New energy multi-source power prediction data recommendation method, device and equipment

Abstract

The invention relates to the technical field of electric power, in particular to a new energy multi-source power prediction data recommendation method, device and equipment, and the method comprises the steps: obtaining the name of a power prediction manufacturer, short-term power prediction data in a target time range, ultra-short-term power prediction data, the available capacity of a plant station, and basic data of the actual power of the plant station; based on the basic data, calculating a single-point ultra-short-term power prediction accuracy rate, a single-day ultra-short-term power prediction accuracy rate, a single-day spot power prediction accuracy rate and a single-day two-term power prediction accuracy rate of each power prediction manufacturer within a target time range, and respectively performing ranking scoring; and respectively recommending power prediction manufacturers and power prediction data thereof based on ranking scoring results of different prediction types. Therefore, appropriate power prediction manufacturers and power prediction data can be quickly recommended to new energy enterprises for different prediction types.

Description

Technical Field

[0001] The present invention relates to the field of electric power technology, and in particular to a method, device and equipment for recommending new energy multi-source power prediction data. Background Art

[0002] As the proportion of new energy grid connection continues to increase, accurate power forecasting has become an important basis for formulating unit power generation plans and enhancing the ability to absorb new energy. Accurate power forecasting can help new energy power stations reasonably arrange power generation plans, thereby avoiding the phenomenon of wind and solar power abandonment caused by excessive power generation.

[0003] In practical applications, power forecast results can serve as a basis for participating in the electricity spot market and help new energy companies formulate relevant strategies. Furthermore, assessing the accuracy of power forecast reporting is a crucial component of the power industry, particularly in renewable energy generation, such as wind and photovoltaic power. Accurate power forecasts help maintain a balanced power system and avoid instability caused by supply-demand imbalances. Dispatch centers can use forecast results to proactively adjust dispatch plans, optimize grid operations, and improve resource utilization efficiency. Therefore, ensuring the accuracy of power forecasts is crucial for these new energy companies.

[0004] In the existing technology, new energy companies generally directly use the forecast data provided by power forecast manufacturers. However, faced with multiple power forecast manufacturers and a huge amount of forecast data, it is impossible to reasonably and efficiently determine the accuracy of the power forecast provided by the power forecast manufacturers, and then select the power forecast manufacturers, which affects their relevant 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, device and equipment for recommending multi-source power forecasting data of new energy, so as to overcome the problem that new energy enterprises are currently unable to make reasonable choices when faced with a large number of power forecasting manufacturers.

[0006] To achieve the above objectives, the present invention adopts the following technical solutions: In a first aspect, the present application provides a method for recommending new energy multi-source power prediction data, comprising: Obtain basic data through the interface, the basic data including the name of the power forecasting manufacturer, short-term power forecast data within the target time range, ultra-short-term power forecast data, plant and station available capacity, and plant and station actual power; wherein the short-term power forecast data and ultra-short-term power forecast data are both provided by the power forecasting manufacturer, and the plant and station available capacity and plant and station actual power are both provided by the new energy plant and station; Based on the basic data, calculate the single-point ultra-short-term power forecast accuracy, single-day ultra-short-term power forecast accuracy, single-day spot power forecast accuracy, and single-day two-item power forecast accuracy of each power forecast manufacturer within the target time range; Based on the single-point ultra-short-term power forecast accuracy corresponding to at least one pre-selected moment on each day within the target time range, the power forecast vendors are ranked by their single-point ultra-short-term power forecast accuracy, and a preset score is awarded to the power forecast vendor that ranks first at each pre-selected moment; The power forecasting vendors are ranked based on their single-day ultra-short-term power forecast accuracy for each day within the target time range, and a preset score is awarded to the power forecasting vendor that ranks first on each day; Power forecast vendors are ranked based on their single-day spot power forecast accuracy for each day within the target time range, and the top-ranked power forecast vendor on each day is awarded a preset score. Power forecast vendors are ranked based on their accuracy of two power forecasts per day within the target time range, and the top-ranked power forecast vendor on each day is given a preset score. The single-point ultra-short-term power forecast data of the power forecasting manufacturer with the highest single-point ultra-short-term power forecast accuracy ranking score at the pre-selected time of the target day will be used as the recommended single-point ultra-short-term power forecast data at the pre-selected time of the target day; The single-day ultra-short-term power forecast data of the power forecasting manufacturer with the highest single-day ultra-short-term power forecast accuracy ranking score for the target day will be used as the recommended single-day ultra-short-term power forecast data for the target day; The power forecast data of the power forecasting manufacturer with the highest single-day spot power forecast accuracy ranking score for the target day will be used as the recommended single-day spot power forecast data for the target day; The power forecast data for the target day of the power forecast manufacturer with the highest single-day power forecast accuracy ranking score will be used as the recommended single-day power forecast data for the target day.

[0007] Furthermore, in some embodiments of the present application, the target time range is the most recent 7 days.

[0008] Furthermore, in some embodiments of the present application, the short-term power forecast data, ultra-short-term power forecast data, plant available capacity and plant actual power are all data at 96 time points in a day, where the intervals between adjacent time points are 15 minutes.

[0009] Furthermore, in some embodiments of the present application, the calculation formula for the single-point ultra-short-term power prediction accuracy is:

[0010] Among them, x is the power prediction manufacturer logo, D j is the day sign, i is the time sign, x_D j i - ACC SDT Indicates the power forecast manufacturer 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 of the plant at time i of the day; For power prediction manufacturers, D j The predicted power at time i of the day; Cap is the available capacity of the plant; n is the total number of daily assessment periods.

[0011] Furthermore, in some embodiments of the present application, the calculation formula for the single-day ultra-short-term power prediction accuracy is:

[0012] Among them, x_D j- ACC SD Indicates the power forecast manufacturer x in D j The single-day ultra-short-term power forecast accuracy of the day.

[0013] Furthermore, in some embodiments of the present application, the calculation formula for the single-day spot power prediction accuracy is:

[0014] x_D j- ACC D Indicates the power forecast manufacturer x in D j The accuracy of the daily spot power forecast.

[0015] Furthermore, in some embodiments of the present application, when the location of the new energy plant has a dedicated calculation formula for the accuracy of the two power forecasts per day, the accuracy of the two power forecasts per day of each power forecast manufacturer within the target time range is calculated based on the corresponding dedicated calculation formula.

[0016] Furthermore, in some embodiments of the present application, When there is no dedicated calculation formula for the accuracy of two power forecasts per day at the location of the new energy plant, the accuracy of two power forecasts per day of each power forecast manufacturer within the target time range is calculated based on the calculation formula for the accuracy of one-day spot power forecast.

[0017] In a second aspect, the present application provides a new energy multi-source power prediction data recommendation device, comprising: an acquisition module, configured to acquire basic data through an interface, the basic data including the name of the power forecasting manufacturer, short-term power forecast data within a target time range, ultra-short-term power forecast data, plant and station available capacity, and plant and station actual power; wherein the short-term power forecast data and ultra-short-term power forecast data are both provided by the power forecasting manufacturer, and the plant and station available capacity and plant and station actual power are both provided by the new energy plant and station; A calculation module is used to calculate the single-point ultra-short-term power forecast accuracy, single-day ultra-short-term power forecast accuracy, single-day spot power forecast accuracy and single-day two-item power forecast accuracy of each power forecast manufacturer within the target time range based on the basic data; A ranking and scoring module is used to rank the power forecasting manufacturers by their single-point ultra-short-term power forecast accuracy based on the single-point ultra-short-term power forecast accuracy corresponding to at least one pre-selected moment on each day within the target time range, and calculate a preset score for the power forecasting manufacturer ranked first at each pre-selected moment; rank the power forecasting manufacturers by their single-day ultra-short-term power forecast accuracy based on the single-day ultra-short-term power forecast accuracy of each day within the target time range, and calculate a preset score for the power forecasting manufacturer ranked first on each day; rank the power forecasting manufacturers by their single-day spot power forecast accuracy based on the single-day spot power forecast accuracy of each day within the target time range, and calculate a preset score for the power forecasting manufacturer ranked first on each day; and rank the power forecasting manufacturers by their single-day two-time power forecast accuracy based on the single-day two-time power forecast accuracy of each day within the target time range, and calculate a preset score for the power forecasting manufacturer ranked first on each day; The recommendation module is used to use the single-point ultra-short-term power forecast data for the pre-selected time of the target day from the power forecast manufacturer 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 pre-selected time of the target day; use the single-day ultra-short-term power forecast data for the target day from the power forecast manufacturer 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; use the single-day spot power forecast data for the target day from the power forecast manufacturer 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 use the two single-day power forecast data for the target day from the power forecast manufacturer with the highest score based on the single-day two power forecast accuracy ranking as the recommended two single-day power forecast data for the target day.

[0018] In a third aspect, the present application provides a new energy multi-source power prediction data recommendation device, comprising a processor and a memory, wherein the processor is connected to the memory: The processor is configured to call and execute the program stored in the memory; The memory is used to store the program, and the program is at least used to execute the above-mentioned new energy multi-source power prediction data recommendation method.

[0019] The present invention relates to the field of electric power technology, and specifically to a method, device, and equipment for recommending multi-source power forecast data for new energy sources. The method comprises: obtaining basic data including the name of a power forecasting manufacturer, short-term power forecast data within a target time range, ultra-short-term power forecast data, available capacity of a plant, and actual power of a plant; based on the basic data, calculating the single-point ultra-short-term power forecast accuracy, single-day ultra-short-term power forecast accuracy, single-day spot power forecast accuracy, and single-day two-point power forecast accuracy of each power forecasting manufacturer within the target time range, and ranking and scoring them respectively; and recommending power forecasting manufacturers and their power forecast data based on the ranking and scoring results of different forecast types. In this way, suitable power forecasting manufacturers and power forecast data can be quickly recommended to new energy enterprises for different forecast types. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0021] Figure 1 It is a flow chart of a method for recommending new energy multi-source power prediction data provided by an embodiment of the present invention.

[0022] Figure 2 It is a schematic diagram of the principle of the new energy multi-source power prediction data recommendation method provided by an embodiment of the present invention.

[0023] Figure 3 It is a structural diagram of a new energy multi-source power prediction data recommendation device provided by an embodiment of the present invention.

[0024] Figure 4 It is a structural diagram of a new energy multi-source power prediction data recommendation device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0025] To make the objectives, technical solutions, and advantages of the present invention more apparent, the technical solutions of the present invention will be described in detail below. Obviously, the embodiments described are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other implementations obtained by those of ordinary skill in the art without inventive effort are within the scope of protection of the present invention.

[0026] Method Example: Figure 1 : is a flow chart of a method for recommending new energy multi-source power prediction data provided by an embodiment of the present invention. Figure 2 This is a schematic diagram of the principle of the new energy multi-source power prediction data recommendation method provided by the embodiment of the present invention. Figure 1 and Figure 2 , this embodiment may include the following steps: S101. Obtain basic data through an interface.

[0027] Among them, the basic data includes the name of the power forecasting manufacturer, short-term power forecast data within the target time range, ultra-short-term power forecast data, plant and station available capacity and plant and station actual power; among them, short-term power forecast data and ultra-short-term power forecast data are both provided by the power forecasting manufacturer, and plant and station available capacity and plant and station actual power are both provided by new energy plants and stations.

[0028] Specifically, the power forecast vendor name is provided by the power forecast vendor. The target time range can be the most recent seven days. Short-term power forecast data refers to 96 points of short-term power forecast data per day for a single renewable energy plant (such as wind power and photovoltaic power). This data is provided by the power forecast vendor. Ultra-short-term power forecast data refers to 96 points of ultra-short-term power forecast data per day for a single renewable energy plant. This data is provided by the power forecast vendor interface. Plant available capacity refers to 96 points of available capacity data per day for a single renewable energy plant. This data is provided by the plant. Plant actual power refers to 96 points of actual power data per day for a single renewable energy plant. This data is provided by the plant.

[0029] S102. Based on the basic data, calculate the single-point ultra-short-term power forecast accuracy, single-day ultra-short-term power forecast accuracy, single-day spot power forecast accuracy, and single-day two-item power forecast accuracy of each power forecast manufacturer within the target time range.

[0030] Specifically, in this application, based on the aforementioned basic data, the ultra-short-term power forecast accuracy can be calculated based on the root mean square error principle. This includes both the single-point ultra-short-term power forecast accuracy and the single-day ultra-short-term power forecast accuracy. Regarding short-term power forecast accuracy, this application distinguishes between spot power forecast accuracy and two-way power forecast accuracy, calculating the single-day spot power forecast accuracy and the single-day two-way power forecast accuracy separately.

[0031] S103. Rank and score power prediction manufacturers based on accuracy.

[0032] Specifically, the power forecasting vendors are ranked multiple times based on the above four types of accuracy at different time points, and scoring operations are performed based on the results of the multiple rankings, including: Based on the single-point ultra-short-term power forecast accuracy corresponding to at least one pre-selected moment on each day within the target time range, the power forecast manufacturers are ranked by single-point ultra-short-term power forecast accuracy, and a preset score is given to the power forecast manufacturer ranked first at each pre-selected moment.

[0033] The power forecasting manufacturers are ranked based on the single-day ultra-short-term power forecast accuracy of each day within the target time range, and a preset score is given to the power forecasting manufacturer ranked first on each day.

[0034] The power forecasting manufacturers are ranked based on the single-day spot power forecast accuracy of each day within the target time range, and a preset score is given to the power forecasting manufacturer ranked first on each day.

[0035] The power forecasting manufacturers are ranked based on the accuracy of the two power forecasts for each day within the target time range, and a preset score is given to the power forecasting manufacturer ranked first on each day.

[0036] S104. Based on the ranking and scoring results, recommend power prediction manufacturers and power prediction data for different types of predictions.

[0037] Specifically, it includes: using the single-point ultra-short-term power forecast data for the pre-selected time of the target day from the power forecast manufacturer 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 pre-selected time of the target day; using the single-day ultra-short-term power forecast data for the target day from the power forecast manufacturer 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 forecast manufacturer 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 two single-day power forecast data for the target day from the power forecast manufacturer with the highest score based on the single-day two power forecast accuracy ranking as the recommended two single-day power forecast data for the target day.

[0038] The new energy multi-source power forecast data recommendation method provided in the present application obtains basic data including the name of the power forecast manufacturer, short-term power forecast data within the target time range, ultra-short-term power forecast data, available capacity of the plant and actual power of the plant; based on the basic data, calculates the single-point ultra-short-term power forecast accuracy, single-day ultra-short-term power forecast accuracy, single-day spot power forecast accuracy and single-day two-point power forecast accuracy of each power forecast manufacturer within the target time range, and ranks and scores them respectively; based on the ranking and scoring results of different prediction types, recommends power forecast manufacturers and their power forecast data respectively, and can quickly recommend suitable power forecast manufacturers and power forecast data to new energy enterprises for different prediction types.

[0039] Furthermore, in some embodiments of the present application, the calculation formula for the single-point ultra-short-term power prediction accuracy is:

[0040] Among them, x is the power prediction manufacturer logo, D j is the day sign, i is the time sign, x_D j i - ACC SDT Indicates the power forecast manufacturer 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 of the plant at time i of the day; For power prediction manufacturers, D j The predicted power at time i of the day; Cap is the available capacity of the plant; n is the total number of daily assessment periods.

[0041] The calculation formula for the single-day ultra-short-term power prediction accuracy is:

[0042] Among them, x_D j- ACC SD Indicates that power forecast manufacturers are in D j The single-day ultra-short-term power forecast accuracy of the day.

[0043] The calculation formula for the single-day spot power forecast accuracy is:

[0044] x_D j- ACC D Indicates the power forecast manufacturer x in D j The accuracy of the daily spot power forecast.

[0045] For the accuracy of the two power forecasts per day, when the location of the new energy plant has a dedicated calculation formula for the accuracy of the two power forecasts per day, the accuracy of the two power forecasts per day of each power forecast manufacturer within the target time range is calculated based on the corresponding dedicated calculation formula; when the location of the new energy plant does not have a dedicated calculation formula for the accuracy of the two power forecasts per day, the accuracy of the two power forecasts per day of each power forecast manufacturer within the target time range is calculated based on the calculation formula for the accuracy of the single-day spot power forecast.

[0046] The following is a detailed description of the new energy multi-source power prediction data recommendation method provided by this application by way of a specific embodiment, specifically including: The first step is to set the operating day as D-day (i.e., the current date, corresponding to the scenario in this application, that is, it is necessary to select an appropriate power forecast manufacturer for D-day to perform power forecasting). When obtaining basic data, specifically obtain the 96-point daily actual power (i.e., the actual power of the plant station) of plant station A in the past week, i.e., D-7, D-6, D-5, D-4, D-3, D-2, and D-1 (i.e., the 7 days closest to D-day); the 96-point daily available capacity (i.e., the available capacity of the plant station) for D-7, D-6, D-5, D-4, D-3, D-2, and D-1 in the past week; and the 96-point daily short-term power forecast and ultra-short-term power forecast data for D-7, D-6, D-5, D-4, D-3, D-2, and D-1 associated with power forecast manufacturers a, b, and c of plant station A...for the past week.

[0047] The second step is to calculate the single-point ultra-short-term power forecast accuracy ACC of each manufacturer, including manufacturer a, manufacturer b, manufacturer c, etc., on D-7, D-6, D-5, D-4, D-3, D-2, and D-1 power forecasts in the past week based on the acquired data. SDT , that is, the ACC of each manufacturer SDT The data contains 7*96 data items.

[0048] Taking manufacturer a as an example, calculate its single-point ultra-short-term power forecast accuracy a_D1i-ACC at time i on day D1 (i.e. day D-1) SDT The specific method is as follows:

[0049] in, and They represent the actual power of the plant at time i on day D1 and the predicted power of manufacturer a respectively.

[0050] Based on the same principle, the single-point ultra-short-term power forecast accuracy at time i on D1 of other manufacturers can be calculated, as well as the single-point ultra-short-term power forecast accuracy of all manufacturers on other days, namely D-7, D-6, D-5, D-4, D-3, and D-2.

[0051] The third step is to calculate the single-day ultra-short-term power forecast accuracy of each power forecast manufacturer on D-7, D-6, D-5, D-4, D-3, D-2, and D-1 in the past week, as well as the single-day spot power forecast accuracy and the single-day two-item power forecast accuracy.

[0052] Taking manufacturer A as an example, calculate the single-day ultra-short-term power forecast accuracy for D1 , Single-day spot power forecast accuracy , as follows:

[0053]

[0054] It should be noted that the accuracy of the two power forecasts for a single day can be based on the calculation formula published by the location of the new energy plant or station. If no announcement is made, the calculation formula shall be consistent with the above-mentioned calculation formula for the accuracy of the single-day spot power forecast.

[0055] Based on the same principle, we can calculate the single-day ultra-short-term power forecast accuracy, single-day spot power forecast accuracy, and single-day two-way power forecast accuracy for other manufacturers on D1. We can also use the same principle to calculate the single-day ultra-short-term power forecast accuracy, single-day spot power forecast accuracy, and single-day two-way power forecast accuracy for each manufacturer on D-7, D-6, D-5, D-4, D-3, and D-2.

[0056] The fourth step is to perform a scoring operation on the manufacturer's accuracy ranking based on the accuracy obtained above. If the accuracy ranks first, the score is 1, and the scores are accumulated.

[0057] The following is a detailed introduction based on the ranking score of single-point ultra-short-term power prediction accuracy: When ranking the single-point ultra-short-term power forecast accuracy, you can select an evaluation time point, that is, a pre-selected time point. For example, select the single-point ultra-short-term power forecast accuracy of any one or several time points among the 96 points, arrange the single-point ultra-short-term power forecast accuracy of each manufacturer at the corresponding time point on D-1 in descending order, and give 1 point to the manufacturer ranked first.

[0058] Based on the same principle, all other dates (D-7, D-6, D-5, D-4, D-3, D-2) are ranked and scored. Then, the scores of manufacturer a, manufacturer b, manufacturer c, ... manufacturer n are summed up to obtain the score of each manufacturer, i.e., a_ACC SDT _Score, b_ACC SDT _Score, c_ACC SDT _Score,…n_ACC SDT _Score.

[0059] Based on the same principle, each manufacturer's single-day ultra-short-term power forecast accuracy, single-day spot power forecast accuracy, and single-day two-item power forecast accuracy are ranked and scored.

[0060] Taking the single-day ultra-short-term power forecast accuracy as an example: Arrange the single-day ultra-short-term power forecast accuracy of each manufacturer on D-1 in descending order, select the manufacturer ranked first, and score it 1. The same applies to other days.

[0061] Based on the above scoring, the scores of manufacturer a, manufacturer b, manufacturer c, ... manufacturer n are summed up to get the single-day ultra-short-term power forecast accuracy score of each manufacturer, that is, a_ACC SD _Score, b_ACC SD _Score, c_ACC SD _Score,…n_ACC SD _Score.

[0062] The ranking and scoring principles for the single-day spot power forecast accuracy and the single-day two-item power forecast accuracy are consistent with the ranking and scoring principles for the single-day ultra-short-term power forecast accuracy mentioned above. Based on the same principles, the single-day spot power forecast accuracy and the single-day two-item power forecast accuracy of each manufacturer can be obtained respectively, 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.

[0063] The fifth step is to make recommendations based on the scoring results of each manufacturer obtained above.

[0064] Specifically, for the single-point ultra-short-term power prediction accuracy, the single-point ultra-short-term power prediction accuracy ranking score results of each manufacturer at the evaluation time point are arranged in descending order, and the ultra-short-term power prediction value at the D-day evaluation time point provided by the manufacturer with the highest score is used as the recommended ultra-short-term power prediction result at the corresponding time point on D-day.

[0065] For single-day ultra-short-term power forecast accuracy, each vendor's single-day ultra-short-term power forecast accuracy ranking is ranked in descending order. The ultra-short-term power forecast values for all time points on Day D provided by the highest-scoring vendor are used as the recommended ultra-short-term power forecast for Day D. Based on the same principle, the spot power forecast and two power forecast data sets for Day D are recommended.

[0066] The new energy multi-source power forecast data recommendation method provided in this application can realize the data access and processing of multiple power forecast manufacturers through the interface, and realize that multiple manufacturers use a unified and measurable forecast accuracy calculation result to display the corresponding power forecast data on the same platform. At the same time, by processing and calculating the multi-source forecast data, the accuracy of the power forecast of each manufacturer is recalculated and ranked using historical forecast data, and the operating day forecast data provided by the one with the highest score will be used as the recommendation result. By establishing a unified and measurable accuracy calculation and evaluation standard and process, it can ensure that all manufacturers are evaluated under the same calculation conditions, ensuring the timeliness, reliability, accuracy, etc. of the forecast result evaluation, and quickly providing new energy plants and stations with data of reference value, indirectly improving the competitiveness and benefits of new energy plants and stations in participating in market transactions.

[0067] Device Example: The present invention also provides a new energy multi-source power prediction data recommendation device for implementing the above method embodiment. Figure 3 FIG. 1 is a schematic diagram of a structure of a device for recommending new energy multi-source power prediction data according to an embodiment of the present invention. Figure 3 As shown, the device includes: The acquisition module 11 is used to obtain basic data through the interface. The basic data includes the name of the power forecast manufacturer, short-term power forecast data within the target time range, ultra-short-term power forecast data, plant and station available capacity and plant and station actual power; among them, the short-term power forecast data and ultra-short-term power forecast data are both provided by the power forecast manufacturer, and the plant and station available capacity and plant and station actual power are both provided by new energy plants and stations.

[0068] The calculation module 12 is used to calculate the single-point ultra-short-term power forecast accuracy, single-day ultra-short-term power forecast accuracy, single-day spot power forecast accuracy and single-day two-point power forecast accuracy of each power forecast manufacturer within the target time range based on basic data.

[0069] The ranking scoring module 13 is used to rank the power forecasting manufacturers based on the single-point ultra-short-term power forecast accuracy corresponding to at least one pre-selected moment on each day within the target time range, and calculate a preset score for the power forecasting manufacturer ranked first at each pre-selected moment; rank the power forecasting manufacturers based on the single-day ultra-short-term power forecast accuracy of each day within the target time range, and calculate a preset score for the power forecasting manufacturer ranked first on each day; rank the power forecasting manufacturers based on the single-day spot power forecast accuracy of each day within the target time range, and calculate a preset score for the power forecasting manufacturer ranked first on each day; and rank the power forecasting manufacturers based on the single-day two-time power forecast accuracy of each day within the target time range, and calculate a preset score for the power forecasting manufacturer ranked first on each day.

[0070] The recommendation module 14 is used to use the single-point ultra-short-term power forecast data for the pre-selected time of the target day from the power forecast manufacturer 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 pre-selected time of the target day; use the single-day ultra-short-term power forecast data for the target day from the power forecast manufacturer 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; use the single-day spot power forecast data for the target day from the power forecast manufacturer 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; use the two single-day power forecast data for the target day from the power forecast manufacturer with the highest score based on the single-day two power forecast accuracy ranking as the recommended two single-day power forecast data for the target day.

[0071] Regarding the apparatus in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0072] The present invention also provides a new energy multi-source power prediction data recommendation device for implementing the above method embodiment. Figure 4 FIG. 1 is a schematic diagram of a new energy multi-source power prediction data recommendation device provided by an embodiment of the present invention. Figure 4 As shown, the device for recommending new energy multi-source power forecast data in this embodiment includes a processor 21 and a memory 22, wherein the processor 21 is connected to the memory 22. The processor 21 is configured to call and execute a program stored in the memory 22; the memory 22 is configured to store a program that is configured to at least execute the method for recommending new energy multi-source power forecast data in the above embodiment.

[0073] The specific implementation scheme of the new energy multi-source power prediction data recommendation device provided in the embodiment of the present application 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.

[0074] It can be understood that the same or similar parts of the above embodiments can be referenced to each other, and the contents not described in detail in some embodiments can refer to the same or similar contents in other embodiments.

[0075] It should be noted that, in the description of the present invention, the terms "first", "second", etc. are used for descriptive purposes only and should not be understood as indicating or implying relative importance. In addition, in the description of the present invention, unless otherwise specified, the meaning of "plurality" is at least two.

[0076] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may be performed out of the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present invention pertain.

[0077] It should be understood that various components of the present invention may be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods may be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof may be used: a discrete logic circuit having logic gate circuits for implementing logic functions on data signals, an application-specific integrated circuit having suitable combinational logic gate circuits, a programmable gate array (PGA), a field-programmable gate array (FPGA), etc.

[0078] Those skilled in the art will understand that all or part of the steps in the method of the above embodiment can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0079] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing module, or each unit may exist physically separately, or two or more units may be integrated into a single module. The aforementioned integrated modules may be implemented in the form of hardware or in the form of software functional modules. If the integrated modules are implemented in the form of software functional modules and sold or used as independent products, they may also be stored in a computer-readable storage medium.

[0080] The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc.

[0081] Throughout this specification, reference to terms such as "one embodiment," "some embodiments," "examples," "specific examples," or "some examples" means that a specific feature, structure, material, or characteristic described in conjunction with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations 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 any one or more embodiments or examples.

[0082] Although the embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and are not to be construed as limitations on the present invention. A person skilled in the art may change, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. A method for recommending new energy multi-source power prediction data, characterized in that: include: Obtain basic data through the interface, the basic data including the name of the power forecasting manufacturer, short-term power forecast data within the target time range, ultra-short-term power forecast data, plant and station available capacity, and plant and station actual power; wherein the short-term power forecast data and ultra-short-term power forecast data are both provided by the power forecasting manufacturer, and the plant and station available capacity and plant and station actual power are both provided by the new energy plant and station; Based on the basic data, calculate the single-point ultra-short-term power forecast accuracy, single-day ultra-short-term power forecast accuracy, single-day spot power forecast accuracy, and single-day two-item power forecast accuracy of each power forecast manufacturer within the target time range; Based on the single-point ultra-short-term power forecast accuracy corresponding to at least one pre-selected moment on each day within the target time range, the power forecast vendors are ranked by their single-point ultra-short-term power forecast accuracy, and a preset score is awarded to the power forecast vendor that ranks first at each pre-selected moment; The power forecasting vendors are ranked based on their single-day ultra-short-term power forecast accuracy for each day within the target time range, and a preset score is awarded to the power forecasting vendor that ranks first on each day; Power forecast vendors are ranked based on their single-day spot power forecast accuracy for each day within the target time range, and the top-ranked power forecast vendor on each day is awarded a preset score. Power forecast vendors are ranked based on their accuracy of two power forecasts per day within the target time range, and the top-ranked power forecast vendor on each day is given a preset score. The single-point ultra-short-term power forecast data of the power forecasting manufacturer with the highest single-point ultra-short-term power forecast accuracy ranking score at the pre-selected time of the target day will be used as the recommended single-point ultra-short-term power forecast data at the pre-selected time of the target day; The single-day ultra-short-term power forecast data of the power forecasting manufacturer with the highest single-day ultra-short-term power forecast accuracy ranking score for the target day will be used as the recommended single-day ultra-short-term power forecast data for the target day; The power forecast data of the power forecasting manufacturer with the highest single-day spot power forecast accuracy ranking score for the target day will be used as the recommended single-day spot power forecast data for the target day; The power forecast data for the target day of the power forecast manufacturer with the highest single-day power forecast accuracy ranking score will be used as the recommended single-day power forecast data for the target day.

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 latest 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 forecast data, ultra-short-term power forecast data, plant available capacity and plant actual power are all data at 96 time points in a day, where the intervals between adjacent time points are 15 minutes.

4. The method for recommending new energy multi-source power prediction data according to claim 1, characterized in that: The calculation formula for the single-point ultra-short-term power prediction accuracy is: Among them, x is the power prediction manufacturer logo, D j is the day sign, i is the time sign, x_D j i - ACC SDT Indicates the power forecast manufacturer 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 of the plant at time i of the day; For power prediction manufacturers, D j The predicted power at time i of the day; Cap is the available capacity of the plant; n is the total number of daily assessment periods.

5. The method for recommending new energy multi-source power prediction data according to claim 4, characterized in that: The calculation formula for the single-day ultra-short-term power prediction accuracy is: Among them, x_D j- ACC SD Indicates the power forecast manufacturer x in D j The single-day ultra-short-term power forecast accuracy of the day.

6. The method for recommending new energy multi-source power prediction data according to claim 5, characterized in that: The calculation formula for the single-day spot power prediction accuracy is: x_D j- ACC D Indicates the power forecast manufacturer x in D j The accuracy of the daily spot power forecast.

7. The method for recommending new energy multi-source power prediction data according to claim 1, characterized in that: When the new energy plant site has a dedicated calculation formula for the accuracy of two power forecasts per day, the accuracy of two power forecasts per day of each power forecast manufacturer within the target time range is calculated based on the corresponding dedicated calculation formula.

8. The method for recommending new energy multi-source power prediction data according to claim 7, characterized in that: When there is no dedicated calculation formula for the accuracy of two power forecasts per day at the location of the new energy plant, the accuracy of two power forecasts per day of each power forecast manufacturer within the target time range is calculated based on the calculation formula for the accuracy of one-day spot power forecast.

9. A new energy multi-source power prediction data recommendation device, characterized in that: include: an acquisition module, configured to acquire basic data through an interface, the basic data including the name of the power forecasting manufacturer, short-term power forecast data within a target time range, ultra-short-term power forecast data, plant and station available capacity, and plant and station actual power; wherein the short-term power forecast data and ultra-short-term power forecast data are both provided by the power forecasting manufacturer, and the plant and station available capacity and plant and station actual power are both provided by the new energy plant and station; A calculation module is used to calculate the single-point ultra-short-term power forecast accuracy, single-day ultra-short-term power forecast accuracy, single-day spot power forecast accuracy and single-day two-item power forecast accuracy of each power forecast manufacturer within the target time range based on the basic data; A ranking and scoring module is used to rank the power forecasting manufacturers by their single-point ultra-short-term power forecast accuracy based on the single-point ultra-short-term power forecast accuracy corresponding to at least one pre-selected moment on each day within the target time range, and calculate a preset score for the power forecasting manufacturer ranked first at each pre-selected moment; rank the power forecasting manufacturers by their single-day ultra-short-term power forecast accuracy based on the single-day ultra-short-term power forecast accuracy of each day within the target time range, and calculate a preset score for the power forecasting manufacturer ranked first on each day; rank the power forecasting manufacturers by their single-day spot power forecast accuracy based on the single-day spot power forecast accuracy of each day within the target time range, and calculate a preset score for the power forecasting manufacturer ranked first on each day; and rank the power forecasting manufacturers by their single-day two-time power forecast accuracy based on the single-day two-time power forecast accuracy of each day within the target time range, and calculate a preset score for the power forecasting manufacturer ranked first on each day; The recommendation module is used to use the single-point ultra-short-term power forecast data for the pre-selected time of the target day from the power forecast manufacturer 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 pre-selected time of the target day; use the single-day ultra-short-term power forecast data for the target day from the power forecast manufacturer 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; use the single-day spot power forecast data for the target day from the power forecast manufacturer 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 use the two single-day power forecast data for the target day from the power forecast manufacturer with the highest score based on the single-day two power forecast accuracy ranking as the recommended two single-day power forecast data for the target day.

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

Images