Distributed photovoltaic load prediction method and system

Abstract

The invention provides a distributed photovoltaic load prediction method and system, and belongs to the technical field of load prediction, and the method specifically comprises the steps that a load data obtaining module is responsible for obtaining overload data of a power transmission line in a distribution network area under different weather types; the data analysis processing module is responsible for analyzing the overload data to obtain overload risk coefficients of the photovoltaic device under different weather types, and the prediction strategy output module is responsible for determining load prediction strategies of the photovoltaic device under different weather types by using the overload risk coefficients. And the efficiency and reliability of distributed photovoltaic load prediction processing are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of load forecasting, and particularly relates to a distributed photovoltaic load forecasting method and system. Background Art

[0002] In order to achieve the load forecasting of the distributed photovoltaic system and improve the stability of the distribution network, in the invention patent application CN202410568098.4, "A Data-Driven Real-Time Detection and Capacity Estimation Method for Distributed Photovoltaic Access", through advanced data mining algorithms, the real-time detection and access capacity estimation of the distributed photovoltaic system connected to the low-voltage distribution network are realized, providing a decision basis for the operation control of the power grid and ensuring the safety and reliability of the distribution network operation.

[0003] During the process of load forecasting for the distributed photovoltaic system, due to the differences in the distribution network areas where the distributed photovoltaic systems are located, there are deviations in the remaining load capacities of the distribution equipment in the distribution network areas where the distributed photovoltaic systems are located. Therefore, the load fluctuations of the distributed photovoltaic systems have different impacts on the stability of the distribution network areas, which makes it an urgent technical problem to generate a differentiated load forecasting strategy for the distributed photovoltaic system according to the operation data of the distribution network area.

[0004] In view of the above technical problems, specifically, the present application provides a distributed photovoltaic load forecasting method and system. Summary of the Invention

[0005] To achieve the purpose of the present invention, the present invention adopts the following technical solutions: In the first aspect, the present application provides a distributed photovoltaic load forecasting system, which specifically includes: A load data acquisition module, a data analysis and processing module, and a prediction strategy output module; Among them, the load data acquisition module is responsible for acquiring the overload data of the transmission lines in the distribution network area under different weather types; The data analysis and processing module is responsible for analyzing the overload data to obtain the load overload risk coefficients of the photovoltaic devices under different weather types; The prediction strategy output module is responsible for determining the load forecasting strategy of the photovoltaic device under different weather types by using the load overload risk coefficients.

[0006] A further technical solution is that the overload data of the transmission line includes the number of load overloads on different dates.

[0007] A further technical solution is that the weather types are divided according to the intervals where the wind speed, light intensity, and rainfall are located.

[0008] A further technical solution lies in that the load overload risk coefficient of the photovoltaic device is determined according to the proportion of the number of dates with overload data in the associated transmission line of the photovoltaic device.

[0009] A further technical solution lies in that the load prediction strategy of the photovoltaic device under different weather types is determined by using the load overload risk coefficient, which specifically includes: When the load overload risk coefficient of the photovoltaic device under the weather type does not meet the requirements, the first load prediction strategy is used to perform the load prediction process of the photovoltaic device.

[0010] When the load overload risk coefficient of the photovoltaic device under the weather type meets the requirements, the third load prediction strategy is used to perform the load prediction process of the photovoltaic device.

[0011] In a second aspect, the present application provides a distributed photovoltaic load prediction method, which is applied to the above-mentioned distributed photovoltaic load prediction system, and specifically includes: S1 Based on the power load data of the distribution network area where the distributed photovoltaic system is located, determine the historical operation data of different transmission lines in the distribution network area under different remaining load capacity intervals. When the load risk coefficient of the distribution network area is within the preset risk coefficient interval based on the historical operation data, proceed to the next step; S2 Obtain the power load data of different power users in the distribution network area, and determine the load fluctuation users among the power users based on the analysis result of the power load data; S3 Determine the associated transmission lines of different photovoltaic devices in the distributed photovoltaic system, determine the composition data of the load fluctuation users in different associated transmission lines, and use the composition data to determine the target photovoltaic device for optimizing the prediction strategy in the photovoltaic device; S4 Determine the load overload risk coefficient of the target photovoltaic device under different weather types based on the historical operation data of different associated transmission lines under different remaining load capacity intervals, and use the load overload risk coefficient to determine the load prediction strategy of the target photovoltaic device under different weather types.

[0012] The beneficial effects of the present invention are as follows: By using the historical operation data of different transmission lines in the distribution network area under different remaining load capacity intervals, it is determined whether the load risk coefficient of the distribution network area is within the preset risk coefficient interval, thereby realizing the assessment of the load risk situation of the distribution network area from the historical load conditions of the transmission lines, and also realizing the screening of the distribution network areas of the transmission lines with higher load levels, thus laying a foundation for generating differentiated load prediction strategies according to the differences in the load risk levels in the distribution network area.

[0013] Based on the load overload risk coefficient, determine the load prediction strategy of the target photovoltaic device under different weather types, thereby fully ensuring the reliability of the load prediction results of the target photovoltaic device with a relatively high load overload risk under the weather type, and at the same time avoiding the technical problem of excessive difficulty in load prediction processing caused by simply adopting a fixed load prediction model.

[0014] A further technical solution is that the historical operation data of the transmission line in different remaining load capacity intervals includes the historical operation time period in different remaining load capacity intervals and the distribution data of the historical operation time period.

[0015] A further technical solution is that the method for determining the load risk coefficient of the distribution network area is as follows: Determine the proportion of the historical operation duration of different transmission lines in the distribution network area in different remaining load capacity intervals based on the historical operation data; Use the proportion of the historical operation duration to determine the overloading risk transmission lines among the transmission lines in the distribution network area; Determine the load risk coefficient of the distribution network area according to the proportion of the number of the overloading transmission lines.

[0016] A further technical solution is that the overloading risk transmission line is a transmission line with a proportion of the historical operation duration greater than a preset duration proportion in a preset remaining load capacity interval.

[0017] A further technical solution is that when the load risk coefficient of the distribution network area is not within the preset risk coefficient interval, it is also necessary to determine whether the load risk coefficient of the distribution network area is greater than the preset load risk coefficient threshold. If so, use the first prediction strategy to perform the load prediction of the distributed photovoltaic system in the distribution network area. If not, use the second prediction strategy to perform the load prediction of the distributed photovoltaic system in the distribution network area.

[0018] A further technical solution is that the method for determining the load overload risk coefficient is as follows: Based on the historical operation data of different associated transmission lines in different remaining load capacity intervals, determine the proportion of the operation duration in different remaining load capacity intervals, and use the proportion of the operation duration to determine the operation probability in different remaining load capacity intervals; According to the historical output data of the target photovoltaic device under the weather type, determine the proportion of the duration in different power generation intervals, and according to the proportion of the duration in different power generation intervals, determine the power generation probability of different power generation intervals; Based on the load capacity thresholds corresponding to different remaining load capacity intervals, the power generation intervals with endpoints greater than the load capacity threshold are taken as matching overload intervals, and the sum of the products of the operating probabilities of different remaining load amount intervals and the power generation probabilities of the matching overload intervals is used to determine the load overload risk coefficient of the target photovoltaic device under the weather type.

[0019] A further technical solution lies in using the load overload risk coefficient to determine the load prediction strategy of the target photovoltaic device under different weather types, which specifically includes: When the load overload risk coefficient is greater than the preset overload risk coefficient threshold, it is determined that the load prediction strategy of the target photovoltaic device under the weather type is the first prediction strategy; When the load overload risk coefficient is not greater than the preset overload risk coefficient threshold, it is determined that the load prediction strategy of the target photovoltaic device under the weather type is the third prediction strategy.

[0020] Other features and advantages will be described in the following specification, and, in part, will become apparent from the specification, or will be understood by implementing the present invention. The objectives and other advantages of the present invention are achieved and obtained by the structures specifically pointed out in the specification and the drawings.

[0021] To make the above objectives, features, and advantages of the present invention more obvious and understandable, the following specific preferred embodiments are given, and in conjunction with the accompanying drawings, the detailed description is as follows. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] By referring to the drawings and describing its exemplary embodiments in detail, the above and other features and advantages of the present invention will become more obvious.

[0023] Figure 1 is a framework diagram of a distributed photovoltaic load prediction system; Figure 2 is a flowchart of a distributed photovoltaic load prediction method; Figure 3 is a flowchart of a method for determining the load risk coefficient of a distribution network area; Figure 4 is a flowchart of a method for determining load fluctuation users among power users. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0024] Now, the exemplary embodiments will be described more fully with reference to the accompanying drawings. However, the exemplary embodiments can be implemented in various forms and should not be construed as limited to the embodiments set forth herein; on the contrary, these embodiments are provided so that the present invention will be thorough and complete, and will fully convey the concept of the exemplary embodiments to those skilled in the art. The same reference numerals in the drawings denote the same or similar structures, and thus their detailed descriptions will be omitted.

[0025] The terms "a", "an", "the", and "said" are used to indicate the presence of one or more elements / components / etc.; the terms "comprising" and "having" are used to mean an open inclusion and refer to the possibility of the existence of additional elements / components / etc. in addition to the listed elements / components / etc.

[0026] Example 1 To solve the above problems, according to one aspect of the present invention, as Figure 1 shown, a distributed photovoltaic load forecasting system is provided, specifically including: a load data acquisition module, a data analysis and processing module, and a prediction strategy output module; wherein the load data acquisition module is responsible for acquiring the overload data of the transmission lines in the distribution network area under different weather types; the data analysis and processing module is responsible for analyzing the overload data to obtain the load overload risk coefficient of the photovoltaic device under different weather types; the prediction strategy output module is responsible for using the load overload risk coefficient to determine the load prediction strategy of the photovoltaic device under different weather types.

[0027] Furthermore, the overload data of the transmission lines includes the number of times of load overload on different dates.

[0028] Specifically, the weather types are divided and processed according to the intervals of the wind speed, light intensity, and rainfall amount.

[0029] It can be understood that the load overload risk coefficient of the photovoltaic device is determined according to the proportion of the number of dates with overload data in the associated transmission lines of the photovoltaic device.

[0030] Specifically, using the load overload risk coefficient to determine the load prediction strategy of the photovoltaic device under different weather types specifically includes: When the load overload risk coefficient of the photovoltaic device under the weather type does not meet the requirements, the first load prediction strategy is used for the load prediction processing of the photovoltaic device.

[0031] When the load overload risk coefficient of the photovoltaic device under the weather type meets the requirements, the third load prediction strategy is used for the load prediction processing of the photovoltaic device.

[0032] Example 2 In a second aspect, as Figure 2 shown, the present application provides a distributed photovoltaic load forecasting method, which is applied to the above-mentioned distributed photovoltaic load forecasting system, and specifically includes: S1 is based on the power load data of the distribution network area where the distributed photovoltaic system is located, determines the historical operation data of different transmission lines in the distribution network area under different remaining load capacity intervals, and enters the next step when the load risk coefficient of the distribution network area is determined to be within the preset risk coefficient interval based on the historical operation data; S2 obtains the power load data of different power users in the distribution network area, and determines the load fluctuation users among the power users based on the analysis result of the power load data; S3 determines the associated transmission lines of different photovoltaic devices in the distributed photovoltaic system, determines the composition data of the load fluctuation users in different associated transmission lines, and uses the composition data to determine the target photovoltaic device for optimizing the prediction strategy in the photovoltaic device; S4 determines the load overload risk coefficient of the target photovoltaic device under different weather types based on the historical operation data of different associated transmission lines under different remaining load capacity intervals, and uses the load overload risk coefficient to determine the load prediction strategy of the target photovoltaic device under different weather types.

[0033] Furthermore, the historical operation data of the transmission line under different remaining load capacity intervals includes the historical operation time period under different remaining load capacity intervals and the distribution data of the historical operation time period.

[0034] Specifically, as Figure 3 shown, the method for determining the load risk coefficient of the distribution network area is: Determine the proportion of the historical operation duration of different transmission lines in the distribution network area under different remaining load capacity intervals based on the historical operation data; Use the proportion of the historical operation duration to determine the overloaded risk transmission lines in the transmission lines in the distribution network area; Determine the load risk coefficient of the distribution network area according to the proportion of the number of the overloaded transmission lines.

[0035] Furthermore, the overloaded risk transmission line is a transmission line whose proportion of the historical operation duration under the preset remaining load capacity interval is greater than the preset duration proportion.

[0036] In addition, it should be noted that when the load risk coefficient of the distribution network area is not within the preset risk coefficient interval, it is also necessary to determine whether the load risk coefficient of the distribution network area is greater than the preset load risk coefficient threshold. If so, use the first prediction strategy to perform the load prediction of the distributed photovoltaic system in the distribution network area. If not, use the second prediction strategy to perform the load prediction of the distributed photovoltaic system in the distribution network area.

[0037] It can be understood that the preset remaining load capacity range is the range where the remaining load capacity is between 0 - 10%.

[0038] Optionally, the method for determining the load risk coefficient of the distribution network area is as follows: Based on the historical operation data, determine the average remaining load capacity of different transmission lines in the distribution network area. When there is no transmission line with an average remaining load capacity not meeting the requirements, use the second prediction strategy to perform load forecasting for the distributed photovoltaic system in the distribution network area; When there is a transmission line with an average remaining load capacity not meeting the requirements: Obtain the proportion of the number of transmission lines with an average remaining load capacity not meeting the requirements. When the proportion of the number of transmission lines with an average remaining load capacity not meeting the requirements is greater than the preset line number proportion, use the first prediction strategy to perform load forecasting for the distributed photovoltaic system in the distribution network area; When the proportion of the number of transmission lines with an average remaining load capacity not meeting the requirements is not greater than the preset line number proportion: Determine the proportion of the historical operation duration of different transmission lines in different remaining load capacity ranges. Use the proportion of the historical operation duration to determine the overloading risk transmission lines in the transmission lines of the distribution network area. When the proportion of the number of overloaded transmission lines does not meet the requirements, use the first prediction strategy to perform load forecasting for the distributed photovoltaic system in the distribution network area; When the proportion of the number of overloaded transmission lines meets the requirements: Based on the historical operation data of different transmission lines in different remaining load capacity ranges at different times, determine the time period in the preset remaining load capacity range and use it as the high - load time period. Based on the distribution data of the high - load time periods of different transmission lines in different time periods, when it is determined that there is no time period in which the proportion of the number of transmission lines belonging to the high - load time period is greater than the preset line number proportion, use the second prediction strategy to perform load forecasting for the distributed photovoltaic system in the distribution network area; When there is a time period in which the proportion of the number of transmission lines belonging to the high - load time period is greater than the preset line number proportion, use it as the load risk time period. When the proportion of the number of load risk time periods does not meet the requirements, use the first prediction strategy to perform load forecasting for the distributed photovoltaic system in the distribution network area; When the proportion of the number of load risk time periods meets the requirements: Based on the distribution data of the load risk time periods in different dates and the proportion of the number of transmission lines belonging to the high - load time periods in different load risk time periods, determine the load risk coefficient of the distribution network area.

[0039] Specifically, such as Figure 4As shown, the method for determining the load fluctuation users among the power users is as follows: Based on the analysis result of the power load data, determine the power load data of the power users at different time periods on different dates; Based on the power load data at different time periods on different dates, determine the load fluctuation dates of the power load data at different time periods on different dates, and use the time periods with the proportion of the number of load fluctuation dates greater than the preset proportion of the number of fluctuation dates as the load fluctuation time periods; Determine whether the power user is a load fluctuation user based on the number of the load fluctuation time periods.

[0040] Furthermore, the load fluctuation date is the date when the deviation amount from the average value of the power load data of the time period on different dates does not meet the requirements.

[0041] It should be noted that when the number of the load fluctuation time periods of the power user is greater than the preset number of fluctuation time periods, it is determined that the power user is a load fluctuation user.

[0042] Furthermore, the method for determining the associated transmission line of the photovoltaic device is as follows: Regard the transmission lines involved in the power transmission of the photovoltaic device in the distribution network area as the associated transmission lines.

[0043] It can be understood that the composition data of the load fluctuation users in the associated transmission lines includes the number of the load fluctuation users in the associated transmission lines and the proportion of the load of the load fluctuation users at different time periods.

[0044] Specifically, the method for determining the target photovoltaic device is as follows: Based on the composition data of the load fluctuation users of the associated transmission circuit of the photovoltaic device, determine the proportion of the load of the load fluctuation users of different associated transmission lines at different time periods; Based on the average value of the proportion of the load of the load fluctuation users of different associated transmission lines at different time periods, determine the load fluctuation risk lines in the associated transmission lines; Determine whether the photovoltaic device is a target photovoltaic device according to the number of the load fluctuation risk lines.

[0045] Furthermore, when the number of the load fluctuation risk lines of the photovoltaic device is greater than the preset threshold of the number of fluctuation risk lines, it is determined that the photovoltaic device is a target photovoltaic device.

[0046] It should be noted that when the photovoltaic device does not belong to the target photovoltaic device, the second prediction strategy is used to determine the load prediction of the distributed photovoltaic system in the distribution network area.

[0047] In another possible embodiment, the method for determining the target photovoltaic device is as follows: Based on the composition data of the load fluctuation users of the associated power transmission circuit of the photovoltaic device, determine the total number of load fluctuation users of the associated power transmission line. When the total number of load fluctuation users of different associated power transmission lines is less than the preset number of fluctuation users, it is determined that the photovoltaic device does not belong to the target photovoltaic device; When the total number of load fluctuation users of different associated power transmission lines is not less than the preset number of fluctuation users: When the total number of load fluctuation users of different associated power transmission lines is within the preset number range, it is determined that the photovoltaic device belongs to the target photovoltaic device; When the total number of load fluctuation users of different associated power transmission lines is not within the preset number range: Determine the load proportion of the load fluctuation users of different associated power transmission lines at different times. Based on the average value of the load proportions of the load fluctuation users of different associated power transmission lines at different times, when it is determined that there is no load fluctuation risk line in the associated power transmission line, it is determined that the photovoltaic device does not belong to the target photovoltaic device; When there is a load fluctuation risk line in the associated power transmission line: Obtain the number of the load fluctuation risk lines. When the number of the load fluctuation risk lines does not meet the requirements, it is determined that the photovoltaic device belongs to the target photovoltaic device; When the number of the load fluctuation risk lines meets the requirements: Obtain the load of the load fluctuation users of different associated power transmission lines at different times, and based on the load of the load fluctuation users of different associated power transmission circuits, determine the load fluctuation risk coefficient at different times. When the load fluctuation risk coefficients at different times all meet the requirements, it is determined that the photovoltaic device does not belong to the target photovoltaic device; When there is a time period in which the load fluctuation risk coefficient does not meet the requirements: When the number of time periods in which the load fluctuation risk coefficient does not meet the requirements is greater than the preset number of time periods, it is determined that the photovoltaic device belongs to the target photovoltaic device; When the number of time periods in which the load fluctuation risk coefficient does not meet the requirements is not greater than the preset number of time periods: Based on the load fluctuation risk coefficients at different times on different dates, determine the line load fluctuation risk coefficient of the associated power transmission line of the photovoltaic device, and based on the line load fluctuation risk coefficient, determine whether the photovoltaic device is a target photovoltaic device.

[0048] Further, when the line load fluctuation risk coefficient is within the preset line fluctuation risk coefficient range, it is determined that the photovoltaic device is a target photovoltaic device.

[0049] Specifically, the method for determining the load overload risk coefficient is as follows: Based on the historical operation data of different associated transmission lines in different remaining load capacity intervals, determine the proportion of operation duration in different remaining load capacity intervals, and use the proportion of operation duration to determine the operation probability in different remaining load capacity intervals; According to the historical output data of the target photovoltaic device under the weather type, determine the proportion of duration in different power generation intervals, and according to the proportion of duration in different power generation intervals, determine the power generation probability of different power generation intervals; Based on the load capacity thresholds corresponding to different remaining load capacity intervals, use the power generation intervals with endpoints greater than the load capacity threshold as the matching overload intervals, and determine the load overload risk coefficient of the target photovoltaic device under the weather type by the sum of the products of the operation probabilities in different remaining load amount intervals and the power generation probabilities in the matching overload intervals.

[0050] Furthermore, use the load overload risk coefficient to determine the load prediction strategy of the target photovoltaic device under different weather types, specifically including: When the load overload risk coefficient is greater than the preset overload risk coefficient threshold, determine that the load prediction strategy of the target photovoltaic device under the weather type is the first prediction strategy; When the load overload risk coefficient is not greater than the preset overload risk coefficient threshold, determine that the load prediction strategy of the target photovoltaic device under the weather type is the third prediction strategy.

[0051] In another possible embodiment, the method for determining the load overload risk coefficient is as follows: S41 According to the historical output data of the target photovoltaic device under the weather type, determine the number of overloads in the associated transmission lines in different remaining load capacity intervals, and determine the overload risk coefficient in different remaining load capacity intervals based on the number of overloads in the associated transmission lines in different remaining load capacity intervals; S42 Based on the historical operation data of different associated transmission lines in different remaining load capacity intervals, determine the proportion of operation duration in different remaining load capacity intervals, and use the proportion of operation duration to determine the operation probability in different remaining load capacity intervals; S43 Based on the operation probabilities and overload risk coefficients corresponding to different remaining load capacity intervals, and combined with the proportion of duration in different power generation intervals of the target photovoltaic device, determine the load overload risk coefficient of the target photovoltaic device under the weather type.

[0052] Optionally, the above step S41 includes the following content: S411 uses the date under the weather type as the weather matching date. When overload situations have occurred in the associated power transmission circuits for different weather matching dates, it is determined that the load prediction strategy of the target photovoltaic device under the weather type is the first prediction strategy. When there is a weather matching date in the associated power transmission line where no overload situation has occurred, it proceeds to step S412; S412 uses the weather matching date with an overload situation as the historical overload date. When there is a historical overload date where the historical overload times of the associated power transmission line do not meet the requirements, it proceeds to step S413. When there is no historical overload date where the historical overload times of the associated power transmission line do not meet the requirements, it proceeds to step S414; S413 When the number of historical overload dates where the historical overload times of the associated power transmission line do not meet the requirements is greater than the preset overload date quantity threshold, it is determined that the load prediction strategy of the target photovoltaic device under the weather type is the first prediction strategy. When the number of historical overload dates where the historical overload times of the associated power transmission line do not meet the requirements is not greater than the preset overload date quantity threshold, it proceeds to step S414; S414 obtains the total historical overload times on the weather matching date. When the total historical overload times do not meet the requirements, it is determined that the load prediction strategy of the target photovoltaic device under the weather type is the first prediction strategy. When the total historical overload times meet the requirements, it proceeds to step S415; S415 determines the overload risk coefficient in different remaining load capacity intervals based on the overload times in the associated power transmission lines in different remaining load capacity intervals. When there is a remaining load capacity interval where the overload risk coefficient does not meet the requirements, it is determined that the load prediction strategy of the target photovoltaic device under the weather type is the first prediction strategy. When there is no remaining load capacity interval where the overload risk coefficient does not meet the requirements, it proceeds to step S42.

[0053] Optionally, the above step S42 includes the following content: S421 determines the proportion of operation duration in different remaining load capacity intervals based on the historical operation data of different associated power transmission lines in different remaining load capacity intervals, and uses the proportion of operation duration to determine the operation probability in different remaining load capacity intervals. When the sum of the products of the operation probability and the overload risk coefficient in different remaining load capacity intervals does not meet the requirements, it is determined that the load prediction strategy of the target photovoltaic device under the weather type is the first prediction strategy. When the sum of the products of the operation probability and the overload risk coefficient in different remaining load capacity intervals meets the requirements, it proceeds to step S422; When there is a remaining load capacity interval with an overload risk coefficient within the preset load risk coefficient interval, it proceeds to step S423. When there is no remaining load capacity interval with an overload risk coefficient within the preset load risk coefficient interval, it proceeds to step S43; S423 When the sum of the operating probabilities of the remaining load capacity intervals with an overload risk coefficient within the preset load risk coefficient interval is greater than the preset operating probability threshold, it determines that the load prediction strategy of the target photovoltaic device under the weather type is the first prediction strategy. When the sum of the operating probabilities of the remaining load capacity intervals with an overload risk coefficient within the preset load risk coefficient interval is not greater than the preset operating probability threshold, it proceeds to step S43.

[0054] Specifically, the first prediction strategy is to perform load prediction processing for different moments. The second prediction strategy is to use the second preset duration as the target unit to determine the load prediction results of the photovoltaic device for different target units. The third prediction strategy is to use the third preset duration as the target unit to determine the load prediction results of the photovoltaic device for different target units.

[0055] It should be noted that the second preset duration is greater than the third preset duration.

[0056] Each embodiment in this specification is described in a progressive manner. The same or similar parts among the embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment, and non-volatile computer storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiments.

[0057] The above describes specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve the desired result. Additionally, the processes depicted in the figures do not necessarily require the specific order or sequential order shown to achieve the desired result. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0058] The above is only one or more embodiments of this specification and is not used to limit this specification. For those skilled in the art, one or more embodiments of this specification can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of one or more embodiments of this specification shall be included within the scope of the claims of this specification.

Claims

1. A distributed photovoltaic load forecasting system, characterized in that, Specifically include: Load data acquisition module, data analysis and processing module, prediction strategy output module; Among them, the load data acquisition module is responsible for acquiring the overload data of the transmission lines in the distribution network area under different weather types; The data analysis and processing module is responsible for analyzing the overload data to obtain the load overload risk coefficient of the photovoltaic device under different weather types; The prediction strategy output module is responsible for determining the load prediction strategy of the photovoltaic device under different weather types by using the load overload risk coefficient.

2. The distributed photovoltaic load forecasting system according to claim 1, wherein The overload data of the transmission line includes the number of load overloads on different dates.

3. The distributed photovoltaic load forecasting system according to claim 1, wherein The weather types are divided and processed according to the intervals of the wind speed, light, and rainfall.

4. The distributed photovoltaic load forecasting system according to claim 1, wherein, The load overload risk coefficient of the photovoltaic device is determined according to the proportion of the number of dates with overload data in the associated transmission line of the photovoltaic device.

5. The distributed photovoltaic load forecasting system according to claim 4, wherein Determining the load prediction strategy of the photovoltaic device under different weather types by using the load overload risk coefficient specifically includes: When the load overload risk coefficient of the photovoltaic device under the weather type does not meet the requirements, the first load prediction strategy is used for the load prediction processing of the photovoltaic device; When the load overload risk coefficient of the photovoltaic device under the weather type meets the requirements, the third load prediction strategy is used for the load prediction processing of the photovoltaic device.

6. A distributed photovoltaic load forecasting method, applied to a distributed photovoltaic load forecasting system according to any one of claims 1-5, characterized in that, Specifically include: Based on the power load data of the distribution network area where the distributed photovoltaic system is located, determine the historical operation data of different transmission lines in the distribution network area under different remaining load capacity intervals. When the load risk coefficient of the distribution network area is within the preset risk coefficient interval based on the historical operation data, proceed to the next step; Obtain the power load data of different power users in the distribution network area, and determine the load fluctuation users among the power users based on the analysis result of the power load data; Determine the associated transmission lines of different photovoltaic devices in the distributed photovoltaic system, determine the composition data of the load fluctuation users in different associated transmission lines, and use the composition data to determine the target photovoltaic device for predicting strategy optimization in the photovoltaic device; Based on the historical operation data of different associated transmission lines under different remaining load capacity intervals, determine the load overload risk coefficient of the target photovoltaic device under different weather types, and use the load overload risk coefficient to determine the load prediction strategy of the target photovoltaic device under different weather types.

7. The distributed photovoltaic load forecasting method according to claim 6, characterized in that, The historical operation data of the transmission line under different remaining load capacity intervals includes the historical operation time period and the distribution data of the historical operation time period under different remaining load capacity intervals.

8. The distributed photovoltaic load forecasting method according to claim 6, wherein, The method for determining the load risk coefficient of the distribution network area is: Determine the proportion of the historical operation duration of different transmission lines in the distribution network area under different remaining load capacity intervals based on the historical operation data; Use the proportion of the historical operation duration to determine the overload risk transmission lines in the transmission lines of the distribution network area; Determine the load risk coefficient of the distribution network area according to the proportion of the number of the overload transmission lines.

9. The distributed photovoltaic load forecasting method according to claim 8, wherein The overloaded-risk transmission line is a transmission line with a historical operation duration ratio greater than a preset duration ratio within a preset remaining load capacity range.

10. The distributed photovoltaic load forecasting method according to claim 8, wherein, When the load risk coefficient of the distribution network area is not within the preset risk coefficient range, it is also necessary to determine whether the load risk coefficient of the distribution network area is greater than the preset load risk coefficient threshold. If so, the first prediction strategy is used to predict the load of the distributed photovoltaic system in the distribution network area. If not, the second prediction strategy is used to predict the load of the distributed photovoltaic system in the distribution network area.

Images