A manufacturer evaluation method based on a power plant power prediction system

Abstract

The present invention discloses a manufacturer evaluation method based on a power plant power prediction system, which relates to the technical field of power prediction. The method includes determining the basic information corresponding to the attributes of each station; determining the basic information corresponding to the attributes of the station to be predicted; determining the matching degree between the station to be predicted and each other station according to the basic information corresponding to the attributes of each station and the basic information corresponding to the attributes of the station to be predicted; taking the station with the highest matching degree as the main station, and taking the stations with a matching degree exceeding the matching degree threshold as auxiliary stations; obtaining the historical power prediction records of the main station and the auxiliary stations, and defining the power prediction period; receiving the power prediction results of each manufacturer for the station to be predicted; and comparing the power prediction results of each manufacturer based on the power prediction period and the evaluation rules to select manufacturers. This helps to compare and analyze the accuracy of the power predictions of each manufacturer, thereby improving the evaluation accuracy and better adapting to the complex and changeable situations of the stations.

Description

Technical Field

[0001] This application relates to the technical field of power prediction, and more specifically, to a manufacturer evaluation method based on a power plant power prediction system. Background Art

[0002] With the development of the energy industry and the increasingly fierce competition in the power market, power plants need to accurately predict future power demands in order to make reasonable power generation plans and dispatching decisions. Therefore, establishing an effective power plant power prediction system has become one of the urgent needs of power manufacturers. However, in order to ensure the reliability and accuracy of the system, power manufacturers need to evaluate the power prediction systems of different manufacturers.

[0003] In the prior art, since power stations are greatly affected by the outside world, the measured power may not be the actual power. As a result, when comparing the power prediction results given by each manufacturer, the accuracy of the evaluation is low, which cannot help the power station to operate accurately and for future layout.

[0004] Therefore, how to improve the accuracy of manufacturer evaluation is a technical problem to be solved at present. Summary of the Invention

[0005] The present invention provides a manufacturer evaluation method based on a power plant power prediction system to solve the technical problem of low accuracy of manufacturer evaluation in the prior art. The method includes:

[0006] Obtain the basic information of the power stations, divide the basic information of the power stations according to attributes, and determine the basic information corresponding to the attributes of each power station;

[0007] Obtain the basic information of the power station to be predicted, divide the basic information of the power station to be predicted according to attributes, and determine the basic information corresponding to the attributes of the power station to be predicted;

[0008] Determine the matching degree between the power station to be predicted and each other power station according to the basic information corresponding to the attributes of each power station and the basic information corresponding to the attributes of the power station to be predicted;

[0009] Take the power station with the highest matching degree as the main power station, and take the power stations with a matching degree exceeding the matching degree threshold as auxiliary power stations;

[0010] Obtain the historical power prediction records of the main power station and the auxiliary power stations, and define the power prediction period;

[0011] Receive the power prediction results of each manufacturer for the power station to be predicted, and obtain the external influencing factors of the main power station and the auxiliary power stations;

[0012] Formulate an evaluation rule according to the external influencing factors of the main power station and the auxiliary power stations, and compare the power prediction results of each manufacturer based on the power prediction period and the evaluation rule to select manufacturers.

[0013] In some embodiments of the present application, the basic information of the stations is divided according to attributes, and the basic information corresponding to the attributes of each station is determined, including:

[0014] After dividing the basic information of the stations according to attributes, the basic information includes climate information, geographical information, resource information, and station scale information;

[0015] Other information is obtained, and the comprehensive relevance of the other information to the climate information, geographical information, resource information, and station scale information is determined respectively;

[0016] The other information is divided into the climate information, geographical information, resource information, and station scale information according to the comprehensive relevance.

[0017] In some embodiments of the present application, dividing the other information into the climate information, geographical information, resource information, and station scale information according to the comprehensive relevance includes:

[0018] The other information with a comprehensive relevance greater than the first relevance threshold is divided into the corresponding basic information;

[0019] The other information with a comprehensive relevance greater than the second relevance threshold and not greater than the first relevance threshold is recorded as information to be investigated;

[0020] The average value of the first relevance threshold and the second relevance threshold is used as the relevance average value. If the comprehensive relevance of the information to be investigated exceeds the relevance average value, the information to be investigated is divided into the corresponding basic information;

[0021] Otherwise, the information to be investigated is not divided into the corresponding basic information.

[0022] In some embodiments of the present application, determining the matching degree between the station to be predicted and each other station according to the basic information corresponding to the attributes of each station and the basic information corresponding to the attributes of the station to be predicted includes:

[0023] The climate information, geographical information, resource information, and station scale information of each station are respectively recorded as the first positive information, the second positive information, the third positive information, and the fourth positive information, and the climate information, geographical information, resource information, and station scale information of the station to be predicted are respectively recorded as the first negative information, the second negative information, the third negative information, and the fourth negative information;

[0024] The first positive information, the second positive information, the third positive information, and the fourth positive information respectively correspond to the first negative information, the second negative information, the third negative information, and the fourth negative information;

[0025] Calculate the matching degrees of the first positive information and the first negative information, the second positive information and the second negative information, the third positive information and the third negative information, and the fourth positive information and the fourth negative information respectively, and denote them as the first sub-matching degree, the second sub-matching degree, the third sub-matching degree, and the fourth sub-matching degree;

[0026] Determine the comprehensive matching degree based on the first sub-matching degree, the second sub-matching degree, the third sub-matching degree, and the fourth sub-matching degree.

[0027] In some embodiments of the present application, the station with the highest matching degree is used as the main station, and the stations with a matching degree exceeding the matching degree threshold are used as auxiliary stations, including:

[0028] The stations with the first sub-matching degree, the second sub-matching degree, the third sub-matching degree, and the fourth sub-matching degree all exceeding their respective corresponding thresholds are used as the first stations;

[0029] Sort the multiple first stations according to the comprehensive matching degree, use the first station ranked first as the main station, and use the stations ranked within the preset range as auxiliary stations;

[0030] If the first sub-matching degree, the second sub-matching degree, the third sub-matching degree, and the fourth sub-matching degree do not all exceed their respective corresponding thresholds, determine the auxiliary stations according to the number of sub-matching degrees exceeding the corresponding thresholds and the comprehensive matching degree.

[0031] In some embodiments of the present application, obtain the historical power prediction records of the main station and the auxiliary stations, and define the power prediction period, including:

[0032] The historical power prediction records include short-term power prediction, medium-term power prediction, and long-term power prediction;

[0033] Screen out the shortest time and the longest time corresponding to the short-term power prediction, medium-term power prediction, and long-term power prediction respectively, and screen out a time with the highest occurrence frequency between the shortest time and the longest time as the intermediate time;

[0034] Calculate the distances between the intermediate time and the shortest time, and the longest time respectively, and update the shortest time or the longest time according to the longer end of the distance to obtain the predicted power period.

[0035] In some embodiments of the present application, formulate an evaluation rule according to the external influencing factors of the main station and the auxiliary stations, including:

[0036] Based on the external influencing factors of the main station and the auxiliary stations, establish the first influence array and the second influence array respectively;

[0037] Based on the first influence array, the second influence array, and the measured power, specify the evaluation rule.

[0038] In some embodiments of the present application, a first influence array and a second influence array are established based on the external influence factors of the main station and the auxiliary station, including:

[0039] Obtain each external influence factor of the main station and the auxiliary station, compare the size of each external influence factor with a preset value, so as to determine the magnitude of the influence of each external influence factor;

[0040] Retain the external influence factors whose influence amount exceeds the influence amount threshold, and sort them according to the magnitude of the influence amount, so as to construct the first influence array and the second influence array, and assign different weights to the first influence array and the second influence array.

[0041] In some embodiments of the present application, an evaluation rule is specified based on the first influence array, the second influence array and the measured power, including:

[0042] Obtain the first influence amount and the second influence amount according to the first influence array and the second influence array respectively, and correct the measured power based on the first influence amount, the second influence amount and their respective weights to obtain the actual power.

[0043] In some embodiments of the present application, based on the power prediction period and the evaluation rule, compare the power prediction results of each manufacturer, and select manufacturers, including:

[0044] Compare the deviation between the power prediction result and the actual power of the same manufacturer in the three time periods of short-term power prediction, medium-term power prediction and long-term power prediction, so as to obtain the first score;

[0045] Compare the deviation between the power prediction results and the actual power of different manufacturers in the same power prediction period, so as to obtain the second score;

[0046] Determine the manufacturer score based on the first score and the second score, and screen suitable manufacturers for power prediction.

[0047] By applying the above technical solutions, the basic information of the station is obtained, and the basic information of the station is divided according to attributes to determine the basic information corresponding to the attributes of each station; the basic information of the station to be predicted is obtained, and the basic information of the station to be predicted is divided according to attributes to determine the basic information corresponding to the attributes of the station to be predicted; the matching degree between the station to be predicted and each other station is determined according to the basic information corresponding to the attributes of each station and the basic information corresponding to the attributes of the station to be predicted; the station with the highest matching degree is used as the main station, and the stations with a matching degree exceeding the matching degree threshold are used as auxiliary stations; the historical power prediction records of the main station and the auxiliary stations are obtained, and the power prediction period is defined; the power prediction results of each manufacturer for the station to be predicted are received, and the external influencing factors of the main station and the auxiliary stations are obtained; an evaluation rule is formulated according to the external influencing factors of the main station and the auxiliary stations, and the power prediction results of each manufacturer are compared based on the power prediction period and the evaluation rule to select manufacturers. In this application, the main station and the auxiliary stations are divided according to the basic information corresponding to the attributes of the station, so as to formulate corresponding evaluation rules, help to compare and analyze the accuracy of the power prediction of each manufacturer, thereby improving the evaluation accuracy and being more adaptable to the complex and changeable situations of the station. Brief Description of the Drawings

[0048] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the accompanying drawings required for the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative efforts.

[0049] Figure 1 The flowchart showing a method for evaluating manufacturers based on a power plant power prediction system according to an embodiment of the present invention is shown. Detailed Embodiments

[0050] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0051] An embodiment of the present application provides a method for evaluating manufacturers based on a power plant power prediction system, as Figure 1 shown, the method includes the following steps:

[0052] Step S101, obtain the basic information of the station, and divide the basic information of the station according to attributes to determine the basic information corresponding to the attributes of each station.

[0053] In this embodiment, the basic information of the station here does not include the station to be predicted, which facilitates subsequent comparison. The station to be predicted is analyzed more accurately through the information of other stations.

[0054] In this embodiment, the basic information of the station is the location information, terrain information, etc. of the electric station. After dividing the basic information of the station according to attributes, the basic information includes climate information, geographical information, resource information, and station scale information. Dividing the basic information of the station according to attributes means which of the original stations belong to climate information, geographical information, resource information, and station scale information, etc. Although other relevant information is not within this definition, it is closely related to it and needs to be screened and divided.

[0055] In some embodiments of the present application, the basic information of the station is divided according to attributes, and the basic information corresponding to the attributes of each station is determined, including:

[0056] After dividing the basic information of the station according to attributes, the basic information includes climate information, geographical information, resource information, and station scale information;

[0057] Other information is obtained, and the comprehensive relevance of the other information to climate information, geographical information, resource information, and station scale information is determined respectively;

[0058] The other information is divided into climate information, geographical information, resource information, and station scale information according to the comprehensive relevance.

[0059] In some embodiments of the present application, dividing the other information into climate information, geographical information, resource information, and station scale information according to the comprehensive relevance includes:

[0060] The other information with a comprehensive relevance greater than the first relevance threshold is divided into the corresponding basic information;

[0061] The other information with a comprehensive relevance greater than the second relevance threshold and not greater than the first relevance threshold is recorded as information to be investigated;

[0062] The average value of the first relevance threshold and the second relevance threshold is used as the relevance average value. If the comprehensive relevance of the information to be investigated exceeds the relevance average value, the information to be investigated is divided into the corresponding basic information;

[0063] Otherwise, the information to be investigated is not divided into the corresponding basic information.

[0064] In this embodiment, each of the climate information, geographical information, resource information, and station scale information includes many kinds of data.

[0065] In this embodiment, if the comprehensive relevance is greater than the first relevance threshold, it indicates a relatively high relevance and can be classified into the corresponding basic information. If the comprehensive relevance is greater than the second relevance threshold and not greater than the first relevance threshold, it indicates an average relevance, not too high. Further screening is required here. If it exceeds the average value, it will be classified into the corresponding basic information.

[0066] Step S102: Obtain the basic information of the to-be-predicted station and classify the basic information of the to-be-predicted station according to attributes to determine the basic information corresponding to the attributes of the to-be-predicted station.

[0067] In this embodiment, the steps for the basic information corresponding to the attributes of the to-be-predicted station are the same as those in step S101.

[0068] Step S103: Determine the matching degree between the to-be-predicted station and each other station according to the basic information corresponding to the attributes of each station and the basic information corresponding to the attributes of the to-be-predicted station.

[0069] In some embodiments of the present application, determining the matching degree between the to-be-predicted station and each other station according to the basic information corresponding to the attributes of each station and the basic information corresponding to the attributes of the to-be-predicted station includes:

[0070] Record the climate information, geographical information, resource information, and station scale information of each station as the first positive information, second positive information, third positive information, and fourth positive information respectively, and record the climate information, geographical information, resource information, and station scale information of the to-be-predicted station as the first negative information, second negative information, third negative information, and fourth negative information respectively;

[0071] The first positive information, second positive information, third positive information, and fourth positive information respectively correspond to the first negative information, second negative information, third negative information, and fourth negative information;

[0072] Calculate the matching degree between the first positive information and the first negative information, the matching degree between the second positive information and the second negative information, the matching degree between the third positive information and the third negative information, and the matching degree between the fourth positive information and the fourth negative information, and record them as the first sub-matching degree, second sub-matching degree, third sub-matching degree, and fourth sub-matching degree;

[0073] Determine the comprehensive matching degree based on the first sub-matching degree, second sub-matching degree, third sub-matching degree, and fourth sub-matching degree.

[0074] Step S104: Use the station with the highest matching degree as the main station, and use the stations with a matching degree exceeding the matching degree threshold as auxiliary stations.

[0075] In some embodiments of the present application, using the station with the highest matching degree as the main station and using the stations with a matching degree exceeding the matching degree threshold as auxiliary stations includes:

[0076] Take the stations where the first sub - matching degree, the second sub - matching degree, the third sub - matching degree, and the fourth sub - matching degree all exceed their respective corresponding thresholds as the first - stage stations;

[0077] Sort the multiple first - stage stations according to the comprehensive matching degree, take the first - ranked first - stage station as the main station, and take the stations within the preset range as the auxiliary stations;

[0078] If the first sub - matching degree, the second sub - matching degree, the third sub - matching degree, and the fourth sub - matching degree do not all exceed their respective corresponding thresholds, determine the auxiliary stations according to the number of sub - matching degrees exceeding the corresponding thresholds and the comprehensive matching degree.

[0079] In this embodiment, the highest matching degree here means that each sub - matching degree is qualified and the comprehensive matching degree is the highest, and the corresponding station is the main station. The main station is the closest to the station to be predicted, and the auxiliary stations are relatively close to the station to be predicted. This is convenient for the subsequent evaluation of power prediction.

[0080] In this embodiment, determining the auxiliary stations according to the number of sub - matching degrees exceeding the corresponding thresholds and the comprehensive matching degree means that different numbers correspond to different comprehensive matching degrees. If it exceeds this matching degree, it can be used as an auxiliary station; otherwise, it cannot.

[0081] Step S105, obtain the historical power prediction records of the main station and the auxiliary stations, and define the power prediction period.

[0082] In this embodiment, in order to facilitate the comparison of power prediction accuracy, the power prediction period is limited and standardized. This avoids errors caused by different time lengths.

[0083] In this embodiment, short - term power prediction: Short - term power prediction usually refers to predicting the power within the next few hours, such as predicting the power within the next 1 hour, 3 hours, or 6 hours. The time interval for this prediction can be from a few minutes to dozens of minutes. Medium - term power prediction: Medium - term power prediction generally predicts the power within the next few days to a week, such as predicting the power within the next 24 hours, 48 hours, or 7 days. The time interval can be from dozens of minutes to several hours. Long - term power prediction: Long - term power prediction usually refers to predicting the power in the next few weeks, months, or years. The time interval can be from several hours to several days. In order to unify the time - length standard and avoid the situation of inconsistent time lengths, the period is defined.

[0084] In some embodiments of the present application, obtaining the historical power prediction records of the main station and the auxiliary stations and defining the power prediction period includes:

[0085] The historical power prediction records include short - term power prediction, medium - term power prediction, and long - term power prediction;

[0086] Screen out the shortest time and the longest time corresponding to short-term power prediction, medium-term power prediction, and long-term power prediction respectively, and screen out a time with the highest frequency of occurrence between the shortest time and the longest time as the intermediate time;

[0087] Calculate the distances between the intermediate time and the shortest time, and the longest time respectively. Update the shortest time or the longest time according to the longer end of the distance to obtain the predicted power period.

[0088] In this embodiment, the shortest time or the longest time is updated according to the longer end of the distance. For example, the shortest time is a0, the longest time is a2, and the intermediate time is a1. The distance between a1 and a2 is the longest. Determine a correction coefficient f according to the magnitude of a2 - a1, and correct a0. The updated shortest time is the corrected a0 * f.

[0089] Step S106: Receive the power prediction results of each manufacturer for the power station to be predicted, and obtain the external influencing factors of the main power station and the auxiliary power station.

[0090] In this embodiment, the external influencing factors are humidity, temperature, wind speed, etc. There are certain errors in the measured power of the power station, and these errors are usually caused by these external influencing factors. Therefore, modifications need to be made accordingly.

[0091] Step S107: Formulate an evaluation rule according to the external influencing factors of the main power station and the auxiliary power station, and compare the power prediction results of each manufacturer based on the power prediction period and the evaluation rule to select manufacturers.

[0092] In some embodiments of the present application, formulating an evaluation rule according to the external influencing factors of the main power station and the auxiliary power station includes:

[0093] Respectively establish a first influence array and a second influence array based on the external influencing factors of the main power station and the auxiliary power station;

[0094] Specify an evaluation rule based on the first influence array, the second influence array, and the measured power.

[0095] In some embodiments of the present application, respectively establishing a first influence array and a second influence array based on the external influencing factors of the main power station and the auxiliary power station includes:

[0096] Obtain each external influencing factor of the main power station and the auxiliary power station, compare the magnitude of each external influencing factor with a preset value, so as to determine the magnitude of the influence amount of each external influencing factor;

[0097] Retain the external influencing factors whose influence amount exceeds the influence amount threshold, and sort them according to the magnitude of the influence amount, so as to construct the first influence array and the second influence array, and assign different weights to the first influence array and the second influence array.

[0098] In this embodiment, the preset value is a range value. If it is below or above this range, it indicates that there is an additional impact on the power.

[0099] In this embodiment, the first impact array (s0, s1,..., sn), where the parameters are the impact amounts, is used to determine the total first impact amount and the second impact amount.

[0100] In some embodiments of the present application, based on the first impact array, the second impact array, and the measured power, an evaluation rule is specified, including:

[0101] The first impact amount and the second impact amount are obtained from the first impact array and the second impact array respectively, and the measured power is corrected based on the first impact amount, the second impact amount, and their respective weights to obtain the actual power.

[0102] In this embodiment, the first impact amount and the second impact amount are q1 and q2 respectively, the corresponding weights are μ1 and μ2 respectively, the total impact amount is = μ1q1 + q2μ2, and each total impact amount corresponds to a correction coefficient. The product of this correction coefficient and the measured power is the actual power.

[0103] In some embodiments of the present application, based on the power prediction period and the evaluation rule, the power prediction results of each manufacturer are compared to select manufacturers, including:

[0104] The deviation between the power prediction result and the actual power of the same manufacturer is compared in three time periods: short-term power prediction, medium-term power prediction, and long-term power prediction, so as to obtain the first score;

[0105] The deviation between the power prediction results and the actual power of different manufacturers is compared in the same power prediction period, so as to obtain the second score;

[0106] Based on the first score and the second score, the manufacturer score is determined, and suitable manufacturers are selected for power prediction.

[0107] In this embodiment, when comparing the power prediction results of multiple manufacturers, horizontal comparison and vertical comparison are performed. Horizontal comparison means that in the same power prediction period, for example, short-term power prediction, the deviation between the power prediction results of different manufacturers and the actual power is compared. Vertical comparison means that in different power prediction periods, the deviation between the power prediction results of the same manufacturer and the actual power is compared. The accuracy of the power prediction of the overall manufacturer is determined by combining horizontal comparison and vertical comparison.

[0108] It should be noted that the smaller the deviation between the power prediction result of the manufacturer and the actual power, the higher the score.

[0109] By applying the above technical solutions, the basic information of the station is obtained, and the basic information of the station is divided according to the attributes to determine the basic information corresponding to the attributes of each station; the basic information of the station to be predicted is obtained, and the basic information of the station to be predicted is divided according to the attributes to determine the basic information corresponding to the attributes of the station to be predicted; the matching degree between the station to be predicted and each other station is determined according to the basic information corresponding to the attributes of each station and the basic information corresponding to the attributes of the station to be predicted; the station with the highest matching degree is used as the main station, and the stations with a matching degree exceeding the matching degree threshold are used as auxiliary stations; the historical power prediction records of the main station and the auxiliary stations are obtained, and the power prediction period is defined; the power prediction results of each manufacturer for the station to be predicted are received, and the external influencing factors of the main station and the auxiliary stations are obtained; an evaluation rule is formulated according to the external influencing factors of the main station and the auxiliary stations, and the power prediction results of each manufacturer are compared based on the power prediction period and the evaluation rule to select manufacturers. In this application, the main station and the auxiliary stations are divided according to the basic information corresponding to the attributes of the station, so as to formulate corresponding evaluation rules, which helps to compare and analyze the accuracy of the power prediction of each manufacturer, thereby improving the evaluation accuracy and being more adaptable to the complex and changeable conditions of the station.

[0110] Through the description of the above embodiments, those skilled in the art can clearly understand that the present invention can be implemented by hardware or by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), including several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in various implementation scenarios of the present invention.

[0111] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, and are not intended to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the various embodiments of the present application.

Claims

1. A manufacturer evaluation method based on a power plant power prediction system, characterized in that, The method includes: Obtain the basic information of the stations, divide the basic information of the stations according to attributes, and determine the basic information corresponding to the attributes of each station; Obtain the basic information of the station to be predicted, divide the basic information of the station to be predicted according to attributes, and determine the basic information corresponding to the attributes of the station to be predicted; Determine the matching degree between the station to be predicted and each other station according to the basic information corresponding to the attributes of each station and the basic information corresponding to the attributes of the station to be predicted; Take the station with the highest matching degree as the main station, and the stations with a matching degree exceeding the matching degree threshold as auxiliary stations; Obtain the historical power prediction records of the main station and the auxiliary stations, and define the power prediction period; Receive the power prediction results of the station to be predicted from each manufacturer, and obtain the external influencing factors of the main station and the auxiliary stations; Formulate an evaluation rule according to the external influencing factors of the main station and the auxiliary stations, and compare the power prediction results of each manufacturer based on the power prediction period and the evaluation rule to select manufacturers; Obtain the historical power prediction records of the main station and the auxiliary stations, and define the power prediction period, including: The historical power prediction records include short-term power prediction, medium-term power prediction and long-term power prediction; Screen out the shortest time and the longest time corresponding to the short-term power prediction, medium-term power prediction and long-term power prediction respectively, and select a time with the highest frequency of occurrence between the shortest time and the longest time as the intermediate time; Calculate the distances between the intermediate time and the shortest time and the longest time respectively, and update the shortest time or the longest time according to the longer end of the distance to obtain the predicted power period; Formulate an evaluation rule according to the external influencing factors of the main station and the auxiliary stations, including: Respectively establish a first influence array and a second influence array based on the external influencing factors of the main station and the auxiliary stations; Formulate an evaluation rule based on the first influence array, the second influence array and the measured power; Respectively establish a first influence array and a second influence array based on the external influencing factors of the main station and the auxiliary stations, including: Obtain each external influencing factor of the main station and the auxiliary stations, compare the size of each external influencing factor with a preset value, so as to determine the size of the influence amount of each external influencing factor; Retain the external influencing factors whose influence amount exceeds the influence amount threshold, and sort them according to the size of the influence amount, so as to construct the first influence array and the second influence array, and assign different weights to the first influence array and the second influence array; Formulate an evaluation rule based on the first influence array, the second influence array and the measured power, including: Obtain the first influence amount and the second influence amount according to the first influence array and the second influence array respectively, and correct the measured power based on the first influence amount, the second influence amount and their respective weights to obtain the actual power.

2. The manufacturer evaluation method based on the power plant power prediction system according to claim 1, characterized in that, And divide the basic information of the stations according to attributes, and determine the basic information corresponding to the attributes of each station, including: After dividing the basic information of the stations according to attributes, the basic information includes climate information, geographical information, resource information and station scale information; Obtain other information, and determine the comprehensive relevance of other information to the climate information, geographical information, resource information and station scale information respectively; Other information is classified into climate information, geographical information, resource information, and station scale information according to the comprehensive relevance.

3. The manufacturer evaluation method based on the power plant power prediction system according to claim 2, wherein Other information is classified into climate information, geographical information, resource information, and station scale information according to the comprehensive relevance, including: Other information with a comprehensive relevance greater than the first relevance threshold is classified into the corresponding basic information; Other information with a comprehensive relevance greater than the second relevance threshold and not greater than the first relevance threshold is recorded as information to be investigated; The average value of the first relevance threshold and the second relevance threshold is used as the average relevance. If the comprehensive relevance of the information to be investigated exceeds the average relevance, the information to be investigated is classified into the corresponding basic information; Otherwise, the information to be investigated is not classified into the corresponding basic information.

4. The manufacturer evaluation method based on the power plant power prediction system according to claim 2, characterized in that The matching degree between the station to be predicted and each other station is determined according to the basic information corresponding to the attributes of each station and the basic information corresponding to the attributes of the station to be predicted, including: The climate information, geographical information, resource information, and station scale information of each station are respectively recorded as the first positive information, the second positive information, the third positive information, and the fourth positive information, and the climate information, geographical information, resource information, and station scale information of the station to be predicted are respectively recorded as the first negative information, the second negative information, the third negative information, and the fourth negative information; The first positive information, the second positive information, the third positive information, and the fourth positive information respectively correspond to the first negative information, the second negative information, the third negative information, and the fourth negative information; The matching degrees between the first positive information and the first negative information, the second positive information and the second negative information, the third positive information and the third negative information, and the fourth positive information and the fourth negative information are calculated respectively, and are recorded as the first sub-matching degree, the second sub-matching degree, the third sub-matching degree, and the fourth sub-matching degree; The comprehensive matching degree is determined based on the first sub-matching degree, the second sub-matching degree, the third sub-matching degree, and the fourth sub-matching degree.

5. The manufacturer evaluation method based on the power plant power prediction system according to claim 4, characterized in that, The station with the highest matching degree is used as the main station, and the stations with a matching degree exceeding the matching degree threshold are used as auxiliary stations, including: The stations with the first sub-matching degree, the second sub-matching degree, the third sub-matching degree, and the fourth sub-matching degree all exceeding their respective corresponding thresholds are used as the first stations; The multiple first stations are sorted according to the comprehensive matching degree, the first-ranked first station is used as the main station, and the stations within the preset range are used as auxiliary stations; If the first sub-matching degree, the second sub-matching degree, the third sub-matching degree, and the fourth sub-matching degree do not all exceed their respective corresponding thresholds, the auxiliary stations are determined according to the number of sub-matching degrees exceeding the corresponding thresholds and the comprehensive matching degree.

6. The manufacturer evaluation method based on the power plant power prediction system according to claim 1, characterized in that, And based on the power prediction period and the evaluation rules, the power prediction results of each manufacturer are compared to select manufacturers, including: The deviations between the power prediction results and the actual power of the same manufacturer are compared in the three time periods of short-term power prediction, medium-term power prediction, and long-term power prediction, so as to obtain the first score; In the same power prediction period, the deviations between the power prediction results and the actual power of different manufacturers are compared, so as to obtain the second score; The manufacturer score is determined based on the first score and the second score, and suitable manufacturers are selected for power prediction.

Images