Method and device for risk assessment of electric field power generation prediction

Abstract

The disclosure provides a risk assessment method and device for power prediction of an electric field, the risk assessment method comprising: calculating a deviation value of historical meteorological prediction data based on actual meteorological data, and establishing a meteorological deviation model; calculating an accuracy value of historical power prediction data based on actual power data, and establishing a power deviation model; obtaining a meteorological deviation prediction value and a power deviation prediction value based on the current meteorological prediction data and the meteorological deviation model and the power deviation model; and evaluating the risk level of power prediction of the electric field according to the meteorological deviation prediction value and the power deviation prediction value based on a preset evaluation rule model.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the field of electric field, in particular to a risk assessment method and device for electric field power prediction, electronic equipment and storage medium. BACKGROUND

[0002] In the product related to wind farm power prediction, the current power prediction model mainly uses historical actual power and predicted weather to establish a power prediction model (in which predicted wind speed is a strong correlation feature of the model), that is, the historical data is mainly used to optimize the power prediction model, so that the predicted weather is used as the input feature of the power prediction model to generate the predicted power.

[0003] However, due to the variability and irregularity of the predicted weather (predicted wind speed), the accuracy of the predicted power cannot be effectively controlled, and the accuracy of the predicted power is not up to standard, which will lead to a large number of inaccurate planned power generation and substandard assessment of the wind farm. SUMMARY

[0004] The exemplary embodiments of the present disclosure provide a risk assessment method and device for electric field power prediction, electronic equipment and storage medium, which at least solve the above technical problems and other technical problems not mentioned above.

[0005] According to one aspect of the present disclosure, a risk assessment method for electric field power prediction is provided, the method comprising: calculating a deviation value of historical weather prediction data based on weather actual data, and establishing a weather deviation model according to the obtained deviation value; calculating an accuracy value of historical power prediction data based on power actual data, and establishing a power deviation model according to the obtained accuracy value; inputting the current weather prediction data into the weather deviation model and the power deviation model respectively to obtain weather deviation prediction value and power deviation prediction value; and based on a preset evaluation rule model, evaluating the risk level of the electric field power prediction according to the weather deviation prediction value and the power deviation prediction value.

[0006] Optionally, the calculating of the deviation value of the historical weather prediction data based on the weather actual data, and the establishing of the weather deviation model according to the obtained deviation value, comprises: classifying the corresponding weather actual data and the historical weather prediction data according to a preset time period, and then classifying again according to a preset magnitude segment; in each classified data set, calculating the deviation value of the historical weather prediction data based on the weather actual data, and establishing the weather deviation model according to the obtained deviation value.

[0007] Optionally, the accuracy value of the historical power prediction data is calculated based on the actual power data, and the power deviation model is established according to the obtained accuracy value, including: establishing a power prediction model based on the historical meteorological forecast data and the actual power data; inputting the historical meteorological forecast data into the power prediction model to obtain power prediction data; calculating the accuracy value of the power prediction data based on the actual power data, and establishing the power deviation model according to the obtained accuracy value.

[0008] Optionally, the accuracy value of the power prediction data is calculated based on the actual power data, and the power deviation model is established according to the obtained accuracy value, including: using the time information and magnitude information in the historical meteorological forecast data as a reference, classifying the corresponding power prediction data and the actual power data according to a preset time period, and then classifying them again according to a preset magnitude segment; in each type of data set after classification, the accuracy value of the power prediction data is calculated based on the actual power data, and the power deviation model is established according to the obtained accuracy value.

[0009] Optionally, the current meteorological forecast data is input into the meteorological deviation model and the probability deviation model respectively to obtain the meteorological deviation prediction value and the power deviation prediction value, including: classifying the current meteorological forecast data according to a preset time period, and then classifying it again according to a preset magnitude segment; inputting each type of classified data set into the meteorological deviation model and the power deviation model respectively to obtain the meteorological deviation prediction value and the power deviation prediction value.

[0010] Optionally, the risk level of the electric field power prediction is evaluated based on the preset evaluation rule model according to the meteorological deviation prediction value and the power deviation prediction value, including: determining the meteorological risk level and power risk level corresponding to the meteorological deviation prediction value and the power deviation prediction value respectively according to the preset evaluation rule model; and determining the evaluation result of the risk level of the electric field power prediction based on the numerical calculation results of the meteorological risk level and the power risk level.

[0011] Optionally, the method also includes: calculating the statistical characteristic value of the current meteorological forecast data, and correcting the evaluation result of the risk level of the electric field power prediction based on the statistical characteristic value; wherein, correcting the risk level based on the statistical characteristic value includes: when the meteorological risk level is greater than or equal to the first preset threshold, if the variance value in the statistical characteristic value is less than the second preset threshold, and the power deviation prediction value is greater than or equal to the third preset threshold, determining that the evaluation result of the risk level of the electric field power prediction is less than the fourth preset threshold.

[0012] Optionally, the method also includes revising the historical meteorological forecast data and the current meteorological forecast data, and the correction step includes: establishing a meteorological correction model based on the historical meteorological forecast data and the actual meteorological data; inputting the historical meteorological forecast data and the current meteorological forecast data into the meteorological correction model respectively to obtain the revised historical meteorological forecast data and the current meteorological forecast data.

[0013] According to another aspect of the present disclosure, a risk assessment device for electric field power generation prediction is also provided, which includes: a meteorological deviation model acquisition module, configured to calculate the deviation value of historical meteorological prediction data based on actual meteorological data, and establish a meteorological deviation model according to the obtained deviation value; a power deviation model acquisition module, configured to calculate the accuracy value of historical power prediction data based on actual power data, and establish a power deviation model according to the obtained accuracy value; a deviation prediction value acquisition module, configured to input current meteorological prediction data into the meteorological deviation model and the power deviation model respectively to obtain a meteorological deviation prediction value and a power deviation prediction value; a risk level assessment module, configured to assess the risk level of electric field power prediction according to the meteorological deviation prediction value and the power deviation prediction value based on a preset assessment rule model.

[0014] According to another aspect of the present disclosure, an electronic device is also provided, which includes: at least one processor; at least one memory storing computer-executable instructions, wherein the computer-executable instructions, when executed by the at least one processor, prompt the at least one processor to execute the risk assessment method as described above.

[0015] According to another aspect of the present disclosure, a computer-readable storage medium storing instructions is further provided, wherein when the instructions are executed by at least one processor, the at least one processor is prompted to perform the risk assessment method as described above.

[0016] The technical solutions provided by the embodiments of the present disclosure bring at least the following beneficial effects:

[0017] According to the risk assessment method, device, electronic device and storage medium for electric field power generation prediction disclosed in the present invention, by combining a meteorological deviation model, a power deviation model and a preset assessment rule model to evaluate the risk level of electric field power prediction, the risk level of electric field power prediction obtained by the assessment can be used in a model or early warning for predicting and optimizing the power generation of the electric field, so as to optimize the power generation size of the electric field through automatic or human intervention, adjust the power generation of the electric field, and thus optimize the power generation prediction of the electric field to obtain a more accurate power generation prediction value of the electric field, thereby preventing the problem of poor stability of the power grid system caused by a large deviation between the power generation prediction value of the electric field and the actual required power generation value, thereby effectively controlling the accuracy of the power generation prediction of the electric field, and avoiding the occurrence of inaccurate planned power generation and substandard assessment of the electric field due to the accuracy of the power generation prediction of the electric field not meeting the standard; or the risk level of the power generation prediction of the electric field obtained by the assessment can be used in the forecast and adjustment of the power trading of the electric field station to maximize the profit of the station.

[0018] In addition, when establishing the meteorological deviation model and the power deviation model, the data set is classified into two-dimensional features and then the deviation value and accuracy value are statistically calculated. This combines the probabilistic statistical thinking of big data with meteorological analysis, thereby improving the accuracy of the risk level assessment of the electric field power forecast.

[0019] In addition, the obtained meteorological risk level can be used for early warning of meteorological forecasts when the deviation is large, thereby facilitating the analysis of the problem and optimizing the method of predicting meteorological data; the obtained power risk level can be used for early warning of electric field power generation predictions when the accuracy is low, thereby facilitating the analysis of the problem and optimizing the method of predicting electric field power generation.

[0020] In addition, correcting the risk level according to the statistical characteristic value can further improve the accuracy of evaluating the risk level of the electric field power prediction when the meteorological risk level is greater than or equal to the first preset threshold. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The accompanying drawings herein are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the description are used to explain the principles of the present disclosure, and do not constitute an improper limitation of the present disclosure.

[0022] Figure 1 A flow chart showing a risk assessment method for electric field power generation prediction according to an exemplary embodiment of the present disclosure;

[0023] Figure 2 A flowchart of establishing a weather deviation model according to an exemplary embodiment of the present disclosure is shown;

[0024] Figure 3A flowchart showing the establishment of a power deviation model according to an example embodiment of the present disclosure;

[0025] Figure 4 A flowchart showing the obtaining of a weather deviation prediction value and a power deviation prediction value according to an example embodiment of the present disclosure;

[0026] Figure 5 A flowchart showing the evaluation of a risk level of a power prediction of an electric field according to an example embodiment of the present disclosure;

[0027] Figure 6 A prediction curve diagram showing a predicted wind speed and an actual wind speed of a station in the Xinjiang region according to an example embodiment of the present disclosure;

[0028] Figure 7 A prediction curve diagram showing a predicted power and an actual power of a station in the Xinjiang region according to an example embodiment of the present disclosure;

[0029] Figure 8 A prediction curve diagram showing a predicted wind speed and an actual wind speed of a station in the Guangxi region according to an example embodiment of the present disclosure;

[0030] Figure 9 A prediction curve diagram showing a predicted power and an actual power of a station in the Guangxi region according to an example embodiment of the present disclosure;

[0031] Figure 10 A prediction curve diagram showing a predicted wind speed and an actual wind speed of a station in the Hebei region according to an example embodiment of the present disclosure;

[0032] Figure 11 A prediction curve diagram showing a predicted power and an actual power of a station in the Hebei region according to an example embodiment of the present disclosure;

[0033] Figure 12 A prediction curve diagram showing a predicted wind speed and an actual wind speed of a station in the Ningxia region according to an example embodiment of the present disclosure;

[0034] Figure 13 A prediction curve diagram showing a predicted power and an actual power of a station in the Ningxia region according to an example embodiment of the present disclosure;

[0035] Figure 14 A prediction curve diagram showing a predicted wind speed and an actual wind speed of a station in the Hubei region according to an example embodiment of the present disclosure;

[0036] Figure 15 A prediction curve diagram showing a predicted power and an actual power of a station in the Hubei region according to an example embodiment of the present disclosure;

[0037] Figure 16 A block diagram of a risk evaluation device for power prediction of an electric field according to an example embodiment of the present disclosure;

[0038] Figure 17 A block diagram of an electronic device showing an example embodiment of the present disclosure. DETAILED DESCRIPTION

[0039] In order for those skilled in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the drawings.

[0040] It should be noted that the terms "first", "second", and the like in the specification and claims of the present disclosure and the above-described drawings are used to distinguish similar objects, and do not necessarily have to describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following embodiments do not represent all embodiments consistent with the present disclosure. Rather, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0041] It should be noted herein that "at least one of a plurality of items" appearing in the present disclosure means that three types of alternatives are included, i.e., "any one of the plurality of items", "a combination of any two or more of the plurality of items", and "all of the plurality of items". For example, "including at least one of A and B" includes the following three alternatives: (1) including A; (2) including B; and (3) including A and B. For another example, "performing at least one of step one and step two" means the following three alternatives: (1) performing step one; (2) performing step two; and (3) performing step one and step two.

[0042] The present disclosure provides a risk assessment method and device for power prediction of an electric field, an electronic device, and a storage medium. By combining a weather bias model, a power bias model, and a preset evaluation rule model to evaluate the risk level of power prediction of an electric field, the evaluated risk level of power prediction of an electric field can be used in a model for optimizing power prediction of an electric field or a warning, so as to optimize the power generation of the electric field through automatic or manual intervention, adjust the power generation of the electric field, thereby optimizing the power generation prediction of the electric field, obtaining a more accurate power generation prediction value of the electric field, preventing the problem of poor stability of the power grid system caused by a large deviation between the power generation prediction value of the electric field and the actual required power generation value, and thereby effectively controlling the accuracy of the power generation prediction of the electric field, avoiding the situation that the planned power generation of the electric field is inaccurate and the assessment is not up to standard due to the inaccuracy of the power generation prediction of the electric field. Alternatively, the evaluated risk level of power prediction of an electric field can be used in the prediction and adjustment of the power transaction of the field station of the electric field, so as to maximize the income of the field station.

[0043] Below, we will refer to Figures 1 to 17 The risk assessment method, device, electronic device and storage medium for predicting electric field power generation disclosed in the present invention are specifically described.

[0044] Figure 1 A flow chart illustrating a risk assessment method for predicting electric field power generation according to an exemplary embodiment of the present disclosure.

[0045] Reference Figure 1 In step S101, the deviation value of the historical meteorological forecast data can be calculated based on the actual meteorological data, and a meteorological deviation model can be established according to the obtained deviation value.

[0046] According to exemplary embodiments of the present disclosure, the European Meteorological Centre's forecast weather source (EC), Goldwind's self-developed single-point weather source (SUP), and Goldwind's self-developed grid weather source (GRIDAI) combined with a hybrid weather source (EC-SUP-GRIDAI) can be used as weather forecast data. It is understood that the source of weather forecast data is not limited to the above-mentioned weather sources, and other weather sources can also be used. In addition, actual weather data can be obtained through observation.

[0047] Figure 2 A flowchart of establishing a weather deviation model according to an exemplary embodiment of the present disclosure is shown.

[0048] Reference Figure 2 According to an exemplary embodiment of the present disclosure, before establishing a meteorological deviation model, the historical meteorological forecast data and the current meteorological forecast data can be corrected, and the correction steps may include: establishing a meteorological correction model based on the historical meteorological forecast data and the actual meteorological data; inputting the historical meteorological forecast data and the current meteorological forecast data into the meteorological correction model respectively to obtain the revised historical meteorological forecast data and the current meteorological forecast data.

[0049] According to an exemplary embodiment of the present disclosure, a meteorological correction model can be established based on historical meteorological forecast data and actual meteorological data using, but not limited to, an elastic network algorithm (ElasticNet). The optimization objective function of the elastic network algorithm can be defined by the following formula (1):

[0050]

[0051] In the above formula (1), n samples refers to the number of samples, Xω refers to the meteorological forecast data, y refers to the actual meteorological data, ω refers to the weight, αρ||ω||1 refers to the L1 regularization, α refers to the complexity parameter, and ρ refers to the regularization loss rate.

[0052] According to an exemplary embodiment of the present disclosure, a weather correction model can be established using historical weather forecast data and actual weather data including but not limited to the past two years, and abnormal data in the historical weather forecast data and actual weather data can be eliminated to ensure data accuracy.

[0053] According to exemplary embodiments of the present disclosure, historical weather forecast data and actual weather data include, but are not limited to, wind speed data and sunshine duration data. Taking wind speed as an example, the present disclosure may set a wind speed threshold of [0 m / s, 50 m / s]. Based on the wind speed constant, it may be determined that if 10 consecutive wind speed points have the same value, the data is considered abnormal and removed.

[0054] According to an exemplary embodiment of the present disclosure, the corresponding actual meteorological data and historical meteorological forecast data can be classified according to a preset time period, and then classified again according to a preset magnitude segment; and in each type of data set after classification, the deviation value of the historical meteorological forecast data can be calculated based on the actual meteorological data, and a meteorological deviation model can be established based on the obtained deviation value.

[0055] According to an exemplary embodiment of the present disclosure, the corresponding actual meteorological data and historical meteorological forecast data can first be classified in a time series. Specifically, the corresponding actual meteorological data and historical meteorological forecast data can be classified with a time granularity including but not limited to 15 minutes, and can be divided into 96 time periods. Then, for the above-mentioned data set within each time period, it can be further classified according to the preset magnitude segment of the wind speed value; for example, 0m / s-3m / s can be classified as a category, 3m / s-13m / s every 1m / s interval can be classified as a category, 13m / s-15m / s can be classified as a category, 15m / s-18m / s can be classified as a category, and 18m / s-40m / s can be classified as a category, which can be divided into 14 wind speed segments as preset magnitude segments. Therefore, the corresponding actual meteorological data and historical meteorological forecast data can be divided into 96×14=1344 categories respectively. In order to ensure the probability accuracy of meteorological deviation in each category, the amount of data in each category after classification can be set to be greater than or equal to 96.

[0056] According to an exemplary embodiment of the present disclosure, for each classified data set including corresponding actual meteorological data and historical meteorological forecast data, a deviation value between the corresponding actual meteorological data and the historical meteorological forecast data can be calculated using, but not limited to, a root mean square error, and the deviation value result of each class can be saved as the result of a meteorological deviation model, for example, it can be saved as, but not limited to, a PKL model. Specifically, the deviation value can be calculated using the following root mean square error formula (2):

[0057]

[0058] Among them, W Mi Refers to actual meteorological data, W Pi Refers to historical weather forecast data, and n refers to the number of samples.

[0059] Return to reference Figure 1 In step S102, the accuracy value of the historical power prediction data can be calculated based on the actual power data, and a power deviation model can be established according to the obtained accuracy value.

[0060] It is understood that the power mentioned in this disclosure refers to the power generated by the electric field. The actual power data can represent the actual power demand.

[0061] Figure 3 A flowchart of establishing a power deviation model according to an exemplary embodiment of the present disclosure is shown.

[0062] Reference Figure 3 According to an exemplary embodiment of the present disclosure, a power prediction model can be established based on historical meteorological forecast data and actual power data; historical meteorological forecast data can be input into the power prediction model to obtain power prediction data; the accuracy value of the power prediction data can be calculated based on the actual power data, and a power deviation model can be established based on the obtained accuracy value.

[0063] According to an exemplary embodiment of the present disclosure, it is possible to first obtain historical weather forecast data and actual power data, including but not limited to the past two years; for abnormal data in the data set, a data screening algorithm can be used to eliminate it. Specifically, the data screening algorithm includes but is not limited to a rule-based screening algorithm, a statistics-based screening algorithm, a clustering-based screening algorithm, an association rule-based screening algorithm, and an artificial neural network-based screening algorithm. Afterwards, a power prediction model can be established based on historical weather forecast data and actual power data using a multilayer perceptron algorithm (MLP), including but not limited to, to input the historical weather forecast data into the power prediction model to obtain power prediction data. Specifically, the optimization loss function in the multilayer perceptron algorithm can be shown as the following formula (3):

[0064]

[0065] Where n refers to the number of samples, refers to the power prediction data, y refers to the actual power data, W refers to the weight; α refers to the complexity parameter, which is used to control the scaling of the loss function.

[0066] It is understandable that the method for obtaining historical power prediction data is not limited to the above method, and can also be obtained through various other methods, such as directly obtaining from a power prediction database.

[0067] According to an exemplary embodiment of the present disclosure, the time information and magnitude information in the historical meteorological forecast data can be used as a reference, and the corresponding power prediction data and power actual data can be classified according to the preset time period, and then classified again according to the preset magnitude segment; in each type of data set after classification, the accuracy value of the power prediction data can be calculated based on the power actual data, and a power deviation model can be established based on the obtained accuracy value.

[0068] According to an exemplary embodiment of the present disclosure, before establishing a power deviation model, historical meteorological forecast data can be corrected, and the correction steps may include: establishing a meteorological correction model based on historical meteorological forecast data and actual meteorological data; inputting historical meteorological forecast data and current meteorological forecast data into the meteorological correction model respectively to obtain revised historical meteorological forecast data.

[0069] According to an exemplary embodiment of the present disclosure, power forecast data and actual power data can be matched with historical weather forecast data by time coordinates. On this basis, the power forecast data and actual power data can be classified while the historical weather forecast data is classified based on time information and magnitude information as a reference. Historical meteorological forecast data can be classified through the following steps. For example, the historical meteorological forecast data can be first classified in time series; specifically, the historical meteorological forecast data can be classified with a time granularity including but not limited to 15 minutes, and can be divided into 96 time periods; then, for the above data set in each time period, it can be further classified according to the preset magnitude segment of wind speed value; for example, 0m / s-3m / s can be classified as one category, 3m / s-13m / s and every 1m / s interval can be classified as one category, 13m / s-15m / s can be classified as one category, 15m / s-18m / s can be classified as one category, and 18m / s-40m / s can be classified as one category, which can be divided into 14 wind speed segments as preset magnitude segments; therefore, the historical meteorological forecast data can be divided into 96×14=1344 categories; in order to ensure the probability accuracy of meteorological deviation in each category, the data size in each category after classification can be set to be greater than or equal to 96. It can be understood that the classified power prediction data and actual power data can also be divided into 1344 categories respectively, and the data size of the power prediction data and actual power data in each category after classification can also be set to be greater than or equal to 96 respectively.

[0070] According to an exemplary embodiment of the present disclosure, for the power prediction data and the actual power data in each category after classification, the accuracy value of the power prediction data in each category relative to the actual power data can be calculated, and the obtained accuracy value in each category can be saved as the result of the power deviation model.

[0071] The above accuracy value can be calculated by the following formula (4):

[0072]

[0073] R refers to the accuracy value, P Mi Refers to the actual power data, P Pi Refers to power forecast data, Cap refers to installed capacity, and n refers to the number of samples.

[0074] Return to reference Figure 1 In step S103, the current weather forecast data can be input into the weather deviation model and the power deviation model respectively to obtain a weather deviation prediction value and a power deviation prediction value.

[0075] According to an exemplary embodiment of the present disclosure, current weather forecast data may also come from the aforementioned mixed weather source.

[0076] According to an exemplary embodiment of the present disclosure, weather forecast data including but not limited to the next 48 hours may be acquired as current weather forecast data.

[0077] Figure 4 A flowchart of obtaining a weather deviation prediction value and a power deviation prediction value according to an exemplary embodiment of the present disclosure is shown.

[0078] Reference Figure 4 According to an exemplary embodiment of the present disclosure, before obtaining the weather deviation prediction value and the power deviation prediction value, the current weather forecast data can be input into the above-mentioned weather correction model to obtain the corrected current weather forecast data.

[0079] According to an exemplary embodiment of the present disclosure, the current meteorological forecast data can be classified according to a preset time period and then classified again according to a preset magnitude segment; each type of classified data set can be input into a meteorological deviation model and a power deviation model respectively to obtain a meteorological deviation prediction value and a power deviation prediction value.

[0080] According to the example embodiments of the present disclosure, for the current weather forecast data, the classification can be performed in the following manner, for example: the current weather forecast data can be first classified in time series; specifically, the current weather forecast data can be classified in time granularity including but not limited to 15 minutes, which can be divided into 96 time periods; then, for the data set in each time period, the data set can be classified again according to the preset magnitude segment of wind speed value; for example, 0m / s-3m / s can be classified as one category, 3m / s-13m / s can be classified as one category with an interval of 1m / s, 13m / s-15m / s can be classified as one category, 15m / s-18m / s can be classified as one category, and 18m / s-40m / s can be classified as one category, and a total of 14 wind speed segments can be classified as the preset magnitude segment; thus, the current weather forecast data can be classified into 96x14=1344 categories.

[0081] It can be understood that the manner of classifying the data set according to the preset time period and then classifying again according to the preset magnitude segment is not limited to the above description.

[0082] According to the example embodiments of the present disclosure, for each data set in the classified current weather forecast data, each data set can be input into the weather bias model and the power bias model respectively, to obtain the weather bias prediction value and the power bias prediction value of each time period at the corresponding time. Then the weather bias prediction value and the power bias prediction value at each time of the day can be averaged to obtain the average value as the weather bias prediction value and the power bias prediction value of the day.

[0083] Referring back to Figure 1 In step S104, the risk level of the power prediction of the power plant can be evaluated based on the preset evaluation rule model according to the weather bias prediction value and the power bias prediction value.

[0084] According to the example embodiments of the present disclosure, the evaluation rules of the risk level in the preset evaluation rule model include but are not limited to the following rules: 0-5 points are classified into 5 levels as the level standard, for example, 1, 2, 3, 4, and 5 levels, and the higher the level, the greater the risk.

[0085] Figure 5 A flowchart of evaluating the risk level of the power prediction of the power plant according to the example embodiments of the present disclosure is shown.

[0086] Referring back to Figure 5 According to the example embodiments of the present disclosure, the weather risk level and the power risk level corresponding to the weather bias prediction value and the power bias prediction value can be determined according to the preset evaluation rule model; and the evaluation result of the risk level of the power prediction of the power plant can be determined according to the numerical calculation result of the weather risk level and the power risk level.

[0087] According to an exemplary embodiment of the present disclosure, the corresponding meteorological risk level and power risk level can be determined based on the magnitude of the meteorological deviation prediction value and the power deviation prediction value, respectively. For example, the meteorological risk level and the power risk level can be determined to be level 1 and 2, respectively. Numerical calculation results include, but are not limited to, the mean and weighted average of the meteorological risk level and the power risk level. That is, the assessment result of the risk level of the electric field power prediction can be determined to be the mean and weighted average of the meteorological risk level and the power risk level.

[0088] According to an exemplary embodiment of the present disclosure, when the meteorological risk level is less than a first preset threshold, that is, when the meteorological risk level is smaller in the risk assessment rules of the current site, for example, the meteorological risk level is less than level 1, then the assessment result of the risk level of the electric field power prediction can be determined as the average of the meteorological risk level and the power risk level.

[0089] According to an exemplary embodiment of the present disclosure, the statistical characteristic value of the current meteorological forecast data can be calculated, and the evaluation result of the risk level of the electric field power prediction can be corrected according to the statistical characteristic value; wherein, correcting the risk level according to the statistical characteristic value can include: when the meteorological risk level is greater than or equal to the first preset threshold, if the variance value in the statistical characteristic value is less than the second preset threshold, and the power deviation prediction value is greater than or equal to the third preset threshold, determining that the evaluation result of the risk level of the electric field power prediction is less than the fourth preset threshold.

[0090] According to an exemplary embodiment of the present disclosure, the statistical characteristic values ​​of the current weather forecast data include but are not limited to: average value, maximum value, minimum value, number of data in each magnitude segment classification, interval distribution, variance, etc.

[0091] According to an exemplary embodiment of the present disclosure, the risk level is corrected according to the statistical characteristic value, which may specifically include but is not limited to the following steps: when the meteorological risk level is large in the risk assessment rules of the current site, for example, the meteorological risk level is greater than or equal to level 1, if the variance in the statistical characteristic value of the current meteorological forecast data is small, for example, the variance is less than 2, that is, the second preset threshold value can be 2, then it can be determined that the interval distribution is mainly light wind, if the power deviation prediction value is greater than or equal to the third preset threshold value, the third preset threshold value can be but is not limited to 85, then it can be determined that the evaluation result value of the risk level of the electric field power prediction is small, for example, less than 1.

[0092] According to an exemplary embodiment of the present disclosure, when using data from November 2021 to 2022 as a training set and data from December 2022 as a test set, the prediction accuracy of December for stations in different regions is as follows:

[0093] It can be understood that the meteorological data mentioned below are all expressed in wind speed, and "forecasted wind speed" is used to represent the historical and current "meteorological forecast data", "actual wind speed" is used to represent "actual meteorological data", "forecasted power" is used to represent the historical "power forecast data", and "measured power" is used to represent "actual power data".

[0094] The table labels have the following meanings: dtime: date, source: meteorological source, nwp_rmse: root mean square error of meteorological statistical forecast, power_rmse: power forecast accuracy, nwp_risk: meteorological risk level, power_risk: power risk level, risk: risk level of electric field power forecast, report_rmse: reported power forecast accuracy

[0095] (1) The risk level assessment of electric field power prediction for a station in Xinjiang is shown in the following table:

[0096]

[0097]

[0098] Figure 6 A prediction curve diagram showing the predicted wind speed and actual wind speed of a station in Xinjiang region according to an exemplary embodiment of the present disclosure.

[0099] Figure 7 A prediction curve diagram showing the predicted power and actual power of a station in Xinjiang region according to an exemplary embodiment of the present disclosure.

[0100] Reference Figure 6 and Figure 7 , level 1 can be used as the evaluation standard for the risk level of the electric field power prediction of a station in the Xinjiang region, that is, 1 can be used as the fourth preset threshold; the accuracy value can be greater than or equal to 80 as the evaluation standard for the power deviation prediction value of a station in the Xinjiang region, that is, 80 can be used as the third preset threshold. In the evaluation results, the risk level of the electric field power prediction is greater than or equal to the first preset threshold, that is, the number of days greater than or equal to 1 is 2, corresponding to rows (4) and (7) in the above table. At this time, the power deviation prediction value of a station in the Xinjiang region should be less than the third preset threshold, that is, it should be less than 80. However, the data in rows (4) and (7) in the above table show that the power deviation prediction value is greater than 80. It can be seen that in the risk level evaluation of the electric field power prediction of a station in the Xinjiang region, the evaluation of rows (4) and (7) for a total of 2 days has deviations, and the overall accuracy of the risk level evaluation of the electric field power prediction is 93.33%.

[0101] (II) The risk level assessment of electric field power prediction for a station in Guangxi is shown in the following table:

[0102]

[0103]

[0104] Figure 8 A prediction curve diagram showing the predicted wind speed and actual wind speed of a station in the Guangxi region according to an exemplary embodiment of the present disclosure.

[0105] Figure 9 A prediction curve diagram showing the predicted power and actual power of a station in the Guangxi region according to an exemplary embodiment of the present disclosure.

[0106] Reference Figure 8 and Figure 9 The risk level evaluation criterion for the electric field power forecast for a station in the Guangxi region can be 1, that is, 1 can be used as the fourth preset threshold. An accuracy value greater than or equal to 80 can be used as the evaluation criterion for the power deviation prediction value for a station in the Guangxi region, that is, 80 can be used as the third preset threshold. Clearly, no deviation was observed in the risk level assessment of the electric field power forecast for a station in the Guangxi region, and the overall accuracy of the risk level assessment for the electric field power forecast was 100%.

[0107] (III) The risk level assessment of the electric field power prediction of a station in Hebei Province is shown in the following table:

[0108]

[0109] Figure 10 A prediction curve diagram showing the predicted wind speed and actual wind speed of a station in Hebei area according to an exemplary embodiment of the present disclosure.

[0110] Figure 11 A prediction curve diagram showing the predicted power and actual power of a station in Hebei area according to an exemplary embodiment of the present disclosure.

[0111] Reference Figure 10 and Figure 11The first level can be used as the evaluation standard of the risk level of the power prediction of the Hebei regional one-station, i.e., 1 is used as the fourth preset threshold value. The accuracy rate value greater than or equal to 80 can be used as the evaluation standard of the power deviation prediction value of the Hebei regional one-station, i.e., 80 is used as the third preset threshold value. In the evaluation result, the number of days when the risk level of the power prediction is greater than or equal to the first preset threshold value, i.e., greater than or equal to 1, is 14, which corresponds to the (2, 3, 10-15, 17, 19, 22-24, 27) rows in the above table. At this time, the power deviation prediction value of the Hebei regional one-station should be less than the third preset threshold value, i.e., less than 80. However, the data in the (3, 19, 24) rows in the above table shows that the power deviation prediction value is greater than 80. It can be seen that in the risk level evaluation of the power prediction of the Hebei regional one-station, the evaluation of the (3, 19, 24) rows in total 3 days is deviated. When the risk level of the power prediction is evaluated, the accuracy rate is 78.57% when the evaluation result is the risk level higher than or equal to the first level, i.e., greater than or equal to 1. When the power deviation prediction value is less than the third preset threshold value, i.e., less than 80, the risk level of the power prediction should be greater than the first preset threshold value, i.e., greater than 1. It can be seen that in the risk level evaluation of the power prediction of the Hebei regional one-station, the data of the (1, 6, 16, 18, 21, 28) rows in total 6 days does not meet this situation. Therefore, the evaluation result of 9 days (corresponding to the data of the (3, 19, 24) rows and the (1, 6, 16, 18, 21, 28) rows in the above table) is deviated. The accuracy rate of the overall evaluation of the risk level of the power prediction is 70%.

[0112] (Four) The risk level evaluation of the power prediction of the Ningxia regional one-station is shown in the following table.

[0113]

[0114]

[0115] Figure 12 A prediction curve diagram of the predicted wind speed and the actual wind speed of the Ningxia regional one-station showing an exemplary embodiment of the present disclosure is shown.

[0116] Figure 13 A prediction curve diagram of the predicted power and the actual power of the Ningxia regional one-station showing an exemplary embodiment of the present disclosure is shown.

[0117] Referring to Figure 12 and Figure 13Level 1 can be used as the evaluation standard for the risk level of the electric field power prediction of a station in the Ningxia region, that is, 1 can be used as the fourth preset threshold; an accuracy value greater than or equal to 80 can be used as the evaluation standard for the power deviation prediction value of a station in the Ningxia region, that is, 80 can be used as the third preset threshold. In the evaluation results, the risk level of the electric field power prediction is high, that is, it is greater than or equal to the first preset threshold, or the number of days greater than or equal to 1 is 2, corresponding to rows (11, 16) in the above table. At this time, the power deviation prediction value of the above-mentioned station in Ningxia region should be less than the third preset threshold, that is, it should be less than 80, which is consistent with the data display of rows (11, 16) in the above table. It can be seen that in the risk level evaluation of the electric field power prediction of a station in Ningxia region, the evaluation result is that the accuracy rate is 100% when the risk level is high, that is, greater than or equal to level 1; and when the power deviation prediction value is less than the third preset threshold, that is, less than 80, the risk level of the electric field power prediction should be greater than the first preset threshold, that is, greater than 1. It can be seen that in the risk level evaluation of the electric field power prediction of a station in Ningxia region, the data of 2 days in rows (9, 21) do not meet this situation; therefore, the evaluation results of 2 days (corresponding to the data in rows 9 and 21 of the above table) have deviations, and the overall accuracy of the risk level evaluation of the electric field power prediction is 93.33%.

[0118] (V) The risk level assessment of the electric field power prediction of a station in Hubei Province is shown in the following table:

[0119]

[0120] Figure 14 A prediction curve diagram showing the predicted wind speed and actual wind speed of a station in Hubei area according to an exemplary embodiment of the present disclosure.

[0121] Figure 15 A prediction curve diagram showing the predicted power and actual power of a station in Hubei area according to an exemplary embodiment of the present disclosure.

[0122] Reference Figure 10 and Figure 11, level 1 can be used as the evaluation standard for the risk level of the electric field power prediction of a station in the Hubei region, that is, 1 can be used as the fourth preset threshold; the accuracy value greater than or equal to 80 can be used as the evaluation standard for the power deviation prediction value of a station in the Hubei region, that is, 80 can be used as the third preset threshold. In the evaluation results, the risk level of the electric field power prediction is greater than or equal to the first preset threshold, that is, the number of days greater than or equal to 1 is 6, corresponding to the (1, 11, 17, 18, 27, 28) rows in the above table. At this time, the power deviation prediction value of a station in the Hubei region should be less than the third preset threshold, that is, it should be less than 80. The data in the (1, 27, 28) rows in the above table show that the power deviation prediction values ​​are all greater than 80. It can be seen that the risk level evaluation result of the electric field power prediction of a station in the Hubei region is a high risk case. There are deviations in the evaluation of a total of 3 days in the (1, 27, 28) rows, which is a deviation from the electric field power prediction. When the risk level is evaluated, the accuracy is 50% when the risk level is higher, that is, greater than or equal to level 1; and when the power deviation prediction value is less than the third preset threshold, that is, less than 80, the risk level of the electric field power prediction should be greater than the first preset threshold, that is, greater than 1. It can be seen that in the risk level evaluation of the electric field power prediction of a station in the Hubei region, the data of one day in row (16) does not meet this situation; therefore, the evaluation results of a total of 4 days (corresponding to the data in rows 1, 27, 28 and 16 in the above table) have deviations, and the overall accuracy of the risk level evaluation of the electric field power prediction is 86.67%. (The deviation in the data in row 10 in the above table is due to the icing of the wind turbine, resulting in lower actual power).

[0123] Figure 16 A block diagram illustrating a risk assessment apparatus for predicting electric field power generation according to an exemplary embodiment of the present disclosure.

[0124] Reference Figure 16 According to an exemplary embodiment of the present disclosure, the present disclosure further provides a risk assessment device 1600 for predicting electric field power generation. The risk assessment device 1600 may include a meteorological deviation model acquisition module 1601, a power deviation model acquisition module 1602, a deviation prediction value acquisition module 1603, and a risk level assessment module 1604.

[0125] The meteorological deviation model acquisition module 1601 can calculate the deviation value of the historical meteorological forecast data based on the actual meteorological data, and establish a meteorological deviation model according to the obtained deviation value;

[0126] The power deviation model acquisition module 1602 may calculate the accuracy value of the historical power prediction data based on the actual power data, and establish the power deviation model according to the obtained accuracy value;

[0127] The deviation prediction value acquisition module 1603 can input the current weather forecast data into the weather deviation model and the power deviation model respectively to obtain the weather deviation prediction value and the power deviation prediction value;

[0128] The risk level assessment module 1604 may assess the risk level of the electric field power prediction based on a preset assessment rule model and according to the meteorological deviation prediction value and the power deviation prediction value.

[0129] It can be understood that the various modules in the above-mentioned risk assessment device 1600 are used to implement the above-mentioned risk assessment method for electric field power generation prediction. The specific implementation process in the exemplary embodiment is roughly the same as the exemplary embodiment in the risk assessment method for electric field power generation prediction, and will not be repeated here. The risk assessment device 1600 can be configured as software, hardware, firmware or any combination of the above items to perform specific functions. For example, these devices may correspond to dedicated integrated circuits, pure software codes, or modules that combine software and hardware. In addition, one or more functions implemented by these devices may also be uniformly executed by components in physical entity devices (for example, processors, clients or servers, etc.).

[0130] Figure 17 A block diagram illustrating an electronic device according to an exemplary embodiment of the present disclosure.

[0131] Reference Figure 17 The electronic device 1700 includes at least one memory 1701 and at least one processor 1702. The at least one memory 1701 stores a set of computer-executable instructions. When the computer-executable instruction set is executed by the at least one processor 1702, the risk assessment method for predicting electric field power generation according to the exemplary embodiment of the present disclosure is executed.

[0132] As an example, the electronic device 1700 may be a PC, a tablet device, a personal digital assistant, a smart phone, or other device capable of executing the above-mentioned instruction set. Here, the electronic device 1700 is not necessarily a single electronic device, but may also be any device or circuit collection capable of executing the above-mentioned instructions (or instruction set) individually or in combination. The electronic device 1700 may also be part of an integrated control system or system manager, or may be configured as a portable electronic device interconnected with a local or remote (e.g., via wireless transmission) interface.

[0133] In electronic device 1700, processor 1702 may include a central processing unit (CPU), a graphics processing unit (GPU), a programmable logic device, a dedicated processor system, a microcontroller, or a microprocessor. By way of example and not limitation, the processor may also include an analog processor, a digital processor, a microprocessor, a multi-core processor, a processor array, a network processor, etc.

[0134] The processor 1702 may execute instructions or codes stored in the memory 1701, which may also store data. Instructions and data may also be sent and received over a network via a network interface device, which may employ any known transmission protocol.

[0135] The memory 1701 may be integrated with the processor 1702, for example, by placing RAM or flash memory within an integrated circuit microprocessor or the like. Furthermore, the memory 1701 may comprise a separate device, such as an external disk drive, a storage array, or any other storage device usable by a database system. The memory 1701 and the processor 1702 may be operatively coupled or may communicate with each other, for example, via an I / O port, a network connection, or the like, such that the processor 1702 can access files stored in the memory.

[0136] In addition, the electronic device 1700 may further include a video display (such as a liquid crystal display) and a user interaction interface (such as a keyboard, a mouse, a touch input device, etc.) All components of the electronic device 1700 may be connected to each other via a bus and / or a network.

[0137] In addition, the above-mentioned risk assessment method for electric field power generation prediction can be implemented by instructions recorded on a computer-readable storage medium. For example, according to an exemplary embodiment of the present disclosure, a computer-readable storage medium storing instructions can be provided, wherein, when the instructions are executed by at least one computing device, the at least one computing device is prompted to execute the above-mentioned risk assessment method for electric field power generation prediction.

[0138] Examples of computer-readable storage media include read-only memory (ROM), random-access programmable read-only memory (PROM), electrically erasable programmable read-only memory (EEPROM), random-access memory (RAM), dynamic random-access memory (DRAM), static random-access memory (SRAM), flash memory, non-volatile memory, CD-ROM, CD-R, CD+R, CD-RW, CD+RW, DVD-ROM, DVD-R, DVD+R, DVD-RW, DVD+RW, DVD-RAM, BD-ROM, BD-R, BD-R LTH, BD-RE, Blu-ray or optical disc storage, hard disk drive (HDD), solid state drive (SSD), card storage (such as, MultiMediaCard, Secure Digital (SD) card or Extreme Digital (XD) card), magnetic tape, floppy disk, magneto-optical data storage device, optical data storage device, hard disk, solid state disk and any other device, the any other device is configured to store the computer program and any associated data, data files and data structures in a non-transitory manner and provide the computer program and any associated data, data files and data structures to a processor or computer so that the processor or computer can execute the computer program.

[0139] The computer program in the computer-readable storage medium can be executed in an environment deployed in a computer device such as a client, a host, an agent device, or a server. In addition, in one example, the computer program and any associated data, data files, and data structures are distributed on a networked computer system, so that the computer program and any associated data, data files, and data structures are stored, accessed, and executed in a distributed manner by one or more processors or computers. It should be noted that the instructions can also be used to perform additional steps in addition to the above steps or to perform more specific processing when executing the above steps. The content of these additional steps and further processing has been mentioned in the description of the relevant methods, and therefore will not be repeated here to avoid repetition.

[0140] It should be noted that the risk assessment device for electric field power generation prediction according to the exemplary embodiment of the present disclosure can completely rely on the operation of computer programs or instructions to realize the corresponding functions, that is, each module corresponds to each step in the functional architecture of the computer program, so that the entire device is called through a special software package (for example, lib library) to realize the corresponding function.

[0141] On the other hand, when the above-mentioned risk assessment device for electric field power generation prediction is implemented in software, firmware, middleware or microcode, the program code or code segment for performing the corresponding operation can be stored in a computer-readable medium such as a storage medium, so that at least one processor or at least one computing device can perform the corresponding operation by reading and running the corresponding program code or code segment.

[0142] According to exemplary embodiments of the present disclosure, the storage device may be integrated with the computing device, for example, by placing RAM or flash memory within an integrated circuit microprocessor. Furthermore, the storage device may include a standalone device, such as an external disk drive, a storage array, or any other storage device usable by a database system. The storage device and the computing device may be operatively coupled or may communicate with each other, for example, via an I / O port, a network connection, or the like, such that the computing device can access instructions stored in the storage device.

[0143] According to the risk assessment method, device, electronic device and storage medium for electric field power generation prediction disclosed in the present invention, by combining a meteorological deviation model, a power deviation model and a preset assessment rule model to evaluate the risk level of electric field power prediction, the risk level of electric field power prediction obtained by the assessment can be used in a model or early warning for predicting and optimizing the power generation of the electric field, so as to optimize the power generation size of the electric field through automatic or human intervention, adjust the power generation of the electric field, and thus optimize the power generation prediction of the electric field to obtain a more accurate power generation prediction value of the electric field, thereby preventing the problem of poor stability of the power grid system caused by a large deviation between the power generation prediction value of the electric field and the actual required power generation value, thereby effectively controlling the accuracy of the power generation prediction of the electric field, and avoiding the occurrence of inaccurate planned power generation and substandard assessment of the electric field due to the accuracy of the power generation prediction of the electric field not meeting the standard; or the risk level of the power generation prediction of the electric field obtained by the assessment can be used in the forecast and adjustment of the power trading of the electric field station to maximize the profit of the station.

[0144] In addition, when establishing the meteorological deviation model and the power deviation model, the data set is classified into two-dimensional features and then the deviation value and accuracy value are statistically calculated. This combines the probabilistic statistical thinking of big data with meteorological analysis, thereby improving the accuracy of the risk level assessment of the electric field power forecast.

[0145] In addition, the obtained meteorological risk level can be used for early warning of meteorological forecasts when the deviation is large, thereby facilitating the analysis of the problem and optimizing the method of predicting meteorological data; the obtained power risk level can be used for early warning of electric field power generation predictions when the accuracy is low, thereby facilitating the analysis of the problem and optimizing the method of predicting electric field power generation.

[0146] In addition, correcting the risk level according to the statistical characteristic value can further improve the accuracy of evaluating the risk level of the electric field power prediction when the meteorological risk level is greater than or equal to the first preset threshold.

[0147] While various exemplary embodiments of the present disclosure have been described above, it should be understood that the foregoing description is merely illustrative and not exhaustive, and the present disclosure is not limited to the disclosed exemplary embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the present disclosure. Therefore, the scope of protection of the present disclosure should be determined by the scope of the claims.

Claims

1. A risk assessment method for electric field power generation prediction, characterized in that: The method comprises: Calculate the deviation value of historical meteorological forecast data based on actual meteorological data, and establish a meteorological deviation model based on the obtained deviation value; Establishing a power prediction model based on the historical weather forecast data and actual power data; Inputting the historical meteorological forecast data into the power forecast model to obtain power forecast data; Calculating the accuracy value of the power prediction data based on the actual power data, and establishing a power deviation model according to the obtained accuracy value; Inputting current weather forecast data into the weather deviation model and the power deviation model respectively to obtain a weather deviation prediction value and a power deviation prediction value; Determine the meteorological risk level and the power risk level corresponding to the meteorological deviation prediction value and the power deviation prediction value respectively according to a preset evaluation rule model; An evaluation result of the risk level of electric field power prediction is determined according to numerical calculation results of the meteorological risk level and the power risk level.

2. The risk assessment method according to claim 1, wherein: The calculation of the deviation value of the historical meteorological forecast data based on the actual meteorological data and the establishment of a meteorological deviation model according to the obtained deviation value include: Classifying the corresponding actual meteorological data and the historical meteorological forecast data according to the preset time period, and then classifying them again according to the preset magnitude segment; In each type of classified data set, the deviation value of the historical meteorological forecast data is calculated based on the actual meteorological data, and the meteorological deviation model is established according to the obtained deviation value.

3. The risk assessment method according to claim 1, wherein: The calculating the accuracy value of the power prediction data based on the actual power data, and establishing the power deviation model according to the obtained accuracy value, includes: Using the time information and magnitude information in the historical meteorological forecast data as a reference, the corresponding power forecast data and the actual power data are classified according to the preset time period and then classified again according to the preset magnitude segment; In each type of data set after classification, the accuracy value of the power prediction data is calculated based on the actual power data, and the power deviation model is established according to the obtained accuracy value.

4. The risk assessment method according to claim 1, wherein: The step of inputting the current weather forecast data into the weather deviation model and the power deviation model respectively to obtain a weather deviation prediction value and a power deviation prediction value comprises: Classifying the current weather forecast data according to the preset time periods and then classifying the data according to the preset magnitude segments; Each type of classified data set is input into the meteorological deviation model and the power deviation model respectively to obtain the meteorological deviation prediction value and the power deviation prediction value.

5. The risk assessment method according to claim 1, wherein: The method further comprises: Calculating the statistical characteristic values ​​of the current meteorological forecast data, and revising the assessment result of the risk level of the electric field power forecast according to the statistical characteristic values; The step of correcting the risk level assessment result of the electric field power prediction according to the statistical characteristic value includes: When the meteorological risk level is greater than or equal to the first preset threshold, if the variance value in the statistical characteristic value is less than the second preset threshold, and the power deviation prediction value is greater than or equal to the third preset threshold, it is determined that the evaluation result of the risk level of the electric field power prediction is less than the fourth preset threshold.

6. The risk assessment method according to any one of claims 1 to 5, wherein: The method further includes revising the historical weather forecast data and the current weather forecast data, wherein the revising step includes: Establishing a weather correction model based on the historical weather forecast data and the actual weather data; The historical weather forecast data and the current weather forecast data are respectively input into the weather correction model to obtain the revised historical weather forecast data and the current weather forecast data.

7. A risk assessment device for predicting electric field power generation, characterized in that: The device comprises: The meteorological deviation model acquisition module is configured to: calculate the deviation value of the historical meteorological forecast data based on the actual meteorological data, and establish the meteorological deviation model according to the obtained deviation value; The power deviation model acquisition module is configured to: establish a power prediction model based on the historical meteorological forecast data and the actual power data; input the historical meteorological forecast data into the power prediction model to obtain power prediction data; calculate the accuracy value of the power prediction data based on the actual power data, and establish a power deviation model according to the obtained accuracy value; The deviation prediction value acquisition module is configured to: input current weather forecast data into the weather deviation model and the power deviation model respectively to obtain a weather deviation prediction value and a power deviation prediction value; The risk level assessment module is configured to: determine the meteorological risk level and power risk level corresponding to the meteorological deviation prediction value and the power deviation prediction value respectively according to a preset assessment rule model; and determine the assessment result of the risk level of the electric field power prediction based on the numerical calculation results of the meteorological risk level and the power risk level.

8. An electronic device, characterized in that: include: at least one processor; at least one memory storing computer-executable instructions, Wherein, when the computer executable instructions are executed by the at least one processor, the at least one processor is prompted to perform the risk assessment method according to any one of claims 1 to 6.

9. A computer-readable storage medium storing instructions, characterized in that: When the instructions are executed by at least one processor, the at least one processor is prompted to perform the risk assessment method according to any one of claims 1 to 6.

Images