Method and device for distributed energy storage control of photovoltaic system

Abstract

The invention is suitable for the field of electric energy dynamic balance and distributed energy storage control, and provides a method and a device for distributed energy storage control of a photovoltaic system. Predicting respective output data of a flexible electrical load, a photovoltaic system and an energy storage system in the DC micro-grid; matching an operation regulation and control strategy of the current DC micro-grid in a preset strategy library according to the output data, and enabling the DC micro-grid to maintain electric energy dynamic balance; based on a big data technology, mining key composition equipment of the DC micro-grid, and obtaining market update data of all the key composition equipment to make a sample set; according to the method, the output of the DC micro-grid can be predicted according to the acquired related data, and whether the equipment with low updating cost is subjected to overclocking use or not is judged through the preset economical efficiency analysis model, namely the equipment updating evaluation model, so that the power supplement of the AC power distribution network is reduced.

Description

Technical Field

[0001] The present invention belongs to the field of electric energy dynamic balance and distributed energy storage control, and in particular, relates to a method and device for distributed energy storage control of a photovoltaic system. Background Art

[0002] PV-storage-direct-flexible refers to the integration of photovoltaics, energy storage, DC distribution systems and flexible power loads on the basis of DC distribution. It aims to solve the problem of scarce flexibility resources and grid-load time-space mismatch faced by the power system under the high penetration of renewable energy, and promote the grid's renewable energy absorption capacity. PV-storage-direct-flexible building distribution is a special form of DC distribution; the development of PV-storage-direct-flexible buildings can make full use of various energy flexibility resources such as distributed renewable energy, energy storage (electricity storage, cold storage, heat storage) and flexible power loads in buildings, so that the power system and building users can obtain considerable economic benefits, and improve the safety, stability and reliability of the power system, while reducing carbon emissions in the whole society.

[0003] For the power system, the photovoltaic storage direct-flexible building can reduce the peak-to-valley difference of power load by making full use of the various energy flexibility resources in the building, which is of great significance to the power system. First, it can reduce or postpone the construction of peak-shaving power plants and transmission and distribution (T&D) infrastructure to meet the annual peak load of less than 100 hours, and avoid the investment and operation and maintenance costs of the newly added power peak-shaving infrastructure; secondly, it helps to improve the efficiency of existing thermal power generating units, thereby reducing energy consumption and reducing power generation costs; finally, it helps to improve the safety, stability and reliability of the power system and improve the quality of power supply.

[0004] For building users, on the one hand, the photovoltaic storage direct flexible building can utilize the bidirectional charging and discharging electric vehicles, energy storage (battery energy storage, cold storage, heat storage) and other resources in the building to store excess electricity when photovoltaic power generation is in excess, or use photovoltaic power generation to drive cold storage and heat storage devices to store cold and heat to indirectly store electricity, and release the stored electricity or cold and heat when photovoltaic power generation is insufficient, reducing the municipal electricity demand of the building and saving operating electricity costs. On the other hand, the flexible power load, bidirectional charging and discharging electric vehicles, and energy storage (battery energy storage, cold storage, heat storage) resources in the building can be used to participate in power demand response and power market transactions when the power system needs it, and obtain considerable economic benefits. The photovoltaic storage direct flexible system can also be used as a backup power source for the building, providing reliable power supply guarantee for the building when the municipal power grid is out of power, enriching the flexibility and selectivity of power supply.

[0005] However, the power of the photovoltaic power generation system, DC power load and energy storage system in the photovoltaic-storage-direct-flexible system changes in real time. Each system is interconnected through a DC distribution system and connected to an external AC distribution network. How to make the distributed energy storage capacity adapt to the capacity of the photovoltaic power generation system and the power load in different seasons is a difficult point in system control. Therefore, designing a control strategy that can coordinate and control the dynamic balance of electric energy between the photovoltaic power generation system (i.e., photovoltaic system), the energy storage system and the power load is the key to ensuring the stable and safe operation of the photovoltaic-storage-direct-flexible system. Summary of the invention

[0006] An object of the present invention is to provide a method and device for distributed energy storage control in a photovoltaic system to solve at least one of the defects mentioned in the background art.

[0007] The first aspect of the present invention is achieved by providing a method for distributed energy storage control of a photovoltaic system, the method comprising: The power efficiency prediction model established based on the DC microgrid topology structure is used to predict the output data of the flexible power load, photovoltaic system, and energy storage system in the DC microgrid. According to the output data, the operation and control strategy of the current DC microgrid is matched in the preset strategy library, so that the DC microgrid maintains a dynamic balance of electric energy; Based on big data technology, the key components of the DC microgrid are mined, and the market update data of all key components are obtained to form a sample set, so as to train the migrated deep learning model through the sample set to obtain an equipment update evaluation model; The equipment update evaluation model is used to periodically predict and sort the update costs of all key component equipment, and the control priority is set according to the sorting results; The output power of the photovoltaic system, the demand power of the flexible power load, and the charging and discharging power of the energy storage system are monitored in real time, and the current operation and control strategy is adjusted according to the monitoring results and the control priority.

[0008] Furthermore, the method also includes: pre-establishing an electric energy efficiency prediction model based on the controlled DC microgrid topology structure; wherein the DC microgrid includes flexible power loads, photovoltaic systems, and energy storage systems interconnected through a DC distribution network, and the DC distribution network can be connected to an AC distribution network.

[0009] The step of pre-establishing the electric energy efficiency prediction model specifically includes: Determine the topology of the DC microgrid according to the controlled DC microgrid; Mirroring the topology through simulation software; Set the constraints and objective function of the model to obtain the energy efficiency evaluation model; The objective function is to minimize the output of the AC distribution network when the flexible power load is met; the constraints are configured as follows: The power generation of the photovoltaic system is are the minimum power generation and maximum power generation of the photovoltaic system, respectively. The loss between the power generation of the photovoltaic system and the output power of the photovoltaic system is negligible. The capacity of the energy storage system is are the minimum and maximum capacities of the energy storage system respectively.

[0010] Furthermore, the method further includes: in the preset strategy library, at least configuring as follows: The first operation control strategy: hour, , at this time the energy storage system is charged; The second operation and control strategy: hour, , at this time the energy storage system discharges; The third operation and control strategy: hour, ,At this time, the energy storage system discharges and the AC distribution network replenishes power; in, Represents the output power of the photovoltaic system, Indicates the required power of the flexible power load, Represents the charging and discharging power of the energy storage system, Indicates the output power supplemented by the AC distribution network.

[0011] Furthermore, after the step of matching the operation and control strategy of the current DC microgrid in the preset strategy library according to the output data, the method further includes: Input the matching operation control strategy into the simulation software for secondary optimization; The results of the secondary optimization are systematically evaluated through simulation software; the evaluated capacity optimization configuration results are output and executed to improve the control smoothness when maintaining the dynamic balance of electric energy; Among them, the systematic evaluation includes technical indicators, environmental indicators and economic indicators.

[0012] Furthermore, the step of mining the key components of the DC microgrid based on big data technology and obtaining the market update data of all key components to prepare a sample set specifically includes: Identify all components of the DC microgrid; Based on big data technology, obtain a reference table of the electricity cost of all component equipment, which at least includes equipment price, maintenance rate or replacement rate; According to the electricity cost, the electricity cost reference table is sorted according to the cost, and the first n devices in the sorting are defined as key component devices, where n is a natural number; Obtain the market prices and price change rates of all key component equipment, obtain market update data, and make the market update data into a sample set.

[0013] Furthermore, in the step of real-time monitoring the output power of the photovoltaic system, the demand power of the flexible power load, and the charging and discharging power of the energy storage system, the method also includes: storing the power consumption records of the flexible power load to analyze the abnormal power consumption of the flexible power load and provide power saving suggestions.

[0014] A second aspect of the present invention is a device for distributed energy storage control of a photovoltaic system, the device being used in the method described, the device comprising: a microgrid output prediction unit, a control strategy matching unit, an update cost evaluation unit, a control parameter setting unit, and a control optimization unit; The microgrid output prediction unit is used to predict the output data of the flexible power load, photovoltaic system and energy storage system in the DC microgrid through an electric energy effectiveness prediction model established based on the DC microgrid topology structure; The control strategy matching unit is used to match the operation control strategy of the current DC microgrid in a preset strategy library according to the output data, so that the DC microgrid maintains a dynamic balance of electric energy; The update cost evaluation unit is used to mine the key components of the DC microgrid based on big data technology, and obtain the market update data of all key components to form a sample set, so as to train the migrated deep learning model through the sample set to obtain an equipment update evaluation model; The control parameter setting unit is used to periodically predict and sort the update costs of all key component devices through the device update evaluation model, and set the control priority according to the sorting result; The control optimization unit is used to monitor the output power of the photovoltaic system, the demand power of the flexible power load, and the charging and discharging power of the energy storage system in real time, and adjust the current operation control strategy according to the monitoring results and the control priority.

[0015] Furthermore, the device also includes: A control strategy optimization unit is used to input the matching operation control strategy into the simulation software for secondary optimization; The optimization result processing unit is used to systematically evaluate the results of the secondary optimization through simulation software; output the evaluated capacity optimization configuration results and execute them to improve the control smoothness when maintaining the dynamic balance of electric energy.

[0016] According to a third aspect of the present invention, a computer device comprises a processor and a memory, wherein the memory stores a computer program, and the processor implements the steps of the method when executing the computer program.

[0017] A fourth aspect of the present invention is a storage medium having a computer program stored thereon, wherein the computer program implements the steps of the method when executed by a processor.

[0018] The present invention provides a method for distributed energy storage control of a photovoltaic system. The method can predict the output of a DC microgrid based on the acquired relevant data, and through a preset economic analysis model, namely, an equipment update evaluation model, determine whether to use over-limit or over-frequency equipment with low update costs, reduce the power supplement of the AC distribution network, maximize the use of the photovoltaic system or the energy storage system, improve the power balancing capability, and ensure the control stability, robustness and accuracy of the microgrid; at the same time, the DC microgrid can utilize the easy-to-control characteristic of DC to construct a DC distribution network to which different types of power sources, energy storage and power-consuming equipment can be flexibly connected and adjusted, actively adjust the demand side response of the power grid through flexible power loads, and enhance the convenience, dynamism and initiative of users in participating in energy management. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 A flow chart of a method for distributed energy storage control of a photovoltaic system provided by an embodiment of the present invention; Figure 2 is a first sub-flow chart of an embodiment of the present invention; Figure 3 is a second sub-flow chart of an embodiment of the present invention; Figure 4 is a third sub-flow chart of an embodiment of the present invention; Figure 5 A structural block diagram of a device for distributed energy storage control of a photovoltaic system provided by an embodiment of the present invention; Figure 6 Another structural block diagram of a device for distributed energy storage control of a photovoltaic system provided by an embodiment of the present invention; Figure 7 It is a block diagram of the internal structure of the update cost evaluation unit in an embodiment of the present invention; Figure 8 A schematic diagram of the connection of various devices in a DC microgrid in one embodiment; Fig. 9 A control flow chart of a device for distributed energy storage control of a photovoltaic system in one embodiment; Fig.10 A block diagram of the internal structure of a computer device provided by an embodiment. DETAILED DESCRIPTION

[0020] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0021] Figure 1 A flow chart of a method for distributed energy storage control of a photovoltaic system provided in an embodiment of the present invention may specifically include the following steps: S101: Predict the output data of the flexible power load, photovoltaic system and energy storage system in the DC microgrid through the power efficiency prediction model established based on the DC microgrid topology structure; In this step, the connection method of each device in the DC microgrid can refer to Figure 8 As shown, multiple users (such as charging piles, air conditioners, household appliances (such as lighting lamps, televisions, refrigerators, sockets, etc. that are suitable for 220V DC)) can be interconnected by low-voltage DC busbars (DC), and equipped with corresponding power metering devices, which can be DC meters, to achieve statistics on power generation and power consumption. Photovoltaic panels are laid on the roofs of each user's building and are configured with reasonable energy storage. The photovoltaic power generation and energy storage units are directly connected to the low-voltage DC busbar through DC conversion devices to supply power to subsequent DC loads (i.e. flexible power loads); of course, appropriate protection devices are set on the line.

[0022] For example, a centralized grid connection point can be set up based on a certain number of users to achieve the interaction between the DC distribution network and the AC distribution network (or AC power grid). After the DC distribution network is connected, the construction cost of the DC distribution network can be directly reflected as the consumption cost. In addition, since the DC distribution network and the existing AC power grid, i.e., the AC220V power grid, are independent, the construction of the photovoltaic system can be carried out without affecting the normal power supply of existing residents, thus shortening the project construction period.

[0023] Depend on Figure 8 It is easy to see that the photovoltaic system and energy storage system are distributed and can be set up on the roofs of various buildings (households) or other spaces. According to the electricity consumption of each household, the photovoltaic power generation and energy storage of each household can be regulated. In addition, the equipment of users in a village constitutes a village-level DC power grid, that is, a DC microgrid. In the DC microgrid, the photovoltaic system and energy storage system are distributed, and their control is also distributed control. In this way, single households, multiple households and villages can be regulated synchronously and independently. In addition, the power efficiency prediction model is pre-established. Exemplarily, the electric energy efficiency prediction model can be established by using HOMER software.

[0024] S102: matching the operation and control strategy of the current DC microgrid in a preset strategy library according to the output data, so that the DC microgrid maintains a dynamic balance of electric energy; S103: Based on big data technology, key components of the DC microgrid are mined, and market update data of all key components are obtained to form a sample set, so as to train the migrated deep learning model through the sample set to obtain an equipment update evaluation model; For example, in Figure 8 The key components include the following categories: grid-connected inverter: used in centralized grid connection points, with rectification and inversion bidirectional conversion functions, to achieve energy interaction between the AC grid and the photovoltaic storage and direct-flexible system, that is, the AC / DC converter shown in the figure; DC home access device: to achieve photovoltaic panel power generation and low-voltage DC grid access, that is, photovoltaic converter, where the photovoltaic converter has MPPT (Maximum Power Point Tracking) function to provide power for DC appliances; flexible DC appliances, such as refrigerators, washing machines, air conditioners, water heaters and other DC loads that have been designed or modified for DCization, can be directly connected to the DC distribution network for operation.

[0025] S104: periodically predicting and ranking the update costs of all key component devices through the device update evaluation model, and setting the control priority according to the ranking results; Generally speaking, the higher the renewal cost, the longer the service life can be achieved by maintaining its operational stability. Therefore, maintaining stability is the priority, while regulation has a lower priority when performing regulation.

[0026] S105: Monitor the output power of the photovoltaic system, the demand power of the flexible power load, and the charging and discharging power of the energy storage system in real time, and adjust the current operation and control strategy according to the monitoring results and the control priority.

[0027] In an example of this embodiment, the method further includes: in the preset strategy library, at least configuring as follows: The first operation control strategy: hour, , at this time the energy storage system is charged; The second operation and control strategy: hour, , at this time the energy storage system discharges; The third operation and control strategy: hour, ,At this time, the energy storage system discharges and the AC distribution network replenishes power; in, Represents the output power of the photovoltaic system, Indicates the required power of the flexible power load, Represents the charging and discharging power of the energy storage system, Indicates the output power supplemented by the AC distribution network.

[0028] In an example of this embodiment, the preset of the operation control strategy in the above strategy library can refer to Fig. 9 Make settings.

[0029] In an example of this embodiment, Figure 2 As shown, the method also includes: S201: pre-establishing an electric energy effectiveness prediction model based on the controlled DC microgrid topology structure; The DC microgrid includes flexible power loads, photovoltaic systems, and energy storage systems interconnected through a DC distribution network, and the DC distribution network can be connected to an AC distribution network.

[0030] The flexible power load, photovoltaic system, and energy storage system in this example are as described above, and can also be referred to Figure 8 , I will not go into details here.

[0031] In an example of this embodiment, Figure 3 As shown, the step of pre-establishing the electric energy effectiveness prediction model specifically includes: S211: Determine a topological structure of the DC microgrid according to the controlled DC microgrid; Exemplarily, the model of each device can be limited in the HOMER software.

[0032] S212: mirroring the topological structure through simulation software; The simulation software is HOMER software, and other similar software may also be used. This example is not limited thereto. Mirroring refers to mapping the physical devices of the DC microgrid to the HOMER software one by one, including the consistency of corresponding models, power, etc.

[0033] S213: setting constraints and objective functions of the model to obtain an energy efficiency evaluation model; The objective function is to minimize the output of the AC distribution network when the flexible power load is met; the constraints are configured as follows: The power generation of the photovoltaic system is are the minimum power generation and maximum power generation of the photovoltaic system, respectively. The loss between the power generation of the photovoltaic system and the output power of the photovoltaic system is negligible. The capacity of the energy storage system is are the minimum and maximum capacities of the energy storage system respectively.

[0034] For example, the photovoltaic system mainly includes photovoltaic panels; the energy storage system may use battery units, hydrogen energy storage units, etc.; When the energy storage system uses battery units, the life of the battery is closely related to its state of charge (SOC). Long-term maintenance of a too high or too low state of charge level will have a negative impact on the life of the battery. However, in practice, batteries are updated very quickly and technological innovation is developing at a high speed. Therefore, when the power generation capacity of the photovoltaic system is insufficient, it is optional to stimulate the capacity limit of the energy storage system to provide higher output to meet the flexible power load.

[0035] In addition, the loss between the generated power of the photovoltaic system and the output power of the photovoltaic system can be quantitatively calculated, and then calibrated according to the quantitative calculation results. Generally, under the condition that the photovoltaic converter remains unchanged, this loss is a constant value.

[0036] In one example of this embodiment, Figure 4 As shown, after the step of matching the operation and control strategy of the current DC microgrid in the preset strategy library according to the output data, the method further includes: S401: inputting the matched operation control strategy into the simulation software for secondary optimization; Among them, the simulation software is HOMER software; The goal of the secondary optimization is to determine the lowest overall cost of the DC microgrid and the lowest comprehensive cost of each device in the DC microgrid, based on the fact that the capacity configuration of the photovoltaic system and the energy storage system meets the flexible power load within a certain period (for example, half a year or a year); S402: Systematically evaluate the results of the secondary optimization search through simulation software; output the evaluated capacity optimization configuration results and execute them to improve the control smoothness when maintaining the dynamic balance of electric energy; Among them, the systematic evaluation includes technical indicators, environmental indicators and economic indicators; The evaluation of the above technical indicators, environmental protection indicators and economic indicators are all existing technologies and will not be described in detail here.

[0037] In an example of this embodiment, the step of mining the key components of the DC microgrid based on big data technology and obtaining the market update data of all key components to prepare a sample set specifically includes: Identify all components of the DC microgrid; all components can refer to Figure 8 ; Based on big data technology, obtain a reference table of the electricity cost of all component equipment, which at least includes equipment price, maintenance rate or replacement rate; It should be noted that the acquisition of equipment price, maintenance rate or replacement rate can be set for a certain time period, such as a quarter.

[0038] According to the electricity cost, the electricity cost reference table is sorted according to the cost, and the first n devices in the sorting are defined as key component devices, where n is a natural number; For example, n is 3, 4 or 5.

[0039] Obtain the market prices and price change rates of all key component equipment, obtain market update data, and make the market update data into a sample set.

[0040] The acquisition of the market price and price change rate of key component equipment can be set to a period, such as every six months, every year, etc.

[0041] In an example of this embodiment, in the step of real-time monitoring the output power of the photovoltaic system, the demand power of the flexible power load, and the charging and discharging power of the energy storage system, the method also includes: storing the power consumption records of the flexible power load to analyze the abnormal power consumption of the flexible power load and provide power saving suggestions.

[0042] Among them, the constant variable comparison method can be used to analyze the abnormal power consumption of flexible power loads; power saving suggestions include but are not limited to replacing power-consuming electrical appliances, using more environmentally friendly similar appliances, reducing lighting brightness, charging in different time periods, etc.

[0043] In another embodiment, Figure 5 As shown, a device for distributed energy storage control of a photovoltaic system, the device is used in the method, the device comprising: a microgrid output prediction unit 100, a control strategy matching unit 200, an update cost evaluation unit 300, a control parameter setting unit 400 and a control optimization unit 500; The microgrid output prediction unit 100 is used to predict the output data of the flexible power load, photovoltaic system and energy storage system in the DC microgrid through an electric energy effectiveness prediction model established based on the DC microgrid topology structure; The control strategy matching unit 200 is used to match the operation control strategy of the current DC microgrid in the preset strategy library according to the output data, so that the DC microgrid maintains a dynamic balance of electric energy; The update cost evaluation unit 300 is used to mine the key components of the DC microgrid based on big data technology, and obtain the market update data of all key components to form a sample set, so as to train the migrated deep learning model through the sample set to obtain an equipment update evaluation model; The control parameter setting unit 400 is used to periodically predict and sort the update costs of all key component devices through the device update evaluation model, and set the control priority according to the sorting result; The control optimization unit 500 is used to monitor the output power of the photovoltaic system, the demand power of the flexible power load, and the charging and discharging power of the energy storage system in real time, and adjust the current operation control strategy according to the monitoring results and the control priority.

[0044] In an example of this embodiment, the microgrid output prediction unit 100 includes a first output prediction module, a second output prediction module, and a third output prediction module, wherein the first output prediction module is used to predict the output data of the flexible power load, that is, the theoretical required power of the flexible power load; the second output prediction module is used to predict the output data of the photovoltaic system, that is, the theoretical output power of the photovoltaic system; the third output prediction module is used to predict the output data of the energy storage system, that is, the theoretical charging and discharging power of the energy storage system.

[0045] In one example of this embodiment, Figure 6 As shown, the device also includes: The control strategy optimization unit 600 is used to input the matching operation control strategy into the simulation software for secondary optimization; The optimization result processing unit 700 is used to systematically evaluate the results of the secondary optimization through simulation software; output the evaluated capacity optimization configuration results and execute them to improve the control smoothness when maintaining the dynamic balance of electric energy.

[0046] In an example of this embodiment, Figure 7 As shown, the update cost evaluation unit 300 includes: A device identification module 310 is used to identify all components of the DC microgrid; Among them, identification can be performed by identifying the device network access ID of each device.

[0047] The equipment sorting module 320 obtains a reference table of the electricity cost of all component equipment based on big data technology, where the electricity cost at least includes equipment price, maintenance rate or replacement rate; A key equipment classification module 330 is used to sort the reference table of kilowatt-hour costs according to the kilowatt-hour costs, and define the first n devices in the sorting as key component devices, where n is a natural number; The sample set generation module 340 is used to obtain the market prices and price change rates of all key component equipment, obtain market update data, and generate the market update data into a sample set.

[0048] The sample set is used to train a migrated deep learning model to obtain a device update evaluation model.

[0049] In another embodiment, Fig.10As shown, a computer device comprises a processor and a memory, wherein the memory stores a computer program, and the processor implements the steps of the method when executing the computer program; In another embodiment, a storage medium stores a computer program thereon, and when the computer program is executed by a processor, the steps of the method are implemented.

[0050] A method for distributed energy storage control of a photovoltaic system is provided in an embodiment of the present invention, and a device for distributed energy storage control of a photovoltaic system is provided based on the method. The method can predict the output of a DC microgrid based on the acquired relevant data, such as the output power of the photovoltaic system, the demand power of the flexible power load, and the charge and discharge power of the energy storage system, and judge whether to use over-limit or over-frequency of equipment with low update cost through a preset equipment update evaluation model, reduce the power supplement of the AC distribution network, maximize the use of the photovoltaic system or the energy storage system, improve the power balancing capability, and ensure the control stability, robustness and accuracy; at the same time, the DC microgrid can utilize the easy-to-control characteristics of DC to construct a DC distribution system that can be flexibly connected and adjusted by different types of power sources, energy storage and power equipment, actively adjust the demand side response of the power grid through flexible power loads, and enhance the convenience, dynamism and initiative of users in participating in energy management.

[0051] Fig.10 An internal structure diagram of a computer device in one embodiment is shown. The computer device includes a processor, a memory, a network interface, an input device and a display screen connected via a system bus. Among them, the memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system and may also store a computer program, which, when executed by the processor, enables the processor to implement a method for distributed energy storage control of a photovoltaic system. The internal memory may also store a computer program, which, when executed by the processor, enables the processor to execute a method for distributed energy storage control of a photovoltaic system. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a button, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0052] It should be understood that, although each step in the flow chart of each embodiment of the present invention is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0053] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0054] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0055] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

[0056] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for distributed energy storage control of a photovoltaic system, characterized in that: The method comprises: The power efficiency prediction model established based on the DC microgrid topology structure is used to predict the output data of the flexible power load, photovoltaic system, and energy storage system in the DC microgrid. According to the output data, the operation and control strategy of the current DC microgrid is matched in the preset strategy library, so that the DC microgrid maintains a dynamic balance of electric energy; Based on big data technology, the key components of the DC microgrid are mined, and the market update data of all key components are obtained to form a sample set, so as to train the migrated deep learning model through the sample set to obtain an equipment update evaluation model; The equipment update evaluation model is used to periodically predict and sort the update costs of all key component equipment, and the control priority is set according to the sorting results; The output power of the photovoltaic system, the demand power of the flexible power load, and the charging and discharging power of the energy storage system are monitored in real time, and the current operation and control strategy is adjusted according to the monitoring results and the control priority.

2. The method according to claim 1, characterized in that The method further comprises: Based on the controlled DC microgrid topology, an electric energy efficiency prediction model is pre-established; wherein the DC microgrid includes flexible power loads, photovoltaic systems, and energy storage systems interconnected through a DC distribution network, and the DC distribution network can be connected to an AC distribution network.

3. The method according to claim 2, characterized in that The step of pre-establishing the electric energy effectiveness prediction model specifically includes: Determine the topology of the DC microgrid according to the controlled DC microgrid; Mirroring the topology through simulation software; Set the constraints and objective function of the model to obtain the energy efficiency evaluation model; The objective function is to minimize the output of the AC distribution network when the flexible power load is met; the constraints are configured as follows: The power generation of the photovoltaic system is are the minimum power generation and maximum power generation of the photovoltaic system, respectively. The loss between the power generation of the photovoltaic system and the output power of the photovoltaic system is negligible. The capacity of the energy storage system is are the minimum and maximum capacities of the energy storage system respectively.

4. The method according to claim 1, characterized in that The method further includes: in the preset strategy library, at least configuring as follows: The first operation control strategy: hour, , at this time the energy storage system is charged; The second operation and control strategy: hour, , at this time the energy storage system discharges; The third operation and control strategy: hour, ,At this time, the energy storage system discharges and the AC distribution network replenishes power; in, Represents the output power of the photovoltaic system, Indicates the required power of the flexible power load, Represents the charging and discharging power of the energy storage system, Indicates the output power supplemented by the AC distribution network.

5. The method according to claim 1, characterized in that After the step of matching the operation and control strategy of the current DC microgrid in the preset strategy library according to the output data, the method further includes: Input the matching operation control strategy into the simulation software for secondary optimization; The results of the secondary optimization are systematically evaluated through simulation software; the evaluated capacity optimization configuration results are output and executed to improve the control smoothness when maintaining the dynamic balance of electric energy; Among them, the systematic evaluation includes technical indicators, environmental indicators and economic indicators.

6. The method according to claim 1, characterized in that The step of mining the key components of the DC microgrid based on big data technology and obtaining the market update data of all key components to prepare a sample set specifically includes: Identify all components of the DC microgrid; Based on big data technology, obtain a reference table of the electricity cost of all component equipment, which at least includes equipment price, maintenance rate or replacement rate; According to the electricity cost, the electricity cost reference table is sorted according to the cost, and the first n devices in the sorting are defined as key component devices, where n is a natural number; Obtain the market prices and price change rates of all key component equipment, obtain market update data, and make the market update data into a sample set.

7. The method according to claim 1, characterized in that In the step of real-time monitoring the output power of the photovoltaic system, the demand power of the flexible power load, and the charging and discharging power of the energy storage system, the method also includes: storing the power consumption records of the flexible power load to analyze the abnormal power consumption of the flexible power load and provide power saving suggestions.

8. A device for distributed energy storage control of a photovoltaic system, the device being used in the method according to any one of claims 1 to 7, characterized in that: The device comprises: a microgrid output prediction unit, a control strategy matching unit, an update cost evaluation unit, a control parameter setting unit and a control optimization unit; The microgrid output prediction unit is used to predict the output data of the flexible power load, photovoltaic system and energy storage system in the DC microgrid through an electric energy effectiveness prediction model established based on the DC microgrid topology structure; The control strategy matching unit is used to match the operation control strategy of the current DC microgrid in a preset strategy library according to the output data, so that the DC microgrid maintains a dynamic balance of electric energy; The update cost evaluation unit is used to mine the key components of the DC microgrid based on big data technology, and obtain the market update data of all key components to form a sample set, so as to train the migrated deep learning model through the sample set to obtain an equipment update evaluation model; The control parameter setting unit is used to periodically predict and sort the update costs of all key component devices through the device update evaluation model, and set the control priority according to the sorting result; The control optimization unit is used to monitor the output power of the photovoltaic system, the demand power of the flexible power load, and the charging and discharging power of the energy storage system in real time, and adjust the current operation control strategy according to the monitoring results and the control priority.

9. The device according to claim 8, characterized in that The device also includes: A control strategy optimization unit is used to input the matching operation control strategy into the simulation software for secondary optimization; The optimization result processing unit is used to systematically evaluate the results of the secondary optimization through simulation software; output the evaluated capacity optimization configuration results and execute them to improve the control smoothness when maintaining the dynamic balance of electric energy.

10. A computer device comprising a processor and a memory, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

Images