New energy available power judgment system and method based on cross validation of multiple algorithms

Abstract

The invention discloses a new energy available power judgment system based on multi-algorithm cross validation, and the system comprises the steps: constructing an available power calculation model of each new energy station, and carrying out the available power calculation through employing a template machine method and a meteorological extrapolation method; judging the non-limited state of the station, marking the power limiting moment and the non-limited moment, judging the power limiting state according to the available power calculated by the template machine method, the available power calculated by the meteorological extrapolation method, the power issued by the AGC scheduling of the station and the deviation ratio obtained by the actual power, and marking the power limiting moment and the non-limited moment; and on the basis of cross validation of available power accuracy, calculating available power accuracy of a template machine method, available power accuracy of a meteorological extrapolation method and available power accuracy of station reporting, and verifying the available power accuracy of station reporting according to the maximum value in the accuracy. Evaluation management of the available power of the new energy station is enhanced, and the accuracy of the available power is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of renewable energy power generation, and in particular to a system and method for judging available power of renewable energy based on cross-validation of multiple algorithms. Background Art

[0002] With the construction of new power systems, the scale of new energy is increasing day by day. The increasing number of new energy stations will have a certain impact on the safe operation of the power grid, optimized dispatching and new energy consumption, and bring pressure to the overall dispatching and management of the power grid. In addition, with the release of two national regulations, the State Grid has put forward higher requirements for the management of new energy. The new energy available power obtained by the power grid dispatching department comes from the reported values ​​of each station, but the reported values ​​of each electric field are not accurate and there are large errors. Therefore, strengthening the evaluation and management of the available power of new energy stations and improving the accuracy of the available power accuracy have become technical problems that need to be solved urgently. Summary of the invention

[0003] The purpose of the present invention is to provide a new energy available power judgment system and method based on cross-validation of multiple algorithms. The present invention strengthens the evaluation and management of the available power of new energy stations, improves the accuracy of the available power accuracy, and is conducive to a comprehensive grasp of the operation status of new energy stations.

[0004] To achieve this purpose, the present invention designs a new energy available power judgment system based on cross-validation of multiple algorithms, which includes:

[0005] The calculation model module is constructed to calculate the available power of each station based on the template method according to the available power calculation unit of the master station side using the template method; the available power calculation unit of the master station side using the meteorological extrapolation method is used to calculate the available power of each station based on the meteorological extrapolation method;

[0006] The non-power-limited state determination module determines the first power-limited state of the station according to the available power of each station based on the template method and the actual power of the station; determines the second power-limited state of the station according to the available power of each station based on the meteorological extrapolation method and the actual power of the station; determines the third power-limited state of the station according to the power dispatched by the station AGC (Automatic Gain Control) and the actual power of the station, and performs a combined cross-validation of the power-limited state to confirm the accurate power-limited state of each corresponding station according to the first power-limited state, the second power-limited state and the third power-limited state of the station, and determines the non-power-limited time of the corresponding station according to the accurate power-limited state of each station;

[0007] The accuracy cross-validation module is used to select the method with the highest accuracy of available power from the available power calculation method based on the station report, the available power calculation method based on the template method and the available power calculation method based on the meteorological extrapolation method as the optimal judgment method for the available power of the station's new energy;

[0008] The accuracy of the available power reported by the station is calculated based on the actual available power of each station at non-power-restricted times and the available power reported by the corresponding station at non-power-restricted times; the accuracy of the available power based on the template method is calculated based on the actual available power of each station at non-power-restricted times and the available power of each station based on the template method; the accuracy of the available power based on the meteorological extrapolation method is calculated based on the actual available power of each station at non-power-restricted times and the available power of each station based on the meteorological extrapolation method.

[0009] Preferably, the specific method of combined cross-validation in the non-power-limited state determination module is: based on the first power-limited state, the second power-limited state and the third power-limited state of the station, combined cross-validation is performed; when any two states are displayed as power-limited states, the station is determined to be in a power-limited state, the power-limited moments and the non-power-limited moments are marked, and the non-power-limited moment data is filtered according to the state marks.

[0010] Beneficial effects of the present invention:

[0011] The present invention is based on constructing an available power calculation model for each new energy station on the main station side of the dispatching department, and respectively adopts a template method and a meteorological extrapolation method to calculate the available power of each station. Based on determining the non-power-restricted state of the station on the main station side and marking the corresponding startup capacity, actual power, available power and other data at the non-power-restricted moment, the available power at the non-power-restricted moment is screened according to the state mark, and then the available power accuracy is calculated according to the actual available power, and the optimal calculation method for the available power of new energy is obtained, thereby improving the accuracy of the accuracy of the available power of the station, strengthening the evaluation and management of the available power of the new energy station, which is conducive to comprehensively grasping the operation of the new energy station, improving the dispatching management level, and providing high-quality services for the development of new energy and promoting the construction of new power systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 It is a structural schematic diagram of the present invention;

[0013] Figure 2 It is a flow chart of the present invention. DETAILED DESCRIPTION

[0014] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents the selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0015] The present invention is further described in detail below with reference to the accompanying drawings and specific embodiments:

[0016] Example 1

[0017] A new energy available power judgment system based on cross-validation of multiple algorithms, such as Figure 1 As shown, it includes:

[0018] The calculation model module is constructed to calculate the available power of each station based on the template method according to the available power calculation unit of the master station side using the template method; the available power calculation unit of the master station side using the meteorological extrapolation method is used to calculate the available power of each station based on the meteorological extrapolation method;

[0019] The non-power-limited state determination module determines the first power-limited state of the station according to the available power of each station based on the template method and the actual power of the station; determines the second power-limited state of the station according to the available power of each station based on the meteorological extrapolation method and the actual power of the station; determines the third power-limited state of the station according to the power dispatched by the station AGC scheduling and the actual power of the station, and performs a combined cross-validation of the power-limited state to confirm the accurate power-limited state of each corresponding station according to the first power-limited state, the second power-limited state and the third power-limited state of the station, and determines the non-power-limited time of the corresponding station according to the accurate power-limited state of each station;

[0020] The accuracy cross-validation module is used to select the method with the highest accuracy of available power from the available power calculation method based on the station report, the available power calculation method based on the template method and the available power calculation method based on the meteorological extrapolation method as the optimal judgment method for the available power of the station's new energy;

[0021] The accuracy of the available power reported by the station is calculated based on the actual available power of each station at non-power-restricted times and the available power reported by the corresponding station at non-power-restricted times; the accuracy of the available power based on the template method is calculated based on the actual available power of each station at non-power-restricted times and the available power of each station based on the template method; the accuracy of the available power based on the meteorological extrapolation method is calculated based on the actual available power of each station at non-power-restricted times and the available power of each station based on the meteorological extrapolation method.

[0022] In the above technical solution, the available power calculation unit of the prototype method in the calculation model building module includes the formula for calculating the available power of each station using the prototype method:

[0023] Based on the mapping relationship between the sample power and the full-field power, the theoretical power P of the site based on the sample method is calculated on the master station side. ylm :

[0024]

[0025] Get the normal startup capacity Q of each new energy station o , calculate the available power P of each station ykm :

[0026]

[0027] Among them, the total installed capacity of each station is Q m The total capacity of the prototype is Q y , the total active power of the sample machine is P y .

[0028] In the above technical solution, the formula for calculating the available power of each station by the meteorological extrapolation method included in the available power calculation unit of the meteorological extrapolation method in the calculation model construction module is:

[0029]

[0030] Among them, the theoretical power of the master station is calculated as P qlm , the startup capacity of each station is Q o , calculate the available power of each station as P qkm , the total installed capacity of each station is Q m .

[0031] In the above technical solution, to obtain the real-time meteorological data of each new energy station, it is necessary to determine whether the data meets the quality requirements. The data that does not meet the quality requirements is optimized and corrected according to the historical meteorological data. The corrected meteorological data and the meteorological extrapolation method are used to calculate the theoretical power of the station based on the meteorological extrapolation method on the master station side.

[0032] In the above technical solution, the available power calculation model is constructed on the master station side by constructing a calculation model module, and two different methods (prototype method and meteorological extrapolation method) are used to calculate the available power of each new energy station. Two estimated values ​​of available power can be obtained through two different calculation methods, providing a data basis for subsequent power-limiting status judgment.

[0033] In the above technical solution, the specific calculation formula for determining the power-limited state of the station by the non-power-limited state determination module according to the available power calculated by the sample machine method and the actual power of the station is:

[0034]

[0035] Among them, the available power is P ykm , the actual power is P m , the deviation rate is D y , if D y If it is greater than the set threshold, it is determined as power restriction and the status is marked as 1; otherwise, it is not power restriction and the status is marked as 0;

[0036] In the above technical solution, the specific calculation formula for determining the power-limiting state of the station by the non-power-limiting state determination module based on the available power calculated by the meteorological extrapolation method and the actual power of the station is:

[0037]

[0038] Among them, the available power is P qkm , the actual power is P m , the deviation rate is D q , if D q If it is greater than the set threshold, it is determined as power restriction and the status is marked as 1; otherwise, it is not power restricted and the status is marked as 0;

[0039] In the above technical solution, the specific calculation formula for determining the power-limited state of the station by the non-power-limited state determination module after calculating the power dispatched by the station AGC scheduling and the actual power of the station is:

[0040]

[0041] Among them, the dispatching power is P a , the actual power is P m , the deviation rate is D a , if D a If it is less than the set threshold, it is judged as power restriction and the status is marked as 1; otherwise, it is not power restriction and the status is marked as 0.

[0042] In the above technical solution, the specific method of combined cross-validation in the non-power-limited state determination module is: based on the first power-limited state, the second power-limited state and the third power-limited state of the station, combined cross-validation is performed; when any two states are displayed as power-limited states, the station is determined to be in power-limited state, the power-limited moments and non-power-limited moments are marked, and the non-power-limited moment data is filtered according to the state mark.

[0043] In the above technical solution, the non-power-limited state determination module determines the power-limited state of the station by comparing the actual power of the station with the available power calculated by three different methods. By combining and cross-validating the three different power-limited state determination methods, the actual power-limited state of the station can be confirmed more accurately, and the non-power-limited time can be determined. The non-power-limited time of each station is determined on the master station side and the corresponding data is marked. The data with the non-power-limited mark is filtered out for calculation in subsequent steps.

[0044] In the above technical solution, the accuracy cross-validation module calculates the specific calculation formula based on the accuracy of the available power reported by the station according to the actual available power of each station at the non-power-limited time and the available power at the non-power-limited time reported by the corresponding station:

[0045]

[0046] Among them, D sP The accuracy rate of available power reported by the station, P m，i is the actual output of power station i at the non-power-limited time, P skm，i The available power reported by power station i during the non-power-limited period, Q i is the power-on capacity of the electric field at the non-power-off time i, n is the number of samples at the non-power-off time in the cycle, if the power-on capacity at a certain time is empty or the power-on capacity is greater than the installed capacity, then Q i The value of is the installed capacity of the station.

[0047] In the above technical solution, the accuracy of the available power of the accuracy cross-validation module based on the template method is calculated according to the actual available power of each station at the non-power-limited time and the specific calculation formula of the available power of each station based on the template method:

[0048]

[0049] Among them, D yP is the accuracy of the available power of the sample machine method, P m，i is the actual output of power station i at the non-power-limited time, P ykm，i is the available power calculated by the sample machine method at the master station side at the non-power-cutoff time i, Q i is the power-on capacity of the electric field at the non-power-off time i, n is the number of samples at the non-power-off time in the cycle, if the power-on capacity at a certain time is empty or the power-on capacity is greater than the installed capacity, then Q iThe value of is the installed capacity of the station.

[0050] In the above technical solution, the accuracy of the available power of the accuracy cross-validation module based on the meteorological extrapolation method is calculated according to the actual available power of each station at the non-power-limited time and the specific calculation formula of the available power of each station based on the meteorological extrapolation method:

[0051]

[0052] Among them, D qP is the accuracy of available power of meteorological extrapolation method, P m，i is the actual output of power station i at the non-power-limited time, P ykm，i is the available power calculated by meteorological extrapolation method at the master station side at the non-power-cutoff time i, Q i is the power-on capacity of the electric field at the non-power-off time i, n is the number of samples at the non-power-off time in the cycle, if the power-on capacity at a certain time is empty or the power-on capacity is greater than the installed capacity, then Q i The value of is the installed capacity of the station.

[0053] In the above technical solution, the specific method of the accuracy cross-validation module to obtain the optimal calculation method according to the maximum value of the available power accuracy is:

[0054] Maximum value of available power accuracy D P Sure:

[0055] D P =Max(D sP , D yP , D qP )

[0056] Among them, D sP The accuracy of the available power reported by the station, D yP is the accuracy of the available power of the sample machine method, D qP is the accuracy of available power of meteorological extrapolation method, based on D P The value verifies the accuracy of the available power reported by the station. If D P =D sP , then the accuracy of available power reported by the verification station is high, and the available power calculation method selected by the station is the optimal calculation method; otherwise, the accuracy of available power reported by the verification station is low, and the available power calculation method selected by the station is not the optimal calculation method, and a recommendation is issued for the station to make the best selection.

[0057] In the above technical solution, the accuracy cross-validation module compares the accuracy of different methods and selects the method with the highest accuracy from the three available power calculation methods as the optimal new energy available power judgment method, thereby improving the accuracy and reliability of the overall system and providing suggestions to each station.

[0058] In the above technical solution, by calculating and comparing the difference between the actual available power and the reported power and the accuracy of different methods, the accuracy of each method can be quantified and the most reliable method can be selected to determine the available power of the station. At the same time, this also helps to monitor and improve the power prediction and reporting mechanism of the station, thereby improving the accuracy and reliability of the overall system.

[0059] Example 2

[0060] A method for judging the available power of new energy based on cross-validation of multiple algorithms, such as Figure 2 As shown, at the main station side of the dispatching department, an available power calculation model for each new energy station is constructed, and the available power is calculated by the template method and the meteorological extrapolation method respectively; at the main station side, the non-limited state of the station is determined and the power-limited time and the non-power-limited time are marked, and the power-limited state is determined according to the available power calculated by the template method, the available power calculated by the meteorological extrapolation method, the power sent by the station AGC dispatching, and the deviation rate obtained by the actual power, and the power-limited time and the non-power-limited time are marked, and the corresponding data of the non-power-limited time are filtered according to the state mark; based on the cross-validation of the available power accuracy, the accuracy of the available power of the template method on the main station side, the accuracy of the available power of the meteorological extrapolation method, and the accuracy of the available power reported by the station are calculated respectively, and the accuracy of the available power reported by the station is verified according to the maximum value of the accuracy.

[0061] The specific method for judging the available power of new energy includes the following steps:

[0062] The available power calculation unit using the template method on the master station side calculates the available power of each station based on the template method; the available power calculation unit using the meteorological extrapolation method on the master station side calculates the available power of each station based on the meteorological extrapolation method;

[0063] The first power restriction state of the station is determined according to the available power of each station based on the template method and the actual power of the station; the second power restriction state of the station is determined according to the available power of each station based on the meteorological extrapolation method and the actual power of the station; the third power restriction state of the station is determined according to the power dispatched by the AGC of the station and the actual power of the station, and a combined cross-validation of the power restriction state is performed to confirm the accurate power restriction state of each corresponding station according to the first power restriction state, the second power restriction state and the third power restriction state of the station, and the non-power restriction time of the corresponding station is determined according to the accurate power restriction state of each station;

[0064] Used to select the method with the highest accuracy of available power from the available power calculation method based on the station report, the available power calculation method based on the template method and the available power calculation method based on the meteorological extrapolation method as the optimal judgment method for the available power of the station's new energy;

[0065] The accuracy of the available power reported by the station is calculated based on the actual available power of each station at non-power-restricted times and the available power reported by the corresponding station at non-power-restricted times; the accuracy of the available power based on the template method is calculated based on the actual available power of each station at non-power-restricted times and the available power of each station based on the template method; the accuracy of the available power based on the meteorological extrapolation method is calculated based on the actual available power of each station at non-power-restricted times and the available power of each station based on the meteorological extrapolation method.

[0066] Example 3

[0067] A computer program product comprises a computer program, wherein when the computer program is executed by a processor, the steps of the method described in Embodiment 2 are implemented.

[0068] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

[0069] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0070] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A system that specifies the functions of a box or multiple boxes.

[0071] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a product including an instruction system, which is implemented in the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0072] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0073] The contents not described in detail in this specification belong to the prior art known to professional and technical personnel in this field.

Claims

1. A new energy available power judgment system based on cross-validation of multiple algorithms, characterized in that: It includes: constructing a calculation model module to calculate the available power of each station based on the template method according to the available power calculation unit of the master station side using the template method; calculating the available power of each station based on the meteorological extrapolation method according to the available power calculation unit of the master station side using the meteorological extrapolation method; The non-power-limited state determination module determines the first power-limited state of the station according to the available power of each station based on the template method and the actual power of the station; determines the second power-limited state of the station according to the available power of each station based on the meteorological extrapolation method and the actual power of the station; determines the third power-limited state of the station according to the power dispatched by the station AGC scheduling and the actual power of the station, and performs a combined cross-validation of the power-limited state to confirm the accurate power-limited state of each corresponding station according to the first power-limited state, the second power-limited state and the third power-limited state of the station, and determines the non-power-limited time of the corresponding station according to the accurate power-limited state of each station; The accuracy cross-validation module is used to select the method with the highest accuracy of available power from the available power calculation method based on the station report, the available power calculation method based on the template method and the available power calculation method based on the meteorological extrapolation method as the optimal judgment method for the available power of the station's new energy; The accuracy of the available power reported by the station is calculated based on the actual available power of each station at non-power-restricted times and the available power reported by the corresponding station at non-power-restricted times; the accuracy of the available power based on the template method is calculated based on the actual available power of each station at non-power-restricted times and the available power of each station based on the template method; the accuracy of the available power based on the meteorological extrapolation method is calculated based on the actual available power of each station at non-power-restricted times and the available power of each station based on the meteorological extrapolation method.

2. According to claim 1, a new energy available power judgment system based on cross-validation of multiple algorithms is characterized by: The formula for calculating the available power of each station by the template method included in the available power calculation unit of the template method in the calculation model building module is: Based on the mapping relationship between the sample power and the full-field power, the theoretical power P of the site based on the sample method is calculated on the master station side. ylm : Get the normal startup capacity Q of each new energy station o , calculate the available power P of each station ykm : Among them, the total installed capacity of each station is Q m , the total capacity of the prototype is Q y , the total active power of the sample machine is P y ; The formula for calculating the available power of each station by the meteorological extrapolation method included in the available power calculation unit of the meteorological extrapolation method in the calculation model construction module is: Among them, the theoretical power of the station calculated by the master station side based on the meteorological extrapolation method is P qlm , the startup capacity of each station is Q o , calculate the available power of each station as P qkm , the total installed capacity of each station is Q m .

3. The new energy available power judgment system based on cross-validation of multiple algorithms according to claim 1 is characterized in that: The specific calculation formula for determining the power-limited state of the station by the non-power-limited state determination module based on the available power calculated by the sample machine method and the actual power of the station is: Among them, the available power is P ykm , the actual power is P m , the deviation rate is D y , if D y If it is greater than the set threshold, it is determined as power restriction and the status is marked as 1; otherwise, it is not power restricted and the status is marked as 0; The specific calculation formula for determining the power-limited state of the station by the non-power-limited state determination module based on the available power calculated by the meteorological extrapolation method and the actual power of the station is: Among them, the available power is P qkm , the actual power is P m , the deviation rate is D q , if D q If it is greater than the set threshold, it is determined as power restriction and the status is marked as 1; otherwise, it is not power restricted and the status is marked as 0; The specific calculation formula for determining the power-limited state of the station by the non-power-limited state determination module after calculating the power dispatched by the station AGC scheduling and the actual power of the station is: Among them, the dispatching power is P a , the actual power is P m , the deviation rate is D a , if D a If it is less than the set threshold, it is judged as power restriction and the status is marked as 1; otherwise, it is not power restriction and the status is marked as 0.

4. The new energy available power judgment system based on cross-validation of multiple algorithms according to claim 1 is characterized in that: The specific method of combined cross-validation in the non-power-restriction state determination module is: combined cross-validation is performed according to the first power-restriction state, the second power-restriction state and the third power-restriction state of the station. When any two states are displayed as power-restriction states, the station is determined to be in power-restriction state, the power-restriction moment and the non-power-restriction moment are marked, and the non-power-restriction moment data is filtered according to the state mark.

5. The new energy available power judgment system based on cross-validation of multiple algorithms according to claim 1 is characterized in that: The specific calculation formula of the accuracy cross-validation module based on the accuracy of the available power reported by the station according to the actual available power of each station at the non-power-limited time and the available power at the non-power-limited time reported by the corresponding station is: Among them, D sP The accuracy rate of available power reported by the station, P m，i is the actual output of power station i at the non-power-limited time, P skm，i The available power reported by power station i during the non-power-limited period, Q i is the power-on capacity of the electric field at the non-power-restriction moment i, and n is the number of samples at the non-power-restriction moment in the cycle.

6. The new energy available power judgment system based on cross-validation of multiple algorithms according to claim 1 is characterized in that: The accuracy of the available power of the accuracy cross-validation module based on the sample machine method is calculated according to the actual available power of each station at the non-power-limited time and the specific calculation formula of the available power of each station based on the sample machine method: Among them, D yP is the accuracy of the available power of the sample machine method, P m，i is the actual output of power station i at the non-power-limited time, P ykm，i is the available power calculated by the sample machine method at the master station side at the non-power-cutoff time i, Q i is the power-on capacity of the electric field at the non-power-restriction moment i, and n is the number of samples at the non-power-restriction moment in the cycle.

7. The new energy available power judgment system based on cross-validation of multiple algorithms according to claim 1 is characterized in that: The accuracy of the available power of the accuracy cross-validation module based on the meteorological extrapolation method is calculated according to the actual available power of each station at the non-power-cut-off time and the specific calculation formula of the available power of each station based on the meteorological extrapolation method: Among them, D qP is the accuracy of available power of meteorological extrapolation method, P m，i is the actual output of power station i at the non-power-limited time, P ykm，i is the available power calculated by meteorological extrapolation method at the master station side at the non-power-cutoff time i, Q i is the power-on capacity of the electric field at the non-power-restriction moment i, and n is the number of samples at the non-power-restriction moment in the cycle.

8. The new energy available power judgment system based on cross-validation of multiple algorithms according to claim 1 is characterized in that: The specific method of the accuracy cross-validation module to obtain the optimal calculation method according to the maximum value of the available power accuracy is: Maximum value of available power accuracy D P Sure: D P =Max(D sP ,D yP ,D qP ) Among them, D sP The accuracy of the available power reported by the station, D yP is the accuracy of the available power of the sample machine method, D qP is the accuracy of available power of meteorological extrapolation method, based on D P The value verifies the accuracy of the available power reported by the station. If D P =D sP , then the accuracy of available power reported by the verification station is high, and the available power calculation method selected by the station is the optimal calculation method; otherwise, the accuracy of available power reported by the verification station is low, and the available power calculation method selected by the station is not the optimal calculation method, and a recommendation is issued for the station to make the best selection.

9. The method for determining the available power of new energy based on cross-validation of multiple algorithms according to claim 1, characterized in that: The available power calculation unit using the template method on the master station side calculates the available power of each station based on the template method; the available power calculation unit using the meteorological extrapolation method on the master station side calculates the available power of each station based on the meteorological extrapolation method; The first power restriction state of the station is determined according to the available power of each station based on the template method and the actual power of the station; the second power restriction state of the station is determined according to the available power of each station based on the meteorological extrapolation method and the actual power of the station; the third power restriction state of the station is determined according to the power dispatched by the AGC of the station and the actual power of the station, and a combined cross-validation of the power restriction state is performed to confirm the accurate power restriction state of each corresponding station according to the first power restriction state, the second power restriction state and the third power restriction state of the station, and the non-power restriction time of the corresponding station is determined according to the accurate power restriction state of each station; Used to select the method with the highest accuracy of available power from the available power calculation method based on the station report, the available power calculation method based on the template method and the available power calculation method based on the meteorological extrapolation method as the optimal judgment method for the available power of the station's new energy; The accuracy of the available power reported by the station is calculated based on the actual available power of each station at non-power-restricted times and the available power reported by the corresponding station at non-power-restricted times; the accuracy of the available power based on the template method is calculated based on the actual available power of each station at non-power-restricted times and the available power of each station based on the template method; the accuracy of the available power based on the meteorological extrapolation method is calculated based on the actual available power of each station at non-power-restricted times and the available power of each station based on the meteorological extrapolation method.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method described in claim 9 are implemented.

Images