Virtual power plant aggregation optimization system and method based on intelligent metering and real-time communication

Abstract

The present invention discloses a virtual power plant aggregation optimization system and method based on intelligent metering and real-time communication, which relates to the field of smart grid technology, including: receiving a predicted value of power demand in a future time zone; receiving a predicted value of power generation in a future time zone; segmenting the predicted value of power demand in a future time zone to obtain a predicted value of power demand in a peak time zone of a large power grid and a predicted value of power demand in a valley time zone of a large power grid; obtaining a distribution topology on the user side of an area; randomly configuring the predicted value of power demand in a peak time zone of a large power grid to obtain several aggregated distribution schemes for peak time zones; optimizing several aggregated distribution schemes for peak time zones to generate a recommended aggregated distribution scheme for a peak time zone, and performing distribution control in combination with the predicted value of power demand in a valley time zone of a large power grid. The present invention solves the technical problem of low efficiency in the allocation of power resources in the prior art when performing power dispatching, realizes the allocation and optimization of power resources, and achieves the technical effect of improving the operation efficiency of the power grid.

Description

Technical Field

[0001] The present invention relates to the field of smart grid technology, and in particular to a virtual power plant aggregation optimization system and method based on smart metering and real-time communication. Background Art

[0002] With the rapid development of industrial production and transportation, the continuous growth of electricity demand and the widespread application of distributed energy, the power system is facing unprecedented challenges. Traditional power dispatching methods mainly rely on centralized control, which is difficult to flexibly respond to the volatility and uncertainty of distributed energy resources. In addition, the lack of real-time communication and data analysis means leads to inefficient allocation of power resources and difficulty in achieving efficient operation of the power grid. Summary of the invention

[0003] The present application provides a virtual power plant aggregation optimization system and method based on smart metering and real-time communication, which is used to solve the technical problem of low efficiency in allocation of power resources when performing power dispatch in the prior art.

[0004] In view of the above problems, the present application provides a virtual power plant aggregation optimization system and method based on smart metering and real-time communication.

[0005] In a first aspect of the present application, a virtual power plant aggregation optimization system based on smart metering and real-time communication is provided, the system comprising:

[0006] A first prediction value receiving module, the first prediction value receiving module receives the future time zone demand power forecast value of the user end list of the first transformer in the first substation collected by the first meter; a second prediction value receiving module, the second prediction value receiving module receives the future time zone power generation forecast value of the distributed power station of the first transformer collected by the second meter; a prediction value segmentation module, the prediction value segmentation module segments the future time zone demand power forecast value to obtain the large power grid peak time zone demand power forecast value and the large power grid valley time zone demand power forecast value; a user side distribution topology acquisition module, the user side distribution topology acquisition module The block obtains the user-side distribution topology of the substation; a random configuration module, which randomly configures the peak time zone demand power forecast value of the large power grid according to the future time zone power generation forecast value, and obtains several peak time zone aggregated distribution plans; a distribution plan optimization module, which optimizes the several peak time zone aggregated distribution plans according to the user-side distribution topology of the substation, and generates a peak time zone recommended aggregated distribution plan; a distribution control module, which performs distribution control according to the valley time zone demand power forecast value of the large power grid and the peak time zone recommended aggregated distribution plan.

[0007] A second aspect of the present application provides a virtual power plant aggregation optimization method based on smart metering and real-time communication, the method comprising:

[0008] Receive the future time zone power demand forecast value of the user end list of the first substation of the first transformer collected by the first meter; receive the future time zone power generation forecast value of the distributed power station of the first transformer collected by the second meter; divide the future time zone power demand forecast value to obtain the large power grid peak time zone power demand forecast value and the large power grid valley time zone power demand forecast value; obtain the substation user side distribution topology; according to the future time zone power generation forecast value, randomly configure the large power grid peak time zone power demand forecast value to obtain several peak time zone aggregated distribution plans; according to the substation user side distribution topology, optimize the several peak time zone aggregated distribution plans to generate a peak time zone recommended aggregated distribution plan; perform distribution control according to the large power grid valley time zone power demand forecast value and the peak time zone recommended aggregated distribution plan.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] The present application receives a future time zone power demand forecast value of a user-side list of a first substation of a first transformer collected by a first meter; receives a future time zone power generation forecast value of a distributed power station of the first transformer collected by a second meter; divides the future time zone power demand forecast value to obtain a large power grid peak time zone power demand forecast value and a large power grid valley time zone power demand forecast value; obtains a substation user-side distribution topology; randomly configures the large power grid peak time zone power demand forecast value according to the future time zone power generation forecast value to obtain a number of peak time zone aggregated distribution plans; optimizes a number of peak time zone aggregated distribution plans according to the substation user-side distribution topology to generate a peak time zone recommended aggregated distribution plan; and performs distribution control according to the large power grid valley time zone power demand forecast value and the peak time zone recommended aggregated distribution plan. The present invention solves the technical problem of low efficiency in the allocation of power resources in the prior art during power dispatching, by receiving and analyzing the predicted values ​​of future time zone power demand and power generation at the user end and distributed power stations, segmenting the demand data, obtaining peak and valley demand forecasts, combining the user-side distribution topology, randomly configuring and optimizing the distribution plan to perform distribution control, thereby realizing the allocation and optimization of power resources and achieving the technical effect of improving the operation efficiency of the power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of 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 creative work.

[0012] Figure 1 A schematic diagram of the structure of a virtual power plant aggregation optimization system based on smart metering and real-time communication provided in an embodiment of the present application;

[0013] Figure 2 A schematic flow chart of a virtual power plant aggregation optimization method based on smart metering and real-time communication provided in an embodiment of the present application.

[0014] Explanation of the accompanying drawings: first prediction value receiving module 11, second prediction value receiving module 12, prediction value segmentation module 13, user-side distribution topology acquisition module 14, random configuration module 15, power distribution plan optimization module 16, power distribution control module 17. DETAILED DESCRIPTION

[0015] The present application provides a virtual power plant aggregation optimization system and method based on intelligent metering and real-time communication, aiming to solve the technical problem of low efficiency in the allocation of power resources in the prior art during power dispatching. By receiving and analyzing the future time zone power demand and power generation forecast values ​​of the user end and distributed power stations, segmenting the demand data, obtaining peak and valley demand forecasts, and combining the user-side distribution topology, randomly configuring and optimizing the distribution plan for distribution control, the allocation and optimization of power resources are realized, thereby achieving the technical effect of improving the operation efficiency of the power grid.

[0016] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0017] It should be noted that any variations of the terms "include" and "have" are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules that are not explicitly listed or inherent to these processes, methods, products or devices.

[0018] Embodiment 1

[0019] like Figure 1As shown, the embodiment of the present application provides a virtual power plant aggregation optimization system based on smart metering and real-time communication, the system comprising:

[0020] The first prediction value receiving module 11 receives the future time zone demand power prediction value of the user terminal list of the first substation of the first transformer collected by the first meter.

[0021] Furthermore, in the system provided in the embodiment of the application, the first prediction value receiving module 11 is also used for:

[0022] The historical year-on-year electricity consumption record value of the first user in the future time zone of the user-side list is collected through the first meter; when the future time zone is the head time zone of the same year, the electricity consumption is predicted according to the historical year-on-year electricity consumption record value of the first user, and the future time zone demand power prediction value of the first user is obtained; when the future time zone is not the head time zone of the same year, the electricity consumption is predicted according to the stored value of the electricity consumption of the time zone recorded in the same year and the historical year-on-year electricity consumption record value of the first user, and the future time zone demand power prediction value of the first user is obtained; the future time zone demand power prediction value of the first user is added to the future time zone demand power prediction value.

[0023] In the embodiment of the present application, the first meter first collects the historical year-on-year electricity consumption record value of the first user in the future time zone of the user-side list. The first meter is a device installed at the user end, responsible for collecting and recording the electricity consumption data of each user. The user-side list contains information about all users in the first area, which is the basis for electricity consumption prediction.

[0024] When predicting the electricity demand in a future time zone, first determine whether the time zone is the head time zone of the same year. The head time zone refers to the period at the beginning of the year, such as January or the beginning of the first quarter. If the future time zone is the head time zone of the same year, the first user's historical year-on-year electricity consumption record values ​​are used for prediction. These historical records reflect the first user's electricity consumption pattern in the head time zone of the same year. By analyzing these patterns, the first user's demand power forecast value in the future time zone is predicted.

[0025] If the future time zone is not the head time zone of the same year, a different method is used for prediction. At this time, analysis is performed based on the stored power consumption values ​​of the time zones recorded in the same year and the historical year-on-year power consumption records of the first user. The stored power consumption values ​​of the time zones recorded in the same year refer to the actual power consumption data of each time zone that the system has recorded in the current year. Combined with these data, the power demand forecast value of the first user in the future time zone is predicted. Finally, the power demand forecast values ​​of these individual users in the future time zones are aggregated to generate a comprehensive power demand forecast value for the future time zones.

[0026] Furthermore, in the system provided in the embodiment of the application, the first prediction value receiving module 11 is also used for:

[0027] The historical year-on-year electricity consumption record values ​​of the first user are arranged in chronological order by year to obtain a sorting result of the first year-on-year electricity consumption record values; when the sorting result of the first year-on-year electricity consumption record values ​​is in an upward or downward trend, the mode value of the change gradient of the historical year-on-year electricity consumption record values ​​of the first user is calculated and set as a change gradient vector; the year-on-year electricity consumption record values ​​of the previous period are predicted according to the change gradient vector to obtain a predicted value of the first user's future time zone demand electricity; when the sorting result of the first year-on-year electricity consumption record values ​​is in other states, the mode value of the historical year-on-year electricity consumption record values ​​of the first user is calculated and set as a predicted value of the first user's future time zone demand electricity.

[0028] In the embodiment of the present application, according to the historical year-on-year electricity consumption record value of the first user, these data are first arranged in the order of the year to obtain the sorting result of the first year-on-year electricity consumption record value. The historical year-on-year electricity consumption record value of the first user refers to the electricity consumption data of the first user in the same time period every year. When the sorting result of the first year-on-year electricity consumption record value is in an upward or downward trend, a statistical analysis method, such as the least squares method and polynomial regression, is further used to calculate the change gradient mode value of these historical electricity consumption record values, and set it as the change gradient vector.

[0029] Next, the change gradient vector is used to predict the year-on-year electricity consumption record value of the previous cycle, so as to obtain the demand power forecast value of the first user in the future time zone. Specifically, LSTM is used for prediction, the historical year-on-year electricity consumption record value is preprocessed, and the data is normalized to meet the input requirements of the neural network. Then, the preprocessed data is divided into a training set and a validation set, and input into the LSTM network for training. During the training process, the LSTM network automatically learns the complex patterns and long-term dependencies in the data through the calculation of multiple layers of neurons. Specifically, the LSTM network controls the flow of information and the update of the state through the input gate, forget gate and output gate, so as to remember the long-term electricity consumption trend and seasonal fluctuations. After the training is completed, the year-on-year electricity consumption record value of the previous cycle is input into the trained LSTM model. The LSTM model predicts the demand power value of the future time zone based on the input data and the learned pattern. In this way, the demand power forecast value of the first user in the future time zone is obtained.

[0030] If the sorting result of the first year-on-year electricity consumption record value does not have an obvious upward or downward trend, but is in other states, that is, no obvious trend, another method is used for prediction. At this time, the mode value of these historical electricity consumption record values ​​is calculated and used as the demand power forecast value of the first user in the future time zone.

[0031] Furthermore, in the system provided in the embodiment of the application, the first prediction value receiving module 11 is also used for:

[0032] Perform electricity consumption forecast based on the historical year-on-year electricity consumption record values ​​of the first user to obtain the first dimension future time zone demand electricity forecast value; obtain the first dimension demand electricity forecast value of the stored value of the time zone electricity consumption recorded in the same year; calculate the electricity deviation vector between the stored value of the time zone electricity consumption recorded in the same year and the first dimension demand electricity forecast value; adjust the first dimension future time zone demand electricity forecast value based on the electricity deviation vector to obtain the first dimension future time zone demand electricity forecast value.

[0033] In an embodiment of the present application, the power consumption is first predicted based on the historical year-on-year power consumption record value of the first user to obtain the power demand forecast value of the first dimension in the future time zone. To achieve this goal, a neural network is used. The LSTM neural network effectively handles long-term dependencies through its long short-term memory unit and can capture complex patterns in time series data. The historical power consumption data is preprocessed, the data is standardized and a time series sample suitable for the LSTM input format is created. Then, the processed data is input into the trained LSTM model to generate the power demand forecast value of the first dimension in the future time zone.

[0034] Next, the first dimension demand power forecast value of the stored value of power consumption in the same time zone is obtained. The stored value of power consumption in the same time zone refers to the actual power consumption data of each time zone that the system has recorded in the current year. These data are stored in the database management system and processed and extracted by data analysis tools such as Panda.

[0035] Then, the power deviation vector between the stored value of power consumption in the time zone recorded in the same year and the power demand prediction value in the future time zone of the first dimension is calculated. The power deviation vector reflects the difference between the predicted value and the actual recorded value. Finally, the power demand prediction value in the future time zone of the first dimension is adjusted according to the power deviation vector to obtain the power demand prediction value in the future time zone of the first user.

[0036] Furthermore, in the system provided in the embodiment of the application, the first prediction value receiving module 11 is also used for:

[0037] Calculate the initial vector set of electricity deviations between the stored values ​​of electricity consumption in the time zone recorded in the same year and the demand power forecast value of the first dimension; when the maximum modulus value of the initial vector set of electricity deviations is less than or equal to the modulus value threshold, configure the electricity deviation vector to 0; when the maximum modulus value of the initial vector set of electricity deviations is greater than the modulus value threshold, perform mode analysis on the initial vector set of electricity deviations to obtain the electricity deviation vector.

[0038] In the embodiment of the present application, the initial vector set of power deviation between the stored value of power consumption in the time zone recorded in the same year and the predicted value of power demand in the first dimension is first calculated. To achieve this, a data analysis tool is used to compare the actual power consumption data with the predicted data, and the difference value of each time zone is calculated to generate the initial vector set of power deviation. The initial vector set of power deviation refers to the difference between the predicted value and the actual recorded value in each time zone.

[0039] Next, evaluate the maximum modulus value of the set of initial vectors of power deviation. The modulus refers to the length or size of a vector and is used to measure the magnitude of the error. Use linear algebra tools to calculate the modulus of each deviation vector and find the maximum value. If the maximum modulus value of the set of initial vectors of power deviation is less than or equal to the preset modulus threshold, configure the power deviation vector to 0. The modulus threshold is a predefined error tolerance range, which means that when the error is within an acceptable range, no further adjustment is required. If the maximum modulus value of the set of initial vectors of power deviation is greater than the modulus threshold, perform a mode analysis on the set of initial vectors of power deviation. Use statistical analysis tools, such as the mode function in the R language, to perform a mode analysis on the set of initial vectors of power deviation to find the most common deviation value in the error, called the power deviation vector.

[0040] The second prediction value receiving module 12 receives the future time zone power generation prediction value of the distributed power station of the first transformer collected by the second meter.

[0041] In the embodiment of the present application, the second prediction value receiving module is responsible for processing the power generation prediction data obtained from the distributed power station. First, the second meter, as a device installed in the distributed power station, continuously collects and records the power generation data of the power station. A distributed power station refers to a plurality of small power generation units that are scattered in the power grid, independently generate electricity and supply power to the power grid.

[0042] To predict the power generation in the future time zone, the LSTM neural network model is used. The LSTM neural network can effectively handle long-term dependencies through its long short-term memory units and can capture complex patterns in time series data. Specifically, the historical power generation data collected by the second meter is first preprocessed, including data cleaning to remove noise and outliers, and data standardization. The preprocessed data is divided into training and test sets and input into the LSTM neural network in the form of time series. The system uses the past power generation data as input and the current power generation as output for model training. Through multiple iterations, the LSTM neural network gradually learns the patterns and trends in the data. After the training is completed, the system inputs the time series data of the future time zone into the trained LSTM model to generate the power generation forecast value of the future time zone.

[0043] The predicted value segmentation module 13 segments the predicted value of power demand in the future time zone to obtain the predicted value of power demand in the peak time zone of the large power grid and the predicted value of power demand in the valley time zone of the large power grid.

[0044] In the embodiment of the present application, the power demand forecast value of the future time zone is input into the forecast value segmentation module, and the time series analysis method is used to analyze the power consumption change pattern in a day to determine which time periods belong to the peak time zone and which time periods belong to the valley time zone. According to the recognition result, the power demand forecast value of the future time zone is segmented to extract the power demand forecast value of the large power grid peak time zone and the power demand forecast value of the large power grid valley time zone.

[0045] The user side distribution topology acquisition module 14 is used to obtain the user side distribution topology of the substation area.

[0046] In the embodiment of the present application, the user-side distribution topology acquisition module first uses GIS technology to collect the geographic location information and power equipment information of all users in the substation area. The collected geographic location information and power equipment information are integrated into the GIS database, and the integrated geographic information data is used to construct the user-side distribution topology map through the spatial analysis function of GIS.

[0047] The random configuration module 15 randomly configures the predicted value of power demand in the peak time zone of the large power grid according to the predicted value of power generation in the future time zone, and obtains a plurality of peak time zone aggregated distribution plans.

[0048] In the embodiment of the present application, the predicted power generation value of the future time zone and the predicted power demand value of the large power grid peak time zone are input into the random configuration module, and then the Monte Carlo simulation method is used to randomly allocate these power generation values ​​according to the predicted power generation value of the future time zone to meet the predicted power demand value of the large power grid peak time zone, and randomly generate multiple configuration schemes. Through multiple random samplings, several peak time zone aggregate distribution schemes are generated.

[0049] Furthermore, in the system provided in the embodiment of the application, the random configuration module 15 is also used for:

[0050] The large power grid peak time zone power demand forecast value includes N users' large power grid peak time zone power demand forecast values; according to the future time zone power generation forecast value, the N users' large power grid peak time zone power demand forecast values ​​are randomly deployed to obtain a first aggregate power generation deployment plan; the first aggregate power generation deployment plan is added to the several peak time zone aggregate distribution plans.

[0051] In an embodiment of the present application, the power demand forecast value of the peak time zone of the large power grid includes the power demand forecast value of the peak time zone of the large power grid of N users. The power generation forecast value of the future time zone and the power demand forecast value of the peak time zone of the large power grid are input into the random configuration module, and the Monte Carlo simulation method is used to randomly allocate the power generation to the power demand forecast value of the peak time zone of the large power grid of N users according to the power generation forecast value of the future time zone. According to the randomly generated configuration plan, the first aggregate power generation deployment plan is obtained. The first aggregate power generation deployment plan refers to connecting all the power generation of the future time zone to the corresponding designated users, so as to meet the peak time zone demand of the large power grid of N users.

[0052] Finally, the first aggregated power generation deployment plan is added to several peak time zone aggregated distribution plans.

[0053] The power distribution scheme optimization module 16 optimizes the aggregated power distribution schemes of the plurality of peak time zones according to the user-side distribution topology of the substation area, and generates a recommended aggregated power distribution scheme of the peak time zone.

[0054] Furthermore, in the system provided in the embodiment of the application, the power distribution scheme optimization module 16 is also used for:

[0055] According to the user-side distribution topology of the substation, a first aggregated power generation deployment plan is obtained, wherein the first aggregated power generation deployment plan includes a first aggregated power generation user list and a first aggregated power generation list; according to the user-side distribution topology of the substation, the first aggregated power generation user list is traversed to obtain a first power transmission path length list, wherein the power transmission path refers to the path from the substation to the user side; the first power transmission path length list is traversed to perform mode statistics on historical power generation loss monitoring values ​​to obtain a first aggregated power generation loss ratio list; power generation loss analysis is performed based on the first aggregated power generation loss ratio list and the first aggregated power generation list to obtain a power generation loss value list; the power generation loss value list is added to obtain a first scheme loss parameter, and several scheme loss parameters are added; minimum value sorting is performed based on the several scheme loss parameters to obtain the recommended aggregated distribution plan for the peak time zone.

[0056] In the embodiment of the present application, firstly, a graph theory algorithm, such as a shortest path algorithm, is used to calculate the optimal path from the substation to each user according to the user-side distribution topology of the substation area, and obtain a first aggregated power generation deployment plan. The plan includes a first aggregated power generation user list and a first aggregated power generation list. The user list contains detailed information of all users, and the power generation list lists the specific power generation allocation of each user.

[0057] Next, we traverse the first aggregated power generation user list, use the geographic information system to calculate the length of the power transmission path from the substation to each user, and generate the first power transmission path length list. The power transmission path refers to the transmission route from the substation to the user side. The path length reflects the distance and potential loss of power during the transmission process. Then we traverse the first power transmission path length list, use historical power generation data and data analysis tools to monitor and count the loss of each path, and generate the first aggregated power generation loss ratio list. The power generation loss ratio refers to the proportion of power loss during the transmission process. Statistical methods are used to identify the most common loss values ​​in the data set.

[0058] According to the first aggregated power generation loss ratio list and the first aggregated power generation list, linear programming and optimization algorithms, such as the linear programming module in Scipy, are used to perform power generation loss analysis and generate a power generation loss value list. The list records the specific loss of each path, and the total loss of each solution is calculated by adding these loss values. The data in the power generation loss value list is added to obtain the loss parameters of the first solution. For each generated aggregate distribution solution, the corresponding loss parameters are calculated. Then, these parameters are added to a set to form several solution loss parameters.

[0059] Based on the loss parameters of several schemes, the scheme with the smallest loss parameter is selected through optimization algorithms such as genetic algorithms to obtain the recommended aggregate distribution scheme for the peak time zone. The recommended aggregate distribution scheme for the peak time zone is the scheme with the smallest transmission loss and the highest efficiency among all schemes.

[0060] The power distribution control module 17 performs power distribution control according to the power demand forecast value of the large power grid in the valley time zone and the recommended aggregated power distribution plan in the peak time zone.

[0061] In the embodiment of the present application, the power distribution control module first receives the power demand forecast value of the valley time zone of the large power grid and the recommended aggregated power distribution plan of the peak time zone, and compares and matches the two input data. Specifically, the total amount of power required in the valley time period is determined according to the demand forecast value of the valley time zone of the large power grid. Then, the power supply capacity in the recommended aggregated power distribution plan of the peak time zone is matched with the demand of the valley time zone, and a comprehensive power distribution plan is generated based on the matching results. Finally, according to the comprehensive power distribution plan, a power distribution control algorithm, such as a PID control algorithm, is used to adjust the power distribution in real time.

[0062] In the embodiments of the present application, in summary, the embodiments of the present application have at least the following technical effects:

[0063] The present application receives a future time zone power demand forecast value of a user-side list of a first substation of a first transformer collected by a first meter; receives a future time zone power generation forecast value of a distributed power station of the first transformer collected by a second meter; divides the future time zone power demand forecast value to obtain a large power grid peak time zone power demand forecast value and a large power grid valley time zone power demand forecast value; obtains a substation user-side distribution topology; randomly configures the large power grid peak time zone power demand forecast value according to the future time zone power generation forecast value to obtain a number of peak time zone aggregated distribution plans; optimizes a number of peak time zone aggregated distribution plans according to the substation user-side distribution topology to generate a peak time zone recommended aggregated distribution plan; and performs distribution control according to the large power grid valley time zone power demand forecast value and the peak time zone recommended aggregated distribution plan. The present invention solves the technical problem of low efficiency in the allocation of power resources in the prior art during power dispatching, by receiving and analyzing the predicted values ​​of future time zone power demand and power generation at the user end and distributed power stations, segmenting the demand data, obtaining peak and valley demand forecasts, combining the user-side distribution topology, randomly configuring and optimizing the distribution plan to perform distribution control, thereby realizing the allocation and optimization of power resources and achieving the technical effect of improving the operation efficiency of the power grid.

[0064] Embodiment 2 is based on the same inventive concept as the virtual power plant aggregation optimization system based on smart metering and real-time communication in the previous embodiment. Figure 2 As shown, the embodiment of the present application provides a virtual power plant aggregation optimization method based on smart metering and real-time communication, the method comprising:

[0065] Receive the future time zone power demand forecast value of the user end list of the first substation of the first transformer collected by the first meter; receive the future time zone power generation forecast value of the distributed power station of the first transformer collected by the second meter; divide the future time zone power demand forecast value to obtain the large power grid peak time zone power demand forecast value and the large power grid valley time zone power demand forecast value; obtain the substation user side distribution topology; according to the future time zone power generation forecast value, randomly configure the large power grid peak time zone power demand forecast value to obtain several peak time zone aggregated distribution plans; according to the substation user side distribution topology, optimize the several peak time zone aggregated distribution plans to generate a peak time zone recommended aggregated distribution plan; perform distribution control according to the large power grid valley time zone power demand forecast value and the peak time zone recommended aggregated distribution plan.

[0066] Further, receiving the predicted value of power demand in the future time zone of the user terminal list of the first transformer zone collected by the first meter includes:

[0067] The historical year-on-year electricity consumption record value of the first user in the future time zone of the user-side list is collected through the first meter; when the future time zone is the head time zone of the same year, the electricity consumption is predicted according to the historical year-on-year electricity consumption record value of the first user, and the future time zone demand power prediction value of the first user is obtained; when the future time zone is not the head time zone of the same year, the electricity consumption is predicted according to the stored value of the electricity consumption of the time zone recorded in the same year and the historical year-on-year electricity consumption record value of the first user, and the future time zone demand power prediction value of the first user is obtained; the future time zone demand power prediction value of the first user is added to the future time zone demand power prediction value.

[0068] Further, when the future time zone is the head time zone of the same year, the power consumption is predicted according to the historical year-on-year power consumption record value of the first user to obtain the power demand prediction value of the first user in the future time zone, including:

[0069] The historical year-on-year electricity consumption record values ​​of the first user are arranged in chronological order by year to obtain a sorting result of the first year-on-year electricity consumption record values; when the sorting result of the first year-on-year electricity consumption record values ​​is in an upward or downward trend, the mode value of the change gradient of the historical year-on-year electricity consumption record values ​​of the first user is calculated and set as a change gradient vector; the year-on-year electricity consumption record values ​​of the previous period are predicted according to the change gradient vector to obtain a predicted value of the first user's future time zone demand electricity; when the sorting result of the first year-on-year electricity consumption record values ​​is in other states, the mode value of the historical year-on-year electricity consumption record values ​​of the first user is calculated and set as a predicted value of the first user's future time zone demand electricity.

[0070] Further, when the future time zone is not the head time zone of the same year, the power consumption is predicted according to the stored value of the power consumption in the time zone recorded in the same year and the historical year-on-year power consumption record value of the first user, and the power demand prediction value of the first user in the future time zone is obtained, including:

[0071] Perform electricity consumption forecast based on the historical year-on-year electricity consumption record values ​​of the first user to obtain the first dimension future time zone demand electricity forecast value; obtain the first dimension demand electricity forecast value of the stored value of the time zone electricity consumption recorded in the same year; calculate the electricity deviation vector between the stored value of the time zone electricity consumption recorded in the same year and the first dimension demand electricity forecast value; adjust the first dimension future time zone demand electricity forecast value based on the electricity deviation vector to obtain the first dimension future time zone demand electricity forecast value.

[0072] Further, calculating the power deviation vector between the stored value of the power consumption in the time zone recorded in the same year and the power demand forecast value of the first dimension includes:

[0073] Calculate the initial vector set of electricity deviations between the stored values ​​of electricity consumption in the time zone recorded in the same year and the demand power forecast value of the first dimension; when the maximum modulus value of the initial vector set of electricity deviations is less than or equal to the modulus value threshold, configure the electricity deviation vector to 0; when the maximum modulus value of the initial vector set of electricity deviations is greater than the modulus value threshold, perform mode analysis on the initial vector set of electricity deviations to obtain the electricity deviation vector.

[0074] Furthermore, according to the predicted value of power generation in the future time zone, the predicted value of power demand in the peak time zone of the large power grid is randomly configured to obtain several peak time zone aggregated distribution schemes, including:

[0075] The large power grid peak time zone power demand forecast value includes N users' large power grid peak time zone power demand forecast values; according to the future time zone power generation forecast value, the N users' large power grid peak time zone power demand forecast values ​​are randomly deployed to obtain a first aggregate power generation deployment plan; the first aggregate power generation deployment plan is added to the several peak time zone aggregate distribution plans.

[0076] Furthermore, according to the user-side distribution topology of the substation area, the plurality of peak time zone aggregate distribution schemes are optimized to generate a peak time zone recommended aggregate distribution scheme, including:

[0077] According to the user-side distribution topology of the substation, a first aggregated power generation deployment plan is obtained, wherein the first aggregated power generation deployment plan includes a first aggregated power generation user list and a first aggregated power generation list; according to the user-side distribution topology of the substation, the first aggregated power generation user list is traversed to obtain a first power transmission path length list, wherein the power transmission path refers to the path from the substation to the user side; the first power transmission path length list is traversed to perform mode statistics on historical power generation loss monitoring values ​​to obtain a first aggregated power generation loss ratio list; power generation loss analysis is performed based on the first aggregated power generation loss ratio list and the first aggregated power generation list to obtain a power generation loss value list; the power generation loss value list is added to obtain a first scheme loss parameter, and several scheme loss parameters are added; minimum value sorting is performed based on the several scheme loss parameters to obtain the recommended aggregated distribution plan for the peak time zone.

[0078] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. The processes depicted in the accompanying drawings do not necessarily require the specific order and continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0079] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

[0080] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A virtual power plant aggregation optimization system based on smart metering and real-time communication, characterized in that: include: A first prediction value receiving module, the first prediction value receiving module receives a future time zone demand power prediction value of a user terminal list of a first substation of a first transformer collected by a first meter; A second prediction value receiving module, which receives a future time zone power generation prediction value of the distributed power station of the first transformer collected by the second meter; A prediction value segmentation module, wherein the prediction value segmentation module segments the future time zone demand power prediction value to obtain a large power grid peak time zone demand power prediction value and a large power grid valley time zone demand power prediction value; A user side distribution topology acquisition module, the user side distribution topology acquisition module obtains the user side distribution topology of the station area; A random configuration module, wherein the random configuration module randomly configures the predicted value of power demand in the peak time zone of the large power grid according to the predicted value of power generation in the future time zone, and obtains a plurality of peak time zone aggregated power distribution schemes; A power distribution scheme optimization module, which optimizes the aggregated power distribution schemes of the plurality of peak time zones according to the user-side distribution topology of the substation area, and generates a recommended aggregated power distribution scheme for the peak time zone; A power distribution control module, which performs power distribution control according to the power demand forecast value of the large power grid in the valley time zone and the recommended aggregated power distribution plan in the peak time zone; According to the predicted value of power generation in the future time zone, the predicted value of power demand in the peak time zone of the large power grid is randomly configured to obtain several peak time zone aggregated distribution schemes, including: The large power grid peak time zone demand power forecast value includes N users' large power grid peak time zone demand power forecast values; According to the predicted power generation in the future time zone, the predicted power demand values ​​of the peak time zone of the large power grid of the N users are randomly deployed to obtain a first aggregated power generation deployment plan; Adding the first aggregated power generation deployment plan to the plurality of peak time zone aggregated power distribution plans; According to the user-side distribution topology of the substation area, the plurality of peak time zone aggregate distribution schemes are optimized to generate a peak time zone recommended aggregate distribution scheme, including: According to the user-side distribution topology of the substation area, a first aggregated power generation deployment plan is obtained, wherein the first aggregated power generation deployment plan includes a first aggregated power generation user list and a first aggregated power generation list; According to the user-side distribution topology of the substation area, traverse the first aggregated power generation user list to obtain a first power transmission path length list, wherein the power transmission path refers to the path from the substation to the user side; Traversing the first power transmission path length list to perform mode statistics on historical power generation loss monitoring values, and obtaining a first aggregated power generation loss ratio list; Perform power generation loss analysis according to the first aggregate power generation loss ratio list and the first aggregate power generation amount list to obtain a power generation loss value list; Add the power generation loss value list to obtain the loss parameter of the first scheme, and add the loss parameters of several schemes; Minimum value sorting is performed based on the loss parameters of the several schemes to obtain the recommended aggregated power distribution scheme for the peak time zone.

2. The system according to claim 1, characterized in that The future time zone demand power forecast value of the user terminal list of the first transformer in the first substation collected by the first meter is received, including: Collecting, by means of the first meter, a historical year-on-year electricity consumption record value of a first user in a future time zone of the user terminal list; When the future time zone is the head time zone of the same year, power consumption is predicted according to the historical year-on-year power consumption record value of the first user to obtain the power demand prediction value of the first user in the future time zone; When the future time zone is not the head time zone of the same year, power consumption is predicted based on the stored value of power consumption in the time zone recorded in the same year and the historical year-on-year power consumption record value of the first user to obtain the predicted power demand value of the first user in the future time zone; The predicted value of the first user's power demand in the future time zone is added to the predicted value of the power demand in the future time zone.

3. The system according to claim 2, characterized in that When the future time zone is the head time zone of the same year, power consumption prediction is performed according to the historical year-on-year power consumption record value of the first user to obtain the power demand prediction value of the first user in the future time zone, including: Arrange the first user's historical year-on-year electricity consumption record values ​​in chronological order by year to obtain a first year-on-year electricity consumption record value sorting result; When the sorting result of the first year-on-year electricity consumption record value is in an upward or downward trend, calculating the change gradient mode value of the first user's historical year-on-year electricity consumption record value, and setting it as the change gradient vector; According to the change gradient vector, the recorded value of year-on-year electricity consumption in the previous period is predicted to obtain the predicted value of the power demand of the first user in the future time zone; When the sorting result of the first year-on-year electricity consumption record value is in other states, the mode value of the historical year-on-year electricity consumption record value of the first user is calculated and set as the predicted power demand value of the first user in the future time zone.

4. The system according to claim 2, characterized in that When the future time zone is not the head time zone of the same year, power consumption is predicted according to the stored value of power consumption in the time zone recorded in the same year and the historical year-on-year power consumption record value of the first user, to obtain the predicted value of power demand in the future time zone of the first user, including: According to the historical year-on-year electricity consumption record value of the first user, electricity consumption is predicted to obtain a predicted value of electricity demand in the first dimension in the future time zone; Obtain the first dimension demand power forecast value of the stored value of power consumption in the time zone recorded in the same year; Calculate the power deviation vector between the stored value of the power consumption in the time zone recorded in the same year and the predicted value of the power demand in the first dimension; The predicted value of the power demand in the future time zone of the first dimension is adjusted according to the power deviation vector to obtain the predicted value of the power demand in the future time zone of the first user.

5. The system according to claim 4, characterized in that Calculating the power deviation vector between the stored value of the power consumption in the time zone recorded in the same year and the predicted value of the power demand in the first dimension includes: Calculate an initial vector set of power deviations between the stored value of power consumption in the time zone recorded in the same year and the predicted value of power demand in the first dimension; When the maximum modulus value of the initial power deviation vector set is less than or equal to the modulus value threshold, the power deviation vector is configured to be 0; When the maximum modulus value of the electric quantity deviation initial vector set is greater than the modulus value threshold, a mode analysis is performed on the electric quantity deviation initial vector set to obtain the electric quantity deviation vector.

6. A virtual power plant aggregation optimization method based on smart metering and real-time communication, characterized in that: The method is performed by a virtual power plant aggregation optimization system based on smart metering and real-time communication according to any one of claims 1 to 5, comprising: Receive a future time zone demand power forecast value of a user terminal list of a first transformer zone collected by a first meter; Receiving a future time zone power generation forecast value of the distributed power station of the first transformer collected by the second meter; Segmenting the predicted power demand value in the future time zone to obtain a predicted power demand value in the peak time zone of the large power grid and a predicted power demand value in the valley time zone of the large power grid; Obtain the user-side distribution topology of the substation area; According to the predicted power generation in the future time zone, the predicted power demand value in the peak time zone of the large power grid is randomly configured to obtain several peak time zone aggregated power distribution schemes; According to the user-side distribution topology of the substation area, the plurality of peak time zone aggregated power distribution schemes are optimized to generate a peak time zone recommended aggregated power distribution scheme; Power distribution control is performed according to the predicted power demand value in the valley time zone of the large power grid and the recommended aggregated distribution plan in the peak time zone.

Images