A regional energy joint output prediction correction method and system

Abstract

The present invention relates to the field of new energy power generation control technology, and in particular to a regional energy joint output prediction correction method and system, the method comprising: obtaining historical environmental data, historical power prediction data, historical actual power data, environmental data at the latest moment, and power prediction data at the latest moment of each power generation unit in the region; calculating the power prediction comprehensive credibility and power short-term prediction accuracy of each power generation unit based on the acquired data; and calculating the corrected power prediction value based on the power prediction data at the latest moment, the power prediction comprehensive credibility, and the power short-term prediction accuracy. The present invention realizes the prediction of the output of heterogeneous multi-energy power generation units in the region, solves the problem of insufficient accuracy and low timeliness of joint output prediction under regional heterogeneous multi-energy conditions, and supports the construction of large energy bases.

Description

Technical Field

[0001] The present invention relates to the field of renewable energy power generation control technology, and in particular to a regional energy joint output prediction and correction method and system. Background Art

[0002] Northwest my country is a vast region with rich solar and wind energy resources, and is an important region for the development of clean energy. At present, my country is committed to building nine large-scale clean energy bases, which not only have large installed capacity, but also integrate a variety of heterogeneous energy sources such as photovoltaic power generation, wind power generation, solar thermal power generation, and thermal power generation. The conversion, coupling and decoupling process of its internal energy forms is extremely complex.

[0003] As the base covers a wide area, the distribution of wind and solar resources varies significantly, and the power generation endowment of each type of resource has its own characteristics. At the same time, each power generation resource is restricted by multiple factors such as time and space, and there is a large degree of uncertainty, which brings great challenges to the scheduling and management of energy.

[0004] In order to give full play to the overall advantages of large-scale clean energy bases and improve energy utilization efficiency, it is urgently necessary to use advanced technologies such as big data, artificial intelligence, and machine learning to accurately predict the overall available capacity and output from the perspective of multi-energy complementary integration.

[0005] However, China still faces many difficulties in predicting the joint output of large-scale clean energy bases, such as insufficient prediction accuracy and low timeliness of joint predictions, which to some extent restrict the efficient utilization and development of clean energy. Summary of the invention

[0006] The purpose of the present invention is to solve at least one technical problem in the background technology and to provide a method and system for correcting regional energy joint output prediction.

[0007] The technical problem to be solved by the present invention is to provide a regional energy joint output prediction and correction method, which is applied to a region including multiple power generation units, and the method comprises:

[0008] Obtain historical environmental data, historical power forecast data, and historical actual power data of each power generation unit in the region;

[0009] Obtain the latest environmental data and power forecast data of each power generation unit at the latest moment;

[0010] Calculating the comprehensive credibility of power prediction of each power generation unit according to the historical environmental data, the historical power prediction data, and the historical actual power data;

[0011] According to the environmental data at the latest moment, trace back a first preset time period, match the data at the nearest similar moment from the historical environmental data according to the first preset time period, and calculate the short-term power prediction accuracy of each power generation unit according to the data at the nearest similar moment;

[0012] The revised power prediction value is calculated based on the power prediction data at the latest moment, the comprehensive credibility of the power prediction and the accuracy of the short-term power prediction.

[0013] Further, the power generation unit includes: a wind power station, a photovoltaic power station, a hydroelectric power station, and a solar thermal power station;

[0014] The environmental data include: light radiation intensity, wind speed, altitude, temperature, and rainfall.

[0015] Furthermore, the latest environmental data and the latest power prediction data include: the latest ultra-short-term environmental data and the latest ultra-short-term power prediction value of the power generation unit.

[0016] Furthermore, the power prediction comprehensive credibility of each power generation unit is calculated by formula (1):

[0017] (1)

[0018] in, Indicates Power generation units, Indicates the power generation unit Historical data, Indicates power generation unit The amount of historical data, and Respectively represent power generation units No. Historical power forecast data and power generation units No. Actual power data, Indicates power generation unit Rated power generation, Indicates power generation unit comprehensive credibility.

[0019] Furthermore, matching the historical environment data to the data at the nearest similar time according to the first preset time length includes:

[0020] Taking a group of environmental data of the latest moment before the moment of environmental data for a first preset time as a benchmark, find the historical environmental data with the most similar features and the smallest comprehensive distance within the first preset time from the historical environmental data as the data of the most recent similar moment.

[0021] Furthermore, the minimum comprehensive distance between the two sets of data is calculated by formula (2):

[0022] (2)

[0023] in, Indicates the calculation time scale, Indicates power generation unit The historical environmental data set with the shortest distance from the environmental data at the latest moment, represents the time series of light irradiance intensity within the first preset time length, represents the temperature time series within the first preset time length, represents the wind speed time series within the first preset time length, represents the rainfall time series within the first preset time length, is based on , , and The distance calculation method used as input.

[0024] Furthermore, the distance calculation method DIS adopts one of the following methods: Euclidean distance, Manhattan distance, Minkowski distance, and Mahalanobis distance.

[0025] Furthermore, the power short-term prediction accuracy is calculated by formula (3):

[0026] (3)

[0027] in, represents the power short-term prediction accuracy of the data at the most recent similar moment, represents a power prediction data set in the data at the most recent similar moment, express The i-th data in represents a set of actual power data in the data at the most recent similar moment, express The i-th data in Represents the power prediction data set , the actual power data set The number of data in .

[0028] Furthermore, the corrected power prediction value is calculated by formula (4):

[0029] (4)

[0030] in, represents the corrected power prediction value, represents the number of power generation units in the area, Indicates power generation unit The overall credibility of represents the power short-term prediction accuracy of the data at the most recent similar moment, Indicates power generation unit The latest power forecast data.

[0031] To achieve the above object, the present invention further provides a regional energy joint output prediction and correction system, which is applied to a region including multiple power generation units, and the system includes:

[0032] A data acquisition unit is used to acquire historical environmental data, historical power forecast data, and historical actual power data of each power generation unit in the region; and is also used to acquire the latest environmental data and the latest power forecast data of each power generation unit;

[0033] A data processing unit, used to generate a time series from the acquired data;

[0034] A data calculation unit, used to calculate the power prediction comprehensive credibility and the power short-term prediction accuracy of each power generation unit according to the data generated by the data processing unit; and also used to calculate the corrected power prediction value according to the power prediction data at the latest moment, the power prediction comprehensive credibility and the power short-term prediction accuracy;

[0035] The data output unit is used to output the revised power prediction value and provide an interface for other systems to obtain the revised power prediction value.

[0036] The beneficial effects of the present invention are:

[0037] The present invention proposes a regional energy joint output prediction correction method and system, firstly, the historical environmental data, historical power prediction data, and historical actual power data of each power generation unit in the region are obtained, then the environmental data and power prediction data of each power generation unit at the latest moment are obtained, and then the comprehensive credibility of the power prediction of each power generation unit is calculated according to the historical environmental data, historical power prediction data, and historical actual power data, and then the data at the nearest similar moment in the same time scale as the latest environmental data in the historical environmental data of each power generation unit is matched, and the short-term power prediction accuracy of each power generation unit at the nearest similar moment is calculated, and finally, the corrected power prediction value is calculated according to the latest power prediction data of each power generation unit, the comprehensive credibility of each power generation unit prediction, and the short-term power prediction accuracy of each power generation unit at the nearest similar moment. The present invention realizes the prediction of the output of heterogeneous multi-energy power generation units in the region, solves the problem of insufficient accuracy and low timeliness of joint output prediction under regional heterogeneous multi-energy conditions, and supports the construction of large energy bases. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 Schematically showing a flow chart of a method for forecasting and correcting regional energy joint processing according to an embodiment of the present invention;

[0039] Figure 2 Schematically showing a flow chart of a method for forecasting and correcting regional energy joint processing according to another embodiment of the present invention;

[0040] Figure 3 The structure diagram of a regional energy joint output prediction and correction system according to an embodiment of the present invention is schematically shown. DETAILED DESCRIPTION

[0041] The content of the present invention will now be discussed with reference to exemplary embodiments. It should be understood that the embodiments discussed are only to enable those skilled in the art to better understand and thus implement the content of the present invention, rather than implying any limitation on the scope of the present invention.

[0042] As used herein, the term “including” and variations thereof are to be interpreted as open-ended terms meaning “including, but not limited to.” The term “based on” is to be interpreted as “based, at least in part, on.” The terms “one embodiment” and “an embodiment” are to be interpreted as “at least one embodiment.”

[0043] Embodiment 1

[0044] Figure 1 The following is a schematic diagram showing a flow chart of a method for joint processing prediction and correction of regional energy according to an embodiment of the present invention. Figure 1As shown, according to one embodiment of the present invention, a regional energy joint output forecast correction method is applied to a region including multiple power generation units.

[0045] Power generation units include: wind power stations, photovoltaic power stations, hydroelectric power stations, and solar thermal power stations;

[0046] The method comprises the following steps:

[0047] Step S102: Acquire historical environmental data, historical power prediction data, and historical actual power data of each power generation unit in the region;

[0048] Environmental data include: light radiation intensity, wind speed, altitude, temperature, and rainfall.

[0049] Step S104: Acquire the latest environmental data and the latest power prediction data of each power generation unit;

[0050] Step S106: Calculate the comprehensive credibility of power prediction of each power generation unit according to historical environmental data, historical power prediction data, and historical actual power data;

[0051] Step S108: trace back a first preset time period according to the latest environmental data, match the data at the most recent similar time period from the historical environmental data according to the first preset time period, and calculate the short-term power prediction accuracy of each power generation unit according to the data at the most recent similar time period;

[0052] Step S110: Calculate the corrected power prediction value according to the power prediction data at the latest moment, the comprehensive credibility of the power prediction and the accuracy of the short-term power prediction.

[0053] In this embodiment, the historical environmental data, historical power prediction data, and historical actual power data of each power generation unit in the area are obtained; the environmental data and power prediction data of each power generation unit at the latest moment are obtained; the comprehensive credibility of the power prediction of each power generation unit is calculated based on the historical environmental data, historical power prediction data, and historical actual power data; the data at the nearest similar moment on the same time scale as the latest environmental data in the historical environmental data of each power generation unit is matched, and the short-term power prediction accuracy of each power generation unit at the nearest similar moment is calculated; based on the latest power prediction data of each power generation unit, the comprehensive credibility of the prediction of each power generation unit and the short-term power prediction accuracy of each power generation unit at the nearest similar moment, the corrected power prediction value is calculated and obtained.

[0054] According to an embodiment of the present invention, the latest environmental data and the latest power prediction data include: the most recent ultra-short-term environmental data of the power generation unit and the most recent ultra-short-term power prediction value.

[0055] According to one embodiment of the present invention, the comprehensive reliability of power prediction of each power generation unit is calculated by formula (1):

[0056] (1)

[0057] in, Indicates Power generation units, Indicates the power generation unit Historical data, Indicates power generation unit The amount of historical data, and Respectively represent power generation units No. Historical power forecast data and power generation units No. Actual power data, Indicates power generation unit Rated power generation, Indicates power generation unit comprehensive credibility.

[0058] According to an embodiment of the present invention, matching the historical environment data to the data at the nearest similar moment according to the first preset time length includes:

[0059] Taking a set of environmental data of the first preset time period before the latest environmental data as a benchmark, find the historical environmental data with the most similar features and the smallest comprehensive distance within the first preset time period from the historical environmental data as the data at the most recent similar moment.

[0060] In this embodiment, the historical environmental data of each power generation unit is matched with data at the most similar time to the latest environmental data. Specifically, a group of environmental data contained in a period of time before the time of the latest environmental data is used as a benchmark, and a group of environmental data with the most similar characteristics on the same time scale and closest to the time of the latest environmental data is found from the historical environmental data.

[0061] According to one embodiment of the present invention, the minimum comprehensive distance between two sets of data is calculated by formula (2):

[0062] (2)

[0063] in, Indicates the calculation time scale, Indicates power generation unit The historical environmental data set with the shortest distance from the latest environmental data, represents the time series of light irradiance intensity within the first preset time length, represents the temperature time series within the first preset time length, represents the wind speed time series within the first preset time length, represents the rainfall time series within the first preset time length, is based on , , and The distance calculation method used as input.

[0064] The distance calculation method represented by DIS can use Euclidean distance, Manhattan distance, Minkowski distance, Mahalanobis distance and other distance algorithms.

[0065] According to an embodiment of the present invention, the power short-term prediction accuracy is calculated by formula (3):

[0066] (3)

[0067] in, Indicates the power short-term prediction accuracy of the data at the most recent similar time. represents the power prediction data set in the data at the most recent similar time. express The data, Represents the actual power data set in the data at the most recent similar time. express The data, Represents the power prediction data set , Actual power data set The number of data in .

[0068] According to an embodiment of the present invention, the corrected power prediction value is calculated by formula (4):

[0069] (4)

[0070] in, represents the corrected power prediction value, represents the number of power generation units in the area, Indicates power generation unit The overall credibility of Indicates the power short-term prediction accuracy of the data at the most recent similar time. Indicates power generation unit The latest power forecast data.

[0071] The present invention provides a regional energy joint output forecast correction method for a regional power system containing multiple power generation units (such as wind power, photovoltaic, hydropower and solar thermal power stations); the method first collects the historical and latest environmental data of each power generation unit as well as the power forecast and actual data, calculates the comprehensive credibility of the power forecast and the short-term forecast accuracy of each power generation unit, and then uses these parameters to correct the power forecast value; the method uses advanced data matching technology and comprehensive distance minimization strategy to identify the most similar historical data segments, and performs weighted average correction on the forecast value through a specific formula to improve the accuracy of the forecast. The present invention improves the accuracy of regional energy output forecasts, enhances the dispatching and operation safety of the power system, and is of great significance for optimizing the allocation of power resources and improving the economic benefits of the power grid.

[0072] Embodiment 2

[0073] Figure 2 A schematic diagram of a regional energy joint processing prediction and correction method according to another embodiment of the present invention is shown. Figure 2 As shown, according to an embodiment of the present invention, a method for correcting regional energy joint output forecasting includes the following steps:

[0074] Step S202: Acquire historical environmental data, historical power prediction data, and historical actual power data of each power generation unit in the area.

[0075] The power generation unit refers to the various wind power stations, photovoltaic power stations, hydroelectric power stations, and solar thermal power stations within the region, and does not include the equipment inside the power generation unit.

[0076] Environmental data, including light radiation intensity, wind speed, altitude, temperature, and rainfall.

[0077] Step S204: Obtain the latest environmental data and power prediction data of each power generation unit.

[0078] The latest environmental data and power forecast data specifically refer to the most recent ultra-short-term environmental data and power forecast values ​​of the power generation unit.

[0079] Step S206: Calculate the comprehensive credibility of the power prediction of each power generation unit based on the historical environmental data, the historical power prediction data, and the historical actual power data.

[0080] Calculate the comprehensive credibility of the power prediction of each power generation unit, specifically: obtain the comprehensive credibility through the first calculation formula. The first calculation formula is:

[0081]

[0082] In the formula, Indicates Power generation units, Indicates the power generation unit Historical data, Indicates power generation unit The number of historical data, and Power generation unit No. Historical forecast power data and power generation units No. Actual power data, Indicates power generation unit Rated power generation, Indicates power generation unit The comprehensive credibility of power prediction.

[0083] Step S208: Match the data of the most recent similar moment in the same time scale as the latest environmental data from the historical environmental data of each power generation unit, and calculate the power short-term prediction accuracy of each power generation unit at the most recent similar moment.

[0084] The data at the most similar moment to the latest environmental data in the historical environmental data of each power generation unit is matched. The data is based on a set of environmental data contained in a period of time (a first preset time length) before the moment of the latest environmental data, and a set of environmental data with the most similar characteristics on the same time scale and closest to the moment of the latest environmental data is found from the historical environmental data.

[0085] For example, the latest environmental data is at 14:00 on October 25, 2023, and if we go back 24 hours, the data from 14:00 on October 25, 2023 to 14:00 on October 24, 2023 is a set of environmental data contained in the period before the latest environmental data. With 24 hours as the time scale, we search for a set of environmental data with the most similar features by sliding the time window. At this time, the first preset time length is 24 hours.

[0086] The second calculation formula is used to calculate the minimum comprehensive distance between the two sets of data. The second calculation formula is:

[0087]

[0088] In the formula, Indicates the selection of length of time, Indicates power generation unit The historical environmental data set with the shortest distance from the latest environmental data, represents the time series of light irradiance intensity within the first preset time length, represents the temperature time series within the first preset time length, represents the wind speed time series within the first preset time length, represents the rainfall time series within the first preset time length, is based on , , and The distance calculation method used as input.

[0089] The distance calculation method represented by can use Euclidean distance, Manhattan distance, Minkowski distance, Mahalanobis distance and other distance algorithms.

[0090] Step S210: Calculate and obtain a revised power forecast value based on the latest power forecast data of each power generation unit, the comprehensive reliability of the forecast of each power generation unit, and the accuracy of the short-term power forecast of each power generation unit at the most recent similar moment.

[0091] In the embodiment of the present invention, the power short-term prediction accuracy is based on the aforementioned , get the predicted power set for the time period corresponding to this set , Actual power set , the short-term power prediction accuracy is obtained through the third calculation formula.

[0092] The power short-term prediction accuracy is calculated by the third calculation formula. The third calculation formula is:

[0093]

[0094] In the formula, Indicates power generation unit exist The power short-term prediction accuracy of the corresponding time period is collected. Represents the power prediction data set , Actual power data set The number of data in .

[0095] It can be understood that the power prediction data set and actual power data set The number of data in is the same, both .

[0096] The corrected power prediction value is obtained by calculation using the fourth calculation formula.

[0097] The fourth calculation formula is:

[0098]

[0099] In the formula, It represents the forecast value of the combined output of power generation units in the region. represents the number of power generation units in the area, Indicates power generation unit The latest power forecast data.

[0100] The regional energy joint output forecast correction method of the present invention accurately calculates the comprehensive credibility of the power forecast and the short-term forecast accuracy of the power generation unit by comprehensively analyzing the historical and latest environmental data, power forecast data and actual power data; by adopting advanced data matching technology and comprehensive distance minimization strategy to identify the historical data segment most similar to the latest environmental data, and correcting the power forecast value through a specific calculation formula; the present invention improves the accuracy of the output forecast of the power generation unit, enhances the dispatch optimization and operation safety of the power system, and is of great significance for improving the economic benefits of the power grid and realizing efficient energy utilization.

[0101] Embodiment 3

[0102] Figure 3 The following is a schematic diagram showing the structure of a regional energy joint output prediction and correction system according to an embodiment of the present invention. Figure 3 As shown, according to one embodiment of the present invention, a regional energy joint output prediction and correction system is applied to a region including multiple power generation units, and the system includes:

[0103] The data acquisition unit 10 is used to acquire the historical environmental data, historical power prediction data, and historical actual power data of each power generation unit in the region; and is also used to acquire the latest environmental data and the latest power prediction data of each power generation unit;

[0104] A data processing unit 20, used to generate a time series from the data acquired by the data acquisition unit;

[0105] The data calculation unit 30 is used to calculate the power prediction comprehensive credibility and the power short-term prediction accuracy of each power generation unit according to the data generated by the data processing unit; and is also used to calculate the corrected power prediction value according to the power prediction data at the latest moment, the power prediction comprehensive credibility and the power short-term prediction accuracy;

[0106] The data output unit 40 is used to output the revised power prediction value and provide an interface for other systems to obtain the revised power prediction value.

[0107] According to an embodiment of the present invention, a regional energy joint output prediction and correction system includes a data acquisition unit 10, a data processing unit 20, a data calculation unit 30, and a data output unit 40. Specifically, the functions of each unit are as follows:

[0108] The data acquisition unit 10 is used to acquire the historical environmental data, historical power prediction data, and historical actual power data of each power generation unit in the area; and acquire the latest environmental data and power prediction data of each power generation unit.

[0109] A data processing unit 20 is used to generate a time series from the acquired specific data;

[0110] The data operation unit 30 is used to calculate the comprehensive credibility of the power prediction of each power generation unit, match the data of the most recent similar moment in the same time scale as the latest environmental data, calculate the accuracy of the short-term power prediction of each power generation unit at the most recent similar moment, and calculate and obtain the corrected power prediction value;

[0111] The data output unit 40 outputs the corrected power prediction value and provides an interface for other systems to obtain the value.

[0112] According to one embodiment of the present invention, an electronic device includes a processor, a memory, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, any regional energy joint output prediction and correction method is implemented.

[0113] According to one embodiment of the present invention, a computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, any regional energy joint output prediction and correction method is implemented.

[0114] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described systems, devices and media can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0115] The present invention realizes the prediction of the output of heterogeneous multi-energy power generation units in a region, solves the problems of insufficient accuracy and low timeliness of joint output prediction under regional heterogeneous multi-energy conditions, and supports the construction of large energy bases.

[0116] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the inventive concept. For example, the above features are replaced with (but not limited to) technical features with similar functions disclosed in the present application.

[0117] It should be understood that the size of the serial numbers of each step in the content of the invention and the embodiments of the present invention does not absolutely mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

Claims

1. A regional energy joint output forecast correction method, applied to a region including multiple power generation units, characterized in that: The method comprises: Obtain historical environmental data, historical power forecast data, and historical actual power data of each power generation unit in the region; Obtain the latest environmental data and power forecast data of each power generation unit at the latest moment; The power prediction comprehensive credibility of each power generation unit is calculated based on the historical environmental data, the historical power prediction data, and the historical actual power data; wherein the power prediction comprehensive credibility of each power generation unit is calculated by formula (1): （1） Wherein, j represents the jth power generation unit, i represents the i-th historical data of the power generation unit, represents the number of historical data of power generation unit j, and They represent the i-th historical power forecast data of power generation unit j and the i-th actual power data of power generation unit j, respectively. represents the rated power generation of power generation unit j, represents the comprehensive credibility of power generation unit j; According to the environmental data at the latest moment, trace back a first preset time period, match the data at the most recent similar moment from the historical environmental data according to the first preset time period, and calculate the power short-term prediction accuracy of each power generation unit according to the data at the most recent similar moment; wherein the power short-term prediction accuracy is calculated by formula (3): （3） in, represents the power short-term prediction accuracy of the data at the most recent similar moment, represents a power prediction data set in the data at the most recent similar moment, express The i-th data in represents a set of actual power data in the data at the most recent similar moment, express The i-th data in Represents the power prediction data set , the actual power data set The number of data in The revised power forecast value is calculated according to the power forecast data at the latest moment, the comprehensive credibility of the power forecast and the accuracy of the short-term power forecast; wherein the revised power forecast value is calculated by formula (4): （4） in, represents the corrected power prediction value, represents the number of power generation units in the area, represents the comprehensive credibility of power generation unit j, represents the power short-term prediction accuracy of the data at the most recent similar moment, Indicates the latest power prediction data of power generation unit j.

2. The regional energy joint output prediction and correction method according to claim 1 is characterized by: The power generation units include: wind power stations, photovoltaic power stations, hydropower stations, and solar thermal power stations; The environmental data include: light radiation intensity, wind speed, altitude, temperature, and rainfall.

3. The regional energy joint output prediction and correction method according to claim 1, characterized in that: The latest environmental data and the latest power prediction data include: the latest ultra-short-term environmental data and the latest ultra-short-term power prediction value of the power generation unit.

4. The regional energy joint output prediction and correction method according to claim 1, characterized in that: Matching the historical environment data to the data at the nearest similar time according to the first preset time length includes: Taking a group of environmental data of the latest moment before the moment of environmental data for a first preset time as a benchmark, find the historical environmental data with the most similar features and the smallest comprehensive distance within the first preset time from the historical environmental data as the data of the most recent similar moment.

5. The regional energy joint output prediction and correction method according to claim 4 is characterized in that: The minimum comprehensive distance between two sets of data is calculated by formula (2): （2） in, Indicates the calculation time scale, The historical environmental data set representing the minimum distance between power generation unit j and the environmental data at the latest moment, represents the time series of light irradiance intensity within the first preset time length, represents the temperature time series within the first preset time length, represents the wind speed time series within the first preset time length, represents the rainfall time series within the first preset time length, is based on , , and The distance calculation method used as input.

6. The regional energy joint output prediction and correction method according to claim 5, characterized in that: The distance calculation method DIS adopts one of the following methods: Euclidean distance, Manhattan distance, Minkowski distance, and Mahalanobis distance.

7. A regional energy joint output prediction and correction system, applied to a region including multiple power generation units, characterized in that: The system comprises: A data acquisition unit is used to acquire historical environmental data, historical power forecast data, and historical actual power data of each power generation unit in the region; and is also used to acquire the latest environmental data and the latest power forecast data of each power generation unit; A data processing unit, used to generate a time series from the acquired data; The data calculation unit is used to calculate the power prediction comprehensive credibility and the power short-term prediction accuracy of each power generation unit according to the data generated by the data processing unit; and is also used to calculate the corrected power prediction value according to the power prediction data at the latest moment, the power prediction comprehensive credibility and the power short-term prediction accuracy; wherein the power prediction comprehensive credibility of each power generation unit is calculated by formula (1): （1） Wherein, j represents the jth power generation unit, i represents the i-th historical data of the power generation unit, represents the number of historical data of power generation unit j, and They represent the i-th historical power forecast data of power generation unit j and the i-th actual power data of power generation unit j, respectively. represents the rated power generation of power generation unit j, represents the comprehensive credibility of power generation unit j; The power short-term prediction accuracy is calculated by formula (3): （3） in, Indicates the power short-term prediction accuracy of the data at the most recent similar time. represents a power prediction data set in the data at the most recent similar moment, express The i-th data in represents a set of actual power data in the data at the most recent similar moment, express The i-th data in Represents the power prediction data set , the actual power data set The number of data in The corrected power prediction value is calculated by formula (4): （4） in, represents the corrected power prediction value, represents the number of power generation units in the area, represents the comprehensive credibility of power generation unit j, represents the power short-term prediction accuracy of the data at the most recent similar moment, represents the latest power forecast data of power generation unit j; The data output unit is used to output the revised power prediction value and provide an interface for other systems to obtain the revised power prediction value.

Images