Distributed energy aggregation management and control method, device, equipment, medium and chip

Abstract

The invention relates to the technical field of power distribution networks, in particular to a distributed energy aggregation management and control method, device and equipment, a medium and a chip, and the method comprises the steps that when a first resource regulation and control condition is met, a group layer selects a most adaptive subgroup from subordinate subgroup layers, and sends a first regulation and control instruction to the group layer; after the most adaptive subgroup receives the first regulation and control instruction or when a second resource regulation and control condition is met, the most adaptive subgroup selects a most adaptive terminal from a subordinate terminal layer and sends a second regulation and control instruction to the most adaptive terminal; and the most adaptive terminal performs resource scheduling according to the received second regulation and control instruction. According to the technical scheme, layered progressive resource regulation and control are carried out by dynamically selecting the most adaptive subgroups and the most adaptive terminals, efficient and flexible global-local collaborative optimization is realized, and effective technical support is provided for stable operation of an energy system under high-proportion renewable energy access.

Description

Technical Field

[0001] The present disclosure relates to the technical field of distribution networks, and particularly to a distributed energy aggregation control method, device, equipment, medium and chip. Background Art

[0002] In recent years, with the steady progress of the low-carbon transformation of energy and the reform of the power market, it has promoted the personalized development of user-side demands, the mature application of distributed energy technologies, and the significant deepening of distribution network application scenarios, and the penetration rate of flexible resources in the power system has been continuously increasing. Promoting the participation of flexible resources in the operation of the power system and power market transactions is a catalyst for realizing the elastic and stable operation of the power system, the industrial development of distributed resources, the optimization of the energy supply structure, and the improvement of comprehensive energy efficiency. At present, efforts are being made to build a new power system with new energy as the main body, which has the basic characteristics of extensive interconnection, intelligent interaction, flexible flexibility, and safe controllability. The aggregation architecture technology for the new power system can provide technologies for intelligent interconnection, flexible clustering, flexible regulation, and reliable coordination for flexible resources that are massive, small-scale, multi-energy heterogeneous, geographically dispersed, and demand-diverse, and promote the technical upgrade of the power grid to an energy Internet.

[0003] The distributed energy aggregation control method refers to the unified management and optimal scheduling of dispersed distributed energy resources through advanced technical means to achieve the efficient utilization of energy and the balance between supply and demand. This method is of great significance for improving the reliability of the energy system, reducing energy costs, and promoting the access and consumption of renewable energy. The diversity and complexity of distributed energy technologies increase the difficulty of aggregation control. Different types of distributed energy have differences in power generation principles, operating characteristics, grid connection requirements, etc., making unified management and optimal scheduling complicated. The distributed energy aggregation control method needs to achieve the collaborative optimization and scheduling of multiple distributed energy resources. However, due to the dispersion and uncertainty of distributed energy, the difficulty of system optimization and scheduling increases. Existing optimization algorithms and scheduling strategies may not fully adapt to the characteristics of distributed energy, resulting in problems such as reduced system efficiency and energy waste. Summary of the Invention

[0004] To solve the problems in the related technologies, embodiments of the present disclosure provide a distributed energy aggregation control method, device, equipment, medium and chip.

[0005] In a first aspect, an embodiment of the present disclosure provides a distributed energy aggregation control method, which is applicable to a distributed energy aggregation control system. The distributed energy aggregation control system includes: a group layer, a subgroup layer, and a terminal layer. The group layer is configured with a group control center for making collective decisions at the regional distribution network level. The subgroup layer consists of edge decision-making devices for decomposing the control tasks of the group layer. The terminal layer includes a distribution network on-site monitoring unit and a distribution network on-site control unit. The method includes:

[0006] When the first resource control condition is met, the group layer selects the most suitable subgroup from its subordinate subgroup layer and sends a first control instruction to it;

[0007] After receiving the first control instruction or when the second resource control condition is met, the most suitable subgroup selects the most suitable terminal from its subordinate terminal layer and sends a second control instruction to it;

[0008] The most suitable terminal performs resource scheduling according to the received second control instruction.

[0009] In an embodiment of the present disclosure, the situation where the first resource control condition is met includes: if a user demand instruction is received, it is determined that the first resource control condition is met; or, if the distributed energy supply within the group cannot meet the load requirements, it is determined that the first resource control condition is met; and / or,

[0010] The situation where the second resource control condition is met includes: if the distributed energy supply within the subgroup cannot meet the load requirements, it is determined that the second resource control condition is met.

[0011] In an embodiment of the present disclosure, the group layer selects the most suitable subgroup from its subordinate subgroup layer and sends a first control instruction to it, including:

[0012] The group layer obtains the subgroup node resource information uploaded by its subordinate subgroup layer;

[0013] Performs first feature extraction and first weight configuration on the subgroup node resource information to obtain first decision-making information;

[0014] Based on the first decision-making information, selects the most suitable subgroup and sends a first control instruction to it;

[0015] Among them, the subgroup node resource information is obtained by integrating the terminal layer resource information uploaded by the terminal layer subordinate to the subgroup layer; the terminal layer resource information includes the operation information and resource supply status information of each terminal device.

[0016] In an embodiment of the present disclosure, performing first feature extraction and first weight configuration on the subgroup node resource information to obtain first decision-making information includes:

[0017] After performing first feature extraction on the subgroup node resource information, a first input vector is obtained;

[0018] The first input vector is input into a first feature attention mechanism to configure first sub-weights, and a first feature vector is obtained;

[0019] The first feature vector is input into a temporal attention mechanism to configure second sub-weights, and a second feature vector is obtained;

[0020] First decision information is obtained based on the second feature vector.

[0021] In an embodiment of the present disclosure, the selecting the most suitable terminal from its subordinate terminal layer and sending a second regulation instruction to it includes:

[0022] After performing second feature extraction and second weight configuration on the terminal layer resource information, second decision information is obtained;

[0023] Based on the second decision information, the most suitable terminal is selected and a second regulation instruction is sent to it.

[0024] In an embodiment of the present disclosure, the obtaining second decision information after performing second feature extraction and second weight configuration on the terminal layer resource information includes:

[0025] After performing second feature extraction on the terminal layer resource information, a second input vector is obtained;

[0026] The second input vector is input into a second feature attention mechanism to configure second weights, and a third feature vector is obtained;

[0027] Second decision information is obtained based on the third feature vector.

[0028] In an embodiment of the present disclosure, it further includes:

[0029] The second input vector is uploaded to the group layer as subgroup node resource information and stored in the subgroup node resource information library;

[0030] The group layer obtaining the subgroup node resource information uploaded by its subordinate subgroup layer includes:

[0031] Obtaining the subgroup node resource information uploaded by its subordinate subgroup layer from the subgroup node resource information library.

[0032] In an embodiment of the present disclosure, the first decision information is a subgroup adaptation score obtained by weighted summation calculation of the eigenvalues of the features configured with first weights and the corresponding first weights;

[0033] Selecting the most suitable subgroup based on the first decision information and sending a first regulation instruction to it includes:

[0034] Comparing the calculated subgroup adaptation scores, and taking the subgroup corresponding to the highest subgroup adaptation score as the most suitable subgroup and sending a first regulation instruction to it.

[0035] In an implementation manner of the present disclosure, the second decision information is a terminal adaptation score obtained by weighted summation of the eigenvalues of the features configured with the second weights and the corresponding second weights;

[0036] Selecting the most suitable terminal based on the second decision information and sending a second regulation instruction to it includes:

[0037] Comparing the calculated terminal adaptation scores, and taking the terminal corresponding to the highest terminal adaptation score as the most suitable terminal and sending a second regulation instruction to it.

[0038] In an implementation manner of the present disclosure, it further includes:

[0039] If the distributed energy supply within the terminal layer cannot meet the load requirements, the terminal layer performs resource scheduling on its subordinate terminal devices.

[0040] In a second aspect, an embodiment of the present disclosure provides a distributed energy aggregation management and control device, including:

[0041] A first regulation module, configured to, when the first resource regulation condition is met, the population layer selects the most suitable subgroup from its subordinate subgroup layer and sends a first regulation instruction to it;

[0042] A second regulation module, configured to, after the most suitable subgroup receives the first regulation instruction or when the second resource regulation condition is met, select the most suitable terminal from its subordinate terminal layer and send a second regulation instruction to it;

[0043] A resource scheduling module, configured to the most suitable terminal perform resource scheduling according to the received second regulation instruction;

[0044] Wherein, the population layer configures a population regulation center for realizing collective decision-making at the regional distribution network level, the subgroup layer is composed of edge decision-making devices for decomposing the regulation tasks of the population layer, and the terminal layer includes a distribution network on-site monitoring unit and a distribution network on-site control unit.

[0045] In an implementation manner of the present disclosure, the situations where the first resource regulation condition is met include: if a user demand instruction is received, it is determined that the first resource regulation condition is met; or, if the distributed energy supply within the population cannot meet the load requirements, it is determined that the first resource regulation condition is met; and / or,

[0046] The situation of satisfying the second resource regulation condition includes: if the distributed energy supply within the subgroup cannot meet the load requirements, it is determined that the second resource regulation condition is satisfied.

[0047] In an implementation manner of the present disclosure, the part of the first regulation module where the population layer selects the most suitable subgroup from its subordinate subgroup layers and sends a first regulation instruction to it is configured as:

[0048] The population layer obtains the subgroup node resource information uploaded by its subordinate subgroup layers;

[0049] After performing first feature extraction and first weight configuration on the subgroup node resource information, first decision information is obtained;

[0050] Based on the first decision information, the most suitable subgroup is selected and a first regulation instruction is sent to it;

[0051] Among them, the subgroup node resource information is obtained by integrating the terminal layer resource information uploaded by the terminal layer subordinate to the subgroup layer; the terminal layer resource information includes the operation information and resource supply status information of each terminal device.

[0052] In an implementation manner of the present disclosure, the part of the first regulation module that obtains first decision information after performing first feature extraction and first weight configuration on the subgroup node resource information is configured as:

[0053] After performing first feature extraction on the subgroup node resource information, a first input vector is obtained;

[0054] The first input vector is input into a first feature attention mechanism to configure a first sub-weight, and a first feature vector is obtained;

[0055] The first feature vector is input into a temporal attention mechanism to configure a second sub-weight, and a second feature vector is obtained;

[0056] Based on the second feature vector, first decision information is obtained.

[0057] In an implementation manner of the present disclosure, the part of the second regulation module that selects the most suitable terminal from its subordinate terminal layer and sends a second regulation instruction to it is configured as:

[0058] After performing second feature extraction and second weight configuration on the terminal layer resource information, second decision information is obtained;

[0059] Based on the second decision information, the most suitable terminal is selected and a second regulation instruction is sent to it.

[0060] In one embodiment of the present disclosure, the part of the second regulation module that performs second feature extraction and second weight configuration on the terminal layer resource information to obtain part of the second decision information is configured as:

[0061] Performing second feature extraction on the terminal layer resource information to obtain a second input vector;

[0062] Inputting the second input vector into a second feature attention mechanism to configure weights to obtain a third feature vector;

[0063] Obtaining second decision information based on the third feature vector.

[0064] In one embodiment of the present disclosure, it further includes:

[0065] A storage module configured to upload the second input vector as subgroup node resource information to the group layer and store it in the subgroup node resource information library;

[0066] The part in the first regulation module where the group layer obtains the subgroup node resource information uploaded by its subordinate subgroup layer is configured as:

[0067] Obtaining the subgroup node resource information uploaded by its subordinate subgroup layer from the subgroup node resource information library.

[0068] In one embodiment of the present disclosure, the first decision information is a subgroup adaptation score obtained by weighted summation of the eigenvalues of the features with configured first weights and the corresponding first weights;

[0069] The part in the first regulation module that selects the most suitable subgroup based on the first decision information and sends a first regulation instruction to it is configured as:

[0070] Comparing the magnitudes of the calculated subgroup adaptation scores, and taking the subgroup corresponding to the highest subgroup adaptation score as the most suitable subgroup and sending a first regulation instruction to it.

[0071] In one embodiment of the present disclosure, the second decision information is a terminal adaptation score obtained by weighted summation of the eigenvalues of the features with configured second weights and the corresponding second weights;

[0072] The part in the second regulation module that selects the most suitable terminal based on the second decision information and sends a second regulation instruction to it is configured as:

[0073] Comparing the magnitudes of the calculated terminal adaptation scores, and taking the terminal corresponding to the highest terminal adaptation score as the most suitable terminal and sending a second regulation instruction to it.

[0074] In one embodiment of the present disclosure, it further includes:

[0075] The terminal layer scheduling module is configured to perform resource scheduling on the subordinate terminal devices of the terminal layer if the distributed energy supply within the terminal layer cannot meet the load requirements.

[0076] In a third aspect, embodiments of the present disclosure provide an electronic device, including a memory and a processor. The memory is used to store one or more computer instructions, and the one or more computer instructions are executed by the processor to implement the method according to any one of the first aspect.

[0077] In a fourth aspect, embodiments of the present disclosure provide a computer-readable storage medium, on which computer instructions are stored. When the computer instructions are executed by a processor, the method according to any one of the first aspect is implemented.

[0078] In a fifth aspect, embodiments of the present disclosure provide a chip, which includes a processor. The processor is used to call a computer program in a memory to execute the above-mentioned distributed energy aggregation control method.

[0079] The technical effects provided by the embodiments of the present disclosure may include the following beneficial effects:

[0080] According to the technical solution provided by the embodiments of the present disclosure, a distributed energy aggregation control method is applicable to a distributed energy aggregation control system. The distributed energy aggregation control system includes: a group layer, a subgroup layer, and a terminal layer. The group layer configures a group control center for collective decision-making at the regional distribution network level. The subgroup layer is composed of edge decision-making devices for decomposing the control tasks of the group layer. The terminal layer includes a distribution network on-site monitoring unit and a distribution network on-site control unit. The method includes: when the first resource scheduling condition is met, the group layer selects the most suitable subgroup from its subordinate subgroup layers and sends a first control instruction to it; after receiving the first control instruction or when the second resource scheduling condition is met, the most suitable subgroup selects the most suitable terminal from its subordinate terminal layers and sends a second control instruction to it; the most suitable terminal performs resource scheduling according to the received second control instruction. The above technical solution decomposes the global problem of distributed resource scheduling into local optimization tasks by dynamically selecting the "most suitable subgroup" and the "most suitable terminal" for hierarchical progressive resource scheduling, significantly reducing the computational complexity of a single decision-making and shortening the response time. While ensuring real-time performance, it realizes efficient and flexible global-local collaborative optimization, providing effective technical support for the stable operation of the energy system under high-proportion renewable energy access.

[0081] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0082] Figure 1 The flowchart showing the distributed energy aggregation management and control method according to an embodiment of the present disclosure.

[0083] Figure 2 The flowchart showing the distributed energy aggregation management and control method according to a specific embodiment of the present disclosure.

[0084] Figure 3 The structural block diagram showing the distributed energy aggregation management and control device according to an embodiment of the present disclosure.

[0085] Figure 4 The structural block diagram showing the electronic device according to an embodiment of the present disclosure.

[0086] Figure 5 The structural schematic diagram showing the computer system suitable for implementing the method according to an embodiment of the present disclosure. Detailed implementation manners

[0087] Hereinafter, the exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings so that those skilled in the art can easily implement them. In addition, for the sake of clarity, parts irrelevant to the description of the exemplary embodiments are omitted in the drawings.

[0088] In the present disclosure, it should be understood that terms such as "including" or "having" are intended to indicate the existence of the features, numbers, steps, actions, components, parts, or combinations thereof disclosed in this specification, and are not intended to preclude the possibility of the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof.

[0089] In addition, it should be noted that, without conflict, the embodiments in the present disclosure and the features in the embodiments can be combined with each other. The present disclosure will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0090] The distributed energy aggregation management and control method refers to the unified management and optimized scheduling of dispersed distributed energy resources through advanced technical means to achieve efficient energy utilization and supply-demand balance. This method is of great significance for improving the reliability of the energy system, reducing energy costs, and promoting the access and consumption of renewable energy. The diversity and complexity of distributed energy technologies increase the difficulty of aggregation management and control. Different types of distributed energy have differences in power generation principles, operation characteristics, grid connection requirements, etc., making unified management and optimized scheduling complex. The distributed energy aggregation management and control method needs to achieve the collaborative optimization and scheduling of multiple distributed energy resources. However, due to the dispersion and uncertainty of distributed energy, the difficulty of system optimization and scheduling increases. Existing optimization algorithms and scheduling strategies may not fully adapt to the characteristics of distributed energy, resulting in problems such as reduced system efficiency and energy waste.

[0091] In view of the above deficiencies, the distributed energy aggregation control method provided by the present disclosure performs hierarchical progressive resource regulation by dynamically selecting the "most suitable subgroup" and the "most suitable terminal", decomposes the global problem of distributed resource scheduling into local optimization tasks, significantly reduces the computational complexity of a single decision, shortens the response time, and achieves efficient and flexible global-local collaborative optimization while ensuring real-time performance, providing effective technical support for the stable operation of the energy system under high proportion of renewable energy access.

[0092] Figure 1 The flowchart showing the distributed energy aggregation control method according to an embodiment of the present disclosure.

[0093] As Figure 1 shown, the distributed energy aggregation control method includes the following steps S110 - S130:

[0094] In step S110, when the first resource regulation condition is satisfied, the group layer selects the most suitable subgroup from its subordinate subgroup layer and sends a first regulation instruction to it;

[0095] In step S120, after receiving the first regulation instruction or when the second resource regulation condition is satisfied, the most suitable subgroup selects the most suitable terminal from its subordinate terminal layer and sends a second regulation instruction to it;

[0096] In step S130, the most suitable terminal performs resource scheduling according to the received second regulation instruction.

[0097] The distributed energy aggregation control method of the present disclosure is applied based on the distribution network scheduling architecture of distributed energy composed of a group layer, a subgroup layer, and a terminal layer. This distribution network scheduling architecture is a hierarchical interactive scheduling framework. Through a multi-level interactive energy scheduling model, while optimizing the operation mode of each subgroup layer, the adjustable multiple interactions between the subgroup layer and the group layer are utilized to optimize and iterate the system operation.

[0098] The group layer configures a group control center such as a server device. Considering that the master station is the top layer of the distribution network scheduling architecture, the group control center is arranged on the master station side, sends scheduling tasks to multiple lower subgroup layers, and coordinates the subgroup layer to jointly complete the in-group decision through instructions such as control and incentive, realizing collective decision-making at the regional distribution network level.

[0099] The subgroup layer is composed of edge decision-making devices and is divided in a static or dynamic manner. For a group composed of heterogeneous resources, static grouping is carried out by comprehensively considering resource types, geographical location distribution, affiliated interest subjects, and subordination relationships, etc. For a group composed of homogeneous resources, generally these resources belong to the same interest subject and there is no problem of interest game. According to the spatio-temporal characteristic information such as the geographical location distribution, operating state, and regulation ability of the resources, dynamic subgroup division is carried out. The function of the subgroup layer is to further decompose the regulation tasks of the group layer, decompose the commands of the regulation center, and perform distributed collaboration among groups to optimize the execution plan.

[0100] The terminal layer includes a distribution network on-site monitoring unit and a distribution network on-site control unit, and specifically includes individual resources such as distributed photovoltaics, EVs, wind turbines, energy storage, and air conditioners located at the very end of the power grid. The terminal layer is regulated by the subgroup layer and also has a self-decision function. The priority of the self-decision command is lower than that of the upper-layer command to achieve optimal response.

[0101] In an implementation manner of the present disclosure, the situation of satisfying the first resource regulation condition includes: if a user demand command is received, it is determined that the first resource regulation condition is satisfied; or, if the distributed energy supply within the group cannot meet the load requirement, it is determined that the first resource regulation condition is satisfied; and / or, the situation of satisfying the second resource regulation condition includes: if the distributed energy supply within the subgroup cannot meet the load requirement, it is determined that the second resource regulation condition is satisfied.

[0102] In the present disclosure manner, when any one of the above first resource regulation conditions is satisfied, the group layer is triggered to select the most suitable subgroup from the subgroup layer and send a first regulation command. After receiving the first regulation command, the most suitable subgroup is triggered to select the most suitable terminal from the terminal layer and send a second regulation command; in addition, when the second resource regulation condition is satisfied, the most suitable subgroup can also be triggered to select the most suitable terminal from the terminal layer and send a second regulation command. In this case, the subgroup layer does not make a decision according to the command of the group layer, but independently decides whether to issue a regulation command according to the distributed resources and load conditions within the subgroup.

[0103] In the present disclosure manner, the user demand command can be a demand response command, such as a command to respond to the peak shaving and valley filling demand issued by the power grid company, or an emergency control command, such as a command to increase the power grid frequency, etc. The situation where the distributed energy supply within the group cannot meet the load requirement and / or the situation where the distributed energy supply within the subgroup cannot meet the load requirement can both be events such as a sudden increase in load, an event where the renewable energy output drops sharply due to special weather, or an event where power shortage occurs due to equipment failure, etc.

[0104] In the present disclosure, when making decisions at the group level and subgroup level, the most suitable subgroup / most suitable terminal is selected to execute the regulation instruction. Usually, the number of the most suitable subgroups is one to achieve single-objective focus, avoid the complexity of multi-resource coordination, and improve the response speed. The number of the most suitable terminals can be one, two or more, so as to facilitate the complementary advantages of different resources. The unselected subgroups / terminals can maintain their original operating states and do not participate in the current regulation cycle, realizing resource isolation.

[0105] In the present disclosure, the first regulation instruction sent by the group level to the most suitable subgroup may carry the instruction content of the global regulation target, such as the power adjustment amount, etc.; the second regulation instruction sent by the most suitable subgroup to the most suitable terminal may carry the instruction content of the specific device operation instruction, such as the energy storage charge and discharge power setting, the photovoltaic load reduction ratio, etc. After receiving the second regulation instruction, the most suitable terminal performs resource scheduling. Specifically, it can parse the second instruction and generate control device parameters, such as the inverter power, the energy storage SOC threshold, etc. The most suitable terminal also monitors the execution result in real time, feeds back the deviation and dynamically adjusts the parameters to optimize the resource scheduling result.

[0106] In an implementation manner of the present disclosure, the group level selects the most suitable subgroup from its subordinate subgroup levels and sends the first regulation instruction to it, including:

[0107] The group level obtains the subgroup node resource information uploaded by its subordinate subgroup levels;

[0108] Performs first feature extraction and first weight configuration on the subgroup node resource information to obtain first decision information;

[0109] Based on the first decision information, selects the most suitable subgroup and sends the first regulation instruction to it;

[0110] Among them, the subgroup node resource information is obtained by integrating the terminal layer resource information uploaded by the terminal layer subordinate to the subgroup layer; the terminal layer resource information includes the operation information and resource supply status information of each terminal device.

[0111] In the present disclosure method, the terminal device realizes the acquisition and perception of information data through methods such as sensing information acquisition and image recognition, so as to enhance the capabilities of communication and cooperation between devices. The operating information of the terminal device can be operating information of the power system such as current, voltage, and frequency. The resource supply status information can be decision-making information based on its own reasoning, including information on whether there is excess power resource supply or whether additional power resource supply is required. The operating information of each terminal device and the corresponding resource supply status information constitute the terminal layer resource information. The terminal layer summarizes the terminal layer resource information and uploads it to the subgroup layer, where it is stored in the terminal layer resource information database of the subgroup layer. The subgroup layer extracts features and integrates resources from the summarized terminal layer resource information to form subgroup node resource information, which is uploaded to the group layer and stored in the subgroup node resource information database of the group layer.

[0112] In the present disclosure method, first, a first feature extraction is performed on the subgroup node resource information. Feature extraction techniques such as principal component analysis (PCA) and long short-term memory network (LSTM) are used to extract key features from the original data, reduce the data dimension, and retain important information.

[0113] After the first feature extraction, a first weight can be configured based on the current regulation target. The first weight can be adjusted. For example, in the regulation scenario of emergency frequency modulation, a high weight can be given to the response speed feature, while in the economic dispatch scenario, a high weight can be given to the regulation cost feature. Then, the eigenvalue of each feature and the weight can be weighted and summed to calculate the subgroup adaptation score. The subgroup adaptation score is used as the first decision-making information, and the most suitable subgroup is selected based on the size of the score value. Then, a first regulation instruction is sent to the most suitable subgroup.

[0114] In an embodiment of the present disclosure, the first decision-making information obtained after the first feature extraction and the first weight configuration of the subgroup node resource information includes:

[0115] After the first feature extraction of the subgroup node resource information, a first input vector is obtained;

[0116] The first input vector is input into the first feature attention mechanism to configure the first sub-weight, and a first feature vector is obtained;

[0117] The first feature vector is input into the temporal attention mechanism to configure the second sub-weight, and a second feature vector is obtained;

[0118] Based on the second feature vector, the first decision-making information is obtained.

[0119] In the present disclosure method, in order to highlight more critical influencing features in the subgroup node resource information, a first feature attention mechanism is introduced, enabling the model to adaptively weight the input features when the group layer performs intelligent regulation. The model in the present disclosure can be a reinforcement learning policy model with an embedded attention layer in the prior art, which will not be elaborated here.

[0120] Specifically, first calculate the first weight. Here, since two attention mechanisms are introduced, in this embodiment, the first weight includes a first sub-weight related to the first feature attention mechanism and a second sub-weight related to the temporal attention mechanism: Set the feature after the first feature extraction as the first input vector of the model, where N is the number of samples, T is the number of subgroups, and n f is the number of terminal devices. The quantization process of the weights corresponding to each feature is: e = σ(XW e +b e ). e = (e1, e2,..., e T ) is the unnormalized first sub-weight, is the trainable coefficient matrix, is the bias parameter, and σ is the Sigmoid activation function. Secondly, normalize the first sub-weight: To make the first sub-weight satisfy a probability distribution with a sum of 1, normalize e through the softmax function to obtain the normalized first sub-weight α j . Thirdly, calculate the intermediate semantic vector: Multiply the normalized first sub-weight α j by the corresponding feature vector x j to achieve the purpose of enhancing or weakening the expression of x j , and then obtain the adaptively optimized first feature vector: X ATT = (α1x1, α2x2,..., α T x T ).

[0121] Since different types of distributed energy and load consumption have large differences in temporality, a temporal attention mechanism is further introduced in the group layer.

[0122] Specifically, first, use the first feature vector X ATT containing feature correlation relationships as the input of the temporal attention mechanism, and quantify the weight at time t during the iteration process: f t = σ([X ATT W f +b f ). Among them, f t = (f t 1 , f t 2,..., f t T ) is the unnormalized second sub-weight, is a trainable coefficient matrix, is a bias parameter. Next, normalize the second sub-weight: Use the softmax function to normalize f t to obtain the normalized second sub-weight Again, to obtain the hidden time information at time t, combine with α t x t through weighted summation to obtain the second feature vector which contains features and temporal correlation information.

[0123] In the present disclosure, the first decision information is a subgroup adaptation score calculated by weighted summation of the eigenvalue of the feature configuring the first weight and the corresponding first weight;

[0124] The selecting the most suitable subgroup based on the first decision information and sending the first regulation instruction to it includes:

[0125] Compare the magnitudes of the calculated subgroup adaptation scores, and use the subgroup corresponding to the highest subgroup adaptation score as the most suitable subgroup and send the first regulation instruction to it.

[0126] In an implementation manner of the present disclosure, the selecting the most suitable terminal from its subordinate terminal layer and sending the second regulation instruction to it includes:

[0127] Perform second feature extraction and second weight configuration on the terminal layer resource information to obtain second decision information;

[0128] Select the most suitable terminal based on the second decision information and send the second regulation instruction to it.

[0129] In the present disclosure, the performing second feature extraction and second weight configuration on the terminal layer resource information to obtain second decision information includes:

[0130] Perform second feature extraction on the terminal layer resource information to obtain a second input vector;

[0131] Input the second input vector into a second feature attention mechanism to configure the second weight to obtain a third feature vector;

[0132] Obtain the second decision information based on the third feature vector.

[0133] The processes of the second feature extraction and second weight configuration in the present disclosure can refer to the processes of the first feature extraction and first weight configuration in the above solution, and will not be elaborated here.

[0134] In the present disclosure method, the second decision information is the terminal adaptation score obtained by weighted summation calculation of the eigenvalue of the feature configured with the second weight and the corresponding second weight;

[0135] The selecting the most suitable terminal based on the second decision information and sending a second regulation instruction to it includes:

[0136] Comparing the magnitudes of the calculated terminal adaptation scores, and taking the terminal corresponding to the highest terminal adaptation score as the most suitable terminal and sending a second regulation instruction to it.

[0137] In an embodiment of the present disclosure, it further includes:

[0138] Uploading the second input vector as subgroup node resource information to the group layer and storing it in the subgroup node resource information library;

[0139] The group layer obtaining the subgroup node resource information uploaded by its subordinate subgroup layer includes:

[0140] Obtaining the subgroup node resource information uploaded by its subordinate subgroup layer from the subgroup node resource information library.

[0141] In the present disclosure method, the second input vector is beneficial data for subgroup decision-making obtained by feature extraction of the terminal layer resource information. Further uploading this beneficial data as subgroup node resource information to the group layer enables the group layer to make further decisions based on this beneficial data, improving the decision-making efficiency.

[0142] In an embodiment of the present disclosure, it further includes:

[0143] If the distributed energy supply within the terminal layer cannot meet the load requirements, the terminal layer performs resource scheduling on its subordinate terminal devices.

[0144] In the present disclosure method, the situation where the distributed energy supply within the terminal layer cannot meet the load requirements can be an event of unexpected load surge, an event of sudden drop in renewable energy output due to special weather, or an event of power shortage due to equipment failure, etc. The terminal layer has a self-decision function. When the above situations occur, it directly performs resource scheduling on the corresponding terminal devices based on the local control strategy, which can better adapt to local dynamic changes and improve the response speed.

[0145] Figure 2 Shows a flowchart of a distributed energy aggregation management and control method according to a specific embodiment of the present disclosure.

[0146] As Figure 2 shown, the specific process of the distributed energy aggregation management and control method is:

[0147] Step 1: Each terminal device 1... terminal device n at the terminal layer uploads the system operation information and the self - decision information of the terminal layer inferred by itself (i.e., resource supply status information) to the subgroup in the subgroup layer to which it belongs. Each subgroup summarizes the uploaded information and stores it in the terminal layer resource information database. The subgroup layer performs second - feature extraction on the information in the terminal layer resource information database to obtain subgroup node resource information, and then uploads it to the group layer. The group layer summarizes the uploaded information and stores it in the subgroup node resource information database.

[0148] Step 2: After analyzing the subgroup node resource information, the group layer decides whether to issue a first regulation instruction according to the distributed resources and load conditions within the group. If not, it waits for the iteration of the subgroup node resource information; if so, it performs first - feature extraction on the subgroup node resource information. The extracted information is analyzed for group - layer regulation decision - making through the first - feature attention mechanism and the temporal attention mechanism to select the most suitable subgroup and send the first regulation instruction. In addition, if a user demand instruction is received, it directly performs group - layer regulation decision - making analysis, selects the most suitable subgroup and sends the first regulation instruction.

[0149] Step 3: After receiving the first regulation instruction, the subgroup layer performs second - feature extraction on the terminal layer resource information. The extracted information is analyzed for subgroup - layer regulation decision - making through the second - feature attention mechanism to select the most suitable terminal device and send a second regulation instruction (not shown in the figure); after the execution unit of the terminal device receives the second regulation instruction, it performs resource scheduling.

[0150] Step 4: The subgroup layer can also independently analyze all the terminal layer resource information within its region, and decide whether to issue a second regulation instruction according to the distributed resources and load conditions within the subgroup. If not, it waits for the iteration of the terminal layer resource information; if so, it performs second - feature extraction on the terminal layer resource information. The extracted information is analyzed for subgroup - layer regulation decision - making through the second - feature attention mechanism to select the most suitable terminal device and send the second regulation instruction. After the execution unit of the terminal device receives the second regulation instruction, it performs resource scheduling.

[0151] Figure 3 The structural block diagram of a distributed energy aggregation control device according to an embodiment of the present disclosure is shown. Among them, the device can be implemented as part or all of an electronic device through software, hardware, or a combination of both.

[0152] As Figure 3 shown, the distributed energy aggregation control device 300 includes:

[0153] A first regulation module 310, configured to select the most suitable subgroup from its subordinate subgroup layer and send a first regulation instruction when the first resource regulation condition is met;

[0154] The second regulation module 320 is configured to select the most suitable terminal from its subordinate terminal layer and send a second regulation instruction after the most suitable subgroup receives the first regulation instruction or when the second resource regulation condition is met;

[0155] The resource scheduling module 330 is configured to perform resource scheduling after the most suitable terminal receives the second regulation instruction;

[0156] Among them, the group layer configures a group regulation center for collective decision-making at the regional distribution network level. The subgroup layer is composed of edge decision-making devices for decomposing the regulation tasks of the group layer. The terminal layer includes a distribution network on-site monitoring unit and a distribution network on-site control unit.

[0157] According to the technical solution provided by the embodiments of the present disclosure, by dynamically selecting the "most suitable subgroup" and the "most suitable terminal" for hierarchical progressive resource regulation, the global problem of distributed resource scheduling is decomposed into local optimization tasks, significantly reducing the computational complexity of a single decision-making and shortening the response time. While ensuring real-time performance, efficient and flexible global-local collaborative optimization is achieved, providing effective technical support for the stable operation of the energy system under high-proportion renewable energy access.

[0158] In an implementation manner of the present disclosure, the situations where the first resource regulation condition is met include: if a user demand instruction is received, it is determined that the first resource regulation condition is met; or, if the distributed energy supply within the group cannot meet the load requirements, it is determined that the first resource regulation condition is met; and / or,

[0159] The situations where the second resource regulation condition is met include: if the distributed energy supply within the subgroup cannot meet the load requirements, it is determined that the second resource regulation condition is met.

[0160] In an implementation manner of the present disclosure, the part of the first regulation module where the group layer selects the most suitable subgroup from its subordinate subgroup layer and sends a first regulation instruction to it is configured to:

[0161] The group layer obtains the subgroup node resource information uploaded by its subordinate subgroup layer;

[0162] Perform first feature extraction and first weight configuration on the subgroup node resource information to obtain first decision-making information;

[0163] Select the most suitable subgroup based on the first decision-making information and send a first regulation instruction to it;

[0164] Among them, the subgroup node resource information is obtained by integrating the terminal layer resource information uploaded by the terminal layer subordinate to the subgroup layer; the terminal layer resource information includes the operation information and resource supply status information of each terminal device.

[0165] In one embodiment of the present disclosure, the part in the first regulation module that performs first feature extraction and first weight configuration on the subgroup node resource information to obtain first decision information is configured as follows:

[0166] Perform first feature extraction on the subgroup node resource information to obtain a first input vector;

[0167] Input the first input vector into a first feature attention mechanism to configure a first sub-weight to obtain a first feature vector;

[0168] Input the first feature vector into a temporal attention mechanism to configure a second sub-weight to obtain a second feature vector;

[0169] Obtain first decision information based on the second feature vector.

[0170] In one embodiment of the present disclosure, the part in the second regulation module that selects the most suitable terminal from its subordinate terminal layer and sends a second regulation instruction to it is configured as follows:

[0171] Perform second feature extraction and second weight configuration on the terminal layer resource information to obtain second decision information;

[0172] Select the most suitable terminal based on the second decision information and send a second regulation instruction to it.

[0173] In one embodiment of the present disclosure, the part in the second regulation module that performs second feature extraction and second weight configuration on the terminal layer resource information to obtain second decision information is configured as follows:

[0174] Perform second feature extraction on the terminal layer resource information to obtain a second input vector;

[0175] Input the second input vector into a second feature attention mechanism to configure a second weight to obtain a third feature vector;

[0176] Obtain second decision information based on the third feature vector.

[0177] In one embodiment of the present disclosure, it further includes:

[0178] A storage module configured to upload the second input vector as subgroup node resource information to the group layer and store it in the subgroup node resource information library;

[0179] The part in the first regulation module where the group layer obtains the subgroup node resource information uploaded by its subordinate subgroup layer is configured as follows:

[0180] Obtain the subgroup node resource information uploaded by its subordinate subgroup layer from the subgroup node resource information library.

[0181] In one embodiment of the present disclosure, the first decision information is a subgroup adaptation score calculated by weighted summation of the eigenvalue of the feature configured with the first weight and the corresponding first weight;

[0182] The part in the first regulation module that selects the most suitable subgroup based on the first decision information and sends the first regulation instruction to it is configured to:

[0183] Compare the magnitudes of the calculated subgroup adaptation scores, and use the subgroup corresponding to the highest subgroup adaptation score as the most suitable subgroup and send the first regulation instruction to it.

[0184] In one embodiment of the present disclosure, the second decision information is a terminal adaptation score calculated by weighted summation of the eigenvalue of the feature configured with the second weight and the corresponding second weight;

[0185] The part in the second regulation module that selects the most suitable terminal based on the second decision information and sends the second regulation instruction to it is configured to:

[0186] Compare the magnitudes of the calculated terminal adaptation scores, and use the terminal corresponding to the highest terminal adaptation score as the most suitable terminal and send the second regulation instruction to it.

[0187] In one embodiment of the present disclosure, it further includes:

[0188] A terminal layer scheduling module, configured to perform resource scheduling on the subordinate terminal devices in the terminal layer if the distributed energy supply within the terminal layer cannot meet the load requirements.

[0189] The present disclosure also discloses an electronic device, Figure 4 showing a structural block diagram of the electronic device according to an embodiment of the present disclosure.

[0190] As Figure 4 shown, the electronic device includes a memory and a processor, wherein the memory is used to store one or more computer instructions, and wherein the one or more computer instructions are executed by the processor to implement the method according to the embodiment of the present disclosure.

[0191] The distributed energy aggregation control method is applicable to a distributed energy aggregation control system, wherein the distributed energy aggregation control system includes: a group layer, a subgroup layer, and a terminal layer. The group layer is configured with a group control center for realizing collective decision-making at the regional distribution network level. The subgroup layer is composed of edge decision-making devices for decomposing the regulation tasks of the group layer. The terminal layer includes a distribution network on-site monitoring unit and a distribution network on-site control unit. The method includes:

[0192] When the first resource regulation condition is met, the group layer selects the most suitable subgroup from its subordinate subgroup layers and sends a first regulation instruction to it;

[0193] After receiving the first regulation instruction or when the second resource regulation condition is met, the most suitable subgroup selects the most suitable terminal from its subordinate terminal layer and sends a second regulation instruction to it;

[0194] The most suitable terminal performs resource scheduling according to the received second regulation instruction.

[0195] In an implementation manner of the present disclosure, the situations where the first resource regulation condition is met include: if a user demand instruction is received, it is determined that the first resource regulation condition is met; or, if the distributed energy supply within the group cannot meet the load requirement, it is determined that the first resource regulation condition is met; and / or,

[0196] The situations where the second resource regulation condition is met include: if the distributed energy supply within the subgroup cannot meet the load requirement, it is determined that the second resource regulation condition is met.

[0197] In an implementation manner of the present disclosure, the group layer selects the most suitable subgroup from its subordinate subgroup layers and sends a first regulation instruction to it, including:

[0198] The group layer obtains the subgroup node resource information uploaded by its subordinate subgroup layers;

[0199] Performs first feature extraction and first weight configuration on the subgroup node resource information to obtain first decision-making information;

[0200] Selects the most suitable subgroup based on the first decision-making information and sends a first regulation instruction to it;

[0201] Among them, the subgroup node resource information is obtained by integrating the terminal layer resource information uploaded by the terminal layer subordinate to the subgroup layer; the terminal layer resource information includes the operation information and resource supply status information of each terminal device;

[0202] In an implementation manner of the present disclosure, the performing first feature extraction and first weight configuration on the subgroup node resource information to obtain first decision-making information includes:

[0203] Performs first feature extraction on the subgroup node resource information to obtain a first input vector;

[0204] Inputs the first input vector into a first feature attention mechanism to configure a first sub-weight, and obtains a first feature vector;

[0205] Inputs the first feature vector into a temporal attention mechanism to configure a second sub-weight, and obtains a second feature vector;

[0206] Obtain first decision information based on the second feature vector.

[0207] In an implementation manner of the present disclosure, the step of selecting the most suitable terminal from its subordinate terminal layer and sending a second regulation instruction to it includes:

[0208] Perform second feature extraction and second weight configuration on the terminal layer resource information to obtain second decision information;

[0209] Select the most suitable terminal based on the second decision information and send a second regulation instruction to it.

[0210] In an implementation manner of the present disclosure, the step of performing second feature extraction and second weight configuration on the terminal layer resource information to obtain second decision information includes:

[0211] Perform second feature extraction on the terminal layer resource information to obtain a second input vector;

[0212] Input the second input vector into a second feature attention mechanism to configure second weights and obtain a third feature vector;

[0213] Obtain second decision information based on the third feature vector.

[0214] In an implementation manner of the present disclosure, it further includes:

[0215] Upload the second input vector as subgroup node resource information to the group layer and store it in the subgroup node resource information library;

[0216] The group layer obtaining the subgroup node resource information uploaded by its subordinate subgroup layer includes:

[0217] Obtain the subgroup node resource information uploaded by its subordinate subgroup layer from the subgroup node resource information library.

[0218] In an implementation manner of the present disclosure, the first decision information is a subgroup adaptation score obtained by weighted summation of the eigenvalue of the feature with the first weight configured and the corresponding first weight;

[0219] The step of selecting the most suitable subgroup based on the first decision information and sending a first regulation instruction to it includes:

[0220] Compare the magnitudes of the calculated subgroup adaptation scores, and use the subgroup corresponding to the highest subgroup adaptation score as the most suitable subgroup and send a first regulation instruction to it.

[0221] In an implementation manner of the present disclosure, the second decision information is a terminal adaptation score obtained by weighted summation of the eigenvalue of the feature with the second weight configured and the corresponding second weight;

[0222] Selecting the most suitable terminal based on the second decision information and sending a second regulation instruction to it includes:

[0223] Comparing the magnitudes of the calculated terminal adaptation scores, and taking the terminal corresponding to the highest terminal adaptation score as the most suitable terminal and sending a second regulation instruction to it.

[0224] In an implementation manner of the present disclosure, it further includes:

[0225] If the distributed energy supply within the terminal layer cannot meet the load requirements, the terminal layer performs resource scheduling on its subordinate terminal devices.

[0226] Figure 5 A schematic structural diagram of a computer system suitable for implementing the method according to the embodiments of the present disclosure is shown.

[0227] As Figure 5 shown, the computer system includes a processing unit, which can execute various methods in the above embodiments according to a program stored in a read-only memory (ROM) or a program loaded from a storage section into a random access memory (RAM). In the RAM, various programs and data required for the operation of the computer system are also stored. The processing unit, ROM, and RAM are connected to each other via a bus. An input / output (I / O) interface is also connected to the bus.

[0228] The following components are connected to the I / O interface: an input part including a keyboard, a mouse, etc.; an output part including a cathode ray tube (CRT), a liquid crystal display (LCD), etc. and a speaker, etc.; a storage part including a hard disk, etc.; and a communication part including a network interface card such as a LAN card, a modem, etc. The communication part performs a communication process via a network such as the Internet. A drive is also connected to the I / O interface as needed. A removable medium, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive as needed, so that a computer program read from it can be installed into the storage part as needed. Among them, the processing unit can be implemented as a processing unit such as a CPU, a GPU, a TPU, an FPGA, an NPU, etc.

[0229] Specifically, according to the embodiments of the present disclosure, the above-described method can be implemented as a computer software program. For example, the embodiments of the present disclosure include a computer program product, which includes a computer program tangibly contained on a machine-readable medium, and the computer program includes program codes for executing the above method. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part, and / or installed from a removable medium.

[0230] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a part of code, which contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than that marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, as well as combinations of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system that performs the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0231] The units or modules involved in the embodiments described in the present disclosure can be implemented in software or by programmable hardware. The described units or modules can also be provided in a processor, and the names of these units or modules do not, in some cases, constitute a limitation to the units or modules themselves.

[0232] As another aspect, the present disclosure also provides a chip, which includes at least one processor and can be used to implement the methods involved in the above system embodiments.

[0233] In a possible design, the chip further includes a memory, which is used to store program instructions and data, and the memory is located inside or outside the processor.

[0234] As another aspect, the present disclosure also provides a computer-readable storage medium, which can be the computer-readable storage medium included in the electronic device or computer system in the above embodiments; or it can exist separately and be a computer-readable storage medium not assembled into the device. The computer-readable storage medium stores one or more programs, and the one or more processors are used to execute the methods described in the present disclosure.

[0235] The above description is only the preferred embodiments of the present disclosure and an explanation of the applied technical principles. Those skilled in the art should understand that the scope of the invention involved in the present disclosure is not limited to the technical solutions formed by the specific combination of the above technical features, and should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the inventive concept. For example, the technical solutions formed by mutually replacing the above features with the (but not limited to) technical features with similar functions disclosed in the present disclosure.

Claims

1. A distributed energy aggregation control method, applicable to a distributed energy aggregation control system, characterized in that, The described distributed energy aggregation control system includes: a group layer, a subgroup layer, and a terminal layer. The group layer is configured with a group control center for achieving collective decision-making at the regional distribution network level. The subgroup layer consists of edge decision-making devices for decomposing the control tasks of the group layer. The terminal layer includes a distribution network on-site monitoring unit and a distribution network on-site control unit. The method includes: When the first resource control condition is met, the group layer selects the most suitable subgroup from its subordinate subgroup layer and sends a first control instruction to it; After receiving the first control instruction or when the second resource control condition is met, the most suitable subgroup selects the most suitable terminal from its subordinate terminal layer and sends a second control instruction to it; The most suitable terminal performs resource scheduling according to the received second control instruction.

2. The distributed energy aggregation control method according to claim 1, wherein The situations where the first resource control condition is met include: if a user demand instruction is received, it is determined that the first resource control condition is met; or, if the distributed energy supply within the group cannot meet the load requirement, it is determined that the first resource control condition is met; and / or The situations where the second resource control condition is met include: if the distributed energy supply within the subgroup cannot meet the load requirement, it is determined that the second resource control condition is met.

3. The distributed energy aggregation control method according to claim 1, characterized in that The group layer selects the most suitable subgroup from its subordinate subgroup layer and sends a first control instruction to it, including: The group layer obtains the subgroup node resource information uploaded by its subordinate subgroup layer; Performs first feature extraction and first weight configuration on the subgroup node resource information to obtain first decision-making information; Based on the first decision-making information, selects the most suitable subgroup and sends a first control instruction to it; Wherein, the subgroup node resource information is obtained by integrating the terminal layer resource information uploaded by the terminal layer subordinate to the subgroup layer; the terminal layer resource information includes the operation information and resource supply status information of each terminal device.

4. The distributed energy aggregation control method according to claim 3, wherein Performing first feature extraction and first weight configuration on the subgroup node resource information to obtain first decision-making information includes: Performing first feature extraction on the subgroup node resource information to obtain a first input vector; Inputting the first input vector into a first feature attention mechanism to configure a first sub-weight to obtain a first feature vector; Inputting the first feature vector into a time series attention mechanism to configure a second sub-weight to obtain a second feature vector; Based on the second feature vector, obtaining first decision-making information.

5. The distributed energy aggregation control method according to claim 3 or 4, characterized in that Selecting the most suitable terminal from its subordinate terminal layer and sending a second control instruction to it includes: Performing second feature extraction and second weight configuration on the terminal layer resource information to obtain second decision-making information; Based on the second decision-making information, selects the most suitable terminal and sends a second control instruction to it.

6. The distributed energy aggregation control method according to claim 5, wherein Performing second feature extraction and second weight configuration on the terminal layer resource information to obtain second decision-making information includes: Performing second feature extraction on the terminal layer resource information to obtain a second input vector; Inputting the second input vector into a second feature attention mechanism to configure a second weight to obtain a third feature vector; Based on the third feature vector, obtaining second decision-making information.

7. The distributed energy aggregation control method according to claim 6, characterized in that, It further includes: Uploading the second input vector as subgroup node resource information to the group layer and storing it in the subgroup node resource information library; The subgroup node resource information obtained by the group layer from the subgroup layers under it includes: Obtaining the subgroup node resource information uploaded by the subgroup layers under it from the subgroup node resource information library.

8. The distributed energy aggregation control and management method according to claim 3, wherein The first decision information is the subgroup adaptation score calculated by the weighted sum of the eigenvalues of the features configured with the first weights and the corresponding first weights; The step of selecting the most suitable subgroup based on the first decision information and sending a first regulation instruction to it includes: Comparing the magnitudes of the calculated subgroup adaptation scores, and taking the subgroup corresponding to the highest subgroup adaptation score as the most suitable subgroup and sending a first regulation instruction to it.

9. The distributed energy aggregation control method according to claim 5, characterized in that The second decision information is the terminal adaptation score calculated by the weighted sum of the eigenvalues of the features configured with the second weights and the corresponding second weights; The step of selecting the most suitable terminal based on the second decision information and sending a second regulation instruction to it includes: Comparing the magnitudes of the calculated terminal adaptation scores, and taking the terminal corresponding to the highest terminal adaptation score as the most suitable terminal and sending a second regulation instruction to it.

10. The distributed energy aggregation control method according to claim 1, characterized in that, It further includes: If the distributed energy supply within the terminal layer cannot meet the load requirements, the terminal layer performs resource scheduling on the terminal devices under it.

11. A distributed energy aggregation control device, characterized in that, It includes: A first regulation module, configured to, when the first resource regulation condition is met, the group layer selects the most suitable subgroup from the subgroup layers under it and sends a first regulation instruction to it; A second regulation module, configured to, after the most suitable subgroup receives the first regulation instruction or when the second resource regulation condition is met, select the most suitable terminal from the terminal layer under it and send a second regulation instruction to it; A resource scheduling module, configured to the most suitable terminal perform resource scheduling according to the received second regulation instruction; Wherein, the group layer configures a group regulation center for realizing collective decision-making at the regional distribution network level, the subgroup layer is composed of edge decision-making devices for decomposing the regulation tasks of the group layer, and the terminal layer includes a distribution network on-site monitoring unit and a distribution network on-site control unit.

12. The distributed energy aggregation control device according to claim 11, wherein The situations where the first resource regulation condition is met include: if a user demand instruction is received, it is determined that the first resource regulation condition is met; or, if the distributed energy supply within the group cannot meet the load requirements, it is determined that the first resource regulation condition is met; and / or, The situations where the second resource regulation condition is met include: if the distributed energy supply within the subgroup cannot meet the load requirements, it is determined that the second resource regulation condition is met.

13. The distributed energy aggregation control device according to claim 11, wherein The part of the first regulation module where the group layer selects the most suitable subgroup from the subgroup layers under it and sends a first regulation instruction to it is configured to: The group layer obtains the subgroup node resource information uploaded by the subgroup layers under it; Performing first feature extraction and first weight configuration on the subgroup node resource information to obtain first decision information; Selecting the most suitable subgroup based on the first decision information and sending a first regulation instruction to it; Among them, the subgroup node resource information is obtained by integrating the terminal layer resource information uploaded by the terminal layer subordinate to the subgroup layer; the terminal layer resource information includes the operation information and resource supply status information of each terminal device.

14. The distributed energy aggregation control device according to claim 13, wherein The part in the first regulation module that performs first feature extraction and first weight configuration on the subgroup node resource information to obtain first decision information is configured as: Performing first feature extraction on the subgroup node resource information to obtain a first input vector; Inputting the first input vector into a first feature attention mechanism to configure a first sub-weight to obtain a first feature vector; Inputting the first feature vector into a temporal attention mechanism to configure a second sub-weight to obtain a second feature vector; Obtaining first decision information based on the second feature vector.

15. The distributed energy aggregation control device according to claim 13 or 14, characterized in that The part in the second regulation module that selects the most suitable terminal from its subordinate terminal layer and sends a second regulation instruction to it is configured as: Performing second feature extraction and second weight configuration on the terminal layer resource information to obtain second decision information; Selecting the most suitable terminal based on the second decision information and sending a second regulation instruction to it.

16. The distributed energy aggregation control device according to claim 15, wherein The part in the second regulation module that performs second feature extraction and second weight configuration on the terminal layer resource information to obtain second decision information is configured as: Performing second feature extraction on the terminal layer resource information to obtain a second input vector; Inputting the second input vector into a second feature attention mechanism to configure a second weight to obtain a third feature vector; Obtaining second decision information based on the third feature vector.

17. The distributed energy aggregation control device according to claim 16, characterized in that, It further includes: A storage module, configured to upload the second input vector as subgroup node resource information to the group layer and store it in the subgroup node resource information library; The part in the first regulation module where the group layer obtains the subgroup node resource information uploaded by its subordinate subgroup layer is configured as: Obtaining the subgroup node resource information uploaded by its subordinate subgroup layer from the subgroup node resource information library.

18. The distributed energy aggregation control device according to claim 13, wherein The first decision information is a subgroup adaptation score obtained by weighted summation of the eigenvalue of the feature configured with the first weight and the corresponding first weight; The part in the first regulation module that selects the most suitable subgroup based on the first decision information and sends a first regulation instruction to it is configured as: Comparing the magnitudes of the calculated subgroup adaptation scores, and taking the subgroup corresponding to the highest subgroup adaptation score as the most suitable subgroup and sending a first regulation instruction to it.

19. The distributed energy aggregation control device according to claim 15, wherein The second decision information is a terminal adaptation score obtained by weighted summation of the eigenvalue of the feature configured with the second weight and the corresponding second weight; The part in the second regulation module that selects the most suitable terminal based on the second decision information and sends a second regulation instruction to it is configured as: Comparing the magnitudes of the calculated terminal adaptation scores, and taking the terminal corresponding to the highest terminal adaptation score as the most suitable terminal and sending a second regulation instruction to it.

20. The distributed energy aggregation control device according to claim 11, wherein It further includes: A terminal layer scheduling module, configured to perform resource scheduling on the terminal devices subordinate to the terminal layer if the distributed energy supply within the terminal layer cannot meet the load requirements.

21. An electronic device, characterized in that, It includes a memory and a processor; wherein, the memory is used for storing one or more computer instructions, and the one or more computer instructions are executed by the processor to implement the method according to any one of claims 1-10.

22. A computer-readable storage medium having computer instructions stored thereon, characterized in that, When the computer instructions are executed by the processor, the method according to any one of claims 1-10 is implemented.

23. A chip, characterized in that, It includes: At least one processor for implementing the method according to any one of claims 1-10.

Images