Hierarchical regulation and control method and device for power grid load resources, electronic equipment and storage medium

Abstract

The invention provides a power grid load resource hierarchical regulation and control method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring operation data of a power distribution network and hierarchical management data of load resources; determining adjustment potential information and power distribution characteristic information of load resources based on the power distribution network operation data and the hierarchical management data; constructing a global optimal operation mode model of the power distribution network, and constructing an objective function and constraint conditions based on the adjustment potential information and the power distribution characteristic information; solving the global optimal operation mode model of the power distribution network to obtain a model output result; dividing the load resources to obtain a plurality of local area load resources; generating load resource scheduling information for the plurality of local area load resources according to the model output result and the load resource information; and the operation state of the target load resource in the plurality of local area load resources is controlled based on the load resource scheduling information, so that stable and efficient operation of the power distribution network can be ensured.

Description

Technical Field

[0001] The present disclosure relates to the field of electric power technology, and in particular to a method, device, electronic device and storage medium for hierarchical control of power grid load resources. Background Art

[0002] With the continuous development of the economy, load resources of different types and sizes have grown rapidly, making it difficult to manage load resources. In addition, the existing distribution network operation strategy control sequence optimization technology has shortcomings when facing the increasing complexity and uncertainty of the distribution network, resulting in reduced power supply quality and reliability. Summary of the invention

[0003] In view of this, the purpose of the present disclosure is to propose a method, device, electronic device and storage medium for hierarchical control of power grid load resources.

[0004] Based on the above purpose, the first aspect of the present disclosure provides a method for hierarchical control of power grid load resources, including: Obtaining distribution network operation data and hierarchical management data of load resources; wherein the load resources are hierarchically managed based on load attributes, and data of the load resources after hierarchical management are obtained as the hierarchical management data; Determining the regulation potential information and power distribution characteristic information of the load resource based on the distribution network operation data and the hierarchical management data; Constructing a global optimal operation mode model of the distribution network, and constructing an objective function and constraint conditions of the global optimal operation mode model of the distribution network based on the regulation potential information and the power allocation characteristic information; Solving the global optimal operation mode model of the distribution network based on the objective function and the constraint conditions to obtain a model output result; Dividing the load resources based on the hierarchical management data to obtain multiple local area load resources; Obtaining load resource information of the plurality of local area load resources, and generating load resource scheduling information for the plurality of local area load resources according to the model output result and the load resource information; The operating state of a target load resource among the plurality of local area load resources is controlled based on the load resource scheduling information.

[0005] In some embodiments, the obtaining of the hierarchical management data includes: Obtain load device data of the load device; Acquiring load terminal data of a load terminal, wherein the load terminal is used to manage at least one load device within the same preset range; acquiring load group data of a load group, wherein the load group is used to manage at least one load terminal of the same type; Obtaining load aggregator data of a load aggregator, wherein the load aggregator is used to manage the load group; The hierarchical management data is determined based on the load equipment data, the load terminal data, the load group data, and the load aggregator data.

[0006] In some embodiments, the constructing of the global optimal operation mode model of the distribution network, and constructing the objective function and constraint conditions of the global optimal operation mode model of the distribution network based on the regulation potential information and the power distribution characteristic information, includes: Building a regulation potential model based on the regulation potential information, and setting the maximum adjustable potential utilization rate of the load resource as the objective function item of the objective function; A power allocation model is constructed based on the power allocation characteristic information, and the power allocation balance information is set as the constraint condition.

[0007] In some embodiments, it also includes: Acquire the correlation between the output of the power generation equipment and the load resource regulation amount information, determine the power generation cost based on the correlation between the output of the power generation equipment and the load resource regulation amount information, and set the power generation cost as the objective function item of the objective function; Acquire distribution information of load resources on nodes and lines based on the hierarchical management data, determine power flow distribution information of the distribution network based on the distribution information, and set the power flow distribution information as the constraint condition; The constraint condition is determined based on at least one of line capacity, node voltage, and load regulation information.

[0008] In some embodiments, the constructing of a global optimal operation mode model of a distribution network includes: Generate a graph structure based on the distribution network operation data and the distribution network topology structure, wherein the nodes of the graph structure represent devices in the distribution network, and the edges of the graph structure represent connection relationships between the devices; Extract features from the graph structure through a graph neural network, update feature representations of nodes through a message propagation mechanism, and dynamically adjust decision variables through reinforcement learning; The step of solving the global optimal operation mode model of the distribution network based on the objective function and the constraint conditions to obtain a model output result includes: The global optimal operation mode model of the distribution network is solved iteratively, the feasible domain is reduced by dynamically adding cutting plane constraints, and the distribution network operation information that satisfies the minimum operation cost is output as the output result of the model.

[0009] In some embodiments, said dividing the load resources based on the hierarchical management data includes: Acquire at least one of geographical distribution information of load resources, network topology association information, load characteristic information, and regulation potential information based on the hierarchical management data; The load resources are divided based on at least one of the geographical distribution information, network topology structure association information, load characteristic information, and regulation potential information of the load resources.

[0010] In some embodiments, generating load resource scheduling information for a plurality of local area load resources according to the model output result and the load resource information includes: Acquire at least one of complementarity information and regulation potential information of the local area load resources according to the load resource information; The load resource scheduling information is determined based on at least one of the complementarity information and the regulation potential information.

[0011] In some embodiments, before controlling the operating state of the target load resource in the load resources based on the load resource scheduling information, the method further includes: generating at least one of a load regulation cost and a load regulation accuracy based on the load resource scheduling information; Obtain a comparison result between at least one of the load regulation cost and the load regulation accuracy and a preset threshold, and modify the load resource scheduling information based on the comparison result.

[0012] A second aspect of the present disclosure provides a power grid load resource hierarchical control device, comprising: The acquisition module is configured to: acquire distribution network operation data and hierarchical management data of load resources; wherein the load resources are hierarchically managed based on load attributes, and the data of the load resources after hierarchical management are acquired as the hierarchical management data; A determination module is configured to: determine the regulation potential information and power distribution characteristic information of the load resource based on the distribution network operation data and the hierarchical management data; A model building module is configured to: build a global optimal operation mode model of the distribution network, and build an objective function and constraint conditions of the global optimal operation mode model of the distribution network based on the regulation potential information and the power distribution characteristic information; A model solving module is configured to solve the global optimal operation mode model of the distribution network based on the objective function and the constraint conditions to obtain a model output result; A division module is configured to: divide the load resources based on the hierarchical management data to obtain a plurality of local area load resources; A generating module is configured to: obtain load resource information of a plurality of said local area load resources, and generate load resource scheduling information for the plurality of said local area load resources according to the output result of the model and the load resource information; The control module is configured to control the operating state of the target load resource among the plurality of local area load resources based on the load resource scheduling information.

[0013] A third aspect of the present disclosure provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for hierarchical control of power grid load resources as described in the first aspect is implemented.

[0014] A fourth aspect of the present disclosure provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the power grid load resource hierarchical control method described in the first aspect.

[0015] From the above, it can be seen that the hierarchical control method, device, electronic device and storage medium of the power grid load resources provided by the present disclosure can obtain detailed information of each load resource and the correlation between them by hierarchical management of load resources, and then obtain the regulation potential information and power distribution characteristic information of the load resources in combination with the distribution network operation data, and evaluate the load resources through multiple dimensions; then, modeling and solving the global optimal operation mode are carried out according to the regulation potential information and power distribution characteristic information of the load resources, and then the scheduling strategy is determined in combination with the distribution network operation data and the regulation potential information, power distribution characteristic information and other information, so as to achieve all-round optimization and effectively improve the operation efficiency and economy of the distribution network; at the same time, the hierarchical control method of the power grid load resources described in this embodiment can adapt to a variety of complex needs, whether it is to deal with the fluctuation of power output of intermittent energy such as photovoltaic and wind power generation, or to deal with the problem of intelligent load participation and multi-time scale optimization, the method described in this embodiment can provide an effective solution through its hierarchical management, modeling analysis and optimization control mechanism to ensure the stable and efficient operation of the distribution network. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the present disclosure or related technologies, the drawings required for use in the embodiments or related technical descriptions are briefly introduced below. Obviously, the drawings described below are only embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0017] Figure 1A flowchart of an exemplary method provided by an embodiment of the present disclosure is shown.

[0018] Figure 2 A schematic diagram of a framework structure of load resource hierarchical management according to an embodiment of the present disclosure is shown.

[0019] Figure 3 A schematic diagram of an exemplary device provided by an embodiment of the present disclosure is shown.

[0020] Figure 4 A schematic diagram of the hardware structure of an exemplary computer device provided in an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0021] In order to make the objectives, technical solutions and advantages of the present disclosure more clearly understood, the present disclosure is further described in detail below in combination with specific embodiments and with reference to the accompanying drawings.

[0022] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present disclosure should be understood by people with ordinary skills in the field to which the present disclosure belongs. The "first", "second" and similar words used in the embodiments of the present disclosure do not indicate any order, quantity or importance, but are only used to distinguish different components. "Including" or "comprising" and similar words mean that the elements or objects appearing before the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0023] like Figure 1 As shown, the embodiment of the present disclosure provides a method for hierarchical control of power grid load resources, including: Step S101, obtaining distribution network operation data and hierarchical management data of load resources; wherein, the load resources are hierarchically managed based on load attributes, and the data of the load resources after hierarchical management are obtained as the hierarchical management data.

[0024] In this embodiment, the distribution network operation data can be obtained from the distribution network monitoring system.

[0025] In this embodiment, the load resources include air conditioners, electric water heaters, lighting equipment, electric vehicle charging piles and other different electrical equipment, that is, specific load equipment.

[0026] In this embodiment, each specific load device is divided based on the load attribute, and the specific load devices are divided into multiple groups. Each group of specific load devices is associated with a load terminal, and the group of load devices is managed through the load terminal; multiple load terminals are divided into one group and associated with a load group, and the group of load terminals is managed through the load group; each load group is associated with a load aggregator, and the load group is managed through the load aggregator, so that the load resources are hierarchically managed from specific load devices to load terminals, load groups, and load aggregators, so that all kinds of load resources in the distribution network can be fully covered. In this way, when a new load resource is added to the distribution network, it can be added to the group of existing specific load devices according to its load attributes and associated with the existing load terminals; or, the load resources newly added to the distribution network with the same load attributes can be separately associated with a new load terminal as a group and the load resource hierarchical management structure can be introduced, so as to ensure that load resources of different types and sizes can be well added to the distribution network.

[0027] In some embodiments, after obtaining the distribution network operation data and the hierarchical management data of load resources, it is also necessary to integrate the distribution network operation data and the hierarchical management data of load resources to facilitate subsequent analysis and modeling, and provide comprehensive data support for subsequent global optimal mode analysis and local collaborative strategy formulation.

[0028] In some embodiments, the distribution network operation data and the hierarchical management data of the load resources are processed, including: associating the data in the distribution network operation data with the corresponding data of the specific load equipment in the hierarchical management data of the load resources.

[0029] In some embodiments, there are some resources in the distribution network that are not managed by the distribution network, such as third-party load resources. The distribution network operation data contains real-time data of the third-party load resources when they are running, such as real-time power data, but there is no power data of the third-party load resources themselves. In this embodiment, by associating the real-time power data in the distribution network operation data with the power data of specific load devices in the hierarchical management data of load resources, the performance of each specific load device in the actual distribution network operation can be fully understood.

[0030] In some embodiments, the real-time power data in the distribution network operation data and the power data of specific load devices in the hierarchical management data of load resources can be associated and matched through unified data identification and indexing. For example, the unique identification code of the specific load device (such as the IMEI code for smart devices) can be used to associate the specific load device data with its operation data in the distribution network monitoring system to ensure that data from different sources can be accurately matched.

[0031] In some embodiments, the distribution network operation data and the hierarchical management data of the load resources are processed, including: cleaning and verifying the acquired data.

[0032] In this embodiment, after associating the data in the distribution network operation data with the corresponding data of the specific load equipment in the hierarchical management data of the load resources, the data needs to be cleaned to remove erroneous data, duplicate data and incomplete data. For example, in the distribution network monitoring system, there may be abnormal voltage values ​​caused by sensor failure. For the abnormal voltage values ​​caused by sensor failure, a reasonable threshold range is set to identify and correct them.

[0033] After that, the data is verified to ensure its accuracy and consistency. For example, the load demand forecast in the load plan should be consistent with the historical data and actual operation of the distribution network. If there is a large deviation, it needs to be re-evaluated and adjusted.

[0034] In some embodiments, the processing of distribution network operation data and hierarchical management data of load resources also includes: converting and normalizing the data. In this embodiment, according to the needs of data analysis and modeling in subsequent steps, the data is converted, including: unifying the units of the data, for example: converting power data into numerical values ​​in megawatts, and converting time data into a unified timestamp format. Afterwards, data of different magnitudes are normalized to facilitate calculation and analysis in the same model. For example, the voltage value is normalized to the [0,1] interval so that data of different voltage levels can be analyzed in the same evaluation system.

[0035] In the process of time data format processing, the unified formatting of time series data can be expressed as: = f ( T ) Where: T is the original time series data, is the formatted data, and f is the formatting function.

[0036] Step S103: determining the regulation potential information and power allocation characteristic information of the load resources based on the distribution network operation data and the hierarchical management data.

[0037] Different types of load resources have different regulation potential information, so it is necessary to determine the corresponding regulation potential evaluation method. For example, for air-conditioning load, its regulation potential information can be achieved by adjusting the set temperature, operating mode (cooling / heating switching), etc. Specifically, the regulation potential information of air-conditioning load under different conditions can be quantified according to the power-temperature curve of the air-conditioning equipment and the user's acceptable comfort range. The regulation potential information of industrial load can be determined based on factors such as production process and equipment operation status. Specifically, by analyzing the operating time and power demand of key equipment in the industrial production process, combined with the flexibility of the company's production plan adjustment, the regulation potential information of industrial load in different time periods is determined. For some special types of loads or newly emerging load types, a flexible model building method is used to determine their regulation potential information according to the attributes of the load resources. In this embodiment, load resources are classified and evaluated from multiple dimensions such as spatial scale, time scale, and operation mode.

[0038] Different types of load resources have different power allocation characteristic information, so it is necessary to determine the corresponding power allocation evaluation method. Taking the electric vehicle charging load as an example, its power allocation characteristic information can be determined based on factors such as the charging power, charging time, battery capacity and status of the electric vehicle. For industrial load groups, the power allocation characteristic information is determined based on the power requirements and production processes of each industrial equipment to ensure that the power balance and optimized operation of the distribution network are achieved while meeting production needs.

[0039] Step S105, constructing a global optimal operation mode model of the distribution network, and constructing an objective function and constraint conditions of the global optimal operation mode model of the distribution network based on the regulation potential information and the power allocation characteristic information.

[0040] In this embodiment, a global optimal operation mode model of the distribution network based on mixed integer linear programming (MILP) can be constructed. When constructing the global optimal operation mode model of the distribution network, the regulation potential information and power distribution characteristic information of the load resources are considered, and the management of load resources is incorporated into the objective function and constraint conditions of the global optimal operation mode model of the distribution network.

[0041] Step S107, solving the global optimal operation mode model of the distribution network based on the objective function and the constraint conditions to obtain a model output result.

[0042] In this embodiment, with the goal of minimizing the operating cost, the global optimal operating mode model of the distribution network is solved by a professional optimization algorithm solver (such as CPLEX or Gurobi), and the model output result, that is, the global optimal operating mode, is obtained.

[0043] In this embodiment, a single-objective optimization method (such as a method for minimizing regulation costs) and a dual-objective optimization method (considering system stability and sustainability under extreme load scenarios) can be used. For example, in the multi-period optimization scheduling strategy, the grid frequency safety factor is considered, the regulation costs of each load group are balanced, and the regulation power of each load group is ensured to fall within a relatively low cost range; in extreme load scenarios, the management cost and error cost are comprehensively considered, and the stable operation of the system is achieved through a dual-objective collaborative optimization method.

[0044] Step S109: Divide the load resources based on the hierarchical management data to obtain load resource information of multiple local area load resources.

[0045] In this embodiment, the distribution and characteristics of load resources are obtained based on hierarchical management data, and the load resources are divided based on the distribution and characteristics of load resources to obtain multiple local area load resources, each of which contains load resources with similar load characteristics and regulation potential.

[0046] Step S111: generating load resource scheduling information for a plurality of local area load resources according to the model output result and the load resource information of a plurality of local area load resources.

[0047] In this embodiment, based on the global optimal operation mode and load resource information of multiple local area load resources, the power exchange strategy and load regulation strategy between regions are determined to improve the operation efficiency and stability of the entire distribution network.

[0048] Step S113: controlling the operating status of a target load resource among the plurality of local area load resources based on the load resource scheduling information.

[0049] In this embodiment, by performing hierarchical management on load resources, detailed information of each load resource and the correlation between them can be obtained, and then the regulation potential information and power distribution characteristic information of the load resources can be obtained in combination with the distribution network operation data, and the load resources can be evaluated through multiple dimensions; then, modeling is performed and the global optimal operation mode is solved based on the regulation potential information and power distribution characteristic information of the load resources, and then the scheduling strategy is determined in combination with the distribution network operation data and various information such as the regulation potential information and power distribution characteristic information, so as to achieve all-round optimization and effectively improve the operation efficiency and economy of the distribution network; at the same time, the hierarchical control method of power grid load resources described in this embodiment can adapt to a variety of complex needs, whether it is to cope with the fluctuation of power output of highly intermittent energy such as photovoltaic and wind power generation, or to deal with the problems of intelligent load participation and multi-time scale optimization, the method described in this embodiment can provide effective solutions through its hierarchical management, modeling analysis and optimization control mechanism to ensure the stability and efficient operation of the power grid.

[0050] In some embodiments, the distribution network operation data may include real-time operation section data of the distribution network and boundary condition data under multivariate planning scenarios.

[0051] In some embodiments, the real-time operation section data of the distribution network includes electrical quantity information, equipment operation status information, distributed power source information, load information, and time information.

[0052] In this embodiment, the electrical quantity information includes information such as voltage, current, power, etc. Among them, the voltage information includes information such as node voltage amplitude (V), voltage phase angle (θ), etc.

[0053] The node voltage amplitude (V) is used to indicate the current voltage of each node in the distribution network, in volts (V). For example, the voltage amplitude of node A is 10.5kV. This is one of the important indicators for measuring the power quality of the distribution network. Too high or too low voltage may affect the normal operation of electrical equipment.

[0054] Voltage phase angle (θ) is used to represent the phase angle of node voltage, in degrees (°). Phase angle information is essential for analyzing power flow distribution and power transmission in distribution networks. For example, in a three-phase AC system, the difference in voltage phase angles at different nodes affects the reactive power flow on the line.

[0055] The current information includes node current amplitude (I), current phase angle (φ) and other information.

[0056] The node current amplitude (I) is used to reflect the current flowing through each node, in amperes (A). For example, the current amplitude of node B is 300A. By monitoring the current amplitude, it is possible to detect in time whether there is an overload risk on the line.

[0057] The current phase angle (φ) is used to represent the phase angle of the node current, in degrees (°). The difference between the current phase angle and the voltage phase angle can be used to calculate parameters such as the power factor.

[0058] Power information includes active power (P), reactive power (Q), apparent power (S) and other information.

[0059] Active power (P) is used to represent the actual electrical energy consumed or generated by a node, in watts (W). Positive values ​​indicate that the node consumes power, and negative values ​​indicate that the node generates power (such as distributed power sources feeding power into the grid). For example, the active power of an industrial load node is 500kW.

[0060] Reactive power (Q) is used to reflect the energy exchange used to establish magnetic and electric fields in the power grid, and its unit is var. Reactive power has an important impact on the voltage stability of the power grid and the operating efficiency of equipment. For example, the reactive power of a substation is 200 var.

[0061] Apparent power (S) is the product of voltage and current, measured in volt-amperes (VA). Apparent power is equal to the square root of the sum of the squares of active power and reactive power, or The apparent power (S) reflects the overall capacity demand of the power grid.

[0062] In this embodiment, the equipment operation status information includes information such as the switch status (SW), the protection device action signal (PROT), etc.

[0063] The switch status (SW) is used to indicate the open and closed status of each switch (such as circuit breakers, disconnectors, etc.) in the distribution network. Usually, 0 indicates that the switch is open, and 1 indicates that the switch is closed. For example, if the incoming switch status of a line is 1, it means that the switch is in the closed state and the line is powered normally.

[0064] The protection device action signal (PROT) is used to mark the action of the protection device. When the protection device (such as overcurrent protection, overvoltage protection, etc.) in the distribution network is activated, a corresponding signal will be issued. The protection device action signal (PROT) is used to record the action of the protection device. For example, 1 indicates that the protection device is activated, and 0 indicates that it is not activated. If an overcurrent fault occurs in a line, the corresponding overcurrent protection device action signal is 1.

[0065] In this embodiment, the distributed power source information includes information such as distributed power source output (P_gen), distributed power source access point information (P_conn), and the like.

[0066] Distributed power output (P_gen) is used to indicate the current power generation of distributed power sources (such as solar photovoltaic power generation, small wind power generation, etc.) in the distribution network, in watts (W). For example, the output of a solar photovoltaic power station at a certain moment is 20kW.

[0067] Distributed generation access point information (P_conn) is used to indicate the access location of the distributed generation in the distribution network, including the access node number, line number, etc. For example, a distributed generation is connected to the 10kV line L1 where node C is located.

[0068] In this embodiment, the load information includes information such as load type (Load_type), load importance level (Load_importance), etc.

[0069] Load type (Load_type) is used to classify and identify different types of loads, such as residential load, industrial load, commercial load, etc. It can be represented by a number or character code, for example, 1 represents residential load, 2 represents industrial load, 3 represents commercial load; or a represents residential load, b represents industrial load, c represents commercial load, etc.

[0070] Load importance level (Load_importance) can be divided into different load importance levels according to the load's requirements for power supply reliability. For example, primary load (such as important medical equipment in hospitals, important communication hubs, etc.), secondary load (such as large shopping malls, office buildings, etc.) and tertiary load (such as ordinary residences, general factories, etc.). The numbers 1, 2, and 3 can also be used to represent different importance levels.

[0071] Time information includes the data collection timestamp (Timestamp). The timestamp (Timestamp) is used to indicate the specific time of the real-time operation section data collection of the distribution network, and the format is usually year-month-day hour: minute: second. For example, 2024-01-0110:30:00 is used for subsequent data analysis and processing to understand the operating status of the distribution network at different time points.

[0072] The real-time operation section data of the distribution network also includes other auxiliary information such as data quality mark (Data_quality), remarks information (Remarks), etc.

[0073] The data quality flag (Data_quality) is used to identify the quality of real-time cross-section data. For example, 0 indicates good data quality, and 1 indicates data anomalies (such as sensor failure, communication interference, etc.). If the voltage data of a node is abnormal due to sensor failure, its data quality flag is 1.

[0074] Remarks are used to indicate other information related to the real-time operation section data, such as whether special operation is performed, whether there is temporary equipment maintenance, etc. For example, during a certain period of time, due to planned maintenance of the line, the operation data of the relevant nodes may be affected, and the maintenance situation is noted in the remarks.

[0075] The boundary condition data in the multi-planning scenario includes load demand forecast information and distributed generation access plan information.

[0076] Load demand forecast information can be obtained according to the load plan. The load plan in the boundary condition data provides the expected demand for various types of loads in different time periods in the future. Based on these data, the load conditions of the distribution network in different time periods can be predicted, which helps to understand the load conditions of the distribution network at different times in the future, thereby helping to optimize power generation plans and load distribution. In some embodiments, the demand patterns of residential loads and commercial loads will be different on weekdays and weekends, in different time periods, and in different seasons: on weekdays, the residential load in the evening peak is greater than the residential load in the morning peak, and the residential load in the afternoon is greater than the commercial load in the morning peak. On weekends, the residential load in the morning is less than the residential load in the afternoon, and the commercial load in the morning is greater than the commercial load in the afternoon; the residential load and commercial load in the afternoon in summer will increase compared to other seasons, and the residential load in the evening in winter will increase compared to other seasons. The load plan can help predict these demand changes to obtain load demand forecast information, so as to adjust the power generation and load distribution strategies based on the load demand forecast information. For example, the residential electricity demand on weekends is higher, and the power generation power of distributed power sources may need to be increased.

[0077] Distributed power access plan information includes the access location, capacity, and power generation forecast of distributed power sources such as solar photovoltaic power generation and small wind power generation devices, which has an important impact on the power flow distribution and voltage control of the distribution network. If a region plans to access a large amount of solar photovoltaic power generation, the load plan can help predict the power generation of these distributed power sources, thereby optimizing the power flow distribution of the distribution network and avoiding overload and voltage fluctuations.

[0078] In some embodiments, Figure 2 As shown, load resources are managed in four levels, from load equipment to load terminals, load groups and load aggregators.

[0079] Load equipment includes various specific electrical equipment, such as air conditioners, electric water heaters, lighting equipment, electric vehicle charging piles, etc. The load equipment data obtained for different load equipment are different: for air conditioners, it is necessary to obtain its model, power, operation mode (cooling / heating), set temperature and other load equipment data; for electric water heaters, it is necessary to obtain its capacity, heating power, current water temperature and other load equipment data; for lighting equipment, it is necessary to obtain power, switch status and usage time preference and other load equipment data; for electric vehicle charging piles, it is necessary to obtain its charging power, charging interface type, communication protocol with the power grid and other load equipment data.

[0080] The load terminal manages load devices within a preset range, such as loads with the same attributes within a user, a shopping mall, or a workshop. The data obtained from the load terminal includes the number and type distribution of the load devices managed by the load terminal, the communication status between the load terminal and the distribution network, etc. For example, a load terminal in a shopping mall may manage a large number of lighting equipment, air conditioning equipment, and some commercial electrical equipment. It is necessary to know the overall operation status of these devices and whether the communication between the load terminal and the distribution network is stable.

[0081] A load group is a collection of load terminals of the same type. The data obtained from the load group includes the number of load terminals, the geographical distribution of each load terminal (if relevant), the overall power demand characteristics of the load group, etc. For example, for a load group composed of air-conditioning load terminals in multiple residential communities, it is necessary to understand the power demand variation patterns of the group in different seasons and time periods. A load aggregator is an entity that performs joint optimization control of multiple load groups. The load group data obtained from the load aggregator includes the list of load groups it manages, the optimization control strategy for each load group, and the interaction agreement with the distribution network operator. For example, the load aggregator may adopt a time-sharing aggregation strategy to adjust the power output of the load groups it manages according to the electricity price and grid load conditions in different time periods.

[0082] Among them, the load terminal is realized through the virtual energy node (Virtual Energy Node, VEN), the load group is realized through the virtual energy node or virtual transformer node (Virtual Transformer Node, VTN), and the load aggregator is realized through the virtual transformer node.

[0083] Virtual energy nodes refer to the virtualization of multiple physical energy devices (such as distributed generation, energy storage equipment, electric vehicles, etc.) into a unified energy supply point in the smart grid through software and communication technology. This virtualization technology enables these decentralized energy devices to participate in the operation and management of the grid as a whole, thereby improving energy utilization efficiency and grid stability.

[0084] Virtual transformer node refers to the use of software-defined network technology and intelligent control technology to virtualize multiple physical transformers and their related equipment into a unified transformer node. This virtualization technology can achieve flexible configuration and dynamic adjustment of transformers to adapt to changes in grid load and improve grid operation efficiency and reliability.

[0085] Load aggregators, load groups and load terminals are managed and optimized through virtual energy nodes and virtual transformer nodes to achieve hierarchical management of load resources and coordinated control of source, grid, load and storage.

[0086] Based on the above-mentioned hierarchical management framework of load resources, the acquisition of the hierarchical management data includes: acquiring load equipment data of the load equipment; acquiring load terminal data of the load terminal, the load terminal is used to manage at least one load equipment within the same preset range; acquiring load group data of the load group, the load group is used to manage at least one load terminal of the same type; acquiring load aggregator data of the load aggregator, the load aggregator is used to manage the load group; determining the hierarchical management data based on the load equipment data, the load terminal data, the load group data and the load aggregator data.

[0087] The load equipment data may include equipment identification information, equipment operating parameters, operating modes, setting parameters, etc. Equipment identification information includes equipment number, equipment type, etc. The equipment number is the unique identification code of each load equipment, which is used to accurately identify and manage the equipment in the system. The equipment type identifies the specific category of the load equipment, such as air conditioners, electric water heaters, lighting equipment, electric vehicle charging piles, etc.

[0088] Equipment operating parameters include power-related information such as rated power and real-time power. Rated power is the rated power of the equipment under normal operating conditions, in watts (W). For example, the rated power of a certain model of air conditioner is 2500W. Real-time power is the current operating power of the equipment, reflecting the actual power consumed by the equipment, in watts (W). By real-time monitoring of real-time power, you can understand the energy consumption of the equipment.

[0089] Different types of equipment have different operating modes. For example, the operating modes of air-conditioning equipment include cooling, heating, dehumidification, ventilation, etc. The operating modes of lighting equipment include switch status (on / off), and the operating modes of electric vehicle charging piles include charging status (charging / stop charging).

[0090] The setting parameters include temperature setting and charging parameters. For air conditioners, electric water heaters and other equipment, the temperature setting is used to record the temperature value set by the user. For electric vehicle charging piles, the charging parameters include charging power setting, charging time setting, etc.

[0091] Load terminal data includes basic terminal information, terminal management information, terminal communication and operating status, etc.

[0092] The basic terminal information includes terminal number, terminal location and other information. The terminal number is a unique identifier of the load terminal, which is used to distinguish different terminal devices. The terminal location is used to record the specific geographical location or area where the load terminal is located, such as a shopping mall, a community, a factory workshop, etc.

[0093] Terminal management information includes the number of managed load devices, load device type distribution and other information. The number of managed load devices is used to count the total number of various load devices managed by the terminal. For example, the number of load devices managed by a shopping mall load terminal is 500. The load device type distribution is used to record in detail the number and proportion of different types of load devices managed by the terminal. For example, there are 200 lighting devices, accounting for 40%; 150 air conditioning devices, accounting for 30%; and 150 commercial electrical equipment, accounting for 30%.

[0094] The terminal communication and operation status includes information such as the communication status with the distribution network and the data transmission success rate. The communication status with the distribution network can be represented by 0 for normal communication and 1 for abnormal communication; or 1 for normal communication and 0 for abnormal communication. For example, the current communication status between the terminal and the distribution network is 0, indicating normal communication. The data transmission success rate is used to count the proportion of the number of successful data transmissions from the terminal to the management system to the total number of transmissions within a certain period of time, expressed as a percentage. For example, the data transmission success rate is 98%.

[0095] The load group data includes information such as the basic information of the load group and the characteristic data of the load group.

[0096] The basic information of the load group includes the load group number, the number of load terminals included, the geographical coverage, and other information. The load group number is the unique identification code for each load group. The number of load terminals included is used to record the specific number of load terminals that make up the load group. For example, the air conditioning load group of a residential community contains 200 load terminals. The geographical coverage is used to describe the geographical area covered by the load group, such as several adjacent residential communities, a specific floor of a commercial area, etc.

[0097] The load group characteristic data includes information such as overall power demand characteristics, power demand curves for different time periods, and seasonal power demand change patterns. The power demand curves for different time periods are used to record the changes in power demand for the load group in different time periods. The curves are usually drawn with time as the horizontal axis and power demand as the vertical axis. For example, in the summer evening from 19:00 to 21:00, the power demand of the air-conditioning load group in the residential area reaches its peak. The seasonal power demand change pattern is used to identify the power demand characteristics of the load group in different seasons. For example, in winter, heating equipment is used more frequently, and the power demand is relatively high; in summer, refrigeration equipment is used frequently, and the power demand is also large.

[0098] Load aggregator data includes basic information of the aggregator, load group management information, optimization control strategy for each load group, and interaction information with distribution network operators.

[0099] The basic information of the aggregator includes the aggregator number, aggregator name, and region. The aggregator number is the unique identifier of the load aggregator; the aggregator name is the company name of the load aggregator; the region is used to identify the geographical location of the load aggregator, such as a city or a region.

[0100] The load group management information includes a list of managed load groups, which is used to list the numbers, names and basic information of all load groups managed by the load aggregator.

[0101] The optimization control strategies for each load group include time-sharing aggregation strategy and demand response strategy. The time-sharing aggregation strategy is used to formulate power regulation strategies for load groups according to the electricity prices and grid load conditions in different time periods. For example, during the low electricity price period, the power consumption of the load group is increased; during the peak electricity price period, the power demand of the load group is reduced. The demand response strategy is the demand response measures taken when the grid encounters an emergency or load adjustment is required. For example, some load groups are required to suspend electricity use for a period of time to relieve the pressure on the grid.

[0102] The information exchanged with the distribution network operator includes the interaction protocol and data interaction record. The interaction protocol is used to clarify the rules such as the format, content and frequency of data interaction between the load aggregator and the distribution network operator. For example, the power forecast data, regulation instructions and other information of the load group are exchanged regularly every day. The data interaction record is used to identify the time, content and results of each data interaction with the distribution network operator for subsequent query and analysis.

[0103] In this embodiment, through the hierarchical management of load resources from load equipment to load terminals, load groups, and load aggregators at four levels, all types of load resources in the distribution network can be fully covered; in the source-grid-load-storage collaboration, this hierarchical structure helps to clarify the management focus and collaboration methods of loads at different levels; load terminals manage the loads within a single user or place, load groups aggregate terminals of the same type, and load aggregators perform joint optimization control on load groups of different types, thereby achieving orderly collaboration from bottom-level equipment to high-level, and improving the ability of the distribution network to cope with fluctuations in renewable energy; for the participation of smart loads, this hierarchical structure facilitates the inclusion of smart loads (such as electric vehicle charging facilities, controllable loads, etc.) into the corresponding management level. For example, electric vehicle charging facilities can be included in the management scope of appropriate load groups or load aggregators based on their distribution and usage characteristics in the distribution network, and their charging behavior can be effectively regulated through hierarchical management, thereby improving the flexibility and adaptability of the distribution network.

[0104] In this embodiment, through the hierarchical management of load resources, comprehensive and accurate load information is provided, covering multi-level data from specific equipment to load groups, load aggregators, such as the model and power of specific load equipment, the number of equipment managed by load terminals, communication status, etc., and the overall power demand characteristics of load groups, etc., to provide refined data support for the operation analysis of the distribution network; in-depth analysis of the characteristics and behaviors of load resources provides a rich foundation for the operation analysis of the distribution network, such as analyzing the characteristics and behavior patterns of different types of load resources to provide a basis for formulating operation strategies; incorporating information such as the load resource regulation potential into the global optimal operation mode model, such as quantifying the different types of load resources. The regulation potential of different types of loads is considered, and the objective function is added to reflect the regulation potential, which helps to optimize the relationship between power generation cost, network loss cost and load resource regulation potential, and supports the global optimization operation of the distribution network; power allocation models are established for different types of loads and reflected in the constraints to ensure reasonable power allocation and achieve power balance and optimized operation of the distribution network; local areas are reasonably divided so that the load resource characteristics and regulation potential within the area are similar, which promotes the coordinated operation of local areas and facilitates management and control; inter-regional coordination strategies are formulated to utilize the complementarity of load resources and differences in regulation potential to achieve power exchange and load regulation, and improve the operating efficiency and stability of the distribution network.

[0105] In some embodiments, the step S105 of constructing a global optimal operation mode model of the distribution network, and constructing an objective function and constraint conditions of the global optimal operation mode model of the distribution network based on the regulation potential information and the power distribution characteristic information, includes: Step S201: constructing a regulation potential model based on the regulation potential information, and setting the maximization of the adjustable potential utilization rate of the load resources as the objective function item of the objective function.

[0106] In this embodiment, an objective function item determined based on the load resource regulation potential is added to the objective function of the global optimal operation mode model of the distribution network based on MILP. For example, maximizing the adjustable potential utilization of load resources is added as an objective function item to the objective function of the global optimal operation mode model of the distribution network to improve the distribution network's ability to cope with renewable energy fluctuations and load changes.

[0107] In addition to the traditional power generation cost and network loss cost, it is necessary to add an objective term related to the load resource regulation potential. For example, an objective function term can be set to maximize the utilization rate of the load resource's adjustable potential to improve the distribution network's ability to cope with renewable energy fluctuations and load changes.

[0108] The regulation potential of load resources is expressed as P reg (For each load resource or load group), the total regulation potential is ∑P reg , then the objective function can be expressed as: minZ=C gen +C loss -λ∑P reg Among them, C gen is the power generation cost, C loss is the network loss cost, and λ is a weight coefficient used to balance the relationship between power generation cost, network loss cost and load resource regulation potential.

[0109] In some embodiments, information such as power generation cost and network loss cost can also be used together with objective function items determined based on load resource regulation potential as objective function items of the objective function of the global optimal operation mode model of the distribution network.

[0110] Step S203: construct a power allocation model based on the power allocation characteristic information, and set the power allocation balance information as the constraint condition.

[0111] In this embodiment, constraints related to the power allocation characteristic information of the load resources are added to the constraint conditions of the global optimal operation mode model of the distribution network. The power allocation characteristic information may include power allocation balance information. For example, for a distribution network in a certain local area, its total power input should be equal to the sum of the power allocations of each load resource, that is: P total =∑P i Among them, P total is the total power input in the local area, P i is the power allocation of the i-th load resource.

[0112] At the same time, it is also necessary to consider the impact of the power allocation of load resources on their own operating characteristics and the stability of the distribution network. For example, for the air-conditioning load group, its power allocation cannot cause voltage fluctuations exceeding the allowable range, that is: ∣V i - V0|≤ΔV max Among them, V i is the node voltage after power distribution, V0 is the initial node voltage, ΔV max is the allowable voltage fluctuation range.

[0113] In this embodiment, when constructing the global optimal operation mode model of the distribution network, it is necessary to clearly define the variables related to load resource management. For example, define the variable x ij Indicates whether the i-th load resource participates in regulation in the j-th time period (0 means not participating, 1 means participating), and the variable y ij It represents the power allocation of the i-th load resource in the j-th time period.

[0114] These variables are associated with other operating parameters of the distribution network (such as the output of power generation equipment, power flow of lines, etc.) to establish mathematical relationships between them.

[0115] In some embodiments, the method further includes: obtaining the correlation between the output of the power generation equipment and the load resource regulation information, determining the power generation cost based on the correlation between the output of the power generation equipment and the load resource regulation information, and setting the power generation cost as the objective function item of the objective function.

[0116] There is a balance between the regulation of load resources and the output of power generation equipment. When load resources are involved in regulation, it will affect the energy balance of the entire distribution network. For example, during peak load periods, if the total load demand is reduced by adjusting the load (such as cutting some interruptible loads), the output of power generation equipment can be reduced accordingly.

[0117] Assume that the output of the power generation equipment is P gen , the load resource adjustment amount is ΔP load , the initial power balance equation of the distribution network is P gen0 =P load0 +P loss0 (where P load0 is the initial load, P loss0 is the initial line loss). After the load resources are adjusted, the new power balance equation becomes P gen1 =(P load0 -ΔP load )+P loss1 (where P gen1 is the output of the power generation equipment after adjustment, P loss1 is the adjusted line loss).

[0118] Different types of power generation equipment have different relationships with load regulation. For example, renewable energy generation (such as solar energy and wind energy) is limited by natural conditions, and its output has certain intermittency and uncertainty. When the load resource regulation potential is large, it can better match the output fluctuations of renewable energy. For example, during the peak period of solar power generation, if the load resources can be appropriately increased (such as increased demand for electric vehicle charging), the dependence on traditional fossil fuel power generation equipment can be reduced.

[0119] In this embodiment, this relationship is described by establishing an objective function based on an optimization algorithm. For example, in a global optimal operation mode model of a distribution network based on mixed integer linear programming (MILP), the objective function is minZ=C gen +C loss λ-∑P reg (C gen is the power generation cost, C lossis the network loss cost, λ is the weight coefficient, P reg is the regulation potential of load resources). Here C gen Related to the output of power generation equipment, by adjusting the regulation potential and power allocation of load resources, the optimal output of power generation equipment can be influenced, thereby minimizing costs.

[0120] In some embodiments, the method further includes: acquiring distribution information of load resources on nodes and lines based on the hierarchical management data, determining flow distribution information of the distribution network based on the distribution information, and setting the flow distribution information as the constraint condition.

[0121] In this embodiment, the distribution of load resources on different nodes and lines will affect the power flow distribution of the lines. For example, in a distribution network, if the load in a certain local area increases, according to Kirchhoff's law, the current on the lines connected to the area will increase, thereby changing the power flow distribution of the lines.

[0122] In this embodiment, the distribution information of load resources on nodes and lines is obtained based on the hierarchical management data, and then the power flow distribution information of the power distribution network is determined based on the distribution information, and the power flow distribution information is set as the constraint condition.

[0123] Specifically, let the impedance of a line be Z, and the voltages at both ends be V1 and V2. According to Ohm's law, the current on the line is I = (V1- V2) Z. When the load resource generates power flow on the line, the difference between V1 and V2 will change, thereby affecting the current.

[0124] In the steady-state analysis of distribution networks, node voltage equations are usually used to describe power flow distribution. For a distribution network with n nodes, the node voltage equation is: ∑

[0125] Among them, Y j is the node admittance matrix element, I i Inject current into the node, S i is the node complex power, S i ∗ is its conjugate complex number, and V is the node voltage.

[0126] When the load resources change, it will affect the node injection current Ii, thereby changing the node voltage Vi and line flow. For example, when the load devices managed by a load terminal increase, the injection current of the node increases, and the node voltage equation can be used to calculate the voltage changes of other nodes and the flow changes on the line.

[0127] In this embodiment, when constructing the global optimal operation mode model of the distribution network, it is necessary to convert the load resource regulation potential information P reg, power distribution amount y ij Load resource management variables are incorporated into the same mathematical model along with other operating parameters such as power generation equipment output and line flow.

[0128] For example, in this model, the power balance equation ( =P total , where P i is the power allocation of each load resource, P total is the total power demand), line capacity limitations (such as P line ≤P max ) are set as constraints, which are interrelated with load resource management variables and other operating parameters. Through this setting, a comprehensive description and optimization control of the distribution network operation status can be achieved, ensuring that the distribution network can achieve efficient operation and optimized management under different resource and constraint conditions.

[0129] In some embodiments, the method further comprises: determining the constraint condition based on at least one of line capacity, node voltage, and load regulation information.

[0130] In this embodiment, at least one of the line capacity constraint, the node voltage constraint, and the load regulation information constraint may be added to the constraint conditions of the global optimal operation mode model of the distribution network.

[0131] Among them, the power balance constraint is: Pgen，i =∑ Pload，k +∑P loss，j Line capacity constraint: P line，j ≤P max，j Voltage Constraint: V min ≤V i ≤V max Load regulation constraint: |V i - V0|≤ΔV max , where V i is the regulated node voltage.

[0132] In some embodiments, the step S105 of constructing a global optimal operation model of the distribution network includes: A graph structure is generated based on the distribution network operation data and the distribution network topology structure, wherein the nodes of the graph structure represent the devices in the distribution network, and the edges of the graph structure represent the connection relationship between the devices; features of the graph structure are extracted through a graph neural network, and the feature representation of the nodes is updated through a message propagation mechanism, and decision variables are dynamically adjusted through reinforcement learning.

[0133] In this embodiment, the topological structure and operation data of the distribution network are converted into a graph structure, where nodes represent devices (such as generators, loads, switches), and edges represent the connection relationship between devices. The device node set V and edge set E are expressed as: V = {v1, v2, …, v N},E={(v i , v j )|vi,vj∈V}, Among them, each node v i The eigenvector x i Including the power, voltage, regulation potential, etc. of the equipment.

[0134] In this embodiment, the graph structure is feature extracted through the graph neural network GNN, and the feature representation of the variable nodes and constraint nodes is updated through the message propagation mechanism. The message propagation mechanism of GNN can be expressed as:

[0135] Among them, h i (l+1) is the hidden state of node i in layer L, N(i) is the neighborhood of node i, W (l) and b (l) are learnable weights and biases, and σ is the activation function.

[0136] The decision variables in the optimization process are dynamically adjusted through reinforcement learning RL strategy. Among them, the decision variables include continuous variables and integer variables. Continuous variables include the output P of the power generation equipment gen，i 、Line flow P line，j The integer variable includes the start and stop status of the load resource x load，k (0 means not participating in regulation, 1 means participating in regulation) and other information.

[0137] The reward function R(τ) of reinforcement learning RL is designed according to the quality of the current solution (such as the objective function value and constraint satisfaction). For example, for trajectory τ, the reward function can be expressed as:

[0138] Where rt is the immediate reward at time step t and γ is the discount factor.

[0139] In this embodiment, a deep learning model (such as Transformer) is also used as a policy network to select the optimal action based on the current state. The update of the policy network can be achieved through the policy gradient method:

[0140] where pθ(τ) is the probability of trajectory τ under policy parameters θ.

[0141] In this embodiment, the proximal policy optimization (PPO) algorithm can also be used to improve the stability of policy updates. The optimization goal of PPO can be expressed as:

[0142] Where δtn is the timing difference error (TD-error), is the cropping parameter.

[0143] In some embodiments, the step S107 of solving the global optimal operation mode model of the distribution network based on the objective function and the constraint condition to obtain the model output result includes: The global optimal operation mode model of the distribution network is solved iteratively, the feasible domain is reduced by dynamically adding cutting plane constraints, and the distribution network operation information that satisfies the minimum operation cost is output as the output result of the model.

[0144] In this embodiment, based on the power generation cost C gen , Network loss cost C loss and the utilization rate of load resource regulation potential P reg Generate the objective function and minimize the running cost: minZ=C gen +C loss -λ∑P reg , where: λ is the weight coefficient, which is used to balance the relationship between different objectives.

[0145] In this embodiment, combining the features extracted by the graph neural network and the reinforcement learning strategy, solving the global optimal operation mode model of the distribution network includes: temporarily relaxing the integer constraints, solving the linear programming (LP) problem, and obtaining a relaxed solution; branching the relaxed solution, creating sub-problems, and selecting the optimal branch through the RL strategy; in the solution process, adding cutting plane constraints as needed to narrow the feasible domain to strengthen the model; dynamically adjusting the variable values ​​through the RL strategy, gradually approaching the optimal solution, and obtaining the distribution network operation information that satisfies the minimum operating cost as the output result of the model. In some embodiments, the division of the load resources based on the hierarchical management data in step S109 includes: Step S301, obtaining at least one of geographical distribution information of load resources, network topology association information, load characteristic information, and regulation potential information based on the hierarchical management data.

[0146] The hierarchical management of load resources provides a wealth of information on the geographical distribution of load resources, load characteristics, and regulation potential, which are important bases for dividing local areas. For example, based on the distribution of load resources in geographic space (load differences in different functional areas), areas with similar geographical locations and similar load types are divided into a local area; combined with load characteristic information (such as seasonality and time period of air conditioning load, relative stability of industrial load) and regulation potential information (electric vehicle charging load has large regulation potential, and some industrial loads have small regulation potential), the division of local areas is further optimized, so that the load characteristics and regulation potential of load resources in the same area are similar, reducing communication costs and power transmission losses between regions, and improving the management efficiency of the distribution network.

[0147] Step S303: dividing the load resources based on at least one of the geographical distribution information, network topology association information, load characteristic information, and regulation potential information of the load resources.

[0148] In this embodiment, the distribution of load resources in geographical space affects its regulation efficiency. For example, in an urban distribution network, the distribution of load resources in different functional areas (such as commercial areas, residential areas, and industrial areas) is significantly different. Commercial areas usually concentrate a large number of commercial electrical equipment, such as lighting, air conditioning and other loads in large shopping malls; residential areas are dominated by residential electrical equipment, such as household appliances; and the load resources in industrial areas are mainly the electricity demand of various industrial production equipment. Based on the geographical distribution information, areas with similar geographical locations and similar load types are divided into a local area. In this way, the communication cost and power transmission loss between regions can be reduced during subsequent regulation, thereby improving the management efficiency of the distribution network.

[0149] In this embodiment, the network topology of the distribution network also has an important influence on the division of local areas. For example, in a distribution network with a ring network structure, the division can be performed according to the load resource conditions on each branch line of the ring network. Load resources with similar load characteristics on the same branch line are divided into a local area, which facilitates monitoring and control of the operating status of the branch line.

[0150] In this embodiment, load characteristics can affect the regulation of load resources. Different types of load resources have different load characteristics. For example, air-conditioning load has obvious seasonal and time characteristics. The load demand is large in summer and winter, and its power consumption is closely related to factors such as the set temperature and outdoor temperature; while industrial load is relatively stable, but there may be large power fluctuations at different stages of the production process. Local areas are divided according to the similarity of load characteristics, and load resources with similar load change patterns (such as consistent peak and valley time periods, the same sensitivity to electricity prices, etc.) are divided into the same local area, so that subsequent scheduling based on inter-regional scheduling can be achieved based on the load characteristics of the load resources.

[0151] In this embodiment, the regulation potential of each load resource is evaluated. For example, the electric vehicle charging load has a large regulation potential, and can adapt to the needs of the distribution network by adjusting the charging time, charging power, etc.; while some industrial loads have relatively small regulation potential due to the particularity of their production processes. Load resources are divided based on the regulation potential information to ensure that each local area contains load resources with similar regulation potential. This makes it easy to formulate a unified regulation strategy and improve regulation efficiency. For example, in a local area, if most load resources have a large regulation potential, a more flexible regulation strategy can be adopted, such as demand response.

[0152] In this embodiment, according to the geographical distribution information of load resources, network topology association information, load characteristic information, regulation potential information and other factors, the reasonable division and management of local areas are realized, the communication cost and power transmission loss between regions are reduced, and the management efficiency of the distribution network is improved. For example, areas with similar geographical locations and similar load types are divided into a local area, which is convenient for monitoring and controlling the operating status of the area. In this embodiment, by analyzing the complementarity of load resources between regions, an effective inter-regional coordination strategy is formulated to achieve power complementarity between regions. For example, the interruptible load in the commercial area is reduced during the peak load period of the power grid, and the energy storage equipment in the residential area stores electric energy during the valley load period and releases it during the peak period to meet the needs of the entire distribution network. In this embodiment, by formulating a joint regulation strategy, according to the regulation potential and response speed of each region, the regulation task allocation of different regions is determined to improve the operating efficiency and stability of the distribution network. For example, when the distribution network faces a sudden power shortage, the load resources of multiple local areas are reasonably called for regulation to avoid the spread of faults.

[0153] In some embodiments, the step S111 of generating load resource scheduling information for a plurality of local area load resources according to the model output result and the load resource information includes: Step S401: acquiring at least one of complementarity information and regulation potential information of the local area load resources according to the load resource information.

[0154] The hierarchical management of load resources clarifies the regulation potential of load resources of different types and regions, and helps analyze the complementarity of load resources in each local area. For example, the interruptible loads in commercial areas (such as some lighting and air conditioning in large shopping malls) and energy storage equipment in residential areas (such as household energy storage batteries) have different regulation capabilities in different time periods. After obtaining this information through hierarchical management of load resources, corresponding power exchange strategies can be formulated to achieve power complementarity between regions.

[0155] When formulating a joint regulation strategy, it is necessary to consider the regulation potential information of load resources in different local areas, which is determined based on the load resource regulation potential data of each area provided by the hierarchical management of load resources. For example, when the distribution network faces a sudden power shortage, the regulation potential and response speed of each area can be understood based on the hierarchical management data, and the regulation tasks can be reasonably allocated to ensure that each local area can respond and execute the regulation tasks within the specified time, avoid regulation conflicts, and improve the operating efficiency and stability of the entire distribution network.

[0156] Step S403: Determine the load resource scheduling information based on at least one of the complementarity information and the regulation potential information.

[0157] In this embodiment, different types of load resources are complementary in terms of regulation characteristics. For example, interruptible loads in commercial areas (such as some lighting and air conditioning in large shopping malls) can be reduced during peak load periods of the power grid, while energy storage devices in residential areas (such as household energy storage batteries) can store electricity during off-peak load periods and release electricity during peak periods, thereby achieving power complementarity between regions. By analyzing the complementary information of load resources in each local area and formulating corresponding power exchange strategies, load resource scheduling information can be determined. For example, when the load demand in a local area is low and there is excess regulation capacity, part of the electricity can be delivered to an adjacent area with higher load demand.

[0158] In this embodiment, the same type of load resources has different regulation potentials in different time periods. For example, there are differences in the load demand and regulation potential of industrial loads on weekdays and weekends. On weekdays, due to the arrangement of production tasks, the regulation potential of some industrial loads is limited; on weekends, their regulation potential may increase. According to the complementarity of load resources in different time periods, a dynamic inter-regional coordination strategy is formulated to determine the load resource scheduling information. For example, during the peak load period of the power grid, resources in areas with greater regulation potential (such as industrial load areas on weekends) are preferentially called to meet the needs of the entire distribution network.

[0159] In this embodiment, a joint regulation strategy is also formulated based on the regulation potential of the load resources in each local area. For example, when the distribution network faces a sudden power shortage, the load resources of multiple local areas can be called for regulation at the same time. The allocation of regulation tasks to different local areas is determined based on the regulation potential and response speed of each local area. When formulating a joint regulation strategy, it is also necessary to consider the communication delay and coordination control mechanism between regions to ensure that each local area can respond and execute the regulation task within the specified time to avoid regulation conflicts.

[0160] In this embodiment, by reasonably utilizing the complementary information and regulation potential information of load resources, power exchange and load regulation between multiple local areas can be realized, so as to improve the operating efficiency of the entire distribution network. For example, unnecessary investment in power generation capacity can be reduced, network losses can be reduced, etc. At the same time, this inter-regional coordination strategy also helps to improve the stability of the distribution network. When a local area fails or the load fluctuates, other areas can provide support through power exchange and load regulation to avoid the spread of the failure and the impact on the entire distribution network.

[0161] In this embodiment, the global optimal operation mode model of the distribution network is solved based on the objective function and the constraint conditions to obtain the model output result, that is, the optimal output information of each distributed power source, the optimal voltage value of each node, and the optimal distribution of the power flow of each line can be obtained.

[0162] In this embodiment, load resource information of multiple local area load resources is obtained, and load resource scheduling information for multiple local area load resources is generated based on the model output results and the load resource information, so as to obtain the power exchange strategy between local areas and the load regulation strategy of each local area.

[0163] In some embodiments, before controlling the operating state of the target load resource in the load resources based on the load resource scheduling information in step S111, the method further includes: Step S501: Generate at least one of a load regulation cost and a load regulation accuracy based on the load resource scheduling information.

[0164] In some embodiments, the performance of the distribution network during the state transition process is evaluated based on stability indicators and economic indicators, and improvement suggestions can be made based on the evaluation results to optimize the operation strategy and control method of the distribution network.

[0165] Among them, the stability index is calculated by the voltage fluctuation root mean square value (VRMS). The voltage fluctuation root mean square value (VRMS) is used to measure the degree of voltage fluctuation at each node during the state transfer process. Its calculation formula is: VRMS=

[0166] Among them, V i is the voltage value of node i during the state transition process, V0 is the voltage value of node i in the initial state, and n is the total number of nodes.

[0167] The economic index is calculated by the additional operating cost. The additional operating cost is used to evaluate the additional power generation cost and network loss cost increase caused by adjusting the strategy during the state transfer process. The calculation formula is: EconomicCost =Δ Cgen +Δ Closs Where, ΔC gen is the additional power generation cost, ΔC loss This is the increase in network loss cost.

[0168] In this embodiment, in addition to the stability index and the economic index, it is also necessary to add an evaluation index of the load resource regulation effect. These newly added evaluation indexes of the load resource regulation effect can more comprehensively reflect the performance of the distribution network during the state transfer process.

[0169] In this embodiment, the evaluation index of the load resource regulation effect includes at least one of the load regulation cost and the load regulation accuracy.

[0170] The load regulation cost is used to reflect the cost required to regulate the load resources during the state transfer process, including direct costs (such as equipment operating costs) and indirect costs (such as user satisfaction loss). The calculation formula is: Cost regulation =

[0171] Among them, C direct,i is the direct regulation cost of the i-th load resource, C indirect,i is the indirect regulation cost of the ith load resource, and m is the total number of load resources.

[0172] Among them, the load regulation accuracy is used to measure the degree of deviation between the actual regulation effect and the expected regulation target, and its calculation formula is: Accuracy regulation =1 - ( P actual,i -P target,i ∣ / ) Among them, P actual,i is the actual regulation power of the i-th load resource, P target,i is the target adjustment power of the ith load resource, and m is the total number of load resources.

[0173] In this embodiment, the voltage value of each node in the state transition process can be obtained according to the real-time operation data of the distribution network, and the root mean square value (VRMS) of the voltage fluctuation of each node can be calculated to obtain the stability index; then, according to the model output result of the global optimal operation mode model of the distribution network in step S107, the additional power generation cost and the increase in network loss cost in the state transition process can be obtained to calculate the total economic index value; then, according to the load resource scheduling information of multiple local area load resources in step S111, the regulation strategy and cost data of each load resource can be obtained, and the direct regulation cost and indirect regulation cost of each load resource can be calculated. The regulation costs of all load resources are summarized to obtain the total load regulation cost; then, combined with the model output result of the global optimal operation mode model of the distribution network in step S107 and the load resource scheduling information of multiple local area load resources in step S111, the target regulation power and actual regulation power of each load resource are obtained, the regulation accuracy of each load resource is calculated, and the regulation accuracy of all load resources is summarized to obtain the total load regulation accuracy.

[0174] Step S503: Obtain a comparison result between at least one of the load regulation cost and the load regulation accuracy and a preset threshold, and modify the load resource scheduling information based on the comparison result.

[0175] In this embodiment, the calculated index values ​​are compared with preset standards or historical data to evaluate the effect of the distribution network operation state transfer. According to the evaluation results, improvement suggestions are put forward and the load resource scheduling information is modified to optimize the operation strategy and control method of the distribution network.

[0176] In some embodiments, the step S113 of controlling the operating state of the target load resource among the plurality of local area load resources based on the load resource scheduling information includes: Step S601, obtain the model output result of the global optimal operation mode model of the distribution network in step S107, and obtain the optimal output of each distributed power source, the optimal voltage value of each node, the optimal distribution of the power flow of each line, etc. These data reflect the ideal operation state of the distribution network under different resources and constraints.

[0177] Step S603, obtaining load resource scheduling information of multiple local area load resources in step S111, including the division of each local area, the coordination relationship between areas (such as power exchange strategy, load regulation strategy, etc.), and the distribution, characteristics and regulation potential of load resources in each local area.

[0178] Step S605, obtaining real-time operation data of the distribution network, such as the current voltage, current, power and other electrical quantity information of each node, and load resource management data (relevant information of specific load equipment, load terminals, load groups, and load aggregators).

[0179] Step S607: sorting load resources of different types and regions according to the load resource regulation potential evaluation results.

[0180] For example, for electric vehicle charging loads, if their charging time is relatively flexible and the charging power can be adjusted according to grid demand, they may have a higher priority in terms of regulation potential; and for certain industrial loads, if they have a large interruptible capacity within a specific period of time, they will also be listed as load resources with high regulation potential.

[0181] Step S609, according to the power allocation characteristics of the load resources, ensure that the power allocation of different load resources is reasonably arranged in the dispatching strategy to meet the requirements of overall power balance and optimized operation of the distribution network.

[0182] For example, during peak load periods, priority is given to load resources with large regulation potential and high power allocation flexibility, such as adjusting air-conditioning loads in large commercial buildings.

[0183] Step S611, formulate a scheduling strategy sequence according to load demand in different time periods, distributed power access conditions and characteristics of load resources.

[0184] For example, during peak load periods, priority is given to dispatching load resources with greater regulation potential to supply power to the load center, while adjusting the state of the tie switch to optimize the power flow distribution. This involves first calling for energy storage equipment to discharge, then adjusting the operating state of interruptible loads (such as some industrial equipment, large commercial lighting, etc.), and finally considering adjusting the charging power of electric vehicles.

[0185] In this embodiment, corresponding scheduling strategy sequence templates can be formulated for different scenarios (such as normal operation, fault recovery, large fluctuations in renewable energy, etc.) so that scheduling decisions can be made quickly and effectively in different situations.

[0186] Step S613: convert the formulated scheduling strategy into a specific control instruction, and send the control instruction to the target load resource.

[0187] For example, if the scheduling strategy is to reduce the charging power of electric vehicles in a certain area during a certain period of time, then this strategy is converted into control instructions for the electric vehicle charging piles, clearly specifying the reduced power value and the execution time range.

[0188] For different types of intelligent devices and load aggregators, targeted instruction format conversion is performed according to their communication protocols and interface requirements to ensure that control instructions can be accurately understood and executed.

[0189] The scheduling strategy can be expressed as: S=f(P load,P source ,S switch ) Among them, S is the scheduling strategy, p load is the load, R source is the distributed power output, S switch It is the switch state.

[0190] Afterwards, the control instructions are sent to the intelligent devices (such as distributed power supply controllers, switch controllers, etc.) and load aggregators in the distribution network through the communication network of the distribution automation master station. During the sending process, a reliable communication mechanism is used to ensure the accurate transmission of the instructions.

[0191] In this embodiment, a monitoring mechanism for instruction sending is established to track the sending status of instructions in real time. If it is found that the instruction sending fails or an abnormal situation occurs, it is resent in time or other remedial measures are taken.

[0192] After receiving the control instructions, smart devices and load aggregators can remotely and in real time control the load resources according to the instructions. For example, smart meters can adjust the operating status of users' electrical equipment according to the instructions, and load aggregators can coordinate the power output of multiple load groups they manage according to the instructions.

[0193] During the control process, feedback information is continuously collected, such as the actual regulation of load resources, the impact on the operation status of the power grid, etc. Based on this feedback information, the dispatching strategy and control instructions are further optimized to achieve more accurate and efficient optimization management of load resources.

[0194] It is understandable that before using the technical solutions of each embodiment of the present disclosure, the type, scope of use, usage scenarios, etc. of the personal information involved will be informed to the user in an appropriate manner, and the user's authorization will be obtained.

[0195] For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly remind the user that the operation requested to be performed will require obtaining and using the user's personal information. Thus, the user can independently choose whether to provide personal information to software or hardware such as an electronic device, application, server, or storage medium that performs the operation of the technical solution of the present disclosure according to the prompt message.

[0196] As an optional but non-limiting implementation, in response to receiving the user's active request, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0197] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0198] It should be noted that the method of the embodiment of the present disclosure can be performed by a single device, such as a computer or a server. The method of the present embodiment can also be applied in a distributed scenario and completed by multiple devices cooperating with each other. In the case of such a distributed scenario, one of the multiple devices can only perform one or more steps in the method of the embodiment of the present disclosure, and the multiple devices will interact with each other to complete the described method.

[0199] It should be noted that the above describes some embodiments of the present disclosure. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the above embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0200] Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, the present disclosure also provides a power grid load resource hierarchical control device.

[0201] refer to Figure 3 , the device comprises: The acquisition module 101 is configured to: acquire distribution network operation data and hierarchical management data of load resources; wherein the load resources are hierarchically managed based on load attributes, and the data of the load resources after hierarchical management are acquired as the hierarchical management data; The determination module 103 is configured to: determine the regulation potential information and power allocation characteristic information of the load resource based on the distribution network operation data and the hierarchical management data; The model building module 105 is configured to: build a global optimal operation mode model of the distribution network, and build an objective function and constraint conditions of the global optimal operation mode model of the distribution network based on the regulation potential information and the power distribution characteristic information; The model solving module 107 is configured to solve the global optimal operation mode model of the distribution network based on the objective function and the constraint conditions to obtain a model output result; The division module 109 is configured to: divide the load resources based on the hierarchical management data to obtain a plurality of local area load resources; The generating module 111 is configured to: obtain load resource information of the plurality of local area load resources, and generate load resource scheduling information for the plurality of local area load resources according to the model output result and the load resource information; The control module 113 is configured to control the operating state of the target load resource among the plurality of local area load resources based on the load resource scheduling information.

[0202] In some embodiments, the obtaining of the hierarchical management data includes: Obtain load device data of the load device; Acquiring load terminal data of a load terminal, wherein the load terminal is used to manage at least one load device within the same preset range; acquiring load group data of a load group, wherein the load group is used to manage at least one load terminal of the same type; Obtaining load aggregator data of a load aggregator, wherein the load aggregator is used to manage the load group; The hierarchical management data is determined based on the load equipment data, the load terminal data, the load group data, and the load aggregator data.

[0203] In some embodiments, the model building module 105 is further configured to: Building a regulation potential model based on the regulation potential information, and setting the maximum adjustable potential utilization rate of the load resource as the objective function item of the objective function; A power allocation model is constructed based on the power allocation characteristic information, and the power allocation balance information is set as the constraint condition.

[0204] In some embodiments, the model building module 105 is further configured to: Acquire the correlation between the output of the power generation equipment and the load resource regulation amount information, determine the power generation cost based on the correlation between the output of the power generation equipment and the load resource regulation amount information, and set the power generation cost as the objective function item of the objective function; Acquire distribution information of load resources on nodes and lines based on the hierarchical management data, determine power flow distribution information of the distribution network based on the distribution information, and set the power flow distribution information as the constraint condition; The constraint condition is determined based on at least one of line capacity, node voltage, and load regulation information.

[0205] In some embodiments, the model building module 105 is further configured to: generate a graph structure based on the distribution network operation data and the distribution network topology structure, wherein the nodes of the graph structure represent the devices in the distribution network, and the edges of the graph structure represent the connection relationship between the devices; extract features of the graph structure through a graph neural network, update the feature representation of the nodes through a message propagation mechanism, and dynamically adjust the decision variables through reinforcement learning.

[0206] In some embodiments, the model solving module 107 is further configured to: iteratively solve the global optimal operation mode model of the distribution network, narrow the feasible domain by dynamically adding cutting plane constraints, and output the distribution network operation information that satisfies the minimized operation cost as the model output result.

[0207] In some embodiments, the partitioning module 109 is further configured to: Acquire at least one of geographical distribution information of load resources, network topology association information, load characteristic information, and regulation potential information based on the hierarchical management data; The load resources are divided based on at least one of the geographical distribution information, network topology structure association information, load characteristic information, and regulation potential information of the load resources.

[0208] In some embodiments, the generating module 111 is further configured to: Acquire at least one of complementarity information and regulation potential information of the local area load resources according to the load resource information; The load resource scheduling information is determined based on at least one of the complementarity information and the regulation potential information.

[0209] In some embodiments, before controlling the operating state of the target load resource in the load resources based on the load resource scheduling information, the device is further configured to: generating at least one of a load regulation cost and a load regulation accuracy based on the load resource scheduling information; Obtain a comparison result between at least one of the load regulation cost and the load regulation accuracy and a preset threshold, and modify the load resource scheduling information based on the comparison result.

[0210] For the convenience of description, the above device is described by dividing it into various modules according to its functions. Of course, when implementing the present disclosure, the functions of each module can be implemented in the same or multiple software and / or hardware.

[0211] The device of the above embodiment is used to implement the corresponding grid load resource hierarchical control method in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be repeated here.

[0212] Based on the same inventive concept, corresponding to any of the above-mentioned embodiments and methods, the present disclosure also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the hierarchical control method for power grid load resources described in any of the above embodiments is implemented.

[0213] Figure 4 A more specific schematic diagram of the hardware structure of an electronic device provided in this embodiment is shown, and the device may include: a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040 are connected to each other through the bus 1050 in the device.

[0214] The processor 1010 can be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0215] The memory 1020 may be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1020 may store an operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program codes are stored in the memory 1020 and are called and executed by the processor 1010.

[0216] The input / output interface 1030 is used to connect the input / output module to realize information input and output. The input / output module can be configured in the device as a component (not shown in the figure), or it can be externally connected to the device to provide corresponding functions. The input device may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device may include a display, a speaker, a vibrator, an indicator light, etc.

[0217] The communication interface 1040 is used to connect a communication module (not shown) to realize communication interaction between the device and other devices. The communication module can realize communication through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0218] The bus 1050 includes a path that transmits information between the various components of the device (eg, the processor 1010 , the memory 1020 , the input / output interface 1030 , and the communication interface 1040 ).

[0219] It should be noted that, although the above device only shows the processor 1010, the memory 1020, the input / output interface 1030, the communication interface 1040 and the bus 1050, in the specific implementation process, the device may also include other components necessary for normal operation. In addition, it can be understood by those skilled in the art that the above device may also only include the components necessary for implementing the embodiments of the present specification, and does not necessarily include all the components shown in the figure.

[0220] The electronic device of the above embodiment is used to implement the corresponding grid load resource hierarchical control method in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be repeated here.

[0221] Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, the present disclosure also provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the grid load resource hierarchical control method as described in any of the above embodiments.

[0222] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device.

[0223] The computer instructions stored in the storage medium of the above embodiment are used to enable the computer to execute the grid load resource hierarchical control method as described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0224] Those skilled in the art will appreciate that the embodiments of the present disclosure may be implemented as a system, method, or computer program product. Therefore, the present disclosure may be specifically implemented in the following forms, namely: complete hardware, complete software (including firmware, resident software, microcode, etc.), or a combination of hardware and software, generally referred to herein as a "circuit," "module," or "system." In addition, in some embodiments, the present disclosure may also be implemented in the form of a computer program product in one or more computer-readable media, which contains computer-readable program code.

[0225] Any combination of one or more computer-readable media may be used. A computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination thereof. More specific examples (non-exhaustive examples) of computer-readable storage media may include, for example: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device, or device.

[0226] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0227] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0228] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0229] It should be understood that each box in the flowchart and / or block diagram and the combination of boxes in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer or other programmable data processing device to produce a machine, and these computer program instructions are executed by a computer or other programmable data processing device to produce a device that implements the functions / operations specified in the boxes in the flowchart and / or block diagram.

[0230] These computer program instructions may also be stored in a computer-readable medium that enables a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable medium produce a product that includes an instruction device that implements the functions / operations specified in the blocks in the flowchart and / or block diagram.

[0231] Computer program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby enabling the instructions executed on the computer or other programmable device to provide a process for implementing the functions / operations specified in the blocks in the flowchart and / or block diagram.

[0232] In addition, although the operations of the disclosed method are described in a particular order in the accompanying drawings, this does not require or imply that the operations must be performed in this particular order, or that all the operations shown must be performed to achieve the desired results. On the contrary, the steps depicted in the flow chart can be performed in a different order. Additionally or alternatively, some steps can be omitted, multiple steps can be combined into one step, and / or one step can be decomposed into multiple steps.

[0233] The flowchart and block diagram in the accompanying drawings illustrate the possible architecture, functions and operations of the system, method and computer program product according to various embodiments of the present application. Wherein, each box in the flowchart or block diagram can represent a module, a program segment, or a part of the code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0234] It should be noted that, although several modules or units of the equipment for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into being embodied by multiple modules or units.

[0235] It should be understood by those skilled in the art that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present disclosure (including the claims) is limited to these examples; based on the concept of the present disclosure, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of different aspects of the embodiments of the present disclosure as described above, which are not provided in detail for the sake of simplicity.

[0236] In addition, to simplify the description and discussion, and in order not to obscure the embodiments of the present disclosure, known power / ground connections to integrated circuit (IC) chips and other components may or may not be shown in the provided figures. In addition, devices may be shown in the form of block diagrams to avoid obscuring the embodiments of the present disclosure, and this also takes into account the fact that the details of the implementation of these block diagram devices are highly dependent on the platform on which the embodiments of the present disclosure are to be implemented (i.e., these details should be fully within the scope of understanding of those skilled in the art). Where specific details (e.g., circuits) are set forth to describe exemplary embodiments of the present disclosure, it is apparent to those skilled in the art that the embodiments of the present disclosure may be implemented without these specific details or with variations in these specific details. Therefore, these descriptions should be considered illustrative rather than restrictive.

[0237] Although the present disclosure has been described in conjunction with specific embodiments of the present disclosure, many alternatives, modifications and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may use the discussed embodiments.

[0238] The embodiments of the present disclosure are intended to cover all such substitutions, modifications and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present disclosure should be included in the scope of protection of the present disclosure.

Claims

1. A method for hierarchical control of power grid load resources, characterized in that: include: Obtaining distribution network operation data and hierarchical management data of load resources; wherein the load resources are hierarchically managed based on load attributes, and data of the load resources after hierarchical management are obtained as the hierarchical management data; Determining the regulation potential information and power distribution characteristic information of the load resource based on the distribution network operation data and the hierarchical management data; Constructing a global optimal operation mode model of the distribution network, and constructing an objective function and constraint conditions of the global optimal operation mode model of the distribution network based on the regulation potential information and the power allocation characteristic information; Solving the global optimal operation mode model of the distribution network based on the objective function and the constraint conditions to obtain a model output result; Dividing the load resources based on the hierarchical management data to obtain multiple local area load resources; Obtaining load resource information of the plurality of local area load resources, and generating load resource scheduling information for the plurality of local area load resources according to the model output result and the load resource information; The operating state of a target load resource among the plurality of local area load resources is controlled based on the load resource scheduling information.

2. The method according to claim 1, characterized in that The acquisition of the hierarchical management data includes: Obtain load device data of the load device; Acquiring load terminal data of a load terminal, wherein the load terminal is used to manage at least one load device within the same preset range; acquiring load group data of a load group, wherein the load group is used to manage at least one load terminal of the same type; Obtaining load aggregator data of a load aggregator, wherein the load aggregator is used to manage the load group; The hierarchical management data is determined based on the load equipment data, the load terminal data, the load group data, and the load aggregator data.

3. The method according to claim 1, characterized in that The constructing of the global optimal operation mode model of the distribution network, and constructing the objective function and constraint conditions of the global optimal operation mode model of the distribution network based on the regulation potential information and the power allocation characteristic information, includes: Building a regulation potential model based on the regulation potential information, and setting the maximum adjustable potential utilization rate of the load resource as the objective function item of the objective function; A power allocation model is constructed based on the power allocation characteristic information, and the power allocation balance information is set as the constraint condition.

4. The method according to claim 3, characterized in that Also includes: Acquire the correlation between the output of the power generation equipment and the load resource regulation amount information, determine the power generation cost based on the correlation between the output of the power generation equipment and the load resource regulation amount information, and set the power generation cost as the objective function item of the objective function; Acquire distribution information of load resources on nodes and lines based on the hierarchical management data, determine power flow distribution information of the power distribution network based on the distribution information, and set the power flow distribution information as the constraint condition; The constraint condition is determined based on at least one of line capacity, node voltage, and load regulation information.

5. The method according to claim 1, characterized in that The constructing of the global optimal operation mode model of the distribution network includes: Generate a graph structure based on the distribution network operation data and the distribution network topology structure, wherein the nodes of the graph structure represent devices in the distribution network, and the edges of the graph structure represent connection relationships between the devices; Extract features from the graph structure through a graph neural network, update feature representations of nodes through a message propagation mechanism, and dynamically adjust decision variables through reinforcement learning; The step of solving the global optimal operation mode model of the distribution network based on the objective function and the constraint conditions to obtain a model output result includes: The global optimal operation mode model of the distribution network is solved iteratively, the feasible domain is reduced by dynamically adding cutting plane constraints, and the distribution network operation information that satisfies the minimum operation cost is output as the output result of the model.

6. The method according to claim 1, characterized in that The dividing the load resources based on the hierarchical management data includes: Acquire at least one of geographical distribution information of load resources, network topology association information, load characteristic information, and regulation potential information based on the hierarchical management data; Dividing the load resources based on at least one of geographical distribution information, network topology association information, load characteristic information, and regulation potential information of the load resources; The generating of load resource scheduling information for the plurality of local area load resources according to the model output result and the load resource information comprises: Acquire at least one of complementarity information and regulation potential information of the local area load resources according to the load resource information; The load resource scheduling information is determined based on at least one of the complementarity information and the regulation potential information.

7. The method according to claim 1, characterized in that Before controlling the operating state of the target load resource in the load resources based on the load resource scheduling information, the method further includes: generating at least one of a load regulation cost and a load regulation accuracy based on the load resource scheduling information; Obtain a comparison result between at least one of the load regulation cost and the load regulation accuracy and a preset threshold, and modify the load resource scheduling information based on the comparison result.

8. A power grid load resource hierarchical control device, characterized in that: include: The acquisition module is configured to: acquire distribution network operation data and hierarchical management data of load resources; wherein the load resources are hierarchically managed based on load attributes, and the data of the load resources after hierarchical management are acquired as the hierarchical management data; A determination module is configured to: determine the regulation potential information and power distribution characteristic information of the load resource based on the distribution network operation data and the hierarchical management data; A model building module is configured to: build a global optimal operation mode model of the distribution network, and build an objective function and constraint conditions of the global optimal operation mode model of the distribution network based on the regulation potential information and the power distribution characteristic information; A model solving module is configured to solve the global optimal operation mode model of the distribution network based on the objective function and the constraint conditions to obtain a model output result; A division module is configured to: divide the load resources based on the hierarchical management data to obtain a plurality of local area load resources; A generating module is configured to: obtain load resource information of a plurality of said local area load resources, and generate load resource scheduling information for the plurality of said local area load resources according to the output result of the model and the load resource information; The control module is configured to control the operating state of the target load resource among the plurality of local area load resources based on the load resource scheduling information.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method for hierarchical control of power grid load resources as described in any one of claims 1 to 7 is implemented.

10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to enable the computer to execute the power grid load resource hierarchical control method as described in any one of claims 1 to 7.

Images