New energy consumption intelligent prediction and regulation system for new power system

Abstract

The present application relates to the technical field of power system operation control, and particularly relates to a new energy consumption intelligent prediction and regulation system for a new type of power system, which divides the grid area grid according to the dispatching boundary through a space-time standardization module, unifies the time window of the measured and predicted data, extracts the homologous data and calculates the absolute deviation value and the relative deviation rate through a data processing module, determines the deviation abnormal grid according to the threshold through a comparison marking module, obtains the spatial deviation area under the same time window through an adjacent determination and a connected domain analysis of a deviation area positioning module, extracts the deviation period and the duration through a deviation period analysis module using a sliding time window, generates a space-time distribution broken line graph through a deviation visualization module, and formulates a partitioned and timed regulation scheme based on the broken line graph characteristics through a regulation module. The present application realizes the space-time positioning and visual presentation of the consumption deviation, so as to adapt to the regulation requirements of the new type of power system with new energy access.

Description

Technical Field

[0001] This invention relates to the field of power system operation and control technology, and in particular to an intelligent prediction and control system for renewable energy consumption in new power systems. Background Technology

[0002] With economic and technological development and the improvement of people's living standards, electricity has become an indispensable secondary energy source in people's production and life, bringing endless convenience. Therefore, ensuring a stable and reliable supply of electricity has become one of the most important tasks of the power system. In existing technologies, the granularity of measured data acquisition from new energy power plants and load terminals does not match that of predicted data, data transmission has time delays, and the timestamps and spatial area divisions of the predicted and measured data are not aligned, making it impossible to synchronously complete point-by-point comparisons. Furthermore, because the errors between measured and predicted data are not broken down, the deviations cannot be attributed to specific regions and time periods, leading to deviations in the control process.

[0003] Therefore, it is necessary to propose an intelligent prediction and control system for new energy consumption in new power systems to solve the above problems. Summary of the Invention

[0004] The purpose of this invention is to provide an intelligent prediction and control system for new energy consumption in new power systems, so as to solve the problem that it is impossible to make point-by-point comparisons between predicted data and measured data, and that the deviation between the two cannot be specified to power areas and time periods.

[0005] To achieve the above objectives, the present invention provides the following technical solution: A smart prediction and control system for renewable energy consumption in new power systems includes the following steps: The spatiotemporal standardization module is used to divide the power grid area into grid areas and unify the measured data and predicted data of the power grid grid area into the same time window through the clock of the dispatch center. The data processing module is used to extract the measured data and predicted data for the corresponding time window in each grid region and calculate the deviation value; The comparison and marking module is used to mark the grid area as an abnormal grid within the corresponding time window based on the deviation value and a pre-set deviation threshold. The deviation region positioning module is used to set adjacency determination conditions between two adjacent deviation anomaly grids within the same time window based on the deviation anomaly grid. According to the adjacency determination conditions, the module determines the deviation anomaly grids by taking the grid region as a unit. The module combines the determined adjacent deviation anomaly grids and isolated deviation anomaly grids to obtain the deviation region within the time window. The deviation period analysis module is used to process the deviation region using a sliding time window based on the deviation region to obtain the deviation period and the duration of the deviation. The deviation visualization module is used to generate a line graph of the deviation distribution based on the deviation time period and the duration of the deviation in the deviation area. The control module is used to control the power system by identifying and analyzing line graphs.

[0006] Preferably, the spatiotemporal standardization module is used to divide the power grid area into grid areas, and to unify the measured data and predicted data of the power grid grid areas into the same time window through the clock of the dispatch center, specifically including: The power grid area is divided according to the dispatch and management boundaries of the power system to obtain grid areas; Set up a continuous, non-overlapping sliding time window. For the measured data and predicted data in the grid area, use the time window to adapt the time window separately to achieve the same time window granularity between the measured data and the predicted data.

[0007] Preferably, the data processing module is used to extract the measured data and predicted data within the corresponding time window for each grid region, and calculate the deviation value, specifically including: Extract the actual output of new energy sources and the actual power absorption capacity of the power grid in the current grid area and the current time window to obtain the measured data; By maintaining the same grid area and time window as the actual data extraction background, the predicted output value of new energy sources and the predicted value of grid absorption capacity are extracted to obtain the predicted data. Using a standard algorithm for power systems, the deviation between measured data and predicted data is calculated. The deviation includes both absolute deviation and relative deviation rate.

[0008] Preferably, the comparison marking module is used to mark the grid region as an abnormal grid within the corresponding time window based on the deviation value and a pre-set deviation threshold, specifically including: The deviation threshold includes the absolute deviation threshold. and relative deviation rate threshold ; Extract the absolute deviation values ​​of all grid regions within the current time window. and relative deviation rate And extract the absolute deviation threshold corresponding to each grid region. and relative deviation rate threshold ; For all grid regions within the current time window, determine the deviation value: If the absolute deviation value ≥ Absolute Deviation Threshold or relative deviation rate ≥ Relative Deviation Rate Threshold The absorption deviation of the current time window in the grid region is determined to be abnormal, and it is marked as an abnormal deviation grid. If the absolute deviation value Absolute Deviation Threshold And relative deviation rate Relative Deviation Rate Threshold If the absorption deviation of the current time window in the grid region is determined to be normal, the grid with abnormal deviation will not be marked.

[0009] Preferably, the deviation region positioning module is used to set adjacency determination conditions between two adjacent deviation anomaly grids within the same time window based on the deviation anomaly grid, and to determine the deviation anomaly grids by grid region according to the adjacency determination conditions, and to combine the determined adjacent deviation anomaly grids and isolated deviation anomaly grids to obtain the deviation region within the time window, specifically including: Based on the deviation anomaly grid, set the adjacency determination conditions; Based on the adjacency determination criteria, deviation anomaly grids in each grid region of the power grid area are determined. By marking all deviation anomaly grids as unvisited, any unvisited deviation anomaly grid is selected, and a connected component analysis algorithm is used to iteratively visit all deviation anomaly grids and mark them as visited according to the adjacency determination criteria until all deviation anomaly grids are marked as visited, thus completing the determination and forming a connected component composed of adjacent deviation anomaly grids, as well as isolated deviation anomaly grids. The isolated deviation anomaly mesh is combined with the connected domain to generate the deviation region.

[0010] Preferably, the step of determining the deviation anomaly grids in each grid region of the power grid area based on the adjacency determination condition specifically includes: The adjacency determination condition is that, within the same time window, deviation abnormal grids in different grid regions share an edge in the horizontal or vertical direction, or two deviation abnormal grids share a vertex in the diagonal direction, that is, two deviation abnormal grids are obliquely adjacent. Based on the adjacency determination criteria, the deviation anomaly grids in each grid region of the power grid area are determined: If two deviation anomalous grids share an edge in the horizontal or vertical direction, they are determined to be adjacent deviation anomalous grids. If two aberration meshes share a vertex in the diagonal direction, they are determined to be adjacent aberration meshes. If two aberration meshes do not meet any of the adjacency criteria, they are determined to be isolated aberration meshes.

[0011] Preferably, the deviation period analysis module is used to process the deviation region using a sliding time window based on the deviation region to obtain the deviation period and the duration of the deviation, specifically including: Set a sliding time window, wherein the start and end times of the sliding time window are consistent with the time window; Using a sliding time window, the deviation area is detected according to a preset sliding step size. If the time range of the sliding time window includes at least one deviation abnormal grid, the time range corresponding to the sliding time window is determined to be a deviation abnormal sliding period, and the start and end times of the deviation abnormal sliding period are recorded. If no deviation abnormal grid is included, it is determined to be a normal period. The sliding step size is one time window. For consecutive periods of abnormal deviation, the periods are merged according to the start time to obtain the deviation periods; The duration of the deviation is obtained based on the deviation period, start time, and end time.

[0012] Preferably, the deviation visualization module is used to generate a line graph of the deviation distribution based on the deviation time period and the duration of the deviation in the deviation region, specifically including: Establish a coordinate system with the time axis as the horizontal axis and the space axis as the vertical axis; The individual deviation region is spatially scaled on the vertical axis of the coordinate system, and time-scaled on the horizontal axis of the coordinate system according to the start and end times of the deviation period. The slope of the line segment corresponding to the deviation period is represented by the duration of the deviation, and a line graph is generated.

[0013] Preferably, the control module is used to control the power system by identifying and analyzing line graphs, specifically including: Based on the line graph, extract the deviation area, deviation period, deviation duration and slope from the line graph to generate control schemes for different power grid areas and deviation periods; The power system is regulated according to the regulation plan.

[0014] The technical effects and advantages of the present invention in the above technical solution are as follows: 1. This invention uses the predicted output value of new energy sources and the predicted value of grid absorption capacity as input data. It extracts the predicted data and measured data simultaneously, aligns them in time and space, and calculates the deviation. It then analyzes the difference between the predicted results and the actual operation to analyze the prediction deviation and carry out targeted grid regulation based on the prediction deviation.

[0015] 2. By processing the deviation anomaly grid through adjacency determination and connected component analysis, contiguous deviation connected components and isolated deviation grids are divided within the same time window to restore the true spatial distribution of the deviation. Combined with the sliding time window, the deviation time period is merged and the duration is calculated, and the absorbed deviation is attributed to a specific spatial region and a specific time segment, which solves the defect of existing technology that cannot locate the spatiotemporal position of the deviation. Attached Figure Description

[0016] Figure 1 This is a structural diagram of the intelligent prediction and control system for renewable energy consumption in a new type of power system, as described in this invention. Detailed Implementation

[0017] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] like Figure 1 As shown, this embodiment provides an intelligent prediction and control system for renewable energy consumption in new power systems, including: The spatiotemporal standardization module is used to divide the power grid area into grid areas and unify the measured data and predicted data of the power grid grid area into the same time window through the clock of the dispatch center. The data processing module is used to extract the measured data and predicted data for the corresponding time window in each grid region and calculate the deviation value; The comparison and marking module is used to mark the grid area as an abnormal grid within the corresponding time window based on the deviation value and a pre-set deviation threshold. The deviation region positioning module is used to set adjacency determination conditions between two adjacent deviation anomaly grids within the same time window based on the deviation anomaly grid. According to the adjacency determination conditions, the module determines the deviation anomaly grids by taking the grid region as a unit. The module combines the determined adjacent deviation anomaly grids and isolated deviation anomaly grids to obtain the deviation region within the time window. The deviation period analysis module is used to process the deviation region using a sliding time window based on the deviation region to obtain the deviation period and the duration of the deviation. The deviation visualization module is used to generate a line graph of the deviation distribution based on the deviation time period and the duration of the deviation in the deviation area. The control module is used to control the power system by identifying and analyzing line graphs.

[0019] In one embodiment of the present invention, the spatiotemporal standardization module is used to divide the power grid area into grid areas, and to unify the measured data and predicted data of the power grid grid areas into the same time window through the clock of the dispatch center, specifically including: The power grid area is divided according to the dispatch and management boundaries of the power system to obtain grid areas; Set up a continuous, non-overlapping sliding time window. For the measured data and predicted data in the grid area, use the time window to adapt the time window separately to achieve the same time window granularity between the measured data and the predicted data.

[0020] In this embodiment of the invention, in order to realize the spatial division of the power grid area, the power grid area is divided using the dispatch management boundary of the power system. The dispatch management boundary is based on the provincial, municipal, and regional dispatch management boundaries of the power system to achieve grid-based partitioning of the entire power grid, resulting in grid areas. For the measured data and predicted data of the grid areas, a continuous and non-overlapping sliding time window is set through the Beidou / GPS high-precision timing clock of the dispatch center. The measured data and predicted data correspond to each other with the same time window to avoid the problem of mismatch between the collection time granularity of measured data and predicted data.

[0021] In one embodiment of the present invention, the data processing module is used to extract the measured data and predicted data within the corresponding time window in each grid region, and calculate the deviation value, specifically including: Extract the actual output of new energy sources and the actual power absorption capacity of the power grid in the current grid area and the current time window to obtain the measured data; By maintaining the same grid area and time window as the actual data extraction background, the predicted output value of new energy sources and the predicted value of grid absorption capacity are extracted to obtain the predicted data. Using a standard algorithm for power systems, the deviation between measured data and predicted data is calculated. The deviation includes both absolute deviation and relative deviation rate.

[0022] In this embodiment of the invention, for measured and predicted data of different grid areas, the data processing module collects measured and predicted data of the same grid area within the same time window. The measured data includes the actual power generation output of new energy units such as wind power and photovoltaic power within the grid, as well as the actual power absorption capacity of the grid for that grid area. The data sources include real-time acquisition results from new energy power plants, load terminals, and grid monitoring devices. The predicted data includes the predicted output of new energy and the predicted grid absorption capacity for that grid area, which is mainly obtained through the prediction results generated in advance by the system. After collecting the measured and predicted data, the deviation quantification calculation method used by the power system is adopted, that is, the measured data is subtracted from the predicted data, and the absolute value is taken to obtain the absolute value of the deviation. The absolute deviation value is divided by the predicted data to calculate the relative deviation rate, so as to obtain the quantification result of the absorption deviation.

[0023] In one embodiment of the present invention, the comparison marking module is used to mark the grid region as an abnormal grid within the corresponding time window based on the deviation value and a pre-set deviation threshold, specifically including: The deviation threshold includes the absolute deviation threshold. and relative deviation rate threshold ; Extract the absolute deviation values ​​of all grid regions within the current time window. and relative deviation rate And extract the absolute deviation threshold corresponding to each grid region. and relative deviation rate threshold ; For all grid regions within the current time window, determine the deviation value: If the absolute deviation value ≥ Absolute Deviation Threshold or relative deviation rate ≥ Relative Deviation Rate Threshold The absorption deviation of the current time window in the grid region is determined to be abnormal, and it is marked as an abnormal deviation grid. If the absolute deviation value Absolute Deviation Threshold And relative deviation rate Relative Deviation Rate Threshold If the absorption deviation of the current time window in the grid region is determined to be normal, the grid with abnormal deviation will not be marked.

[0024] In this embodiment of the invention, the absolute deviation threshold is set in a differentiated and graded manner based on the installed capacity of new energy and the scale of power absorption by the grid within the grid area, in order to adapt to the absolute deviation control requirements of the grid area. The relative deviation rate threshold is set uniformly or classified according to the type of new energy, in order to measure the relative severity of the deviation. Based on the current time window unified by the system as the judgment period, the absolute deviation value and relative deviation rate of all grid areas in the power grid area under this time window are extracted. Using the absolute deviation threshold and relative deviation rate threshold corresponding to each grid area, the deviation of the grid area is judged. That is, for a single grid under this time window, if any one condition is met, the grid area can be judged as having an abnormal absorption. Only when both the absolute deviation value and the relative deviation rate are lower than their respective thresholds will the grid area be judged as having normal absorption under the current time window. After judging all grid regions, for grids judged as having absorptive abnormalities, the system performs spatial encoding and current time window encoding to obtain the deviation abnormal grids. For normal grid regions, their original data is retained.

[0025] In one embodiment of the present invention, the deviation region positioning module is used to set an adjacency determination condition between two adjacent deviation anomaly grids within the same time window based on the deviation anomaly grid, and to determine the deviation anomaly grids by grid region according to the adjacency determination condition, and to combine the determined adjacent deviation anomaly grids and isolated deviation anomaly grids to obtain the deviation region within the time window, specifically including: Based on the deviation anomaly grid, set the adjacency determination conditions; Based on the adjacency determination criteria, deviation anomaly grids in each grid region of the power grid area are determined. By marking all deviation anomaly grids as unvisited, any unvisited deviation anomaly grid is selected, and a connected component analysis algorithm is used to iteratively visit all deviation anomaly grids and mark them as visited according to the adjacency determination criteria until all deviation anomaly grids are marked as visited, thus completing the determination and forming a connected component composed of adjacent deviation anomaly grids, as well as isolated deviation anomaly grids. The isolated deviation anomaly mesh is combined with the connected domain to generate the deviation region.

[0026] The process of determining the deviation anomalies of grid cells in each grid region of the power grid area based on the adjacency determination criteria specifically includes: The adjacency determination condition is that, within the same time window, deviation abnormal grids in different grid regions share an edge in the horizontal or vertical direction, or two deviation abnormal grids share a vertex in the diagonal direction, that is, two deviation abnormal grids are obliquely adjacent. Based on the adjacency determination criteria, the deviation anomaly grids in each grid region of the power grid area are determined: If two deviation anomalous grids share an edge in the horizontal or vertical direction, they are determined to be adjacent deviation anomalous grids. If two aberration meshes share a vertex in the diagonal direction, they are determined to be adjacent aberration meshes. If two aberration meshes do not meet any of the adjacency criteria, they are determined to be isolated aberration meshes.

[0027] In this embodiment of the invention, adjacency determination is performed on the deviation anomaly grids to pinpoint the specific spatial region of the power grid area where the anomaly is absorbed. Specifically, for different deviation anomaly grids within the same time window, adjacency determination conditions are set based on the geographical distribution of the power grid grid areas. These conditions are set using a combination of four-adjacency and eight-adjacency methods. Four-adjacency refers to two deviation anomaly grids being directly adjacent only in the horizontal direction (left and right) or the vertical direction (up and down), sharing a complete edge. This is an adjacency relationship that satisfies the horizontal or vertical edge-sharing condition. Eight-adjacency refers to an adjacency relationship that includes four additional diagonal directions on top of four-adjacency. That is, two deviation anomaly grids satisfy the adjacency condition regardless of whether they share a horizontal or vertical edge or only a vertex in the diagonal direction. Through these determination conditions, deviation anomalies in some new energy power plants and load clusters with oblique distribution can be identified. Since most grids are diagonally adjacent, using only four-adjacent grids would break down these real, continuous deviations into isolated grids. This embodiment, by combining eight-adjacent grids, can completely identify diagonally continuous anomalies without missing any actual, continuous areas of grid absorption anomalies. Therefore, if two deviation anomaly grids share an edge in the horizontal or vertical direction, they are determined to be adjacent deviation anomaly grids; if two deviation anomaly grids share a vertex in the diagonal direction, they are determined to be adjacent deviation anomaly grids. If two deviation anomaly grids do not meet any of the adjacent determination conditions, they are determined to be isolated deviation anomaly grids. By using adjacent deviation anomaly grids to represent continuous regional absorption anomalies, such as large-scale cloud cover blocking photovoltaics and sudden changes in regional wind speed, and using isolated deviation anomaly grids to represent single-point local deviations, such as single-site faults and single-point data fluctuations, the distinction can truly reflect whether the absorption anomaly is a regional problem or a single-point problem, and targeted adjustments can be made, which is consistent with the actual operation scenario of the power grid. A connected component analysis algorithm is employed to obtain connected components composed of adjacent deviation anomaly grids. The algorithm uses a breadth-first search (BFS) approach, suitable for spatial clustering of scattered deviation anomaly grids within a two-dimensional, regularly arranged power grid space, within the same time window. By traversing the entire grid, the first unvisited deviation anomaly grid is selected as the starting grid of the current connected component. This starting grid is added to the traversal queue and immediately marked as visited. The iteration process continues until the queue is empty. The iteration involves retrieving the current grid from the head of the queue and performing adjacency checks based on four-adjacency and eight-adjacency connections. The decision criteria involve searching all adjacent grids in the horizontal, vertical, and diagonal directions of the current grid. Grids with abnormal deviations within the search range that have not been visited are selected. These adjacent grids with abnormal deviations are marked as visited and added to the end of a queue. When the queue is empty, it indicates that all grids with abnormal deviations that satisfy the adjacency condition with the starting grid have been traversed. All visited grids combine to form an independent connected component. After continuous iteration, several connected components are generated. For isolated grids with abnormal deviations that have no adjacency relationship, they independently form a single-grid connected component, which is then combined with other connected components to generate a deviation region.

[0028] In one embodiment of the present invention, the deviation period analysis module is used to process the deviation region using a sliding time window based on the deviation region to obtain the deviation period and the duration of the deviation, specifically including: Set a sliding time window, wherein the start and end times of the sliding time window are consistent with the time window; Using a sliding time window, the deviation area is detected according to a preset sliding step size. If the time range of the sliding time window includes at least one deviation abnormal grid, the time range corresponding to the sliding time window is determined to be a deviation abnormal sliding period, and the start and end times of the deviation abnormal sliding period are recorded. If no deviation abnormal grid is included, it is determined to be a normal period. The sliding step size is one time window. For consecutive periods of abnormal deviation, the periods are merged according to the start time to obtain the deviation periods; The duration of the deviation is obtained based on the deviation period, start time, and end time.

[0029] In this embodiment of the invention, for aberration meshes scattered across multiple consecutive time windows within a deviation region, the start and end times of the deviation are obtained by using a sliding time window. The duration, start and end boundaries of the sliding time window are consistent with the time window set by the spatiotemporal standardization module. Therefore, the preset sliding step size of the sliding time window is one time window, allowing the sliding time window to slide continuously window by window along the time axis. Specifically, a single deviation region is treated as an analysis unit, and the sliding time window is slid sequentially along the time axis from morning to night to detect whether the deviation region's aberration meshes are included within that time range. If the window contains... The presence of at least one abnormal grid indicates a reduction deviation in that region during that time period, classifying it as an abnormal sliding period. The start and end times of this period are then accurately recorded. If there are no abnormal grids within the window, it is considered a normal period and is not recorded. Since the sliding step size is one time window, adjacent abnormal sliding periods are directly connected end-to-end on the time axis, belonging to the same continuous deviation process. All abnormal sliding periods are arranged in ascending order of start time, and the continuously connected periods are merged into a complete deviation period. For the merged complete deviation period, the duration of the deviation period is calculated by subtracting the start time from the end time.

[0030] In one embodiment of the present invention, the deviation visualization module is used to generate a line graph of the deviation distribution based on the deviation time period and the duration of the deviation in the deviation region, specifically including: Establish a coordinate system with the time axis as the horizontal axis and the space axis as the vertical axis; The individual deviation region is spatially scaled on the vertical axis of the coordinate system, and time-scaled on the horizontal axis of the coordinate system according to the start and end times of the deviation period. The slope of the line segment corresponding to the deviation period is represented by the duration of the deviation, and a line graph is generated.

[0031] In this embodiment of the invention, as shown in the above process, a two-dimensional spatiotemporal line graph is used to achieve an integrated visualization of the spatial distribution, time span, and duration of new energy consumption deviation. Specifically, the system time reference is used as the horizontal axis (time axis), and time scales are marked according to the time window intervals to cover the time range of all deviation periods. The grid spatial grid partitions and deviation regions are used as the vertical axis (spatial axis), and the deviation regions are arranged according to the deviation regions. Each vertical axis scale uniquely corresponds to an independent deviation region. This independent deviation region includes adjacent deviation anomaly grids and isolated deviation anomaly grids, thus completing the establishment of a time-space coordinate system. For a single independent deviation region, a fixed and unique spatial scale value is first assigned to it on the vertical axis to lock the spatial position of the deviation region. Then, the start and end times of the deviation period corresponding to the deviation region are used to accurately locate the start and end points of the time on the horizontal axis to complete the coordinate calibration of the spatial position of the deviation region and the time interval. The slope of the deviation period line segment is represented by the duration of the deviation. The longer the duration of the deviation, the greater the slope of the corresponding line segment, and the shorter the duration of the deviation, the smaller the slope.

[0032] In one embodiment of the present invention, the control module is used to control the power system by identifying and analyzing line graphs, specifically including: Based on the line graph, extract the deviation area, deviation period, deviation duration and slope from the line graph to generate control schemes for different power grid areas and deviation periods; The power system is regulated according to the regulation plan.

[0033] In this embodiment of the invention, the control module accurately extracts the spatial location of the deviation region, the time period of deviation occurrence, the duration of deviation, and the corresponding slope characteristic information by intelligently analyzing the spatiotemporal distribution line graph of the deviation. Based on the spatiotemporal distribution and duration of different deviations, it formulates zoned and time-based control schemes to achieve targeted control of the power system's new energy consumption, ensuring the stable operation of the power grid and the efficient consumption of new energy.

[0034] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the claimed invention. The scope of protection claimed by the appended claims and their equivalents is defined.

Claims

1. A smart prediction and control system for renewable energy consumption in new power systems, characterized in that, include: The spatiotemporal standardization module is used to divide the power grid area into grid areas and unify the measured data and predicted data of the power grid grid area into the same time window through the clock of the dispatch center. The data processing module is used to extract the measured data and predicted data for the corresponding time window in each grid region and calculate the deviation value; The comparison and marking module is used to mark the grid area as an abnormal grid within the corresponding time window based on the deviation value and a pre-set deviation threshold. The deviation region positioning module is used to set adjacency determination conditions between two adjacent deviation anomaly grids within the same time window based on the deviation anomaly grid. According to the adjacency determination conditions, the module determines the deviation anomaly grids by taking the grid region as a unit. The module combines the determined adjacent deviation anomaly grids and isolated deviation anomaly grids to obtain the deviation region within the time window. The deviation period analysis module is used to process the deviation region using a sliding time window based on the deviation region to obtain the deviation period and the duration of the deviation. The deviation visualization module is used to generate a line graph of the deviation distribution based on the deviation time period and the duration of the deviation in the deviation area. The control module is used to control the power system by identifying and analyzing line graphs.

2. The intelligent prediction and control system for renewable energy consumption in new power systems according to claim 1, characterized in that, The spatiotemporal standardization module is used to divide the power grid area into grid areas, and to unify the measured and predicted data of the power grid grid areas into the same time window through the clock of the dispatch center. Specifically, it includes: The power grid area is divided according to the dispatch and management boundaries of the power system to obtain grid areas; Set up a continuous, non-overlapping sliding time window. For the measured data and predicted data in the grid area, use the time window to adapt the time window separately to achieve the same time window granularity between the measured data and the predicted data.

3. The intelligent prediction and control system for renewable energy consumption in new power systems according to claim 1, characterized in that, The data processing module is used to extract the measured data and predicted data for each grid region within the corresponding time window, and to calculate the deviation value, specifically including: Extract the actual output of new energy sources and the actual power absorption capacity of the power grid in the current grid area and the current time window to obtain the measured data; By maintaining the same grid area and time window as the actual data extraction background, the predicted output value of new energy sources and the predicted value of grid absorption capacity are extracted to obtain the predicted data. Using a standard algorithm for power systems, the deviation between measured data and predicted data is calculated. The deviation includes both absolute deviation and relative deviation rate.

4. The intelligent prediction and control system for renewable energy consumption in new power systems according to claim 1, characterized in that, The comparison marking module is used to mark the grid region as an abnormal grid within the corresponding time window based on the deviation value and a pre-set deviation threshold. Specifically, it includes: The deviation threshold includes the absolute deviation threshold. and relative deviation rate threshold ; Extract the absolute deviation values ​​of all grid regions within the current time window. and relative deviation rate And extract the absolute deviation threshold corresponding to each grid region. and relative deviation rate threshold ; For all grid regions within the current time window, determine the deviation value: If the absolute deviation value ≥ Absolute Deviation Threshold or relative deviation rate ≥ Relative Deviation Rate Threshold The absorption deviation of the current time window in the grid region is determined to be abnormal, and it is marked as an abnormal deviation grid. If the absolute deviation value Absolute Deviation Threshold And relative deviation rate Relative Deviation Threshold If the absorption deviation of the current time window in the grid region is determined to be normal, the grid with abnormal deviation will not be marked.

5. The intelligent prediction and control system for renewable energy consumption in new power systems according to claim 1, characterized in that, The deviation region positioning module is used to set adjacency determination conditions between two adjacent deviation anomaly grids within the same time window based on the deviation anomaly grid, and to determine the deviation anomaly grids by grid region according to the adjacency determination conditions. The module then combines the determined adjacent deviation anomaly grids and isolated deviation anomaly grids to obtain the deviation region within the time window, specifically including: Based on the deviation anomaly grid, set the adjacency determination conditions; Based on the adjacency determination criteria, deviation anomaly grids in each grid region of the power grid area are determined. By marking all deviation anomaly grids as unvisited, any unvisited deviation anomaly grid is selected, and a connected component analysis algorithm is used to iteratively visit all deviation anomaly grids and mark them as visited according to the adjacency determination criteria until all deviation anomaly grids are marked as visited, thus completing the determination and forming a connected component composed of adjacent deviation anomaly grids, as well as isolated deviation anomaly grids. The isolated deviation anomaly mesh is combined with the connected domain to generate the deviation region.

6. The intelligent prediction and control system for new energy consumption in a new power system according to claim 5, characterized in that, The process of determining the deviation anomalies of grid cells in each grid region of the power grid area based on the adjacency determination criteria specifically includes: The adjacency determination condition is that, within the same time window, deviation abnormal grids in different grid regions share an edge in the horizontal or vertical direction, or two deviation abnormal grids share a vertex in the diagonal direction, that is, two deviation abnormal grids are obliquely adjacent. Based on the adjacency determination criteria, the deviation anomaly grids in each grid region of the power grid area are determined: If two deviation anomalous grids share an edge in the horizontal or vertical direction, they are determined to be adjacent deviation anomalous grids. If two aberration meshes share a vertex in the diagonal direction, they are determined to be adjacent aberration meshes. If two aberration meshes do not meet any of the adjacency criteria, they are determined to be isolated aberration meshes.

7. The intelligent prediction and control system for renewable energy consumption in new power systems according to claim 1, characterized in that, The deviation period analysis module is used to process the deviation region using a sliding time window based on the deviation region to obtain the deviation period and the duration of the deviation, specifically including: Set a sliding time window, wherein the start and end times of the sliding time window are consistent with the time window; Using a sliding time window, the deviation area is detected according to a preset sliding step size. If the time range of the sliding time window includes at least one deviation abnormal grid, the time range corresponding to the sliding time window is determined to be a deviation abnormal sliding period, and the start and end times of the deviation abnormal sliding period are recorded. If no deviation abnormal grid is included, it is determined to be a normal period. The sliding step size is one time window. For consecutive periods of abnormal deviation, the periods are merged according to the start time to obtain the deviation periods; The duration of the deviation is obtained based on the deviation period, start time, and end time.

8. The intelligent prediction and control system for renewable energy consumption in new power systems according to claim 1, characterized in that, The deviation visualization module is used to generate a line graph of the deviation distribution based on the deviation time period and the duration of the deviation in the deviation region, specifically including: Establish a coordinate system with the time axis as the horizontal axis and the space axis as the vertical axis; The individual deviation region is spatially scaled on the vertical axis of the coordinate system, and time-scaled on the horizontal axis of the coordinate system according to the start and end times of the deviation period. The slope of the line segment corresponding to the deviation period is represented by the duration of the deviation, and a line graph is generated.

9. The intelligent prediction and control system for renewable energy consumption in new power systems according to claim 1, characterized in that, The control module is used to control the power system by identifying and analyzing line graphs, specifically including: Based on the line graph, extract the deviation area, deviation period, deviation duration and slope from the line graph to generate control schemes for different power grid areas and deviation periods; The power system is regulated according to the regulation plan.

Images