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

Abstract

The invention discloses a power demand prediction method and apparatus, an electronic device and a storage medium. The method comprises the steps of obtaining a plurality of power demand data sets of a preset region in a plurality of historical time periods; constructing a linear regression prediction model based on the plurality of power demand data groups and the plurality of historical time periods; inputting the target time period into a linear regression prediction model to obtain a first power demand value corresponding to the target time period; obtaining new energy electric vehicle charging demand data and electric appliance electricity demand data in a first preset time period in a preset area; the ending time of the first preset time period is earlier than the starting time of the target time period; determining a target adjustment coefficient based on the new energy electric vehicle charging demand data and the electric appliance electricity demand data; and adjusting the first power demand value based on the target adjustment coefficient to obtain a target power demand value. By adopting the embodiment of the invention, the accuracy of the predicted value of the power demand is improved.

Description

Technical Field

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

[0002] Electricity consumption forecasting is an important daily task for power system-related departments. Electricity demand forecasting is of great significance to the work of the power sector and related economic and new energy departments.

[0003] With the popularization of new energy electric vehicles and the continuous upgrading of electrical equipment, the changes in electricity demand in these areas have an important impact on the overall electricity demand. However, the current electricity demand forecast does not take into account the impact caused by the popularization of new energy electric vehicles and the continuous upgrading of electrical equipment, resulting in inaccurate electricity demand forecasts. Summary of the invention

[0004] The embodiments of the present application provide a method, device, electronic device and storage medium for predicting electricity demand, which take into account the impact of new energy electric vehicle charging demand data and electrical appliance electricity demand data on future electricity demand, and improve the accuracy of the predicted value of electricity demand.

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

[0006] Acquire multiple power demand data groups in a preset region within multiple historical time periods; each power demand data group includes power demand value, population, industrial output value, regional area, and total fiscal revenue, and each power demand data group corresponds to a historical time period;

[0007] Constructing a linear regression prediction model based on multiple power demand data sets and multiple historical time periods;

[0008] Inputting the target time period into the linear regression prediction model to obtain a first power demand value corresponding to the target time period;

[0009] Acquire new energy electric vehicle charging demand data and electrical appliance power demand data in a preset area within a first preset time period; the end time of the first preset time period is earlier than the start time of the target time period;

[0010] Determine the target adjustment coefficient based on the charging demand data of new energy electric vehicles and the electricity demand data of electrical appliances;

[0011] The first power demand value is adjusted based on the target adjustment coefficient to obtain a target power demand value.

[0012] In a second aspect, an embodiment of the present application provides a power demand prediction device, the device comprising: an acquisition unit and a processing unit;

[0013] An acquisition unit is used to acquire multiple power demand data groups in a preset region within multiple historical time periods; each power demand data group includes power demand value, population, industrial production value, regional area, and total fiscal revenue, and each power demand data group corresponds to a historical time period;

[0014] A processing unit, configured to construct a linear regression prediction model based on a plurality of power demand data groups and a plurality of historical time periods;

[0015] Inputting the target time period into the linear regression prediction model to obtain a first power demand value corresponding to the target time period;

[0016] An acquisition unit, used to acquire new energy electric vehicle charging demand data and electrical appliance power demand data in a preset area within a first preset time period; the end time of the first preset time period is earlier than the start time of the target time period;

[0017] A processing unit, used to determine a target adjustment coefficient based on the charging demand data of the new energy electric vehicle and the power demand data of the electrical appliances;

[0018] The first power demand value is adjusted based on the target adjustment coefficient to obtain a target power demand value.

[0019] 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.

[0020] 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.

[0021] 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.

[0022] The implementation of the present invention has the following beneficial effects:

[0023] It can be seen that the electricity demand forecasting method described in the embodiment of the present invention obtains multiple electricity demand data groups in a preset area within multiple historical time periods, wherein each electricity demand data group includes electricity demand value, population size, gross industrial output value, regional area, and total fiscal revenue, and each electricity demand data group corresponds to a historical time period, and then constructs a linear regression prediction model based on the multiple electricity demand data groups and multiple historical time periods, and then inputs the target time period into the linear regression prediction model to obtain a first electricity demand value corresponding to the target time period, and then obtains the new energy electric vehicle charging demand data and electrical appliance electricity demand data of the preset area within the first preset time period; the end time of the first preset time period is earlier than the start time of the target time period, and then determines the target adjustment coefficient based on the new energy electric vehicle charging demand data and the electrical appliance electricity demand data, and finally adjusts the first electricity demand value based on the target adjustment coefficient to obtain the target electricity demand value. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] 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.

[0025] Figure 1 is a flow chart of a method for predicting power demand provided by an embodiment of the present application;

[0026] Figure 2 is a flow chart for determining a target adjustment coefficient provided by an embodiment of the present application;

[0027] Figure 3 It is a structural schematic diagram of a power demand prediction device provided in an embodiment of the present application;

[0028] Figure 4 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0029] 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.

[0030] 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.

[0031] 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.

[0032] See also Figure 1 , Figure 1 This is a flow chart of a method for predicting power demand provided by an embodiment of the present application, including but not limited to the following steps:

[0033] S101: Acquire multiple power demand data sets in a preset region within multiple historical time periods.

[0034] In this embodiment, each power demand data group includes power demand value, population, industrial output value, regional area, and total fiscal revenue, and each power demand data group corresponds to a historical time period.

[0035] The forecast of electricity demand is of great significance to power system planning, power enterprise operation, and social and economic development. Accurate electricity demand forecast helps determine the type and scale of power sources that need to be built in the future. If it is predicted that electricity demand will continue to grow rapidly, it is necessary to plan and build new power plants in advance, including different types of power sources such as thermal power, hydropower, nuclear power, wind power, and solar power. The electricity demand forecast provides a basis for the expansion and upgrading of the power grid. As the demand for electricity grows, the power grid needs to continuously expand its capacity, increase voltage levels, and optimize the grid structure to ensure the safe and reliable transmission of electricity. Accurate electricity demand forecast can help power companies reasonably arrange the operation of generator sets, improve power generation efficiency, and reduce operating costs. According to the electricity demand forecast for different time periods, power companies can optimize generators. The start and stop plan of the group makes the generator set work within the efficient operation range; in the power market environment, power demand forecast is crucial for power companies to participate in market transactions. Accurate prediction of power demand can help companies formulate reasonable power purchase and sales strategies and improve market competitiveness; electricity is an important new energy source for the development of modern social economy. Stable power supply is crucial for industrial production, commercial activities and residents' lives. Accurate power demand forecast can help the government and relevant departments to prepare power supply guarantee work in advance and ensure stable economic development; power demand forecast is conducive to promoting the optimization and sustainable development of new energy structure. By predicting future power demand, we can reasonably plan the development and utilization of renewable new energy, reduce dependence on traditional fossil new energy, and reduce environmental pollution and greenhouse gas emissions.

[0036] The value of electricity demand has a great relationship with population size, gross industrial output value, regional area, and total fiscal revenue. The increase in population directly leads to an increase in the number of households. As the population grows, the number of households increases accordingly, and the demand for electricity will also rise. Every family needs to use various electrical appliances in daily life, such as lighting, television, refrigerator, washing machine, air conditioner, etc. The frequency and duration of use of these devices are related to the number of family members. The larger the population, the total amount of electrical appliances used will usually increase, resulting in an increase in residents' demand for electricity. As the population increases, the demand for public service facilities will also increase, such as schools, hospitals, shopping malls, supermarkets, transportation hubs, etc. These public service facilities require a lot of electricity to maintain normal operation. Schools need to provide lighting and power supply for classrooms, laboratories, libraries, etc. Hospitals need to provide stable power supply for various medical equipment. Shopping malls and supermarkets need to supply power for lighting, air conditioning, elevators and other equipment. Transportation hubs need to provide power for signal lights, electronic display screens, ventilation equipment, etc. Therefore, the increase in population will lead to an increase in the demand for public service electricity. The increase in gross industrial output value means the expansion of industrial production scale and the increase in production activities. Industrial enterprises need a lot of electricity to drive various equipment and machines in the production process, such as production line equipment, motors, heating equipment, refrigeration equipment, etc. Industrial enterprises in different industries have different demands for electricity, but in general, the increase in gross industrial output value usually leads to an increase in industrial production electricity demand; the size of the area will affect the scale and density of infrastructure construction. Larger areas usually require more infrastructure construction, such as roads, bridges, railways, airports, water conservancy facilities, etc. These infrastructure construction projects require a lot of electricity to drive various mechanical equipment during the construction process, such as cranes, mixers, welding machines, etc. Therefore, the increase in regional area may lead to an increase in infrastructure construction electricity demand, thereby affecting the electricity demand value; the increase in the total value of fiscal revenue can provide the government with more funds for investment in infrastructure construction, improvement of public service facilities and industrial development. These investment projects may directly or indirectly affect the electricity demand value.

[0037] It needs to be explained that it is also necessary to determine whether the power supply data, historical population data, industrial production data, and temperature change data meet the preset conditions. If so, a linear regression prediction model is constructed based on the power supply data, historical population data, industrial production data, and temperature change data. If not, data that is not within the preset range is obtained to obtain abnormal data, and then the abnormal data is deleted to obtain target power supply data, target historical population data, target industrial production data, and target temperature change data. Finally, a linear regression prediction model is constructed based on the target power supply data, target historical population data, target industrial production data, and target temperature change data.

[0038] It can be seen that by obtaining the electricity demand value, population size, gross industrial output value, regional area, and total fiscal revenue of a preset region in multiple historical time periods, multiple electricity demand data groups can be obtained, and each electricity demand data group corresponds to a historical time period. By analyzing the data in multiple historical time periods, the relationship between indicators such as the region's population size, gross industrial output value, regional area, and total fiscal revenue and the electricity demand value can be observed.

[0039] S102: Constructing a linear regression prediction model based on multiple power demand data groups and multiple historical time periods.

[0040] In this embodiment, illustratively, multiple power demand data groups are mapped to a coordinate system to obtain multiple first coordinate points, wherein the horizontal axis of the coordinate system is time and the vertical axis is the power demand value. Specifically, a coordinate system is first constructed, wherein the horizontal axis represents time and the vertical axis represents power demand value. Time can be marked according to historical time periods, and can be in units of years or months, and arranged in sequence starting from a certain time point in the past, which is not limited here. These first coordinate points intuitively show the changes in power demand values ​​in different historical time periods. By observing the distribution of these points, we can preliminarily understand the changing trend of power demand over time.

[0041] Exemplarily, the corresponding fine-tuning parameters are determined according to the population, gross industrial output, regional area, and total fiscal revenue of each power demand data group in the multiple power demand data groups, and multiple fine-tuning parameters are obtained. Specifically, power demand is not only affected by time, but also closely related to multiple factors such as population, gross industrial output, regional area, and total fiscal revenue. These factors may change in different historical time periods, thereby affecting power demand to varying degrees. Each factor can be analyzed separately, and the correlation between it and the power demand value is calculated. Then, the corresponding weight is determined according to the size of the correlation, and then the fine-tuning parameters are obtained. For example, if the correlation between population and power demand value is 0.3, the correlation between gross industrial output and power demand value is 0.5, the correlation between regional area and power demand value is 0.1, and the correlation between total fiscal revenue and power demand value is 0.2, then a comprehensive fine-tuning parameter can be determined according to these correlation values. For example, each correlation value can be multiplied by a coefficient and then added to obtain the fine-tuning parameter.

[0042] Exemplarily, the corresponding coordinate points among the multiple first coordinate points are fine-tuned according to multiple fine-tuning parameters to obtain multiple second coordinate points. Specifically, for each first coordinate point, the fine-tuning parameter corresponding to it is adjusted. For example, if a first coordinate point is (2015, 150) and the corresponding fine-tuning parameter is 10, then the point can be adjusted to (2015, 160). The fine-tuned second coordinate points more accurately reflect the actual situation of power demand after considering the influence of multiple factors. These points can be used to construct a linear regression prediction model, so that the model can better fit the actual data and improve the accuracy of the prediction.

[0043] Exemplarily, a linear regression prediction model is constructed based on multiple second coordinate points. Specifically, a general linear regression equation can be used, and multiple second coordinate points can be substituted into the general linear regression equation. The slope and intercept of the general linear regression equation are calculated, and the linear regression prediction model is determined. The relationship between the power demand value and time can be determined.

[0044] It should be explained that, in this embodiment, not only a linear regression prediction model can be constructed, but also a time series model and a machine learning model can be constructed to determine the relationship between the power demand value and time.

[0045] It can be seen that mapping the electricity demand data group to the coordinate system allows complex data to be presented in an intuitive graphical form. By drawing coordinate points in the coordinate system where the horizontal axis represents time and the vertical axis represents the electricity demand value, the changing trend of electricity demand over time can be clearly seen. Because electricity demand is affected by many factors such as population size, gross industrial output value, regional area, and total fiscal revenue, the fine-tuning parameters determined by comprehensively considering these factors can more comprehensively reflect the actual situation of electricity demand. The linear regression prediction model constructed by the second coordinate point obtained through multi-factor fine-tuning can better fit the actual data.

[0046] S103: Input the target time period into a linear regression prediction model to obtain a first power demand value corresponding to the target time period.

[0047] In this embodiment, the target time period is a certain time interval in the future for which we hope to predict electricity demand, for example, it can be the next year, five years or ten years, etc. The target time period is converted into a form corresponding to the independent variable in the model. Since the horizontal axis of the model is time, the specific time point or interval of the target time period needs to be converted into a numerical value that the model can handle. For example, if the model uses years as the time unit, then if the target time period is three years in the future, it is necessary to determine the current year and add three years to obtain a specific year value, and then input this value into the model. When the target time period is input into the linear regression prediction model, the model will calculate according to the established relationship to determine the electricity demand value predicted under this target time period, and obtain the first electricity demand value.

[0048] S104: Obtaining new energy electric vehicle charging demand data and electrical appliance power demand data in a preset area within a first preset time period.

[0049] In this embodiment, with the popularity of new energy vehicles, especially electric vehicles, the impact of their charging demand on the power demand value has become increasingly prominent. The increase in the number of electric vehicles means that more electricity will be used for vehicle charging. The charging power of different types of electric vehicles is different. The charging power in the fast charging mode is usually higher, which will consume a lot of electricity in a short time. With the continuous advancement of science and technology, various new electrical appliances continue to emerge, such as smart home devices, large-screen high-definition televisions, high-performance computers, etc. The popularity of these new electrical appliances has increased the electricity demand of residents and commercial users. The functions of new electrical appliances are becoming more and more powerful, and they will also consume more electricity. It can be seen that the charging demand data of new energy electric vehicles and the electricity demand data of electrical appliances will have a great impact on the electricity demand, so the charging demand data of new energy electric vehicles and the electricity demand data of electrical appliances in the preset area within the first preset time period are obtained.

[0050] S105: Determine a target adjustment coefficient based on the new energy electric vehicle charging demand data and the electrical appliance power demand data.

[0051] In this implementation, see Figure 2 , Figure 2 A flow chart for determining a target adjustment coefficient provided by an embodiment of the present application includes but is not limited to the following steps:

[0052] S201: Fitting is performed based on the charging demand data of new energy electric vehicles to obtain a new energy electric vehicle charging demand straight line.

[0053] In this embodiment, after obtaining the charging demand data of the new energy electric vehicle, a fitting method is used to fit the charging demand data of the new energy electric vehicle. After the fitting is completed, a new energy electric vehicle charging demand straight line can be obtained. The new energy electric vehicle charging demand straight line obtained by the fitting method can simply and intuitively highlight the overall change direction of the new energy electric vehicle charging demand.

[0054] S202: Determine the slope corresponding to the new energy electric vehicle charging demand straight line to obtain a first slope.

[0055] In this implementation, any two points on the new energy electric vehicle charging demand line are selected to calculate the slope corresponding to the new energy electric vehicle charging demand line to obtain a first slope.

[0056] S203: Fitting is performed based on the electrical appliance power demand data to obtain an electrical appliance power demand straight line.

[0057] In this embodiment, after obtaining the electrical appliance power demand data, a fitting method is used to fit the electrical appliance power demand data. After the fitting is completed, a straight line for the electrical appliance power demand can be obtained. The straight line for the electrical appliance power demand obtained by the fitting method can simply and intuitively highlight the overall change direction of the electrical appliance power demand.

[0058] S204: Determine the slope corresponding to the electrical appliance power demand line to obtain a second slope.

[0059] In this embodiment, any two points on the electrical appliance power demand line are selected to calculate the slope corresponding to the electrical appliance power demand line to obtain the second slope.

[0060] S205: Determine a target adjustment coefficient based on the first slope and the second slope.

[0061] In this embodiment, exemplarily, a first reference weight corresponding to the first slope and a second reference weight corresponding to the second slope are determined. Specifically, a mapping relationship between preset slopes and reference weights may be pre-stored, and the first reference weight corresponding to the first slope and the second reference weight corresponding to the second slope are determined based on the mapping relationship.

[0062] Exemplarily, the number of new energy electric vehicles in a preset area within a first preset time period is obtained. Specifically, the number of new energy electric vehicles refers to the total number of new energy electric vehicles that have been registered and are in use at a specific time point and within a specific range. The growth of the number of new energy electric vehicles will directly drive the demand for public charging piles. A large number of new energy electric vehicles need to be charged in public places such as streets, parking lots, shopping centers, etc., which requires an increase in the number and layout density of public charging piles. The more new energy electric vehicles there are, the greater the amount of charging required for daily driving. Each new energy electric vehicle needs to be charged regularly to maintain normal operation. Whether it is commuting, shopping or leisure, daily activities, charging is indispensable. The more new energy electric vehicles there are, the more new energy electric vehicles will travel long distances, which puts higher requirements on charging facilities and charging capacity along highways and other routes.

[0063] Exemplarily, a first optimization factor corresponding to the number of new energy electric vehicles is determined. Specifically, a mapping relationship between the number of new energy electric vehicles and the optimization factor is pre-stored, and the first optimization factor corresponding to the number of new energy electric vehicles is determined based on the mapping relationship.

[0064] Exemplarily, the first reference weight is optimized according to the first optimization factor to obtain the first target weight. Specifically, the first reference weight can be optimized according to the first optimization factor. The specific calculation formula is as follows:

[0065] The first target weight=the first reference weight×(1+the first optimization factor); the first target weight can be obtained according to the above formula.

[0066] Exemplarily, the number of households in a preset area within a first preset time period is obtained. Specifically, as the number of households increases, the demand for basic living appliances will also increase accordingly. Each family is usually equipped with some necessary appliances, such as refrigerators, televisions, washing machines, etc. Therefore, the more households there are, the greater the total ownership of these basic appliances, which will lead to an increase in the overall demand for electrical appliances in the preset area. The increase in the number of households will also drive the demand for emerging appliances. With the development of science and technology and the improvement of living standards, various smart appliances and high-end home appliances are gradually entering households, such as smart speakers, air purifiers, sweeping robots, etc. The establishment of new families and the replacement of existing families will increase the demand for these emerging appliances, which will lead to an increase in the overall demand for electrical appliances in the preset area.

[0067] Exemplarily, the second optimization factor corresponding to the number of households is determined. Specifically, a mapping relationship between the number of households and the optimization factor may be pre-stored, and the second optimization factor corresponding to the number of households is determined based on the mapping relationship.

[0068] Exemplarily, the second reference weight is optimized according to the second optimization factor to obtain the second target weight. Specifically, the second reference weight can be optimized according to the second optimization factor. The specific calculation formula is as follows:

[0069] The second target weight=the second reference weight×(1+the second optimization factor); the second target weight can be obtained according to the above formula.

[0070] Exemplarily, the target adjustment coefficient is obtained by calculating based on the first slope, the second slope, the first target weight, and the second target weight. First, the reference adjustment coefficient is obtained by calculating based on the first slope, the second slope, the first target weight, and the second target weight. The target adjustment coefficient is calculated specifically according to the following formula:

[0071] F=a×α+b×β

[0072] Among them, F is the reference adjustment coefficient, a is the first slope, b is the second slope, α is the first target weight, and β is the second target weight.

[0073] Exemplarily, if the reference adjustment coefficient is less than or equal to the preset adjustment coefficient, the number of net in-migration population in the preset area during the first preset time period is obtained. Specifically, if the reference adjustment coefficient is less than or equal to the preset adjustment coefficient, it means that the current reference adjustment coefficient needs to be slightly adjusted. In this way, the number of net in-migration population in the preset area during the first preset time period is obtained. As the net in-migration population increases, more families will settle in the area. Each family needs to use various electrical appliances to meet daily life needs, such as lighting, televisions, refrigerators, washing machines, air conditioners, etc. The use of these devices will directly lead to an increase in residents' demand for electricity.

[0074] Exemplarily, the third optimization factor corresponding to the number of net in-migration population is determined. Specifically, a mapping relationship between the number of net in-migration population and the optimization factor may be pre-stored, and the third optimization factor corresponding to the number of net in-migration population is determined based on the mapping relationship.

[0075] Exemplarily, the reference adjustment coefficient is optimized according to the third optimization factor to obtain the target adjustment coefficient. Specifically, the reference adjustment coefficient can be optimized according to the third optimization factor. The specific calculation formula is as follows:

[0076] Target adjustment coefficient=reference adjustment coefficient×(1+third optimization factor); The target adjustment coefficient can be obtained according to the above formula.

[0077] It can be seen that determining the third optimization factor based on the number of net migrants can accurately optimize the specific circumstances of population changes. Different numbers of net migrants may have different degrees of impact on electricity demand. By establishing optimization factors corresponding to the number of net migrants, the reference adjustment coefficient can be adjusted more accurately to better adapt to changes in electricity demand brought about by population changes.

[0078] It should be noted that if the reference adjustment coefficient is greater than the preset adjustment coefficient, the historical adjustment coefficients within multiple historical time periods are obtained to obtain x historical adjustment coefficients, where x is a positive integer, and each historical adjustment coefficient corresponds to an adjustment coefficient detection moment. Specifically, the historical adjustment coefficient is the adjustment coefficient data recorded during similar experiments or monitoring processes within the historical time period.

[0079] Exemplarily, fitting is performed based on x historical adjustment coefficients and corresponding adjustment coefficient detection moments to obtain a fitting straight line, wherein the horizontal axis of the fitting straight line is time and the vertical axis is the adjustment coefficient. Specifically, the x historical adjustment coefficients and the corresponding adjustment coefficient detection moments are used as data points for fitting operation. Fitting can be performed using a linear regression method or a polynomial fitting method. The purpose of fitting is to find a straight line that can better describe the trend of historical adjustment coefficients changing over time. The horizontal axis of the obtained target fitting straight line is time, and the vertical axis is the historical adjustment coefficient.

[0080] Exemplarily, the target slope of the fitting line is obtained. Specifically, by arbitrarily selecting two points on the target fitting line, the slope corresponding to the target fitting line can be calculated to obtain the target slope.

[0081] Exemplarily, the target optimization parameter corresponding to the target slope is determined. Specifically, a mapping relationship between a preset slope and an optimization parameter may be pre-stored, and the target optimization parameter corresponding to the target slope is determined based on the mapping relationship.

[0082] Exemplarily, the reference adjustment coefficient is optimized according to the target optimization parameter to obtain the target adjustment coefficient. Specifically, the reference adjustment coefficient can be optimized according to the target optimization parameter. The specific calculation formula is as follows:

[0083] Target adjustment coefficient = reference adjustment coefficient × (1 + target optimization parameter); The target adjustment coefficient can be obtained according to the above formula.

[0084] It can be seen that the fitting straight line is obtained by fitting according to the historical adjustment coefficients and the corresponding adjustment coefficient detection moments, which makes full use of past experience data. By analyzing the changing trends of historical data, we can better understand whether the current changes in the adjustment coefficients are in line with historical laws and possible future development trends.

[0085] It can be seen that by fitting the new energy electric vehicle charging demand data to obtain the new energy electric vehicle charging demand straight line, and fitting the electrical appliance electricity demand data to obtain the electrical appliance electricity demand straight line, it is possible to intuitively show the changing trends of these two electricity demands over time or other related variables. The slope of the demand straight line reflects the rate of increase or decrease in demand. By determining the slopes for the new energy electric vehicle charging demand and the electrical appliance electricity demand respectively, the rate of change of these two demands in a specific time period can be quantitatively understood, and the first reference weight and the second reference weight are determined for the first slope (new energy electric vehicle charging demand slope) and the second slope (electrical appliance electricity demand slope), respectively. The relative importance of these two demands in the target adjustment coefficient was preliminarily considered. The first reference weight was optimized according to the first optimization factor corresponding to the number of new energy electric vehicles to obtain the first target weight, and the second reference weight was optimized according to the second optimization factor corresponding to the number of households to obtain the second target weight, which further improved the accuracy and adaptability of the weights. The target adjustment coefficient was obtained by calculation based on the first slope, the second slope, and the optimized first target weight and the second target weight. This coefficient comprehensively considers the charging demand of new energy electric vehicles and the electricity demand of electrical appliances as well as related influencing factors, and can more comprehensively reflect the overall changes in regional electricity demand.

[0086] S106: Adjust the first power demand value based on the target adjustment coefficient to obtain a target power demand value.

[0087] In this embodiment, first, the first power demand value is adjusted based on the target adjustment coefficient to obtain the second power demand value. Exemplarily, n temperatures in the temperature change data are determined, where n is an integer greater than 1. Since the demand for electricity is large during the high temperature in summer and the low temperature in winter, an obvious seasonal peak in electricity consumption will be formed. During the peak period of electricity consumption, the demand for electricity will be greater, so the temperature will affect the determination of the power demand value. Exemplarily, the maximum temperature and the minimum temperature among n temperatures are determined, and the temperature difference between the maximum temperature and the minimum temperature is determined to obtain a target temperature difference. Based on the maximum temperature and the minimum temperature, k intervals corresponding to the target temperature difference are determined, wherein k is an integer greater than 1. The n temperatures are placed into k intervals, and the number of temperatures in the k intervals is counted to obtain the number of k temperatures. The weight corresponding to each of the k intervals is obtained to obtain k weights, wherein the sum of the k weights is 1. The closer the interval is to the middle value of the temperature, the smaller the weight is. Temperatures that are too high or too low will have a greater impact on electricity demand. When the temperature is near the middle value, it often represents a relatively stable climate state. Under this stable temperature state, the demand for electricity is usually relatively stable. Exemplarily, the quantity proportion corresponding to each interval range is determined according to the k temperature quantities, and k quantity proportions are obtained. A weighted operation is performed according to the k quantity proportions and the k weights to obtain a target deviation parameter. The second power demand value is adjusted based on the target deviation parameter to obtain a target power demand value. Specifically, the second power demand value can be optimized according to the target deviation parameter. The specific calculation formula is as follows:

[0088] Target power demand value=second power demand value×(1+target deviation parameter); The target power demand value can be obtained according to the above formula.

[0089] It can be seen that by determining multiple temperature intervals, the temperature change data can be divided more finely. Different temperature intervals correspond to different electricity demand characteristics. After determining the maximum temperature, minimum temperature and temperature difference, the interval range is determined according to these values, which can better reflect the actual temperature distribution. The closer the interval range is to the middle temperature value, the smaller the weight is. This is because in the middle temperature range, the electricity demand is usually relatively stable and the change range is small, while the extreme temperature interval far from the middle value often has a greater impact on the electricity demand. Therefore, assigning a larger weight can highlight these key influencing factors. By weighted operation of the temperature quantity proportion and the weight, the target deviation parameter can be obtained. This parameter comprehensively considers the temperature quantity distribution and weight size of different temperature intervals, and can more accurately reflect the degree of influence of temperature deviation from the middle value on electricity demand. As time goes by, the temperature change data is continuously updated. This method can adjust the electricity demand value in real time to adapt to dynamic temperature changes and electricity demand changes. Whether it is seasonal temperature changes or sudden extreme weather conditions, they can be reflected in the electricity demand forecast in a timely manner.

[0090] In summary, the implementation of the present invention has the following beneficial effects:

[0091] It can be seen that the electricity demand forecasting method described in the embodiment of the present invention obtains multiple electricity demand data groups in a preset area within multiple historical time periods, wherein each electricity demand data group includes electricity demand value, population size, gross industrial output value, regional area, and total fiscal revenue, and each electricity demand data group corresponds to a historical time period, and then constructs a linear regression prediction model based on the multiple electricity demand data groups and multiple historical time periods, and then inputs the target time period into the linear regression prediction model to obtain a first electricity demand value corresponding to the target time period, and then obtains the new energy electric vehicle charging demand data and electrical appliance electricity demand data of the preset area within the first preset time period; the end time of the first preset time period is earlier than the start time of the target time period, and then determines the target adjustment coefficient based on the new energy electric vehicle charging demand data and the electrical appliance electricity demand data, and finally adjusts the first electricity demand value based on the target adjustment coefficient to obtain the target electricity demand value.

[0092] See also Figure 3 , Figure 3 It is a structural diagram of a power demand prediction device provided in an embodiment of the present application. The power demand prediction device 300 includes: an acquisition unit 301 and a processing unit 302;

[0093] The acquisition unit 301 is used to acquire multiple power demand data groups in a preset region within multiple historical time periods; each power demand data group includes power demand value, population, industrial production value, regional area, and total fiscal revenue, and each power demand data group corresponds to a historical time period;

[0094] A processing unit 302 is used to construct a linear regression prediction model based on multiple power demand data groups and multiple historical time periods;

[0095] Inputting the target time period into the linear regression prediction model to obtain a first power demand value corresponding to the target time period;

[0096] The acquisition unit 301 is used to acquire the charging demand data of new energy electric vehicles and the electricity demand data of electrical appliances in a preset area within a first preset time period; the end time of the first preset time period is earlier than the start time of the target time period;

[0097] The processing unit 302 is used to determine the target adjustment coefficient based on the new energy electric vehicle charging demand data and the electrical appliance power demand data;

[0098] The first power demand value is adjusted based on the target adjustment coefficient to obtain a target power demand value.

[0099] In some possible implementations, in terms of constructing a linear regression prediction model based on multiple power demand data groups and multiple historical time periods, the processing unit 302 is specifically configured to:

[0100] Mapping the plurality of power demand data sets to a coordinate system to obtain a plurality of first coordinate points; the horizontal axis of the coordinate system is time and the vertical axis is power demand value;

[0101] Determine corresponding fine-tuning parameters according to the population, industrial production value, regional area, and total fiscal revenue of each power demand data group in the plurality of power demand data groups, and obtain a plurality of fine-tuning parameters;

[0102] Fine-tune corresponding coordinate points among the plurality of first coordinate points according to a plurality of fine-tuning parameters to obtain a plurality of second coordinate points;

[0103] A linear regression prediction model is constructed based on multiple second coordinate points.

[0104] In some possible implementations, in determining the target adjustment coefficient corresponding to the new energy electric vehicle charging demand data, the processing unit 302 is specifically configured to:

[0105] According to the charging demand data of new energy electric vehicles, a straight line of charging demand of new energy electric vehicles is obtained;

[0106] Determine the slope corresponding to the new energy electric vehicle charging demand straight line to obtain a first slope;

[0107] Fitting is performed based on the electrical appliance power demand data to obtain an electrical appliance power demand straight line;

[0108] Determine the slope corresponding to the electrical appliance power demand line to obtain a second slope;

[0109] A target adjustment coefficient is determined based on the first slope and the second slope.

[0110] In some possible implementations, in determining the target adjustment coefficient based on the first slope and the second slope, the processing unit 302 is specifically configured to:

[0111] Determine a first reference weight corresponding to the first slope and a second reference weight corresponding to the second slope;

[0112] Obtaining the number of new energy electric vehicles in a preset area within a first preset time period;

[0113] Determine a first optimization factor corresponding to the number of new energy electric vehicles;

[0114] Optimizing the first reference weight according to the first optimization factor to obtain a first target weight;

[0115] Obtain the number of households in a preset area within a first preset time period;

[0116] Determine a second optimization factor corresponding to the number of households;

[0117] Optimizing the second reference weight according to the second optimization factor to obtain a second target weight;

[0118] A target adjustment coefficient is obtained by performing calculation based on the first slope, the second slope, the first target weight, and the second target weight.

[0119] In some possible implementations, in terms of obtaining the target adjustment coefficient by calculation based on the first slope, the second slope, the first target weight, and the second target weight, the processing unit 302 is specifically configured to:

[0120] Calculating based on the first slope, the second slope, the first target weight, and the second target weight to obtain a reference adjustment coefficient;

[0121] If the reference adjustment coefficient is less than or equal to the preset adjustment coefficient, the number of net immigrants in the preset area during the first preset time period is obtained;

[0122] Determine the third optimization factor corresponding to the number of net in-migration population;

[0123] The reference adjustment coefficient is optimized according to the third optimization factor to obtain the target adjustment coefficient.

[0124] In some possible implementations, the processing unit 302 is further specifically configured to:

[0125] If the reference adjustment coefficient is greater than the preset adjustment coefficient, the historical adjustment coefficients in multiple historical time periods are obtained to obtain x historical adjustment coefficients; x is a positive integer, and each historical adjustment coefficient corresponds to an adjustment coefficient detection moment;

[0126] Fitting is performed according to x historical adjustment coefficients and corresponding adjustment coefficient detection times to obtain a fitting straight line; the horizontal axis of the fitting straight line is time and the vertical axis is the adjustment coefficient;

[0127] Get the target slope of the fitted straight line;

[0128] Determine target optimization parameters with target slope;

[0129] The reference adjustment coefficient is optimized according to the target optimization parameter to obtain the target adjustment coefficient.

[0130] In some possible implementations, in adjusting the first power demand value based on the target adjustment coefficient to obtain the target power demand value, the processing unit 302 is specifically configured to:

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

[0132] Determine n temperatures in the temperature change data; n is an integer greater than 1;

[0133] Determine the maximum and minimum temperatures among n temperatures;

[0134] Determine the temperature difference between the maximum temperature and the minimum temperature to obtain a target temperature difference;

[0135] According to the maximum temperature and the minimum temperature, k interval ranges corresponding to the target temperature difference are determined; k is an integer greater than 1;

[0136] Put n temperatures into k intervals;

[0137] Count the number of temperatures in k intervals to obtain k temperatures;

[0138] Obtain the weight corresponding to each of the k intervals to obtain k weights; the sum of the k weights is 1, and the weight of the interval closer to the middle value of the temperature is smaller;

[0139] Determine the quantity proportion corresponding to each interval range according to the k number of temperatures, and obtain k quantity proportions;

[0140] Perform a weighted operation based on the k quantity proportions and k weights to obtain the target deviation parameter;

[0141] The second power requirement value is adjusted based on the target deviation parameter to obtain a target power requirement value.

[0142] See also Figure 4 , Figure 4 Schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. Figure 4 As 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:

[0143] Acquire multiple power demand data groups in a preset region within multiple historical time periods; each power demand data group includes power demand value, population, industrial output value, regional area, and total fiscal revenue, and each power demand data group corresponds to a historical time period;

[0144] Constructing a linear regression prediction model based on multiple power demand data sets and multiple historical time periods;

[0145] Inputting the target time period into the linear regression prediction model to obtain a first power demand value corresponding to the target time period;

[0146] Acquire new energy electric vehicle charging demand data and electrical appliance power demand data in a preset area within a first preset time period; the end time of the first preset time period is earlier than the start time of the target time period;

[0147] Determine the target adjustment coefficient based on the charging demand data of new energy electric vehicles and the electricity demand data of electrical appliances;

[0148] The first power demand value is adjusted based on the target adjustment coefficient to obtain a target power demand value.

[0149] In some possible implementations, in terms of constructing a linear regression prediction model based on multiple power demand data sets and multiple historical time periods, the program includes instructions for performing the following steps:

[0150] Mapping the plurality of power demand data sets to a coordinate system to obtain a plurality of first coordinate points; the horizontal axis of the coordinate system is time and the vertical axis is power demand value;

[0151] Determine corresponding fine-tuning parameters according to the population, industrial production value, regional area, and total fiscal revenue of each power demand data group in the plurality of power demand data groups, and obtain a plurality of fine-tuning parameters;

[0152] Fine-tune corresponding coordinate points among the plurality of first coordinate points according to a plurality of fine-tuning parameters to obtain a plurality of second coordinate points;

[0153] A linear regression prediction model is constructed based on multiple second coordinate points.

[0154] In some possible implementations, in determining the target adjustment coefficient corresponding to the new energy electric vehicle charging demand data, the above program includes instructions for performing the following steps:

[0155] According to the charging demand data of new energy electric vehicles, a straight line of charging demand of new energy electric vehicles is obtained;

[0156] Determine the slope corresponding to the new energy electric vehicle charging demand straight line to obtain a first slope;

[0157] Fitting is performed based on the electrical appliance power demand data to obtain an electrical appliance power demand straight line;

[0158] Determine the slope corresponding to the electrical appliance power demand line to obtain a second slope;

[0159] A target adjustment coefficient is determined based on the first slope and the second slope.

[0160] In some possible implementations, in determining the target adjustment coefficient based on the first slope and the second slope, the program includes instructions for performing the following steps:

[0161] Determine a first reference weight corresponding to the first slope and a second reference weight corresponding to the second slope;

[0162] Obtaining the number of new energy electric vehicles in a preset area within a first preset time period;

[0163] Determine a first optimization factor corresponding to the number of new energy electric vehicles;

[0164] Optimizing the first reference weight according to the first optimization factor to obtain a first target weight;

[0165] Obtain the number of households in a preset area within a first preset time period;

[0166] Determine a second optimization factor corresponding to the number of households;

[0167] Optimizing the second reference weight according to the second optimization factor to obtain a second target weight;

[0168] A target adjustment coefficient is obtained by performing calculation based on the first slope, the second slope, the first target weight, and the second target weight.

[0169] In some possible implementations, in terms of calculating based on the first slope, the second slope, the first target weight, and the second target weight to obtain the target adjustment coefficient, the program includes instructions for performing the following steps:

[0170] Calculating based on the first slope, the second slope, the first target weight, and the second target weight to obtain a reference adjustment coefficient;

[0171] If the reference adjustment coefficient is less than or equal to the preset adjustment coefficient, the number of net immigrants in the preset area during the first preset time period is obtained;

[0172] Determine the third optimization factor corresponding to the number of net in-migration population;

[0173] The reference adjustment coefficient is optimized according to the third optimization factor to obtain the target adjustment coefficient.

[0174] In some possible implementations, the above program includes instructions for performing the following steps:

[0175] If the reference adjustment coefficient is greater than the preset adjustment coefficient, the historical adjustment coefficients in multiple historical time periods are obtained to obtain x historical adjustment coefficients; x is a positive integer, and each historical adjustment coefficient corresponds to an adjustment coefficient detection moment;

[0176] Fitting is performed according to x historical adjustment coefficients and corresponding adjustment coefficient detection times to obtain a fitting straight line; the horizontal axis of the fitting straight line is time and the vertical axis is the adjustment coefficient;

[0177] Get the target slope of the fitted straight line;

[0178] Determine target optimization parameters with target slope;

[0179] The reference adjustment coefficient is optimized according to the target optimization parameter to obtain the target adjustment coefficient.

[0180] In some possible implementations, in terms of adjusting the first power demand value based on the target adjustment coefficient to obtain the target power demand value, the program includes instructions for performing the following steps:

[0181] Adjust the first power demand value based on the target adjustment coefficient to obtain a second power demand value;

[0182] Determine n temperatures in the temperature change data; n is an integer greater than 1;

[0183] Determine the maximum and minimum temperatures among n temperatures;

[0184] Determine the temperature difference between the maximum temperature and the minimum temperature to obtain a target temperature difference;

[0185] According to the maximum temperature and the minimum temperature, k interval ranges corresponding to the target temperature difference are determined; k is an integer greater than 1;

[0186] Put n temperatures into k intervals;

[0187] Count the number of temperatures in k intervals to obtain k temperatures;

[0188] Obtain the weight corresponding to each of the k intervals to obtain k weights; the sum of the k weights is 1, and the weight of the interval closer to the middle value of the temperature is smaller;

[0189] Determine the quantity proportion corresponding to each interval range according to the k number of temperatures, and obtain k quantity proportions;

[0190] Perform a weighted operation based on the k quantity proportions and k weights to obtain the target deviation parameter;

[0191] The second power requirement value is adjusted based on the target deviation parameter to obtain a target power requirement value.

[0192] 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.

[0193] 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 demand forecasting methods described in the above method embodiments.

[0194] The 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 electricity demand forecasting methods recorded in the above method embodiments.

[0195] 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.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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 demand, characterized in that: include: Acquire multiple power demand data groups in a preset region within multiple historical time periods; each power demand data group includes power demand value, population, industrial output value, regional area, and total fiscal revenue, and each power demand data group corresponds to a historical time period; constructing a linear regression prediction model based on the multiple power demand data groups and the multiple historical time periods; Inputting the target time period into the linear regression prediction model to obtain a first power demand value corresponding to the target time period; Acquiring new energy electric vehicle charging demand data and electrical appliance power demand data in the preset area within a first preset time period; the end time of the first preset time period is earlier than the start time of the target time period; Determining a target adjustment coefficient based on the new energy electric vehicle charging demand data and the electrical appliance power demand data; The first power demand value is adjusted based on the target adjustment coefficient to obtain a target power demand value.

2. The method according to claim 1, characterized in that The constructing a linear regression prediction model based on the multiple power demand data groups and the multiple historical time periods includes: Mapping the plurality of power demand data groups to a coordinate system to obtain a plurality of first coordinate points; the horizontal axis of the coordinate system is time and the vertical axis is power demand value; Determine a corresponding fine-tuning parameter according to the population, gross industrial output value, regional area, and total fiscal revenue value of each power demand data group in the plurality of power demand data groups, and obtain a plurality of fine-tuning parameters; Fine-tune corresponding coordinate points among the plurality of first coordinate points according to the plurality of fine-tuning parameters to obtain a plurality of second coordinate points; The linear regression prediction model is constructed according to the multiple second coordinate points.

3. The method according to claim 1 or 2, characterized in that The determining of the target adjustment coefficient corresponding to the new energy electric vehicle charging demand data includes: Performing a fitting based on the new energy electric vehicle charging demand data to obtain a new energy electric vehicle charging demand straight line; Determine the slope corresponding to the new energy electric vehicle charging demand straight line to obtain a first slope; Fitting is performed according to the electrical appliance power demand data to obtain an electrical appliance power demand straight line; Determine the slope corresponding to the electrical appliance power demand straight line to obtain a second slope; The target adjustment coefficient is determined based on the first slope and the second slope.

4. The method according to claim 3, characterized in that The determining the target adjustment coefficient based on the first slope and the second slope includes: Determine a first reference weight corresponding to the first slope and a second reference weight corresponding to the second slope; Obtaining the number of new energy electric vehicles in the preset area within the first preset time period; Determining a first optimization factor corresponding to the number of new energy electric vehicles; Optimize the first reference weight according to the first optimization factor to obtain a first target weight; Obtaining the number of households in the preset area within the first preset time period; Determining a second optimization factor corresponding to the number of households; Optimize the second reference weight according to the second optimization factor to obtain a second target weight; The target adjustment coefficient is obtained by performing calculation based on the first slope, the second slope, the first target weight, and the second target weight.

5. The method according to claim 4, characterized in that The calculating based on the first slope, the second slope, the first target weight, and the second target weight to obtain the target adjustment coefficient includes: Calculating based on the first slope, the second slope, the first target weight, and the second target weight to obtain a reference adjustment coefficient; If the reference adjustment coefficient is less than or equal to the preset adjustment coefficient, the number of net in-migration population in the preset area during the first preset time period is obtained; Determine a third optimization factor corresponding to the number of net in-migration population; The reference adjustment coefficient is optimized according to the third optimization factor to obtain the target adjustment coefficient.

6. The method according to claim 5, characterized in that The method further comprises: If the reference adjustment coefficient is greater than the preset adjustment coefficient, the historical adjustment coefficients in the multiple historical time periods are obtained to obtain x historical adjustment coefficients; x is a positive integer, and each historical adjustment coefficient corresponds to an adjustment coefficient detection moment; Perform fitting according to the x historical adjustment coefficients and the corresponding adjustment coefficient detection times to obtain a fitting straight line; the horizontal axis of the fitting straight line is time and the vertical axis is the adjustment coefficient; Obtaining a target slope of the fitted straight line; determining a target optimization parameter with the target slope; The reference adjustment coefficient is optimized according to the target optimization parameter to obtain the target adjustment coefficient.

7. The method according to claim 1, characterized in that The adjusting the first power demand value based on the target adjustment coefficient to obtain a target power demand value includes: Adjust the first power demand value based on the target adjustment coefficient to obtain a second power demand value; Determine n temperatures in the temperature change data; n is an integer greater than 1; Determine the maximum temperature and the minimum temperature among the n temperatures; Determine a temperature difference between the maximum temperature and the minimum temperature to obtain a target temperature difference; According to the maximum temperature and the minimum temperature, k interval ranges corresponding to the target temperature difference are determined; k is an integer greater than 1; The n temperatures fall into the k intervals; Counting the number of temperatures in the k intervals to obtain k numbers of temperatures; Obtaining a weight corresponding to each of the k intervals to obtain k weights; the sum of the k weights is 1, and the weight of the interval closer to the middle value of the temperature is smaller; Determine the quantity proportion corresponding to each interval range according to the k temperature quantities, and obtain k quantity proportions; Performing a weighted operation according to the k quantity proportions and the k weights to obtain a target deviation parameter; The second power requirement value is adjusted based on the target deviation parameter to obtain the target power requirement value.

8. A power demand forecasting device, characterized in that: The device comprises: an acquisition unit and a processing unit; The acquisition unit is used to acquire multiple power demand data groups in a preset region within multiple historical time periods; each power demand data group includes power demand value, population, industrial production value, regional area, and total fiscal revenue, and each power demand data group corresponds to a historical time period; The processing unit is used to construct a linear regression prediction model based on the multiple power demand data groups and the multiple historical time periods; Inputting the target time period into the linear regression prediction model to obtain a first power demand value corresponding to the target time period; The acquisition unit is used to acquire the charging demand data of new energy electric vehicles and the electricity demand data of electrical appliances in the preset area within a first preset time period; the end time of the first preset time period is earlier than the start time of the target time period; The processing unit is used to determine the target adjustment coefficient based on the charging demand data of the new energy electric vehicle and the power demand data of the electrical appliance; The first power demand value is adjusted based on the target adjustment coefficient to obtain a target power demand 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