New energy power generation intelligent scheduling system based on meteorological data

Abstract

The invention discloses a new energy power generation intelligent scheduling system based on meteorological data, and the system comprises a construction module which is used for obtaining regional feature information in a new energy station, and constructing a power generation region layout diagram based on GIS geographic information; the generation module is used for acquiring the power generation data and the meteorological data at the data acquisition nodes of the same power generation area, generating a power prediction data set, constructing a power prediction model, and obtaining a power prediction value according to the power prediction model; the analysis module is used for analyzing the power prediction value and the power demand value to obtain demand difference characteristics, and setting an optimal scheduling scheme for the demand difference characteristics based on the power market data; and the scheduling module is used for configuring a scheduling strategy for the new energy station based on the optimal scheduling scheme of each power generation area, reasonably formulating a scheduling scheme which meets the power demand and minimizes the scheduling cost, and improving the accuracy and efficiency of intelligent scheduling, thereby improving the income of a new energy power generation enterprise.

Description

Technical Field

[0001] The present application relates to the technical field of power generation dispatching, and in particular to an intelligent dispatching system for new energy power generation based on meteorological data. Background Art

[0002] With the enhancement of environmental awareness and the development of renewable energy technology, renewable energy power generation has become one of the important topics in today's energy field, and power dispatching of renewable energy power generation systems is one of the key issues.

[0003] In the existing technology, traditional power generation scheduling faces a series of challenges, such as large errors in meteorological data prediction leading to uncertainty in new energy power, failure to meet power supply needs, energy waste, etc. These problems will lead to unstable power supply and unnecessary energy costs, further reducing the profits and economic stability of new energy companies. Summary of the invention

[0004] In order to solve the above technical problems, the present application provides a new energy power generation intelligent scheduling system based on meteorological data. By constructing a power generation area layout map, screening the preferred meteorological data and power generation data of each power generation area, building a power prediction model, and according to the actual power demand, reasonably formulating a scheduling plan that minimizes the scheduling cost and meets the power demand, the accuracy and efficiency of intelligent scheduling are improved, thereby increasing the profits of new energy power generation companies.

[0005] In some embodiments of the present application, a new energy power generation intelligent scheduling system based on meteorological data is provided, including:

[0006] A construction module is used to obtain regional characteristic information of different areas in the new energy station, and to construct a power generation area layout map based on GIS geographic information, wherein the power generation area layout includes multiple power generation areas and data collection nodes;

[0007] A generation module is used to obtain power generation data and meteorological data at data collection nodes in the same power generation area, and generate a power prediction data group, build a power prediction model based on multiple power prediction data groups, and obtain a power prediction value for a preset time period in the corresponding power generation area according to the power prediction model;

[0008] An analysis module is used to analyze the power forecast value and the corresponding power demand value of each power generation area, obtain the demand difference characteristics, and set the optimal scheduling plan for the demand difference characteristics based on the power market data;

[0009] The scheduling module is used to configure the scheduling strategy for the new energy stations based on the preferred scheduling plan for each power generation area.

[0010] In some embodiments of the present application, constructing a power generation area layout diagram includes:

[0011] Acquire first historical information related to meteorological data and second historical information related to power data in the new energy station, and generate a first correlation coefficient between the first historical information and the meteorological data and a second correlation coefficient between the second historical information and the power data;

[0012] Setting first historical information where the first correlation coefficient is greater than a first preset coefficient threshold and second historical information where the second correlation coefficient is greater than a second preset coefficient threshold as regional feature information;

[0013] Acquire regional characteristic information of each area in the new energy station, analyze the regional characteristic information, determine multiple pending power generation areas, and if the number of power generation units in the pending power generation area is within a preset number range, set the center point of the corresponding pending power generation area as the origin of the power generation area;

[0014] According to the number of power generation units and power generation power in each to-be-determined power generation area, the radius length of the corresponding power generation area is set;

[0015] The location information of the corresponding power generation area is generated according to the origin and radius length of the power generation area, and the power generation area layout map is constructed according to the location information of each power generation area.

[0016] In some embodiments of the present application, the radius length of the corresponding power generation area is set according to the number of power generation units and the power generation power in each to-be-determined power generation area, including:

[0017] The calculation formula of the radius length of the power generation area is:

[0018]

[0019] Among them, r is the radius length, s is the number of power generation units, a1 is the first conversion coefficient, a2 is the second conversion coefficient, and qi is the power generation power of the i-th power generation unit.

[0020] In some embodiments of the present application, a power prediction model is constructed according to a plurality of power prediction data groups, including:

[0021] Acquire power generation data and meteorological data at the data collection node, and construct a power prediction data group of the corresponding data collection node for the meteorological data and power generation data at the same data collection node and at the same time node;

[0022] According to the meteorological data in the power prediction data group of each data collection node, a plurality of power prediction values ​​corresponding to the collection period are obtained and a power prediction curve is generated, wherein the horizontal axis of the power prediction curve is time and the vertical axis is the power prediction value;

[0023] Analyze the power generation data in the corresponding power prediction data group to generate an actual power curve for the corresponding collection period, where the abscissa of the actual power curve is time and the ordinate is the actual power value;

[0024] Aligning the power prediction curve and the actual power curve of the same data collection point, and determining the first reference deviation curve segment and the second reference deviation curve segment of the power prediction curve and the actual power curve of the corresponding time period based on a preset deviation judgment rule;

[0025] Analyze the first reference deviation curve segment and the second reference deviation curve segment of the same preset analysis section to obtain the prediction deviation amount corresponding to the preset analysis section, and set the quality evaluation value of the meteorological data of the corresponding data collection node according to the multiple prediction deviation amounts;

[0026] Filter out meteorological data with a quality evaluation value greater than a preset quality evaluation value threshold, and set them as preferred meteorological data;

[0027] Generate training set data and test set data according to the preferred meteorological data and corresponding power generation data of the same power generation area;

[0028] A power prediction model for the corresponding power generation area is constructed based on the training set data, and the credibility of the power prediction model is generated based on the test set data;

[0029] Pre-set credibility threshold;

[0030] If the credibility is greater than the credibility threshold, a power forecast value for a preset period is generated based on the predicted meteorological data of the data collection node corresponding to the power generation area;

[0031] If the credibility is less than the credibility threshold, the training set data is iteratively trained and the power prediction model is rebuilt.

[0032] In some embodiments of the present application, the preset deviation judgment rule includes:

[0033] The power prediction curve and the actual power curve of the same data collection point are aligned, and several preset analysis sections are set to calculate the deviation area between the power prediction curve and the actual power curve in each preset analysis section;

[0034] If the deviation area of ​​the preset analysis segment is greater than the preset deviation area threshold, the curve segment of the power prediction curve of the current preset analysis segment is set as the first reference deviation curve segment, and the curve segment of the actual power curve of the current preset analysis segment is set as the second reference deviation curve segment.

[0035] In some embodiments of the present application, a scheduling analysis is performed on the power forecast value and the corresponding power demand value of each power generation area to obtain multiple scheduling schemes, including:

[0036] Obtain the comprehensive power demand value of the power system during a preset period of time, set the supply ratio of the corresponding power generation area according to the total historical power generation of each power generation area at the same time, and determine the power demand value that each power generation area needs to provide during the preset period of time according to the supply ratio and the comprehensive power demand value;

[0037] Establishing a power demand curve according to the power demand values ​​that each power generation area needs to provide at different time nodes in a preset period, wherein the horizontal axis of the power demand curve is time and the vertical axis is the power demand value;

[0038] Establish a power prediction curve based on the power prediction values ​​of each power generation area at different time nodes in a preset period, wherein the horizontal axis of the power prediction curve is time and the vertical axis is the power prediction value;

[0039] Analyze the power demand value and the power forecast value at the same time node in the power demand curve and the power forecast curve to obtain the demand difference value between the power demand value and the power forecast value at the same time node;

[0040] The demand difference characteristics of each power generation area are generated according to the number of times the demand difference value is greater than the preset demand difference standard value within the preset time period and the difference value of the demand difference value greater than the preset demand difference standard value.

[0041] In some embodiments of the present application, generating demand difference characteristics for each power generation area includes:

[0042] The calculation formula for the demand difference characteristics of each power generation area is:

[0043]

[0044] Wherein, W is the demand difference characteristic, c is the demand difference conversion coefficient, u is the number of times the demand difference value is greater than the preset demand difference standard value within the preset time period, Rz is the zth demand difference value, and R0 is the preset demand difference standard value.

[0045] 8. The intelligent dispatching system for renewable energy power generation based on meteorological data according to claim 6 is characterized in that before setting the optimal dispatching scheme for demand difference characteristics, it includes:

[0046] Based on the electricity market data, establish the objective function of minimizing the dispatch cost;

[0047] The objective function of minimizing the scheduling cost is:

[0048] Y=min[T(m,n,mnj,Fmn)];

[0049] Among them, Y is the objective function of minimizing the scheduling cost, T(m, n, mnj, Fmn) is the scheduling cost required to use the Fmnth scheduling scheme to meet the power demand value n according to the demand difference characteristic m, and min is the minimum value symbol.

[0050] In some embodiments of the present application, setting a preferred scheduling scheme for demand difference characteristics includes:

[0051] Based on the historical dispatch plan library, select the dispatch plan corresponding to the demand difference characteristics of each power generation area;

[0052] According to the objective function of minimizing the scheduling cost, multiple scheduling plans are analyzed to obtain the scheduling cost of each scheduling plan and generate a scheduling cost sequence, and the scheduling plan corresponding to the minimum scheduling cost is selected as the preferred scheduling plan;

[0053] Simulate the priority scheduling scheme and generate the application degree of the priority scheduling scheme according to the simulation results;

[0054] If the application degree is greater than the preset application degree threshold, the dispatch strategy is configured for the new energy station according to the corresponding preferred dispatch plan;

[0055] If the application degree is less than the preset application degree threshold, the preferred scheduling scheme is reselected according to the scheduling cost sequence and the application degree is recalculated until a preferred scheduling scheme with an application degree greater than the application degree threshold is obtained.

[0056] Compared with the prior art, the intelligent dispatching system for renewable energy power generation based on meteorological data in the embodiment of the present application has the following beneficial effects:

[0057] By constructing a power generation area layout map, screening the optimal meteorological data and power generation data of each power generation area, building a power prediction model, and based on the actual power demand, reasonably formulating a scheduling plan that minimizes the scheduling cost to meet the power demand, the accuracy and efficiency of intelligent scheduling can be improved, thereby increasing the profits of new energy power generation companies. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 It is a schematic diagram of an intelligent dispatching system for renewable energy power generation based on meteorological data in a preferred embodiment of the present application. DETAILED DESCRIPTION

[0059] The specific implementation methods of the present application are further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present application but are not intended to limit the scope of the present application.

[0060] In the description of the present application, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0061] The terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0062] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0063] like Figure 1 As shown, a new energy power generation intelligent scheduling system based on meteorological data in a preferred embodiment of the present application includes:

[0064] A construction module is used to obtain regional characteristic information of different areas in the new energy station, and to construct a power generation area layout map based on GIS geographic information, wherein the power generation area layout includes multiple power generation areas and data collection nodes;

[0065] A generation module is used to obtain power generation data and meteorological data at data collection nodes in the same power generation area, and generate a power prediction data group, build a power prediction model based on multiple power prediction data groups, and obtain a power prediction value for a preset time period in the corresponding power generation area according to the power prediction model;

[0066] An analysis module is used to analyze the power forecast value and the corresponding power demand value of each power generation area, obtain the demand difference characteristics, and set the optimal scheduling plan for the demand difference characteristics based on the power market data;

[0067] The scheduling module is used to configure the scheduling strategy for the new energy stations based on the preferred scheduling plan for each power generation area.

[0068] In some embodiments of the present application, constructing a power generation area layout diagram includes:

[0069] Acquire first historical information related to meteorological data and second historical information related to power data in the new energy station, and generate a first correlation coefficient between the first historical information and the meteorological data and a second correlation coefficient between the second historical information and the power data;

[0070] Setting first historical information where the first correlation coefficient is greater than a first preset coefficient threshold and second historical information where the second correlation coefficient is greater than a second preset coefficient threshold as regional feature information;

[0071] Acquire regional characteristic information of each area in the new energy station, analyze the regional characteristic information, determine multiple pending power generation areas, and if the number of power generation units in the pending power generation area is within a preset number range, set the center point of the corresponding pending power generation area as the origin of the power generation area;

[0072] According to the number of power generation units and power generation power in each to-be-determined power generation area, the radius length of the corresponding power generation area is set;

[0073] The location information of the corresponding power generation area is generated according to the origin and radius length of the power generation area, and the power generation area layout map is constructed according to the location information of each power generation area.

[0074] In this embodiment, regional characteristic information such as historical power supply demand, historical meteorological data, geographical characteristics, etc. are used to obtain multiple pending power generation areas. The origin is set according to the center of the pending power generation area, and the area and location information of the power generation area are determined according to the power generation units and power generation power in the pending power generation area, thereby obtaining a power generation area layout map.

[0075] In this embodiment, areas with similar regional characteristic information are divided into the same power generation area according to the power generation area layout diagram, and the collection and analysis of meteorological data are accelerated to ensure the timeliness of power forecasting, and the power generation power of the power generation area is controlled within a preset range, thereby reducing the error of power forecasting by meteorological data, laying the foundation for the subsequent realization of new energy power forecasting based on meteorological data, and at the same time helping to meet the electricity demand in the region and improve the intelligent scheduling and management of new energy power generation.

[0076] In some embodiments of the present application, the radius length of the corresponding power generation area is set according to the number of power generation units and the power generation power in each to-be-determined power generation area, including:

[0077] The calculation formula of the radius length of the power generation area is:

[0078]

[0079] Among them, r is the radius length, s is the number of power generation units, a1 is the first conversion coefficient, a2 is the second conversion coefficient, and qi is the power generation power of the i-th power generation unit.

[0080] In this embodiment, the first conversion coefficient is to convert the total number of power generation units into a unit value with the same radius length, and the second conversion coefficient is to convert the sum of the power generation of multiple power generation units into a unit value with the same radius length.

[0081] In this embodiment, the area of ​​the power generation area and the data acquisition nodes included in the power generation area are determined according to the center and radius length of the power generation area, so as to avoid the complexity of power supply caused by too much power supply or too many power generation units, resulting in large errors in subsequent power prediction and reducing the accuracy of power generation scheduling.

[0082] In some embodiments of the present application, a power prediction model is constructed according to a plurality of power prediction data groups, including:

[0083] Acquire power generation data and meteorological data at the data collection node, and construct a power prediction data group of the corresponding data collection node for the meteorological data and power generation data at the same data collection node and at the same time node;

[0084] According to the meteorological data in the power prediction data group of each data collection node, a plurality of power prediction values ​​corresponding to the collection period are obtained and a power prediction curve is generated, wherein the horizontal axis of the power prediction curve is time and the vertical axis is the power prediction value;

[0085] Analyze the power generation data in the corresponding power prediction data group to generate an actual power curve for the corresponding collection period, where the abscissa of the actual power curve is time and the ordinate is the actual power value;

[0086] Aligning the power prediction curve and the actual power curve of the same data collection point, and determining the first reference deviation curve segment and the second reference deviation curve segment of the power prediction curve and the actual power curve of the corresponding time period based on a preset deviation judgment rule;

[0087] Analyze the first reference deviation curve segment and the second reference deviation curve segment of the same preset analysis section to obtain the prediction deviation amount corresponding to the preset analysis section, and set the quality evaluation value of the meteorological data of the corresponding data collection node according to the multiple prediction deviation amounts;

[0088] Filter out meteorological data with a quality evaluation value greater than a preset quality evaluation value threshold, and set them as preferred meteorological data;

[0089] Generate training set data and test set data according to the preferred meteorological data and corresponding power generation data of the same power generation area;

[0090] A power prediction model for the corresponding power generation area is constructed based on the training set data, and the credibility of the power prediction model is generated based on the test set data;

[0091] Pre-set credibility threshold;

[0092] If the credibility is greater than the credibility threshold, a power forecast value for a preset period is generated based on the predicted meteorological data of the data collection node corresponding to the power generation area;

[0093] If the credibility is less than the credibility threshold, the training set data is iteratively trained and the power prediction model is rebuilt.

[0094] In this embodiment, the quality evaluation value is obtained by summing up the mean values ​​of multiple prediction deviations in each preset analysis section. When the sum of the mean values ​​of the prediction deviations is larger, it means that the deviation between the power prediction value and the actual prediction value of the meteorological data at the current data collection node is larger, and the quality evaluation value of the meteorological data is smaller. When the sum of the mean values ​​of the prediction deviations is smaller, it means that the deviation between the power prediction value and the actual prediction value of the meteorological data at the current data collection node is smaller, and the quality evaluation value of the meteorological data is larger.

[0095] In this embodiment, based on the power prediction data group constructed for each data acquisition node, the power prediction value and the actual power value of the meteorological data at the corresponding data acquisition node are obtained, and the corresponding power prediction curve and the actual power curve are generated. The two curves are time-aligned to obtain the curve segments with deviations and calculate the corresponding prediction deviations, thereby obtaining the prediction accuracy (i.e., the quality evaluation value) of the meteorological data at the corresponding data acquisition node, screening out the preferred meteorological data, and constructing a power prediction model for each power generation area based on the preferred meteorological data and power generation data, which greatly improves the accuracy of the later power prediction and ensures the accuracy and efficiency of intelligent scheduling.

[0096] In this embodiment, the prediction accuracy of meteorological data is obtained through the power prediction data group of each data collection node, thereby obtaining the preferred meteorological data. A power prediction model is constructed based on the preferred meteorological data and power generation data to ensure the accuracy of power prediction through meteorological data in the later stage, lay the foundation for the new energy power generation scheduling strategy, help meet the electricity demand in the region, and ensure the effectiveness of the intelligent scheduling management of new energy power generation.

[0097] In some embodiments of the present application, the preset deviation judgment rule includes:

[0098] The power prediction curve and the actual power curve of the same data collection point are aligned, and several preset analysis sections are set to calculate the deviation area between the power prediction curve and the actual power curve in each preset analysis section;

[0099] If the deviation area of ​​the preset analysis segment is greater than the preset deviation area threshold, the curve segment of the power prediction curve of the current preset analysis segment is set as the first reference deviation curve segment, and the curve segment of the actual power curve of the current preset analysis segment is set as the second reference deviation curve segment.

[0100] In this embodiment, the preset analysis section divides the curve into multiple curve segments on average, and compares the curve segments within the preset analysis section to obtain the deviation area between the power prediction curve and the actual power curve. The deviation area refers to the area difference between the two curve segments within the preset analysis section. The preset deviation area threshold is the maximum standard area difference between the power prediction curve and the actual power curve. If the deviation area is greater than the maximum standard area difference, the power prediction error is large, that is, the prediction accuracy of the corresponding meteorological data is low.

[0101] In this embodiment, the corresponding first reference deviation curve segment and second reference deviation curve segment are obtained through preset deviation judgment rules, thereby obtaining multiple predicted deviation amounts and quality evaluation values ​​of corresponding meteorological data, laying the foundation for the subsequent construction of a power prediction model and improving the accuracy of the power prediction model, thereby ensuring the accuracy of new energy power generation scheduling.

[0102] In some embodiments of the present application, a scheduling analysis is performed on the power forecast value and the corresponding power demand value of each power generation area to obtain multiple scheduling schemes, including:

[0103] Obtain the comprehensive power demand value of the power system during a preset period of time, set the supply ratio of the corresponding power generation area according to the total historical power generation of each power generation area at the same time, and determine the power demand value that each power generation area needs to provide during the preset period of time according to the supply ratio and the comprehensive power demand value;

[0104] Establishing a power demand curve according to the power demand values ​​that each power generation area needs to provide at different time nodes in a preset period, wherein the horizontal axis of the power demand curve is time and the vertical axis is the power demand value;

[0105] Establish a power prediction curve based on the power prediction values ​​of each power generation area at different time nodes in a preset period, wherein the horizontal axis of the power prediction curve is time and the vertical axis is the power prediction value;

[0106] Analyze the power demand value and the power forecast value at the same time node in the power demand curve and the power forecast curve to obtain the demand difference value between the power demand value and the power forecast value at the same time node;

[0107] The demand difference characteristics of each power generation area are generated according to the number of times the demand difference value is greater than the preset demand difference standard value within the preset time period and the difference value of the demand difference value greater than the preset demand difference standard value.

[0108] In this embodiment, the supply ratio is set according to the number of multiple power generation units in each power generation area and the total historical power generation power. The comprehensive power demand value is divided according to the supply ratio to obtain the power demand value of each power generation area in the future period.

[0109] In some embodiments of the present application, generating demand difference characteristics for each power generation area includes:

[0110] The calculation formula for the demand difference characteristics of each power generation area is:

[0111]

[0112] Wherein, W is the demand difference characteristic, c is the demand difference conversion coefficient, u is the number of times the demand difference value is greater than the preset demand difference standard value within the preset time period, Rz is the zth demand difference value, and R0 is the preset demand difference standard value.

[0113] In this embodiment, the demand difference conversion coefficient refers to converting the calculated value of the number of times the demand difference value is greater than the preset demand difference standard value and the difference value greater than the preset demand difference standard value into a unit value consistent with the demand difference characteristics.

[0114] In this embodiment, multiple dispatching plans are derived according to the characteristics of demand differences, and the dispatching plans are comprehensively analyzed with the electricity prices in the power market to obtain a dispatching plan with the lowest dispatching cost, thereby increasing the profits of new energy power generation companies.

[0115] In some embodiments of the present application, before setting a preferred scheduling solution for demand difference characteristics, the process includes:

[0116] Based on the electricity market data, establish the objective function of minimizing the dispatch cost;

[0117] The objective function of minimizing the scheduling cost is:

[0118] Y=min[T(m,n,mnj,Fmn)];

[0119] Among them, Y is the objective function of minimizing the scheduling cost, T(m, n, mnj, Fmn) is the scheduling cost required to use the Fmnth scheduling scheme to meet the power demand value n according to the demand difference characteristic m, and min is the minimum value symbol.

[0120] In this embodiment, real-time electricity market data includes real-time electricity price data, electricity price forecast data within a preset time period, etc. The spot transaction price of the electricity market is obtained based on the electricity market data, and the dispatching cost of each dispatching plan is generated based on the electricity market data, so that the dispatching plan with the lowest dispatching cost is selected when performing power generation dispatching, thereby increasing the profits of new energy power generation companies.

[0121] In some embodiments of the present application, setting a preferred scheduling scheme for demand difference characteristics includes:

[0122] Based on the historical dispatch plan library, select the dispatch plan corresponding to the demand difference characteristics of each power generation area;

[0123] According to the objective function of minimizing the scheduling cost, multiple scheduling plans are analyzed to obtain the scheduling cost of each scheduling plan and generate a scheduling cost sequence, and the scheduling plan corresponding to the minimum scheduling cost is selected as the preferred scheduling plan;

[0124] Simulate the priority scheduling scheme and generate the application degree of the priority scheduling scheme according to the simulation results;

[0125] If the application degree is greater than the preset application degree threshold, the dispatch strategy is configured for the new energy station according to the corresponding preferred dispatch plan;

[0126] If the application degree is less than the preset application degree threshold, the preferred scheduling scheme is reselected according to the scheduling cost sequence and the application degree is recalculated until a preferred scheduling scheme with an application degree greater than the application degree threshold is obtained.

[0127] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and substitutions can be made without departing from the technical principles of the present application. These improvements and substitutions should also be regarded as the scope of protection of the present application.

Claims

1. A new energy power generation intelligent dispatching system based on meteorological data, characterized in that: include: A construction module is used to obtain regional characteristic information of different areas in the new energy station, and to construct a power generation area layout map based on GIS geographic information, wherein the power generation area layout includes multiple power generation areas and data collection nodes; A generation module is used to obtain power generation data and meteorological data at data collection nodes in the same power generation area, and generate a power prediction data group, build a power prediction model based on multiple power prediction data groups, and obtain a power prediction value for a preset time period in the corresponding power generation area according to the power prediction model; An analysis module is used to analyze the power forecast value and the corresponding power demand value of each power generation area, obtain the demand difference characteristics, and set the optimal scheduling plan for the demand difference characteristics based on the power market data; The scheduling module is used to configure the scheduling strategy for the new energy stations based on the preferred scheduling plan for each power generation area.

2. The intelligent dispatching system for renewable energy power generation based on meteorological data according to claim 1, characterized in that: Construct a layout diagram of the power generation area, including: Acquire first historical information related to meteorological data and second historical information related to power data in the new energy station, and generate a first correlation coefficient between the first historical information and the meteorological data and a second correlation coefficient between the second historical information and the power data; Setting first historical information where the first correlation coefficient is greater than a first preset coefficient threshold and second historical information where the second correlation coefficient is greater than a second preset coefficient threshold as regional feature information; Acquire regional characteristic information of each area in the new energy station, analyze the regional characteristic information, determine multiple pending power generation areas, and if the number of power generation units in the pending power generation area is within a preset number range, set the center point of the corresponding pending power generation area as the origin of the power generation area; According to the number of power generation units and power generation power in each to-be-determined power generation area, the radius length of the corresponding power generation area is set; The location information of the corresponding power generation area is generated according to the origin and radius length of the power generation area, and the power generation area layout map is constructed according to the location information of each power generation area.

3. The intelligent dispatching system for renewable energy power generation based on meteorological data according to claim 2, characterized in that: The radius length of the corresponding power generation area is set according to the number of power generation units and power generation power in each to-be-determined power generation area, including: The calculation formula of the radius length of the power generation area is: Among them, r is the radius length, s is the number of power generation units, a1 is the first conversion coefficient, a2 is the second conversion coefficient, and qi is the power generation power of the i-th power generation unit.

4. The intelligent dispatching system for renewable energy power generation based on meteorological data according to claim 3, characterized in that: A power prediction model is constructed based on multiple power prediction data sets, including: Acquire power generation data and meteorological data at the data collection node, and construct a power prediction data group of the corresponding data collection node for the meteorological data and power generation data at the same data collection node and at the same time node; According to the meteorological data in the power prediction data group of each data collection node, a plurality of power prediction values ​​corresponding to the collection period are obtained and a power prediction curve is generated, wherein the horizontal axis of the power prediction curve is time and the vertical axis is the power prediction value; Analyze the power generation data in the corresponding power prediction data group to generate an actual power curve for the corresponding collection period, wherein the abscissa of the actual power curve is time and the ordinate is the actual power value; Aligning the power prediction curve and the actual power curve of the same data collection point, and determining the first reference deviation curve segment and the second reference deviation curve segment of the power prediction curve and the actual power curve of the corresponding time period based on a preset deviation judgment rule; Analyze the first reference deviation curve segment and the second reference deviation curve segment of the same preset analysis section to obtain the prediction deviation amount corresponding to the preset analysis section, and set the quality evaluation value of the meteorological data of the corresponding data collection node according to the multiple prediction deviation amounts; Filter out meteorological data with a quality evaluation value greater than a preset quality evaluation value threshold, and set them as preferred meteorological data; Generate training set data and test set data according to the preferred meteorological data and corresponding power generation data of the same power generation area; A power prediction model for the corresponding power generation area is constructed based on the training set data, and the credibility of the power prediction model is generated based on the test set data; Pre-set credibility threshold; If the credibility is greater than the credibility threshold, a power forecast value for a preset period is generated based on the forecast meteorological data of the data collection node corresponding to the power generation area; If the credibility is less than the credibility threshold, the training set data is iteratively trained and the power prediction model is rebuilt.

5. The intelligent dispatching system for renewable energy power generation based on meteorological data according to claim 4, characterized in that: The preset deviation judgment rules include: The power prediction curve and the actual power curve of the same data collection point are aligned, and several preset analysis sections are set to calculate the deviation area between the power prediction curve and the actual power curve in each preset analysis section; If the deviation area of ​​the preset analysis segment is greater than the preset deviation area threshold, the curve segment of the power prediction curve of the current preset analysis segment is set as the first reference deviation curve segment, and the curve segment of the actual power curve of the current preset analysis segment is set as the second reference deviation curve segment.

6. The intelligent dispatching system for renewable energy power generation based on meteorological data according to claim 5, characterized in that: The power forecast value and the corresponding power demand value of each power generation area are analyzed and dispatched to obtain multiple dispatch plans, including: Obtain the comprehensive power demand value of the power system during a preset period of time, set the supply ratio of the corresponding power generation area according to the total historical power generation of each power generation area at the same time, and determine the power demand value that each power generation area needs to provide during the preset period of time according to the supply ratio and the comprehensive power demand value; Establishing a power demand curve according to the power demand values ​​that each power generation area needs to provide at different time nodes in a preset period, wherein the horizontal axis of the power demand curve is time and the vertical axis is the power demand value; Establish a power prediction curve based on the power prediction values ​​of each power generation area at different time nodes in a preset period, wherein the horizontal axis of the power prediction curve is time and the vertical axis is the power prediction value; Analyze the power demand value and the power forecast value at the same time node in the power demand curve and the power forecast curve to obtain the demand difference value between the power demand value and the power forecast value at the same time node; The demand difference characteristics of each power generation area are generated according to the number of times the demand difference value is greater than the preset demand difference standard value within the preset time period and the difference value of the demand difference value greater than the preset demand difference standard value.

7. The intelligent dispatching system for renewable energy power generation based on meteorological data according to claim 6, characterized in that: Generate demand differentiation characteristics for each generation region, including: The calculation formula for the demand difference characteristics of each power generation area is: Wherein, W is the demand difference characteristic, c is the demand difference conversion coefficient, u is the number of times the demand difference value is greater than the preset demand difference standard value within the preset time period, Rz is the zth demand difference value, and R0 is the preset demand difference standard value.

8. The intelligent dispatching system for renewable energy power generation based on meteorological data according to claim 6, characterized in that: Before setting the optimal scheduling plan for demand difference characteristics, it includes: Based on the electricity market data, establish the objective function of minimizing the dispatch cost; The objective function of minimizing the scheduling cost is: Y=min[T(m,n,mnj,Fmn)]; Among them, Y is the objective function of minimizing the scheduling cost, T(m, n, mnj, Fmn) is the scheduling cost required to use the Fmnth scheduling scheme to meet the power demand value n according to the demand difference characteristic m, and min is the minimum value symbol.

9. The intelligent dispatching system for renewable energy power generation based on meteorological data according to claim 8, characterized in that: Set optimal scheduling solutions based on demand difference characteristics, including: Based on the historical dispatch plan library, select the dispatch plan corresponding to the demand difference characteristics of each power generation area; According to the objective function of minimizing the scheduling cost, multiple scheduling plans are analyzed to obtain the scheduling cost of each scheduling plan and generate a scheduling cost sequence, and the scheduling plan corresponding to the minimum scheduling cost is selected as the preferred scheduling plan; Simulate the priority scheduling scheme and generate the application degree of the priority scheduling scheme according to the simulation results; If the application degree is greater than the preset application degree threshold, the dispatch strategy is configured for the new energy station according to the corresponding preferred dispatch plan; If the application degree is less than the preset application degree threshold, the preferred scheduling scheme is reselected according to the scheduling cost sequence and the application degree is recalculated until a preferred scheduling scheme with an application degree greater than the application degree threshold is obtained.

Images