Region regulation and control deduction method and system based on distribution network area aggregation equivalence

Abstract

The invention provides an area regulation and control deduction method and system based on distribution network area aggregation equivalence. The method comprises the following steps: acquiring current measurement data of a distribution area in a set area; based on the current measurement data, performing deduction prediction by using the trained transformer area power loss calculation model to obtain predicted power loss data of the distribution network transformer area; regulating and controlling the load of the set area by using the predicted power loss data; wherein the transformer area power loss calculation model is obtained by training a long-short term memory network based on historical measurement data and a distribution network transformer area aggregation equivalent model. A transformer area power loss calculation model is modeled in detail, in combination with transformer area internal power loss calculation, future state data prediction can be carried out by adopting a long-short term memory network, regional regulation and control deduction can be met, a large number of distributed power supplies and flexible loads can be simplified, the transformer area internal power loss is considered, and the calculation efficiency is improved. And rapid generation of future state operation time sequence data can be realized.

Description

Technical Field

[0001] This invention belongs to the field of steady-state aggregated equivalent modeling technology of distribution network areas, specifically involving a regional regulation and control simulation method and system based on the aggregated equivalent modeling of distribution network areas. Background Technology

[0002] Due to the characteristics of wind and solar resources and the daily routines of residents, the integration of large-scale distributed power sources and flexible loads into the distribution network has led to increased complexity in regional power grid operation, bidirectional power flow, and diversified control measures. Utilizing regional power grid control simulations to assist in the pre-formulation of control strategies for distributed power sources and flexible loads has become an important means for dispatching agencies to ensure the safe operation of regional power grids and improve dispatch control levels. However, due to the small individual capacity and large quantity of distributed power sources and flexible loads, including large-scale distributed power sources and flexible loads in the scope of regional control simulations will significantly increase the scale of the simulation model, reduce the efficiency of the simulation model solution, and increase the calculation time for control simulations, making it difficult to meet the time requirements for intraday future-state regional control simulations.

[0003] To incorporate large-scale distributed power sources and flexible loads into the scope of regional control simulations and to meet the time requirements for intraday future regional control simulation calculations, there is an urgent need to study steady-state aggregation equivalent modeling techniques for distribution network areas connected to distributed power sources and flexible loads. Currently, a large amount of research has been conducted on equivalent modeling of distribution network areas, such as detailed classical load models and integrated load models, and simplified PQ (Power-Quantity Node, active and reactive power) node equivalent models.

[0004] Existing distribution network area models have problems such as difficulty in detailed modeling, failure to consider losses, and lack of future state data when participating in regional control simulations. They are difficult to meet the requirements of regional control simulations to simplify the processing of a large number of distributed power sources and flexible loads, consider the power loss inside the distribution area, and generate future state runtime sequence data quickly. Summary of the Invention

[0005] To overcome the shortcomings of the prior art, in a first aspect, this invention proposes a regional control simulation method based on the aggregation and equivalence of distribution network areas, comprising:

[0006] Obtain the current measurement data of the distribution radio stations within the designated area;

[0007] Based on the current measurement data, the predicted power loss data of the distribution network area is obtained by using the trained power loss calculation model of the distribution area.

[0008] The load in the designated area is adjusted using the predicted power loss data.

[0009] The power loss calculation model for the distribution transformer area is obtained by training a long short-term memory network based on historical measurement data and the distribution network distribution transformer area aggregation equivalent model.

[0010] Preferably, the training process of the power loss calculation model for the transformer substation includes:

[0011] Based on the historical measurement data of the distribution network area, the historical power equivalent data is obtained by using the distribution network area aggregation equivalent model;

[0012] Based on the historical power equivalent data, the historical power loss data is obtained using the distribution network area aggregated equivalent model;

[0013] Using the historical power equivalent data and the historical power loss data, the Long Short Time Memory Network is trained to obtain the power loss calculation model for the transformer area.

[0014] Preferably, the distribution network area aggregated equivalent model includes: a power equivalent algorithm and an internal power loss algorithm for the aggregated equivalent objects of the distribution network area.

[0015] Preferably, the power equivalence algorithm for the aggregated equivalent objects includes: wind power aggregated equivalent algorithm, photovoltaic aggregated equivalent algorithm, load aggregated equivalent algorithm, energy storage aggregated equivalent algorithm, and reactive power aggregated equivalent algorithm;

[0016] The process for determining the power equivalence algorithm for the aggregated equivalent objects is as follows:

[0017] Aggregate and equalize all distributed wind power within the distribution network area to obtain a wind power aggregation and equalization object; determine the active power data and reactive power data of all distributed wind power within the distribution network area from the historical measurement data; use the active power data and reactive power data of all distributed wind power to perform power aggregation and equalization on the wind power aggregation and equalization object to obtain a wind power aggregation and equalization algorithm.

[0018] Aggregate and equalize all distributed photovoltaics within the distribution network area to obtain a photovoltaic aggregation and equalization object; determine the active power data and reactive power data of all distributed photovoltaics within the distribution network area from the historical measurement data; use the active power data and reactive power data of all distributed photovoltaics to perform power aggregation and equalization on the photovoltaic aggregation and equalization object to obtain a photovoltaic aggregation and equalization algorithm.

[0019] Aggregate and equalize the loads of all users within the distribution network area to obtain a load aggregation and equalization object; determine the active power data and reactive power data of all users within the distribution network area from the historical measurement data; use the active power data and reactive power data of all users to perform power aggregation and equalization on the load aggregation and equalization object to obtain a load aggregation and equalization algorithm.

[0020] Aggregate and equate all household energy storage within the distribution network area to obtain an energy storage aggregation equation object; determine the active power data and reactive power data of all household energy storage within the distribution network area from the historical measurement data; use the active power data and reactive power data of all household energy storage to perform power aggregation equation on the energy storage aggregation equation object to obtain an energy storage aggregation equation algorithm;

[0021] Aggregate and equalize all reactive power compensation devices within the distribution network area to obtain reactive power aggregation and equalization objects; determine the active power data and reactive power data of all reactive power compensation devices within the distribution network area from the historical measurement data; use the active power data and reactive power data of all reactive power compensation devices within the distribution network area to perform power aggregation and equalization on the reactive power aggregation and equalization objects to obtain the reactive power aggregation and equalization algorithm.

[0022] Preferably, the process for determining the internal power loss algorithm of the distribution network area is as follows:

[0023] Aggregate and equalize the aggregated equivalent objects and the grid-connected points within the distribution network area to obtain internal power loss objects; determine the active power data and reactive power data of the grid-connected points in the distribution network area from the historical measurement data; use the active power data and reactive power data of the grid-connected points in the distribution network area, as well as the aggregation and equalization algorithm corresponding to each aggregated equivalent object, to perform power aggregation and equalization on the internal power loss objects to obtain the internal power loss algorithm.

[0024] Preferably, the expression for the internal power loss algorithm is as follows:

[0025]

[0026] In the above formula, sp t For the active power data of the internal power loss object at time t, perform power aggregation and equalization. t np represents the reactive power data of the internal power loss object at time t, which is the equivalent of power aggregation. t For the active power data at grid connection point t, np t For the reactive power data at grid connection point t, wp A,t wp provides the active power data for power aggregation and equivalent values ​​of wind power equivalent aggregation objects at time t. A,t For the reactive power data of the wind power equivalent aggregation object at time t, pp A,t pq represents the active power data of the photovoltaic equivalent aggregation object at time t, which is the power aggregation equivalent. A,t lp represents the reactive power data of the photovoltaic equivalent aggregation object at time t, representing the power aggregation equivalent. A,tlp represents the active power data of the load equalization aggregation object at time t, which is the power aggregation equalization value. A,t For the reactive power data of the load equalization aggregation object at time t, eq A,t For the active power data of the energy storage equivalent aggregation object at time t, eq A,t dp represents the reactive power data of the energy storage equivalent aggregation object at time t, representing the power aggregation equivalent. A,t dq represents the active power data of the reactive power equalization object at time t, which is the power aggregation equalization value. A,t The reactive power data of the reactive power equalization object at time t is used for power aggregation.

[0027] Preferably, the predicted power loss data includes:

[0028] Predicted active power loss data for distributed wind power, distributed photovoltaic power, user loads, household energy storage and reactive power compensation devices within the distribution network area;

[0029] Predicted reactive power loss data for distributed wind power, distributed photovoltaic power, user loads, household energy storage, and reactive power compensation devices within the distribution network area.

[0030] Preferably, before obtaining the predicted power loss data of the distribution network area by performing extrapolation and prediction using the trained distribution area power loss calculation model based on the current measurement data, the method further includes:

[0031] Based on the power inflow power, multiple measurement data in the current measurement data are processed to obtain multiple negative value measurement data;

[0032] The multiple negative value measurement data are sorted according to the same time series to obtain the measurement data sorting result;

[0033] The measurement data sorting results are then subjected to outlier removal or data reconstruction to obtain the final current measurement data.

[0034] Preferably, the step of reconstructing outlier data from the sorted measurement data to obtain the final current measurement data includes:

[0035] For outliers in the sorting results of the measurement data, at least one of the following algorithms—box plot method, interpolation method, and time series prediction method—is used to reconstruct the data and obtain the final current measurement data.

[0036] Secondly, this invention application also proposes a regional control simulation system based on the aggregation and equivalence of distribution network areas, comprising:

[0037] The measurement data acquisition module is used to acquire the current measurement data of the distribution radio stations within a set area;

[0038] The power loss data acquisition module is used to perform extrapolation and prediction based on the current measurement data and the trained distribution area power loss calculation model to obtain the predicted power loss data of the distribution network area; wherein, the distribution area power loss calculation model is obtained by training a long short time memory network based on historical measurement data and the distribution network area aggregated equivalent model.

[0039] The control module is used to control the load of the set area using the predicted power loss data.

[0040] Preferably, the system further includes: a power loss calculation model construction module for transformer substations, used for:

[0041] Based on the historical measurement data of the distribution network area, the historical power equivalent data is obtained by using the distribution network area aggregation equivalent model;

[0042] Based on the historical power equivalent data, the historical power loss data is obtained using the distribution network area aggregated equivalent model;

[0043] Using the historical power equivalent data and the historical power loss data, the Long Short Time Memory Network is trained to obtain the power loss calculation model for the transformer area.

[0044] Preferably, the distribution network area aggregated equivalent model includes: a power equivalent algorithm and an internal power loss algorithm for the aggregated equivalent objects of the distribution network area.

[0045] Preferably, the power equivalence algorithm for the aggregated equivalent objects includes: wind power aggregated equivalent algorithm, photovoltaic aggregated equivalent algorithm, load aggregated equivalent algorithm, energy storage aggregated equivalent algorithm, and reactive power aggregated equivalent algorithm;

[0046] The process for determining the power equivalence algorithm for the aggregated equivalent objects is as follows:

[0047] Aggregate and equalize all distributed wind power within the distribution network area to obtain a wind power aggregation and equalization object; determine the active power data and reactive power data of all distributed wind power within the distribution network area from the historical measurement data; use the active power data and reactive power data of all distributed wind power to perform power aggregation and equalization on the wind power aggregation and equalization object to obtain a wind power aggregation and equalization algorithm.

[0048] Aggregate and equalize all distributed photovoltaics within the distribution network area to obtain a photovoltaic aggregation and equalization object; determine the active power data and reactive power data of all distributed photovoltaics within the distribution network area from the historical measurement data; use the active power data and reactive power data of all distributed photovoltaics to perform power aggregation and equalization on the photovoltaic aggregation and equalization object to obtain a photovoltaic aggregation and equalization algorithm.

[0049] Aggregate and equalize the loads of all users within the distribution network area to obtain a load aggregation and equalization object; determine the active power data and reactive power data of all users within the distribution network area from the historical measurement data; use the active power data and reactive power data of all users to perform power aggregation and equalization on the load aggregation and equalization object to obtain a load aggregation and equalization algorithm.

[0050] Aggregate and equate all household energy storage within the distribution network area to obtain an energy storage aggregation equation object; determine the active power data and reactive power data of all household energy storage within the distribution network area from the historical measurement data; use the active power data and reactive power data of all household energy storage to perform power aggregation equation on the energy storage aggregation equation object to obtain an energy storage aggregation equation algorithm;

[0051] Aggregate and equalize all reactive power compensation devices within the distribution network area to obtain reactive power aggregation and equalization objects; determine the active power data and reactive power data of all reactive power compensation devices within the distribution network area from the historical measurement data; use the active power data and reactive power data of all reactive power compensation devices within the distribution network area to perform power aggregation and equalization on the reactive power aggregation and equalization objects to obtain the reactive power aggregation and equalization algorithm.

[0052] Preferably, the process for determining the internal power loss algorithm of the distribution network area is as follows:

[0053] Aggregate and equalize the aggregated equivalent objects and the grid-connected points within the distribution network area to obtain internal power loss objects; determine the active power data and reactive power data of the grid-connected points in the distribution network area from the historical measurement data; use the active power data and reactive power data of the grid-connected points in the distribution network area, as well as the aggregation and equalization algorithm corresponding to each aggregated equivalent object, to perform power aggregation and equalization on the internal power loss objects to obtain the internal power loss algorithm.

[0054] Preferably, the expression for the internal power loss algorithm is as follows:

[0055]

[0056] In the above formula, sp t For the active power data of the internal power loss object at time t, perform power aggregation and equalization. t np represents the reactive power data of the internal power loss object at time t, which is the equivalent of power aggregation. t For the active power data at grid connection point t, np t For the reactive power data at grid connection point t, wp A,twp provides the active power data for power aggregation and equivalent values ​​of wind power equivalent aggregation objects at time t. A,t For the reactive power data of the wind power equivalent aggregation object at time t, pp A,t pq represents the active power data of the photovoltaic equivalent aggregation object at time t, which is the power aggregation equivalent. A,t lp represents the reactive power data of the photovoltaic equivalent aggregation object at time t, representing the power aggregation equivalent. A,t lp represents the active power data of the load equalization aggregation object at time t, which is the power aggregation equalization value. A,t For the reactive power data of the load equalization aggregation object at time t, eq A,t For the active power data of the energy storage equivalent aggregation object at time t, eq A,t dp represents the reactive power data of the energy storage equivalent aggregation object at time t, representing the power aggregation equivalent. A,t dq represents the active power data of the reactive power equalization object at time t, which is the power aggregation equalization value. A,t The reactive power data of the reactive power equalization object at time t is used for power aggregation.

[0057] Preferably, the predicted power loss data includes:

[0058] Predicted active power loss data for distributed wind power, distributed photovoltaic power, user loads, household energy storage and reactive power compensation devices within the distribution network area;

[0059] Predicted reactive power loss data for distributed wind power, distributed photovoltaic power, user loads, household energy storage, and reactive power compensation devices within the distribution network area.

[0060] Preferably, the system further includes: a current measurement data processing module, comprising:

[0061] The negative value measurement data acquisition submodule is used to process multiple measurement data in the current measurement data with positive and negative values ​​based on the power inflow power to obtain multiple negative value measurement data.

[0062] The measurement data sorting result acquisition submodule is used to sort the multiple negative value measurement data according to the same time series to obtain the measurement data sorting result;

[0063] The data processing submodule is used to remove outliers or reconstruct data from the sorting results of the measurement data to obtain the final current measurement data.

[0064] Preferably, the data processing submodule is used for:

[0065] For outliers in the sorting results of the measurement data, at least one of the following algorithms—box plot method, interpolation method, and time series prediction method—is used to reconstruct the data and obtain the final current measurement data.

[0066] Thirdly, this application also proposes an electronic device, comprising: at least one processor and a memory; wherein the memory and the processor are connected via a bus;

[0067] The memory is used to store one or more programs;

[0068] When the one or more programs are executed by the at least one processor, the method for regional regulation and control based on the aggregation and equalization of distribution network areas is implemented.

[0069] Fourthly, this application also proposes a readable storage medium having an executable program stored thereon, which, when executed, implements the aforementioned method for regional regulation and control simulation based on distribution network area aggregation and equivalence.

[0070] Compared with the closest prior art, the present invention application has the following beneficial effects:

[0071] This invention discloses a regional control simulation method and system based on distribution network substation aggregation and equivalence. The method involves acquiring current measurement data of distribution substations within a designated area; using this current measurement data, performing simulation and prediction based on a trained substation power loss calculation model to obtain predicted power loss data for the distribution network substations; and using this predicted power loss data to regulate the load in the designated area. The substation power loss calculation model is obtained by training a Long Short-Term Memory (LSTM) network based on historical measurement data and a distribution network substation aggregation and equivalence model. By performing detailed modeling of the substation power loss calculation model, combined with substation internal power loss calculation, and employing an LSM network for future data prediction, aggregating a large number of distributed power sources and flexible loads into a distribution network substation aggregation and equivalence model, the method simplifies the processing of a large number of distributed power sources and flexible loads in regional control simulation, considers internal substation power loss, and enables rapid generation of future runtime sequence data. Attached Figure Description

[0072] Figure 1 A flowchart of a regional regulation deduction method based on distribution network area aggregation and equivalent is provided in this invention application;

[0073] Figure 2 This invention application provides an architecture diagram of a distribution network area aggregation equivalent model based on a regional regulation extrapolation method for distribution network area aggregation equivalents.

[0074] Figure 3 This invention application provides an architecture diagram of a regional control and regulation simulation system based on the aggregation and equivalence of distribution network areas;

[0075] Figure 4 This is a schematic diagram of the operation of an electronic device provided in this invention application. Detailed Implementation

[0076] The specific embodiments of this invention will be further described in detail below with reference to the accompanying drawings.

[0077] Example 1:

[0078] like Figure 1 As shown, this invention application proposes a regional regulation and control simulation method based on the aggregation and equivalence of distribution network areas, which may include the following steps:

[0079] Step 1: Obtain the current measurement data of the distribution radio stations within the designated area;

[0080] Step 2: Based on the current measurement data, use the trained distribution area power loss calculation model to perform extrapolation and prediction to obtain the predicted power loss data of the distribution network distribution area; wherein, the distribution area power loss calculation model is obtained by training a long short time memory network based on historical measurement data and the distribution network distribution area aggregated equivalent model.

[0081] Step 3: Use the predicted power loss data to regulate the load in the designated area.

[0082] In step 1 above, the current measurement data is the data collected from the distribution substation within the set area. This data can be the ledger information of distributed wind power, distributed photovoltaic, user load (including electric vehicle charging piles), household energy storage, reactive power compensation devices, busbars, and other equipment within the distribution substation within the set area. The measurement data types for distributed wind power, distributed photovoltaic, user load, household energy storage, and reactive power compensation devices are active and reactive power data, the measurement data type for busbars is voltage amplitude data, and the measurement data type for grid connection points is active and reactive power data.

[0083] Furthermore, in step 2, before performing the extrapolation and prediction based on the current measurement data and the trained power loss calculation model for the distribution network area to obtain the predicted power loss data for the distribution network area, the following steps are also included:

[0084] Step 2.1: Using the power inflow as a reference, process the positive and negative values ​​of multiple measurement data in the current measurement data to obtain multiple negative value measurement data;

[0085] Step 2.2: Sort the multiple negative value measurement data according to the same time series to obtain the measurement data sorting result;

[0086] Step 2.3: Perform outlier removal or data reconstruction on the sorted measurement data to obtain the final current measurement data.

[0087] Further, in step 2.3, the outlier data reconstruction of the sorted measurement data to obtain the final current measurement data includes:

[0088] For outliers in the sorting results of the measurement data, at least one of the following algorithms—box plot method, interpolation method, and time series prediction method—is used to reconstruct the data and obtain the final current measurement data.

[0089] To meet the modeling data requirements of the distribution network area aggregated equivalent model, the measured data acquired on-site needs to be processed sequentially, including positive / negative processing, time alignment, anomaly reconstruction, and loss calculation. Positive / negative processing treats the power flowing into the equipment as positive, processing the measured data to determine its sign, resulting in a negative value. Time alignment involves sorting the negative measured data according to the same time series. Based on the sorting results, anomaly reconstruction is used to remove or reconstruct outliers from the sorted negative measured data; common reconstruction methods include box plotting, interpolation, and time series prediction. Loss calculation refers to using the final current measured data for subsequent calculations of the active and reactive power data of the aggregated equivalent objects within the distribution network area.

[0090] By acquiring and organizing the current measurement data of the distribution network area, we can obtain data such as active power, reactive power, and voltage amplitude of the equipment and grid connection points within the distribution network area in the same time series, as well as active and reactive power loss data within the distribution network area. This can provide a data foundation for the subsequent establishment of the distribution network area aggregated equivalent model, the training of the area power loss calculation model, and the steady-state accuracy assessment.

[0091] Furthermore, to meet the requirements of regulation and control simulation within a designated area (e.g., a county), a simplified model of the distribution network distribution area is established, considering factors such as power loss within the distribution area, and rapid generation of future-state runtime sequence data. This model includes equivalent objects of wind power, photovoltaic power, loads, energy storage, reactive power aggregation connected to the external power grid, as well as internal power loss objects. The structure of the distribution network distribution area aggregation equivalent model is as follows: Figure 2 As shown;

[0092] Furthermore, in step 2, the training process of the power loss calculation model for the transformer area includes the following steps:

[0093] Step a: Based on the historical measurement data of the distribution network area, obtain the historical power equivalent data using the distribution network area aggregation equivalent model;

[0094] Step b: Based on the historical power equivalent data, use the distribution network area aggregated equivalent model to obtain historical power loss data;

[0095] Step c: Using the historical power equivalent data and the historical power loss data, train the Long Short Time Memory network to obtain the power loss calculation model for the transformer area.

[0096] Furthermore, the distribution network area aggregated equivalent model includes: a power equivalent algorithm and an internal power loss algorithm for the aggregated equivalent objects of the distribution network area.

[0097] Compared to the aggregated equivalent model of distribution network areas based on historical measurement data, the key to supporting county-level operational simulations lies in establishing an aggregated equivalent model of distribution network areas applicable to future scenarios, based on real-time measurement data and ultra-short-term forecast data of internal equipment. Due to the inability to directly obtain active and reactive power data at the grid connection points of distribution network areas in the future, the internal power loss object in the model becomes the focus of establishing the aggregated equivalent model of distribution network areas in the future. Furthermore, considering the unclear and inaccurate nature of the internal topology and related parameters of distribution network areas, a Long Short-Term Memory (LSTM) network, suitable for time series modeling, was used to train the power loss calculation model. The input and output settings of the power loss calculation model during training are as follows:

[0098] (1) Input data: The historical measurement data of the distribution network area includes the active and reactive historical measurement data of a large number of distributed power sources and flexible loads such as distributed wind power, distributed photovoltaic, user load (including electric vehicle charging piles), household energy storage, and reactive power compensation devices, as well as the historical voltage amplitude measurement data of each bus.

[0099] (2) Output data: Historical active and reactive power loss data within the transformer area.

[0100] To meet the needs of future county-level operation simulation, the power loss calculation model of the transformer area trained based on LSTM can use a 4-hour time window and a 5-minute time granularity to continuously organize historical operation data and uniformly input it into the LSTM for model training.

[0101] Furthermore, the power equivalence algorithm for the aggregated equivalent objects includes: wind power aggregated equivalent algorithm, photovoltaic aggregated equivalent algorithm, load aggregated equivalent algorithm, energy storage aggregated equivalent algorithm, and reactive power aggregated equivalent algorithm;

[0102] The process for determining the power equivalence algorithm for the aggregated equivalent objects is as follows:

[0103] Aggregate and equalize all distributed wind power within the distribution network area to obtain a wind power aggregation and equalization object; determine the active power data and reactive power data of all distributed wind power within the distribution network area from the historical measurement data; use the active power data and reactive power data of all distributed wind power to perform power aggregation and equalization on the wind power aggregation and equalization object to obtain a wind power aggregation and equalization algorithm.

[0104] Aggregate and equalize all distributed photovoltaics within the distribution network area to obtain a photovoltaic aggregation and equalization object; determine the active power data and reactive power data of all distributed photovoltaics within the distribution network area from the historical measurement data; use the active power data and reactive power data of all distributed photovoltaics to perform power aggregation and equalization on the photovoltaic aggregation and equalization object to obtain a photovoltaic aggregation and equalization algorithm.

[0105] Aggregate and equalize the loads of all users within the distribution network area to obtain a load aggregation and equalization object; determine the active power data and reactive power data of all users within the distribution network area from the historical measurement data; use the active power data and reactive power data of all users to perform power aggregation and equalization on the load aggregation and equalization object to obtain a load aggregation and equalization algorithm.

[0106] Aggregate and equate all household energy storage within the distribution network area to obtain an energy storage aggregation equation object; determine the active power data and reactive power data of all household energy storage within the distribution network area from the historical measurement data; use the active power data and reactive power data of all household energy storage to perform power aggregation equation on the energy storage aggregation equation object to obtain an energy storage aggregation equation algorithm;

[0107] Aggregate and equalize all reactive power compensation devices within the distribution network area to obtain reactive power aggregation and equalization objects; determine the active power data and reactive power data of all reactive power compensation devices within the distribution network area from the historical measurement data; use the active power data and reactive power data of all reactive power compensation devices within the distribution network area to perform power aggregation and equalization on the reactive power aggregation and equalization objects to obtain the reactive power aggregation and equalization algorithm.

[0108] The active and reactive power calculation formulas for each aggregated equivalent object in the above-mentioned distribution network area aggregated equivalent model are as follows:

[0109] (1) Wind power aggregation equivalent object

[0110] The wind power aggregation equivalent object refers to the aggregation equivalent of all distributed wind power within the distribution network area. The wind power aggregation equivalent object is directly connected to the 10kV bus and is processed as a PQ node in the steady-state power flow calculation. Its active and reactive power data are obtained by summing the active and reactive power data of each distributed wind power at the corresponding time points. The specific calculation formula is as follows:

[0111]

[0112] In equation (1), W represents the number of distributed wind power plants within the transformer substation; wp A,t For the active power data of the wind power equivalent aggregation object at time t, wq A,t wp represents the reactive power data of the wind power equivalent aggregation object at time t. i,t The active power data of the i-th distributed wind power unit within the transformer area at time t is given by wq. i,t This represents the reactive power data of the i-th distributed wind power unit within the transformer area at time t.

[0113] (2) Photovoltaic polymer equivalent objects

[0114] The photovoltaic aggregated equivalent object refers to the aggregated equivalent of all distributed photovoltaics within the distribution network area. The photovoltaic aggregated equivalent object is directly connected to the 10kV bus and is processed as a PQ node in the steady-state power flow calculation. Its active and reactive power data are obtained by summing the active and reactive power data of each distributed photovoltaic at the corresponding time points. The specific calculation formula is as follows:

[0115]

[0116] In the formula, P represents the number of distributed photovoltaic units within the transformer substation, and pp A,t pq represents the active power data of the photovoltaic equivalent aggregated object at time t. A,t The reactive power data of the photovoltaic equivalent aggregation object at time t, pp j,t pq represents the active power data of the j-th distributed photovoltaic unit within the transformer area at time t. j,t This represents the reactive power data of the j-th distributed photovoltaic system within the transformer substation at time t.

[0117] (3) Load aggregation equivalent objects

[0118] The load aggregation equivalent object refers to the aggregated equivalent of all user loads within the distribution network area. The load aggregation equivalent object is directly connected to the 10kV bus and is processed as a PQ node in the steady-state power flow calculation. Its active and reactive power data are obtained by summing the active and reactive power data of each user load at corresponding time points. The specific calculation formula is as follows:

[0119]

[0120] In the formula, L represents the number of user loads within the transformer area, and lp A,t lq represents the active power of the load equivalent aggregate at time t. A,t lp represents the reactive power of the load equivalent aggregate at time t. m,t Let lq be the active power of the m-th user load within the transformer area at time t.m,t Let t be the reactive power of the m-th user load within the transformer area at time t.

[0121] (4) Energy storage aggregation equivalent objects

[0122] The energy storage aggregation equivalent object refers to the aggregated equivalent of all household energy storage within the distribution network area. The energy storage aggregation equivalent object is directly connected to the 10kV bus and is processed as a PQ node in the steady-state power flow calculation. Its active and reactive power data are obtained by summing the active and reactive power data of each household energy storage at the corresponding time points. The specific calculation formula is as follows:

[0123]

[0124] In the formula, E represents the number of residential energy storage units within the transformer substation, and ep A,t For the active power of the energy storage equivalent aggregate object at time t, eq A,t ep represents the reactive power of the energy storage equivalent aggregated object at time t. n,t Let eq be the active power of the nth residential energy storage unit within the distribution area at time t. n,t Let t be the reactive power of the nth household energy storage unit within the distribution area at time t.

[0125] (5) Reactive power aggregation equivalent object

[0126] The reactive power aggregation equivalent object refers to the aggregated equivalent of all reactive power compensation devices within the distribution network area. This object is directly connected to the 10kV bus and is processed as a PQ node in steady-state power flow calculations. Its reactive power data is obtained by summing the reactive power data of each reactive power compensation device at corresponding time points. The specific calculation formula is as follows:

[0127]

[0128] In the formula, D represents the number of reactive power compensation devices within the transformer substation, and dp A,t dq represents the active power of the reactive power equivalent aggregation object at time t. A,t dq represents the reactive power of the reactive power equivalent aggregation object at time t. k,t Let t be the reactive power of the k-th reactive power compensation device within the transformer area at time t.

[0129] Furthermore, the process for determining the internal power loss algorithm of the distribution network area is as follows:

[0130] Aggregate and equalize the aggregated equivalent objects and the grid-connected points within the distribution network area to obtain internal power loss objects; determine the active power data and reactive power data of the grid-connected points in the distribution network area from the historical measurement data; use the active power data and reactive power data of the grid-connected points in the distribution network area, as well as the aggregation and equalization algorithm corresponding to each aggregated equivalent object, to perform power aggregation and equalization on the internal power loss objects to obtain the internal power loss algorithm.

[0131] The above-mentioned aggregation and equivalence of the wind power aggregation equivalent object, the photovoltaic aggregation equivalent object, the load aggregation equivalent object, the energy storage aggregation equivalent object, the reactive power aggregation equivalent object, and the grid connection points within the distribution network area are aggregated and equivalenced to obtain an internal power loss object. Based on the historical measurement data, the active power data and reactive power data of the wind power aggregation equivalent object, the photovoltaic aggregation equivalent object, the load aggregation equivalent object, the energy storage aggregation equivalent object, the reactive power aggregation equivalent object, and the grid connection points within the distribution network area are determined. Using the active power data and reactive power data of the wind power aggregation equivalent object, the photovoltaic aggregation equivalent object, the load aggregation equivalent object, the energy storage aggregation equivalent object, the reactive power aggregation equivalent object, and the grid connection points within the distribution network area, power aggregation and equivalence are performed on the internal power loss object to obtain an internal power loss algorithm.

[0132] The aforementioned internal power loss refers to the aggregated equivalent of the power loss transmitted by all equipment and lines within the distribution network area. The internal power loss object is directly connected to the 10kV bus and is processed as a PQ node in the steady-state power flow calculation. Its active and reactive power data are calculated using the power balance principle. It is obtained by subtracting the active and reactive power measurement data and values ​​of the internal equipment at the corresponding time point from the active and reactive power data of the grid connection point of the distribution network area, i.e., the internal active and reactive power loss data. The expression of the internal power loss algorithm is as follows:

[0133]

[0134] In the above formula, sp t For the active power data of the internal power loss object at time t, perform power aggregation and equalization. t np represents the reactive power data of the internal power loss object at time t, which is the equivalent of power aggregation. t Let nq be the active power data at grid connection point t. t For the reactive power data at grid connection point t, wp A,t wq represents the active power data of the wind power equivalent aggregation object at time t, which is used for power aggregation and equivalent data. A,t For the reactive power data of the wind power equivalent aggregation object at time t, pp A,tpq represents the active power data of the photovoltaic equivalent aggregation object at time t, which is the power aggregation equivalent. A,t lp represents the reactive power data of the photovoltaic equivalent aggregation object at time t, representing the power aggregation equivalent. A,t For the active power data of the load equalization aggregation object at time t, lq A,t For the reactive power data of the load equalization aggregation object at time t, ep A,t For the active power data of the energy storage equivalent aggregation object at time t, eq A,t dp represents the reactive power data of the energy storage equivalent aggregation object at time t, representing the power aggregation equivalent. A,t dq represents the active power data of the reactive power equalization object at time t, which is the power aggregation equalization value. a,t The reactive power data of the reactive power equalization object at time t is used for power aggregation.

[0135] The aforementioned internal power loss is based on the active and reactive power data of aggregated equivalent objects, obtained by subtracting the active and reactive power measurement data and values ​​of internal equipment at the corresponding time point from the active and reactive power data of the distribution network area's grid connection point.

[0136] Further, in step 2, the predicted power loss data includes:

[0137] Predicted active power loss data for distributed wind power, distributed photovoltaic power, user loads, household energy storage and reactive power compensation devices within the distribution network area;

[0138] Predicted reactive power loss data for distributed wind power, distributed photovoltaic power, user loads, household energy storage, and reactive power compensation devices within the distribution network area.

[0139] Predicted power loss data is obtained by collecting real-time measurement data from distribution network areas, or by using ultra-short-term forecast data from internal equipment. This data is used to calculate the intraday future loss data of equipment within the distribution network area, including six types of equipment: busbars, distributed wind power, distributed photovoltaic, user loads, residential energy storage, and reactive power compensation devices. Specific loss data and acquisition methods are as follows:

[0140] (1) The daily future loss data of the bus equipment is the bus voltage amplitude time series data, which is obtained by filling all future time points within the day using real-time measured bus amplitude data.

[0141] (2) The intraday future time series data of distributed wind power is the active and reactive power loss data of wind power. The active power loss data is the ultra-short-term active power prediction data, and the reactive power loss data is calculated and obtained based on the active and reactive power coupling characteristics of wind power and real-time control measurement data.

[0142] (3) The intraday future state loss data of distributed photovoltaics consists of photovoltaic active and reactive power loss data. The active power loss data is ultra-short-term active power prediction data, and the reactive power loss data is calculated and obtained based on the active and reactive power coupling characteristics of the inverter and real-time control measurement data.

[0143] (4) The daily future state loss data of user load consists of active and reactive power loss data of load. The active power loss data is the ultra-short-term active power prediction data, and the reactive power loss data is calculated and obtained based on the active and reactive power coupling characteristics of user load and real-time control measurement data.

[0144] (5) The daily future state loss data of household energy storage is the active and reactive power loss data of energy storage. The active power loss data is the daily active power plan data, and the reactive power loss data is calculated and obtained based on the active and reactive coupling characteristics of household energy storage and real-time control measurement data.

[0145] (6) The reactive power compensation device’s intraday future state loss data is reactive power loss data, and the reactive power loss data is intraday reactive power plan data.

[0146] The obtained intraday future state loss data of the distribution network area is used to calculate the active and reactive power loss data of wind power, photovoltaic, load, energy storage and reactive power aggregation equivalent objects in the distribution network area aggregation equivalent model using formulas (1)-(5). The data is then input into the power loss calculation model of the distribution area to obtain the internal power loss algorithm of the internal power loss object, and then obtain the relevant loss data of the intraday future state distribution network area aggregation equivalent model to support the county-level steady-state regulation and control simulation work under the intraday future state.

[0147] The method of this invention, in order to meet the requirements of distribution network equipment participating in county-level steady-state control simulation, builds a distribution network aggregated equivalent model based on historical measurement data of equipment and grid connection points within the distribution network. This model includes equivalent objects such as wind power, photovoltaics, loads, energy storage, reactive power aggregation, and internal power loss objects. It trains an LSTM-based active and reactive power calculation model for the internal power loss objects, inputs real-time measurement data of the distribution network and ultra-short-term predicted power loss data of the internal equipment, and considers the requirements of internal power loss, future time series generation, and internal object participation in control within the distribution network. This obtains intraday future time series data of the distribution network aggregated equivalent model that meets the requirements of county-level steady-state control simulation, supporting dispatchers in carrying out pre-dispatch work for county-level distributed power sources and flexible loads.

[0148] The present invention also has the following effects:

[0149] 1. A distribution network area aggregation equivalent model is proposed. Taking into account the needs of power loss within the distribution network area, future time series generation, and internal object participation in regulation, an aggregation equivalent model of the distribution network area is built, including wind power, photovoltaic, load, energy storage, reactive power aggregation equivalent objects and internal power loss objects. It includes four parts: processing of historical measurement data of distribution network areas, establishment of distribution network area aggregation equivalent model, training of power loss calculation model of distribution area, and calculation of data of distribution network area aggregation equivalent model within the day. It provides a simplified model of distribution network area for the participation of internal equipment of distribution network area in county-level steady-state regulation and control simulation.

[0150] 2. A power loss calculation model for distribution transformer areas was proposed. By organizing historical measurement data of distribution transformer areas, an active and reactive power calculation model for internal power loss objects based on LSTM was trained. This enabled the acquisition of active and reactive power time series data of internal power loss objects in the aggregated equivalent model of distribution transformer areas under intraday future states, providing intraday future state time series data for county-level steady-state control simulation.

[0151] Example 2:

[0152] like Figure 3 As shown, the present invention also provides a regional control simulation system based on distribution network area aggregation and equivalence, comprising:

[0153] The measurement data acquisition module is used to acquire the current measurement data of the distribution radio stations within a set area;

[0154] The power loss data acquisition module is used to perform extrapolation and prediction based on the current measurement data and the trained distribution area power loss calculation model to obtain the predicted power loss data of the distribution network area; wherein, the distribution area power loss calculation model is obtained by training a long short time memory network based on historical measurement data and the distribution network area aggregated equivalent model.

[0155] The control module is used to control the load of the set area using the predicted power loss data.

[0156] Furthermore, the system also includes: a power loss calculation model construction module for transformer substations, used for:

[0157] Based on the historical measurement data of the distribution network area, the historical power equivalent data is obtained by using the distribution network area aggregation equivalent model;

[0158] Based on the historical power equivalent data, the historical power loss data is obtained using the distribution network area aggregated equivalent model;

[0159] Using the historical power equivalent data and the historical power loss data, the Long Short Time Memory Network is trained to obtain the power loss calculation model for the transformer area.

[0160] Furthermore, the distribution network area aggregated equivalent model includes: a power equivalent algorithm and an internal power loss algorithm for the aggregated equivalent objects of the distribution network area.

[0161] Furthermore, the power equivalence algorithm for the aggregated equivalent objects includes: wind power aggregated equivalent algorithm, photovoltaic aggregated equivalent algorithm, load aggregated equivalent algorithm, energy storage aggregated equivalent algorithm, and reactive power aggregated equivalent algorithm;

[0162] The process for determining the power equivalence algorithm for the aggregated equivalent objects is as follows:

[0163] Aggregate and equalize all distributed wind power within the distribution network area to obtain a wind power aggregation and equalization object; determine the active power data and reactive power data of all distributed wind power within the distribution network area from the historical measurement data; use the active power data and reactive power data of all distributed wind power to perform power aggregation and equalization on the wind power aggregation and equalization object to obtain a wind power aggregation and equalization algorithm.

[0164] Aggregate and equalize all distributed photovoltaics within the distribution network area to obtain a photovoltaic aggregation and equalization object; determine the active power data and reactive power data of all distributed photovoltaics within the distribution network area from the historical measurement data; use the active power data and reactive power data of all distributed photovoltaics to perform power aggregation and equalization on the photovoltaic aggregation and equalization object to obtain a photovoltaic aggregation and equalization algorithm.

[0165] Aggregate and equalize the loads of all users within the distribution network area to obtain a load aggregation and equalization object; determine the active power data and reactive power data of all users within the distribution network area from the historical measurement data; use the active power data and reactive power data of all users to perform power aggregation and equalization on the load aggregation and equalization object to obtain a load aggregation and equalization algorithm.

[0166] Aggregate and equate all household energy storage within the distribution network area to obtain an energy storage aggregation equation object; determine the active power data and reactive power data of all household energy storage within the distribution network area from the historical measurement data; use the active power data and reactive power data of all household energy storage to perform power aggregation equation on the energy storage aggregation equation object to obtain an energy storage aggregation equation algorithm;

[0167] Aggregate and equalize all reactive power compensation devices within the distribution network area to obtain reactive power aggregation and equalization objects; determine the active power data and reactive power data of all reactive power compensation devices within the distribution network area from the historical measurement data; use the active power data and reactive power data of all reactive power compensation devices within the distribution network area to perform power aggregation and equalization on the reactive power aggregation and equalization objects to obtain the reactive power aggregation and equalization algorithm.

[0168] Furthermore, the process for determining the internal power loss algorithm of the distribution network area is as follows:

[0169] Aggregate and equalize the aggregated equivalent objects and the grid-connected points within the distribution network area to obtain internal power loss objects; determine the active power data and reactive power data of the grid-connected points in the distribution network area from the historical measurement data; use the active power data and reactive power data of the grid-connected points in the distribution network area, as well as the aggregation and equalization algorithm corresponding to each aggregated equivalent object, to perform power aggregation and equalization on the internal power loss objects to obtain the internal power loss algorithm.

[0170] Furthermore, the expression for the internal power loss algorithm is as follows:

[0171]

[0172] In the above formula, sp t For the active power data of the internal power loss object at time t, perform power aggregation and equalization. t For the reactive power data of the internal power loss object at time t, perform power aggregation and equalization. t Let nq be the active power data at grid connection point t. t For the reactive power data at grid connection point t, wp A,t wq represents the active power data of the wind power equivalent aggregation object at time t, which is used for power aggregation and equivalent data. A,t For the reactive power data of the wind power equivalent aggregation object at time t, pp A,t pq represents the active power data of the photovoltaic equivalent aggregation object at time t, which is the power aggregation equivalent. A,t lp represents the reactive power data of the photovoltaic equivalent aggregation object at time t, representing the power aggregation equivalent. A,t For the active power data of the load equalization aggregation object at time t, lq A,t For the reactive power data of the load equalization aggregation object at time t, ep A,t For the active power data of the energy storage equivalent aggregation object at time t, eq A,t dp represents the reactive power data of the energy storage equivalent aggregation object at time t, representing the power aggregation equivalent. A,t dq represents the active power data of the reactive power equalization object at time t, which is the power aggregation equalization value. a,t The reactive power data of the reactive power equalization object at time t is used for power aggregation.

[0173] Furthermore, the predicted power loss data includes:

[0174] Predicted active power loss data for distributed wind power, distributed photovoltaic power, user loads, household energy storage and reactive power compensation devices within the distribution network area;

[0175] Predicted reactive power loss data for distributed wind power, distributed photovoltaic power, user loads, household energy storage, and reactive power compensation devices within the distribution network area.

[0176] Furthermore, the system also includes: a current measurement data processing module, comprising:

[0177] The negative value measurement data acquisition submodule is used to process multiple measurement data in the current measurement data with positive and negative values ​​based on the power inflow power to obtain multiple negative value measurement data.

[0178] The measurement data sorting result acquisition submodule is used to sort the multiple negative value measurement data according to the same time series to obtain the measurement data sorting result;

[0179] The data processing submodule is used to remove outliers or reconstruct data from the sorting results of the measurement data to obtain the final current measurement data.

[0180] Furthermore, the data processing submodule is used for:

[0181] For outliers in the sorting results of the measurement data, at least one of the following algorithms—box plot method, interpolation method, and time series prediction method—is used to reconstruct the data and obtain the final current measurement data.

[0182] This invention builds an aggregated equivalent model of the distribution network area, including wind power, photovoltaic, load, energy storage, reactive power aggregation equivalent objects and internal power loss objects, based on historical measurement data of internal equipment and grid connection points within the distribution network area. It trains a power loss calculation model of the distribution network area based on LSTM for the internal power loss objects, inputs real-time measurement data of the distribution network area and ultra-short-term forecast plan data of internal equipment, and obtains intraday future time series data of the aggregated equivalent model of the distribution network area that meets the requirements of steady-state regulation and control in the county, supporting dispatchers in carrying out pre-dispatch work of distributed power sources and flexible loads in the county.

[0183] Example 3:

[0184] like Figure 4 As shown, the present invention also provides an electronic device, which may be a computer device, a microcontroller device, a smart mobile device, etc. The electronic device in this embodiment may include a processor, a memory, a transceiver component, etc. The memory, processor, and transceiver component are connected via a bus; the memory can be used to store executable programs, and an exemplary executable program may include instructions; the processor is used to execute the instructions stored in the memory. The memory can also be used to store data, which can be accessed and / or modified when instructions are executed.

[0185] The processor may be a Central Processing Unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing and control core of the terminal, and it is suitable for implementing one or more instructions. Specifically, it is suitable for loading and executing one or more instructions in the storage medium to realize the corresponding method flow or corresponding function, so as to realize the steps of the regional regulation and control simulation method based on the aggregation and equalization of distribution network areas in the above embodiments.

[0186] Example 4:

[0187] Based on the same inventive concept, this invention also provides a readable storage medium, specifically an electronic device readable storage medium (Memory). This readable storage medium is a memory device within an electronic device used to store programs and data. It is understood that the storage medium here can include both built-in storage media within the electronic device and extended storage media supported by the electronic device. The storage medium provides storage space, which stores the terminal's operating system. Furthermore, this storage space also stores one or more instructions suitable for loading and execution by a processor. These instructions can be one or more executable programs (including program code). It should be noted that the storage medium here can be high-speed RAM or non-volatile memory, such as at least one disk storage device. Loading and executing one or more instructions stored in the storage medium by the processor can implement the steps of the regional control calculation method based on distribution network area aggregation and equivalence in the above embodiments.

[0188] Those skilled in the art will understand that embodiments of this invention can be provided as methods, systems, or computer program products. Therefore, this invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this invention can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0189] This invention application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0190] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0191] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0192] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit its protection scope. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that after reading the present invention, they can still make various changes, modifications or equivalent substitutions to the specific implementation of the application, but these changes, modifications or equivalent substitutions are all within the protection scope of the claims pending approval.

Claims

1. A regional control simulation method based on the aggregation and equivalence of distribution network areas, characterized in that, include: Obtain the current measurement data of the distribution radio stations within the designated area; Based on the current measurement data, the predicted power loss data of the distribution network area is obtained by using the trained power loss calculation model of the distribution area. The load in the designated area is adjusted using the predicted power loss data. The power loss calculation model for the distribution transformer area is obtained by training a long short-term memory network based on historical measurement data and the distribution network distribution transformer area aggregation equivalent model.

2. The method according to claim 1, characterized in that, The training process of the power loss calculation model for the transformer substation includes: Based on the historical measurement data of the distribution network area, the historical power equivalent data is obtained by using the distribution network area aggregation equivalent model; Based on the historical power equivalent data, the historical power loss data is obtained using the distribution network area aggregated equivalent model; Using the historical power equivalent data and the historical power loss data, the Long Short Time Memory Network is trained to obtain the power loss calculation model for the transformer area.

3. The method according to claim 1 or 2, characterized in that, The distribution network area aggregated equivalent model includes: the power equivalent algorithm and the internal power loss algorithm of the aggregated equivalent object of the distribution network area.

4. The method according to claim 3, characterized in that, The power equivalence algorithms for the aggregated equivalent objects include: wind power aggregated equivalent algorithm, photovoltaic aggregated equivalent algorithm, load aggregated equivalent algorithm, energy storage aggregated equivalent algorithm, and reactive power aggregated equivalent algorithm; The process for determining the power equivalence algorithm for the aggregated equivalent objects is as follows: Aggregate and equalize all distributed wind power within the distribution network area to obtain a wind power aggregation and equalization object; determine the active power data and reactive power data of all distributed wind power within the distribution network area from the historical measurement data; use the active power data and reactive power data of all distributed wind power to perform power aggregation and equalization on the wind power aggregation and equalization object to obtain a wind power aggregation and equalization algorithm. Aggregate and equalize all distributed photovoltaics within the distribution network area to obtain a photovoltaic aggregation and equalization object; determine the active power data and reactive power data of all distributed photovoltaics within the distribution network area from the historical measurement data; use the active power data and reactive power data of all distributed photovoltaics to perform power aggregation and equalization on the photovoltaic aggregation and equalization object to obtain a photovoltaic aggregation and equalization algorithm. Aggregate and equalize the loads of all users within the distribution network area to obtain a load aggregation and equalization object; determine the active power data and reactive power data of all users within the distribution network area from the historical measurement data; use the active power data and reactive power data of all users to perform power aggregation and equalization on the load aggregation and equalization object to obtain a load aggregation and equalization algorithm. Aggregate and equate all household energy storage within the distribution network area to obtain an energy storage aggregation equation object; determine the active power data and reactive power data of all household energy storage within the distribution network area from the historical measurement data; use the active power data and reactive power data of all household energy storage to perform power aggregation equation on the energy storage aggregation equation object to obtain an energy storage aggregation equation algorithm; Aggregate and equalize all reactive power compensation devices within the distribution network area to obtain reactive power aggregation and equalization objects; determine the active power data and reactive power data of all reactive power compensation devices within the distribution network area from the historical measurement data; use the active power data and reactive power data of all reactive power compensation devices within the distribution network area to perform power aggregation and equalization on the reactive power aggregation and equalization objects to obtain the reactive power aggregation and equalization algorithm.

5. The method according to claim 4, characterized in that, The process for determining the internal power loss algorithm of the distribution network area is as follows: Aggregate and equalize the aggregated equivalent objects and the grid-connected points within the distribution network area to obtain internal power loss objects; determine the active power data and reactive power data of the grid-connected points in the distribution network area from the historical measurement data; use the active power data and reactive power data of the grid-connected points in the distribution network area, as well as the aggregation and equalization algorithm corresponding to each aggregated equivalent object, to perform power aggregation and equalization on the internal power loss objects to obtain the internal power loss algorithm.

6. The method according to claim 5, characterized in that, The expression for the internal power loss algorithm is as follows: In the above formula, sp t For the active power data of the internal power loss object at time t, perform power aggregation and equalization. t np represents the reactive power data of the internal power loss object at time t, which is the equivalent of power aggregation. t Let nq be the active power data at grid connection point t. t For the reactive power data at grid connection point t, wp A,t wq represents the active power data of the wind power equivalent aggregation object at time t, which is used for power aggregation and equivalent data. A,t For the reactive power data of the wind power equivalent aggregation object at time t, pp A,t pq represents the active power data of the photovoltaic equivalent aggregation object at time t, which is the power aggregation equivalent. A,t lp represents the reactive power data of the photovoltaic equivalent aggregation object at time t, representing the power aggregation equivalent. A,t lp represents the active power data of the load equalization aggregation object at time t, which is the power aggregation equalization value. A,t For the reactive power data of the load equalization aggregation object at time t, eq A,t For the active power data of the energy storage equivalent aggregation object at time t, eq A,t dp represents the reactive power data of the energy storage equivalent aggregation object at time t, representing the power aggregation equivalent. A,t dq represents the active power data of the reactive power equalization object at time t, which is the power aggregation equalization value. A,t The reactive power data of the reactive power equalization object at time t is used for power aggregation.

7. The method according to claim 1, characterized in that, The predicted power loss data includes: Predicted active power loss data for distributed wind power, distributed photovoltaic power, user loads, household energy storage and reactive power compensation devices within the distribution network area; Predicted reactive power loss data for distributed wind power, distributed photovoltaic power, user loads, household energy storage, and reactive power compensation devices within the distribution network area.

8. The method according to claim 1, characterized in that, Before obtaining the predicted power loss data of the distribution network area by extrapolating and predicting using the trained power loss calculation model based on the current measurement data, the method further includes: Based on the power inflow power, multiple measurement data in the current measurement data are processed to obtain multiple negative value measurement data; The multiple negative value measurement data are sorted according to the same time series to obtain the measurement data sorting result; The measurement data sorting results are then subjected to outlier removal or data reconstruction to obtain the final current measurement data.

9. The method according to claim 8, characterized in that, The step of reconstructing outlier data from the sorted measurement data to obtain the final current measurement data includes: For outliers in the sorting results of the measurement data, at least one of the following algorithms—box plot method, interpolation method, and time series prediction method—is used to reconstruct the data and obtain the final current measurement data.

10. A regional control and regulation simulation system based on the aggregation and equivalence of distribution network areas, characterized in that, include: The measurement data acquisition module is used to acquire the current measurement data of the distribution radio stations within a set area; The power loss data acquisition module is used to perform extrapolation and prediction based on the current measurement data and the trained distribution area power loss calculation model to obtain the predicted power loss data of the distribution network area; wherein, the distribution area power loss calculation model is obtained by training a long short time memory network based on historical measurement data and the distribution network area aggregated equivalent model. The control module is used to control the load of the set area using the predicted power loss data.

Images