A method, device and medium for improving the ability of a substation to absorb distributed photovoltaic energy

Abstract

The present invention belongs to the field of power supply technology, and provides a method, device and medium for improving the ability of a substation to absorb distributed photovoltaic energy, including collecting the load node power in the substation, the external load of the substation, the energy storage charging and discharging power, the load obtained from the power grid and the photovoltaic power generation information in the substation through the local management module of each substation, and uploading them to the centralized control station; establishing a load prediction model and a photovoltaic output prediction model in the centralized control station; each substation collects m load power values ​​and weather data every day, and brings them into the load prediction model for calculation; the distributed photovoltaic power source in each substation collects m historical data every day, and brings them into the photovoltaic output prediction model of the substation for calculation. The application of this method can help solve the problems caused by the randomness and intermittency of new energy power generation, improve the ability of the distribution substation to absorb local distributed photovoltaic power, and contribute to the sustainable development of the power system.

Description

Technical Field

[0001] The present invention belongs to the field of electric power technology, and specifically relates to a method, a device and a medium for improving the ability of a substation to absorb distributed photovoltaic energy. Background Art

[0002] As the work of "carbon peak and carbon neutrality" advances, distribution substations need to absorb more distributed photovoltaic energy. Distributed photovoltaic power generation specifically refers to a distributed power generation system that uses photovoltaic modules to directly convert solar energy into electrical energy. The output of photovoltaic distributed power sources is closely related to natural conditions such as the real-time intensity of local solar radiation, and has obvious intermittent and volatile characteristics.

[0003] In actual work, it is necessary not only to ensure that distributed power sources are connected to the grid in an orderly, safe and reliable manner, but also to improve the capacity of distributed photovoltaic energy consumption. At present, most existing studies only evaluate the maximum static capacity level of distributed power sources in distribution network areas based on certain focuses, lacking guidance methods for improving the capacity of distributed photovoltaic energy consumption in the entire area, and are not universal, which will lead to the inability of some areas to fully consume photovoltaic energy, resulting in a waste of electricity. Summary of the invention

[0004] In order to solve the above technical problems, the present invention provides a method, a device and a medium for improving the ability of a substation to absorb distributed photovoltaic energy.

[0005] The technical solution of the present invention is: a method for improving the ability of a substation to absorb distributed photovoltaic energy, comprising the following steps:

[0006] (1) Through the local management module of each substation, the load node power in the substation, the load transmitted from the substation, the energy storage charging and discharging power, the load obtained from the grid and the photovoltaic power generation power information are collected and uploaded to the centralized control station; the acquired data satisfies the following formula:

[0007] P L +P D_O =P ES +P D_I +P pv (1)

[0008] Among them, P L is the standard traditional load in the area; P D_O It is the power transmitted from the substation. When the output of distributed photovoltaic or energy storage is greater than P L When P D_O Greater than 0, otherwise equal to 0; P ES It is the energy storage in the station area. It is negative when charging, positive when discharging, and 0 when not working. D_I It is the power source obtained from the power grid side of the distribution station area; P pvis the distributed photovoltaic power generation power;

[0009] (2) Establish a load forecasting model and a photovoltaic output forecasting model for the substation at the centralized control station;

[0010] (3) According to the load prediction model and the photovoltaic output prediction model in step (2), the predicted value of the load and photovoltaic output of each substation on the next day are predicted. At the same time, combined with formula (1) in step (1), P is calculated according to the predicted value. L，t and P pv，t , P L，t is the standard traditional load at time point t, P pv，t is the distributed photovoltaic power generation power at time point t;

[0011] At the same time point, when P L，t ≥P pv，t When , it means that the distributed photovoltaic power in the area can be consumed normally, and the process ends;

[0012] When P L，t <P pv，t When , it means that the normal load in the substation cannot fully absorb the distributed photovoltaic power, and the substation absorption capacity needs to be improved, then go to step (4);

[0013] (4) Take the following measures to consume excess photovoltaic power, including absorbing excess power by charging energy storage devices; absorbing excess power by increasing the load of charging piles; using flexible interconnected substations and centralized control stations to coordinate with substations with high load demand to absorb excess distributed photovoltaic power in substations;

[0014] Through the above measures, if the distributed photovoltaic power is completely absorbed, the process ends; if there is excess distributed photovoltaic power, the process proceeds to step (5).

[0015] (5) Send excess electricity back for sale online.

[0016] Preferably, in step (2), historical load data of each load node in the substation is collected, and the substation collects m load power values ​​every day, where m is a natural number greater than 0, as the load vector data for one day, and weather data is added as a feature vector to train the load prediction model;

[0017] The historical data of each distributed photovoltaic power source in the substation area is collected to form a training vector. The distributed photovoltaic power sources in the substation area also collect historical data m times a day to train the photovoltaic output prediction model of the substation area.

[0018] Preferably, in step (2), the historical data of the distributed photovoltaic power source includes light intensity, weather problems, and distributed photovoltaic power source output data.

[0019] Preferably, in step (2), the load forecasting model and the distributed photovoltaic output forecasting model are trained by using the LS TM deep learning model.

[0020] Preferably, in step (4), when there is a surplus of distributed photovoltaic power, the charging price is lowered to encourage new energy vehicles to use electricity, increase the load of charging piles, and thus absorb more electricity.

[0021] Preferably, the data collected in step (1) should be within the safety constraint information, which includes maximum capacity information, distribution station area transformer capacity information and area line capacity information.

[0022] Preferably, the method also includes analyzing the substations that perform long-term power feedback through monitoring data, and adjusting the load connected to the distribution substation, thereby increasing the upper limit of the static absorption capacity of distributed photovoltaic power in the distribution substation.

[0023] Preferably, the method for adjusting the load connected to the distribution station area includes: connecting more power loads, adjusting the grid structure of the station area, or connecting the power loads of adjacent stations with high load rates and no distributed photovoltaic power sources to absorb them.

[0024] A computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the method for improving the capacity of a substation to absorb distributed photovoltaic energy is implemented based on any one of the above items.

[0025] A computer-readable storage medium is also provided, on which a computer program is stored, wherein when the computer program is executed by a processor, the method for improving the ability of a substation to absorb distributed photovoltaic energy is based on any of the above-mentioned items.

[0026] The beneficial effects of the present invention are:

[0027] (1) The distribution station area can independently control the load of the control station area according to the strategy of the centralized control station, thereby improving the ability to absorb photovoltaic power;

[0028] (2) The distribution substation can coordinate with other substations to absorb distributed photovoltaic power through flexible interconnection devices based on the strategy of the centralized control station;

[0029] (3) Based on the long-term distributed photovoltaic power transmission area, optimization and transformation can be carried out to improve its upper limit capacity of distributed photovoltaic power consumption;

[0030] The application of this method can help solve the problems caused by the randomness and intermittency of renewable energy generation, improve the local distributed photovoltaic power absorption capacity of distribution station areas, and contribute to the sustainable development of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 It is the overall structure diagram of the system of the present invention,

[0032] Figure 2 is a flow chart of the method of the present invention. DETAILED DESCRIPTION

[0033] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0034] This embodiment provides an operation method of a system for improving the ability of a substation to absorb distributed photovoltaic energy.

[0035] See also Figure 1 The operation of the system is based on several local management modules and a centralized control station; the local management module is set in each substation, including equipment management components, data acquisition components and strategy execution components; the centralized control station includes equipment management components, substation management components, model training components, load management components and strategy control components. The local management modules and centralized control stations are both existing mature equipment, and the specific working methods will not be repeated here.

[0036] See also Figure 2 , the operation method includes the following steps:

[0037] (1) Through the local management module of each substation, the load node power in the substation, the load transmitted from the substation, the energy storage charging and discharging power, the load obtained from the grid and the photovoltaic power generation power information are collected and uploaded to the centralized control station; the acquired data satisfies the following formula:

[0038] P L +P D_O =P ES +P D_I +P pv (1)

[0039] Among them, P L is the standard traditional load in the area; P D_O It is the power transmitted from the substation. When the output of distributed photovoltaic or energy storage is greater than P L When P D_O Greater than 0, otherwise equal to 0; P ES It is the energy storage in the station area. It is negative when charging, positive when discharging, and 0 when not working. D_I It is the power source obtained from the power grid side of the distribution station area; P pv is the distributed photovoltaic power generation power;

[0040] At the same time, the collected data should be within the safety constraint information, which includes the maximum capacity information, the transformer capacity information of the distribution area, and the line capacity information of the distribution area. That is, the collected value at the time of operation cannot exceed the maximum value.

[0041] (2) At the centralized control station, a load forecasting model and a distributed photovoltaic output forecasting model are established and trained by using the LSTM deep learning model;

[0042] Collect historical load data of each load node in the substation. The substation collects load power values ​​96 times every 15 minutes as the load vector data for the day. At the same time, weather data is added as the feature vector to train the load forecasting model.

[0043] The historical data of each distributed photovoltaic power source in the substation area is collected to form a training vector, including light intensity, weather problems, and distributed photovoltaic power output data. The distributed photovoltaic power sources in the substation area collect historical data 96 times a day every 15 minutes to train the photovoltaic output prediction model of the substation area; if there is no distributed photovoltaic power source in a substation area, the photovoltaic output model will not be trained;

[0044] (3) According to the load prediction model and the photovoltaic output prediction model in step (2), the predicted value of the load and photovoltaic output of each substation on the next day are predicted. At the same time, combined with formula (1) in step (1), P is calculated according to the predicted value. L，t and P pv，t , P L，t is the standard traditional load at time point t, and P pv，t Distributed photovoltaic power generation power at time point t;

[0045] At the same time point, when P L，t ≥P pv，t When , it means that the distributed photovoltaic power in the substation can be consumed normally, then it ends, that is, the consumed power load is greater than the photovoltaic power generation load, so the photovoltaic power generation connected in the substation can be fully used;

[0046] When P L，t <P pv，t When , it means that the normal load in the substation cannot fully absorb the distributed photovoltaic power, and the substation absorption capacity needs to be improved. That is, the photovoltaic power generation is in excess and the substation cannot fully absorb it, then go to step (4);

[0047] (4) Take the following measures to consume excess photovoltaic power, including charging energy storage devices to absorb excess power, and when the photovoltaic output ends, the energy storage devices are discharged as a power source;

[0048] Absorb excess electricity by increasing the load of charging piles, for example, by lowering charging prices, encouraging new energy vehicles to use electricity, and increasing the load of charging piles, thereby absorbing more electricity;

[0049] By using the flexible interconnected substations, the central control station coordinates with the substations with high load demand to absorb the excess distributed photovoltaic power. Specifically, according to the prediction analysis, when a distributed photovoltaic power reverse transmission occurs in a certain substation, the central control station selects the substation that can be connected through the flexible interconnection device (FID), and selects the substation with high predicted load rate to coordinate and absorb the excess power first;

[0050] Through the above measures, if the distributed photovoltaic power is completely absorbed, the process ends; if there is excess distributed photovoltaic power, the process proceeds to step (5).

[0051] (5) Send excess electricity back for sale online.

[0052] It also includes analyzing the long-term power feedback of substations through monitoring data, adjusting the grid structure of the substation by connecting more power loads, or connecting the power loads of adjacent substations with high load rates and no distributed photovoltaic power sources to absorb them, thereby increasing the upper limit of the static absorption capacity of distributed photovoltaic power generation in the distribution station area.

[0053] This embodiment provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it is based on the above-mentioned method for improving the ability of a substation to absorb distributed photovoltaic energy.

[0054] This embodiment also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, it is based on the above-mentioned method for improving the ability of the substation to absorb distributed photovoltaic energy.

[0055] The distribution substation of the present invention can autonomously control the load increase of the substation according to the strategy of the centralized control station, thereby improving the ability to absorb photovoltaic power; the distribution substation can cooperate with other substations to absorb distributed photovoltaic power through the substation flexible interconnection device according to the strategy of the centralized control station; the substation that has been feeding back distributed photovoltaic power for a long time can be optimized and transformed to improve its upper limit capacity of absorbing distributed photovoltaic power;

[0056] The application of this method can help solve the problems caused by the randomness and intermittency of renewable energy generation, improve the local distributed photovoltaic power absorption capacity of distribution station areas, and contribute to the sustainable development of the power system.

[0057] The present invention is not limited to the above-mentioned embodiments. On the basis of the technical solution disclosed in the present invention, technicians in this field can make some substitutions and deformations to some technical features therein according to the disclosed technical content without creative labor, and these substitutions and deformations are all within the protection scope of the present invention.

Claims

1. A method for improving the ability of a substation to absorb distributed photovoltaic energy, characterized in that: The following steps are involved: 1) Through the local management module of each substation, collect the load node power in the substation, the external load of the substation, the energy storage charging and discharging power, the load obtained from the power grid and the photovoltaic power generation power information of the substation and upload them to the centralized control station; the acquired data satisfies the following formula: P L +P D_O =P ES +P D_I +P pv (1) Among them, P L is the standard traditional load in the area; P D_O It is the power transmitted from the substation. When the output of distributed photovoltaic or energy storage is greater than P L When P D_O Greater than 0, otherwise equal to 0; P ES It is the energy storage in the station area. It is negative when charging, positive when discharging, and 0 when not working. D_I It is to obtain electric energy from the grid side of the distribution station area; P pv is the distributed photovoltaic power generation power; 2) Establish load forecasting model and photovoltaic output forecasting model in the centralized control station; 3) According to the load prediction model in step 2) and the photovoltaic output prediction model of the substation, the predicted value of the load and photovoltaic output of each substation on the next day are predicted. At the same time, combined with formula (1) in step 1), P is obtained according to the predicted value. L，t and P pv，t , P L，t is the standard traditional load at time point t, P pv，t is the distributed photovoltaic power generation power at time point t; At the same time point, when P L，t ≥P pv，t When , it means that the distributed photovoltaic power in the area can be consumed normally, and the process ends; When P L，t <P pv，t When the normal load in the substation cannot fully absorb the distributed photovoltaic power, it is necessary to improve the substation's absorption capacity, then go to step 4); 4) Take the following measures to consume excess photovoltaic power, including absorbing excess power by charging energy storage devices; absorbing excess power by increasing the load of charging piles; using flexible interconnected substations and centralized control stations to coordinate with substations with high load demand to absorb excess distributed photovoltaic power in substations; Through the above measures, if the distributed photovoltaic power is fully absorbed, the process ends; if there is excess distributed photovoltaic power, the process proceeds to step 5). 5) Send excess electricity back for sale online; The data collected in step 1) should be within the safety constraint information, which includes maximum capacity information, transformer capacity information of distribution substation area and line capacity information of substation area; In step 2), the historical load data of each load node in the substation is collected. The substation collects m load power values ​​every day, where m is a natural number greater than 0, as the load vector data for one day. At the same time, weather data is added as a feature vector to train the load forecasting model. The historical data of each distributed photovoltaic power source in the substation area is collected to form a training vector. The distributed photovoltaic power sources in the substation area also collect historical data m times a day to train the photovoltaic output prediction model of the substation area. The historical data of the distributed photovoltaic power source, including light intensity, weather problems, and distributed photovoltaic power source output data; It also includes analyzing the long-term power transmission areas through monitoring data, and adjusting the load connected to the distribution area to increase the upper limit of the static absorption capacity of distributed photovoltaic power distribution areas; The method for adjusting the load connected to the distribution station area includes: connecting more power loads, adjusting the grid structure of the station area, or connecting the power loads of adjacent stations with high load rates and no distributed photovoltaic power sources.

2. A method for improving the ability of a substation to absorb distributed photovoltaic energy according to claim 1, characterized in that: In step 2), the load forecasting model and distributed photovoltaic output forecasting model are trained by using the LS TM deep learning model.

3. The method for improving the distributed photovoltaic energy consumption capacity of a substation according to claim 1 is characterized in that: In step 4), when there is a surplus of distributed photovoltaic power, the charging price is lowered to encourage new energy vehicles to use electricity, increase the load of charging piles, and thus absorb more electricity.

4. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, it implements the method for improving the ability of a substation to absorb distributed photovoltaic energy based on any one of claims 1 to 3.

5. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for improving the ability of a substation to absorb distributed photovoltaic energy as described in any one of claims 1 to 3 is implemented.

Images