Power load prediction method and device, electronic equipment and storage medium

Abstract

The invention discloses a power load prediction method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a plurality of economic data groups and a plurality of historical power load values of a preset region in a plurality of historical time periods, determining a first influence coefficient corresponding to an equipment manufacturing industry statistical value, a second influence coefficient corresponding to a new energy industry statistical value and a third influence coefficient corresponding to an agricultural electrification statistical value based on the plurality of economic data sets and the plurality of historical power load values, determining a target adjustment factor based on the first influence coefficient, the second influence coefficient and the third influence coefficient, determining a first reference power load value based on a mean value of the plurality of historical power load values, and adjusting the first reference power load value based on the temperature data to obtain a second reference power load value, and adjusting the second reference power load value based on the target adjustment factor to obtain a target power load value. By adopting the embodiment of the invention, the accuracy of a power load prediction result is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power load forecasting, and in particular to a power load forecasting method, device, electronic equipment and storage medium. Background Art

[0002] Electricity and economic growth promote and relate to each other and have a very close connection. In order to achieve the coordinated development of electricity load demand and economic growth, it is necessary to combine electricity planning with economic development.

[0003] Based on the power load forecast results for different time periods, power companies can optimize the scheduling and operation of generator sets to ensure sufficient power supply during peak load periods and avoid waste of power generation resources during low load periods. However, the accuracy of current power load forecast results is not high. Summary of the invention

[0004] The embodiments of the present application provide a method, device, electronic device and storage medium for predicting power load, which improves the accuracy of power load prediction results by determining the impact of economic data such as equipment manufacturing industry production statistics, new energy industry production statistics, and agricultural electrification production statistics on power load values.

[0005] In a first aspect, an embodiment of the present application provides a method for predicting power load, comprising:

[0006] Obtain multiple economic data groups and multiple historical power load values ​​in a preset region within multiple historical time periods; one historical time period corresponds to one economic data group and one power load value; each economic data group includes equipment manufacturing industry statistics, new energy industry statistics, and agricultural electrification statistics; the time length of each historical time period in multiple historical time periods is a preset time length;

[0007] Determine, based on multiple economic data groups and multiple historical power load values, a first impact coefficient corresponding to the equipment manufacturing industry statistics, a second impact coefficient corresponding to the new energy industry statistics, and a third impact coefficient corresponding to the agricultural electrification statistics;

[0008] Determine a target adjustment factor based on the first influence coefficient, the second influence coefficient, and the third influence coefficient;

[0009] Determining a first reference power load value based on an average of a plurality of historical power load values;

[0010] Acquire temperature data of a target future time period; the time length of the target future time period is equal to a preset time length;

[0011] Adjust the first reference power load value based on the temperature data to obtain a second reference power load value;

[0012] The second reference power load value is adjusted based on the target adjustment factor to obtain a target power load value.

[0013] In a second aspect, an embodiment of the present application provides a power load prediction device, the device comprising: an acquisition unit and a processing unit;

[0014] An acquisition unit is used to acquire multiple economic data groups and multiple historical power load values ​​in a preset region within multiple historical time periods; one historical time period corresponds to one economic data group and one power load value; each economic data group includes statistical values ​​of equipment manufacturing industry, statistical values ​​of new energy industry, and statistical values ​​of agricultural electrification;

[0015] A processing unit, configured to determine, based on a plurality of economic data groups and a plurality of historical power load values, a first influence coefficient corresponding to the equipment manufacturing industry statistics, a second influence coefficient corresponding to the new energy industry statistics, and a third influence coefficient corresponding to the agricultural electrification statistics;

[0016] Determine a target adjustment factor based on the first influence coefficient, the second influence coefficient, and the third influence coefficient;

[0017] Determining a first reference power load value corresponding to a plurality of historical power load values;

[0018] An acquisition unit, used to acquire temperature data of a target time period; the target time period is a time period after the current moment;

[0019] a processing unit, configured to adjust the first reference power load value based on the temperature data to obtain a second reference power load value;

[0020] The second reference power load value is adjusted based on the target adjustment factor to obtain a target power load value.

[0021] In a third aspect, an embodiment of the present invention provides an electronic device, comprising: a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor so that the electronic device executes the method of the first aspect.

[0022] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the method of the first aspect.

[0023] In a fifth aspect, an embodiment of the present invention provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, so that a computer executes the method of the first aspect.

[0024] The implementation of the present invention has the following beneficial effects:

[0025] It can be seen that the power load forecasting method, device, electronic device and storage medium described in the embodiments of the present invention include: obtaining multiple economic data groups and multiple historical power load values ​​in a preset area within multiple historical time periods, determining a first influence coefficient corresponding to the equipment manufacturing industry statistical value, a second influence coefficient corresponding to the new energy industry statistical value, and a third influence coefficient corresponding to the agricultural electrification statistical value based on the multiple economic data groups and the multiple historical power load values, and then determining a target adjustment factor based on the first influence coefficient, the second influence coefficient and the third influence coefficient, and then determining a first reference power load value based on the average of multiple historical power load values, and obtaining temperature data for a target future time period, adjusting the first reference power load value based on the temperature data to obtain a second reference power load value, and finally adjusting the second reference power load value based on the target adjustment factor to obtain a target power load value, and by determining the influence of economic data such as equipment manufacturing industry production statistics, new energy industry production statistics, and agricultural electrification production statistics on the power load value, the accuracy of the power load forecasting result is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the implementation methods of the present application or the background technology, the drawings required for use in the implementation methods of the present application or the background technology will be described below.

[0027] Figure 1 is a flow chart of a power load forecasting method provided in an embodiment of the present application;

[0028] Figure 2 It is a time series diagram provided by an embodiment of the present application;

[0029] Figure 3 It is a structural schematic diagram of a power load prediction device provided in an embodiment of the present application;

[0030] Figure 4 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0031] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the implementation mode of the present application will be clearly and completely described below in conjunction with the drawings in the implementation mode of the present application. Obviously, the described implementation mode is only a part of the implementation mode of the present application, not all the implementation modes. Based on the implementation mode in the present application, all other implementation modes obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0032] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0033] Reference to "embodiment" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiment may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0034] See also Figure 1 , Figure 1 This is a flow chart of a method for predicting power load provided by an embodiment of the present application, including but not limited to the following steps:

[0035] S101: Acquire multiple economic data groups and multiple historical power load values ​​in a preset region within multiple historical time periods.

[0036] In this embodiment, one historical time period corresponds to one economic data group and one power load value; each economic data group includes statistical values ​​of equipment manufacturing industry, statistical values ​​of new energy industry, and statistical values ​​of agricultural electrification; the time length of each historical time period in multiple historical time periods is a preset time length.

[0037] It should be explained that you can select a time period of several years from the current moment in order to better reflect the current economic and power load conditions. For example, you can select historical data from the past 5 or 10 years. The preset time length can be set according to the specific situation. Generally, you can choose one day, one week, one month or one quarter. If the power company can only provide monthly power load data, then the preset time length can be set to one month.

[0038] It needs to be explained that the equipment manufacturing industry mainly includes the manufacturing of industrial robots, power generation equipment, power transmission and transformation equipment, railway equipment, aviation equipment, satellites and application equipment.

[0039] Specifically, according to the determined data sources, relevant data on equipment manufacturing, new energy industry and agricultural electrification production in the preset region in multiple historical time periods are collected. Data can be obtained through online query, data application, purchase report, etc., and the collected data are sorted and classified to ensure that the data format is unified and accurate, and multiple historical time periods are consecutive time periods. The collected economic data and power load values ​​are matched according to the historical time periods to ensure that one historical time period corresponds to one economic data group and one power load value. For example, if the preset time period is one month, then each month's economic data group (including equipment manufacturing industry statistics, new energy industry statistics, and agricultural electrification statistics) should correspond to the power load value of that month.

[0040] It can be seen that each economic data group contains statistical values ​​for the equipment manufacturing industry, new energy industry and agricultural electrification, which allows independent analysis of different industries. By continuously observing data from multiple historical time periods, we can discover the changing trend of power load over time and its dynamic relationship with economic activities.

[0041] It should be explained that a time series graph can also be drawn based on multiple economic data groups and multiple historical power load values ​​in a preset region in multiple historical time periods, and time series graphs can be drawn for multiple economic data groups and multiple historical power load values ​​respectively, and the correlation coefficient of the two time series can be calculated, and the relationship between the economic data and the power load value can be determined based on the correlation coefficient of the two time series. Figure 2 , Figure 2 It is a time series graph provided in the implementation mode of the present application, in which the horizontal axis is time and the vertical axis is the historical power load value. Overall, the time series graph can show an obvious upward trend, indicating that the power load gradually increases with the passage of time.

[0042] S102: Determine a first impact coefficient corresponding to the equipment manufacturing industry statistics, a second impact coefficient corresponding to the new energy industry statistics, and a third impact coefficient corresponding to the agricultural electrification statistics based on multiple economic data groups and multiple historical power load values.

[0043] In this embodiment, exemplarily, multiple equipment manufacturing industry statistical values, multiple new energy industry statistical values, and multiple agricultural electrification statistical values ​​are obtained from multiple economic data groups. Specifically, each economic data group includes one equipment manufacturing industry statistical value, one new energy industry statistical value, and one agricultural electrification statistical value, and multiple economic data groups include multiple equipment manufacturing industry statistical values, multiple new energy industry statistical values, and multiple agricultural electrification statistical values.

[0044] Exemplarily, a first straight line is obtained by fitting multiple equipment manufacturing industry statistical values ​​with multiple historical time periods. Specifically, a fitting method is used to fit multiple equipment manufacturing industry statistical values ​​with multiple historical time periods to obtain the first straight line, and the vertical axis of the first straight line is the equipment manufacturing industry statistical value, and the horizontal axis is the historical time period. The first straight line obtained after fitting can intuitively highlight the changes in the equipment manufacturing industry statistical values ​​in multiple historical time periods.

[0045] Exemplarily, the slope of the first straight line is acquired to obtain the first slope. Specifically, any two points in the first straight line are selected to calculate the slope corresponding to the first straight line to obtain the first slope.

[0046] Exemplarily, the first influence coefficient corresponding to multiple equipment manufacturing industry statistics is determined based on the first slope. Specifically, it can be a mapping relationship between a preset slope and the influence coefficient corresponding to the equipment manufacturing industry statistics. The first influence coefficient corresponding to the first slope can be determined based on the mapping relationship.

[0047] Exemplarily, a second straight line is obtained by fitting multiple new energy industry statistical values ​​with multiple historical time periods. Specifically, a fitting method is used to fit multiple new energy industry statistical values ​​with multiple historical time periods to obtain the second straight line, and the vertical axis of the second straight line is the new energy industry statistical value, and the horizontal axis is the historical time period. The second straight line obtained after fitting can intuitively highlight the changes in the new energy industry statistical values ​​in multiple historical time periods.

[0048] Exemplarily, the second slope is obtained based on the slope of the second straight line. Specifically, any two points in the second straight line are selected to calculate the slope corresponding to the second straight line to obtain the second slope.

[0049] Exemplarily, the second influence coefficient corresponding to multiple new energy industry statistical values ​​is determined based on the second slope. Specifically, it can be a mapping relationship between a preset slope and the influence coefficient corresponding to the new energy industry statistical value, and the second influence coefficient corresponding to the second slope can be determined based on the mapping relationship.

[0050] Exemplarily, a third straight line is obtained by fitting based on multiple agricultural electrification statistical values. Specifically, a fitting method is used to fit multiple agricultural electrification statistical values ​​with multiple historical time periods to obtain the third straight line, and the vertical axis of the third straight line is the agricultural electrification statistical value, and the horizontal axis is the historical time period. The third straight line obtained after fitting can intuitively highlight the changes in the agricultural electrification statistical values ​​in multiple historical time periods.

[0051] Exemplarily, the slope of the third straight line is obtained to obtain the third slope. Specifically, any two points in the third straight line are selected to calculate the slope corresponding to the third straight line to obtain the third slope.

[0052] Exemplarily, the third influence coefficient corresponding to multiple agricultural electrification statistical values ​​is determined based on the third slope. Specifically, it can be a mapping relationship between a preset slope and the influence coefficient corresponding to the agricultural electrification statistical value, and the third influence coefficient corresponding to the third slope can be determined based on the mapping relationship.

[0053] It can be seen that the first influence coefficient, the second influence coefficient and the third influence coefficient are determined based on the first slope, the second slope and the third slope respectively. The calculation is based on objective historical data, avoiding the interference of subjective factors, making the determination of the influence coefficient more scientific and accurate. The determination process of the influence coefficient is actually exploring the relationship between the development of various industries and the power load. By analyzing the relationship between the changes in industrial statistical values ​​over time and the power load value, the degree of influence of various industries on the power load can be determined.

[0054] S103: Determine a target adjustment factor based on the first influence coefficient, the second influence coefficient, and the third influence coefficient.

[0055] In this embodiment, exemplarily, a first reference weight corresponding to the first influence coefficient, a second reference weight corresponding to the second influence coefficient, and a third reference weight corresponding to the third influence coefficient are determined. Specifically, it can be a mapping relationship between preset influence coefficients and reference weights. According to the mapping relationship, the first reference weight corresponding to the first influence coefficient, the second reference weight corresponding to the second influence coefficient, and the third reference weight corresponding to the third influence coefficient can be determined, and the sum of the three weights of the first reference weight, the second reference weight, and the third reference weight is 1.

[0056] Exemplarily, the population growth rate of a preset region in multiple historical time periods is obtained, and a first optimization factor corresponding to the population growth rate is determined. The first reference weight is optimized according to the first optimization factor to obtain a first target weight. Specifically, population growth usually leads to an increase in the overall demand for various products. For the equipment manufacturing industry, population growth may mean an increase in the demand for equipment related to infrastructure construction, and population growth will drive the development of related industries, thereby indirectly affecting the demand for the equipment manufacturing industry. Therefore, the population growth rate of the preset region in multiple historical time periods is obtained, and then the first optimization factor corresponding to the population growth rate is determined. It can be a correspondence between a preset population growth rate and an optimization factor. Based on the correspondence, the first optimization factor corresponding to the population growth rate can be determined, and then the first reference weight is optimized according to the first optimization factor. The specific calculation formula is as follows: first target weight = first reference weight × (1 + first optimization factor); the first target weight can be obtained according to the above formula.

[0057] Exemplarily, the total amount of new energy vehicles used in a preset region within multiple historical time periods is obtained, and a second optimization factor corresponding to the total amount of new energy vehicles used is determined. The second reference weight is optimized according to the second optimization factor to obtain the second target weight. Specifically, the increase in the total amount of new energy vehicles used means that the market demand for new energy vehicles is growing. This growth in demand will prompt enterprises in the new energy vehicle industry chain to expand their production scale, including battery production, motor manufacturing, electronic control systems and other related enterprises. The expansion of the production scale of enterprises will bring more investment, output and employment, thereby promoting the expansion of the overall scale of the new energy industry, increasing the statistical value of the new energy industry, and further increasing the second impact coefficient. Therefore, the total amount of new energy vehicles used in the preset region within multiple historical time periods is obtained, and then the second optimization factor corresponding to the total amount of new energy vehicles used is determined. It can be a correspondence between the preset total amount of new energy vehicles used and the optimization factor. Based on the correspondence, the second optimization factor corresponding to the total amount of new energy vehicles used can be determined, and then the second reference weight is optimized according to the second optimization factor to obtain the second target weight. The specific calculation formula is as follows: second target weight=second reference weight×(1+second optimization factor); the second target weight can be obtained according to the above formula.

[0058] Exemplarily, the statistical value of agricultural production area in a preset area is obtained, and the third optimization factor corresponding to the statistical value of agricultural production area is determined. The third reference weight is optimized according to the third optimization factor to obtain the third target weight. Specifically, the larger the agricultural production area, the larger the scale of agricultural production, and the demand for electricity will increase accordingly. The increase in agricultural production area may prompt local governments and power departments to increase the construction of agricultural power infrastructure. In order to meet the electricity demand of large-scale agricultural production, it is necessary to build more power facilities such as substations and transmission lines to improve the power supply situation in rural areas. The improvement of power infrastructure can provide better conditions for the development of agricultural electrification, improve the statistical value of agricultural electrification, and thus affect the third influence coefficient. Then, the third optimization factor corresponding to the statistical value of agricultural production area is determined, which can be the corresponding relationship between the preset statistical value of agricultural production area and the optimization factor. Based on the corresponding relationship, the third optimization factor corresponding to the total amount of new energy vehicle use can be determined, and then the third reference weight is optimized according to the third optimization factor to obtain the third target weight. The specific calculation formula is as follows: third target weight = third reference weight × (1 + third optimization factor); the third target weight can be obtained according to the above formula.

[0059] Exemplarily, the target adjustment factor is obtained by calculation based on the first target weight, the second target weight, the third target weight, the first influence coefficient, the second influence coefficient, and the third influence coefficient. Specifically, the reference adjustment factor is obtained by calculation based on the first target weight, the second target weight, the third target weight, the first influence coefficient, the second influence coefficient, and the third influence coefficient. The reference adjustment factor is calculated specifically according to the following formula:

[0060] F=a×α+b×β+c×ε

[0061] Among them, F is the reference adjustment factor, a is the first influence coefficient, b is the second influence coefficient, c is the third influence coefficient, α is the first target weight, β is the second target weight, and ε is the third target weight.

[0062] Exemplarily, the gross domestic product of a preset region in multiple historical time periods is obtained, the target fine-tuning parameters corresponding to the gross domestic product are determined, and the reference adjustment factor is fine-tuned according to the target fine-tuning parameters to obtain the target adjustment factor. Specifically, the growth of gross domestic product usually means an increase in economic activities in the preset region, and also means more investment and construction activities. New infrastructure construction projects, such as roads, bridges, factories, and houses, all require a large amount of electricity to support the construction process. Therefore, the gross domestic product of the preset region in multiple historical time periods is obtained, and then the target fine-tuning parameters corresponding to the gross domestic product are determined. It can be a mapping relationship between the preset gross domestic product and the fine-tuning parameters. Based on the mapping relationship, the target fine-tuning parameters corresponding to the gross domestic product can be determined, and then the reference adjustment factor is fine-tuned according to the target fine-tuning parameters to obtain the target adjustment factor. The specific calculation formula is as follows: target adjustment factor = reference adjustment factor × (1 + target fine-tuning parameter); the target adjustment factor can be obtained according to the above formula.

[0063] It can be seen that by determining the reference weights corresponding to different influencing coefficients and optimizing them according to specific factors (population growth rate, total use of new energy vehicles, and statistical values ​​of agricultural production area), the target weights can be obtained, which can make the determination of weights more personalized and accurate. As time goes by, the development of the region will change, and factors such as population growth rate, total use of new energy vehicles, and statistical values ​​of agricultural production area will also change constantly. The weights can be adjusted in time according to these changes, so that the target adjustment factor can adapt to the development and changes of the region. The dynamic adjustment of the weights enables the target adjustment factor to reflect the latest situation in the region in real time, thereby improving the reliability of power load forecasting and adjustment.

[0064] S104: Determine a first reference power load value based on an average of multiple historical power load values.

[0065] In this embodiment, exemplarily, the mean of multiple historical power load values ​​is obtained to obtain an average power load value, the mean square error corresponding to the multiple historical power load values ​​is determined, the target optimization coefficient corresponding to the mean square error is determined, the average power load value is optimized according to the target optimization coefficient, and a first reference power load value is obtained. Specifically, the mean of multiple historical power load values ​​is first calculated to obtain the average power load value, and then the mean square error corresponding to the multiple historical power load values ​​is calculated. The average power load value represents the average level of power load in multiple historical time periods. By calculating this value, the overall power demand scale of the preset area in history can be intuitively understood. The mean square error reflects the degree of dispersion of multiple historical power load values ​​relative to the average power load value. The larger the mean square error, the greater the fluctuation of the historical power load value, and the smaller the mean square error, the relatively stable load value. Then, the target optimization coefficient corresponding to the mean square error is determined, which can be a mapping relationship between the preset mean square error and the optimization coefficient. Based on the mapping relationship, the target optimization coefficient corresponding to the mean square error can be determined, and then the average power load value is optimized according to the target optimization coefficient to obtain the first reference power load value. The specific calculation formula is as follows: first reference power load value = average power load value × (1 + target optimization coefficient); The first reference power load value can be obtained according to the above formula.

[0066] It can be seen that by calculating the mean square error, the discreteness of multiple historical power load values ​​can be quantified, reflecting the fluctuation of the power load. A larger mean square error indicates a large load fluctuation, and vice versa. Considering the target optimization coefficient corresponding to the mean square error when determining the first reference power load value can fully consider the fluctuation characteristics of the load, so that the obtained first reference power load value more accurately reflects the actual situation.

[0067] S105: Acquire temperature data for a target future time period.

[0068] In this embodiment, the time length of the target future time period is equal to the preset time length.

[0069] For example, temperature differences can directly affect power load. Temperature changes can affect the production and operation activities of some industries, and thus indirectly affect power load. For example, high or low temperature weather may affect the progress and methods of construction, thereby affecting the electricity demand of the construction industry. In hot weather, outdoor construction may be restricted, and some projects may adjust construction time or adopt different construction methods, which may cause changes in power load. Similarly, low temperature weather may affect logistics and transportation. For example, the transportation demand for refrigerated goods may increase, thereby affecting power load, so obtain temperature data for the target future time period.

[0070] The temperature data of a preset area in multiple historical time periods can be incorporated as input variables into the power load forecasting model to improve the accuracy of the forecast. There is a close relationship between temperature and power load. By analyzing the correlation between temperature and power load in historical data, a more accurate forecasting model can be established. For example, regression analysis, neural networks and other methods can be used to take temperature data together with other economic, social and other variables as input to predict future power loads. The introduction of historical temperature data can better capture the impact of temperature changes on power loads and improve the accuracy of forecasts.

[0071] S106: Adjust the first reference power load value based on the temperature data to obtain a second reference power load value.

[0072] In this embodiment, multiple temperature values ​​in the temperature data are obtained, and the average temperature value corresponding to the multiple temperature values ​​is determined. If the average temperature value is less than the preset temperature value, the first adjustment coefficient corresponding to the average temperature value is determined, and the first reference power load value is adjusted based on the first adjustment coefficient to obtain the second reference power load value. Specifically, when the average temperature value is less than the preset temperature value, it indicates that the current temperature is at a relatively low state. Historical data shows that there is a certain correlation between temperature and power load. When the average temperature value is less than the preset temperature value, the usage of temperature-related electrical equipment will change. Therefore, the first adjustment coefficient corresponding to the average temperature value is determined, and the first reference power load value is adjusted based on the first adjustment coefficient. The specific calculation formula is as follows: second reference power load value = first reference power load value × (1 + first adjustment coefficient); the second reference power load value can be obtained according to the above formula.

[0073] If the average temperature value is greater than or equal to the preset temperature value, the target temperature straight line is fitted based on the temperature data to obtain the target temperature straight line, the temperature rise slope corresponding to the target temperature straight line is determined, the second adjustment coefficient corresponding to the temperature rise slope is determined, and the first reference power load value is adjusted based on the second adjustment coefficient to obtain the second reference power load value. Specifically, when the average temperature value is greater than or equal to the preset temperature value, it indicates that it is in a relatively high temperature range. In this range, the influence of temperature on power load is different from that in the lower temperature range. By fitting the target temperature straight line based on the temperature data and determining the temperature rise slope, the relationship between temperature change and power load in the high temperature range can be more accurately captured. As the temperature rises, the use of refrigeration equipment such as air conditioners will increase significantly, resulting in a rapid increase in power load, and this rising trend may not be linear. By fitting the temperature straight line, the complex relationship between temperature and power load can be better reflected, so that the adjusted second reference power load value is more in line with the actual situation. By fitting the temperature data using the fitting method, the target temperature straight line can be obtained, and the vertical axis of the target temperature straight line is the temperature value and the horizontal axis is the time. The target temperature straight line obtained after fitting can intuitively highlight the temperature change. Then, the temperature rise slope corresponding to the target temperature line is determined, and the second adjustment coefficient corresponding to the temperature rise slope is determined. Specifically, it can be a mapping relationship between the preset temperature rise slope and the adjustment coefficient, and then the second adjustment coefficient corresponding to the temperature rise slope can be determined according to the mapping relationship. Then, the first reference power load value is adjusted based on the second adjustment coefficient to obtain the second reference power load value. The specific calculation formula is as follows: second reference power load value = first reference power load value × (1 + second adjustment coefficient); The second reference power load value can be obtained according to the above formula.

[0074] It can be seen that by distinguishing between the two situations where the average temperature value is less than the preset temperature value and the situation where it is greater than or equal to the preset temperature value, and using different methods to determine the adjustment coefficient, the impact of temperature on the power load can be considered more finely. The relationship between temperature and power load may be different in different temperature ranges. This situation-by-situation processing can more accurately capture this change, thereby improving the accuracy of power load prediction. For the situation where the average temperature value is less than the preset temperature value, the first adjustment coefficient corresponding to the average temperature value is directly determined. This method can quickly adjust the power load according to the current temperature conditions. For the situation where the average temperature value is greater than or equal to the preset temperature value, the target temperature straight line is obtained by fitting the temperature data, and then the temperature rise slope is determined to obtain the second adjustment coefficient. This method can take into account the trend of temperature changes and make the adjustment coefficient more dynamic and forward-looking.

[0075] S107: Adjust the second reference power load value based on the target adjustment factor to obtain a target power load value.

[0076] In this embodiment, if the target adjustment factor is greater than the preset adjustment factor, fitting is performed based on multiple historical power load values ​​and multiple historical time periods to obtain a fitting straight line, the horizontal axis of the fitting straight line is time and the vertical axis is the historical power load value, the target slope of the fitting straight line is determined, the target optimization parameter corresponding to the target slope is determined, and the second reference power load value is optimized according to the target optimization parameter to obtain the target power load value. Specifically, it can be the correspondence between the slope of the preset fitting straight line and the optimization parameter. Based on the correspondence, the target optimization parameter corresponding to the target slope can be determined, and then the second reference power load value is optimized according to the target optimization parameter to obtain the target power load value. The specific calculation formula is as follows: target power load value = second reference power load value × (1 + target optimization parameter); the target power load value can be obtained according to the above formula.

[0077] It can be seen that when the target adjustment factor is greater than the preset adjustment factor, the trend of power load changes over time can be captured by fitting a straight line based on multiple historical power load values ​​and multiple historical time periods. After determining the target slope of the fitting line, the target optimization parameter is determined according to the target slope, and the second reference power load value is optimized, so that the prediction results are more in line with the dynamic changes of the actual situation.

[0078] When the target adjustment factor is less than or equal to the preset adjustment factor, the second reference power load value is adjusted directly based on the target adjustment factor to obtain the target power load value. The specific calculation formula is as follows: target power load value = second reference power load value × (1 + target adjustment factor); The target power load value can be obtained according to the above formula.

[0079] In summary, the implementation of the present invention has the following beneficial effects:

[0080] It can be seen that the power load forecasting method, device, electronic device and storage medium described in the embodiments of the present invention include: obtaining multiple economic data groups and multiple historical power load values ​​in a preset area within multiple historical time periods, determining a first influence coefficient corresponding to the equipment manufacturing industry statistical value, a second influence coefficient corresponding to the new energy industry statistical value, and a third influence coefficient corresponding to the agricultural electrification statistical value based on the multiple economic data groups and the multiple historical power load values, and then determining a target adjustment factor based on the first influence coefficient, the second influence coefficient and the third influence coefficient, and then determining a first reference power load value based on the average of multiple historical power load values, and obtaining temperature data for a target future time period, adjusting the first reference power load value based on the temperature data to obtain a second reference power load value, and finally adjusting the second reference power load value based on the target adjustment factor to obtain a target power load value, and by determining the influence of economic data such as equipment manufacturing industry production statistics, new energy industry production statistics, and agricultural electrification production statistics on the power load value, the accuracy of the power load forecasting result is improved.

[0081] See also Figure 3 , Figure 3 It is a structural schematic diagram of a power load prediction device provided in an embodiment of the present application. The power load prediction device 300 includes: an acquisition unit 301 and a processing unit 302;

[0082] The acquisition unit 301 is used to acquire multiple economic data groups and multiple historical power load values ​​in a preset region within multiple historical time periods; one historical time period corresponds to one economic data group and one power load value; each economic data group includes equipment manufacturing industry statistics, new energy industry statistics, and agricultural electrification statistics;

[0083] A processing unit 302 is used to determine a first influence coefficient corresponding to the equipment manufacturing industry statistics, a second influence coefficient corresponding to the new energy industry statistics, and a third influence coefficient corresponding to the agricultural electrification statistics based on multiple economic data groups and multiple historical power load values;

[0084] Determine a target adjustment factor based on the first influence coefficient, the second influence coefficient, and the third influence coefficient;

[0085] Determining a first reference power load value corresponding to a plurality of historical power load values;

[0086] An acquisition unit 301 is used to acquire temperature data of a target time period; the target time period is a time period after the current moment;

[0087] The processing unit 302 is used to adjust the first reference power load value based on the temperature data to obtain a second reference power load value;

[0088] The second reference power load value is adjusted based on the target adjustment factor to obtain a target power load value.

[0089] In some possible implementations, in determining a first influence coefficient corresponding to the equipment manufacturing industry statistics, a second influence coefficient corresponding to the new energy industry statistics, and a third influence coefficient corresponding to the agricultural electrification statistics based on multiple economic data groups and multiple historical power load values, the processing unit 302 is specifically used to:

[0090] Obtain multiple equipment manufacturing industry statistics, multiple new energy industry statistics, and multiple agricultural electrification statistics in multiple economic data groups;

[0091] The first straight line is obtained by fitting multiple equipment manufacturing industry statistics and multiple historical time periods;

[0092] Obtaining the slope of the first straight line to obtain a first slope;

[0093] Determine a first influence coefficient corresponding to a plurality of equipment manufacturing industry statistical values ​​based on the first slope;

[0094] The second straight line is obtained by fitting multiple new energy industry statistical values ​​with multiple historical time periods;

[0095] Based on the slope of the second straight line, a second slope is obtained;

[0096] Determine a second impact coefficient corresponding to a plurality of new energy industry statistical values ​​based on the second slope;

[0097] The third straight line is obtained by fitting based on multiple agricultural electrification statistical values;

[0098] Obtaining the slope of the third straight line to obtain a third slope;

[0099] A third influence coefficient corresponding to a plurality of agricultural electrification statistical values ​​is determined based on the third slope.

[0100] In some possible implementations, in determining the target adjustment factor based on the first influence coefficient, the second influence coefficient, and the third influence coefficient, the processing unit 302 is specifically configured to:

[0101] Determine a first reference weight corresponding to the first influence coefficient, a second reference weight corresponding to the second influence coefficient, and a third reference weight corresponding to the third influence coefficient;

[0102] Get the population growth rate of a preset region in multiple historical time periods;

[0103] determining a first optimization factor corresponding to a population growth rate;

[0104] Optimizing the first reference weight according to the first optimization factor to obtain a first target weight;

[0105] Get the total amount of new energy vehicles used in a preset region in multiple historical time periods;

[0106] Determine a second optimization factor corresponding to the total amount of new energy vehicles used;

[0107] Optimizing the second reference weight according to the second optimization factor to obtain a second target weight;

[0108] Get the statistical value of agricultural production area in the preset region;

[0109] Determine a third optimization factor corresponding to the statistical value of agricultural production area;

[0110] Optimizing the third reference weight according to the third optimization factor to obtain a third target weight;

[0111] The target adjustment factor is obtained by performing calculation based on the first target weight, the second target weight, the third target weight, the first influence coefficient, the second influence coefficient, and the third influence coefficient.

[0112] In some possible implementations, in terms of obtaining the target adjustment factor by calculating based on the first target weight, the second target weight, the third target weight, the first influence coefficient, the second influence coefficient, and the third influence coefficient, the processing unit 302 is specifically configured to:

[0113] Calculate based on the first target weight, the second target weight, the third target weight, the first influence coefficient, the second influence coefficient, and the third influence coefficient to obtain a reference adjustment factor;

[0114] Get the gross domestic product of a preset region in multiple historical time periods;

[0115] Determine the target fine-tuning parameters corresponding to the gross domestic product;

[0116] The reference adjustment factor is fine-tuned according to the target fine-tuning parameter to obtain the target adjustment factor.

[0117] In some possible implementations, the processing unit 302 is specifically configured to:

[0118] If the target adjustment factor is greater than the preset adjustment factor, fitting is performed based on multiple historical power load values ​​and multiple historical time periods to obtain a fitting straight line; the horizontal axis of the fitting straight line is time and the vertical axis is the historical power load value;

[0119] Determine the target slope of the fitted line;

[0120] determining a target optimization parameter corresponding to the target slope;

[0121] The second reference power load value is optimized according to the target optimization parameter to obtain a target power load value.

[0122] In some possible implementations, in determining the first reference power load value based on the average of multiple historical power load values, the processing unit 302 is specifically configured to:

[0123] Obtain the average of multiple historical power load values ​​to obtain an average power load value;

[0124] Determine a mean square error corresponding to a plurality of historical power load values;

[0125] Determine the target optimization coefficient corresponding to the mean square error;

[0126] The average power load value is optimized according to the target optimization coefficient to obtain a first reference power load value.

[0127] In some possible implementations, in terms of adjusting the first reference power load value based on the temperature data to obtain the second reference power load value, the processing unit 302 is specifically configured to:

[0128] Get multiple temperature values ​​in temperature data;

[0129] Determine an average temperature value corresponding to the multiple temperature values;

[0130] If the average temperature value is less than the preset temperature value, determining a first adjustment coefficient corresponding to the average temperature value;

[0131] Adjust the first reference power load value based on the first adjustment coefficient to obtain a second reference power load value;

[0132] If the average temperature value is greater than or equal to the preset temperature value, fitting is performed based on the temperature data to obtain the target temperature straight line;

[0133] Determine the temperature rise slope corresponding to the target temperature straight line;

[0134] determining a second adjustment coefficient corresponding to the temperature rising slope;

[0135] The first reference power load value is adjusted based on the second adjustment coefficient to obtain a second reference power load value.

[0136] See also Figure 4 , Figure 4 Schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. Figure 4As shown, the electronic device 400 includes a transceiver 401, a processor 402 and a memory 403. They are connected via a bus 404. The memory 403 is used to store computer programs and data, and the transceiver 401 can transmit the data stored in the memory 403 to the processor 402. The above program includes instructions for executing the following steps:

[0137] Obtain multiple economic data groups and multiple historical power load values ​​in a preset region within multiple historical time periods; one historical time period corresponds to one economic data group and one power load value; each economic data group includes equipment manufacturing industry statistics, new energy industry statistics, and agricultural electrification statistics; the time length of each historical time period in multiple historical time periods is a preset time length;

[0138] Determine, based on multiple economic data groups and multiple historical power load values, a first impact coefficient corresponding to the equipment manufacturing industry statistics, a second impact coefficient corresponding to the new energy industry statistics, and a third impact coefficient corresponding to the agricultural electrification statistics;

[0139] Determine a target adjustment factor based on the first influence coefficient, the second influence coefficient, and the third influence coefficient;

[0140] Determining a first reference power load value based on an average of a plurality of historical power load values;

[0141] Acquire temperature data of a target future time period; the time length of the target future time period is equal to a preset time length;

[0142] Adjust the first reference power load value based on the temperature data to obtain a second reference power load value;

[0143] The second reference power load value is adjusted based on the target adjustment factor to obtain a target power load value.

[0144] In some possible implementations, in terms of determining a first impact coefficient corresponding to the equipment manufacturing industry statistics, a second impact coefficient corresponding to the new energy industry statistics, and a third impact coefficient corresponding to the agricultural electrification statistics based on multiple economic data groups and multiple historical power load values, the program includes instructions for performing the following steps:

[0145] Obtain multiple equipment manufacturing industry statistics, multiple new energy industry statistics, and multiple agricultural electrification statistics in multiple economic data groups;

[0146] The first straight line is obtained by fitting multiple equipment manufacturing industry statistics and multiple historical time periods;

[0147] Obtaining the slope of the first straight line to obtain a first slope;

[0148] Determine a first influence coefficient corresponding to a plurality of equipment manufacturing industry statistical values ​​based on the first slope;

[0149] The second straight line is obtained by fitting multiple new energy industry statistical values ​​with multiple historical time periods;

[0150] Based on the slope of the second straight line, a second slope is obtained;

[0151] Determine a second impact coefficient corresponding to a plurality of new energy industry statistical values ​​based on the second slope;

[0152] The third straight line is obtained by fitting based on multiple agricultural electrification statistical values;

[0153] Obtaining the slope of the third straight line to obtain a third slope;

[0154] A third influence coefficient corresponding to a plurality of agricultural electrification statistical values ​​is determined based on the third slope.

[0155] In some possible implementations, in terms of determining the target adjustment factor based on the first influence coefficient, the second influence coefficient, and the third influence coefficient, the program includes instructions for performing the following steps:

[0156] Determine a first reference weight corresponding to the first influence coefficient, a second reference weight corresponding to the second influence coefficient, and a third reference weight corresponding to the third influence coefficient;

[0157] Get the population growth rate of a preset region in multiple historical time periods;

[0158] determining a first optimization factor corresponding to a population growth rate;

[0159] Optimizing the first reference weight according to the first optimization factor to obtain a first target weight;

[0160] Get the total amount of new energy vehicles used in a preset region in multiple historical time periods;

[0161] Determine a second optimization factor corresponding to the total amount of new energy vehicles used;

[0162] Optimizing the second reference weight according to the second optimization factor to obtain a second target weight;

[0163] Get the statistical value of agricultural production area in the preset region;

[0164] Determine a third optimization factor corresponding to the statistical value of agricultural production area;

[0165] Optimizing the third reference weight according to the third optimization factor to obtain a third target weight;

[0166] The target adjustment factor is obtained by performing calculation based on the first target weight, the second target weight, the third target weight, the first influence coefficient, the second influence coefficient, and the third influence coefficient.

[0167] In some possible implementations, in terms of obtaining the target adjustment factor by calculating based on the first target weight, the second target weight, the third target weight, the first influence coefficient, the second influence coefficient, and the third influence coefficient, the program includes instructions for performing the following steps:

[0168] Calculate based on the first target weight, the second target weight, the third target weight, the first influence coefficient, the second influence coefficient, and the third influence coefficient to obtain a reference adjustment factor;

[0169] Get the gross domestic product of a preset region in multiple historical time periods;

[0170] Determine the target fine-tuning parameters corresponding to the gross domestic product;

[0171] The reference adjustment factor is fine-tuned according to the target fine-tuning parameter to obtain the target adjustment factor.

[0172] In some possible implementations, the above program includes instructions for performing the following steps:

[0173] If the target adjustment factor is greater than the preset adjustment factor, fitting is performed based on multiple historical power load values ​​and multiple historical time periods to obtain a fitting straight line; the horizontal axis of the fitting straight line is time and the vertical axis is the historical power load value;

[0174] Determine the target slope of the fitted line;

[0175] determining a target optimization parameter corresponding to the target slope;

[0176] The second reference power load value is optimized according to the target optimization parameter to obtain a target power load value.

[0177] In some possible implementations, in determining the first reference power load value based on the average of multiple historical power load values, the program includes instructions for performing the following steps:

[0178] Obtain the average of multiple historical power load values ​​to obtain an average power load value;

[0179] Determine a mean square error corresponding to a plurality of historical power load values;

[0180] Determine the target optimization coefficient corresponding to the mean square error;

[0181] The average power load value is optimized according to the target optimization coefficient to obtain a first reference power load value.

[0182] In some possible implementations, in terms of adjusting the first reference power load value based on the temperature data to obtain the second reference power load value, the program includes instructions for performing the following steps:

[0183] Get multiple temperature values ​​in temperature data;

[0184] Determine an average temperature value corresponding to the multiple temperature values;

[0185] If the average temperature value is less than the preset temperature value, determining a first adjustment coefficient corresponding to the average temperature value;

[0186] Adjust the first reference power load value based on the first adjustment coefficient to obtain a second reference power load value;

[0187] If the average temperature value is greater than or equal to the preset temperature value, fitting is performed based on the temperature data to obtain the target temperature straight line;

[0188] Determine the temperature rise slope corresponding to the target temperature straight line;

[0189] determining a second adjustment coefficient corresponding to the temperature rising slope;

[0190] The first reference power load value is adjusted based on the second adjustment coefficient to obtain a second reference power load value.

[0191] It should be understood that the electronic devices in this application may include smart phones (such as Android phones, iOS phones, Windows Phone phones, etc.), tablet computers, PDAs, laptops, mobile Internet devices MID (Mobile Internet Devices, MID for short) or wearable devices or servers, edge computing nodes, etc. The above electronic devices are only examples, not exhaustive, and include but are not limited to the above electronic devices.

[0192] The embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. The computer program is executed by a processor to implement part or all of the steps of any one of the power load forecasting methods described in the above method embodiments.

[0193] An embodiment of the present application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute part or all of the steps of any one of the power load forecasting methods recorded in the above method embodiments.

[0194] It should be noted that, for the above-mentioned various method implementations, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the implementations described in the specification are all optional implementations, and the actions and modules involved are not necessarily required by this application.

[0195] In the above-mentioned embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0196] In the several embodiments provided in this application, it should be understood that the disclosed device can be implemented in other ways. For example, the device implementation described above is only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0197] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0198] 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 separately, or two or more units may be integrated into one unit. The above integrated unit may be implemented in the form of hardware or in the form of a software program module.

[0199] If the integrated unit is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, 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 memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of each implementation method of the present application. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0200] A person skilled in the art can understand that all or part of the steps in the various methods of the above-mentioned embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, and the memory can include: a flash drive, a read-only memory (English: Read-Only Memory, abbreviated as: ROM), a random access memory (English: Random Access Memory, abbreviated as: RAM), a magnetic disk or an optical disk, etc.

[0201] The above is a detailed introduction to the implementation methods of the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above implementation methods is only used to help understand the method and core idea of ​​the present application. At the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for predicting power load, characterized in that: include: Acquire multiple economic data groups and multiple historical power load values ​​in a preset region within multiple historical time periods; one historical time period corresponds to one economic data group and one power load value; each economic data group includes statistical values ​​of equipment manufacturing industry, statistical values ​​of new energy industry, and statistical values ​​of agricultural electrification; the time length of each historical time period in the multiple historical time periods is a preset time length; Determine, based on the multiple economic data groups and the multiple historical power load values, a first influence coefficient corresponding to the equipment manufacturing industry statistics, a second influence coefficient corresponding to the new energy industry statistics, and a third influence coefficient corresponding to the agricultural electrification statistics; Determine a target adjustment factor based on the first influence coefficient, the second influence coefficient, and the third influence coefficient; determining a first reference power load value based on an average of the plurality of historical power load values; Acquire temperature data of a target future time period; the time length of the target future time period is equal to the preset time length; adjusting the first reference power load value based on the temperature data to obtain a second reference power load value; The second reference power load value is adjusted based on the target adjustment factor to obtain a target power load value.

2. The method according to claim 1, characterized in that The determining, based on the multiple economic data groups and the multiple historical power load values, a first influence coefficient corresponding to the equipment manufacturing industry statistics, a second influence coefficient corresponding to the new energy industry statistics, and a third influence coefficient corresponding to the agricultural electrification statistics, comprises: Acquire multiple equipment manufacturing industry statistics, multiple new energy industry statistics, and multiple agricultural electrification statistics from the multiple economic data groups; Fitting the plurality of equipment manufacturing industry statistics with the plurality of historical time periods to obtain a first straight line; Obtaining the slope of the first straight line to obtain a first slope; Determine the first influence coefficient corresponding to the plurality of equipment manufacturing industry statistics based on the first slope; Fitting the multiple new energy industry statistical values ​​with the multiple historical time periods to obtain a second straight line; Based on the slope of the second straight line, a second slope is obtained; Determine the second influence coefficient corresponding to the plurality of new energy industry statistical values ​​based on the second slope; Perform fitting according to the plurality of agricultural electrification statistical values ​​to obtain a third straight line; Obtaining the slope of the third straight line to obtain a third slope; A third influence coefficient corresponding to the plurality of agricultural electrification statistical values ​​is determined based on the third slope.

3. The method according to claim 1, characterized in that The determining of the target adjustment factor based on the first influence coefficient, the second influence coefficient, and the third influence coefficient includes: Determine a first reference weight corresponding to the first influence coefficient, a second reference weight corresponding to the second influence coefficient, and a third reference weight corresponding to the third influence coefficient; Obtaining the population growth rate of the preset region during the multiple historical time periods; determining a first optimization factor corresponding to the population growth rate; Optimize the first reference weight according to the first optimization factor to obtain a first target weight; Obtain the total amount of new energy vehicles used in the preset area during the multiple historical time periods; Determining a second optimization factor corresponding to the total amount of use of the new energy vehicles; Optimize the second reference weight according to the second optimization factor to obtain a second target weight; Obtaining the statistical value of the agricultural production area of ​​the preset region; Determining a third optimization factor corresponding to the agricultural production area statistical value; Optimizing the third reference weight according to the third optimization factor to obtain a third target weight; The target adjustment factor is obtained by performing calculation based on the first target weight, the second target weight, the third target weight, the first influence coefficient, the second influence coefficient, and the third influence coefficient.

4. The method according to claim 3, characterized in that The calculating based on the first target weight, the second target weight, the third target weight, the first influence coefficient, the second influence coefficient, and the third influence coefficient to obtain the target adjustment factor includes: Calculate based on the first target weight, the second target weight, the third target weight, the first influence coefficient, the second influence coefficient, and the third influence coefficient to obtain a reference adjustment factor; Obtaining the gross domestic product of the preset region in the multiple historical time periods; Determining target fine-tuning parameters corresponding to the gross production value; The reference adjustment factor is fine-tuned according to the target fine-tuning parameter to obtain the target adjustment factor.

5. The method according to any one of claims 1 to 4, characterized in that: The method further comprises: If the target adjustment factor is greater than the preset adjustment factor, fitting is performed based on the multiple historical power load values ​​and the multiple historical time periods to obtain a fitting straight line; the horizontal axis of the fitting straight line is time and the vertical axis is the historical power load value; Determining a target slope of the fitted straight line; Determining a target optimization parameter corresponding to the target slope; The second reference power load value is optimized according to the target optimization parameter to obtain the target power load value.

6. The method according to claim 1, characterized in that The determining a first reference power load value based on the average of the plurality of historical power load values ​​comprises: Obtaining the average of the multiple historical power load values ​​to obtain an average power load value; Determining mean square errors corresponding to the plurality of historical power load values; Determining a target optimization coefficient corresponding to the mean square error; The average power load value is optimized according to the target optimization coefficient to obtain the first reference power load value.

7. The method according to claim 6, characterized in that The adjusting the first reference power load value based on the temperature data to obtain a second reference power load value includes: Acquire multiple temperature values ​​in the temperature data; Determining an average temperature value corresponding to the multiple temperature values; If the average temperature value is less than a preset temperature value, determining a first adjustment coefficient corresponding to the average temperature value; Adjust the first reference power load value based on the first adjustment coefficient to obtain the second reference power load value; If the average temperature value is greater than or equal to the preset temperature value, fitting is performed based on the temperature data to obtain a target temperature straight line; Determine the temperature rise slope corresponding to the target temperature straight line; determining a second adjustment coefficient corresponding to the temperature rising slope; The first reference power load value is adjusted based on the second adjustment coefficient to obtain the second reference power load value.

8. A power load forecasting device, characterized in that: The device comprises: an acquisition unit and a processing unit; The acquisition unit is used to acquire multiple economic data groups and multiple historical power load values ​​in a preset region within multiple historical time periods; one historical time period corresponds to one economic data group and one power load value; each economic data group includes equipment manufacturing industry statistics, new energy industry statistics, and agricultural electrification statistics; The processing unit is used to determine a first influence coefficient corresponding to the equipment manufacturing industry statistics, a second influence coefficient corresponding to the new energy industry statistics, and a third influence coefficient corresponding to the agricultural electrification statistics based on the multiple economic data groups and the multiple historical power load values; Determine a target adjustment factor based on the first influence coefficient, the second influence coefficient, and the third influence coefficient; Determining a first reference power load value corresponding to the plurality of historical power load values; The acquisition unit is used to acquire temperature data of a target time period; the target time period is a time period after the current moment; The processing unit is configured to adjust the first reference power load value based on the temperature data to obtain a second reference power load value; The second reference power load value is adjusted based on the target adjustment factor to obtain a target power load value.

9. An electronic device, characterized in that: The method comprises a processor, a memory, a communication interface and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the one or more programs include instructions for executing the steps in the method described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the method according to any one of claims 1 to 7.

Images