Intelligent dispatching system and method based on electric power

Abstract

The invention relates to an intelligent scheduling system and method based on electric power, and belongs to the technical field of data processing, and the method comprises the steps: S1, obtaining the position information and power utilization types of all power distribution rooms in a target region, and obtaining a historical power supply sequence and power supply total data; s2, dividing the target area into a plurality of sub-areas, and integrating and dividing the power distribution rooms with the same power utilization category into three group levels in the sub-areas; s3, respectively inputting each mean value sequence in the prediction model, and setting a prediction result as the power demand of each power distribution room in each group level in prediction time; and S4, calculating the first total power demand of the power distribution room of each power utilization type in each sub-region in the prediction time and the second total power demand of the target region, and carrying out power dispatching. The method can predict the power demand of the power distribution rooms of different power utilization types in different areas, thereby avoiding the power failure of the power distribution rooms due to insufficient power supply.

Description

Technical Field

[0001] The present invention belongs to the technical field of data processing, and in particular relates to a system and method based on electric power intelligent dispatching. Background Art

[0002] Power dispatching is an effective management method adopted to ensure the safe and stable operation of the power grid, reliable external power supply, and orderly progress of various types of power production. With the development of science and technology, comprehensive monitoring and management of the power system can be achieved through data informationization, so that the power system can operate stably, effectively optimize the dispatch of power resources, and promote the planning and construction of the power grid.

[0003] For example, the Chinese patent application "CN112507131A" discloses a method, device and system for constructing a knowledge graph for power dispatching, the method includes the following steps: information acquisition step, obtaining preset index information of power and electricity, the index information includes available capacity for peak load regulation, network reserve coefficient, power margin, electricity margin, peak load avoidance and power supply balance; knowledge extraction step, extracting knowledge from the preset index information, knowledge extraction includes entity extraction, relationship extraction and attribute extraction; knowledge processing step, processing the extracted knowledge according to preset specifications; knowledge graph construction step, storing the processed knowledge in a graph database to construct a knowledge graph. The present invention adopts a unified means to store power and electricity index information, realizes the rapid construction of the knowledge graph for power dispatching, and improves the efficiency of power dispatching. For another example, the Chinese patent application "CN110489399A" discloses an automatic management system and method for electric power dispatching, which includes: an SQL database server, one or more electric power dispatching clients and multiple substation clients, the SQL database server is respectively connected to one or more electric power dispatching clients and multiple substation clients; each substation client corresponds to a substation or power station, and is arranged at the corresponding substation or power station, for the staff to input the electric power data and send the electric power data to the SQL database server; the electric power dispatching client is used to obtain the electric power data from the SQL database server, and provide report generation and data query functions. The automatic management system and method for electric power dispatching of the present invention uses the SQL database server and the electric power dispatching client to complete the data processing, classification and presentation work, replacing manual summary, improving the work efficiency of electric power dispatching, reducing the error rate of data calculation, and improving the level of electric power dispatching management.

[0004] However, in the above-mentioned prior art, the power data is dispatched by graph data and the power dispatch data is statistically managed. In actual situations, power dispatch may result in insufficient power allocation and excessive power allocation, which affects the reasonable dispatch of power resources. Summary of the invention

[0005] The present invention aims to provide a system and method based on intelligent power dispatching to solve the technical problems of insufficient power distribution and excessive power distribution in power dispatching in the prior art.

[0006] The specific technical solutions of the present invention are as follows:

[0007] A method based on intelligent power dispatching includes the following steps:

[0008] Step S1: Obtain a GIS image of the urban power supply area and define it as a target area, mark the location information and power consumption categories of all distribution rooms in the target area, set a time series for each power consumption category, and obtain the historical power supply series of each distribution room in the time series and the total power supply data of the historical power supply series based on the power consumption category;

[0009] Step S2: Divide the target area into multiple sub-areas, and integrate the distribution rooms with the same power consumption category into three group levels in the sub-areas;

[0010] Step S3: Establish a prediction model, calculate the average value of the historical power supply series data of the three group levels, generate each mean value sequence and input it into the prediction model, and set the prediction result as the power demand of each distribution room at each group level at the prediction time;

[0011] Step S4: Calculate the first total power demand of the power distribution room of each power consumption category in each sub-area at the predicted time and the second total power demand of the target area, and perform power dispatch.

[0012] Preferably, in step S2, the target area is divided into multiple sub-areas based on the location information, and in each of the sub-areas, the distribution rooms with the same electricity consumption category are integrated and divided into three group levels based on a preset interval array and the total power supply data, and the historical power supply series corresponding to each of the group levels are defined as a first-level series, a second-level series and a third-level series.

[0013] Preferably, in step S2, dividing the target area based on the location information to generate a plurality of sub-areas comprises the following steps:

[0014] Step S21: construct a rectangular coordinate block, the rectangular coordinate block includes the entire target area, divide the rectangular coordinate block into a plurality of areas of preset rectangular sizes and extract one of the areas to be defined as a first selected area, obtain the number of the power distribution rooms in the first selected area and define it as a first value, obtain the total value of the total power supply data corresponding to each of the power distribution rooms in the first selected area and define it as a second value;

[0015] Step S22: setting a first threshold and a second threshold, judging the first value and the second value based on the first threshold and the second threshold, if the first value is less than or equal to the first threshold, and the second value is less than or equal to the second threshold, setting the first selected area as the sub-area, otherwise, dividing the first selected area into equidistant areas to generate multiple sub-selected areas;

[0016] Step S23: Repeat step S22 until the number of the distribution rooms in the set sub-area is less than or equal to the first threshold, and the total value of the total power supply data corresponding to each of the distribution rooms is less than or equal to the second threshold, so as to divide the target area in the rectangular coordinate block into each of the sub-areas.

[0017] Preferably, in step S22, each of the first selected areas is divided equally to generate a plurality of sub-selected areas based on the following steps:

[0018] Based on the rectangular coordinate block, the coordinates of the four endpoints of the first selection area are obtained, and the vertical distance and the horizontal distance of the first selection area are obtained; based on the midpoints of the vertical distance and the horizontal distance, the first selection area is divided in the horizontal and vertical directions to generate four areas, which are defined as the four sub-selections.

[0019] Preferably, in step S3, the prediction model is established, and the data at the same time point of the first-level series, the second-level series and the third-level series are added and the average value is obtained to generate a first mean sequence, a second mean sequence and a third mean sequence and input them into the prediction model respectively, and the first prediction result, the second prediction result and the third prediction result are output respectively based on the preset prediction time, and are respectively set as the first power demand, the second power demand and the third power demand of each distribution room in the corresponding group level at the prediction time.

[0020] Preferably, in step S3, establishing the prediction model and outputting the first prediction results based on the preset prediction time respectively include the following steps:

[0021] The first mean value sequence is set as the first target variable, the historical temperature data in the same time series as the first target variable is obtained and defined as the first variable data, the supply customer data of the power distribution room in the same time series as the first target variable is obtained and defined as the second variable data, and the prediction model is constructed by the first target variable, the first variable data and the second variable data;

[0022] The first derivative e′ of the first variable data is calculated based on the first formula 1 , the first formula is: (i=2,3,…,I), where e (1，i) is the value of the first variable data in the i-th time series, e (1，i-1) is the value of the first variable data in the (i-1)th time series, Δt is the time interval of the time series, and the second-order derivative e″ of the first variable data is calculated based on the second formula 1 , the second formula is (i=2, 3, ..., I-1), use the same steps to calculate the first-order derivative e' of the second variable data 2 and the second-order derivative e″ 2 , the first prediction result of the prediction model is calculated based on the third formula The third formula is: (k=0, 1,...,3K; K=22; i=2, 3,...,I-1),

[0023] Among them, K is two sets of variable data, is the regression coefficient, which is calculated by solving the fourth formula,

[0024] The fourth formula is: (k=0, 1,...,K; K=2; i=2, 3,...,I), where is the partial derivative operator symbol, and y is the first target variable.

[0025] Preferably, in step S4, the first total power demand of the distribution room of each power consumption category in each sub-area at the predicted time is calculated based on the first power demand, the second power demand and the third power demand, the number of the sub-areas is obtained to calculate the second total power demand of the target area, and power scheduling is performed based on the second total power demand.

[0026] Preferably, in step S4, the second total power demand W of the target area at the predicted time is obtained based on a fifth formula, and the fifth formula is: Wherein, H is the number of the electricity consumption categories, Q is the number of the sub-areas, is the nth prediction result, and m is the number of distribution rooms contained in each level in the group level.

[0027] Preferably, power dispatch is completed based on the power demand of all the distribution rooms contained in each sub-area in the target area. If a line fault occurs in a distribution room, based on the group classification to which the distribution room belongs and the location information, the power demand of the distribution room with a lower power demand than that of the faulty distribution room is screened out from the nearest group classification for dispatch.

[0028] The present invention also provides a system based on electric power intelligent dispatching, which is used to implement the method based on electric power intelligent dispatching, and the system includes the following modules:

[0029] A data acquisition module is used to acquire a GIS image of a city power supply area and define it as a target area, mark the location information and power consumption categories of all distribution rooms in the target area, set a time series for each power consumption category, and acquire a historical power supply series of each distribution room in the time series and total power supply data of the historical power supply series based on the power consumption category;

[0030] A region division module, used for dividing the target region by the location information to generate a plurality of sub-regions, in each of the sub-regions, based on a preset interval array and the total power supply data, integrating and dividing the distribution rooms with the same power consumption category into three group levels, and defining the historical power supply series corresponding to each of the group levels as a first-level series, a second-level series, and a third-level series;

[0031] A data prediction module, used for establishing a prediction model, adding the data of the first-level sequence, the second-level sequence and the third-level sequence at the same time point and calculating the average value to generate a first mean value sequence, a second mean value sequence and a third mean value sequence and inputting them into the prediction model respectively, outputting a first prediction result, a second prediction result and a third prediction result respectively based on a preset prediction time, and setting them as the first power demand, the second power demand and the third power demand of each distribution room in the corresponding group level at the prediction time;

[0032] A data generation module calculates the first total power demand of the distribution room of each power consumption category in each sub-area at the predicted time through the first power demand, the second power demand and the third power demand, obtains the number of the sub-areas to calculate the second total power demand of the target area, and performs power dispatch based on the second total power demand.

[0033] The present invention provides a power intelligent dispatching system and method, which has the following beneficial effects:

[0034] The present invention first divides the target area into multiple sub-areas according to the preset area size, which is conducive to reducing the error range of power prediction, and then divides the various types of distribution rooms in the sub-areas into four categories according to the power consumption category, collects historical power supply series according to different power consumption scenarios, which is conducive to improving the credibility of the historical power supply series, and then divides the total power supply data of each distribution room of the same power consumption category into three group levels by setting an interval array, and respectively calculates the average value of each historical power supply series in each group level to generate three level series, and inputs the three level series into the prediction model for prediction, which can not only retain the characteristic distribution of the series in each group level, but also reduce the data calculation amount of the prediction model, and finally sets each prediction result to the power demand of the distribution room of different power consumption categories in each sub-area at the prediction time, and then calculates the second total power demand of the target area, and the power system can complete intelligent scheduling of the distribution rooms of each power consumption category in different sub-areas based on each prediction result, avoid power failures in the distribution room due to insufficient power supply, and reduce the phenomenon of power distribution waste.

[0035] The present invention also sets historical temperature data closely related to electricity demand and supplier data of the distribution room as two variable data in the prediction model and performs differential operations, thereby improving the prediction accuracy of the prediction model when predicting the first target variable in the time series, and avoiding excessive smoothing of the prediction results when predicting a single variable, which reduces the prediction accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 This is a flowchart of the steps of the method for intelligent power dispatching according to the present invention;

[0037] Figure 2 A flowchart of the steps for dividing each sub-area of ​​the present invention;

[0038] Figure 3 This is a structural diagram of the power intelligent dispatching system based on the present invention. DETAILED DESCRIPTION

[0039] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation mode, structure, characteristics and effects of the present invention are described in detail below in combination with the accompanying drawings and preferred embodiments.

[0040] Example 1

[0041] like Figure 1 As shown, a method based on intelligent power dispatching of the present invention includes:

[0042] Step S1: Obtain a GIS image of the urban power supply area and define it as the target area, mark the location information and power consumption categories of all distribution rooms in the target area, set the time series for each power consumption category, and obtain the historical power supply series of each distribution room in the time series and the total power supply data of the historical power supply series based on the power consumption category.

[0043] Specifically, in this embodiment, GIS image refers to a spatial image generated by a geographic information system, which can clearly depict the geographic information of the required object. By integrating with the urban power system, it is convenient to accurately and visually locate the location information of each node in the power system. The target area refers to the regional scope involved in power demand scheduling, including but not limited to urban and rural areas. The distribution room refers to the distribution place for distributing electric energy to low-voltage users, and the building or building complex used for electric energy distribution, control and protection. The power system can complete various types of power supply scheduling needs based on the conversion and transmission of the distribution room. The types of distribution rooms include but are not limited to distribution boxes for a residential building, distribution rooms for industrial production, and power supply rooms for shopping malls and office buildings. In this embodiment, the power demand of each distribution room in the target area is predicted to realize the function of intelligent power scheduling. The location information refers to the coordinate longitude and latitude. In this embodiment, the power consumption categories refer to four categories: residential power consumption, general industrial and commercial power consumption, large-scale industrial power consumption, and agricultural production power consumption. The types of each distribution room are divided according to the power consumption category, which can be In order to avoid omission of power demand, it can effectively improve the accuracy of data prediction. Time series refers to data that arranges historical time based on a set time interval. In order to reasonably use the historical data of different power consumption categories, different power consumption categories are set to different time series. For example, the residential power consumption category can set the time series of historical dates to 0:00, 3:00, 6:00, 9:00, 12:00, 15:00, 18:00, 21:00 and 24:00, that is, each day in the historical date is divided into a time series with an interval of 3 hours. The general industrial and commercial power consumption category can divide each day in the historical date into a time series with an interval of 2 hours. In this embodiment, in order to reduce the system operation load, each day in the historical date of each power consumption category is uniformly divided into a time series with an interval of 3 hours. The time series should be continuous and have more feature points, such as including multiple types such as different seasons, holidays and working days. The historical power supply series refers to the power supply in each time series, and the total power supply data refers to the sum of the power supply of each distribution room in all time series.

[0044] Step S2: Divide the target area based on the location information to generate multiple sub-areas. In each sub-area, the distribution rooms with the same electricity consumption category are integrated and divided into three group levels based on the preset interval array and the total power supply data. The historical power supply series corresponding to each group level are defined as the first-level series, the second-level series and the third-level series.

[0045] Specifically, in this embodiment, how the location information is divided will be described in detail later. After the area division is completed, the target area is first divided into multiple sub-areas according to the conditions, which can effectively and accurately determine the distribution range of each distribution room, so as to achieve the purpose of refined power dispatching. The interval array can be set by dividing the data distribution law in the total power supply data of the distribution room of the same power consumption category according to the level to set the value range. For example, the interval arrays corresponding to the four power consumption categories are {(0, 0.5], (0.5, 1], (1, ∞)}, {(0, 10], (10, 30], (30, ∞)}, {(0, 20], (20, 60], (60, ∞)} and {(0, 5], (5, 15], (15, ∞)}, the unit is: ten thousand degrees, wherein the values ​​of each interval correspond to the three group levels of the four electricity consumption categories, which are set as Class A, Class B and Class C respectively, and the historical power supply series contained in the three group levels are set as the first-level series, the second-level series and the third-level series of the electricity consumption categories. By classifying the total power supply data of the distribution room by level, the deviation can be reduced when the average value of the historical power supply series is obtained in the following steps.

[0046] Step S3: Establish a prediction model, add the data of the first-level series, the second-level series and the third-level series at the same time point and calculate the average value to generate a first mean sequence, a second mean sequence and a third mean sequence and input them into the prediction model respectively, output the first prediction result, the second prediction result and the third prediction result respectively based on the preset prediction time, and set them as the first power demand, the second power demand and the third power demand of each distribution room in the corresponding group level at the prediction time.

[0047] Specifically, in this embodiment, the prediction model is to establish a mathematical model to predict the target variable. Since the historical power supply series is data that fluctuates with the time series, its change law is closely related to the temperature data and the power supply user data of the distribution room. Therefore, the prediction model used in this embodiment is a regression prediction model. By using a variety of differential data, this model can not only reduce the load of equipment operation during data training, but also reduce the prediction error when predicting the time series data of the target variable, and avoid over-fitting of the characteristic values. Taking the average value after integration means accumulating the historical power supply series of the same group level on each corresponding time series and then calculating the average value. For example, there are 10 distribution rooms at group level A in the residential electricity consumption category. The historical power supply series of these 10 distribution rooms are added based on each time series and divided by 10 to calculate the average value of each time series, and the combination of the average values ​​on each time series is defined as the first mean sequence. Then, the first mean sequence is input into the prediction model and the first prediction result corresponding to the prediction time is output and set as the power demand of each distribution room at the same group level, that is, the first power demand, wherein the first power demand is based on the time series data corresponding to the prediction time. Repeat this step, and integrate the series at other group levels to output the second power demand and the third power demand.

[0048] Step S4: Calculate the first total power demand of the distribution room of each power consumption category in each sub-area at the predicted time based on the first power demand, the second power demand and the third power demand, obtain the number of sub-areas to calculate the second total power demand of the target area, and perform power dispatch based on the second total power demand.

[0049] Specifically, in this embodiment, the first power demand, the second power demand and the third power demand respectively refer to the power demand of a single distribution room in class A, class B and class C in each power consumption category in each sub-area within the predicted time. By counting the number of distribution rooms of class A, class B and class C in the sub-area and then accumulating and integrating them, the power demand of each power consumption category in each sub-area can be calculated. By counting the power demand of each sub-area, the second total power demand of the target area within the predicted time can be calculated, so as to achieve the purpose of intelligent power scheduling and avoid power failures in the distribution room due to insufficient power supply.

[0050] The present invention first divides the target area into multiple sub-areas according to the preset area size, which is conducive to reducing the error range of power prediction, and then divides the various types of distribution rooms in the sub-areas into four categories according to the power consumption category, collects historical power supply series according to different power consumption scenarios, which is conducive to improving the credibility of the historical power supply series, and then divides the total power supply data of each distribution room of the same power consumption category into three group levels by setting an interval array, and respectively calculates the average value of each historical power supply series in each group level to generate three level series, and inputs the three level series into the prediction model for prediction, which can not only retain the characteristic distribution of the series in each group level, but also reduce the data calculation amount of the prediction model, and finally sets each prediction result to the power demand of the distribution room of different power consumption categories in each sub-area at the prediction time, and then calculates the second total power demand of the target area, and the power system can complete intelligent scheduling of the distribution rooms of each power consumption category in different sub-areas based on each prediction result, avoid power failures in the distribution room due to insufficient power supply, and reduce the phenomenon of power distribution waste.

[0051] The present invention also sets historical temperature data closely related to electricity demand and supplier data of the distribution room as two variable data in the prediction model and performs differential operations, thereby improving the prediction accuracy of the prediction model when predicting the first target variable in the time series, and avoiding excessive smoothing of the prediction results when predicting a single variable, which reduces the prediction accuracy.

[0052] It is particularly noteworthy that the present invention can predict the power demand of distribution rooms of different power consumption categories in different areas, thereby solving the problem of power failures in the distribution room due to insufficient power supply.

[0053] Example 2

[0054] Based on Embodiment 1, in step S2, dividing the target area based on the location information to generate multiple sub-areas includes the following steps:

[0055] Step S21: construct a rectangular coordinate block, the rectangular coordinate block includes the entire target area, divide the rectangular coordinate block into a plurality of areas of preset rectangular sizes and extract one of the areas as a first selected area, obtain the number of distribution rooms in the first selected area and define it as a first value, obtain the total value of the total power supply data corresponding to each distribution room in the first selected area and define it as a second value;

[0056] Step S21: setting a first threshold and a second threshold, judging the first value and the second value based on the first threshold and the second threshold, if the first value is less than or equal to the first threshold, and the second value is less than or equal to the second threshold, setting the first selected area as a sub-area, otherwise, dividing the first selected area into equidistant areas to generate multiple sub-selected areas;

[0057] Step S23: Repeat step S22 until the number of distribution rooms in the set sub-area is less than or equal to the first threshold, and the total value of the total power supply data corresponding to each distribution room is less than or equal to the second threshold, so as to divide the target area in the rectangular coordinate block into sub-areas.

[0058] Specifically, in this embodiment, if Figure 2 As shown, the rectangular coordinate block R2 refers to reducing the target area according to a preset ratio so as to completely include the target area R1. The rectangular coordinate block can locate and describe the irregular target area through coordinate points, reducing the error of the actual distance caused by the insufficient accuracy of the longitude and latitude in the location information of the distribution room. The preset rectangular size refers to presetting the shape of a maximum area, and randomly dividing the target area in the rectangular coordinate block into various areas less than or equal to the size of the shape. For example, the preset rectangle r1 is set to a size of 2×2 (unit: cm), then the rectangular coordinate block is sequentially divided into multiple areas less than or equal to 2×2 (unit: cm), and then the distribution room in each area is determined. Whether the number of distribution rooms and the total power supply data corresponding to each distribution room are less than or equal to the preset first threshold and second threshold respectively, if so, the area is set as a sub-area, if not, the area is further divided into multiple sub-areas by the equidistant division method, and the same steps are performed for judgment to complete the division of all sub-areas in the target area. Through this step, the distribution range of each distribution room can be narrowed. At the same time, setting the second threshold can screen out areas with larger power supply and make more detailed divisions, which is conducive to classifying and predicting the power supply of each distribution room in the target area, providing high-precision data for the execution of the next step, and effectively meeting the needs of intelligent power dispatching.

[0059] In step S3, establishing a prediction model and outputting first prediction results based on preset prediction times respectively include the following steps:

[0060] The first mean value sequence is set as the first target variable, the historical temperature data in the same time series as the first target variable is obtained and defined as the first variable data, the supply user data of the power distribution room in the same time series as the first target variable is obtained and defined as the second variable data, and a prediction model is constructed by the first target variable, the first variable data and the second variable data;

[0061] Calculate the first derivative e' of the first variable data based on the first formula 1 , the first formula is: (i=2,3,…,I), where e (1，i) is the value of the first variable data in the i-th time series, e (1，i-1) is the value of the first variable data in the (i-1)th time series, Δt is the time interval of the time series, and the second-order derivative e″ of the first variable data is calculated based on the second formula1 , the second formula is (i=2, 3, ..., I-1), use the same steps to calculate the first-order derivative e' of the second variable data 2 and the second-order derivative e″ 2 , the first prediction result of the prediction model is calculated based on the third formula The third formula is: (k=0, 1, ···, 3K; K=2; i=2, 3, ···, I-1), where K is two sets of variable data, is the regression coefficient, which is calculated by solving the fourth formula: (k=0, 1,...,K; K=2; i=2, 3,...,I), where is the partial derivative operator symbol, and y is the first target variable.

[0062] Specifically, in this embodiment, the first target variable refers to the first mean sequence, the first variable data and the second variable data refer to the influencing factors that affect the first target variable, wherein the historical temperature data refers to the past temperature change data, and the supplier data refers to the number of households, businesses and factories supplied by each distribution room. Since the power supply of distribution rooms of various electricity consumption categories will change with changes in temperature and suppliers, the time series data of the two variable data are differentially calculated to generate the prediction result of the first target variable at the prediction time.

[0063] Specifically, the first variable data and the second variable data are respectively subjected to a secondary difference operation through the first formula and the second formula to obtain two new variable data, which can be called differential variable data, wherein the differential operation refers to the time derivative of the time series data of each variable in at least two or more variable data, wherein the differential variable data subjected to the first-order difference and the differential variable data subjected to the second-order difference are variable data of two different concepts, and since two variable data are used, the value of K is 2, and in the third formula, each variable in the differential variable data is added with the corresponding regression coefficient The sum of the products of , wherein each regression coefficient of the variable data and each regression coefficient of the differential variable data are determined by the fourth formula for the third formula to obtain the predicted value of the first target variable. The first mean sequence, the second mean sequence and the third mean sequence are respectively set as the first variable data, and the first prediction result, the second prediction result and the third prediction result at the prediction time are output, which correspond to the power demand corresponding to the three group levels A, B and C of the distribution rooms with the same power consumption category in the sub-area at the prediction time. For example, in the sub-area, the prediction time is set to 12 hours, the electricity consumption category is residential electricity consumption, the number of distribution rooms at group level A is 100, the number of distribution rooms at group level B is 50, the number of distribution rooms at group level C is 30, the first prediction result is 1, the second prediction result is 1.5, and the third prediction result is 3. Then, in the prediction of the next 12 hours, the power demand of the 100 A-level distribution rooms for residential electricity consumption in the sub-area is 1, the power demand of the 50 B-level distribution rooms is 1.5, and the power demand of the 30 C-level distribution rooms is 3. The unit of power demand is: 10,000 kWh.

[0064] Each first constituency is equally divided to generate multiple sub-constituencies based on the following steps:

[0065] Based on the rectangular coordinate block, the coordinates of the four endpoints of the first selection are obtained, and the vertical distance and horizontal distance of the first selection are obtained. Based on the midpoints of the vertical distance and the horizontal distance, the first selection is divided in the horizontal and vertical directions to generate four areas, which are defined as four sub-selections.

[0066] Specifically, in this embodiment, if Figure 2 As shown in the figure, the horizontal and vertical coordinates of the four endpoints in the first selection area r1 are marked, which are (x 1 ,y 1 )、(x 1 ,y 2 )、(x 2 ,y 1 ) and (x 2 ,y 2 ), get the midpoints of each side in the first selection area respectively and Connect separately and Generate the first connection line, connect and A second connection line is generated, that is, the first selection area is divided into four areas by the first connection line and the second connection line, wherein each area is set as a sub-selection area.

[0067] In step S4, the second total power demand W of the target area at the predicted time is obtained based on the fifth formula, and the fifth formula is: Where H is the number of electricity consumption categories, Q is the number of sub-regions, is the nth prediction result, and m is the number of distribution rooms included in each level of the group level.

[0068] Specifically, in this embodiment, the above steps can predict the power demand of the distribution room of each power consumption category in each sub-area, and the fifth formula summarizes the second total power demand W of the target area at the predicted time. For example, the target area is divided into 3 sub-areas, and the corresponding power demand of the distribution room of each power consumption category in each sub-area in the next 12 hours is (265, 300, 500, 200), (280, 100, 200, 100) and (100, 180, 600, 300) respectively. The second total power demand W of the target area in the next 12 hours is calculated to be 265+300+500+200+280+100+200+100+100+180+600+300=3125, in units of ten thousand kWh.

[0069] Power dispatch is completed based on the power demand of all distribution rooms contained in each sub-area in the target area. If there is a line fault in a distribution room, the power demand lower than that of the faulty distribution room is selected from the nearest group classification for dispatch based on the group classification and location information to which the distribution room belongs.

[0070] Specifically, the power system provides the required electricity to each distribution room based on the second total electricity demand of the target area and the electricity demand of each sub-area within the predicted time to complete the power dispatching work. If a distribution room suffers a power outage due to a line fault, the location information can be used to determine the distribution room closest to the faulty distribution room and with the smallest electricity demand to connect the power supply, thereby avoiding economic losses and safety issues caused by long power outages.

[0071] Example 3

[0072] like Figure 3 As shown, the present invention also provides a system based on electric power intelligent dispatching, which is used to implement the above-mentioned method based on electric power intelligent dispatching, and the system mainly includes:

[0073] A data acquisition module is used to obtain a GIS image of the urban power supply area and define it as a target area, mark the location information and power consumption categories of all distribution rooms in the target area, set a time series for each power consumption category, and obtain the historical power supply series of each distribution room in the time series and the total power supply data of the historical power supply series based on the power consumption category;

[0074] A region division module is used to divide the target region into multiple sub-regions according to the location information. In each sub-region, the distribution rooms with the same power consumption category are integrated and divided into three group levels based on the preset interval array and the total power supply data. The historical power supply series corresponding to each group level are defined as the first-level series, the second-level series and the third-level series.

[0075] A data prediction module is used to establish a prediction model, add the data of the same time point of the first-level sequence, the second-level sequence and the third-level sequence and then calculate the average value to generate a first mean value sequence, a second mean value sequence and a third mean value sequence and input them into the prediction model respectively, output a first prediction result, a second prediction result and a third prediction result respectively based on a preset prediction time, and set them as the first power demand, the second power demand and the third power demand of each distribution room in the corresponding group level at the prediction time;

[0076] The data generation module calculates the first total power demand of the distribution room of each power consumption category in each sub-area at the predicted time through the first power demand, the second power demand and the third power demand, obtains the number of sub-areas to calculate the second total power demand of the target area, and performs power dispatch based on the second total power demand.

[0077] The present invention also provides a computer storage medium, which stores program instructions, wherein when the program instructions are executed, the device where the computer storage medium is located is controlled to execute the above-mentioned method based on intelligent power dispatching. It should be understood that although the steps in the flowcharts of the various embodiments of the present invention are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless clearly stated in this document, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least part of the steps in each embodiment may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0078] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The above-mentioned program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchl ink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0079] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any brief modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention are still within the scope of the technical solution of the present invention.

Claims

1. A method based on intelligent power dispatching, characterized in that: The steps include: Step S1: Obtain a GIS image of the urban power supply area and define it as a target area, mark the location information and power consumption categories of all distribution rooms in the target area, set a time series for each power consumption category, and obtain the historical power supply series of each distribution room in the time series and the total power supply data of the historical power supply series based on the power consumption category; Step S2: Divide the target area into multiple sub-areas, and integrate the distribution rooms with the same power consumption category into three group levels in the sub-areas; Step S3: Establish a prediction model, calculate the average value of the historical power supply series data of the three group levels, generate each mean value sequence and input it into the prediction model, and set the prediction result as the power demand of each distribution room at each group level at the prediction time; Step S4: Calculate the first total power demand of the power distribution room of each power consumption category in each sub-area at the predicted time and the second total power demand of the target area, and perform power dispatch.

2. The method based on intelligent power dispatching according to claim 1, characterized in that: In step S2, the target area is divided into multiple sub-areas based on the location information. In each of the sub-areas, the distribution rooms with the same electricity consumption category are integrated and divided into three group levels based on a preset interval array and the total power supply data. The historical power supply series corresponding to each group level are defined as a first-level series, a second-level series and a third-level series.

3. The method based on electric power intelligent dispatching according to claim 2 is characterized in that: Dividing the target area based on the location information to generate multiple sub-areas includes the following steps: Step S21: construct a rectangular coordinate block, the rectangular coordinate block includes the entire target area, divide the rectangular coordinate block into a plurality of areas of preset rectangular sizes and extract one of the areas to be defined as a first selected area, obtain the number of the power distribution rooms in the first selected area and define it as a first value, obtain the total value of the total power supply data corresponding to each of the power distribution rooms in the first selected area and define it as a second value; Step S22: setting a first threshold and a second threshold, judging the first value and the second value based on the first threshold and the second threshold, if the first value is less than or equal to the first threshold, and the second value is less than or equal to the second threshold, setting the first selected area as the sub-area, otherwise, dividing the first selected area into equidistant areas to generate multiple sub-selected areas; Step S23: Repeat step S22 until the number of the distribution rooms in the set sub-area is less than or equal to the first threshold, and the total value of the total power supply data corresponding to each of the distribution rooms is less than or equal to the second threshold, so as to divide the target area in the rectangular coordinate block into each of the sub-areas.

4. The method based on intelligent power dispatching according to claim 3 is characterized in that: In step S22, each of the first selected areas is equally divided to generate a plurality of sub-selected areas based on the following steps: Based on the rectangular coordinate block, the coordinates of the four endpoints of the first selection area are obtained, and the vertical distance and the horizontal distance of the first selection area are obtained; based on the midpoints of the vertical distance and the horizontal distance, the first selection area is divided in the horizontal and vertical directions to generate four areas, which are defined as the four sub-selections.

5. The method based on intelligent power dispatching according to claim 1 is characterized in that: In the step S3, the prediction model is established, and the data of the first-level series, the second-level series and the third-level series at the same time point are added and the average value is obtained to generate a first mean sequence, a second mean sequence and a third mean sequence and input them into the prediction model respectively, and the first prediction result, the second prediction result and the third prediction result are output respectively based on the preset prediction time, and are respectively set as the first power demand, the second power demand and the third power demand of each distribution room in the corresponding group level at the prediction time.

6. The method based on intelligent power dispatching according to claim 5 is characterized in that: Establishing the prediction model and outputting the first prediction results based on the preset prediction time respectively comprises the following steps: The first mean value sequence is set as the first target variable, the historical temperature data in the same time series as the first target variable is obtained and defined as the first variable data, the supply customer data of the power distribution room in the same time series as the first target variable is obtained and defined as the second variable data, and the prediction model is constructed by the first target variable, the first variable data and the second variable data; The first-order derivative e′1 of the first variable data is calculated based on a first formula, wherein the first formula is: Among them, e (1，i) is the value of the first variable data in the i-th time series, e (1，i-1) is the value of the first variable data in the (i-1)th time series, Δt is the time interval of the time series, and the second-order derivative e″1 of the first variable data is calculated based on the second formula. The second formula is: The first-order derivative e′2 and the second-order derivative e″2 of the second variable data are calculated using the same steps, and the first prediction result of the prediction model is calculated based on the third formula: The third formula is: Among them, K is two sets of variable data, is the regression coefficient, and the regression coefficient is calculated by solving the fourth formula, which is: in is the partial derivative operator symbol, and y is the first target variable.

7. The method based on intelligent power dispatching according to claim 1 is characterized in that: In the step S4, the first total power demand of the distribution room of each power consumption category in each sub-area at the predicted time is calculated based on the first power demand, the second power demand and the third power demand, the number of the sub-areas is obtained to calculate the second total power demand of the target area, and power scheduling is performed based on the second total power demand.

8. The method based on intelligent power dispatching according to claim 7 is characterized in that: In step S4, the second total power demand W of the target area at the predicted time is obtained based on the fifth formula, and the fifth formula is: Wherein, H is the number of the electricity consumption categories, Q is the number of the sub-areas, is the nth prediction result, and m is the number of distribution rooms contained in each level in the group level.

9. The method based on intelligent power dispatching according to claim 8, characterized in that: Power dispatch is completed based on the power demand of all the distribution rooms contained in each sub-area in the target area. If a line fault occurs in a distribution room, the power demand lower than that of the faulty distribution room is selected from the closest distribution room based on the group classification to which the distribution room belongs and the location information for dispatch.

10. A power intelligent dispatching system, used to implement a power intelligent dispatching method as claimed in any one of claims 1 to 9, characterized in that: The system includes the following modules: A data acquisition module is used to acquire a GIS image of a city power supply area and define it as a target area, mark the location information and power consumption categories of all distribution rooms in the target area, set a time series for each power consumption category, and acquire a historical power supply series of each distribution room in the time series and total power supply data of the historical power supply series based on the power consumption category; A region division module, used for dividing the target region by the location information to generate a plurality of sub-regions, in each of the sub-regions, based on a preset interval array and the total power supply data, integrating and dividing the distribution rooms with the same power consumption category into three group levels, and defining the historical power supply series corresponding to each of the group levels as a first-level series, a second-level series, and a third-level series; A data prediction module, used for establishing a prediction model, adding the data of the first-level sequence, the second-level sequence and the third-level sequence at the same time point and calculating the average value to generate a first mean value sequence, a second mean value sequence and a third mean value sequence and inputting them into the prediction model respectively, outputting a first prediction result, a second prediction result and a third prediction result respectively based on a preset prediction time, and setting them as the first power demand, the second power demand and the third power demand of each distribution room in the corresponding group level at the prediction time; A data generation module calculates the first total power demand of the distribution room of each power consumption category in each sub-area at the predicted time through the first power demand, the second power demand and the third power demand, obtains the number of the sub-areas to calculate the second total power demand of the target area, and performs power dispatch based on the second total power demand.

Images