Power grid electricity sale quantity prediction method and electricity sale management system

Abstract

The invention discloses a power grid power sale quantity prediction method and a power sale management system, and relates to the technical field of power grid management. Power grid coverage areas are obtained through an acquisition end, each area is marked to form an initial area list, and after area power consumption data are obtained, time-space analysis is performed on the power consumption data to obtain a power grid power sale quantity prediction result; constructing a regional electricity consumption influence index according to a regional electricity consumption time sequence analysis result, constructing a regional electricity consumption fluctuation factor according to a regional electricity consumption space-time analysis result, and combining the electricity consumption influence index and the electricity consumption fluctuation factor to dynamically obtain the predicted electricity consumption of the region. And summing the predicted electricity consumption of all the regions to obtain the predicted electricity sale quantity of the power grid. According to the prediction method, the power grid coverage areas are divided, data analysis is performed on each area independently, then the predicted power consumption of the areas is dynamically obtained, and then the predicted power sales of the power grid is obtained by summing the predicted power consumption of all the areas, so that the prediction accuracy and precision of the predicted power sales of the power grid are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid management, and in particular to a power grid power sales forecasting method and a power sales management system. Background Art

[0002] Grid management refers to the process of comprehensive coordination and control of all aspects of power system operation, maintenance, dispatch and optimization, aiming to ensure the safe, stable, economical and efficient operation of the power system. Grid management involves all aspects of power production, transmission, distribution and use, and is a core component of the modern energy system.

[0003] The prior art has the following defects: The existing power grid's electricity sales are set based on the electricity sales in the previous period. However, in actual applications, since the power grid usually covers a certain area and there are factors in the area that affect electricity consumption, setting it based on the electricity sales in the previous period may result in problems such as too much or too little electricity sales.

[0004] Based on this, the present invention proposes a power grid electricity sales forecasting method and power sales management system, which divides the power grid coverage area, performs data analysis on each area separately, dynamically obtains the predicted electricity consumption of the area, and then sums the predicted electricity consumption of all areas to obtain the power grid predicted electricity sales, which is beneficial to improving the prediction accuracy and precision of the power grid predicted electricity sales. Summary of the invention

[0005] The purpose of the present invention is to provide a power grid electricity sales amount prediction method and electricity sales management system to solve the shortcomings of the background technology.

[0006] In order to achieve the above object, the present invention provides the following technical solution: a method for predicting power sales volume of a power grid, the prediction method comprising the following steps: The data collection end obtains the grid coverage area and marks each area to form an initial area list; After obtaining the regional electricity consumption data, conduct spatiotemporal analysis on the electricity consumption data, build the regional electricity consumption impact index based on the regional electricity consumption time series analysis results, and build the regional electricity consumption fluctuation factor based on the regional electricity consumption spatiotemporal analysis results; The electricity consumption impact index is combined with the electricity consumption fluctuation factor to dynamically obtain the predicted electricity consumption of the region, and the predicted electricity consumption of all regions is summed up to obtain the predicted electricity sales of the power grid.

[0007] In a preferred embodiment, constructing a regional electricity consumption impact index based on the regional electricity consumption time series analysis results includes the following steps: Obtain regional electricity consumption data, including electricity consumption change index and industrial output value change index; The electricity consumption change index and the industrial output value change index are normalized, and the value range of the electricity consumption change index and the industrial output value change index is mapped to [0,1]; The normalized electricity consumption change index and industrial output value change index are summed to obtain the electricity consumption impact index.

[0008] In a preferred embodiment, the power consumption impact index is combined with the power consumption fluctuation factor to dynamically obtain the predicted power consumption of the region, including the following steps: The variation coefficient of the region is obtained by multiplying the power consumption fluctuation factor by the power consumption impact index, and the current power consumption of the region is obtained. The predicted power consumption of the region is obtained by adjusting the current power consumption by the variation coefficient. The expression is: , where To predict electricity consumption, is the current power consumption, is the coefficient of variation, is the change threshold; After obtaining the predicted electricity consumption of each area, the predicted electricity consumption of all areas is summed up to obtain the predicted electricity sales of the power grid.

[0009] In a preferred embodiment, constructing a regional power consumption fluctuation factor based on the regional power consumption spatiotemporal analysis results includes the following steps: Obtain the number of nodes in the area, obtain the power consumption of each node at multiple time points, calculate the average power consumption of the node, and calculate the power consumption standard deviation and power consumption accumulation coefficient of the area based on the average power consumption; The power consumption fluctuation factor is calculated by combining the power consumption standard deviation and the power consumption accumulation coefficient. The expression is: , where is the cumulative coefficient of electricity consumption, is the standard deviation of electricity consumption, is the power fluctuation factor, , is the adjustment coefficient, and , are all greater than 0.

[0010] In a preferred embodiment, the standard deviation of power consumption in a region is calculated based on the average power consumption, and the expression is: , where is the standard deviation of electricity consumption, is the number of nodes, For the The average power consumption of each node is is the average power consumption. The larger the standard deviation of power consumption, the greater the overall power consumption volatility in the region, that is, the lower the information reliability of the region; The cumulative power consumption coefficient of the area is calculated based on the average power consumption. The expression is: , where is the cumulative coefficient of electricity consumption, is the number of nodes, For the The average power consumption of each node is is the time interval of integration, Indicates at time The sum of the average power consumption of all nodes in the area at that time.

[0011] In a preferred embodiment, the processing logic of the power consumption change index is: obtaining the power consumption change rate at multiple time points within the monitoring time period, summing the power consumption change rates at multiple time points to obtain the power consumption change index, and for the current time point, the acquisition logic of the power consumption change rate is: obtaining the power difference by subtracting the power consumption at the previous time point from the power consumption at the current time point, obtaining the interval duration by subtracting the current time point from the previous time point, and obtaining the power consumption change index by dividing the power difference by the interval duration; The industrial output value change index: obtains the industrial output value change rate at multiple time points within the monitoring period, and sums the industrial output value change rates at multiple time points to obtain the industrial output value change index. For the current time point, the logic for obtaining the industrial output value change rate is: obtain the power difference by subtracting the industrial output value at the previous time point from the industrial output value at the current time point, obtain the interval duration by subtracting the current time point from the previous time point, and obtain the industrial output value change index by dividing the power difference by the interval duration.

[0012] A power grid electricity sales management system, comprising a data acquisition module, a prediction module, and a management module; Data acquisition module: obtain the grid coverage area and mark each area to form an initial area list: Prediction module: obtain regional electricity consumption data, conduct spatiotemporal analysis on the electricity consumption data, construct the regional electricity consumption impact index based on the results of regional electricity consumption time series analysis, construct the regional electricity consumption fluctuation factor based on the results of regional electricity consumption spatiotemporal analysis, dynamically obtain the regional predicted electricity consumption by combining the electricity consumption impact index with the electricity consumption fluctuation factor, and sum up the predicted electricity consumption of all regions to obtain the predicted electricity sales of the power grid; Management module: Generate corresponding management strategies based on the power grid's predicted power sales and the relationship between the power grid's storage capacity and electricity prices.

[0013] In a preferred embodiment, after the management module obtains the predicted power sales of the power grid, it manages it according to the comparison relationship between the predicted power sales and the power storage of the power grid. If the predicted power sales are greater than the power storage of the power grid, it is analyzed that the current power storage is insufficient to support the power sales, and power can be transferred from other power grid sub-grids for compensation. If the predicted power sales are less than or equal to the power storage of the power grid, it is analyzed that the current power storage is sufficient to support the power sales; When the analysis shows that the current storage capacity is sufficient to support the electricity sales, the current electricity price is obtained. If the current electricity price is less than the preset price threshold, the excess electricity is stored. If the current electricity price is greater than or equal to the preset price threshold, the excess electricity can be sold to determine whether there is electricity compensation demand in other regions. If not, the excess electricity is stored. If so, the excess electricity is sold to other regions.

[0014] In the above technical solution, the technical effects and advantages provided by the present invention are: The present invention obtains the grid coverage area through the acquisition terminal, and forms an initial area list after marking each area, obtains the regional power consumption data, performs spatiotemporal analysis on the power consumption data, constructs the regional power consumption impact index based on the regional power consumption time series analysis result, constructs the regional power consumption fluctuation factor based on the regional power consumption spatiotemporal analysis result, combines the power consumption impact index with the power consumption fluctuation factor to dynamically obtain the regional predicted power consumption, and sums the predicted power consumption of all areas to obtain the predicted power sales of the grid. The prediction method divides the grid coverage area, performs data analysis on each area separately, and then dynamically obtains the predicted power consumption of the area, and then sums the predicted power consumption of all areas to obtain the predicted power sales of the grid, which is conducive to improving the prediction accuracy and precision of the predicted power sales of the grid.

[0015] The present invention obtains regional power consumption data through a prediction module, performs spatiotemporal analysis on the power consumption data, constructs a regional power consumption impact index based on the results of the regional power consumption time series analysis, constructs a regional power consumption fluctuation factor based on the results of the regional power consumption spatiotemporal analysis, combines the power consumption impact index with the power consumption fluctuation factor to dynamically obtain the regional predicted power consumption, sums the predicted power consumption of all regions to obtain the predicted power sales of the power grid, sends the predicted power sales of the power grid to the management module, and the management module generates a corresponding management strategy based on the predicted power sales of the power grid and the relationship between the power storage capacity and the electricity price. This enables the power grid to be managed based on the predicted power sales, thereby improving the efficiency of power grid power sales management. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0017] Figure 1 The figure is a flow chart of the method of the present invention. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] Example 1: Please refer to Figure 1 As shown, a method for predicting power sales volume of a power grid described in this embodiment includes the following steps: The collection end obtains the grid coverage area and marks each area to form an initial area list. After obtaining the regional electricity consumption data, the electricity consumption data is subjected to spatiotemporal analysis. The regional electricity consumption impact index is constructed based on the regional electricity consumption time series analysis results. The regional electricity consumption fluctuation factor is constructed based on the regional electricity consumption spatiotemporal analysis results. The electricity consumption impact index is combined with the electricity consumption fluctuation factor to dynamically obtain the predicted electricity consumption of the region. The predicted electricity consumption of all regions is summed up to obtain the predicted electricity sales of the power grid.

[0020] This application obtains the grid coverage area through the acquisition terminal, and forms an initial area list after marking each area. After obtaining the regional electricity consumption data, the electricity consumption data is analyzed in time and space, and the regional electricity consumption impact index is constructed based on the regional electricity consumption time series analysis results. The regional electricity consumption fluctuation factor is constructed based on the regional electricity consumption time and space analysis results. The electricity consumption impact index and the electricity consumption fluctuation factor are combined to dynamically obtain the predicted electricity consumption of the region, and the predicted electricity consumption of all areas is summed to obtain the predicted electricity sales of the power grid. This prediction method divides the grid coverage area, analyzes the data of each area separately, and then dynamically obtains the predicted electricity consumption of the area, and then sums the predicted electricity consumption of all areas to obtain the predicted electricity sales of the power grid, which is conducive to improving the prediction accuracy and precision of the predicted electricity sales of the power grid.

[0021] Embodiment 2: The acquisition end obtains the grid coverage area and marks each area to form an initial area list, including the following steps: Grid topology data collection: Obtain regional division and power network structure information from the grid GIS system or dispatch center database.

[0022] Sensor data collection: Collect electricity consumption data through smart meters and substation monitoring devices in the area to determine regional boundaries and nodes.

[0023] External data integration: Obtain matching data on administrative divisions, user distribution, and regional power grid coverage.

[0024] Region name (such as Region A, B, C).

[0025] The coordinate range or boundary information of the region.

[0026] Key facilities in the area (substations, load centers).

[0027] Store information for each region in a unified format, for example: Area name: Area A; Coordinate range: [(x1,y1),(x2,y2),...]; Load center: Substation A1; Electricity consumption type: mainly industrial; According to the coverage of the power grid, the entire network is divided into multiple independent areas, each of which corresponds to a load center or power supply node.

[0028] Marking method: Area Number: Assign a unique number to each area (e.g. A1, B2).

[0029] Feature tagging: Labeling based on regional characteristics.

[0030] Priority marking: Classification based on regional power supply importance, load size and other information (such as core area, secondary area).

[0031] Combine all the area names, boundaries, and markings into a complete list, for example: ; Table 1 The initial region list is saved to a database or distributed storage system for use by subsequent prediction models and scheduling systems.

[0032] After obtaining the regional electricity consumption data, perform spatiotemporal analysis on the electricity consumption data, and construct the regional electricity consumption impact index based on the regional electricity consumption time series analysis results, including the following steps: Historical electricity consumption records: historical data of smart meters, substations or power load monitoring systems in the region.

[0033] Time granularity: data at the day, hour, or minute level.

[0034] Spatial distribution: covers all divided areas.

[0035] Obtain regional electricity consumption data, including electricity consumption change index and industrial output value change index; The electricity consumption change index and the industrial output value change index are normalized, and the value range of the electricity consumption change index and the industrial output value change index is mapped to [0,1]. The normalized electricity consumption change index and the industrial output value change index are summed to obtain the electricity consumption impact index.

[0036] The processing logic of the power consumption change index is: obtain the power consumption change rate at multiple time points within the monitoring period, sum the power consumption change rates at multiple time points to obtain the power consumption change index. For the current time point, the logic for obtaining the power consumption change rate is: obtain the power difference by subtracting the power consumption at the previous time point from the power consumption at the current time point, obtain the interval duration by subtracting the current time point from the previous time point, and obtain the power consumption change index by dividing the power difference by the interval duration. Industrial output value change index: obtain the industrial output value change rate at multiple time points during the monitoring period, and sum the industrial output value change rates at multiple time points to obtain the industrial output value change index. For the current time point, the logic for obtaining the industrial output value change rate is: obtain the power difference by subtracting the industrial output value at the previous time point from the industrial output value at the current time point, obtain the interval duration by subtracting the current time point from the previous time point, and obtain the industrial output value change index by dividing the power difference by the interval duration; 1) Relationship between electricity consumption change index and future regional electricity consumption changes The larger the value of the power consumption change index is, the faster the rate of change of regional power consumption is, and there is a significant increase or decrease in power demand in a short period of time. If the change index is positive and large, it means that regional power consumption is growing rapidly and power consumption may continue to increase in the future. If the change index is negative and has a large absolute value, it means that regional power consumption is decreasing rapidly and there may be a trend of decreasing power consumption in the future.

[0037] The smaller the value of the power consumption change index is, the more stable the regional power consumption is and the power demand fluctuates slightly. In the future, power consumption is likely to remain stable with less fluctuation.

[0038] 2) Relationship between the industrial output value change index and the future regional electricity consumption change The larger the value of the industrial output value change index is, the faster the industrial activities are changing, and the industrial electricity demand may increase or decrease significantly. If the change index is positive and large, it means that the industrial output value is growing rapidly, which may lead to an increase in industrial electricity demand. If the change index is negative and has a large absolute value, it means that the industrial output value is declining rapidly, which may lead to a decrease in industrial electricity demand.

[0039] The smaller the value of the industrial output change index is, the more stable the industrial activities are, and the smaller the impact on the change of electricity demand is. In the future, industrial electricity consumption may remain stable and will not fluctuate significantly.

[0040] The regional electricity consumption fluctuation factor is constructed based on the results of the regional electricity consumption spatiotemporal analysis, including the following steps: Get the number of nodes in the area (each node can be a community, factory, hospital, etc.), get the power consumption of each node at multiple time points, calculate the average power consumption of the node, and calculate the standard deviation of the power consumption of the area based on the average power consumption. The expression is: , where is the standard deviation of electricity consumption, is the number of nodes, For the The average power consumption of each node is is the average power consumption. The larger the standard deviation of power consumption, the greater the overall power consumption volatility in the region, that is, the lower the information reliability of the region; The cumulative power consumption coefficient of the area is calculated based on the average power consumption. The expression is: , where is the cumulative coefficient of electricity consumption, is the number of nodes, For the The average power consumption of each node is is the time interval for integration (for example, from the beginning to the end of the day, or any time period during the week), Indicates at time The sum of the average power consumption of all nodes in the region at time t. The larger the power consumption accumulation coefficient, the greater the cumulative increase in the overall power consumption of the region, that is, the greater the information reliability of the region.

[0041] The power consumption fluctuation factor is calculated by combining the power consumption standard deviation and the power consumption accumulation coefficient. The expression is: , where is the cumulative coefficient of electricity consumption, is the standard deviation of electricity consumption, is the power fluctuation factor, , is the adjustment coefficient, and , are all greater than 0.

[0042] The power consumption impact index and the power consumption fluctuation factor are combined to dynamically obtain the predicted power consumption of the region, including the following steps: The variation coefficient of the region is obtained by multiplying the power consumption impact index by the power consumption fluctuation factor, and the current power consumption of the region is obtained (it can be the power consumption within a week or within 24 hours). The predicted power consumption of the region is obtained by adjusting the current power consumption by the variation coefficient. The expression is: , where To predict electricity consumption, is the current power consumption, is the coefficient of variation, is the change threshold. In the above algorithm, the change threshold is used to analyze whether the power consumption of the area is increasing or decreasing. When the change coefficient is greater than or equal to the change threshold, the power consumption of the analysis area is increasing. When the change coefficient is less than the change threshold, the power consumption of the analysis area is decreasing. After obtaining the predicted electricity consumption of each area, the predicted electricity consumption of all areas is summed up to obtain the predicted electricity sales of the power grid.

[0043] Embodiment 3: A power grid electricity sales management system described in this embodiment includes a data acquisition module, a prediction module, and a management module; Data acquisition module: obtains the grid coverage area and marks each area to form an initial area list, which is sent to the prediction module: Prediction module: obtain regional electricity consumption data, conduct spatiotemporal analysis on the electricity consumption data, construct the regional electricity consumption impact index based on the results of the regional electricity consumption time series analysis, construct the regional electricity consumption fluctuation factor based on the results of the regional electricity consumption spatiotemporal analysis, combine the electricity consumption impact index with the electricity consumption fluctuation factor to dynamically obtain the regional predicted electricity consumption, sum up the predicted electricity consumption of all regions to obtain the predicted electricity sales of the power grid, and send the predicted electricity sales of the power grid to the management module; Management module: Generate corresponding management strategies based on the power grid's predicted power sales and the relationship between the power grid's storage capacity and electricity prices.

[0044] After the management module obtains the predicted power sales of the power grid, it manages it according to the comparison between the predicted power sales and the power storage of the power grid. If the predicted power sales are greater than the power storage of the power grid, it is analyzed that the current power storage is insufficient to support the power sales, and power can be transferred from other power grid sub-grids for compensation. If the predicted power sales are less than or equal to the power storage of the power grid, it is analyzed that the current power storage is sufficient to support the power sales; When the current electricity storage capacity is sufficient to support the electricity sales, the current electricity price is obtained. If the current electricity price is less than the preset price threshold, the excess electricity is stored. If the current electricity price is greater than or equal to the preset price threshold, the excess electricity can be sold to obtain whether there is electricity compensation demand in other regions. If not, the excess electricity is stored. If so, the excess electricity is sold to other regions. It should be noted that in the present application, the current electricity price is obtained. If the current electricity price is less than the preset price threshold, the excess electricity will be stored. If the current electricity price is greater than or equal to the preset price threshold, the excess electricity can be sold after analysis. The analysis is only performed when the electricity is in non-emergency use (such as industrial use, etc.). If other areas are in emergency use (such as emergency use, etc.), the electricity will be directly compensated to other areas.

[0045] This application obtains regional electricity consumption data through a prediction module, performs spatiotemporal analysis on the electricity consumption data, constructs a regional electricity consumption impact index based on the results of the regional electricity consumption time series analysis, constructs a regional electricity consumption fluctuation factor based on the results of the regional electricity consumption spatiotemporal analysis, combines the electricity consumption impact index with the electricity consumption fluctuation factor to dynamically obtain the regional predicted electricity consumption, sums up the predicted electricity consumption of all regions to obtain the predicted power grid sales, and sends the predicted power grid sales to the management module. The management module generates a corresponding management strategy based on the predicted power grid sales and the relationship between the power grid storage and electricity prices. This enables the power grid to be managed based on the predicted power sales, thereby improving the efficiency of power grid sales management.

[0046] In this application, the application scenarios of the power grid sales management system are as follows: Scenario 1: Peak power consumption management in a large urban area Background: A power grid covers multiple large areas in City A (such as Area 1, Area 2, and Area 3), each of which includes residential areas, commercial areas, and industrial parks. Recently, due to high temperatures, the peak of residential electricity consumption and the increase in industrial load have led to a sharp increase in the overall electricity demand in City A. The power grid needs to predict the electricity consumption trends in each major area and formulate a control strategy.

[0047] Data collection module: The system obtains the coverage of large areas 1, 2 and 3, and marks the residential areas, commercial areas and industrial parks within each area. Obtain the electricity consumption data of each area at multiple time points, such as: Area 1: 50% residential areas, 30% commercial areas, and 20% industrial parks. Area 2: 40% residential areas, 40% commercial areas, and 20% industrial parks. Area 3: 30% residential areas, 20% commercial areas, and 50% industrial parks.

[0048] Prediction module: Perform spatiotemporal analysis on the power consumption of each large area, and construct the power consumption impact index and fluctuation factor. Predict the peak power consumption time periods of each large area: the power consumption of area 1 rises rapidly from 6 pm to 10 pm (peak power consumption of residents). The power demand of area 3 increases from 9 am to 4 pm (peak load of industry). Dynamically combine the impact index and fluctuation factor to calculate the predicted power consumption of each large area. Summarize the predicted power consumption of each large area to obtain the overall predicted power sales of the power grid.

[0049] Management module: Analyze the comparison between the predicted power sales and the current power grid storage: If the predicted power sales are greater than the power grid storage, compensate for the power from the neighboring power grid (such as city B). If the predicted power sales are less than the power grid storage, dynamically allocate the storage: store excess power in the time period of the low-peak area (such as area 2). Prioritize power dispatch support in the time period of the peak area (such as area 1 and area 3). The power grid successfully balanced the power demand between large regions, avoided the power shortage caused by insufficient power storage during peak hours, and improved the efficiency of power management.

[0050] Scenario 2: Emergency power allocation across large regions Background: Due to natural disasters, power supply facilities in a large area (area 2) were partially damaged, and commercial areas and industrial parks experienced serious power shortages, requiring emergency power compensation. However, power consumption in other large areas (areas 1 and 3) was relatively stable and there was excess power storage.

[0051] Data collection module: The system obtains the emergency power demand of area 2 and marks it as a priority compensation area, especially the power consumption of the industrial park (accounting for 50% of the power consumption of area 2). At the same time, the power storage situation of area 1 and area 3 is obtained, and it is found that 30% of the power storage in these two areas can be used for allocation.

[0052] Prediction module: Analyze the emergency power demand of area 2, and dynamically adjust the compensation priority based on the high power consumption characteristics of the industrial park. Calculate the power storage release strategy of area 1 and area 3: Prioritize the transmission of power to the industrial park in area 2 without affecting the normal power consumption of its own residential and commercial areas.

[0053] Management module: Dispatch the excess power storage in Region 1 and Region 3 to compensate for the emergency needs of Region 2. Priority is given to meeting the power needs of the industrial park in Region 2, followed by the commercial area. If the power storage is insufficient, the inter-regional electricity price is increased to purchase power from the neighboring power grid (such as City B) for further supplementation. The industrial park in Region 2 obtains the required power support in a timely manner to ensure that production and emergency repair tasks proceed normally in an emergency. The excess power in Regions 1 and 3 is reasonably distributed without affecting their normal power needs.

[0054] Scenario 3: Low-peak electricity price storage and cross-regional electricity sales optimization Background: In a certain city's power grid, the power demand in the industrial park of Region 3 decreased due to the holiday shutdown, and a large amount of power storage was not used. At the same time, the power grids of Region 1 and the neighboring city C predicted that the power demand would increase significantly in the future.

[0055] Data collection module: The system obtains the power storage and current electricity price of the industrial park in area 3. It finds that the current electricity price is lower than the preset threshold (in the off-peak period). It obtains the predicted power consumption of area 1 and finds that the power demand in residential areas will increase rapidly at night. It obtains the predicted data of city C, which shows that there will be a large demand for power consumption in the industrial park the next day.

[0056] Prediction module: Dynamically analyze the power storage and electricity price of region 3 and find that there is no high power demand in the region in the short term. Based on the power demand of region 1 and city C, predict their peak power demand time and compensation demand.

[0057] Management module: During the current off-peak electricity price period, the excess power storage in region 3 is stored. During the peak power consumption period in region 1, part of the power storage is released to meet the power demand of the residential area. During the peak period of the industrial park in city C, the remaining power storage is sold at a higher electricity price to maximize the cross-regional transaction benefits. The power storage in region 3 is reasonably utilized, and the benefits are optimized through cross-regional power sales. The power demand of region 1 and city C is guaranteed, avoiding possible power shortages.

[0058] Based on the above scenario examples, we can see that by adjusting the electricity consumption characteristics of residential areas, commercial areas and industrial parks in large areas, we can achieve: Dynamically predict the electricity demand of each major area and improve the electricity efficiency within the region. Rationally dispatch excess storage power to ensure power supply in emergency situations. Utilize low-peak electricity prices to store electricity and optimize cross-regional electricity sales to maximize the use of grid resources.

[0059] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0060] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0061] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A method for predicting power sales volume of a power grid, characterized by: The prediction method comprises the following steps: The data collection end obtains the grid coverage area and marks each area to form an initial area list; After obtaining the regional electricity consumption data, conduct spatiotemporal analysis on the electricity consumption data, build the regional electricity consumption impact index based on the regional electricity consumption time series analysis results, and build the regional electricity consumption fluctuation factor based on the regional electricity consumption spatiotemporal analysis results; The electricity consumption impact index is combined with the electricity consumption fluctuation factor to dynamically obtain the predicted electricity consumption of the region, and the predicted electricity consumption of all regions is summed up to obtain the predicted electricity sales of the power grid.

2. A method for predicting power sales volume of a power grid according to claim 1, characterized in that: The power consumption impact index of a region is constructed based on the time series analysis results of regional power consumption, including the following steps: Obtain regional electricity consumption data, including electricity consumption change index and industrial output value change index; The electricity consumption change index and the industrial output value change index are normalized, and the value range of the electricity consumption change index and the industrial output value change index is mapped to [0,1]; The normalized electricity consumption change index and industrial output value change index are summed to obtain the electricity consumption impact index.

3. A method for predicting power sales volume of a power grid according to claim 2, characterized in that: The power consumption impact index and the power consumption fluctuation factor are combined to dynamically obtain the predicted power consumption of the region, including the following steps: The variation coefficient of the region is obtained by multiplying the power consumption fluctuation factor by the power consumption impact index, and the current power consumption of the region is obtained. The predicted power consumption of the region is obtained by adjusting the current power consumption by the variation coefficient. The expression is: , where To predict electricity consumption, is the current power consumption, is the coefficient of variation, is the change threshold; After obtaining the predicted electricity consumption of each area, the predicted electricity consumption of all areas is summed up to obtain the predicted electricity sales of the power grid.

4. A method for predicting power sales volume of a power grid according to claim 3, characterized in that: The regional electricity consumption fluctuation factor is constructed based on the results of the regional electricity consumption spatiotemporal analysis, including the following steps: Obtain the number of nodes in the area, obtain the power consumption of each node at multiple time points, calculate the average power consumption of the node, and calculate the power consumption standard deviation and power consumption accumulation coefficient of the area based on the average power consumption; The power consumption fluctuation factor is calculated by combining the power consumption standard deviation and the power consumption accumulation coefficient. The expression is: , where is the cumulative coefficient of electricity consumption, is the standard deviation of electricity consumption, is the power fluctuation factor, , is the adjustment coefficient, and , are all greater than 0.

5. A method for predicting power sales volume of a power grid according to claim 4, characterized in that: The standard deviation of electricity consumption in a region is calculated based on the average electricity consumption. The expression is: , where is the standard deviation of electricity consumption, is the number of nodes, For the The average power consumption of each node is is the average power consumption. The larger the standard deviation of power consumption, the greater the overall power consumption volatility in the region, that is, the lower the information reliability of the region; The cumulative power consumption coefficient of the area is calculated based on the average power consumption. The expression is: , where is the cumulative coefficient of electricity consumption, is the number of nodes, For the The average power consumption of each node is is the time interval of integration, Indicates at time The sum of the average power consumption of all nodes in the area at that time.

6. A method for predicting power sales volume of a power grid according to claim 5, characterized in that: The processing logic of the power consumption change index is: obtain the power consumption change rate at multiple time points within the monitoring time period, sum the power consumption change rates at multiple time points to obtain the power consumption change index, and for the current time point, the acquisition logic of the power consumption change rate is: obtain the power difference by subtracting the power consumption at the previous time point from the power consumption at the current time point, obtain the interval duration by subtracting the current time point from the previous time point, and obtain the power consumption change index by dividing the power difference by the interval duration; The industrial output value change index: obtains the industrial output value change rate at multiple time points within the monitoring period, and sums the industrial output value change rates at multiple time points to obtain the industrial output value change index. For the current time point, the logic for obtaining the industrial output value change rate is: obtain the power difference by subtracting the industrial output value at the previous time point from the industrial output value at the current time point, obtain the interval duration by subtracting the current time point from the previous time point, and obtain the industrial output value change index by dividing the power difference by the interval duration.

7. A power grid electricity sales management system, implemented based on the prediction method according to any one of claims 1 to 6, characterized in that: Including data collection module, prediction module and management module; Data acquisition module: obtain the grid coverage area and mark each area to form an initial area list: Prediction module: obtain regional electricity consumption data, conduct spatiotemporal analysis on the electricity consumption data, construct the regional electricity consumption impact index based on the results of regional electricity consumption time series analysis, construct the regional electricity consumption fluctuation factor based on the results of regional electricity consumption spatiotemporal analysis, dynamically obtain the regional predicted electricity consumption by combining the electricity consumption impact index with the electricity consumption fluctuation factor, and sum up the predicted electricity consumption of all regions to obtain the predicted electricity sales of the power grid; Management module: Generate corresponding management strategies based on the power grid's predicted power sales and the relationship between the power grid's storage capacity and electricity prices.

8. A power grid electricity sales management system according to claim 7, characterized in that: After the management module obtains the predicted power sales of the power grid, it manages it according to the comparison relationship between the predicted power sales and the power storage of the power grid. If the predicted power sales are greater than the power storage of the power grid, it is analyzed that the current power storage is insufficient to support the power sales, and power can be transferred from other power grid sub-grids for compensation. If the predicted power sales are less than or equal to the power storage of the power grid, it is analyzed that the current power storage is sufficient to support the power sales; When the analysis shows that the current storage capacity is sufficient to support the electricity sales, the current electricity price is obtained. If the current electricity price is less than the preset price threshold, the excess electricity is stored. If the current electricity price is greater than or equal to the preset price threshold, the excess electricity can be sold to determine whether there is electricity compensation demand in other regions. If not, the excess electricity is stored. If so, the excess electricity is sold to other regions.

Images