A method for load forecasting and adjustment of distribution network

Abstract

The present invention discloses a method for load forecasting and adjustment of a distribution network, which relates to the technical field of load forecasting of distribution networks. The method comprises the following steps: based on the management areas of different distribution networks in a city, the usage types of the distribution network are divided into residential, commercial, industrial, and mixed types, a city distribution network database is established, and distribution network archives are established based on the types; daily load data of different distribution networks in different historical months are collected, hourly predicted peak loads of different regions are calculated based on temperature intervals, and predicted surplus loads and predicted deficit loads are obtained in combination with the planned loads of different distribution networks, and surplus load time intervals and deficit load time intervals of different regions in different months are divided. The present invention predicts the load of the distribution network in combination with the characteristics of the management area of ​​the distribution network, and performs profit and loss management pairing on the distribution network in combination with the predicted load, thereby enhancing practicality and functionality.

Description

Technical Field

[0001] The present invention relates to the technical field of distribution network load forecasting, and in particular to a distribution network load forecasting and adjustment method. Background Art

[0002] The power supply load of a distribution network refers to the load it bears for supplying power to the outside world in its region. It is necessary to ensure that the power supply load is greater than the power consumption load at any given time to meet the power supply needs of the region. Therefore, it is necessary to predict the power consumption load in the area under the distribution network's responsibility to ensure the stable operation of the distribution network.

[0003] A Chinese patent with publication number "CN114819280A" discloses "a distribution network load forecasting method, belonging to the field of power load forecasting technology, the specific steps of the forecasting method are as follows: step one: obtaining historical power data; step two: determining load influencing factors and selecting similar days; step three: determining electric vehicle load data; step four: extracting training sets; step five: constructing a regional short-term load forecasting model; step six: load forecasting;" Although it can predict the distribution network load through the short-term load forecasting model, the regional composition of different distribution networks in actual situations is different. Under different regional compositions, the fluctuation of the distribution network load also varies under the influence of different temperatures. The existing load forecast cannot perform detailed analysis and prediction for the area under the jurisdiction of the distribution network, and cannot perform load transfer and pairing management based on the load profit and loss of different regions. There are problems of low practicality and functionality.

[0004] Currently, no effective solutions have been proposed for the problems in related technologies. Summary of the Invention

[0005] In response to the problems in the related art, the present invention proposes a distribution network load forecasting and adjustment method to overcome the above technical problems existing in the existing related art.

[0006] To this end, the specific technical solutions adopted in the present invention are as follows:

[0007] A method for load forecasting and adjustment of a distribution network, the method comprising the following steps:

[0008] S1. Based on the management areas of different urban distribution networks, the types of distribution network usage are divided into residential, commercial, industrial, and mixed types. An urban distribution network database is established, and distribution network files are created based on the types.

[0009] S2. Collect daily load data for different distribution networks in different months. Calculate hourly predicted peak loads for different regions based on temperature ranges. Combined with the planned loads of different distribution networks, obtain predicted surplus loads and predicted deficit loads. Identify surplus load time intervals and deficit load time intervals for different regions in different months.

[0010] S3. Based on the daily surplus load range, predicted surplus load, deficit load range, and predicted deficit load in different regions and months, daily forecast matching is performed on the distribution network files in different months, and comprehensive adjustments are made to the distribution network load.

[0011] As a preferred embodiment, the S1 includes the following sub-steps:

[0012] S11. Based on the management areas of each distribution network under the city in the GIS map, obtain the proportion of residential areas in different distribution network management areas , the proportion of commercial area , industrial zone area ratio , based on the area proportion of different distribution network management areas, the distribution network types are divided into the following steps:

[0013] When the proportion of residential area in the distribution network management area ≥70%, it means that the current distribution network type is residential;

[0014] When the commercial area accounts for the proportion of the distribution network management area ≥60%, it means that the current distribution network type is commercial;

[0015] When the industrial area in the distribution network management area accounts for ≥50%, it means the current distribution network type is industrial;

[0016] When the proportion of residential area, commercial area and industrial area in the distribution network management area does not meet the above ratios, it means that the current distribution network type is mixed;

[0017] S12. Establish the urban distribution network database of the current city through MySQL, and establish type groups in the database, including residential, commercial, industrial, and mixed types. Based on the types of each distribution network under the city, establish distribution network files under the corresponding groups, and number the distribution networks in the files in sequence. The distribution network files include the geographical location, planned load, and name of the distribution network.

[0018] As a preferred embodiment, the S2 includes the following sub-steps:

[0019] S21. Collect the daily and hourly load peak values ​​of different distribution networks in historical months, and collect the daily and hourly temperature values ​​in historical months. Based on different distribution network grouping types, group the working days and weekends in the same month based on the temperature range;

[0020] S22. Calculate the hourly peak load based on the temperature range grouping. Combined with the current meteorological data of the distribution network, obtain the predicted peak load of the distribution network at each moment of the day. Combined with the planned loads of different distribution networks, calculate the predicted surplus load and predicted deficit load, and divide the surplus load time interval and the deficit load time interval.

[0021] As a preferred embodiment, the S21 includes the following sub-steps:

[0022] S211. Collect temperature data for the same month in the past two years and obtain the temperature value for each hour in the current month. , and distinguish between working days and weekends, where n and N represent the month and the day of the month respectively, and P represents the time;

[0023] S222: Based on different distribution network grouping types, group working days and weekends in the same month based on temperature ranges. The specific steps are as follows:

[0024] For residential areas, a range of 3°C is used to capture the subtle changes in residential loads under different temperature conditions, including , i represents the highest temperature point, based on the temperature values ​​of the residential distribution network at different times in the current month , the distribution network load peak data at the same time every day in the same month are summarized into the same temperature range according to the temperature value, and the data file of the current time is established. The file includes all temperature ranges at this time in the current month and the summarized distribution network load peak data in each temperature range. At the same time, weekdays and weekends are grouped separately;

[0025] For commercial areas, a range of 6°C is used to capture the changes in commercial area loads under different temperature conditions, including , i represents the highest temperature point, based on the temperature values ​​at different times of the current month in the commercial distribution network , the distribution network load peak data at the same time every day in the same month are summarized into the same temperature range according to the temperature value, and the data file of the current time is established. The file includes all temperature ranges at this time in the current month and the summarized distribution network load peak data in each temperature range. At the same time, weekdays and weekends are grouped separately;

[0026] For industrial type, a range of 10°C is used to capture the overall change trend of industrial load, including , i represents the highest temperature point, based on the temperature values ​​at different times of the current month in the industrial distribution network , the distribution network load peak data at the same time every day in the same month are summarized into the same temperature range according to the temperature value, and the data file of the current time is established. The file includes all temperature ranges at this time in the current month and the summarized distribution network load peak data in each temperature range. At the same time, weekdays and weekends are grouped separately;

[0027] For mixed type, a temperature interval of 7°C is used to capture the overall change trend of the mixed zone load, including , i represents the highest temperature point, based on the temperature values ​​at different times in the current month of the hybrid distribution network , the distribution network load peak data at the same time every day in the same month are summarized in the same temperature range according to the temperature value, and a data file for the current moment is established. The file includes all temperature ranges at this moment in the current month and the summarized distribution network load peak data in each temperature range. At the same time, weekdays and weekends are grouped separately.

[0028] As a preferred embodiment, the S22 includes the following sub-steps:

[0029] S221. Combined with the data archive, for the same distribution network in the same month and on working days and weekends, take the extreme values ​​of the distribution network load peak data in all temperature ranges at the same time, and obtain representative loads of different temperature ranges at the same time. The specific algorithm formula is:

[0030] ;

[0031] in, represents the nth distribution network load peak data in the i-th temperature interval at the same time, Represents the representative load of the i-th temperature interval at time Q, and calculates the representative load of weekdays and the representative load of weekends respectively;

[0032] S222: Based on meteorological information, obtain the predicted temperature of the current distribution network at each moment of the day. For weekdays and weekends, match the predicted temperature to the temperature range in the data file at the same moment, and select the corresponding representative load as the predicted peak load at the current moment. , Q is the time, and its value range is 0-23;

[0033] S223, based on the planned load of the current distribution network , calculate the difference load at each moment of the current forecast day , and its algorithm formula is:

[0034] ;

[0035] The differential load at each moment Make a judgment to determine the type of the current differential load. The specific steps are as follows:

[0036] when When ≥0, the current differential load is the predicted surplus load, which is recorded as ;

[0037] when When <0, the current differential load is the predicted deficit load, which is recorded as ;

[0038] Based on the predicted surplus load and predicted deficit load at different times of the day, the surplus load time interval and the deficit load time interval are divided. The time period corresponding to the predicted surplus load is summarized into the surplus load time interval of the day, and the time period corresponding to the predicted deficit load is summarized into the deficit load time interval of the day.

[0039] As a preferred embodiment, the S3 includes the following sub-steps:

[0040] S31. Based on the meteorological forecast information, obtain the predicted surplus load or predicted deficit load at different times of day in different months, perform time matching analysis on different regions, and obtain a time matching combination;

[0041] S32. Based on the combination results of the time matching analysis, load matching analysis is performed on different distribution networks, and one-to-one or one-to-many combinations are performed on different distribution network areas to generate a distribution network load matching strategy.

[0042] As a preferred embodiment, the S31 includes the following sub-steps:

[0043] S311. Obtain a surplus load set based on the daily predicted surplus load or predicted deficit load of different distribution stations. or deficit load collection ,in represents the moment of load surplus or load deficit, Represents the surplus load time period of the distribution network numbered n on that day, Represents the current day's deficit load period for the distribution network numbered n;

[0044] S312. For any two distribution networks i and j, , when satisfied When , it represents the surplus and deficit time matching of distribution networks i and j. Record the combination separately and exclude all i that meet the above from the distribution network number. For the excluded distribution networks 1 to m and j, calculate the combined matching situation:

[0045] When satisfied When , after recording the combination, exclude the 1 to m that meet the above conditions from the distribution network number, and repeat the above until there is no combination;

[0046] Repeat the above steps until all matching combinations for the power distribution network deficit time periods are obtained.

[0047] As a preferred embodiment, the S32 includes the following steps:

[0048] S321, calculate the corresponding time for each combination after pairing When all the absolute value differences in the set are greater than or equal to 0, it means that the load pairing result is met. When there are multiple sets of matching results, the absolute value differences in each combination are accumulated and sorted in ascending order. The first combination is selected as the pairing combination with the current distribution network deficit, and all subsequent combination schemes containing the surplus distribution network number in the current pairing combination are deleted;

[0049] S322, for the remaining distribution networks that meet the time matching but do not meet the load matching, the surplus combinations in the time matching scheme are accumulated and combined, and the accumulated surplus combinations at the corresponding moment are calculated. When all the absolute value differences in the set are greater than or equal to 0, it means that the load pairing result is met. When there are multiple sets of matching results, the absolute value differences in each new combination are accumulated and sorted in ascending order. The first new combination is selected as the pairing combination for the current distribution network deficit, and all subsequent combination schemes containing the surplus distribution network numbers in the current new pairing combination are deleted. If all the absolute value differences in the set are still not greater than or equal to 0 after re-combination, the current distribution network is marked red in the urban distribution network database;

[0050] S323. After all the distribution networks under the jurisdiction of the urban distribution network database have been paired, the paired distribution networks are associated and a separate file is created to summarize the load profit and loss complementation. At the same time, all the red-marked distribution networks are summarized into the same file.

[0051] S324: Repeat the above operation to perform daily pairing based on daily weather information.

[0052] The beneficial effects of the present invention are:

[0053] The present invention sets different temperature interval division strategies for different types of distribution networks under its jurisdiction, combines the load fluctuation characteristics of residential, industrial, commercial, and mixed areas, captures the sensitivity of loads in different areas to temperature changes, and makes precise predictions of distribution network loads. The obtained data is processed by taking extreme values, effectively avoiding deviations in prediction results caused by short-term load fluctuations, making the prediction results more stable and reliable, and enhancing the practicality of the method.

[0054] The present invention combines the meteorological data of the current forecast day to obtain the temperature value at each moment of the day, and separately matches each moment with the temperature interval divided by historical data, thereby obtaining the predicted peak load at each moment. By calculating the difference between the planned load and the predicted peak load, it can be determined whether the current distribution network needs to adjust the load at the current moment, which helps to formulate more precise and dynamic load scheduling strategies to balance supply and demand and ensure the stable operation of the power grid.

[0055] By performing time matching and load matching on the surplus and deficit time periods of different distribution networks, the present invention can determine a distribution network with complementary loads, transfer the surplus load to meet the deficit load, effectively balance the power supply and demand relationship between different regions, avoid the waste of power resources, improve the utilization efficiency of power resources, and facilitate the management and adjustment of the distribution network under the jurisdiction of the city;

[0056] The present invention accumulates the absolute value differences and arranges them in ascending order when there are multiple groups of matching results, and selects the first combination. This can give priority to the combination that is most suitable for load matching, ensuring that the combination with the smallest total difference is selected under the premise of satisfying load matching, thereby achieving efficient allocation of power resources, and summarizing the red-marked distribution networks into the same file, making it easier to focus on and process those distribution networks that cannot achieve effective load matching on the same day, providing data support for subsequent grid transformation, load adjustment and other measures, and enhancing practicality and functionality. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0058] Figure 1 The present invention is a flow chart of a method for load forecasting and adjustment in a distribution network according to an embodiment of the present invention. DETAILED DESCRIPTION

[0059] To further illustrate each embodiment, the present invention provides drawings, which are part of the disclosure of the present invention. They are mainly used to illustrate the embodiments and can be used in conjunction with the relevant descriptions in the specification to explain the operating principles of the embodiments. By referring to these contents, ordinary technicians in this field should be able to understand other possible implementation methods and advantages of the present invention. The components in the figures are not drawn to scale, and similar component symbols are generally used to represent similar components.

[0060] According to an embodiment of the present invention, a method for predicting and adjusting load in a distribution network is provided.

[0061] The present invention will now be further described with reference to the accompanying drawings and specific embodiments:

[0062] Example 1: Figure 1 As shown, a distribution network load forecasting and adjustment method according to an embodiment of the present invention includes the following steps:

[0063] S1. Based on the management areas of different urban distribution networks, the types of distribution network usage are divided into residential, commercial, industrial, and mixed types. An urban distribution network database is established, and distribution network files are created based on the types.

[0064] S11. Based on the management areas of each distribution network under the city in the GIS map, obtain the proportion of residential areas in different distribution network management areas , the proportion of commercial area , industrial zone area ratio , based on the area proportion of different distribution network management areas, the distribution network types are divided into the following steps:

[0065] When the proportion of residential area in the distribution network management area ≥70%, it means that the current distribution network type is residential;

[0066] When the commercial area accounts for the proportion of the distribution network management area ≥60%, it means that the current distribution network type is commercial;

[0067] When the industrial area in the distribution network management area accounts for ≥50%, it means the current distribution network type is industrial;

[0068] When the proportion of residential area, commercial area and industrial area in the distribution network management area does not meet the above ratios, it means that the current distribution network type is mixed;

[0069] S12. Establish the urban distribution network database of the current city through MySQL, and establish type groups in the database, including residential, commercial, industrial, and mixed types. Based on the types of each distribution network under the city, establish distribution network files under the corresponding groups, and number the distribution networks in the files in sequence. The distribution network files include the geographical location, planned load, and name of the distribution network.

[0070] It should be noted that the numbering format of the distribution network takes the residential type as an example, which is JM-001, JM-002, ..., JM-00N, where N is the total number of distribution networks under the current residential type grouping. By dividing the types of distribution networks, data support can be provided for temperature range division in subsequent load forecasts. The planned load is the maximum load set during the design of the current distribution network.

[0071] S2. Collect daily load data for different distribution networks in different months. Calculate hourly predicted peak loads for different regions based on temperature ranges. Combined with the planned loads of different distribution networks, obtain predicted surplus loads and predicted deficit loads. Identify surplus load time intervals and deficit load time intervals for different regions in different months.

[0072] S21. Collect the daily and hourly load peak values ​​of different distribution networks in historical months, and collect the daily and hourly temperature values ​​in historical months. Based on different distribution network grouping types, group the working days and weekends in the same month based on the temperature range;

[0073] S211. Collect temperature data for the same month in the past two years and obtain the temperature value for each hour in the current month. , and distinguish between working days and weekends, where n and N represent the month and the day of the month respectively, and P represents the time;

[0074] S222: Based on different distribution network grouping types, group working days and weekends in the same month based on temperature ranges. The specific steps are as follows:

[0075] For residential areas, a range of 3°C is used to capture the subtle changes in residential loads under different temperature conditions, including , i represents the highest temperature point, based on the temperature values ​​of the residential distribution network at different times in the current month , the distribution network load peak data at the same time every day in the same month are summarized into the same temperature range according to the temperature value, and the data file of the current time is established. The file includes all temperature ranges at this time in the current month and the summarized distribution network load peak data in each temperature range. At the same time, weekdays and weekends are grouped separately;

[0076] For commercial areas, a range of 6°C is used to capture the changes in commercial area loads under different temperature conditions, including , i represents the highest temperature point, based on the temperature values ​​at different times of the current month in the commercial distribution network , the distribution network load peak data at the same time every day in the same month are summarized into the same temperature range according to the temperature value, and the data file of the current time is established. The file includes all temperature ranges at this time in the current month and the summarized distribution network load peak data in each temperature range. At the same time, weekdays and weekends are grouped separately;

[0077] For industrial type, a range of 10°C is used to capture the overall change trend of industrial load, including , i represents the highest temperature point, based on the temperature values ​​at different times of the current month in the industrial distribution network , the distribution network load peak data at the same time every day in the same month are summarized into the same temperature range according to the temperature value, and the data file of the current time is established. The file includes all temperature ranges at this time in the current month and the summarized distribution network load peak data in each temperature range. At the same time, weekdays and weekends are grouped separately;

[0078] For mixed type, a temperature interval of 7°C is used to capture the overall change trend of the mixed zone load, including , i represents the highest temperature point, based on the temperature values ​​at different times in the current month of the hybrid distribution network , the distribution network load peak data at the same time every day in the same month are summarized in the same temperature range according to the temperature value, and a data file for the current moment is established. The file includes all temperature ranges at this moment in the current month and the summarized distribution network load peak data in each temperature range. At the same time, weekdays and weekends are grouped separately.

[0079] It should be noted that i represents the highest temperature point. The specific settings can be flexibly set according to the monthly climate in different regions. Residential loads are mainly composed of household electricity consumption, with obvious peaks in the morning and evening, and large seasonal load fluctuations. A finer temperature range is used to capture subtle changes in residential loads under different temperature conditions. Commercial loads are mainly composed of office and commercial activities, with peaks during the day and troughs at night, and small seasonal load fluctuations. A medium-width temperature range is used to capture changes in commercial loads under different temperature conditions. Industrial loads are mainly composed of production equipment, which are usually relatively stable and have no obvious peak hours. Seasonal load fluctuations are small. A wider temperature range is used to capture the overall change trend of industrial loads. Mixed loads are composed of multiple types, including residential houses, commercial facilities, and industrial production equipment. The load curve is more complex. A temperature range between commercial and industrial types is selected, and a distinction is made between weekdays and weekends to improve the representativeness and accuracy of subsequent load forecasts.

[0080] S22. Calculate the hourly peak load based on the temperature range grouping. Combined with the current meteorological data of the distribution network, obtain the predicted peak load of the distribution network at each moment of the day. Combined with the planned loads of different distribution networks, calculate the predicted surplus load and predicted deficit load, and divide the surplus load time interval and the deficit load time interval;

[0081] S221. Combined with the data archive, for the same distribution network in the same month and on working days and weekends, take the extreme values ​​of the distribution network load peak data in all temperature ranges at the same time, and obtain representative loads of different temperature ranges at the same time. The specific algorithm formula is:

[0082] ;

[0083] in, represents the nth distribution network load peak data in the i-th temperature interval at the same time, Represents the representative load of the i-th temperature interval at time Q, and calculates the representative load of weekdays and the representative load of weekends respectively;

[0084] It should be noted that the sources of the distribution network load peak data on weekdays and weekends are weekdays and weekends respectively. By separately calculating the representative load at each moment on weekdays and weekends, the accuracy of subsequent predicted loads can be improved. By taking the maximum value, load fluctuations can be prevented from affecting subsequent distribution network pairing.

[0085] S222: Based on meteorological information, obtain the predicted temperature of the current distribution network at each moment of the day. For weekdays and weekends, match the predicted temperature to the temperature range in the data file at the same moment, and select the corresponding representative load as the predicted peak load at the current moment. , Q is the time, and its value range is 0-23;

[0086] S223, based on the planned load of the current distribution network , calculate the difference load at each moment of the current forecast day , and its algorithm formula is:

[0087] ;

[0088] The differential load at each moment Make a judgment to determine the type of the current differential load. The specific steps are as follows:

[0089] when When ≥0, the current differential load is the predicted surplus load, which is recorded as ;

[0090] when When <0, the current differential load is the predicted deficit load, which is recorded as ;

[0091] Based on the predicted surplus load and predicted deficit load at different times of the day, the surplus load time interval and the deficit load time interval are divided. The time period corresponding to the predicted surplus load is summarized into the surplus load time interval of the day, and the time period corresponding to the predicted deficit load is summarized into the deficit load time interval of the day.

[0092] It should be noted that by combining the meteorological data of the current forecast day, the temperature value at each moment of the day is obtained, and each moment is matched separately in combination with the divided temperature intervals, so as to obtain the predicted peak load at each moment. By calculating the difference between the planned load and the predicted peak load, it can be determined whether the current distribution network needs to adjust the load at the current moment.

[0093] Example 2: S3, based on the daily surplus load interval, predicted surplus load, deficit load interval, and predicted deficit load of different regions in different months, daily forecast matching is performed on the distribution network files in different months, and comprehensive adjustment of the distribution network load is performed;

[0094] S31. Based on the meteorological forecast information, obtain the predicted surplus load or predicted deficit load at different times of day in different months, perform time matching analysis on different regions, and obtain a time matching combination;

[0095] S311. Obtain a surplus load set based on the daily predicted surplus load or predicted deficit load of different distribution stations. or deficit load collection ,in represents the moment of load surplus or load deficit, Represents the surplus load time period of the distribution network numbered n on that day, Represents the current day's deficit load period for the distribution network numbered n;

[0096] S312. For any two distribution networks i and j, , when satisfied When , it represents the surplus and deficit time matching of distribution networks i and j. Record the combination separately and exclude all i that meet the above from the distribution network number. For the excluded distribution networks 1 to m and j, calculate the combined matching situation:

[0097] When satisfied When , after recording the combination, exclude the 1 to m that meet the above conditions from the distribution network number, and repeat the above until there is no combination;

[0098] Repeat the above steps until all matching combinations for the power distribution network deficit time periods are obtained.

[0099] It should be noted that by giving priority to any two distribution networks i and j, To perform pairing, first obtain and eliminate the one-to-one pairing situation, and then obtain the one-to-many pairing situation by combining and eliminating multiple distribution network surpluses and single deficits, which is convenient for subsequent load matching analysis;

[0100] S32. Based on the combined results of the time matching analysis, load matching analysis is performed on different distribution networks, and one-to-one or one-to-many combinations are performed on different distribution network areas to generate a distribution network load matching strategy;

[0101] S321, calculate the corresponding time for each combination after pairing When all the absolute value differences in the set are greater than or equal to 0, it means that the load pairing result is met. When there are multiple sets of matching results, the absolute value differences in each combination are accumulated and sorted in ascending order. The first combination is selected as the pairing combination with the current distribution network deficit, and all subsequent combination schemes containing the surplus distribution network number in the current pairing combination are deleted;

[0102] S322, for the remaining distribution networks that meet the time matching but do not meet the load matching, the surplus combinations in the time matching scheme are accumulated and combined, and the accumulated surplus combinations at the corresponding moment are calculated. When all the absolute value differences in the set are greater than or equal to 0, it means that the load pairing result is met. When there are multiple sets of matching results, the absolute value differences in each new combination are accumulated and sorted in ascending order. The first new combination is selected as the pairing combination for the current distribution network deficit, and all subsequent combination schemes containing the surplus distribution network numbers in the current new pairing combination are deleted. If all the absolute value differences in the set are still not greater than or equal to 0 after re-combination, the current distribution network is marked red in the urban distribution network database;

[0103] It should be noted that when there are multiple groups of matching results, the absolute value differences are accumulated and arranged in ascending order, and the first combination is selected. The most suitable combination in load matching can be selected first to ensure that the combination with the smallest total difference is selected while satisfying the load matching, thereby achieving efficient allocation of power resources.

[0104] S323. After all the distribution networks under the jurisdiction of the urban distribution network database have been paired, the paired distribution networks are associated and a separate file is created to summarize the load profit and loss complementation. At the same time, all the red-marked distribution networks are summarized into the same file.

[0105] S324: Repeat the above operation to perform daily pairing based on daily weather information.

[0106] It should be noted that all red-marked distribution networks are grouped into the same file to facilitate focused attention and processing of those distribution networks that cannot achieve effective load matching on the same day, providing data support for subsequent grid transformation, load adjustment and other measures. Repeating the above operations for daily pairing in combination with daily meteorological information can dynamically adjust the pairing combination of distribution networks according to changes in meteorological conditions.

[0107] In summary, the present invention sets different temperature interval division strategies for the types of distribution networks under its jurisdiction, combines the load fluctuation characteristics of residential, industrial, commercial and mixed areas, captures the sensitivity of loads in different areas to temperature changes, and makes precise predictions of the load of the distribution network. The obtained data is processed by the extreme value method, which effectively avoids the deviation of the prediction results caused by short-term load fluctuations, making the prediction results more stable and reliable. By combining the meteorological data of the current prediction day, the temperature value at each moment of the day is obtained, and the temperature intervals divided by historical data are separately matched at each moment to obtain the predicted peak load at each moment. By calculating the difference between the planned load and the predicted peak load, it can be determined whether the current distribution network needs to adjust the load at the current moment, which is helpful to formulate a more refined and dynamic load scheduling strategy to balance supply and demand and ensure the stable operation of the power grid.

[0108] By performing time matching and load matching for the surplus and deficit time periods of different distribution networks, we can determine a distribution network with complementary loads, transfer the surplus load to meet the deficit load, and effectively balance the power supply and demand relationship between different regions, avoid the waste of power resources, improve the utilization efficiency of power resources, and facilitate the management and adjustment of the distribution network under the jurisdiction of the city.

[0109] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for load forecasting and adjustment of a distribution network, characterized in that: The method comprises the following steps: S1. Based on the management areas of different urban distribution networks, the types of distribution network usage are divided into residential, commercial, industrial, and mixed types. An urban distribution network database is established, and distribution network files are created based on the types. S2. Collect daily load data for different distribution networks in different months. Calculate hourly predicted peak loads for different regions based on temperature ranges. Combined with the planned loads of different distribution networks, obtain predicted surplus loads and predicted deficit loads. Identify surplus load time intervals and deficit load time intervals for different regions in different months. S21. Collect the daily and hourly load peak values ​​of different distribution networks in historical months, and also collect the daily and hourly temperature values ​​in historical months. Based on different distribution network grouping types, group the working days and weekends in the same month based on the temperature range. Set temperature ranges of different widths according to the characteristics of different regions to specifically capture the peak charge under temperature changes in different regions and perform grouping and matching. S211. Collect temperature data for the same month in the past two years and obtain the temperature value for each hour in the current month. , and distinguish between working days and weekends, where n and N represent the month and the day of the month respectively, and P represents the time; S212: Based on different distribution network grouping types, group working days and weekends in the same month based on temperature ranges. The specific steps are as follows: For residential areas, a range of 3°C is used to capture the subtle changes in residential loads under different temperature conditions, including , i represents the highest temperature point, based on the temperature values ​​of the residential distribution network at different times in the current month , the distribution network load peak data at the same time every day in the same month are summarized into the same temperature range according to the temperature value, and the data file of the current time is established. The file includes all temperature ranges at this time in the current month and the summarized distribution network load peak data in each temperature range. At the same time, weekdays and weekends are grouped separately; For commercial areas, a range of 6°C is used to capture the changes in commercial area loads under different temperature conditions, including , i represents the highest temperature point, based on the temperature values ​​at different times of the current month in the commercial distribution network , the distribution network load peak data at the same time every day in the same month are summarized into the same temperature range according to the temperature value, and the data file of the current time is established. The file includes all temperature ranges at this time in the current month and the summarized distribution network load peak data in each temperature range. At the same time, weekdays and weekends are grouped separately; For industrial type, a range of 10°C is used to capture the overall change trend of industrial load, including , i represents the highest temperature point, based on the temperature values ​​at different times of the current month in the industrial distribution network , the distribution network load peak data at the same time every day in the same month are summarized into the same temperature range according to the temperature value, and the data file of the current time is established. The file includes all temperature ranges at this time in the current month and the summarized distribution network load peak data in each temperature range. At the same time, weekdays and weekends are grouped separately; For mixed type, a temperature interval of 7°C is used to capture the overall change trend of the mixed zone load, including , i represents the highest temperature point, based on the temperature values ​​at different times in the current month of the hybrid distribution network , the distribution network load peak data at the same time every day in the same month are summarized into the same temperature range according to the temperature value, and the data file of the current time is established. The file includes all temperature ranges at this time in the current month and the summarized distribution network load peak data in each temperature range. At the same time, weekdays and weekends are grouped separately; It should be noted that i represents the highest temperature point. The specific settings can be flexibly set according to the monthly climate in different regions. Residential loads are mainly composed of household electricity consumption, with obvious peaks in the morning and evening, and large seasonal load fluctuations. A finer temperature range is used to capture subtle changes in residential loads under different temperature conditions. Commercial loads are mainly composed of office and commercial activities, with peaks during the day and troughs at night, and small seasonal load fluctuations. A medium-width temperature range is used to capture changes in commercial loads under different temperature conditions. Industrial loads are mainly composed of production equipment, which are usually relatively stable and have no obvious peak hours. Seasonal load fluctuations are small. A wider temperature range is used to capture the overall change trend of industrial loads. Mixed loads are composed of various types, including residential houses, commercial facilities, and industrial production equipment. The load curve is more complex. A temperature range between commercial and industrial types is selected, and a distinction is made between weekdays and weekends to improve the representativeness and accuracy of subsequent load forecasts. S22. Calculate the hourly peak load based on the temperature range grouping. Combined with the current meteorological data of the distribution network, obtain the predicted peak load of the distribution network at each moment of the day. Combined with the planned loads of different distribution networks, calculate the predicted surplus load and predicted deficit load, and divide the surplus load time interval and the deficit load time interval; S221. Combined with the data archive, for the same distribution network in the same month and on working days and weekends, take the extreme values ​​of the distribution network load peak data in all temperature ranges at the same time, and obtain representative loads of different temperature ranges at the same time. The specific algorithm formula is: ； in, represents the nth distribution network load peak data in the i-th temperature interval at the same time, Represents the representative load of the i-th temperature interval at time Q, and calculates the representative load of weekdays and the representative load of weekends respectively; S222: Based on meteorological information, obtain the predicted temperature of the current distribution network at each moment of the day. For weekdays and weekends, match the predicted temperature to the temperature range in the data file at the same moment, and select the corresponding representative load as the predicted peak load at the current moment. , Q is the time, and its value range is 0-23; S223, based on the planned load of the current distribution network , calculate the difference load at each moment of the current forecast day , and its algorithm formula is: ； The differential load at each moment Make a judgment to determine the type of the current differential load. The specific steps are as follows: when When ≥0, the current differential load is the predicted surplus load, which is recorded as ; when When <0, the current differential load is the predicted deficit load, which is recorded as ; Based on the predicted surplus load and predicted deficit load at different times of the day, the surplus load time interval and the deficit load time interval are divided, and the time period corresponding to the predicted surplus load is summarized into the surplus load time interval of the day, and the time period corresponding to the predicted deficit load is summarized into the deficit load time interval of the day; It should be noted that by combining the meteorological data of the current forecast day, the temperature value at each moment of the day is obtained, and each moment is matched separately in combination with the divided temperature intervals, so as to obtain the predicted peak load at each moment. By calculating the difference between the planned load and the predicted peak load, it can be determined whether the current distribution network needs to adjust the load at the current moment; S3. Based on the daily surplus load intervals, predicted surplus loads, deficit load intervals, and predicted deficit loads of different regions in different months, daily forecast matching is performed on the distribution network files in different months, and comprehensive adjustments are made to the distribution network loads. S31. Based on the meteorological forecast information, obtain the predicted surplus load or predicted deficit load at different times of day in different months, perform time matching analysis on different regions, and obtain a time matching combination; S311. Obtain a surplus load set based on the daily predicted surplus load or predicted deficit load of different distribution stations. or deficit load collection ,in represents the moment of load surplus or load deficit, Represents the surplus load time period of the distribution network numbered on that day, Represents the current day's deficit load period for the distribution network numbered n; S312. For any two distribution networks i and j, , when satisfied When , it represents the surplus and deficit time matching of distribution networks i and j. Record the combination separately and exclude all i that meet the above from the distribution network number. For the excluded distribution networks 1 to m and j, calculate the combined matching situation: When satisfied When , after recording the combination, exclude the 1 to m that meet the above conditions from the distribution network number, and repeat the above until there is no combination; Repeat the above steps until all matching combinations of the distribution network deficit time periods are obtained; It should be noted that by giving priority to any two distribution networks i and j, To perform pairing, first obtain and eliminate the one-to-one pairing situation, and then obtain the one-to-many pairing situation by combining and eliminating multiple distribution network surpluses and single deficits, which is convenient for subsequent load matching analysis; S32. Based on the combination results of the time matching analysis, load matching analysis is performed on different distribution networks, and one-to-one or one-to-many combinations are performed on different distribution network areas to generate a distribution network load pairing strategy.

2. A method for load forecasting and adjustment of a distribution network according to claim 1, characterized in that: The S1 comprises the following sub-steps: S11. Based on the management areas of each distribution network under the city in the GIS map, obtain the proportion of residential areas in different distribution network management areas , the proportion of commercial area , industrial zone area ratio , based on the area proportion of different distribution network management areas, the distribution network types are divided into the following steps: When the proportion of residential area in the distribution network management area ≥70%, it means that the current distribution network type is residential; When the commercial area accounts for the proportion of the distribution network management area ≥60%, it means that the current distribution network type is commercial; When the industrial area in the distribution network management area accounts for ≥50%, it means the current distribution network type is industrial; When the proportion of residential area, commercial area and industrial area in the distribution network management area does not meet the above ratios, it means that the current distribution network type is mixed; S12, pass Establish the urban distribution network database of the current city, and establish type groups in the database, including residential, commercial, industrial, and mixed types. Based on the types of each distribution network under the city, establish distribution network files under the corresponding groups, and number the distribution networks in the files in sequence. The distribution network files include the geographical location, planned load, and name of the distribution network.

3. A method for load forecasting and adjustment of a distribution network according to claim 1, characterized in that: The S32 includes the following steps: S321, calculate the corresponding time for each combination after pairing and When all the absolute value differences in the set are greater than or equal to 0, it means that the load pairing result is met. When there are multiple sets of matching results, the absolute value differences in each combination are accumulated and sorted in ascending order. The first combination is selected as the pairing combination with the current distribution network deficit, and all subsequent combination schemes containing the surplus distribution network number in the current pairing combination are deleted; S322, for the remaining distribution networks that meet the time matching but do not meet the load matching, the surplus combinations in the time matching scheme are accumulated and combined, and the accumulated surplus combinations at the corresponding moment are calculated. When all the absolute value differences in the set are greater than or equal to 0, it means that the load pairing result is met. When there are multiple sets of matching results, the absolute value differences in each new combination are accumulated and sorted in ascending order. The first new combination is selected as the pairing combination for the current distribution network deficit, and all subsequent combination schemes containing the surplus distribution network numbers in the current new pairing combination are deleted. If all the absolute value differences in the set are still not greater than or equal to 0 after re-combination, the current distribution network is marked red in the urban distribution network database; S323. After all the distribution networks under the jurisdiction of the urban distribution network database have been paired, the paired distribution networks are associated and a separate file is created to summarize the load profit and loss complementation. At the same time, all the red-marked distribution networks are summarized into the same file. S324: Repeat the above operation to perform daily pairing based on daily weather information.

Images