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

Abstract

The invention provides a power load gap prediction method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining future meteorological data and a future weather type corresponding to a to-be-predicted date, and obtaining meteorological data and power data in a preset historical time period containing the future weather type; based on the future meteorological data, the meteorological data and the power data, determining a total consumed power load and an adjusted power load corresponding to the to-be-predicted date; based on the meteorological data and the power data, determining a power load increment provided by the outside and corresponding to the to-be-predicted date; and determining the power load gap corresponding to the to-be-predicted date based on the total consumed power load, the adjusted power load and the power load increment provided by the outside, thereby solving the technical problem of inaccurate prediction of the power load gap in the prior art, and achieving the purpose of accurately regulating and controlling the power load through accurately predicting the power load gap.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method, device, electronic device and storage medium for predicting power load gap. Background Art

[0002] Forecasting electricity supply and demand gaps can address the volatility of renewable energy and sudden load changes caused by extreme weather. Predicting supply and demand gaps and triggering demand response can reduce the need for backup capacity and promote the uptake of renewable energy. Against this backdrop, relevant technologies are evolving from traditional forecasting techniques to those based on artificial intelligence (AI), but they still face challenges such as insufficient integration of physical mechanisms with data-driven approaches and difficulty quantifying complex meteorological factors.

[0003] Both traditional and AI-based forecasting technologies have flaws. Traditional forecasting techniques analyze the time series characteristics of historical data. While computationally simple, they lack adaptability to complex influencing factors, leading to inaccurate predictions of the electricity supply and demand gap. AI-based forecasting techniques, such as model-based forecasting, rely on training data. Training data for extreme weather events is relatively scarce, resulting in poor forecasting capabilities for these conditions. Consequently, model outputs are not always accurate. Summary of the Invention

[0004] In view of this, the purpose of this application is to propose a method, device, electronic device and storage medium for predicting power load gap to overcome all or part of the deficiencies in the prior art.

[0005] Based on the above-mentioned purpose, the present application provides a method for predicting the power load gap, including: obtaining future meteorological data and future weather types corresponding to the date to be predicted, and obtaining meteorological data and power data within a predetermined historical time period containing the future weather type; based on the future meteorological data, the meteorological data and the power data, respectively determining the total consumed power load and the adjusted power load corresponding to the date to be predicted; based on the meteorological data and the power data, determining the externally provided power load increment corresponding to the date to be predicted; based on the total consumed power load, the adjusted power load and the externally provided power load increment, determining the power load gap corresponding to the date to be predicted.

[0006] Optionally, the future meteorological data includes a plurality of first temperature values, the meteorological data includes a plurality of second temperature values, and the power data includes a plurality of load values; based on the future meteorological data, the meteorological data and the power data, determining the total consumed power load corresponding to the predicted date, including: performing calculations based on the plurality of second temperature values ​​and the plurality of load values ​​to obtain a temperature sensitivity coefficient; calculating a first temperature average value of the plurality of first temperature values, and calculating a second temperature average value of the plurality of second temperature values, and determining the difference between the first temperature average value and the second temperature average value as a temperature change; determining the product of the temperature sensitivity coefficient and the temperature change as a power load increment; and calculating the power load increment. The sum of the load increment and the predetermined basic power load is determined as the consumed power load; among the multiple weather types corresponding to the multiple load values, the weather type that occurs most frequently is determined as the standard weather type; among the multiple load values, the load value corresponding to the future weather type is screened as the first load value, and the first load average value corresponding to the first load value is calculated, and the load value corresponding to the standard weather type is screened as the second load value, and the second load average value corresponding to the second load value is calculated; the ratio of the first load average value to the second load average value is calculated, and the ratio is used as the weather type coefficient; the product value of the weather type coefficient and the consumed power load is determined as the total consumed power load.

[0007] Optionally, the externally provided power load increment includes the power load increment provided by wind and the power load increment provided by sunlight, the meteorological data also includes multiple wind speeds and multiple light intensities, and the power data also includes multiple wind power generation powers and multiple photovoltaic power generation powers; determining the externally provided power load increment corresponding to the predicted date based on the meteorological data and the power data includes: determining the power load increment provided by wind based on the multiple wind speeds and the multiple wind power generation powers; determining the power load increment provided by sunlight based on the multiple light intensities and the multiple photovoltaic power generation powers; and determining the sum of the power load increment provided by wind and the power load increment provided by sunlight as the externally provided power load increment.

[0008] Optionally, determining the electric load increment provided by the wind force based on the multiple wind speeds and the multiple wind power generation powers includes: calculating based on the multiple wind speeds to obtain a wind intensity index; calculating based on the multiple wind power generation powers to obtain a wind power output fluctuation rate; inputting the wind intensity index and the wind power output fluctuation rate into a pre-trained prediction model, and outputting a wind power resource fluctuation coefficient through the prediction model; and determining the product value of the wind intensity index and the wind power resource fluctuation coefficient as the electric load increment provided by the wind force.

[0009] Optionally, determining the electric load increment provided by the illumination based on the multiple illumination intensities and the multiple photovoltaic power generation powers includes: calculating based on the multiple illumination intensities to obtain illumination intensity fluctuation rates; calculating based on the multiple photovoltaic power generation powers to obtain photovoltaic power fluctuation rates; calculating based on the illumination intensity fluctuation rates and the photovoltaic power fluctuation rates to obtain an illumination resource fluctuation coefficient; and determining the product value of the illumination intensity fluctuation rate and the illumination resource fluctuation coefficient as the electric load increment provided by the illumination.

[0010] Optionally, the future meteorological data includes multiple first temperature values, and the meteorological data also includes multiple third temperature values; based on the future meteorological data, the meteorological data and the power data, the adjusted power load corresponding to the predicted date is determined, including: determining a temperature deviation value based on the multiple first temperature values ​​and the multiple third temperature values; determining a temperature fluctuation rate based on the multiple third temperature values; performing a weighted sum calculation on the temperature deviation value, the temperature fluctuation rate, the wind intensity index and the weather type coefficient to obtain the adjusted power load.

[0011] Optionally, the power load gap corresponding to the predicted date is determined based on the total consumed power load, the adjusted power load and the externally provided power load increment, including: calculating a first sum of the total consumed power load and the adjusted power load, calculating a second sum of the externally provided power load increment and the predetermined power load, and determining the difference between the first sum and the second sum as the power load gap.

[0012] Based on the same inventive concept, the present application also provides a device for predicting power load gaps, including: an acquisition module, configured to acquire future meteorological data and future weather types corresponding to the date to be predicted, and to acquire meteorological data and power data within a predetermined historical time period containing the future weather types; a first determination module, configured to determine the total consumed power load and the adjusted power load corresponding to the date to be predicted based on the future meteorological data, the meteorological data and the power data, respectively; a second determination module, configured to determine the externally provided power load increment corresponding to the date to be predicted based on the meteorological data and the power data; and a third determination module, configured to determine the power load gap corresponding to the date to be predicted based on the total consumed power load, the adjusted power load and the externally provided power load increment.

[0013] Based on the same inventive concept, the present application also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable by the processor, wherein the processor implements the method described above when executing the computer program.

[0014] Based on the same inventive concept, the present application also provides a non-transitory computer-readable storage medium, which stores computer instructions, and the computer instructions are used to enable a computer to execute the method as described above.

[0015] As can be seen from the above description, the present application provides a method, apparatus, electronic device, and storage medium for predicting a power load shortfall. The method includes obtaining future meteorological data and future weather types corresponding to a date to be predicted, and obtaining meteorological data and power data within a predetermined historical time period that includes the future weather types. Based on the future meteorological data, the meteorological data, and the power data, the total power load consumption and the adjusted power load corresponding to the date to be predicted are determined. The determination of the total power load consumption has a data basis, ensuring accuracy. By adjusting the power load, the total power load consumption can be adjusted, improving the model's adaptability to complex weather conditions and making the total power load consumption determined based on future meteorological data more accurate. Based on the meteorological data and the power data, an externally provided power load increment corresponding to the date to be predicted is determined, and the externally provided power load increment for the date to be predicted is quantified, thereby accurately determining the externally provided power load increment for the date to be predicted. Based on the total power load consumption, the adjusted power load, and the externally provided power load increment, the power load shortfall corresponding to the date to be predicted is determined. The determination of the power load shortfall has a data basis, ensuring accuracy in determining the power load shortfall. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in this application or related technologies, the following briefly introduces the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are merely embodiments of this application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0017] Figure 1 A schematic flow chart of a method for predicting a power load gap according to an embodiment of the present application;

[0018] Figure 2 A schematic diagram of a process for determining the total power consumption load according to an embodiment of the present application;

[0019] Figure 3 A schematic diagram of a process for determining an increase in power load provided by wind power according to an embodiment of the present application;

[0020] Figure 4 A schematic diagram of a process for determining an increment of power load provided by illumination according to an embodiment of the present application;

[0021] Figure 5 A schematic diagram of the structure of a device for predicting power load shortfall according to an embodiment of the present application;

[0022] Figure 6 This is a schematic diagram of the hardware structure of the electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0023] In order to make the objectives, technical solutions and advantages of this application more clear, this application is further described in detail below in combination with specific embodiments and with reference to the accompanying drawings.

[0024] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present application should have the usual meanings understood by people with ordinary skills in the field to which this application belongs. The "first", "second" and similar words used in the embodiments of the present application do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0025] As described in the background section, forecasting the electricity supply-demand gap can address the volatility of renewable energy and sudden load changes caused by extreme weather. Predicting supply-demand gaps in advance and triggering demand response can reduce the need for backup capacity and promote the uptake of renewable energy. Forecast results can also provide decision-making support for market participants and optimize trading strategies. Electricity supply-demand gap forecasting is a critical component of power system operation and dispatch, and its accuracy directly impacts the safety and reliability of the power grid. Relevant forecasting technologies have evolved from traditional statistical models to artificial intelligence and big data analytics, but they still face challenges such as insufficient integration of physical mechanisms with data-driven approaches and difficulty quantifying complex meteorological factors. Traditional forecasting technologies primarily rely on historical load data and simple meteorological correlations, failing to fully leverage massive amounts of data to improve accuracy. Electricity supply and demand are influenced by multiple factors, including temperature, wind speed, weather type, customer churn, and policy adjustments. These technologies often focus on a single or limited number of factors and fail to fully consider the physical impact of meteorological factors (such as temperature, wind speed, and weather type) on electricity supply and demand, resulting in significant forecast bias. Furthermore, due to their over-reliance on historical data, they are unable to adapt to dynamic scenarios such as frequent changes in proxy users and significant climate impacts on distributed generation. With the increasing proportion of new energy and the frequent occurrence of extreme climate events, existing forecasting technologies face major challenges. Forecasting technologies also include machine learning models such as LSTM (Long Short-Term Memory) and XGBoost (eXtreme GradientBoosting, efficient gradient boosting algorithm), which rely on large amounts of high-quality data, have poor generalization capabilities under rare meteorological conditions, and may generate physically unfeasible forecasts. In addition, forecasting technologies also include deep learning models, such as neural networks and Transformers. Their black box characteristics make the results difficult to interpret, and power dispatchers have low trust in them, making them difficult to run in real time. Moreover, the power market environment changes frequently, and existing models are difficult to adjust quickly to adapt to new data and new scenarios, making it difficult to meet real-time requirements.

[0026] Specifically, existing prediction technologies have the following defects:

[0027] (1) Traditional statistical methods: including exponential smoothing and ARIMA models (AutoRegressive IntegratedMoving Average Model, a statistical model used for time series analysis and forecasting), etc., make forecasts by analyzing the time series characteristics of historical data. The calculation is simple but the adaptability to complex influencing factors is insufficient, which leads to inaccurate predictions of the electricity supply and demand gap.

[0028] (2) Machine learning methods: such as artificial neural networks and support vector machines, learn the mapping relationship between supply and demand gaps and influencing factors by training large amounts of data. However, they do not deeply integrate the physical relationship between meteorological factors and power supply and demand, and their ability to predict supply and demand fluctuations under extreme weather conditions is limited. Moreover, they rely on training data, and there is relatively little training data corresponding to extreme weather conditions. The model's ability to predict extreme weather conditions is poor, making the prediction results output by the model not always accurate.

[0029] (3) Deep learning models: These include neural networks and Transformers. Their black-box nature makes the results difficult to interpret, resulting in low confidence among power dispatchers and difficulty in real-time operation. They also rely on training data, making the model's output predictions not always accurate.

[0030] In addition to the aforementioned forecasting techniques, other forecasting technologies include purely data-driven statistical learning methods. These methods rely entirely on historical data, mining patterns and regularities within the data for predictions without incorporating physical mechanisms. These methods have limited ability to account for external factors, and data quality and quantity significantly impact forecast results, potentially leading to overfitting. Purely data-driven models lack inherent correlation analysis of physical factors such as meteorology and supply and demand, making it difficult to justify forecast results. Forecasting technologies also include time series forecasting models. These methods utilize historical load, renewable energy output, and meteorological data to directly predict future supply and demand gaps using models such as ARIMA and LSTM. However, these methods are less adaptable to extreme weather conditions and offer limited interpretability, resulting in inconsistently accurate forecasts.

[0031] In view of this, the present application embodiment proposes a method for predicting power load gap, referring to Figure 1 , including the following steps:

[0032] Step 101 : Acquire future meteorological data and future weather types corresponding to a date to be predicted, and acquire meteorological data and power data within a predetermined historical time period including the future weather types.

[0033] In this step, abnormal changes in meteorological factors can affect changes in power load demand. Therefore, the power load supply and demand gap can be predicted in advance based on meteorological factors, so that the power load can be dispatched reasonably. This application is applicable to the accurate prediction and dynamic regulation of power supply and demand gaps by market entities such as power grid companies; analysis of the impact of new energy output fluctuations on the power grid and formulation of plans; virtual power plants optimize the call strategy of adjustable loads through predictive models; power grid companies provide early warning of load surges in weather conditions such as high temperatures and cold waves.

[0034] Obtain future weather data and weather types for the predicted date. The future weather type is determined in advance based on the future weather data. Based on user experience, weather types can be categorized into sunny, cloudy, rainy, windy, and snowy. To achieve more accurate weather types, further categorization can be performed. For example, rainy days can be categorized into light rain, moderate rain, heavy rain, and extreme rain; and windy days can be categorized into light wind, moderate wind, strong wind, and extreme wind. Weather types and weather data have a predetermined correspondence. Given the weather data, the weather type can be matched based on the predetermined correspondence. Therefore, given the future weather data, the future weather type can be pre-determined based on the future weather data and subsequently obtained. It should be noted that weather types include extreme weather types. Weather types with a historical occurrence frequency less than a predetermined number of times are categorized as extreme weather types. For example, if the occurrence frequency of force 13 wind in the weather data is less than a predetermined number of times, the weather type is classified as extreme wind. To ensure reliable prediction of the power load shortfall for the predicted date, meteorological and power data for a predetermined historical time period containing future weather types are obtained. The weather type of the predicted date is consistent with that of the predetermined historical time period, and the meteorological data are close, so the power load gap of the predicted date is accurately inferred based on the power data of the predetermined historical time period.

[0035] Step 102 : Based on the future meteorological data, the meteorological data and the power data, respectively determine the total consumed power load and the adjusted power load corresponding to the date to be predicted.

[0036] In this step, since the predicted date and the predetermined historical time period have the same weather type, the electricity consumption for the predicted date and the predetermined historical time period is similar. Based on the relationship between the meteorological data and electricity data in the predetermined historical time period, the relationship between the meteorological data and electricity data for the predicted date can be inferred, thereby determining the total power load consumption corresponding to the predicted date. The determination of the total power load consumption has a data basis, making the determination of the total power load consumption accurate. Since future meteorological data and meteorological data are not exactly the same, it is also necessary to determine the adjusted power load based on future meteorological data, meteorological data, and electricity data. By adjusting the power load, the total power load consumption can be adjusted, improving the model's adaptability to complex weather conditions and making the total power load consumption determined based on future meteorological data more accurate.

[0037] Step 103: Determine the externally provided power load increment corresponding to the predicted date based on the meteorological data and the power data.

[0038] In this step, there are various ways to provide electricity, and the externally provided power load increment refers to providing the power load increment in a way related to meteorological factors, such as wind power generation and photovoltaic power generation. In the case that the future weather type is an extreme weather type, although the externally provided power load can increase, the user's demand for electricity also increases. Based on the meteorological data and power data, the externally provided power load increment corresponding to the date to be predicted is determined, wherein the power load increment is used to characterize the amount of change in power load. Since the date to be predicted and the predetermined historical time period have the same weather type, the meteorological data corresponding to the two time periods are similar, and thus the externally provided power load increments of the two time periods are similar. Therefore, based on the meteorological data and power data of the predetermined historical time period, the externally provided power load increment of the date to be predicted can be quantified, so as to achieve the purpose of accurately determining the externally provided power load increment corresponding to the date to be predicted.

[0039] Step 104 : determining the power load gap corresponding to the to-be-predicted date based on the total consumed power load, the adjusted power load, and the power load increment provided by the outside world.

[0040] In this step, only after the power load gap is determined can the power supply situation for the predicted date be subsequently determined. The power load gap refers to the difference between the total consumed power load and the provided power load. The total consumed power load reflects the power load required for the predicted date. This power load is provided by externally provided power load increments, which are weather-dependent. Therefore, the power load gap is determined by subtracting the externally provided power load increments from the total consumed power load. Furthermore, because the impact of meteorological data on electricity is complex, an adjustment is required to accurately determine the power load gap. The predicted date and the predetermined historical time period share the same meteorological type, and the power consumption for the predicted date and the predetermined historical time period is similar. Based on future meteorological data corresponding to the predicted date, as well as meteorological and power data from the predetermined historical time period, the total consumed power load is determined, the adjusted power load, and the externally provided power load increment are adjusted. Finally, based on the total consumed power load, the adjusted power load, and the externally provided power load increment, the power load gap corresponding to the predicted date is determined. There is a data basis for determining the power load gap, so as to achieve the purpose of accurately determining the power load gap.

[0041] Through the above scheme, future meteorological data and future weather types corresponding to the date to be predicted are obtained, as well as meteorological data and power data within a predetermined historical time period that includes the future weather types. Based on the future meteorological data, the meteorological data, and the power data, the total power load consumption and the adjusted power load corresponding to the date to be predicted are determined. The determination of the total power load consumption has a data basis, ensuring accuracy. By adjusting the power load, the total power load consumption can be adjusted, improving the model's adaptability to complex weather conditions and making the total power load consumption determined based on future meteorological data more accurate. Based on the meteorological data and the power data, the externally provided power load increment corresponding to the date to be predicted is determined, and the externally provided power load increment for the date to be predicted is quantified, achieving accurate determination of the externally provided power load increment for the date to be predicted. Based on the total power load consumption, the adjusted power load, and the externally provided power load increment, the power load gap corresponding to the date to be predicted is determined. The power load gap determination has a data basis, ensuring accurate determination of the power load gap.

[0042] In some embodiments, the future meteorological data includes a plurality of first temperature values, the meteorological data includes a plurality of second temperature values, and the power data includes a plurality of load values; based on the future meteorological data, the meteorological data and the power data, determining the total consumed power load corresponding to the predicted date, including: performing calculations based on the plurality of second temperature values ​​and the plurality of load values ​​to obtain a temperature sensitivity coefficient; calculating a first temperature average value of the plurality of first temperature values, and calculating a second temperature average value of the plurality of second temperature values, and determining the difference between the first temperature average value and the second temperature average value as a temperature change; determining the product value of the temperature sensitivity coefficient and the temperature change as a power load increment; and The sum of the power load increment and the predetermined basic power load is determined as the consumed power load; among the multiple weather types corresponding to the multiple load values, the weather type with the highest frequency of occurrence is determined as the standard weather type; among the multiple load values, the load value corresponding to the future weather type is screened as the first load value, and the first load average value corresponding to the first load value is calculated, and the load value corresponding to the standard weather type is screened as the second load value, and the second load average value corresponding to the second load value is calculated; the ratio of the first load average value to the second load average value is calculated, and the ratio is used as the weather type coefficient; the product value of the weather type coefficient and the consumed power load is determined as the total consumed power load.

[0043] In this embodiment, since temperature changes can cause significant changes in power load consumption, it is necessary to calculate a temperature sensitivity coefficient based on multiple second temperature values ​​and multiple load values, where the temperature sensitivity coefficient is used to quantify the degree of impact of temperature changes on power load. The temperature sensitivity coefficient is determined by the following formula:

[0044]

[0045] Among them, L i is the load value of the ith hour, α1 is the formula parameter, β1 is the temperature sensitivity coefficient, T i is the second temperature value of the i-th hour, n is the total hours, L i =α1+β1×T i +ε, ε is the predetermined adjustment value.

[0046] Since the predetermined historical time period includes multiple hours, in order to make the parameters for determining the temperature sensitivity coefficient representative, the second temperature value is divided into intervals, namely, a high temperature zone (T ≥ 30°C), a normal temperature zone (10°C ≤ T < 30°C), and a low temperature zone (T < 10°C). The average temperature value and average load value of each interval are used to calculate formula (1).

[0047] The derivation process of formula (1) is as follows:

[0048] For a set of data points (T i , L i ), i = 1, 2, ..., n, the goal of the least squares method is to minimize the sum of squared errors:

[0049]

[0050] By taking partial derivatives of S with respect to α1 and β1 and setting them to 0, we can obtain the equations for solving α1 and β1, and obtain formula (1):

[0051]

[0052] Although the weather type of the predicted date is the same as that of the predetermined historical time period, the temperature may be different. It is also necessary to determine the temperature change between the predicted date and the predetermined historical time period. Therefore, the first temperature average of multiple first temperature values ​​is calculated, and the second temperature average of multiple second temperature values ​​is calculated, and the difference between the first temperature average and the second temperature average is determined as the temperature change.

[0053] The temperature change is determined by the following formula:

[0054] ΔT = first temperature average value - second temperature average value Formula (3),

[0055] Where ΔT is the temperature change.

[0056] The temperature sensitivity coefficient represents the impact of a unit temperature change on the power load. Therefore, by multiplying the temperature sensitivity coefficient by the temperature change, the impact of the temperature change on the power load, that is, the power load increment, can be determined.

[0057] The power load increment is determined by the following formula:

[0058] ΔQ=β1*ΔT Formula (4),

[0059] Among them, ΔQ is the power load increment and β1 is the temperature sensitivity coefficient.

[0060] In addition to the power load changes caused by temperature fluctuations, there is also a base power load consumption value, namely a predetermined base power load. The predetermined base power load can be determined based on historical experience. The sum of the power load increment and the predetermined base power load is the consumed power load.

[0061] The consumed power load is determined by the following formula:

[0062] Q T =Q0+ΔQ Formula (5),

[0063] Among them, Q T It is the power consumption load, and Q0 is the predetermined basic power load.

[0064] Because different weather types have different impacts on the supply and demand of power load, a weather type coefficient is also calculated. This coefficient quantifies the degree of impact of weather types on power load, thereby regulating power consumption. To improve screening efficiency, after obtaining load values, they are categorized by weather type to form sample sets for different weather types. For example, all data for sunny days can be grouped into one category, and all data for rainy days into another. From multiple load values, the load values ​​corresponding to the future weather type are selected as first load values, and a first load average corresponding to the first load value is calculated to determine the load value for the future weather type. Among the multiple weather types corresponding to the multiple load values, the most frequently occurring weather type is identified as the standard weather type. This is because its frequency indicates its fundamental nature, and therefore it is designated as the standard weather type. The load values ​​corresponding to the standard weather type are selected as second load values, and a second load average corresponding to the second load value is calculated. The ratio of the first load average to the second load average is calculated and used as the weather type coefficient to quantify the degree of impact of the future weather type on power load compared to the standard weather type. The load is adjusted through the weather type coefficient to accurately capture the inherent causal relationship between meteorological factors and power load.

[0065] The weather type coefficient is determined by the following formula:

[0066]

[0067] Among them, C L-type is the weather type coefficient, is the first load average value, is the second load average value.

[0068] The power consumption load is adjusted using the weather type coefficient, and the weather type coefficient and the power consumption load are multiplied to obtain the total power consumption load.

[0069] The total consumed electrical load is determined by the following formula:

[0070] Q = Q T *C L-type Formula (7),

[0071] Wherein, Q is the total power consumption load.

[0072] Taking into account the impact of meteorological factors on power load, multiple coefficients are used to adjust the quantities related to power load to ensure the accuracy of the final total power consumption load.

[0073] like Figure 2 As shown, Figure 2 This is a flow chart of determining the total consumed power load according to an embodiment of the present application. The temperature sensitivity coefficient is calculated based on multiple second temperature values ​​and multiple load values; the power load increment is calculated based on the temperature sensitivity coefficient; the sum of the power load increment and the predetermined basic power load is calculated to obtain the consumed power load; based on the weather type, multiple load values ​​are screened and the weather type coefficient is calculated using the screened load values; and the total consumed power load is calculated based on the weather type coefficient and the consumed power load.

[0074] In some embodiments, the externally provided power load increment includes the power load increment provided by wind and the power load increment provided by light, the meteorological data also includes multiple wind speeds and multiple light intensities, and the power data also includes multiple wind power generation powers and multiple photovoltaic power generation powers; determining the externally provided power load increment corresponding to the predicted date based on the meteorological data and the power data includes: determining the power load increment provided by wind based on the multiple wind speeds and the multiple wind power generation powers; determining the power load increment provided by light based on the multiple light intensities and the multiple photovoltaic power generation powers; and determining the sum of the power load increment provided by wind and the power load increment provided by light as the externally provided power load increment.

[0075] In this embodiment, the externally provided power load increment is an externally provided power load increment related to meteorological factors. Therefore, the externally provided power load increment includes the power load increment provided by wind power and the power load increment provided by sunlight. Since the date to be predicted and the predetermined historical time period have the same weather type, the meteorological data corresponding to the two time periods are similar. Therefore, the externally provided power on the date to be predicted is similar to that in the predetermined historical time period. Based on multiple wind speeds and multiple wind power generation powers in the predetermined historical time period, it is determined that the wind power load increment on the date to be predicted is reliable; based on multiple light intensities and multiple photovoltaic power generation powers in the predetermined historical time period, it is determined that the sunlight power load increment on the date to be predicted is reliable. The sum of the wind power load increment and the sunlight power load increment is determined as the externally provided power load increment, so that the determined externally provided power load increment is reliable.

[0076] In some embodiments, determining the incremental power load provided by the wind force based on the multiple wind speeds and the multiple wind power generation powers includes: performing calculations based on the multiple wind speeds to obtain a wind intensity index; performing calculations based on the multiple wind power generation powers to obtain a wind power output fluctuation rate; inputting the wind intensity index and the wind power output fluctuation rate into a pre-trained prediction model, and outputting a wind power resource fluctuation coefficient through the prediction model; and determining the product value of the wind intensity index and the wind power resource fluctuation coefficient as the incremental power load provided by the wind force.

[0077] In this embodiment, the wind intensity index is an index used to quantify the impact of wind speed on power load. A standardized value is calculated from multiple wind speeds to reflect the potential utilization of wind energy. Therefore, the wind intensity index is calculated based on multiple wind speeds.

[0078] The wind intensity index is calculated using the following formula:

[0079] WSI=α2·V avg +β2·D+γ·T turb Formula (8),

[0080] Among them, WSI is the wind intensity index, V avg is the average wind speed of multiple wind speeds; D is the effective duration corresponding to multiple wind speeds, which can be calculated by the cumulative time when the wind speed reaches a certain threshold; T turb is the degree of wind speed fluctuation, and the calculation formula is σ v is the standard deviation of wind speed, α2 is the first predetermined weight, γ2 is the second predetermined weight, and β is the third predetermined weight.

[0081] Wind power output fluctuation is used to quantify the temporal variability of wind farm output power, reflecting the impact of wind power's intermittent and uncontrollable nature on the power grid. Wind power output fluctuation is calculated using multiple wind turbine outputs to measure the severity of fluctuations. A sliding window approach is used to calculate wind power output fluctuation within a predetermined historical time period (e.g., 72 hours).

[0082] The wind power output fluctuation rate ε is determined by the following formula W :

[0083] ε W =(latest wind power generation power among multiple wind power generation powers - average electric power corresponding to the wind power generation power) / average electric power corresponding to the wind power generation power Formula (9).

[0084] Wind power output has the risk of fluctuation. The wind intensity index and wind power output fluctuation rate are input into the pre-trained prediction model. The prediction model outputs the wind power resource fluctuation coefficient. The influence of wind intensity index and wind power output fluctuation rate is combined to determine the wind power resource fluctuation coefficient. W As input, the fluctuation rate of wind power output As the output, use random forest for regression, assuming the regression model is Y j , the characteristic importance (WSI) corresponding to WSI is the wind power resource fluctuation coefficient (CV). This means that for every 1-unit increase in WSI, wind power output will increase by a certain percentage, and the increase percentage is the wind power resource fluctuation coefficient. The product of the wind intensity index and the wind power resource fluctuation coefficient is determined as the incremental power load provided by wind power.

[0085] The increase in electrical load provided by wind power is determined by the following formula:

[0086] ΔW i =CV*WSI i Formula (10),

[0087] Where ΔW i is the power load increment provided by the wind power corresponding to the i-th hour, CV is the wind power resource fluctuation coefficient, WSI i is the wind intensity index corresponding to the i-th hour.

[0088] By adding up all the hours in the forecasted day, we can get the increase in electricity load provided by wind power.

[0089] Quantifying the net impact of wind power generation on power load not only considers the contribution of wind speed to power generation potential through the wind intensity index, but also considers the uncertainty caused by wind speed volatility through the wind power resource fluctuation coefficient. This ensures the accuracy of the determined power load increment provided by wind power and strengthens the quantitative analysis of power supply and demand fluctuations under complex weather conditions.

[0090] like Figure 3 As shown, Figure 3 This is a flow chart illustrating how to determine the incremental power load provided by wind power, according to an embodiment of the present application. The flow chart analyzes the effective duration of wind output and the degree of wind speed fluctuation based on multiple wind speeds. A wind intensity index is calculated based on the multiple wind speeds, effective duration of wind output, and degree of wind speed fluctuation. A wind power resource fluctuation coefficient is calculated based on the wind intensity index and wind power output fluctuation rate. The incremental power load provided by wind power is calculated based on the wind intensity index and wind power resource fluctuation coefficient.

[0091] In some embodiments, determining the electric load increment provided by the illumination based on the multiple illumination intensities and the multiple photovoltaic power generation powers includes: calculating based on the multiple illumination intensities to obtain the illumination intensity fluctuation rate; calculating based on the multiple photovoltaic power generation powers to obtain the photovoltaic power fluctuation rate; calculating based on the illumination intensity fluctuation rate and the photovoltaic power fluctuation rate to obtain the illumination resource fluctuation coefficient; and determining the product value of the illumination intensity fluctuation rate and the illumination resource fluctuation coefficient as the electric load increment provided by the illumination.

[0092] In this embodiment, the light intensity fluctuation rate is an indicator for measuring the degree of change in light intensity, and is calculated based on multiple light intensities to obtain the light intensity fluctuation rate.

[0093] The light intensity fluctuation rate is determined by the following formula:

[0094]

[0095] in, is the light intensity fluctuation rate in the i-th hour, i i is the light intensity corresponding to the i-th hour, is the average value corresponding to multiple light intensities, and k is the total number of multiple light intensities.

[0096] The PV power fluctuation rate is an important indicator for measuring the degree of variability in the output power of a PV system. It reflects the intermittent and unstable nature of PV power generation. The PV power fluctuation rate is calculated based on multiple PV power generation values.

[0097]

[0098] in, is the photovoltaic power generation power fluctuation rate, gi is the photovoltaic power generation power in the i-th hour, is the average value of multiple photovoltaic power generation powers, and k is the total number of multiple photovoltaic power generation powers.

[0099] The light resource fluctuation coefficient is an indicator that comprehensively evaluates the stability of solar energy resources by combining the light intensity fluctuation rate and the photovoltaic power generation power fluctuation rate. This coefficient reflects the fluctuation characteristics of the entire process from raw light to power output. The light resource fluctuation coefficient is calculated based on the light intensity fluctuation rate and the photovoltaic power generation power fluctuation rate. The photovoltaic power generation power fluctuation rate r g and light intensity fluctuation rate r i There is a linear relationship between g =μ+θr i +v Formula (15) uses the least squares method to estimate the coefficient θ, which is the light resource fluctuation coefficient. The product of the light intensity fluctuation rate and the light resource fluctuation coefficient is determined as the power load increment provided by the light.

[0100] The increase in electrical load provided by sunlight is determined by the following formula:

[0101]

[0102] Where, ΔL j is the power load increment provided by the sunlight corresponding to the jth hour, θ is the light resource fluctuation coefficient, is the light intensity fluctuation rate corresponding to the jth hour.

[0103] By adding up all the hours in the day to be predicted, the increase in power load provided by sunlight can be obtained.

[0104] The net impact of solar power generation on power load is quantified. The uncertainty caused by light volatility is taken into account through the light intensity fluctuation rate and the light resource fluctuation coefficient. This ensures the accuracy of the power load increment provided by the determined light and strengthens the quantitative analysis of power supply and demand fluctuations under complex weather conditions.

[0105] like Figure 4 As shown, Figure 4 This is a flow chart illustrating how to determine the incremental power load provided by illumination, according to an embodiment of the present application. The flow chart includes calculating the illumination intensity fluctuation rate based on multiple illumination intensities. Calculating the photovoltaic power fluctuation rate based on multiple photovoltaic power generation rates. Determining the illumination resource fluctuation coefficient based on the illumination intensity fluctuation rate and the photovoltaic power fluctuation rate. Calculating the incremental power load provided by illumination based on the illumination intensity fluctuation rate and the illumination resource fluctuation coefficient.

[0106] In some embodiments, the future meteorological data includes multiple first temperature values, and the meteorological data also includes multiple third temperature values; based on the future meteorological data, the meteorological data and the power data, the adjusted power load corresponding to the predicted date is determined, including: determining a temperature deviation value based on the multiple first temperature values ​​and the multiple third temperature values; determining a temperature fluctuation rate based on the multiple third temperature values; performing a weighted sum calculation on the temperature deviation value, the temperature fluctuation rate, the wind intensity index and the weather type coefficient to obtain the adjusted power load.

[0107] In this embodiment, the difference between two sets of different temperature data sets (first temperature values ​​and third temperature values) is quantified by comparing them to determine the temperature deviation value. Based on multiple first temperature values ​​and multiple third temperature values, the temperature deviation value is determined. The temperature deviation value is calculated by subtracting the average value corresponding to the multiple third temperature values ​​from the average value corresponding to the multiple first temperature values. The temperature fluctuation rate is an important indicator for quantifying the degree of temperature change, which reflects the severity of temperature changes over time. Based on multiple third temperature values, the temperature fluctuation rate is determined. The temperature fluctuation rate is calculated by calculating the variance values ​​corresponding to the multiple third temperature values. In addition to temperature, meteorological factors that affect power load demand also include weather type and wind force. Therefore, in addition to using parameters related to temperature, it is also necessary to use the wind intensity index and weather type coefficient to determine the adjustment of power load and enhance adaptability to extreme weather.

[0108] The adjusted power load is determined by the following formula:

[0109] DMI = w1×temperature deviation value + w2×wind intensity index + w3×weather type coefficient + w4×temperature fluctuation rate formula (17),

[0110] Among them, w1 is the predetermined weight corresponding to the temperature deviation value, w2 is the predetermined weight corresponding to the wind intensity index, w3 is the predetermined weight corresponding to the weather type coefficient, and w4 is the predetermined weight corresponding to the temperature fluctuation rate. w1+w2+w3+w4=1.

[0111] The introduction of power load adjustment comprehensively considers the weights of multiple factors, including temperature deviation, wind intensity, weather type, and temperature fluctuation, enhancing real-time response to extreme weather. The impact of multiple meteorological factors, including temperature, wind speed, wind intensity index (WSI), and weather type, on power supply and demand is quantified. By integrating physical mechanisms with statistical models, a "two-wheel drive" system for predicting the power supply and demand gap is constructed. This ensures the physical rationality of the prediction while enhancing the ability to capture complex nonlinear relationships. By introducing a dynamic meteorological impact index, the supply and demand gap is dynamically adjusted, enhancing the model's adaptability to extreme weather. Its core value lies in improving forecast accuracy, addressing uncertainty, and supporting intelligent dispatch, making it an indispensable key technology in the construction of new power systems. Statistical models can capture the complex nonlinear relationships and short-term dynamic patterns implicit in historical data, compensating for the inadequate portrayal of local details or accidental factors by physical mechanisms. Combining these two approaches can reduce the errors of a single model and improve overall forecast accuracy. With the increasing penetration of new energy sources and the deepening of power market reform, this method will play an increasingly important role in ensuring energy security and promoting low-carbon transformation.

[0112] In some embodiments, the power load gap corresponding to the predicted date is determined based on the total consumed power load, the adjusted power load and the externally provided power load increment, including: calculating a first sum of the total consumed power load and the adjusted power load, calculating a second sum of the externally provided power load increment and the predetermined power load, and determining the difference between the first sum and the second sum as the power load gap.

[0113] In this embodiment, the externally provided incremental power load refers to the power load provided by meteorological factors. In addition, the base provided power load, namely the predetermined provided power load, is also included. The predetermined provided power load is determined based on historical experience. The provided power load is determined by calculating the second sum of the externally provided incremental power load and the predetermined provided power load. The total consumed power load is the total required power load. To enhance adaptability to extreme weather conditions, the total consumed power load is also added with the adjusted power load to obtain the first sum. The difference between the first and second sums is determined as the power load shortfall.

[0114] G final =Total consumed power load + adjusted power load - externally provided power load increment - scheduled power load Formula (18),

[0115] Equation (18) reflects the dynamic balance between meteorological factors (through load and renewable energy output) and the supply of conventional power sources (thermal, hydropower, etc.). The positive or negative gap value indicates the supply and demand surplus or shortage state of the power market. Through the above steps, this method combines the physical mechanism driven by meteorological data (load and renewable energy output model) with real-time supply and demand data to achieve quantitative calculation of the supply and demand gap.

[0116] It should be noted that the method of the embodiment of the present application can be performed by a single device, such as a computer or server. The method of this embodiment can also be applied in a distributed scenario and performed by multiple devices working together. In such a distributed scenario, one of the multiple devices may only perform one or more steps of the method of the embodiment of the present application, and the multiple devices will interact with each other to complete the method.

[0117] It should be noted that the above description is limited to some embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in an order different from that described in the above embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0118] Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, the present application also provides a device for predicting power load gaps.

[0119] refer to Figure 5 The power load gap prediction device includes:

[0120] The acquisition module 10 is configured to acquire future meteorological data and future weather types corresponding to a date to be predicted, and to acquire meteorological data and power data within a predetermined historical time period including the future weather types.

[0121] The first determining module 20 is configured to determine the total consumed power load and the adjusted power load corresponding to the predicted date based on the future meteorological data, the meteorological data and the power data.

[0122] The second determining module 30 is configured to determine the increment of externally provided power load corresponding to the predicted date based on the meteorological data and the power data.

[0123] The third determining module 40 is configured to determine the power load gap corresponding to the to-be-predicted date based on the total consumed power load, the adjusted power load and the power load increment provided by the outside.

[0124] The above-described device obtains future meteorological data and future weather types corresponding to a date to be predicted, as well as meteorological data and power data within a predetermined historical time period that includes the future weather types. Based on the future meteorological data, the meteorological data, and the power data, the total power load consumption and the adjusted power load corresponding to the date to be predicted are determined. The determination of the total power load consumption is based on a data foundation, ensuring accuracy. By adjusting the power load, the total power load consumption can be adjusted, improving the model's adaptability to complex weather conditions and making the total power load consumption determined based on future meteorological data more accurate. Based on the meteorological data and the power data, the externally provided power load increment corresponding to the date to be predicted is determined, and the externally provided power load increment for the date to be predicted is quantified, thereby accurately determining the externally provided power load increment for the date to be predicted. Based on the total power load consumption, the adjusted power load, and the externally provided power load increment, the power load gap corresponding to the date to be predicted is determined. The power load gap determination is based on a data foundation, ensuring accuracy.

[0125] In some embodiments, the first determination module 20 is further configured such that the future meteorological data includes a plurality of first temperature values, the meteorological data includes a plurality of second temperature values, and the power data includes a plurality of load values; a temperature sensitivity coefficient is obtained based on the plurality of second temperature values ​​and the plurality of load values; a first temperature average value of the plurality of first temperature values ​​is calculated, and a second temperature average value of the plurality of second temperature values ​​is calculated, and a difference between the first temperature average value and the second temperature average value is determined as a temperature variation; a product value of the temperature sensitivity coefficient and the temperature variation is determined as a power load increment; and a power load increment is multiplied by a predetermined basic power load. The sum value is determined as the power consumption load; among the multiple weather types corresponding to the multiple load values, the weather type that occurs most frequently is determined as the standard weather type; among the multiple load values, the load value corresponding to the future weather type is screened as the first load value, and the first load average value corresponding to the first load value is calculated, and the load value corresponding to the standard weather type is screened as the second load value, and the second load average value corresponding to the second load value is calculated; the ratio of the first load average value to the second load average value is calculated, and the ratio is used as the weather type coefficient; the product value of the weather type coefficient and the power consumption load is determined as the total power consumption load.

[0126] In some embodiments, the second determination module 30 is further configured such that the externally provided power load increment includes the power load increment provided by wind and the power load increment provided by illumination, the meteorological data further includes multiple wind speeds and multiple light intensities, and the power data further includes multiple wind power generation powers and multiple photovoltaic power generation powers; based on the multiple wind speeds and the multiple wind power generation powers, the power load increment provided by wind is determined; based on the multiple light intensities and the multiple photovoltaic power generation powers, the power load increment provided by illumination is determined; and the sum of the power load increment provided by wind and the power load increment provided by illumination is determined as the externally provided power load increment.

[0127] In some embodiments, the second determination module 30 is further configured to perform calculations based on the multiple wind speeds to obtain a wind intensity index; perform calculations based on the multiple wind power generation powers to obtain a wind power output fluctuation rate; input the wind intensity index and the wind power output fluctuation rate into a pre-trained prediction model, and output a wind power resource fluctuation coefficient through the prediction model; and determine the product value of the wind intensity index and the wind power resource fluctuation coefficient as the power load increment provided by the wind power.

[0128] In some embodiments, the second determination module 30 is further configured to perform calculations based on the multiple light intensities to obtain a light intensity fluctuation rate; perform calculations based on the multiple photovoltaic power generation powers to obtain a photovoltaic power fluctuation rate; perform calculations based on the light intensity fluctuation rate and the photovoltaic power generation power fluctuation rate to obtain a light resource fluctuation coefficient; and determine the product value of the light intensity fluctuation rate and the light resource fluctuation coefficient as the power load increment provided by the light.

[0129] In some embodiments, the first determination module 20 is further configured such that the future meteorological data includes multiple first temperature values, and the meteorological data also includes multiple third temperature values; a temperature deviation value is determined based on the multiple first temperature values ​​and the multiple third temperature values; a temperature fluctuation rate is determined based on the multiple third temperature values; and a weighted summation calculation is performed on the temperature deviation value, the temperature fluctuation rate, the wind intensity index and the weather type coefficient to obtain the adjusted power load.

[0130] In some embodiments, the third determination module 40 is further configured to calculate a first sum of the total consumed power load and the adjusted power load, calculate a second sum of the externally provided power load increment and the predetermined provided power load, and determine the difference between the first sum and the second sum as the power load gap.

[0131] For the convenience of description, the above devices are described as being divided into various modules according to their functions. Of course, when implementing this application, the functions of each module can be implemented in the same or multiple software and / or hardware.

[0132] The device of the above embodiment is used to implement the corresponding power load gap prediction method in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be repeated here.

[0133] Based on the same inventive concept, corresponding to any of the above-mentioned embodiments and methods, the present application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and runnable on the processor, wherein when the processor executes the program, it implements the power load gap prediction method as described in any of the above embodiments.

[0134] Figure 6 10 is a schematic diagram showing a more specific hardware structure of an electronic device provided in this embodiment. The device may include: a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040 are communicatively connected to each other within the device via the bus 1050.

[0135] The processor 1010 can be implemented using a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0136] The memory 1020 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage devices, dynamic storage devices, etc. The memory 1020 can store an operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 1020 and is called and executed by the processor 1010.

[0137] The input / output interface 1030 is used to connect an input / output module to implement information input and output. The input / output module can be configured as a component in the device (not shown in the figure) or can be externally connected to the device to provide corresponding functions. Input devices may include a keyboard, mouse, touch screen, microphone, various sensors, etc., and output devices may include a display, speaker, vibrator, indicator light, etc.

[0138] The communication interface 1040 is used to connect to a communication module (not shown) to enable communication between the device and other devices. The communication module can communicate via a wired method (such as USB, network cable, etc.) or a wireless method (such as mobile network, WiFi, Bluetooth, etc.).

[0139] The bus 1050 comprises a path for transmitting information between the various components of the device (eg, the processor 1010 , the memory 1020 , the input / output interface 1030 , and the communication interface 1040 ).

[0140] It should be noted that although the above device only shows the processor 1010, the memory 1020, the input / output interface 1030, the communication interface 1040, and the bus 1050, in a specific implementation, the device may also include other components necessary for normal operation. In addition, it will be understood by those skilled in the art that the above device may only include the components necessary to implement the embodiments of this specification, and does not necessarily include all the components shown in the figure.

[0141] The electronic device of the above embodiment is used to implement the corresponding power load gap prediction method in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be described in detail here.

[0142] Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, the present application also provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the power load gap prediction method described in any of the above embodiments.

[0143] The computer-readable media of this embodiment include permanent and non-permanent, removable and non-removable media that can be used to store information by any method or technology. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device.

[0144] The computer instructions stored in the storage medium of the above embodiment are used to enable the computer to execute the power load gap prediction method described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0145] Based on the same concept, corresponding to any of the above-mentioned embodiment methods, the present application also provides a computer program product, including computer program instructions. When the computer program instructions are run on a computer, the computer executes the power load gap prediction method as described in any of the above embodiments, which has the beneficial effects of the corresponding method embodiments and will not be repeated here.

[0146] It should be noted that the embodiments of the present application can be further described in the following manner:

[0147] It is understandable that before using the technical solutions of each embodiment of the present disclosure, the type, scope of use, usage scenarios, etc. of the personal information involved will be informed to the user in an appropriate manner, and the user's authorization will be obtained.

[0148] For example, in response to a user's active request, a prompt message is sent to the user to clearly inform the user that the requested operation will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the electronic device, application, server, storage medium, or other software or hardware that performs the operation of the disclosed technical solution based on the prompt message.

[0149] As an optional but non-limiting implementation, in response to a user's active request, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. Furthermore, the pop-up window may also contain a selection control for the user to select "agree" or "disagree" to provide personal information to the electronic device.

[0150] It is understandable that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0151] Those skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present application is limited to these examples. In line with the present application, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of the different aspects of the embodiments of the present application as described above, which are not provided in detail for the sake of simplicity.

[0152] In addition, for simplicity of description and discussion, and in order not to make the embodiment of the application difficult to understand, the known power supply / ground connection with integrated circuit (IC) chip and other components may or may not be shown in the accompanying drawings provided. In addition, the device can be shown in the form of a block diagram to avoid making the embodiment of the application difficult to understand, and this also takes into account the following fact, that is, the details of the embodiment of these block diagram devices are highly dependent on the platform to be implemented in the embodiment of the application (that is, these details should be fully within the scope of understanding of those skilled in the art). When specific details (for example, circuit) are set forth to describe exemplary embodiments of the application, it will be apparent to those skilled in the art that the embodiment of the application can be implemented without these specific details or when these specific details are changed. Therefore, these descriptions should be considered to be illustrative rather than restrictive.

[0153] Although the present invention has been described in conjunction with specific embodiments thereof, many alternatives, modifications, and variations of these embodiments will be apparent to those skilled in the art based on the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may utilize the embodiments discussed.

[0154] The embodiments of the present application are intended to cover all such substitutions, modifications, and variations that fall within the broad scope of the present application. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present application should be included in the scope of protection of the present application.

Claims

1. A method for predicting power load gap, characterized in that: include: Acquiring future meteorological data and future weather types corresponding to a date to be predicted, and acquiring meteorological data and power data within a predetermined historical time period including the future weather types; Based on the future meteorological data, the meteorological data and the power data, respectively determining the total consumed power load and the adjusted power load corresponding to the to-be-predicted date; Determining an externally provided power load increment corresponding to the predicted date based on the meteorological data and the power data; The power load gap corresponding to the to-be-predicted date is determined based on the total consumed power load, the adjusted power load and the power load increment provided by the outside world.

2. The method according to claim 1, characterized in that The future weather data includes a plurality of first temperature values, the weather data includes a plurality of second temperature values, and the power data includes a plurality of load values; Determining a total power load corresponding to the predicted date based on the future weather data, the weather data, and the power data includes: Performing calculation based on the plurality of second temperature values ​​and the plurality of load values ​​to obtain a temperature sensitivity coefficient; Calculating a first temperature average of the plurality of first temperature values, and calculating a second temperature average of the plurality of second temperature values, and determining a difference between the first temperature average and the second temperature average as a temperature variation; Determine the product of the temperature sensitivity coefficient and the temperature change as the power load increment; determining a sum of the power load increment and a predetermined basic power load as a consumed power load; Among the multiple weather types corresponding to the multiple load values, determining the weather type with the highest frequency as the standard weather type; Among the multiple load values, a load value corresponding to the future weather type is selected as a first load value, and a first load average value corresponding to the first load value is calculated; and a load value corresponding to the standard weather type is selected as a second load value, and a second load average value corresponding to the second load value is calculated; calculating a ratio of the first load average value to the second load average value, and using the ratio as a weather type coefficient; A product value of the weather type coefficient and the consumed electric power load is determined as the total consumed electric power load.

3. The method according to claim 1, characterized in that The externally provided power load increment includes a power load increment provided by wind power and a power load increment provided by sunlight, the meteorological data further includes multiple wind speeds and multiple sunlight intensities, and the power data further includes multiple wind power generation powers and multiple photovoltaic power generation powers; The determining, based on the meteorological data and the power data, an increment of externally provided power load corresponding to the predicted date includes: determining an increase in electric load provided by the wind power based on the plurality of wind speeds and the plurality of wind power generation powers; determining an electrical load increment provided by the illumination based on the multiple illumination intensities and the multiple photovoltaic power generation powers; The sum of the power load increment provided by the wind and the power load increment provided by the sunlight is determined as the power load increment provided by the outside world.

4. The method according to claim 3, characterized in that The determining, based on the multiple wind speeds and the multiple wind power generation powers, of an electric load increment provided by the wind power comprises: Performing calculation based on the multiple wind speeds to obtain a wind intensity index; Calculating based on the multiple wind power generation powers to obtain a wind power output fluctuation rate; Inputting the wind intensity index and the wind power output fluctuation rate into a pre-trained prediction model, and outputting a wind power resource fluctuation coefficient through the prediction model; The product value of the wind intensity index and the wind power resource fluctuation coefficient is determined as the power load increment provided by the wind power.

5. The method according to claim 3, characterized in that The determining, based on the multiple illumination intensities and the multiple photovoltaic power generation powers, an increment of the electric load provided by the illumination, comprises: Performing calculation based on the multiple light intensities to obtain a light intensity fluctuation rate; Calculating based on the multiple photovoltaic power generation powers to obtain a photovoltaic power generation power fluctuation rate; Calculating based on the light intensity fluctuation rate and the photovoltaic power generation power fluctuation rate to obtain a light resource fluctuation coefficient; The product value of the illumination intensity fluctuation rate and the illumination resource fluctuation coefficient is determined as the power load increment provided by the illumination.

6. The method according to claim 1, characterized in that The future meteorological data includes a plurality of first temperature values, and the meteorological data also includes a plurality of third temperature values; Determining an adjusted power load corresponding to the to-be-predicted date based on the future meteorological data, the meteorological data, and the power data includes: determining a temperature deviation value based on the plurality of first temperature values ​​and the plurality of third temperature values; determining a temperature fluctuation rate based on the plurality of third temperature values; The temperature deviation value, the temperature fluctuation rate, the wind intensity index and the weather type coefficient are weighted and summed to obtain the adjusted power load.

7. The method according to claim 1, characterized in that The determining of the power load gap corresponding to the to-be-forecasted date based on the total consumed power load, the adjusted power load, and the power load increment provided by the outside world includes: Calculate a first sum of the total consumed power load and the adjusted power load, calculate a second sum of the externally provided power load increment and the predetermined provided power load, and determine the difference between the first sum and the second sum as the power load gap.

8. A device for predicting power load shortfall, characterized in that: include: an acquisition module configured to acquire future meteorological data and future weather types corresponding to a date to be predicted, and to acquire meteorological data and power data within a predetermined historical time period including the future weather types; a first determining module configured to determine the total consumed power load and the adjusted power load corresponding to the to-be-predicted date based on the future meteorological data, the meteorological data and the power data; A second determining module is configured to determine an externally provided power load increment corresponding to the predicted date based on the meteorological data and the power data; The third determining module is configured to determine the power load gap corresponding to the to-be-predicted date based on the total consumed power load, the adjusted power load and the power load increment provided by the outside.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the program, the method according to any one of claims 1 to 7 is implemented.

10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to enable a computer to execute the method according to any one of claims 1 to 7.

Images