Recommendation methods, devices and equipment for multi-source power prediction data of new energy

Abstract

This invention relates to the field of power technology, specifically to a method, apparatus, and equipment for recommending multi-source power prediction data for new energy sources. The method includes: acquiring basic data including the name of the power prediction vendor, short-term power prediction data within a target time range, ultra-short-term power prediction data, available power plant capacity, and actual power output of the power plant; based on the basic data, calculating the accuracy rates of single-point ultra-short-term power prediction, daily ultra-short-term power prediction, daily spot power prediction, and daily two-way power prediction within the target time range for each power prediction vendor, and ranking and scoring them accordingly; and recommending power prediction vendors and their power prediction data based on the ranking and scoring results for different prediction types. In this way, suitable power prediction vendors and power prediction data can be quickly recommended to new energy enterprises for different prediction types.

Description

Technical Field

[0001] This invention relates to the field of power technology, specifically to a method, apparatus, and equipment for recommending multi-source power prediction data for new energy sources. Background Technology

[0002] With the continuous increase in the proportion of new energy grid connection, accurate power forecasting has become an important basis for formulating unit power generation plans and enhancing the capacity for new energy consumption. Accurate power forecasting can help new energy power plants to rationally arrange power generation plans, thereby avoiding the phenomenon of wind and solar curtailment caused by excessive power generation.

[0003] In practical applications, on the one hand, power forecasting results can serve as a basis for participating in the electricity spot market, helping new energy companies formulate relevant strategies. On the other hand, assessing the accuracy of power forecasting reports is a crucial aspect of the power industry, especially in the field of renewable energy generation, such as wind and solar power. Accurate power forecasting helps maintain the balance of the power system, avoiding instability caused by supply and demand imbalances. Relevant dispatch centers can adjust dispatch plans in advance based on forecasting results, optimize grid operation, and improve resource utilization efficiency. Therefore, ensuring the accuracy of power forecasting is of paramount importance to these new energy companies.

[0004] In existing technologies, new energy companies generally use the forecast data provided by power forecasting companies directly. However, faced with multiple power forecasting companies and a large amount of forecast data, they cannot reasonably and efficiently determine the accuracy of the power forecasts provided by the power forecasting companies, thus affecting their selection of power forecasting companies and their related strategy formulation and reporting work. Summary of the Invention

[0005] In view of this, the purpose of the present invention is to provide a method, apparatus and equipment for recommending multi-source power prediction data for new energy, so as to overcome the problem that new energy companies are unable to make reasonable choices when faced with a large number of power prediction manufacturers.

[0006] To achieve the above objectives, the present invention adopts the following technical solution:

[0007] Firstly, this application provides a method for recommending multi-source power prediction data for new energy sources, including:

[0008] Basic data is obtained through an interface. The basic data includes the name of the power prediction vendor, short-term power prediction data within the target time range, ultra-short-term power prediction data, available capacity of power plants, and actual power of power plants. The short-term power prediction data and ultra-short-term power prediction data are provided by the power prediction vendor, and the available capacity of power plants and actual power of power plants are provided by the new energy power plants.

[0009] Based on the aforementioned basic data, calculate the single-point ultra-short-term power prediction accuracy, single-day ultra-short-term power prediction accuracy, single-day spot power prediction accuracy, and single-day two-way power prediction accuracy for each power prediction vendor within the target time range.

[0010] Based on the single-point ultra-short-term power prediction accuracy corresponding to at least one pre-selected time in each day within the target time range, the power prediction vendors are ranked according to their single-point ultra-short-term power prediction accuracy, and a preset score is calculated for the power prediction vendor ranked first at each pre-selected time.

[0011] Based on the daily ultra-short-term power prediction accuracy of each day within the target time range, the power prediction vendors are ranked according to their daily ultra-short-term power prediction accuracy, and a preset score is given to the power prediction vendor ranked first on each day.

[0012] Based on the daily spot power forecast accuracy of each day within the target time range, power forecasting vendors are ranked according to their daily spot power forecast accuracy, and a preset score is given to the power forecasting vendor ranked first on each day.

[0013] Based on the daily two-way power prediction accuracy within the target time range, power prediction vendors are ranked according to their daily two-way power prediction accuracy, and a preset score is given to the power prediction vendor ranked first on each day.

[0014] The single-point ultra-short-term power prediction data for the target day's pre-selected time will be used as the recommended single-point ultra-short-term power prediction data for the target day's pre-selected time, based on the power prediction accuracy ranking score of the power prediction vendor with the highest score.

[0015] The daily ultra-short-term power forecast data for the target day will be the recommended daily ultra-short-term power forecast data, based on the power forecast vendor with the highest score in the daily ultra-short-term power forecast accuracy ranking.

[0016] The daily spot power forecast data for the target day will be the recommended daily spot power forecast data for the target day, based on the power forecast provider with the highest score in the daily spot power forecast accuracy ranking.

[0017] The power forecasting vendor with the highest score based on the accuracy ranking of the two power forecasts for a single day will be used as the recommended two power forecasts for the target day.

[0018] Furthermore, in some embodiments of this application, the target time range is the most recent 7 days.

[0019] Furthermore, in some embodiments of this application, the short-term power prediction data, ultra-short-term power prediction data, available power plant capacity, and actual power plant power are all data from 96 time points in a day, with the interval between adjacent time points being 15 minutes.

[0020] Furthermore, in some embodiments of this application, the formula for calculating the accuracy of the single-point ultra-short-term power prediction is as follows:

[0021]

[0022] Where x is the power prediction vendor identifier, and D j x_D is the day marker, i is the time marker, and x_D is the hour marker. j i - ACC SDT Indicates that power prediction vendor x in D j The accuracy of single-point ultra-short-term power prediction at time i of the day; D j The actual power output of the plant at time i on the day; For power prediction manufacturers to D j The predicted power at time i on a given day; Cap is the available capacity of the power plant; n is the total number of assessment periods on a given day.

[0023] Furthermore, in some embodiments of this application, the formula for calculating the accuracy of the daily ultra-short-term power prediction is as follows:

[0024]

[0025] Where x_D j- ACC SD Indicates that power prediction vendor x in D j Daily ultra-short-term power prediction accuracy.

[0026] Furthermore, in some embodiments of this application, the formula for calculating the daily spot power prediction accuracy is as follows:

[0027]

[0028] x_D j- ACC D Indicates that power prediction vendor x in D j Daily spot power prediction accuracy.

[0029] Furthermore, in some embodiments of this application, when the location of the new energy power plant has a dedicated formula for calculating the accuracy of daily two-way power prediction, the daily two-way power prediction accuracy of each power prediction manufacturer within the target time range is calculated based on the corresponding dedicated formula.

[0030] Furthermore, in some embodiments of this application,

[0031] When there is no dedicated formula for calculating the accuracy of daily two-way power forecasts in the location of the new energy plant, the daily two-way power forecast accuracy of each power forecasting manufacturer within the target time range is calculated based on the formula for calculating the accuracy of daily spot power forecasts.

[0032] Secondly, this application provides a new energy multi-source power prediction data recommendation device, comprising:

[0033] The acquisition module is used to acquire basic data through an interface. The basic data includes the name of the power prediction vendor, short-term power prediction data within the target time range, ultra-short-term power prediction data, available capacity of the power plant, and actual power of the power plant. The short-term power prediction data and ultra-short-term power prediction data are provided by the power prediction vendor, and the available capacity of the power plant and the actual power of the power plant are provided by the new energy power plant.

[0034] The calculation module is used to calculate, based on the basic data, the single-point ultra-short-term power prediction accuracy, the single-day ultra-short-term power prediction accuracy, the single-day spot power prediction accuracy, and the single-day two-way power prediction accuracy of each power prediction manufacturer within the target time range.

[0035] The ranking and scoring module is used to rank power forecasting vendors based on their single-point ultra-short-term power forecast accuracy at at least one pre-selected time point within each day of the target time range, and to award a preset score to the power forecasting vendor ranked first at each pre-selected time point; to rank power forecasting vendors based on their daily ultra-short-term power forecast accuracy within each day of the target time range, and to award a preset score to the power forecasting vendor ranked first on each day; to rank power forecasting vendors based on their daily spot power forecast accuracy within each day of the target time range, and to award a preset score to the power forecasting vendor ranked first on each day; and to rank power forecasting vendors based on their daily two-way power forecast accuracy within each day of the target time range, and to award a preset score to the power forecasting vendor ranked first on each day.

[0036] The recommendation module is used to select the single-point ultra-short-term power forecast data for the target day's pre-selected time from the power forecasting vendor with the highest score based on the single-point ultra-short-term power forecast accuracy ranking; to select the single-day ultra-short-term power forecast data for the target day from the power forecasting vendor with the highest score based on the single-day ultra-short-term power forecast accuracy ranking; to select the single-day spot power forecast data for the target day from the power forecasting vendor with the highest score based on the single-day spot power forecast accuracy ranking; and to select the single-day two-part power forecast data for the target day from the power forecasting vendor with the highest score based on the single-day two-part power forecast accuracy ranking.

[0037] Thirdly, this application provides a new energy multi-source power prediction data recommendation device, including a processor and a memory, wherein the processor is connected to the memory:

[0038] The processor is used to call and execute the program stored in the memory;

[0039] The memory is used to store the program, which is at least used to execute the above-described method for recommending new energy multi-source power prediction data.

[0040] This invention relates to the field of power technology, specifically to a method, apparatus, and equipment for recommending multi-source power prediction data for new energy sources. The method includes: acquiring basic data including the name of the power prediction vendor, short-term power prediction data within a target time range, ultra-short-term power prediction data, available power plant capacity, and actual power output of the power plant; based on the basic data, calculating the accuracy rates of single-point ultra-short-term power prediction, daily ultra-short-term power prediction, daily spot power prediction, and daily two-way power prediction within the target time range for each power prediction vendor, and ranking and scoring them accordingly; and recommending power prediction vendors and their power prediction data based on the ranking and scoring results for different prediction types. In this way, suitable power prediction vendors and power prediction data can be quickly recommended to new energy enterprises for different prediction types. Attached Figure Description

[0041] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0042] Figure 1This is a flowchart illustrating the new energy multi-source power prediction data recommendation method provided in this embodiment of the invention.

[0043] Figure 2 This is a schematic diagram illustrating the principle of the new energy multi-source power prediction data recommendation method provided in this embodiment of the invention.

[0044] Figure 3 This is a schematic diagram of the structure of the new energy multi-source power prediction data recommendation device provided in an embodiment of the present invention.

[0045] Figure 4 This is a schematic diagram of the structure of the new energy multi-source power prediction data recommendation device provided in an embodiment of the present invention. Detailed Implementation

[0046] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be described in detail below. Obviously, the described embodiments are merely some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other implementation methods obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0047] Method Implementation Examples:

[0048] Figure 1 This is a flowchart illustrating the new energy multi-source power prediction data recommendation method provided in an embodiment of the present invention. Figure 2 This is a schematic diagram illustrating the principle of the new energy multi-source power prediction data recommendation method provided in this embodiment of the invention. Please refer to [link / reference]. Figure 1 and Figure 2 This embodiment may include the following steps:

[0049] S101. Obtain basic data through the interface.

[0050] The basic data includes the name of the power forecasting vendor, short-term power forecast data within the target time range, ultra-short-term power forecast data, available power plant capacity, and actual power of the power plant. The short-term and ultra-short-term power forecast data are provided by the power forecasting vendors, while the available power plant capacity and actual power of the power plant are provided by the new energy power plants.

[0051] Specifically, the power forecast vendor name is provided by the power forecast vendor. The target time range can be selected as the most recent 7 days. Short-term power forecast data specifically refers to the short-term power forecast data for a single renewable energy plant (such as wind and solar power) for 96 points per day (i.e., data from 96 time points in a day, with adjacent time points spaced 15 minutes apart), provided by the power forecast vendor. Ultra-short-term power forecast data refers to the ultra-short-term power forecast data for a single renewable energy plant for 96 points per day, provided by the power forecast vendor's interface. Available plant capacity refers to the available capacity data for a single renewable energy plant for 96 points per day, provided by the plant itself. Actual plant power refers to the actual power data for a single renewable energy plant for 96 points per day, provided by the plant itself.

[0052] S102. Based on the basic data, calculate the single-point ultra-short-term power prediction accuracy, single-day ultra-short-term power prediction accuracy, single-day spot power prediction accuracy, and single-day two-way power prediction accuracy of each power prediction manufacturer within the target time range.

[0053] Specifically, in this application, based on the aforementioned basic data, the accuracy of ultra-short-term power prediction can be calculated using the root mean square error principle, specifically including the accuracy of single-point ultra-short-term power prediction and the accuracy of daily ultra-short-term power prediction. For short-term power prediction accuracy, this application distinguishes between spot power prediction accuracy and two-way power prediction accuracy, calculating the daily spot power prediction accuracy and the daily two-way power prediction accuracy separately.

[0054] S103. Rank and score power prediction vendors based on accuracy.

[0055] Specifically, based on the four types of accuracy at different time points, each power prediction vendor was ranked multiple times, and a scoring process was performed based on the results of these multiple rankings, including:

[0056] Based on the single-point ultra-short-term power prediction accuracy corresponding to at least one pre-selected time in each day within the target time range, the power prediction vendors are ranked according to their single-point ultra-short-term power prediction accuracy, and a preset score is calculated for the power prediction vendor ranked first at each pre-selected time.

[0057] Based on the daily ultra-short-term power forecast accuracy within the target time range, power forecasting vendors are ranked according to their daily ultra-short-term power forecast accuracy, and a preset score is given to the power forecasting vendor ranked first on each day.

[0058] Based on the daily spot power forecast accuracy of each day within the target time range, power forecasting vendors are ranked according to their daily spot power forecast accuracy, and a preset score is given to the power forecasting vendor ranked first on each day.

[0059] Furthermore, based on the daily two-way power forecast accuracy within the target time range, the power forecasting vendors are ranked according to their daily two-way power forecast accuracy, and a preset score is calculated for the power forecasting vendor ranked first on each day.

[0060] S104. Based on the ranking and scoring results, recommend power prediction vendors and power prediction data for different types of predictions.

[0061] Specifically, this includes: using the single-point ultra-short-term power forecast data for the target day's pre-selected time period from the power forecasting vendor with the highest score based on the single-point ultra-short-term power forecast accuracy ranking as the recommended single-point ultra-short-term power forecast data for the target day's pre-selected time period; using the single-day ultra-short-term power forecast data for the target day from the power forecasting vendor with the highest score based on the single-day ultra-short-term power forecast accuracy ranking as the recommended single-day ultra-short-term power forecast data for the target day; using the single-day spot power forecast data for the target day from the power forecasting vendor with the highest score based on the single-day spot power forecast accuracy ranking as the recommended single-day spot power forecast data for the target day; and using the single-day two power forecast data for the target day from the power forecasting vendor with the highest score based on the single-day two power forecast accuracy ranking as the recommended single-day two power forecast data for the target day.

[0062] The new energy multi-source power prediction data recommendation method provided in this application obtains basic data including the name of the power prediction vendor, short-term power prediction data within the target time range, ultra-short-term power prediction data, available power plant capacity, and actual power of the power plant. Based on the basic data, it calculates the accuracy rates of single-point ultra-short-term power prediction, single-day ultra-short-term power prediction, single-day spot power prediction, and single-day two-way power prediction within the target time range for each power prediction vendor, and ranks and scores them respectively. Based on the ranking and scoring results of different prediction types, it recommends power prediction vendors and their power prediction data respectively, which can quickly recommend suitable power prediction vendors and power prediction data to new energy companies for different prediction types.

[0063] Furthermore, in some embodiments of this application, the formula for calculating the accuracy of single-point ultra-short-term power prediction is as follows:

[0064]

[0065] Where x is the power prediction vendor identifier, and D j x_D is the day marker, i is the time marker, and x_D is the hour marker. j i - ACC SDT Indicates that power prediction vendor x in D j The accuracy of single-point ultra-short-term power prediction at time i of the day; D j The actual power output of the plant at time i on the day; For power prediction manufacturers to D j The predicted power at time i on a given day; Cap is the available capacity of the power plant; n is the total number of assessment periods on a given day.

[0066] The formula for calculating the accuracy of daily ultra-short-term power prediction is as follows:

[0067]

[0068] Where x_D j- ACC SD This indicates that power prediction manufacturers are in D j Daily ultra-short-term power prediction accuracy.

[0069] The formula for calculating the accuracy of daily spot power forecast is as follows:

[0070]

[0071] x_D j- ACC D Indicates that power prediction vendor x in D j Daily spot power prediction accuracy.

[0072] Regarding the accuracy of daily two-way power forecasts, if there is a dedicated formula for calculating the accuracy of daily two-way power forecasts in the location of the new energy power plant, then the accuracy of daily two-way power forecasts for each power forecasting vendor within the target time range is calculated based on the corresponding dedicated formula. However, if there is no dedicated formula for calculating the accuracy of daily two-way power forecasts in the location of the new energy power plant, then the accuracy of daily two-way power forecasts for each power forecasting vendor within the target time range is calculated based on the formula for calculating the accuracy of daily spot power forecasts.

[0073] The following will provide a detailed description of the new energy multi-source power prediction data recommendation method provided in this application, using a specific embodiment as an example. Specifically, it includes:

[0074] The first step is to set the operating day as day D (i.e., the current date, corresponding to the scenario in this application, which is that a suitable power prediction vendor needs to be selected for power prediction on day D). When acquiring basic data, specifically acquire the daily 96-point actual power (i.e., actual power of the plant) of plant A for the past week, namely days D-7, D-6, D-5, D-4, D-3, D-2, and D-1 (i.e., the 7 days closest to day D), the daily 96-point available capacity (i.e., available capacity of the plant) for the past week, namely days D-7, D-6, D-5, D-4, D-3, D-2, and D-1, and the daily 96-point short-term power prediction and ultra-short-term power prediction data of power prediction vendors a, b, and c associated with plant A for the past week, namely days D-7, D-6, D-5, D-4, D-3, D-2, and D-1.

[0075] The second step, based on the acquired data, is to calculate the single-point ultra-short-term power prediction accuracy (ACC) for each vendor (a), vendor b, and vendor c… for the power predictions of D-7, D-6, D-5, D-4, D-3, D-2, D-1, etc., over the past week. SDT That is, the ACC of each manufacturer SDT Each set of data contains 7*96 records.

[0076] Taking manufacturer a as an example, calculate its single-point ultra-short-term power prediction accuracy a_D1i-ACC at time i on day D1 (i.e., day D-1). SDT The specific methods are as follows:

[0077]

[0078] in, and Let represent the actual power output of the power plant at time i on day D1 and the predicted power output of manufacturer a, respectively.

[0079] Based on the same principle, the single-point ultra-short-term power prediction accuracy at time i on day D1 of other manufacturers can be calculated, as well as the single-point ultra-short-term power prediction accuracy of all manufacturers on other days, namely D-7, D-6, D-5, D-4, D-3, and D-2.

[0080] The third step is to calculate the daily ultra-short-term power forecast accuracy of each power forecasting vendor for the past week, including days D-7, D-6, D-5, D-4, D-3, D-2, and D-1, as well as the daily spot power forecast accuracy and the daily two-way power forecast accuracy.

[0081] Taking manufacturer A as an example, calculate its daily ultra-short-term power prediction accuracy for day D1. Daily spot power prediction accuracy The details are as follows:

[0082]

[0083]

[0084] It should be noted that the calculation formula for the accuracy of two power forecasts per day can be based on the formula published by the location of the new energy power plant. If no such formula is published, the calculation formula is the same as the calculation formula for the accuracy of the daily spot power forecast mentioned above.

[0085] Based on the same principle, the daily ultra-short-term power forecast accuracy, daily spot power forecast accuracy, and daily two-way power forecast accuracy for other manufacturers on day D1 can be calculated. Similarly, based on the same principle, the daily ultra-short-term power forecast accuracy, daily spot power forecast accuracy, and daily two-way power forecast accuracy for each manufacturer on days D-7, D-6, D-5, D-4, D-3, and D-2 can also be calculated.

[0086] The fourth step is to rank and score manufacturers based on the accuracy rates obtained above. If a manufacturer ranks first in accuracy, it will receive 1 point, and so on.

[0087] The following is a detailed introduction based on the ranking and scoring of single-point ultra-short-term power prediction accuracy:

[0088] When ranking the accuracy of single-point ultra-short-term power prediction, a pre-selected evaluation time point can be selected. For example, the accuracy of single-point ultra-short-term power prediction can be selected from any one or several time points out of 96 points. The accuracy of single-point ultra-short-term power prediction of each manufacturer at the corresponding time point on day D-1 can be sorted in descending order, and 1 point can be awarded to the manufacturer ranked first.

[0089] Based on the same principle, ranking and scoring operations are performed for all other dates (D-7, D-6, D-5, D-4, D-3, D-2). Then, the scores of vendor a, vendor b, vendor c, ... vendor n are summed to obtain the score for each vendor, i.e., a_ACC. SDT _Score、b_ACC SDT _Score、c_ACC SDT _Score,…n_ACC SDT _Score.

[0090] And based on the same principle, ranking and scoring operations are performed on the accuracy of daily ultra-short-term power prediction, daily spot power prediction, and daily two-way power prediction for each manufacturer.

[0091] Taking the daily ultra-short-term power prediction accuracy as an example: sort the daily ultra-short-term power prediction accuracy of each manufacturer in descending order for day D-1, select the manufacturer ranked first, and score it 1. The same applies to other days.

[0092] Based on the scoring results obtained above, the scores of manufacturers a, b, c, ... n are summed to obtain the daily ultra-short-term power prediction accuracy score for each manufacturer, i.e., a_ACC. SD _Score、b_ACC SD _Score、c_ACC SD _Score,…n_ACC SD _Score.

[0093] The ranking and scoring principles for daily spot power forecast accuracy and daily two-time power forecast accuracy are consistent with the ranking and scoring principles for daily ultra-short-term power forecast accuracy. Based on the same principles, the daily spot power forecast accuracy and daily two-time power forecast accuracy of each manufacturer can be obtained, including: a_ACC D _Score、b_ACC D _Score、c_ACC D _Score,…n_ACC D _Score, and a_ACC ED _Score、b_ACC ED _Score、c_ACC ED _Score,…n_ACC ED _Score.

[0094] The fifth step is to make recommendations based on the scoring results of each manufacturer obtained above.

[0095] Specifically, regarding the accuracy of single-point ultra-short-term power prediction, the ranking and scoring results of the accuracy of single-point ultra-short-term power prediction at the evaluation time point of each manufacturer are arranged in descending order. The ultra-short-term power prediction value provided by the manufacturer with the highest score at the evaluation time point of day D is taken as the recommended result of ultra-short-term power prediction at the corresponding time point of day D.

[0096] To assess the accuracy of daily ultra-short-term power forecasts, the ranking and scoring results of each manufacturer's daily ultra-short-term power forecast accuracy are sorted in descending order. The ultra-short-term power forecast values ​​for all time points on day D provided by the manufacturer with the highest score will be used as the recommended ultra-short-term power forecast for day D. Based on the same principle, spot power forecasts for day D and recommendations for two power forecast data sets are also provided.

[0097] The new energy multi-source power prediction data recommendation method provided in this application enables data access and processing from multiple power prediction manufacturers through an interface. This allows multiple manufacturers to display their corresponding power prediction data on a unified and measurable prediction accuracy calculation platform. Simultaneously, by processing and calculating the multi-source prediction data, historical prediction data is used to perform a secondary calculation and ranking of the power prediction accuracy of each manufacturer. The prediction data provided by the manufacturer with the highest score for the operating day is used as the recommendation result. By establishing a unified and measurable accuracy calculation and evaluation standard and process, it ensures that all manufacturers are evaluated under the same calculation conditions, guaranteeing the timeliness, reliability, and accuracy of the prediction results evaluation. This provides new energy power plants with valuable reference data quickly, indirectly improving their competitiveness and efficiency in market transactions.

[0098] Device Example:

[0099] The present invention also provides a new energy multi-source power prediction data recommendation device for implementing the above method embodiments. Figure 3 This is a schematic diagram of the structure of the new energy multi-source power prediction data recommendation device provided in an embodiment of the present invention, as shown below. Figure 3 As shown, the device includes:

[0100] The acquisition module 11 is used to acquire basic data through an interface. The basic data includes the name of the power prediction vendor, short-term power prediction data within the target time range, ultra-short-term power prediction data, available capacity of the power plant, and actual power of the power plant. Among them, the short-term power prediction data and ultra-short-term power prediction data are provided by the power prediction vendor, and the available capacity of the power plant and the actual power of the power plant are provided by the new energy power plant.

[0101] The calculation module 12 is used to calculate the accuracy of single-point ultra-short-term power prediction, single-day ultra-short-term power prediction, single-day spot power prediction, and single-day two-way power prediction for each power prediction manufacturer within the target time range based on the basic data.

[0102] The ranking and scoring module 13 is used to rank power forecasting vendors based on the accuracy of single-point ultra-short-term power forecasting at least one pre-selected time point in each day within the target time range, and to assign a preset score to the power forecasting vendor ranked first in each pre-selected time point; to rank power forecasting vendors based on the accuracy of single-day ultra-short-term power forecasting in each day within the target time range, and to assign a preset score to the power forecasting vendor ranked first in each day; to rank power forecasting vendors based on the accuracy of single-day spot power forecasting in each day within the target time range, and to assign a preset score to the power forecasting vendor ranked first in each day; and to rank power forecasting vendors based on the accuracy of single-day two-way power forecasting in each day within the target time range, and to assign a preset score to the power forecasting vendor ranked first in each day.

[0103] The recommendation module 14 is used to select the single-point ultra-short-term power forecast data for the target day's pre-selected time from the power forecasting vendor with the highest score based on the single-point ultra-short-term power forecast accuracy ranking as the recommended single-point ultra-short-term power forecast data for the target day's pre-selected time; to select the single-day ultra-short-term power forecast data for the target day from the power forecasting vendor with the highest score based on the single-day ultra-short-term power forecast accuracy ranking as the recommended single-day ultra-short-term power forecast data for the target day; to select the single-day spot power forecast data for the target day from the power forecasting vendor with the highest score based on the single-day spot power forecast accuracy ranking as the recommended single-day spot power forecast data for the target day; and to select the single-day two-part power forecast data for the target day from the power forecasting vendor with the highest score based on the single-day two-part power forecast accuracy ranking as the recommended single-day two-part power forecast data for the target day.

[0104] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0105] The present invention also provides a new energy multi-source power prediction data recommendation device for implementing the above method embodiments. Figure 4 This is a schematic diagram of the structure of the new energy multi-source power prediction data recommendation device provided in an embodiment of the present invention, as shown below. Figure 4 As shown, the new energy multi-source power prediction data recommendation device of this embodiment includes a processor 21 and a memory 22, with the processor 21 connected to the memory 22. The processor 21 is used to call and execute the program stored in the memory 22; the memory 22 is used to store the program, which is at least used to execute the new energy multi-source power prediction data recommendation method in the above embodiments.

[0106] The specific implementation scheme of the new energy multi-source power prediction data recommendation device provided in this application embodiment can refer to the implementation scheme of the new energy multi-source power prediction data recommendation method in any of the above embodiments, and will not be repeated here.

[0107] It is understood that the same or similar parts in the above embodiments can be referred to each other, and the contents not described in detail in some embodiments can be referred to the same or similar contents in other embodiments.

[0108] It should be noted that in the description of this invention, the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance. Furthermore, in the description of this invention, unless otherwise stated, "a plurality of" means at least two.

[0109] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing a particular logical function or process, and the scope of the preferred embodiments of the invention includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as will be understood by those skilled in the art to which embodiments of the invention pertain.

[0110] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0111] Those skilled in the art will understand that all or part of the steps of the methods described in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it includes one or a combination of the steps of the method embodiments.

[0112] Furthermore, the functional units in the various embodiments of the present invention can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0113] The storage media mentioned above can be read-only memory, disk, or optical disk, etc.

[0114] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0115] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A method for recommending multi-source power prediction data for new energy sources, characterized in that, include: Basic data is obtained through an interface. The basic data includes the name of the power prediction vendor, short-term power prediction data within the target time range, ultra-short-term power prediction data, available capacity of power plants, and actual power of power plants. The short-term power prediction data and ultra-short-term power prediction data are provided by the power prediction vendor, and the available capacity of power plants and actual power of power plants are provided by the new energy power plants. Based on the aforementioned basic data, calculate the single-point ultra-short-term power prediction accuracy, single-day ultra-short-term power prediction accuracy, single-day spot power prediction accuracy, and single-day two-way power prediction accuracy for each power prediction vendor within the target time range. Based on the single-point ultra-short-term power prediction accuracy corresponding to at least one pre-selected time in each day within the target time range, the power prediction vendors are ranked according to their single-point ultra-short-term power prediction accuracy, and a preset score is calculated for the power prediction vendor ranked first at each pre-selected time. Based on the daily ultra-short-term power prediction accuracy of each day within the target time range, the power prediction vendors are ranked according to their daily ultra-short-term power prediction accuracy, and a preset score is given to the power prediction vendor ranked first on each day. Based on the daily spot power forecast accuracy of each day within the target time range, power forecasting vendors are ranked according to their daily spot power forecast accuracy, and a preset score is given to the power forecasting vendor ranked first on each day. Based on the daily two-way power prediction accuracy within the target time range, power prediction vendors are ranked according to their daily two-way power prediction accuracy, and a preset score is given to the power prediction vendor ranked first on each day. The single-point ultra-short-term power prediction data for the target day's pre-selected time will be used as the recommended single-point ultra-short-term power prediction data for the target day's pre-selected time, based on the power prediction accuracy ranking score of the power prediction vendor with the highest score. The daily ultra-short-term power forecast data for the target day will be the recommended daily ultra-short-term power forecast data, based on the power forecast vendor with the highest score in the daily ultra-short-term power forecast accuracy ranking. The daily spot power forecast data for the target day will be the recommended daily spot power forecast data for the target day, based on the highest score in the daily spot power forecast accuracy ranking. The power forecasting vendor with the highest score based on the accuracy ranking of the two power forecasts for a single day will be used as the recommended two power forecasts for the target day. The formula for calculating the accuracy of single-point ultra-short-term power prediction is as follows: Where x is the identifier of the power prediction vendor, and D j x_D is the day marker, i is the time marker, and x_D is the hour marker. j i - ACC SDT Indicates that power prediction vendor x in D j The accuracy of single-point ultra-short-term power prediction at time i of the day; D j The actual power output of the plant at time i on the day; For power prediction manufacturers to D j The predicted power at time i on a given day; Cap is the available capacity of the power plant; n is the total number of assessment periods on a given day; The formula for calculating the accuracy of the daily ultra-short-term power prediction is as follows: Where x_D j- ACC SD Indicates that power prediction vendor x in D j Daily ultra-short-term power prediction accuracy; The formula for calculating the accuracy of daily spot power forecast is as follows: x_D j- ACC D Indicates that power prediction vendor x in D j Daily spot power prediction accuracy.

2. The method for recommending new energy multi-source power prediction data according to claim 1, characterized in that, The target time range is the most recent 7 days.

3. The method for recommending new energy multi-source power prediction data according to claim 1, characterized in that, The short-term power prediction data, ultra-short-term power prediction data, available power plant capacity, and actual power plant power are all data from 96 time points per day, with an interval of 15 minutes between adjacent time points.

4. The method for recommending new energy multi-source power prediction data according to claim 1, characterized in that, When the location of the new energy plant has a dedicated formula for calculating the accuracy of daily two-way power prediction, the daily two-way power prediction accuracy of each power prediction manufacturer within the target time range is calculated based on the corresponding dedicated formula.

5. The method for recommending new energy multi-source power prediction data according to claim 4, characterized in that, When there is no dedicated formula for calculating the accuracy of daily two-way power forecasts in the location of the new energy plant, the daily two-way power forecast accuracy of each power forecasting manufacturer within the target time range is calculated based on the formula for calculating the accuracy of daily spot power forecasts.

6. A new energy multi-source power prediction data recommendation device, characterized in that, include: The acquisition module is used to acquire basic data through an interface. The basic data includes the name of the power prediction vendor, short-term power prediction data within the target time range, ultra-short-term power prediction data, available capacity of the power plant, and actual power of the power plant. The short-term power prediction data and ultra-short-term power prediction data are provided by the power prediction vendor, and the available capacity of the power plant and the actual power of the power plant are provided by the new energy power plant. The calculation module is used to calculate, based on the basic data, the single-point ultra-short-term power prediction accuracy, the single-day ultra-short-term power prediction accuracy, the single-day spot power prediction accuracy, and the single-day two-way power prediction accuracy of each power prediction manufacturer within the target time range. The ranking and scoring module is used to rank power forecasting vendors based on their single-point ultra-short-term power forecast accuracy at at least one pre-selected time point within each day of the target time range, and to award a preset score to the power forecasting vendor ranked first at each pre-selected time point; to rank power forecasting vendors based on their daily ultra-short-term power forecast accuracy within each day of the target time range, and to award a preset score to the power forecasting vendor ranked first on each day; to rank power forecasting vendors based on their daily spot power forecast accuracy within each day of the target time range, and to award a preset score to the power forecasting vendor ranked first on each day; and to rank power forecasting vendors based on their daily two-way power forecast accuracy within each day of the target time range, and to award a preset score to the power forecasting vendor ranked first on each day. The recommendation module is used to select the single-point ultra-short-term power forecast data for the target day's pre-selected time from the power forecasting vendor with the highest score based on the single-point ultra-short-term power forecast accuracy ranking, and to select the single-day ultra-short-term power forecast data for the target day from the power forecasting vendor with the highest score based on the single-day ultra-short-term power forecast accuracy ranking, and to select the single-day spot power forecast data for the target day from the power forecasting vendor with the highest score based on the single-day spot power forecast accuracy ranking, and to select the single-day two-part power forecast data for the target day from the power forecasting vendor with the highest score based on the single-day two-part power forecast accuracy ranking. The formula for calculating the accuracy of single-point ultra-short-term power prediction is as follows: Where x is the identifier of the power prediction vendor, and D j x_D is the day marker, i is the time marker, and x_D is the hour marker. j i - ACC SDT Indicates that power prediction vendor x in D j The accuracy of single-point ultra-short-term power prediction at time i of the day; D j The actual power output of the plant at time i on the day; For power prediction manufacturers to D j The predicted power at time i on a given day; Cap is the available capacity of the power plant; n is the total number of assessment periods on a given day; The formula for calculating the accuracy of the daily ultra-short-term power prediction is as follows: Where x_D j- ACC SD Indicates that power prediction vendor x in D j Daily ultra-short-term power prediction accuracy; The formula for calculating the accuracy of daily spot power forecast is as follows: x_D j- ACC D Indicates that power prediction vendor x in D j Daily spot power prediction accuracy.

7. A new energy multi-source power prediction data recommendation device, characterized in that, It includes a processor and a memory, wherein the processor is connected to the memory: The processor is used to call and execute the program stored in the memory; The memory is used to store the program, which is at least used to execute the new energy multi-source power prediction data recommendation method according to any one of claims 1-5.

Images