obtaining historical data of the power load from the power GIS system and/or the power management system PMS; determining the time series data of the power load according to the historical data. It is easy to notice that the use of the ARIMA time series prediction model to realize early warning of stations with lower open capacity in the future can effectively reduce the labor cost of traditional manual visits and research, and avoid errors in subjective judgments. Applying trends, forecasting demand based on data, assisting relevant decision-making departments to carry out upgrade and transformation planning for early-warning stations as soon as possible, strengthen distribution network planning and construction, reduce construction costs, and resolve the impact of industry expansion restrictions from the source. , improve the efficiency of industrial expansion and connection, and optimize the power business environment.

FIG. 2 is a schematic structural diagram of an apparatus for predicting station capacity according to an embodiment of the present application. As shown in FIG. 2 , the apparatus includes:

a first determining module 40, configured to determine the time series data of the power load, wherein the time series data is the power load corresponding to each time point in the historical time period;

establishing module 42 for establishing an autoregressive moving average model according to the time series data, wherein the autoregressive moving average model is used to predict the power load;

The second determination module 44 is configured to determine the target power load of the target station area within the target time period according to the autoregressive moving average model;

The third determination module 46 is configured to determine the capacity of the target station area at least according to the target power load, wherein the larger the target power load, the larger the capacity.

In the device for predicting the capacity of the station area, the first determination module 40 is used to determine the time series data of the power load, wherein the time series data is the power load corresponding to each time point in the historical time period; the establishment module 42 is used to determine the power load according to For the time series data, an autoregressive moving average model is established, wherein the autoregressive moving average model is used to predict the power load; the second determination module 44 is used to determine the target power of the target station area within the target time period according to the autoregressive moving average model load; the third determination module 46 is used to determine the capacity of the target station area at least according to the target electric power load, wherein, the larger the target electric power load is, the larger the capacity is, and the purpose of predicting the electric power load of the station area by using the autoregressive moving average model is achieved. , so as to realize the technical effect of predicting the capacity of the station area according to the prediction result, and then providing a data reference for the construction of the distribution network and the business expansion business according to the predicted result. The construction cost of the distribution network is high, and the technical problems of the low efficiency of industrial expansion and connection.

In some embodiments of the present application, before establishing the autoregressive moving average model, the outliers in the power load data may be eliminated by the following methods: comparing the power loads corresponding to each time point with the preset parameter range one by one, when the power load does not When it falls within the preset parameter range, the power load data is determined to be an outlier, and the outlier is deleted.

In some optional embodiments of the present application, before establishing the autoregressive moving average model according to the time series data, when the power load corresponding to each time point has a trend of increasing or decreasing in the historical time period, the time series data are analyzed for Differential processing.

In some embodiments of the present application, after performing differential processing on the time series data, it can be determined whether the time series data has heteroscedasticity; when the time series data has heteroscedasticity, the autocorrelation function value and the partial correlation function value of the time series data are set. not significantly different from zero.

In some optional embodiments of the present application, an autoregressive moving average model may be established according to time series data, specifically: determining the type of partial autocorrelation function and autocorrelation function of the time series data; establishing an autoregressive power load forecasting autoregressive function according to the type moving average model.

According to another aspect of the embodiments of the present application, a non-volatile storage medium is also provided, where the non-volatile storage medium includes a stored program, wherein when the program runs, the device where the non-volatile storage medium is located is controlled to execute any arbitrary program. A method for predicting the capacity of a station area.

Specifically, the above-mentioned storage medium is used to store program instructions that perform the following functions, and realize the following functions:

Determine the time series data of the power load, where the time series data is the power load corresponding to each time point in the historical time period; according to the time series data, establish an autoregressive moving average model, where the autoregressive moving average model is used to predict the power load ; Determine the target power load of the target station area in the target time period according to the autoregressive moving average model; at least determine the capacity of the target station area according to the target power load, wherein the larger the target power load, the greater the capacity.

According to another aspect of the embodiments of the present application, a processor is also provided, and the processor is configured to run a program, wherein when the program runs, any method for predicting the capacity of a station area is executed.

Specifically, the above-mentioned processor is used to call the program instructions in the memory to realize the following functions:

Determine the time series data of the power load, where the time series data is the power load corresponding to each time point in the historical time period; according to the time series data, establish an autoregressive moving average model, where the autoregressive moving average model is used to predict the power load ; Determine the target power load of the target station area in the target time period according to the autoregressive moving average model; at least determine the capacity of the target station area according to the target power load, wherein the larger the target power load, the greater the capacity.

The above-mentioned serial numbers of the embodiments of the present application are only for description, and do not represent the advantages or disadvantages of the embodiments.

In the above-mentioned embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.

In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are only illustrative, for example, the division of the units may be a logical function division, and there may be other division methods in actual implementation, for example, multiple units or components may be combined or Integration into another system, or some features can be ignored, or not implemented. On the other hand, the shown or discussed mutual coupling or direct coupling or communication connection may be through some interfaces, indirect coupling or communication connection of units or modules, and may be in electrical or other forms.

The units described as separate components may or may not be physically separated, and components shown as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution in this embodiment.

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

The integrated unit, if implemented in the form of a software functional unit and sold or used as an independent product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the present application can be embodied in the form of software products in essence, or the parts that contribute to the prior art, or all or part of the technical solutions, and the computer software products are stored in a storage medium , including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes .

The above are only the preferred embodiments of the present application. It should be pointed out that for those skilled in the art, without departing from the principles of the present application, several improvements and modifications can also be made. It should be regarded as the protection scope of this application.

Claims (10)

1. a method for predicting the capacity of a station area, is characterized in that, comprises: determining the time series data of the power load, wherein the time series data is the power load corresponding to each time point in the historical time period; establishing an autoregressive moving average model according to the time series data, wherein the autoregressive moving average model is used to predict the power load; Determine the target power load of the target station area in the target time period according to the autoregressive moving average model; The capacity of the target site is determined based on at least the target power load, wherein the larger the target power load, the larger the capacity. 2. The method according to claim 1, characterized in that, before establishing an autoregressive moving average model according to the time series data, comprising: Comparing the electrical load corresponding to each time point with a preset parameter range one by one, when the electrical load does not belong to the preset parameter range, determine that the electrical load data is an outlier, and delete the Outliers. 3. The method according to claim 1, wherein before establishing an autoregressive moving average model according to the time series data, the method further comprises: When the power load corresponding to each time point has an increasing or decreasing trend within the historical time period, the time series data is subjected to differential processing. 4. The method according to claim 3, wherein after performing differential processing on the time series data, the method further comprises: Determine whether the time series data has heteroscedasticity; When the time series data has heteroscedasticity, the autocorrelation function value and the partial correlation function value of the time series data are not significantly different from zero. 5. The method according to claim 1, wherein, establishing an autoregressive moving average model according to the time series data, comprising: determining the partial autocorrelation function and the type of the autocorrelation function of the time series data; An autoregressive moving average model for power load forecasting is established according to the type. 6. The method according to claim 5, wherein establishing an autoregressive moving average model for power load forecasting according to the type, comprising: When the partial autocorrelation function is of the truncation type and the autocorrelation function is of the tailing type, an AR model for power load forecasting is established according to the time series data, and the autoregressive moving average model is determined according to the AR model. ; When the partial autocorrelation function is a tailing type, and the autocorrelation function is a tailing type, a power load forecasting MA model is established according to the time series data, and the autoregressive moving average model is determined according to the MA model. ; When the partial autocorrelation function is of a smear type, and the autocorrelation function is of a smear type, an autoregressive moving average model for power load forecasting is established according to the time series data. 7. The method according to claim 1, wherein determining the time series data of the power load comprises: Obtain the historical data of the power load from the power GIS system and/or the power management system PMS; Time series data of the electrical load is determined according to the historical data. 8. A device for predicting station capacity, comprising: a first determining module, configured to determine the time series data of the power load, wherein the time series data is the power load corresponding to each time point in the historical time period; establishing a module for establishing an autoregressive moving average model for power load forecasting according to the time series data; a second determining module, configured to determine the target power load of the target station area within the target time period according to the autoregressive moving average model; A third determining module, configured to determine the capacity of the target station area at least according to the target power load, wherein the larger the target power load, the larger the capacity. 9. A non-volatile storage medium, characterized in that the non-volatile storage medium comprises a stored program, wherein when the program runs, a device where the non-volatile storage medium is located is controlled to execute the claims The method for predicting the capacity of a station area described in any one of 1 to 7. 10. A processor, wherein the processor is configured to run a program, wherein when the program runs, the method for predicting the capacity of a station area according to any one of claims 1 to 7 is executed.

Images