Rural area reverse heavy overload treatment method, treatment device, equipment and medium

Abstract

The invention provides a treatment method, a treatment device, equipment and a medium for reverse heavy overload of a rural area, and belongs to the technical field of distributed photovoltaics. The management method comprises the following steps: acquiring load prediction data and distributed photovoltaic prediction data of a background region in n years; constructing a reverse heavy overload governance model by taking the minimum cost as a target; constructing a photovoltaic power generation efficiency prediction model and a load ratio prediction model; solving a reverse heavy overload governance model according to the photovoltaic power generation efficiency prediction model and the load ratio prediction model; and obtaining a reverse heavy overload treatment scheme of the current transformer area by using the reverse heavy overload treatment model. According to the reverse heavy overload governance model constructed by the invention, the minimum governance cost is taken as a target under the condition of considering the light abandoning loss, and parameters comprise the capacity expansion cost of a distribution transformer, the cost of regulating and controlling terminal transformation for realizing distributed photovoltaic flexible control and the light abandoning loss; and a reverse heavy overload treatment scheme of the current transformer area can be obtained by using the reverse heavy overload treatment model.

Description

Technical Field

[0001] The present invention belongs to the technical field of distributed photovoltaics, and specifically relates to a method, a device, an electronic device and a storage medium for controlling reverse heavy overload in a rural area. Background Art

[0002] After clean energy represented by distributed photovoltaics is connected to the distribution network, the randomness and volatility of its output increase the complexity of the power grid flow, and the risk of reverse overload of the distribution network becomes more severe, affecting the healthy and stable operation of the distribution network. Taking rural substations as an example, there are currently a large number of distributed photovoltaics on rooftops in rural areas. When the output of distributed photovoltaics is too large and higher than the local load level, the output that is not absorbed is sent back to the distribution transformer, causing reverse overload problems. Reverse overload increases the saturation of the operating core of the distribution transformer, causing the risk of transformer burning.

[0003] When managing a substation where a reverse heavy overload occurs, it is necessary to determine an appropriate management plan while taking the cost into consideration. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides a method, a device, an electronic device and a storage medium for managing reverse heavy overload in a rural area.

[0005] In order to solve one, part or all of the above technical problems, the technical solution adopted by the present invention is: A method for managing reverse heavy overload in rural areas, comprising: obtaining load forecast data of the rural areas and distributed photovoltaic forecast data for n years; constructing a reverse heavy overload management model with the goal of minimizing cost; constructing a photovoltaic power generation efficiency prediction model and a load ratio prediction model; solving the reverse heavy overload management model according to the photovoltaic power generation efficiency prediction model and the load ratio prediction model; and obtaining a reverse heavy overload management plan for the current area using the reverse heavy overload management model.

[0006] Furthermore, the reverse overload management model is: ,in The cost of expanding the capacity of distribution transformers is To control the terminal transformation cost for distributed photovoltaics, It is the loss of abandoned light.

[0007] Furthermore, , where i represents the i-th distribution transformer newly installed after the expansion of the distribution transformer in the substation area, is the cost of the i-th distribution transformer; , where U is the predicted number of households with distributed photovoltaic installed capacity; The cost of each control terminal; ,in is the average amount of abandoned light at time t, is the electricity price, n is the number of forecast years, and t is the accumulated time sequence number each year, measured in hours.

[0008] Furthermore, the constraints of the reverse overload management model are: , , , , ;in Forecasting installed capacity for distributed photovoltaics, is the average photovoltaic power generation efficiency at time t, is the average output ratio of the control at time t, P is the load forecast data, is the load ratio at time t, is the rated capacity of the distribution transformer after expansion; ,in is the rated capacity of the i-th distribution transformer; ; According to the photovoltaic power generation efficiency prediction model, Obtained according to the load ratio prediction model.

[0009] Furthermore, the method for constructing a photovoltaic power generation efficiency prediction model and a load ratio prediction model includes: collecting photovoltaic power generation efficiency historical data and load ratio historical data; constructing a SARIMA model for photovoltaic power generation efficiency prediction and load ratio prediction respectively, and the SARIMA model is expressed as ; Determined based on the historical data of photovoltaic power generation efficiency and load ratio and The SARIMA model is fitted to obtain the photovoltaic power generation efficiency prediction model and the load ratio prediction model.

[0010] Furthermore, the method for obtaining load forecast data and distributed photovoltaic forecast data includes: predicting the load data of the back-end area n years later based on the current load data of the area and the load growth curve of the area in recent years, and obtaining load forecast data; obtaining the average installed capacity per household based on the total installed capacity and number of installed households of distributed photovoltaics in the area; predicting the total installed capacity of the back-end area n years later based on the growth curve of the total installed capacity of distributed photovoltaics in recent years in the area, and obtaining the predicted installed capacity of distributed photovoltaics, and obtaining the predicted number of households of distributed photovoltaics based on the average installed capacity per household.

[0011] Furthermore, the photovoltaic power generation efficiency historical data includes: photovoltaic power generation efficiency data, weather data and noon sun altitude at each hour; the load ratio historical data includes maximum load, real-time load at each hour and weather data.

[0012] A device for managing reverse heavy overload in a rural substation includes an acquisition module, a construction module and a management module; the acquisition module is used to acquire load forecast data and distributed photovoltaic forecast data of the substation n years ago; the construction module is used to construct a reverse heavy overload management model with the goal of minimizing cost, to construct a photovoltaic power generation efficiency prediction model and a load ratio prediction model, and to solve the reverse heavy overload management model based on the photovoltaic power generation efficiency prediction model and the load ratio prediction model; the management module is used to use the reverse heavy overload management model to acquire a reverse heavy overload management plan for the current substation.

[0013] An electronic device includes a processor and a memory; the memory is used to store executable instructions, and the processor is used to execute the instructions to implement the management method.

[0014] A computer-readable storage medium stores instructions, and when the instructions are executed, the governance method is implemented.

[0015] Compared with the prior art, the present invention has the following beneficial effects: In the control method proposed in the present invention, a reverse heavy overload control model is constructed. The reverse heavy overload control model takes the minimum control cost as the goal while taking into account the abandoned light loss. The parameters include the cost of expanding the distribution transformer, the cost of modifying the control terminal to achieve flexible control of distributed photovoltaics, and the abandoned light loss. At the same time, the indicators such as the load of the distribution transformer not exceeding 80% are used as constraints for the reverse heavy overload control model. Therefore, the reverse heavy overload control model can be used to obtain the reverse heavy overload control plan for the current substation, the number of newly installed distribution transformers and the rated capacity of each newly installed distribution transformer when the distribution transformer is expanded, and the number of distributed photovoltaic control terminals installed.

[0016] The present invention refers to the growth curve of the total installed capacity of distributed photovoltaic power generation in the region in recent years and the load growth curve of the region in recent years, and obtains the load forecast data and distributed photovoltaic forecast data of the background area after n years, so that the reverse heavy overload management model can use the load forecast data and distributed photovoltaic forecast data. The present invention constructs a photovoltaic power generation efficiency prediction model and a load ratio prediction model based on the seasonal changes in photovoltaic output and load, combined with the historical data of photovoltaic power generation efficiency and the historical data of load ratio, which can realize the prediction of photovoltaic power generation efficiency and the prediction of load ratio, thereby providing data for the construction and solution of the reverse heavy overload management model. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The present invention is further described in detail below in conjunction with the accompanying drawings.

[0018] Figure 1 : Flow chart of embodiment 1 of the present invention; Figure 2 : A schematic diagram of Embodiment 2 of the present invention; Figure 3 : Schematic diagram of embodiment 3 of the present invention. DETAILED DESCRIPTION

[0019] In order to better understand the present invention, the content of the present invention is further clearly described below in conjunction with the embodiments and the accompanying drawings, but the protection content of the present invention is not limited to the following embodiments. In the following description, a large number of specific details are provided to provide a more thorough understanding of the present invention. However, it is obvious to those skilled in the art that the present invention can be implemented without one or more of these details.

[0020] Example 1: See Figure 1 The purpose of this embodiment is to provide a method for managing reverse overload in rural areas. The management method includes: Step S1, obtaining load forecast data and distributed photovoltaic forecast data for the background area for n years.

[0021] According to the current load data of the substation, refer to the load growth curve of the region in recent years, and predict the load data of the substation n years later to obtain the load forecast data. The value of n is 3-5.

[0022] According to the total installed capacity of distributed photovoltaics in the area and the number of households with installed capacity, the average installed capacity per household is obtained. At the same time, referring to the growth curve of the total installed capacity of distributed photovoltaics in the area in recent years, the total installed capacity of the background area after n years is predicted to obtain the predicted installed capacity of distributed photovoltaics, and the predicted number of households with distributed photovoltaics is obtained based on the average installed capacity per household.

[0023] Step S2, constructing a reverse overload management model with the goal of minimizing cost.

[0024] The first measure to deal with reverse overload is to expand the distribution transformer, and the second is to flexibly control the distributed photovoltaics to reduce the photovoltaic output. However, most of the rooftop photovoltaics in rural areas are currently connected to the grid in an unordered and blind manner, and cannot be regulated from the grid side. In order to achieve flexible control of distributed photovoltaics, it is necessary to install a control terminal for each household's distributed photovoltaics. At the same time, when the photovoltaic output is reduced, the light will be abandoned.

[0025] Based on the above situation, a reverse overload governance model is constructed ,in The cost of expanding the capacity of distribution transformers is To control the terminal transformation cost for distributed photovoltaics, The reverse heavy overload management model aims to minimize the management cost while taking into account the loss of abandoned light.

[0026] , where i represents the i-th distribution transformer newly installed after the expansion of the distribution transformer in the substation area, is the cost of the i-th distribution transformer, in RMB, including the transformer purchase cost, installation cost and operation and maintenance cost for n years.

[0027] , where U is the predicted number of households with distributed photovoltaic installed capacity; The cost of each control terminal, in Yuan, includes purchase cost, installation cost and operation and maintenance cost for n years.

[0028] ,in is the average amount of abandoned solar power at time t, in kWh; is the unit price of electricity, in RMB / kWh; n is the number of forecast years; t is the accumulated time sequence number each year, in hours.

[0029] The constraints of the reverse overload governance model are: , , , , .

[0030] In the constraints The predicted installed capacity of distributed photovoltaic power generation, in kW; is the average photovoltaic power generation efficiency at time t, is the average output ratio of the control at time t; P is the load forecast data, unit kW; is the load ratio at time t; It is the rated capacity of the distribution transformer after expansion, in kW.

[0031] ,in is the rated capacity of the i-th distribution transformer, in kW. and There is a corresponding relationship, which can be determined according to the current cost of transformers with different capacities.

[0032] .

[0033] Step S3, constructing a photovoltaic power generation efficiency prediction model and a load ratio prediction model.

[0034] Photovoltaic power generation efficiency is the ratio of real-time power generation to rated power, which is related to factors such as solar altitude and weather. However, in the same region, the changes in photovoltaic power generation efficiency at every moment of every day in different years are similar. Therefore, a photovoltaic power generation efficiency prediction model can be constructed based on historical data statistics. The photovoltaic power generation efficiency prediction model can be used to obtain photovoltaic power generation efficiency at different times of the year to apply to the calculation of the reverse overload management model. Similar to photovoltaic power generation efficiency, the load ratio is the ratio of real-time load to maximum load, which is related to factors such as season and weather. A load ratio prediction model can also be constructed based on historical data.

[0035] The photovoltaic power generation efficiency prediction model and load ratio prediction model are constructed using the seasonal autoregressive integrated moving average model (SARIMA).

[0036] The construction method of the photovoltaic power generation efficiency prediction model and the load ratio prediction model includes: S301. Collecting historical data on photovoltaic power generation efficiency and load ratio Collect historical data related to photovoltaic power generation efficiency in the current region, including photovoltaic power generation efficiency at each hour, weather conditions, etc., and calculate the noon sun altitude data based on the time corresponding to the data. Collect historical data related to load ratio in the current region or similar regions, including maximum load, real-time load at each hour, weather conditions, etc.

[0037] The historical data is then characterized and cleaned. During the characterization process, non-numerical data such as weather conditions are replaced with numerical values. For example, different weather types such as sunny, cloudy, and rainy are refined and replaced with numerical values.

[0038] When cleaning data, first remove missing values ​​and outliers, and then normalize the remaining data.

[0039] S302, constructing SARIMA models for photovoltaic power generation efficiency prediction and load ratio prediction respectively.

[0040] The SARIMA model can be expressed as , where p is the order of the nonseasonal autoregressive term, d is the order of the nonseasonal difference, q is the order of the nonseasonal moving average term, P is the order of the seasonal autoregressive term, D is the order of the seasonal difference, Q is the order of the seasonal moving average term, and m is the length of the seasonal cycle.

[0041] Based on the historical data of photovoltaic power generation efficiency and load ratio, the autocorrelation diagram and partial autocorrelation diagram are used to assist in determining and Automated methods such as AIC (Akaike Information Criterion) can also be used to determine the optimal parameters.

[0042] The SARIMA model is then fitted using the selected parameters, which can be done using statistical software or programming languages ​​such as the statsmodels library in Python.

[0043] After fitting, the photovoltaic power generation efficiency prediction model and load ratio prediction model are obtained. At the same time, the autocorrelation of the model residuals is checked to ensure that the model can fully capture the information in the data.

[0044] Step S4, solving the reverse heavy overload control model according to the photovoltaic power generation efficiency prediction model and the load ratio prediction model.

[0045] According to the photovoltaic power generation efficiency prediction model and the load ratio prediction model, the predicted values ​​of photovoltaic power generation efficiency and load ratio at different times can be obtained, that is, and . Then the heavy overload management model is solved.

[0046] Step S5, using the reverse heavy overload management model to obtain the reverse heavy overload management plan for the current substation.

[0047] The reverse overload control model is used to obtain the reverse overload control plan for the current substation. The plan includes the number of newly installed distribution transformers and the rated capacity of each newly installed distribution transformer when the distribution transformer is expanded, as well as the number of distributed photovoltaic control terminals installed.

[0048] Example 2: See Figure 2 The purpose of this embodiment is to provide a device for managing reverse overload in rural areas, which is used to perform the management method of embodiment 1. The management device 200 includes: an acquisition module 201, a construction module 202 and a management module 203.

[0049] The acquisition module 201 is used to acquire the load forecast data and distributed photovoltaic forecast data of the background area for n years. In combination with Embodiment 1, the acquisition module 201 is used to execute step S1.

[0050] The construction module 202 is used to construct a reverse heavy overload management model with the minimum cost as the goal, to construct a photovoltaic power generation efficiency prediction model and a load ratio prediction model, and to solve the reverse heavy overload management model according to the photovoltaic power generation efficiency prediction model and the load ratio prediction model. In combination with Example 1, the construction module 202 is used to execute steps S2-S4.

[0051] The management module 203 is used to obtain the reverse heavy overload management plan of the current area by using the reverse heavy overload management model. In combination with Embodiment 1, the management module 202 is used to execute step S5.

[0052] Regarding the device in this embodiment, the specific manner in which each unit or module performs operations has been described in detail in Example 1 and will not be elaborated here.

[0053] Those skilled in the art should understand that for the convenience and simplicity of description, the present application only uses the division of the above-mentioned functional modules or units as examples in the device embodiments. In actual applications, the above-mentioned functions can be assigned to different functional modules or units as needed, that is, the internal structure of the device can be divided into different functional modules or units to complete all or part of the functions described above.

[0054] Example 3: See Figure 3 The purpose of this embodiment is to provide an electronic device 300, including at least one processor 301 and one or more memories 302 for storing executable instructions of the processor 301. The processor 301 is used to execute the instructions in the memory 302 to implement the governance method described in Example 1.

[0055] It should be noted that the electronic device 300 may be a desktop computer, a portable computer, a network server, a mobile phone, a tablet computer, a wireless terminal, an embedded device, a chip system or a Figure 3 In addition, Figure 3 The components shown in the figure do not constitute a limitation on the terminal device, except Figure 3 In addition to the components shown, the electronic device 300 may include more or fewer components than shown, or combine certain components, or arrange the components differently.

[0056] Embodiment 4: The purpose of this embodiment is to provide a computer-readable storage medium.

[0057] All or part of the processes in the above method embodiments can be completed by computer instructions to instruct relevant hardware. The program can be stored in the computer-readable storage medium. When the program is executed, it can implement the governance method described in Example 1.

[0058] The computer-readable storage medium may be an internal storage unit of the electronic device of Example 3, such as a hard disk or a memory. The computer-readable storage medium may also be an external storage device of the electronic device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. Further, the computer-readable storage medium may also include both an internal storage unit and an external storage device of the above-mentioned electronic device. The computer-readable storage medium is used to store computer programs and other programs and data required by the electronic device. The computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.

[0059] In conjunction with the several embodiments provided in this application, it should be understood that the provided devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the assessment of the modules or units is only a logical function assessment. There may be other assessment methods in actual implementation, such as multiple modules or units or components can be combined or integrated into another device, or some features can be ignored or not executed.

[0060] In addition, in the embodiment of the device of the present application, each functional module or unit can be integrated into one unit, or each module or unit can exist physically separately, or two or more modules or units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional modules.

[0061] If the above-mentioned integrated unit is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard drives, ROM, RAM, magnetic disks or optical disks.

[0062] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Other modifications or equivalent substitutions made to the technical solution of the present invention by ordinary technicians in the field should be included in the scope of the claims of the present invention as long as they do not depart from the spirit and scope of the technical solution of the present invention.

Claims

1. A method for managing reverse overload in rural areas, characterized in that: include: Obtain the load forecast data and distributed photovoltaic forecast data of the background area for n years; Construct a reverse overload governance model with the goal of minimizing costs; Construct photovoltaic power generation efficiency prediction model and load ratio prediction model; Solve the reverse heavy overload control model based on the photovoltaic power generation efficiency prediction model and the load ratio prediction model; The reverse heavy overload management model is used to obtain the reverse heavy overload management plan for the current substation.

2. The method for controlling reverse overload in rural areas according to claim 1 is characterized in that: The reverse heavy overload management model is: ,in The cost of expanding the capacity of distribution transformers is To control the terminal transformation cost for distributed photovoltaics, It is the loss of abandoned light.

3. The method for controlling reverse overload in rural areas according to claim 2 is characterized in that: , where i represents the i-th distribution transformer newly installed after the expansion of the distribution transformer in the substation area, is the cost of the i-th distribution transformer; , where U is the predicted number of households with distributed photovoltaic installed capacity; The cost of each control terminal; ,in is the average amount of abandoned light at time t, is the electricity price, n is the number of forecast years, and t is the accumulated time sequence number each year, measured in hours.

4. The method for treating reverse overload in rural areas according to claim 3 is characterized in that: The constraints of the reverse overload governance model are: , , , , ;in Forecasting installed capacity for distributed photovoltaics, is the average photovoltaic power generation efficiency at time t, is the average output ratio of the control at time t, P is the load forecast data, is the load ratio at time t, is the rated capacity of the distribution transformer after expansion; ,in is the rated capacity of the i-th distribution transformer; ； According to the photovoltaic power generation efficiency prediction model, Obtained according to the load ratio prediction model.

5. The method for treating reverse overload in rural areas according to claim 1, characterized in that: The method of constructing a photovoltaic power generation efficiency prediction model and a load ratio prediction model includes: Collect historical data on photovoltaic power generation efficiency and load ratio; SARIMA models are constructed for photovoltaic power generation efficiency prediction and load ratio prediction respectively. The SARIMA model is expressed as ; Determined based on the historical data of photovoltaic power generation efficiency and load ratio and The value of The SARIMA model was fitted respectively to obtain the photovoltaic power generation efficiency prediction model and the load ratio prediction model.

6. The method for treating reverse overload in rural areas according to claim 1, characterized in that: Methods for obtaining load forecast data and distributed photovoltaic forecast data include: According to the current load data of the substation and the load growth curve of the region in recent years, the load data of the substation in the next n years is predicted to obtain the load forecast data; According to the total installed capacity of distributed photovoltaics in the area and the number of households with installed capacity, the average installed capacity per household is obtained; according to the growth curve of the total installed capacity of distributed photovoltaics in the area in recent years, the total installed capacity of the background area after n years is predicted to obtain the predicted installed capacity of distributed photovoltaics, and the predicted number of households with installed capacity of distributed photovoltaics is obtained based on the average installed capacity per household.

7. The method for treating reverse overload in rural areas according to claim 5, characterized in that: The photovoltaic power generation efficiency historical data includes: photovoltaic power generation efficiency data, weather data and noon sun altitude at each hour; the load ratio historical data includes maximum load, real-time load at each hour and weather data.

8. A device for treating reverse overload in rural areas, characterized in that: Includes acquisition module, construction module and governance module; The acquisition module is used to acquire load forecast data and distributed photovoltaic forecast data in the background area for n years; The construction module is used to construct a reverse heavy overload management model with the goal of minimizing cost, to construct a photovoltaic power generation efficiency prediction model and a load ratio prediction model, and to solve the reverse heavy overload management model according to the photovoltaic power generation efficiency prediction model and the load ratio prediction model; The management module is used to obtain the reverse heavy overload management plan of the current area by using the reverse heavy overload management model.

9. An electronic device, characterized in that: It comprises a processor and a memory; the memory is used to store executable instructions, and the processor is used to execute the instructions to implement the governance method described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The readable storage medium stores instructions, which, when executed, implement the governance method described in any one of claims 1-7.

Images