Low-voltage distribution area microgrid control methods, systems and media

Abstract

This invention discloses a method, system, and medium for microgrid control in low-voltage distribution areas. The method includes: a resource acquisition module in the terminal acquisition device collects various types of terminal resource data to obtain compressed resource data; the low-voltage distribution area side aggregates the compressed resource data based on the constructed parent-child cluster local communication network to obtain aggregated resource data, and uploads it to the master station; the master station predicts the upper and lower limits of various resources using a large model based on the aggregated resource data, historical data, historical curves, predicted curves, and load energy storage control targets, and sends this prediction to the dynamic balance management module; a lightweight self-learning module calculates the control upper and lower limits and adjustment step size based on the aggregated resource data and the upper and lower limits of various resources sent by the dynamic balance management module; and the dynamic balance management module controls various resources based on the control upper and lower limits and adjustment step size sent by the lightweight self-learning module. This embodiment not only improves control accuracy but also reduces control time.

Description

Technical Field

[0001] This invention relates to the field of control technology, and in particular to a method, system and medium for controlling a low-voltage distribution area microgrid. Background Technology

[0002] Integrated source-grid-load-storage microgrid control technology is an advanced technology that coordinates the four key elements of a power system—power source, grid, load, and energy storage—to achieve efficient and coordinated operation across all stages of energy production, transmission, consumption, and storage. Its core objective is to enhance the stability, economy, and renewable energy absorption capacity of the power system through flexible interaction among multiple elements, thus contributing to the construction of new power systems. Currently, the commonly used integrated source-grid-load-storage microgrid control technology relies on low-voltage smart terminals, electricity meters, and end-point sensing devices. It vertically integrates distributed power sources, energy storage systems, charging piles, flexible loads, and distribution networks, enabling data acquisition and coordinated optimization across all stages of energy production, transmission, consumption, and storage within the distribution area. By leveraging real-time data acquisition and combining predictive models and control strategies, it dynamically adjusts the output of photovoltaic inverters, the charging and discharging status of energy storage, and the operating sequence of interruptible loads, addressing issues such as voltage exceeding limits, three-phase imbalance, and reverse power flow caused by the high proportion of distributed energy access in low-voltage distribution areas. At the same time, the demand response mechanism guides users to participate in peak shaving and valley filling, reduces the risk of transformer overload in the distribution area, improves the local consumption rate of renewable energy, and ensures power supply reliability by seamlessly switching between grid-connected and islanded modes.

[0003] Currently, the microgrid control in low-voltage distribution areas is carried out in a chain-like, in-depth manner. The coordination of terminal resources mainly relies on the unified control of the master station. The data collection frequency of the master station is low, the load forecast accuracy is limited, and the control precision is low. The integration of terminal resources is low. When changes occur in field resources, it often takes 1-2 collection cycles to detect the changes. The effect of the control also takes 1-2 cycles to obtain, resulting in a relatively long control time. Summary of the Invention

[0004] This invention provides a method, system, and medium for regulating low-voltage distribution area microgrids, aiming to solve the problems of long regulation time and low regulation accuracy in existing low-voltage distribution area microgrid regulation.

[0005] In a first aspect, embodiments of the present invention provide a low-voltage distribution area microgrid control method, applied to a low-voltage distribution area microgrid control system. The low-voltage distribution area microgrid control system includes a master station and a low-voltage distribution area side. The low-voltage distribution area side includes end-point acquisition equipment, a dynamic balance management module, and a lightweight self-learning module. The method includes:

[0006] The resource acquisition module in the terminal acquisition device collects various types of terminal resource data to obtain compressed resource data;

[0007] The low-voltage distribution area uses the local communication network of the constructed parent-child cluster to aggregate the compressed resource data to obtain aggregated resource data, and then uploads the aggregated resource data to the main station.

[0008] The main station uses a large model to predict the upper and lower limits of various resources based on the aggregated resource data, historical data, historical curves, predicted curves, and load storage regulation targets.

[0009] The dynamic balance management module receives the upper and lower limits of various resources issued by the main station;

[0010] The lightweight self-learning module calculates the upper and lower limits of regulation and the adjustment step size based on the aggregated resource data and the upper and lower limits of various resources sent by the dynamic balance management module.

[0011] The dynamic balance management module regulates the various resources based on the upper and lower limits and the adjustment step size sent by the lightweight self-learning module.

[0012] Secondly, embodiments of the present invention also provide a low-voltage distribution area microgrid control system, including a master station and a low-voltage distribution area side. The low-voltage distribution area side includes end-point acquisition equipment, a dynamic balance management module, and a lightweight self-learning module. A prediction unit is configured in the master station, and an acquisition unit, a data aggregation unit, a data distribution unit, a first calculation unit, and a first control unit are configured in the low-voltage distribution area side.

[0013] The acquisition unit is used by the resource acquisition module in the terminal acquisition device to acquire various types of terminal resource data to obtain compressed resource data;

[0014] The construction and aggregation unit is used by the low-voltage distribution area to aggregate the compressed resource data based on the local communication network of the constructed parent-child cluster to obtain aggregated resource data, and then upload the aggregated resource data to the main station.

[0015] The prediction unit is used by the main station to predict the upper and lower limits of various resources based on the aggregated resource data, historical data, historical curves, prediction curves, and load storage regulation targets using a large model.

[0016] The issuing unit is used by the dynamic balance management module to receive the upper and lower limit values ​​of various resources issued by the main station;

[0017] The first calculation unit is used by the lightweight self-learning module to calculate the upper and lower limits of regulation and the adjustment step size based on the aggregated resource data and the upper and lower limits of various resources sent by the dynamic balance management module;

[0018] The first control unit is used by the dynamic balance management module to control the various resources according to the control upper and lower limits and the adjustment step size sent by the lightweight self-learning module.

[0019] Thirdly, embodiments of the present invention also provide a low-voltage distribution area microgrid control system, which includes a master station and a low-voltage distribution area side. Both the master station and the low-voltage distribution area side include a memory and a processor. The memory stores a computer program. When the processors of the master station and the low-voltage distribution area side execute their respective computer programs, they jointly implement the above-mentioned method.

[0020] Fourthly, embodiments of the present invention also provide a computer-readable storage medium storing a computer program that, when executed by a plurality of processors, can implement the above-described method.

[0021] This invention provides a method, system, and medium for regulating a low-voltage distribution area microgrid. The method includes: a resource acquisition module in the terminal acquisition device collects various types of terminal resource data to obtain compressed resource data; the low-voltage distribution area side aggregates the compressed resource data based on a constructed parent-child cluster local communication network to obtain aggregated resource data, and uploads the aggregated resource data to the master station; the master station predicts the upper and lower limits of various resources using a large model based on the aggregated resource data, historical data, historical curves, predicted curves, and load storage regulation targets; the dynamic balance management module receives the upper and lower limits of various resources from the master station; the lightweight self-learning module calculates the regulation upper and lower limits and adjustment step size based on the aggregated resource data and the upper and lower limits of various resources sent by the dynamic balance management module; and the dynamic balance management module regulates the various resources based on the regulation upper and lower limits and the adjustment step size sent by the lightweight self-learning module. In the technical solution of this invention embodiment, based on the local communication network of the constructed parent-child cluster, various terminal resource data are horizontally integrated and summarized at the low-voltage distribution area side to obtain summarized resource data; the main station predicts the upper and lower limits of various resources through a large model based on the historical data, historical curves, predicted curves, and load energy storage control targets of the summarized resource data; based on the upper and lower limits of various resources, the control upper and lower limits and adjustment step size are calculated through a lightweight self-learning module; and the various resources are controlled through a dynamic balance management module according to the control upper and lower limits and adjustment step size. Since both the lightweight self-learning module and the dynamic balance management module are set at the low-voltage distribution area side, when various resources change, they can make relevant responses in a timely manner, improving the accuracy of control. Moreover, it also ensures that control and data collection do not interfere with each other, effectively reducing the control time. Attached Figure Description

[0022] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This invention provides an overall architecture diagram of a low-voltage distribution area microgrid control system.

[0024] Figure 2 This is a schematic flowchart of a low-voltage distribution area microgrid control method provided in an embodiment of the present invention;

[0025] Figure 3 This is a schematic diagram of a sub-process of a low-voltage distribution area microgrid control method provided in an embodiment of the present invention;

[0026] Figure 4 This is a schematic diagram of another sub-process of a low-voltage distribution area microgrid control method provided in an embodiment of the present invention;

[0027] Figure 5 This is a schematic diagram illustrating how the main station predicts the upper and lower limits of various resources using a large model, as provided in an embodiment of the present invention.

[0028] Figure 6 This is another schematic diagram of a low-voltage distribution area microgrid control method provided in an embodiment of the present invention;

[0029] Figure 7 This is a schematic diagram illustrating the dynamic balance management module and lightweight self-learning module used in embodiments of the present invention to achieve dynamic balance of source load;

[0030] Figure 8 This is a schematic block diagram of a low-voltage distribution area microgrid control system provided in an embodiment of the present invention;

[0031] Figure 9 This is a schematic block diagram of a computer device provided in an embodiment of the present invention. Detailed Implementation

[0032] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0033] It should be understood that, when used in this specification and the appended claims, the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0034] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0035] It should also be further understood that the term "and / or" as used in this specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0036] As used in this specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if [described condition or event] is detected" may be interpreted, depending on the context, as "once determined," "in response to determination," "once [described condition or event] is detected," or "in response to detection of [described condition or event]."

[0037] Please see Figure 1 , Figure 1 This is an overall architecture diagram of a low-voltage distribution area microgrid control system provided by an embodiment of the present invention. The low-voltage distribution area microgrid control system includes a master station and a low-voltage distribution area side. The low-voltage distribution area side includes end-point acquisition equipment, a dynamic balance management module, and a lightweight self-learning module. The master station is communicatively connected to the dynamic balance management module via a 4G network. The dynamic balance management module is communicatively connected to the lightweight self-learning module to send aggregated resource data and upper and lower limits of various resources to the lightweight self-learning module, and receives the control upper and lower limits and adjustment step size returned by the lightweight self-learning module to control various resources. The dynamic balance management module is communicatively connected to a resource acquisition module located in the end-point acquisition equipment to obtain aggregated resources. It should be noted that in this embodiment, various end-point resource data include source-grid-load-storage resource data, specifically, source refers to photovoltaic, wind power, and biogas; grid refers to the power grid; load refers to charging piles, heating and cooling loads, etc.; and storage refers to household storage, distribution area energy storage, etc.

[0038] Figure 2 This is a schematic flowchart of a low-voltage distribution area microgrid control method provided in an embodiment of the present invention. Figure 2 As shown, the method includes the following steps S110-S160.

[0039] S110, The resource acquisition module in the terminal acquisition device acquires various types of terminal resource data to obtain compressed resource data.

[0040] In this embodiment of the invention, the resource acquisition module in the terminal acquisition device uses a second-level polling mechanism to achieve real-time data synchronization and updates, that is, it uses a high-frequency acquisition strategy to collect various types of terminal resource data to obtain compressed resource data. Specifically, as shown... Figure 3 As shown, step S110 may include steps S111-S112:

[0041] S111, the resource acquisition module in the terminal acquisition device uses a preloading mechanism and a time series data compression algorithm to acquire various types of terminal resource data to obtain compressed resource data;

[0042] S112. Save the compressed resource data to the cache area and update the compressed resource data in the cache area in a high-frequency manner.

[0043] In this embodiment of the invention, the time-series data compression algorithm includes lossless compression, lossy compression, and hybrid compression algorithms. This algorithm reduces storage and transmission costs by decreasing data volume while preserving key information as much as possible. It combines time-series characteristics (such as timestamp difference encoding and XOR value compression) to achieve efficient real-time compression. The specific choice requires a trade-off between compression ratio, accuracy loss, computational resources, and scenario requirements. The pre-loading mechanism refers to pre-collecting the data required by the acquisition plan according to the actual business scenario. After collection, the data is placed in a cache and updated frequently before acquisition requests arrive. Upon receiving an acquisition command, it immediately responds with a response latency controlled within 50ms, enabling real-time response to sudden data acquisition requests.

[0044] S120. The low-voltage distribution area side summarizes the compressed resource data based on the local communication network of the constructed parent-child cluster to obtain summarized resource data, and uploads the summarized resource data to the main station.

[0045] In this embodiment of the invention, a local communication network based on a parent-child cluster is constructed relying on a local high-speed acquisition channel. Through a multi-node dynamic multi-hop mechanism, a multi-point, multi-hop self-organizing network and self-routing are achieved, effectively ensuring a minute-level data acquisition cycle. Specifically, as... Figure 4As shown, step S120 may include steps S121-S123: S121, designing the low-voltage distribution area as a tree or star topology based on wireless transmission, and setting up parent and child end acquisition devices; S122, dividing subnets through private IP segments, and using built-in routing to achieve VLAN routing forwarding between the parent and child end acquisition devices; S123, configuring NAT service, DHCP service, and static / dynamic routing protocols for the parent end acquisition device, restricting direct communication between the child end acquisition devices, and only allowing communication through the parent end acquisition device to obtain the local communication network of the parent-child cluster. It should be noted that in this embodiment, NAT (Network Address Translation) is a technology used to translate IP addresses and ports in an IP network, and DHCP (Dynamic Host Configuration Protocol) is a protocol used to automatically allocate IP addresses and other network configuration parameters, aiming to simplify the management of network devices. It should also be noted that, in this embodiment, relying on wireless communication, all data from the sub-end acquisition devices are aggregated and forwarded by the parent end acquisition device. All sub-end acquisition devices directly correspond to the parent end acquisition device, reducing data forwarding time. Wireless communication can be completed in milliseconds. Relying on the pre-loading mechanism, it is ensured that data communication and acquisition are completed within minutes.

[0046] S130. The main station predicts the upper and lower limits of various resources through a large model based on the aggregated resource data, historical data, historical curves, prediction curves, and load storage regulation targets.

[0047] In this embodiment of the invention, the historical data includes historical load data and historical weather data, and the forecast curve includes a load forecast curve and a weather forecast curve. The historical curve is a historical output curve of new energy sources, such as... Figure 5 As shown, the main station predicts the new energy output curve based on the weather forecast curve and the historical curve using the new energy output prediction model in the large model; based on the new energy output curve, the historical data, the load forecast curve, the aggregated resource data, and the load energy storage control target, it predicts the upper and lower limits of various resources using the large model. It should be noted that in this embodiment, the weather forecast curve can predict sunlight, wind speed, temperature, etc. The upper and lower limits of various resources include low-voltage substation thresholds, photovoltaic output upper and lower limits, and energy storage upper and lower limits. It should also be noted that in this embodiment, the large model can also predict the new energy output curve, weather conditions, and operational indicators, etc.

[0048] S140, The dynamic balance management module receives the upper and lower limits of various resources issued by the main station.

[0049] In this embodiment of the invention, the master station sends the predicted upper and lower limits of various resources to the dynamic balance management module. The dynamic balance management module performs local dynamic adjustment of source, grid, load, and storage based on the upper and lower limits of various resources, and conducts comparative analysis based on actual data and predicted data to train and optimize the lightweight self-learning model in the lightweight self-learning module. Based on the actual resource changes in the field, and in accordance with the operational goals of safety, economy, and low carbon, it adjusts the output and consumption of various resources (photovoltaic output, wind turbine output, charging pile charging load, etc.) to ensure that green electricity is generated to the fullest extent possible within the preset range of the master station, that green electricity is consumed locally as much as possible, and that source and load are dynamically balanced.

[0050] S150, the lightweight self-learning module calculates the upper and lower limits of regulation and the adjustment step size based on the aggregated resource data and the upper and lower limits of various resources sent by the dynamic balance management module.

[0051] In this embodiment of the invention, the lightweight self-learning module receives the aggregated resource data and the upper and lower limits of various resources sent by the dynamic balance management module; it inputs the aggregated resource data into the lightweight self-learning model to calculate the upper and lower limits of regulation; and it determines the adjustment step size based on the upper and lower limits of regulation and the upper and lower limits of various resources. It should be noted that in this embodiment, the upper and lower limits of various resources are regulation parameters, and the lightweight self-learning model also outputs operating indicators; the regulation parameters and operating indicators form a regulation strategy. It should also be noted that in this embodiment, the lightweight self-learning model is a local regulation model. Because local resources are limited, the model training uses the upper and lower limits of various resources (baseline strategy) and historical regulation strategies combined with the current aggregated resource data, without training a large-scale model of the entire system.

[0052] S160, The dynamic balance management module regulates the various resources according to the upper and lower limits and the adjustment step size sent by the lightweight self-learning module.

[0053] In this embodiment of the invention, the dynamic balance management module receives the upper and lower limits of regulation and the adjustment step size sent by the lightweight self-learning module, and regulates the various resources according to the upper and lower limits of regulation and the adjustment step size. It should be noted that in this embodiment, the regulation process is fine-tuning. For example, in photovoltaic regulation, the power generation limit is not reduced from 50kW to 20kW in one step. It is first adjusted to around 20kW, for example, to 25kW, and then adjusted to 22kW in increments of 1kW. After reaching the target of 22kW, it continues to make fine-tuning in even smaller steps to continuously optimize.

[0054] Figure 6This is a flowchart illustrating a low-voltage distribution area microgrid control method according to another embodiment of the present invention, as shown below. Figure 6 As shown, in this embodiment, the low-voltage distribution area microgrid control method includes steps S210-S290. Steps S210-S260 are similar to steps S110-S160 in the previous embodiment and will not be described again here. The following details the additional steps S270-S290 in this embodiment.

[0055] S270. The dynamic balance management module obtains the adjusted aggregated resource data and sends the adjusted aggregated resource data to the lightweight self-learning module.

[0056] S280, the lightweight self-learning module calculates the optimal control upper and lower limits and the optimal adjustment step size based on the aggregated resource data after control, the upper and lower limits of various resources and historical control strategies.

[0057] S290, the dynamic balance management module regulates the various resources according to the optimal control upper and lower limits and the optimal adjustment step size sent by the lightweight self-learning module.

[0058] In this embodiment of the invention, if the source and load of the various resources are unbalanced, the process returns to the step of obtaining the adjusted aggregated resource data from the dynamic balance management module and sending the adjusted aggregated resource data to the lightweight self-learning module, until the source and load of the various resources are balanced. Understandably, source and load imbalance in low-voltage distribution areas refers to a mismatch between the power supply capacity of the low-voltage side of the distribution network (e.g., 380V / 220V distribution areas) and the user load demand, which may lead to problems such as decreased voltage quality, equipment overload, and increased line losses. It should be noted that in this embodiment, during the adjustment process, the lightweight self-learning module interacts with the dynamic balance management module, fine-tuning resources according to different adjustment step sizes and continuously monitoring the operational changes of various resources. This process continuously iterates through parameter fine-tuning and strategy optimization, continuously updating and optimizing the model.

[0059] Please see Figure 7 , Figure 7 This diagram illustrates the dynamic balance management module and lightweight self-learning module used in embodiments of the present invention to achieve dynamic source load balancing. Figure 7In this process, based on the upper and lower limits of various resources, weather forecast data (optional), and aggregated resource data, the lightweight self-learning model in the lightweight self-learning module generates control upper and lower limits and adjustment step sizes. The aggregated resource data includes distributed energy output power, energy storage charging and discharging power, and various load powers, while the weather forecast data is data sent from the main station. After the dynamic balance management module controls various resources according to the control upper and lower limits and adjustment step sizes, it obtains the controlled aggregated resource data and sends it to the lightweight self-learning module. The lightweight self-learning module calculates the optimal control upper and lower limits and the optimal adjustment step size based on the controlled aggregated resource data, the upper and lower limits of various resources, and historical control strategies. The dynamic balance management module controls various resources according to the optimal control upper and lower limits and the optimal adjustment step size, repeating this process until the source-load balance of various resources is achieved.

[0060] In summary, the low-voltage distribution area utilizes a dynamic balance management module and a lightweight self-learning module to collaboratively manage various resources. Relying on the upper and lower limits of various resources from the main station, it locally monitors changes in these resources and rapidly performs integrated source-grid-load-storage control to achieve dynamic balance in the low-voltage distribution area's microgrid. After dynamic adjustments, the local lightweight self-learning model is continuously optimized based on changes in various resources before and after control. Throughout the entire control process, the speed and effectiveness of dynamic balancing in the low-voltage distribution area's microgrid are greatly improved, effectively shortening control time and increasing control accuracy. The local horizontal integration of source-grid-load-storage microgrid resources in the low-voltage distribution area makes microgrid source-load balancing safer, more economical, and more efficient.

[0061] Figure 8 This is a schematic block diagram of a low-voltage distribution area microgrid control system provided in an embodiment of the present invention. Figure 8 As shown, this corresponds to the low-voltage distribution area microgrid control method applied to the main station and low-voltage distribution area side described above. The low-voltage distribution area microgrid control system 70 includes a unit for executing the aforementioned low-voltage distribution area microgrid control method. Specifically, please refer to... Figure 8 The low-voltage distribution area microgrid control system 70 includes a prediction unit 101 configured in the main station 10, and a data acquisition unit 201, a data collection and aggregation unit 202, a data distribution unit 203, a first calculation unit 204, and a first control unit 205 configured in the low-voltage distribution area side 20.

[0062] The acquisition unit 201 is used by the resource acquisition module in the terminal acquisition device to acquire various types of terminal resource data to obtain compressed resource data; the construction and aggregation unit 202 is used by the low-voltage distribution area side to aggregate the compressed resource data based on the constructed parent-child cluster local communication network to obtain aggregated resource data, and upload the aggregated resource data to the master station; the prediction unit 101 is used by the master station to predict the upper and lower limits of various resources through a large model based on the aggregated resource data, historical data, historical curves, prediction curves, and load energy storage control targets; the distribution unit 203 is used by the dynamic balance management module to receive the upper and lower limits of various resources distributed by the master station; the first calculation unit 204 is used by the lightweight self-learning module to calculate the control upper and lower limits and adjustment step size based on the aggregated resource data and the upper and lower limits of various resources sent by the dynamic balance management module; the first control unit 205 is used by the dynamic balance management module to control various resources based on the control upper and lower limits and adjustment step size sent by the lightweight self-learning module.

[0063] In some embodiments, such as this one, the acquisition unit 201 includes an acquisition subunit and a storage unit.

[0064] The acquisition subunit is used by the resource acquisition module in the terminal acquisition device to acquire various types of terminal resource data to obtain compressed resource data using a preloading mechanism and a time series data compression algorithm; the storage unit is used to save the compressed resource data to the cache area and update the compressed resource data in the cache area in a high-frequency manner.

[0065] In some embodiments, such as this one, the construction and aggregation unit 202 includes a setting unit, a forwarding unit, and a configuration unit.

[0066] The setting unit is used to design the low-voltage distribution area as a tree or star topology based on wireless transmission, and to set up parent and child end acquisition devices; the forwarding unit is used to divide subnets through private IP segments and to use built-in routing to realize VLAN routing forwarding between the parent and child end acquisition devices; the configuration unit is used to configure the NAT service, DHCP service, and static / dynamic routing protocol of the parent end acquisition device, and to restrict direct communication between the child end acquisition devices, and only allow communication through the parent end acquisition device to obtain the local communication network of the parent-child cluster.

[0067] In some embodiments, such as this one, the prediction unit 101 includes a first prediction subunit and a second prediction subunit.

[0068] The first prediction subunit is used by the main station to predict the new energy output curve based on the weather forecast curve and the historical curve using the new energy output prediction model in the large model; the second prediction subunit is used to predict the upper and lower limits of various resources based on the new energy output curve, the historical data, the load forecast curve, the aggregated resource data, and the load energy storage regulation target using the large model.

[0069] In some embodiments, such as this one, the first computing unit 204 includes a receiving unit, a computing subunit, and a determining unit.

[0070] The receiving unit is used by the lightweight self-learning module to receive the aggregated resource data and the upper and lower limits of various resources sent by the dynamic balance management module; the calculation subunit is used to input the aggregated resource data into the lightweight self-learning model to calculate the upper and lower limits of regulation; and the determining unit is used to determine the adjustment step size based on the upper and lower limits of regulation and the upper and lower limits of various resources.

[0071] In some embodiments, such as another embodiment, the low-voltage distribution area microgrid control system 70 further includes an acquisition and transmission unit, a second calculation unit, a second control unit, and a return execution unit configured in the low-voltage distribution area side 20.

[0072] The acquisition and sending unit is used by the dynamic balance management module to acquire the adjusted aggregated resource data and send the adjusted aggregated resource data to the lightweight self-learning module; the second calculation unit is used by the lightweight self-learning module to calculate the optimal adjustment upper and lower limits and the optimal adjustment step size based on the adjusted aggregated resource data, the upper and lower limits of various resources, and historical adjustment strategies; the second adjustment unit is used by the dynamic balance management module to adjust various resources based on the optimal adjustment upper and lower limits and the optimal adjustment step size sent by the lightweight self-learning module; the return execution unit is used to return to the step of the dynamic balance management module acquiring the adjusted aggregated resource data and sending the adjusted aggregated resource data to the lightweight self-learning module if the source load of various resources is unbalanced, until the source load of various resources is balanced.

[0073] The aforementioned low-voltage distribution area microgrid control system can be implemented as a computer program, which can, for example... Figure 9 It runs on the computer device shown.

[0074] Please see Figure 9 , Figure 9This is a schematic block diagram of a computer device provided in an embodiment of this application. The computer device 900 can be the aforementioned main station and low-voltage distribution area side.

[0075] See Figure 9 The computer device 900 includes a processor 902, a memory, and an interface 905 connected via a system bus 901, wherein the memory may include a non-volatile storage medium 903 and internal memory 904.

[0076] The non-volatile storage medium 903 can store an operating system 9031 and a computer program 9032. When the computer program 9032 is executed, it enables the processor 902 to execute a low-voltage substation microgrid control method.

[0077] The processor 902 provides computing and control capabilities to support the operation of the entire computer device 900.

[0078] The internal memory 904 provides an environment for the execution of the computer program 9032 in the non-volatile storage medium 903.

[0079] This interface 905 is used for communication with other devices. Those skilled in the art will understand that... Figure 9 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device 900 to which the present application is applied. The specific computer device 900 may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0080] The processors 902 in the main station and the low-voltage distribution area are used to run computer programs 9032 stored in their respective memories. When the computer programs 9032 are executed, the processors 902 can perform a low-voltage distribution area microgrid control method.

[0081] It should be understood that in the embodiments of this application, the processor 902 may be a central processing unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0082] It will be understood by those skilled in the art that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program may be stored in a storage medium, which is a computer-readable storage medium. The computer program is executed by at least one processor in the computer system to implement the process steps of the embodiments of the above methods.

[0083] Therefore, the present invention also provides a storage medium. This storage medium can be a computer-readable storage medium. The storage medium stores a computer program. When executed by a processor, the computer program causes the processor to perform any embodiment of the low-voltage distribution area microgrid control method described above.

[0084] The storage medium can be any computer-readable storage medium capable of storing program code, such as a USB flash drive, portable hard drive, read-only memory (ROM), magnetic disk, or optical disk.

[0085] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0086] In the several embodiments provided by this invention, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For example, the division of each unit is merely a logical functional division, and there may be other division methods in actual implementation. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed.

[0087] The steps in the method of this invention can be adjusted, merged, or reduced in order according to actual needs. The units in the device of this invention can be merged, divided, or reduced according to actual needs. Furthermore, the functional units in the various embodiments of this invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0088] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of the present invention, in essence, 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. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, a terminal, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention.

[0089] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0090] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Since these modifications and variations fall within the scope of the claims and their equivalents, this invention also intends to include these modifications and variations.

[0091] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and such modifications or substitutions are intended to be within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be subject to the scope of protection of the claims.

Claims

1. A method for controlling a low-voltage distribution area microgrid, applied to a low-voltage distribution area microgrid control system, characterized in that, The low-voltage distribution area microgrid control system includes a master station and a low-voltage distribution area side. The low-voltage distribution area side includes terminal acquisition equipment, a dynamic balance management module, and a lightweight self-learning module. The method includes: The resource acquisition module in the terminal acquisition device collects various types of terminal resource data to obtain compressed resource data; The low-voltage distribution area uses the local communication network of the constructed parent-child cluster to aggregate the compressed resource data to obtain aggregated resource data, and then uploads the aggregated resource data to the main station. The main station uses a large model to predict the upper and lower limits of various resources based on the aggregated resource data, historical data, historical curves, predicted curves, and load storage regulation targets. The dynamic balance management module receives the upper and lower limits of various resources issued by the main station; The lightweight self-learning module calculates the upper and lower limits of regulation and the adjustment step size based on the aggregated resource data and the upper and lower limits of various resources sent by the dynamic balance management module. The dynamic balance management module regulates the various resources according to the upper and lower limits and the adjustment step size sent by the lightweight self-learning module; The dynamic balance management module acquires the adjusted aggregated resource data and sends the adjusted aggregated resource data to the lightweight self-learning module; The lightweight self-learning module calculates the optimal upper and lower control limits and the optimal adjustment step size based on the aggregated resource data after regulation, the upper and lower limits of various resources, and historical regulation strategies. The dynamic balance management module regulates the various resources based on the optimal upper and lower limits of regulation sent by the lightweight self-learning module and the optimal adjustment step size; The construction of the local communication network for the parent and child clusters includes: The low-voltage distribution area is designed as a tree or star topology based on wireless transmission, and parent end acquisition devices and child end acquisition devices are set up. Subnets are divided using private IP segments, and VLAN routing forwarding between the parent end acquisition device and the child end acquisition device is achieved using built-in routing. Configure the NAT service, DHCP service, and static / dynamic routing protocol of the parent terminal acquisition device, restrict direct communication between the child terminal acquisition devices, and only allow communication between the parent and child clusters through the parent terminal acquisition device; The forecast curves include load forecast curves and weather forecast curves. The main station, based on the aggregated resource data, historical data, historical curves, forecast curves, and load storage regulation targets, uses a large model to predict the upper and lower limits of various resources, including: The main station predicts the new energy output curve based on the weather forecast curve and the historical curve using the new energy output prediction model in the large model. Based on the new energy output curve, the historical data, the load forecast curve, the aggregated resource data, and the load storage regulation target, the upper and lower limits of various resources are predicted by the large model.

2. The low-voltage distribution area microgrid control method according to claim 1, characterized in that, The resource acquisition module in the terminal acquisition device uses a high-frequency acquisition strategy to collect various types of terminal resource data, including: The resource acquisition module in the terminal acquisition device uses a preloading mechanism and a time-series data compression algorithm to acquire various types of terminal resource data to obtain compressed resource data. The compressed resource data is saved to a cache area, and the compressed resource data in the cache area is updated frequently.

3. The method according to claim 1, characterized in that, The lightweight self-learning module calculates the upper and lower limits of regulation and the adjustment step size based on the aggregated resource data and the upper and lower limits of various resources sent by the dynamic balance management module, including: The lightweight self-learning module receives the aggregated resource data and the upper and lower limits of various resources sent by the dynamic balance management module; The aggregated resource data is input into a lightweight self-learning model to calculate the upper and lower limits of regulation. The adjustment step size is determined based on the upper and lower limits of the regulation and the upper and lower limits of the various resources.

4. The method according to claim 3, characterized in that, The method further includes: If the source load of the various types of resources is unbalanced, the process returns to the step of obtaining the adjusted aggregated resource data from the dynamic balance management module and sending the adjusted aggregated resource data to the lightweight self-learning module until the source load of the various types of resources is balanced.

5. A low-voltage distribution area microgrid control system, characterized in that, The system includes a main station and a low-voltage distribution area. The low-voltage distribution area includes end-point acquisition equipment, a dynamic balance management module, and a lightweight self-learning module. The main station is equipped with a prediction unit, and the low-voltage distribution area includes an acquisition unit, a data aggregation unit, a data distribution unit, a data transmission unit, a first calculation unit, a first control unit, an acquisition and transmission unit, a second calculation unit, and a second control unit. The acquisition unit is used by the resource acquisition module in the terminal acquisition device to acquire various types of terminal resource data to obtain compressed resource data; The construction and aggregation unit is used by the low-voltage distribution area to aggregate the compressed resource data based on the local communication network of the constructed parent-child cluster to obtain aggregated resource data, and then upload the aggregated resource data to the main station. The prediction unit is used by the main station to predict the upper and lower limits of various resources based on the aggregated resource data, historical data, historical curves, prediction curves, and load storage regulation targets using a large model. The issuing unit is used by the dynamic balance management module to receive the upper and lower limit values ​​of various resources issued by the main station; The first calculation unit is used by the lightweight self-learning module to calculate the upper and lower limits of regulation and the adjustment step size based on the aggregated resource data and the upper and lower limits of various resources sent by the dynamic balance management module; The first control unit is used by the dynamic balance management module to control the various resources according to the control upper and lower limits and the adjustment step size sent by the lightweight self-learning module; The acquisition and sending unit is used by the dynamic balance management module to acquire the adjusted aggregated resource data and send the adjusted aggregated resource data to the lightweight self-learning module. The second calculation unit is used by the lightweight self-learning module to calculate the optimal control upper and lower limits and the optimal adjustment step size based on the aggregated resource data after regulation, the upper and lower limits of various resources, and historical regulation strategies. The second control unit is used by the dynamic balance management module to control the various resources according to the optimal control upper and lower limits and the optimal adjustment step size sent by the lightweight self-learning module; The construction of the local communication network for the parent and child clusters includes: The low-voltage distribution area is designed as a tree or star topology based on wireless transmission, and parent end acquisition devices and child end acquisition devices are set up. Subnets are divided using private IP segments, and VLAN routing forwarding between the parent end acquisition device and the child end acquisition device is achieved using built-in routing. Configure the NAT service, DHCP service, and static / dynamic routing protocol of the parent terminal acquisition device, restrict direct communication between the child terminal acquisition devices, and only allow communication between the parent and child clusters through the parent terminal acquisition device; The forecast curves include load forecast curves and weather forecast curves, and the forecast unit includes: The first prediction subunit is used by the main station to predict the new energy output curve based on the weather prediction curve and the historical curve through the new energy output prediction model in the large model. The second prediction subunit is used to predict the upper and lower limits of various resources based on the new energy output curve, the historical data, the load prediction curve, the aggregated resource data, and the load storage regulation target through the large model.

6. A low-voltage distribution area microgrid control system, characterized in that, The system includes a main station and a low-voltage distribution area, each of which includes a memory and a processor. The memory stores a computer program, and the processors of the main station and the low-voltage distribution area execute their respective computer programs to jointly implement the method as described in any one of claims 1-4.

7. A computer-readable storage medium, characterized in that, The storage medium stores a computer program that, when executed by a plurality of processors, can implement the method as described in any one of claims 1-4.

Images