Negative pressure unloading bidirectional power distribution optimization intelligent control system

Abstract

The present invention discloses a bidirectional power distribution optimization intelligent control system for negative pressure unloading, which relates to the technical field of power distribution system. The system includes: an object set extraction module extracts the power consumption object set and the power supply object set of the target power distribution area; a power consumption characteristic analysis module collects historical power consumption data and constructs a power consumption portrait set; a power supply characteristic analysis module traverses the power supply object set and obtains a power supply control feature set; a model construction module constructs a negative pressure unloading twin simulation model based on the power distribution network topology, combined with the power consumption portrait set, the power supply control feature set, the connection relationship network and the negative pressure unloading principle; an initialization module initializes the negative pressure unloading twin simulation model according to the power consumption portrait set and the power supply control feature set; a twin simulation control decision module uses the negative pressure unloading twin simulation model to make intelligent control decisions and obtain a distribution control plan. Thus, the technical effect of improving the distribution response speed and efficiency and optimizing the distribution precision is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of power distribution systems, and in particular to a bidirectional power distribution optimization intelligent control system for negative pressure unloading. Background Art

[0002] In modern industrial and urban power distribution networks, with the continuous growth of electricity demand and the widespread application of distributed energy, the management of distribution systems has become increasingly complex. The distribution system not only needs to meet diverse electricity demand, but also needs to achieve energy efficiency optimization and cost control under the premise of ensuring power supply reliability. The existing distribution system regulation mainly relies on fixed preset parameters and manual intervention, which is difficult to cope with complex and changeable power consumption scenarios, especially hybrid distribution network scenarios such as photovoltaic and energy storage power stations. There are technical problems such as extensive regulation, high delay, and insufficient energy efficiency optimization. Summary of the invention

[0003] The present invention provides a bidirectional power distribution optimization intelligent control system with negative pressure unloading to solve the technical problems of high delay in extensive control and insufficient energy efficiency optimization in the prior art, and to achieve the technical effects of improving the power distribution response speed and efficiency and optimizing the power distribution precision.

[0004] The present invention also provides a negative pressure unloading bidirectional power distribution optimization intelligent control system, comprising:

[0005] An object set extraction module, the object set extraction module is used to interact with the target power distribution area and extract the power consumption object set and the power supply object set; a power consumption characteristic analysis module, the power consumption characteristic analysis module is used to collect and obtain the historical power consumption data set based on the power consumption object set, and analyze the power consumption characteristics of multiple power consumption objects according to the historical power consumption data set to construct a power consumption portrait set; a power supply characteristic analysis module, the power supply characteristic analysis module is used to traverse the power supply object set, interact with multiple power supply objects, obtain multiple groups of power supply performance data, and analyze the power supply characteristics to obtain multiple power supply control feature sets; a model construction module, the model construction module is used to collect and obtain the historical power consumption data set based on the target power distribution area The power distribution network topology is constructed by taking the power consumption object set and the power supply object set as the network body, obtaining the connection relationship network, and combining the power consumption portrait set, multiple power supply regulation feature sets, the connection relationship network and the negative pressure unloading principle to construct a negative pressure unloading twin simulation model; an initialization module, wherein the initialization module is used to initialize the negative pressure unloading twin simulation model according to the power consumption portrait set and multiple power supply regulation feature sets; a twin simulation regulation decision module, wherein the twin simulation regulation decision module is used to perform intelligent regulation decisions based on twin simulation according to the negative pressure unloading twin simulation model and the negative pressure unloading principle to obtain a power distribution regulation plan.

[0006] The present invention discloses a bidirectional power distribution optimization intelligent control system for negative pressure unloading, including an object set extraction module for interacting with target power distribution areas, extracting power consumption object sets and power supply object sets; a power consumption characteristic analysis module, based on the power consumption object set, collecting historical power consumption data, analyzing power consumption characteristics and constructing a power consumption portrait set; a power supply characteristic analysis module, traversing the power supply object set, obtaining power supply performance data, analyzing power supply characteristics and obtaining a power supply control feature set; a model construction module, based on the topology of the distribution network, with the power consumption object set and the power supply object set as the main body, combining the power consumption portrait set, the power supply control feature set, the connection relationship network and the negative pressure unloading principle, to construct a negative pressure unloading twin simulation model; an initialization module, according to the power consumption portrait set and the power supply control feature set, initializes the negative pressure unloading twin simulation model; a twin simulation control decision module, based on the twin simulation model and the negative pressure unloading principle, makes intelligent control decisions and obtains a distribution control plan. The bidirectional power distribution optimization intelligent control system for negative pressure unloading disclosed by the present invention solves the technical problems of high extensive control delay and insufficient energy efficiency optimization, and achieves the technical effects of improving the distribution response speed and efficiency and optimizing the distribution precision. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] Figure 1 It is a structural schematic diagram of the bidirectional power distribution optimization intelligent control system for negative pressure unloading of the present invention;

[0008] Figure 2 A schematic diagram of the process of constructing a negative pressure unloading twin simulation model in the bidirectional power distribution optimization intelligent control system of negative pressure unloading of the present invention.

[0009] Explanation of the accompanying drawings: object set extraction module 11, power consumption characteristic analysis module 12, power supply characteristic analysis module 13, model construction module 14, initialization module 15, twin simulation control decision module 16. DETAILED DESCRIPTION

[0010] The technical solution provided in the embodiments of the present invention is to solve the technical problems of high delay in extensive control and insufficient energy efficiency optimization in the prior art. The overall idea adopted is as follows:

[0011] First, the object set extraction module is used to interact with the target distribution area and extract the power consumption object set and the power supply object set. Then, the power consumption characteristic analysis module collects and obtains the historical power consumption data set based on the power consumption object set, and analyzes the power consumption characteristics of multiple power consumption objects according to the historical power consumption data set to construct a power consumption portrait set. Then, the power supply characteristic analysis module traverses the power supply object set, interacts with multiple power supply objects, obtains multiple sets of power supply performance data, and analyzes the power supply characteristics to obtain multiple power supply regulation feature sets. Next, the model construction module is based on the distribution network topology of the target distribution area, takes the power consumption object set and the power supply object set as the network body, obtains the connection relationship network, and combines the power consumption portrait set, multiple power supply regulation feature sets, the connection relationship network and the negative pressure unloading principle to construct a negative pressure unloading twin simulation model. Furthermore, the initialization module initializes the negative pressure unloading twin simulation model according to the power consumption portrait set and multiple power supply regulation feature sets. Finally, the twin simulation regulation decision module makes an intelligent regulation decision based on twin simulation according to the negative pressure unloading twin simulation model and the negative pressure unloading principle to obtain a distribution regulation plan.

[0012] The above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods of the specification to better understand the above technical solution. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments of the present invention. It should be understood that the present invention is not limited to the example embodiments used only to explain the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention. In addition, it should be noted that, for the convenience of description, only the parts related to the present invention are shown in the drawings, rather than all of them. Example

[0013] Figure 1 The schematic diagram of the structure of the bidirectional power distribution optimization intelligent control system for negative pressure unloading of the present invention is shown in FIG. 1 , wherein the system includes:

[0014] The object set extraction module 11 is used to interact with the target power distribution area and extract the power consumption object set and the power supply object set.

[0015] Specifically, first, obtain the power consumption object set and power supply object set contained in the target power distribution area. The power consumption object set includes all equipment and facilities that need electricity, represented by terminal distribution equipment corresponding to multiple power consumption objects, exemplarily including power distribution rooms in factories or industrial parks, transformers in communities, energy storage power stations, etc. The power supply object set includes all equipment and facilities that can generate or distribute electricity, such as power plants, substations, energy storage power stations, distributed photovoltaics, etc.

[0016] Specifically, for a multi-level power distribution network, the intermediate power distribution facilities and equipment can be regarded as both power users and power supply users. For example, a substation receives high-voltage power from a power plant and then converts the power into a lower voltage through a transformer to supply residential, commercial and industrial power. In this process, the substation is both a power user that receives power and a power supply user that distributes power.

[0017] Similarly, energy storage plants, such as battery energy storage systems (BESS), store electricity when there is excess power and release it when there is a shortage. Therefore, they can both absorb power from the grid (as a consumer) and supply power to the grid (as a supplier). Some factories and industrial parks may have their own power generation facilities installed, such as solar photovoltaic panels or wind turbines. When their power production exceeds their own needs, they can supply power to the grid. When power production is insufficient, they may need to obtain power from the grid.

[0018] In some embodiments, the target power distribution area is interacted with, and the power consumption object set and the power supply object set are extracted. The execution steps include:

[0019] Connect to the distribution management system of the target distribution area to obtain a power consumption information set and a power supply information set; parse the power consumption information set, classify and mark it, and obtain the power consumption object set and the power supply object set; obtain the intersection of the power consumption object set and the power supply object set, and mark it as a bidirectional object.

[0020] Specifically, first, connect to the distribution management system of the target distribution area, such as the distribution management system (such as the SCADA system) for communication, obtain historical power data including current, voltage, power, etc., and obtain the power consumption information set and power supply information set. Among them, the power consumption information set includes the load demand, power factor and other information of each power user; the power supply information set includes the power generation capacity, energy storage status and other information of each power supply object.

[0021] Furthermore, the electricity consumption information set is parsed, analyzed and processed to identify which devices are electricity users and which devices are power supply objects. Then, the intersection of the electricity consumption object set and the power supply object set is obtained to identify those devices that can both obtain electricity from the power grid (as electricity users) and supply power to the power grid (as power supply objects). Examples include energy storage power stations, buildings with photovoltaic roofs, factories and industrial parks with power generation facilities, etc.

[0022] The power consumption characteristic analysis module 12 is used to collect and obtain a historical power consumption data set based on the power consumption object set, and analyze the power consumption characteristics of multiple power consumption objects according to the historical power consumption data set to construct a power consumption portrait set.

[0023] Specifically, the power consumption portrait set is used to describe the power consumption characteristics of multiple power users in the target area. It is a detailed description of the power consumption characteristics of each power user, including the average power consumption, peak and valley periods, power consumption stability, and power consumption seasonality of each power user. Power consumption portraits help to better understand and predict power grid load, thereby optimizing power distribution and scheduling.

[0024] In some embodiments, based on the electricity consumption object set, a historical electricity consumption data set is collected and acquired, and the electricity consumption characteristics of multiple electricity consumption objects are analyzed according to the historical electricity consumption data set to construct an electricity consumption portrait set. The execution steps include:

[0025] Using the electricity consumption object set as an index, interact with the target area electricity consumption database to obtain the historical electricity consumption data set; parse the historical electricity consumption data to extract features and obtain the electricity consumption characteristics of multiple electricity consumption objects; based on a clustering algorithm, perform cluster analysis on the electricity consumption characteristics, and according to the clustering analysis results, group the multiple electricity consumption objects to form electricity consumption characteristic classification labels; based on the electricity consumption characteristic classification labels, in combination with the electricity consumption characteristics, construct multiple electricity consumption portraits to generate the electricity consumption portrait set.

[0026] Specifically, first, through the index of the power consumption object set, through SQL, NoSQL database management system, connect and query the power consumption database of the target area to obtain the historical power consumption data set. These data include the power consumption and power consumption mode of each power consumption object in different time periods.

[0027] Specifically, the acquired historical power consumption data is analyzed, and power consumption characteristics are extracted through statistical analysis, signal processing, etc. Exemplarily, the power consumption characteristics include average power consumption, power consumption peak, power consumption valley, power consumption frequency, etc.

[0028] Furthermore, based on clustering algorithms (such as K-means, DBSCAN, hierarchical clustering, etc.), cluster analysis is performed on the power consumption characteristics to group power users with similar power consumption characteristics. Then, based on the clustering analysis results, a power consumption characteristic classification label is assigned to each power user, and these labels can represent different power consumption modes or categories.

[0029] Specifically, based on the classification labels of electricity consumption characteristics and combined with specific electricity consumption characteristics, multiple electricity consumption portraits are constructed. Each electricity consumption portrait describes in detail the electricity consumption characteristics of a certain type of electricity user, such as daily electricity consumption patterns, peak electricity consumption times, etc. Finally, all electricity consumption portraits are summarized to form an electricity consumption portrait set for subsequent analysis and application.

[0030] The above steps, through the analysis and clustering of electricity consumption characteristics, obtain electricity consumption portraits and accurately describe the electricity consumption characteristics of electricity users, which facilitates the analysis and prediction of electricity consumption behavior, thereby improving the operating efficiency and reliability of the power system.

[0031] The power supply characteristic analysis module 13 is used to traverse the power supply object set, interact with multiple power supply objects, obtain multiple groups of power supply performance data, and analyze the power supply characteristics to obtain multiple power supply control feature sets.

[0032] In some embodiments, the power supply object set is traversed, multiple power supply objects are interacted, multiple groups of power supply performance data are obtained, and power supply characteristics are analyzed to obtain multiple power supply regulation feature sets. The execution steps include:

[0033] Interact with multiple power supply objects to obtain the power supply performance data, which includes power supply capacity data, power supply cost data and power supply attribute data; based on the power supply performance data, extract key control indicator values ​​and output them as the power supply control feature set, wherein the key control indicators include response speed, control range, and cost characteristic curve.

[0034] Specifically, it interacts with multiple power supply objects and obtains power supply performance data, which involves communicating with power supply objects (such as power stations, energy storage equipment, renewable energy equipment, etc.) to obtain data on power supply capacity, power supply cost and power supply attributes. Among them, power supply capacity includes maximum and minimum output power, startup and shutdown time, etc.; power supply cost includes fuel cost, operation and maintenance cost, etc.; power supply attributes include power generation type (such as thermal power, hydropower, wind power, solar power, etc.), equipment age, equipment efficiency, etc.

[0035] Specifically, based on the power supply performance data, the key control indicator values ​​are extracted and output as a power supply control feature set, which involves analyzing the collected power supply performance data and extracting the key control indicators. These include response speed (i.e., the time required for the device to switch from one output state to another), control range (i.e., the difference between the maximum and minimum output power that the device can provide), and cost characteristic curve (i.e., the relationship between output power and cost). Exemplarily, the key control indicator values ​​are extracted through data analysis and machine learning techniques, such as regression analysis, cluster analysis, and decision trees.

[0036] Through the above steps, the characteristics of the power supply objects can be better understood and utilized to optimize the dispatch and management of the power grid. For example, by understanding the response speed and regulation range of each power supply object, the load of the power grid can be better predicted and managed; by understanding the cost characteristic curve of each power supply object, power can be allocated more efficiently to minimize the total cost of the target distribution area.

[0037] The model building module 14 is used to obtain a connection relationship network based on the distribution network topology of the target distribution area, with the power consumption object set and the power supply object set as the network body, and to construct a negative pressure unloading twin simulation model by combining the power consumption portrait set, multiple power supply regulation feature sets, the connection relationship network and the negative pressure unloading principle.

[0038] Specifically, the negative pressure unloading twin simulation model is used to map the power distribution process to the negative pressure unloading process in the digital twin space, including mapping electricity to material particles waiting to be unloaded. These particles flow in the power grid and wait to be unloaded (i.e., consumed) at the appropriate place; mapping power users to negative pressure unloading ports that attract and consume material particles (electricity). Different power users have different suction forces, depending on their power needs. Furthermore, the flow and distribution of electricity is simulated through the physical process of negative pressure unloading to optimize the power distribution in the target distribution area.

[0039] Exemplarily, a negative pressure unloading twin simulation model is constructed by combining numerical methods, fluid dynamics simulation, etc.

[0040] Through the above steps, we can more intuitively understand the operation of the power system, thereby simplifying the calculation process of decision optimization and improving the efficiency of distribution control.

[0041] In some embodiments, based on the power distribution network topology of the target power distribution area, the power consumption object set and the power supply object set are taken as network entities to obtain a connection relationship network, and the execution steps include:

[0042] Obtain the distribution network topology data of the target distribution area, collect the geographic location information and connection relationship of multiple power users and multiple power supply objects; establish a digital network space, map each power user in the power user set to a power node, and map each power supply object in the power supply object set to a power supply node; based on the connection relationship, establish relationship edges between multiple power user nodes and multiple power supply nodes, wherein the relationship edges are marked with direction, connection distance, connection loss, and connection capacity.

[0043] Specifically, first, obtain the topological structure information of the distribution network from the distribution management system or related data platform, including data on substations, distribution lines and distribution facilities. Then, use the Geographic Information System (GIS) and other measurement tools to determine the geographical location of electricity users (such as residential areas and industrial areas) and power supply objects (such as substations and power stations).

[0044] Specifically, each power-consuming object is mapped to a power-consuming node, and each power-supplying object is mapped to a power-supplying node. Representations of these nodes are established in the digital space, and unique identifiers are assigned to them. Furthermore, based on the previously collected connection relationships, relationship edges between power-consuming nodes and power-supplying nodes are established, and the direction, connection distance, connection loss, and connection capacity are marked for each relationship edge. The direction indicates the direction of power transmission, from the power supply node to the power-consuming node. The connection distance indicates the actual physical distance between the power supply node and the power-consuming node. The connection loss indicates the power loss caused by distance and other factors during power transmission. The connection capacity indicates the maximum ability of the power supply node to provide power to the power-consuming node.

[0045] Through the above steps, clear connection relationships and node attributes are determined, the power transmission path and loss conditions are understood, and basic data support is provided for power regulation and optimization in the target distribution area.

[0046] In some embodiments, a negative pressure unloading twin simulation model is constructed by combining the power consumption portrait set, the plurality of power supply regulation feature sets, the connection relationship network and the negative pressure unloading principle, and the execution steps include:

[0047] Based on the digital network space, a twin simulation space is constructed; according to the multiple power supply regulation feature sets, the multiple power supply nodes are mapped into multiple twin material sources and twin materials of corresponding particle sizes, wherein the twin material sources are marked with material output characteristics; according to the power consumption portrait set, the multiple power consumption nodes are mapped into negative pressure unloading ports with different suction forces; based on the connection relationship network, a material plane is constructed, and material passages between the multiple twin material sources and the multiple negative pressure unloading ports are configured on the material plane, wherein the multiple material passages are configured with friction coefficients and plane connectivity constraints based on the connectivity of the power grid in the target distribution area.

[0048] Specifically, first, a twin simulation space is established based on the digital network space. The twin simulation space is built based on the digital twin model to reflect the actual power grid system. Then, each power supply node of the power grid system is mapped to a material source in the twin model. These twin material sources will simulate the generation and output of electricity. The material output characteristics of each twin material source will be marked according to the characteristics of the power supply node.

[0049] Illustratively, the power supply regulation range of the power supply node determines the twin material output rate range of the twin material source, and the energy type of the power supply node determines the material radius of the twin material source. This is because the energy cleanliness (characterized by carbon emissions) of electric energy with different properties is different. By allocating a smaller material radius to the twin material source with higher energy cleanliness, it is possible to ensure that the twin material corresponding to the electric energy with higher energy cleanliness can be allocated with priority during the simulation process based on numerical methods, fluid dynamics, etc.

[0050] Specifically, each power-consuming node of the power grid system is mapped to a negative pressure unloading port in the twin model, which will simulate the consumption of electricity. The suction of each unloading port will be set according to the power demand of the power node. For example, if the power demand of a power node is large, the suction of the corresponding negative pressure unloading port should also be large accordingly, so as to ensure that the node can obtain enough electricity. On the contrary, if the power demand of a power node is small, the suction of the corresponding negative pressure unloading port should also be small accordingly.

[0051] Specifically, the connection relationship of the power grid system is mapped to the material paths in the twin model, which will simulate the transmission of electricity. The friction coefficient and plane connectivity constraints of each path will be set according to the connectivity of the power grid. Among them, the material plane represents the entire power system, and the material path between the twin material source and the negative pressure unloading port represents the transmission path of electricity.

[0052] Specifically, the friction coefficient represents the difficulty of power transmission, which is related to factors such as the length and resistance of the power line. The plane connectivity constraint constrains the movement path of the twin material, ensuring that the unloading path of the twin material during the simulation is consistent with the distribution line of the actual power grid. Through the above settings, the loss during power transmission can be simulated to ensure that the efficiency of power supply meets expectations.

[0053] For example, if the length of a power line is long, then in the model, the friction coefficient of the corresponding material path may be large, indicating that the resistance of power transmission is large. On the contrary, if the length of a power line is short, then the friction coefficient of the corresponding material path may be small, indicating that the difficulty of power transmission is small. In addition, the width of the material path in the plane connectivity constraint corresponds to the load capacity (such as current) of the distribution line, and the voltage constraints marked by different material paths ensure the safety and stability of the simulation-based decision results in practical applications.

[0054] The initialization module 15 is used to initialize the negative pressure unloading twin simulation model according to the power consumption portrait set and the multiple power supply regulation feature sets.

[0055] In some embodiments, the negative pressure unloading twin simulation model is initialized according to the power consumption portrait set and the plurality of power supply regulation feature sets, and the execution steps include:

[0056] Interact with the target power distribution area to obtain real-time grid time and real-time connectivity information; based on the real-time grid time and the power consumption portrait set, update the negative pressure parameters of the multiple negative pressure unloading ports; based on the real-time connectivity information, update the multiple material passages of the material plane; interact with the multiple power supply objects to obtain real-time power supply data; based on the real-time power supply data and the multiple power supply control feature sets, update the feeding parameters of the multiple twin material sources and the particle size parameters of the twin materials of the corresponding particle size.

[0057] Specifically, first, the target distribution area is interacted with to obtain the real-time status of the power grid, including information such as the power grid timestamp and the connectivity of the power grid. The connectivity information of the power grid refers to the availability of the power grid distribution lines, which is used to identify whether there are currently unavailable lines such as failures or maintenance.

[0058] Specifically, based on the real-time grid time, the power consumption portrait set is called, the power consumption demand characteristics of multiple power users in the current time period are measured, and the negative pressure parameters of each negative pressure unloading port are updated (i.e., the suction is adjusted) to match the real-time power demand and load characteristics.

[0059] Specifically, the material path of the material plane is updated according to the real-time connectivity information, which involves adjusting the friction coefficient of the material path and the plane connectivity constraint to reflect the actual connection status and transmission path of the current power grid.

[0060] Specifically, the real-time power supply situation of each power supply object is obtained, and real-time power supply data is collected, including power supply capacity, power supply cost, etc. Then, according to the real-time power supply data and the power supply control feature set, the output parameters of the twin material source are adjusted, such as adjusting the feeding speed and particle size, to adapt to the real-time power supply.

[0061] In other words, through real-time power supply data, the output status of multiple power supply objects can be determined, especially the real-time identity of energy storage power stations, buildings with photovoltaic roofs, factories and industrial parks with power generation facilities, etc., which are both electricity users and power supply objects. This ensures a comprehensive and accurate twin simulation of the real-time status of the target distribution area, thereby more effectively managing and optimizing distribution control.

[0062] In some embodiments, Figure 2 As shown, combining the connection relationship network with the negative pressure unloading principle, a negative pressure unloading twin simulation model is constructed, and the execution steps also include:

[0063] Based on the distribution network level, the negative pressure unloading twin simulation model is hierarchically graded to obtain multiple sub-material planes, wherein each sub-material plane is marked with a corresponding distribution network level; the connection relationship network is parsed to obtain a tree-like connection relationship network; according to the tree-like connection relationship network, multiple sub-material planes are hierarchically connected to form a graded negative pressure unloading twin simulation model, wherein the unloading port of the upper-level sub-material plane corresponds to the twin material source of the lower-level sub-material plane; based on the graded negative pressure unloading twin simulation model, power distribution optimization is performed layer by layer from top to bottom.

[0064] Specifically, according to the levels of different power users and power supply objects in the distribution network (such as main distribution network, secondary distribution network, low-voltage distribution network, etc.), multiple negative pressure unloading ports and twin material sources in the negative pressure unloading twin simulation model are hierarchically clustered based on levels, and the sub-material plane corresponding to each level is obtained, and the corresponding distribution network level is marked on the sub-material plane. Among them, the sub-material plane corresponds to a type of classification result in the hierarchical classification, and multiple sub-material planes of the same level are multiple secondary distribution networks in parallel.

[0065] Exemplarily, each power user (main distribution or substation equipment) under the main distribution network corresponds to a sub-distribution network, and the main distribution network includes multiple sub-distribution networks. The corresponding high-level material plane may include multiple low-level sub-material planes.

[0066] Specifically, the connection relationship of the power system is analyzed and a tree-like connection relationship network is constructed. In this network, each node corresponds to a sub-material plane, and each edge corresponds to the connection relationship between two sub-material planes, which is used to understand the structure and flow path of the power system.

[0067] Specifically, according to the tree-like connection relationship network, each sub-material plane is hierarchically connected to form a graded negative pressure unloading twin simulation model. Among them, the material unloading port of the upper-level sub-material plane (such as the power input end of the secondary distribution station / substation) corresponds to the twin material source (power output end) of the lower-level sub-material plane (such as the material plane where the tertiary distribution station / substation or user terminal equipment is located). In other words, after receiving the electric energy, the material unloading port in the upper-level sub-material plane will be further sent to the power-consuming equipment at the next level, and the input and output of electric energy are corresponding, so the material unloading port in the upper-level sub-material plane can be regarded as the twin material source in the lower-level sub-material plane.

[0068] Through the above models, the flow and distribution of electricity can be clearly represented, and the complex structure and dynamic behavior of the power system can be mapped into a simpler and more intuitive model, thereby improving the efficiency and stability of the power system.

[0069] The twin simulation control decision module 16 is used to make intelligent control decisions based on twin simulation according to the negative pressure unloading twin simulation model and the negative pressure unloading principle to obtain a power distribution control plan.

[0070] Specifically, computational fluid dynamics (CFD) methods are used to simulate the flow and distribution of electricity to simplify the optimization settings and calculations of bidirectional power distribution optimization, and then, based on the simulation results, intelligent control decisions are made, including adjusting the supply and distribution of electricity to optimize the operation of the power system.

[0071] In summary, the bidirectional power distribution optimization intelligent control system for negative pressure unloading provided by the present invention has the following technical effects:

[0072] Through the object set extraction module, the target distribution area is interacted to extract the power consumption object set and the power supply object set; the power consumption characteristic analysis module, based on the power consumption object set, collects historical power consumption data, analyzes the power consumption characteristics and constructs a power consumption portrait set; the power supply characteristic analysis module traverses the power supply object set, obtains the power supply performance data, analyzes the power supply characteristics and obtains the power supply regulation feature set; the model construction module, based on the distribution network topology, takes the power consumption object set and the power supply object set as the main body, combines the power consumption portrait set, the power supply regulation feature set, the connection relationship network and the negative pressure unloading principle, to construct a negative pressure unloading twin simulation model; the initialization module, according to the power consumption portrait set and the power supply regulation feature set, initializes the negative pressure unloading twin simulation model; the twin simulation regulation decision module, based on the twin simulation model and the negative pressure unloading principle, makes intelligent regulation decisions and obtains the distribution regulation plan.

[0073] This achieves the technical effect of improving the distribution response speed and efficiency and optimizing the distribution precision.

[0074] It should be understood that the embodiments disclosed in the present invention and the above description can enable those skilled in the art to use the present invention to implement the present invention. At the same time, the present invention is not limited to the above-mentioned embodiments. It should be understood that those skilled in the art can still modify the technical solutions recorded in the above-mentioned embodiments, or replace some of the technical features therein by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. Negative pressure unloading bidirectional power distribution optimization intelligent control system, characterized by: The system comprises: An object set extraction module, the object set extraction module is used to interact with the target power distribution area and extract the power consumption object set and the power supply object set; An electricity consumption characteristic analysis module, the electricity consumption characteristic analysis module is used to collect and obtain a historical electricity consumption data set based on the electricity consumption object set, and analyze the electricity consumption characteristics of multiple electricity consumption objects according to the historical electricity consumption data set to construct an electricity consumption portrait set; A power supply characteristic analysis module, which is used to traverse the power supply object set, interact with multiple power supply objects, obtain multiple groups of power supply performance data, and analyze power supply characteristics to obtain multiple power supply control feature sets; A model building module, wherein the model building module is used to obtain a connection relationship network based on the distribution network topology of the target distribution area, taking the power consumption object set and the power supply object set as the network body, and combining the power consumption portrait set, the multiple power supply regulation feature sets, the connection relationship network and the negative pressure unloading principle to build a negative pressure unloading twin simulation model; An initialization module, the initialization module being used to initialize the negative pressure unloading twin simulation model according to the power consumption portrait set and a plurality of power supply regulation feature sets; A twin simulation control decision module, which is used to make intelligent control decisions based on twin simulation according to the negative pressure unloading twin simulation model and the negative pressure unloading principle to obtain a power distribution control plan; Wherein, based on the power distribution network topology of the target power distribution area, taking the power consumption object set and the power supply object set as the network body, obtaining the connection relationship network, the execution steps include: Acquire the distribution network topology data of the target distribution area, and collect the geographical location information and connection relationship of the plurality of power users and the plurality of power supply objects; Establishing a digital network space, mapping each of the power-consuming objects in the power-consuming object set to a power-consuming node, and mapping each of the power-supplying objects in the power-supplying object set to a power-supplying node; Based on the connection relationship, establish relationship edges between the plurality of power consumption nodes and the plurality of power supply nodes, wherein the relationship edges are marked with direction, connection distance, connection loss, and connection capacity; Among them, combining the power consumption portrait set, the multiple power supply regulation feature sets, the connection relationship network and the negative pressure unloading principle, a negative pressure unloading twin simulation model is constructed, and the execution steps include: Based on the digital network space, construct a twin simulation space; According to the plurality of power supply control feature sets, mapping the plurality of power supply nodes to a plurality of twin material sources and twin materials of corresponding particle sizes, wherein the twin material sources are marked with material output characteristics; According to the power consumption image set, mapping the plurality of power consumption nodes to negative pressure unloading ports with different suction forces; Based on the connection relationship network, a material plane is constructed, and a plurality of material passages between the twin material sources and the negative pressure unloading ports are configured on the material plane, wherein the plurality of material passages are configured with a friction coefficient and a plane connectivity constraint based on the connectivity of the power grid in the target distribution area; In which, combining the connection relationship network with the negative pressure unloading principle, a negative pressure unloading twin simulation model is constructed, and the execution step also includes: Based on the distribution network level, the negative pressure unloading twin simulation model is hierarchically graded to obtain a plurality of sub-material planes, wherein each of the sub-material planes is marked with a corresponding distribution network level; Parsing the connection relationship network to obtain a tree-like connection relationship network; According to the tree-like connection relationship network, multiple sub-material planes are hierarchically connected to form a graded negative pressure unloading twin simulation model, wherein the unloading port of the upper-level sub-material plane corresponds to the twin material source of the lower-level sub-material plane; Based on the hierarchical negative pressure unloading twin simulation model, power distribution optimization is performed layer by layer from top to bottom.

2. The negative pressure unloading bidirectional power distribution optimization intelligent control system according to claim 1, characterized in that: Interact with the target power distribution area, extract the power consumption object set and the power supply object set, and the execution steps include: Connect to the power distribution management system of the target power distribution area to obtain the power consumption information set and the power supply information set; Parsing the electricity usage information set, classifying and marking it, and obtaining the electricity usage object set and the power supply object set; The intersection of the power consumption object set and the power supply object set is obtained and marked as a bidirectional object.

3. The bidirectional power distribution optimization intelligent control system for negative pressure unloading according to claim 2 is characterized in that: Based on the electricity consumption object set, a historical electricity consumption data set is collected and acquired, and the electricity consumption characteristics of multiple electricity consumption objects are analyzed according to the historical electricity consumption data set to construct an electricity consumption portrait set. The execution steps include: Using the electricity consumption object set as an index, interacting with the target area electricity consumption database, and acquiring the historical electricity consumption data set; Analyzing the historical electricity consumption data to extract features and obtaining the electricity consumption characteristics of the plurality of electricity consumption objects; Based on a clustering algorithm, cluster analysis is performed on the power consumption characteristics, and according to the cluster analysis results, a plurality of power consumption objects are grouped to form power consumption characteristic classification labels; Based on the electricity usage characteristic classification labels and in combination with the electricity usage characteristics, a plurality of electricity usage portraits are constructed to generate the electricity usage portrait set.

4. The bidirectional power distribution optimization intelligent control system for negative pressure unloading according to claim 3 is characterized in that: Traversing the power supply object set, interacting with multiple power supply objects, obtaining multiple sets of power supply performance data, and analyzing power supply characteristics to obtain multiple power supply regulation feature sets, the execution steps include: Interacting with a plurality of the power supply objects to obtain the power supply performance data, wherein the power supply performance data includes power supply capacity data, power supply cost data and power supply attribute data; Based on the power supply performance data, key control index values ​​are extracted and output as the power supply control feature set, wherein the key control indexes include response speed, control range, and cost characteristic curve.

5. The bidirectional power distribution optimization intelligent control system for negative pressure unloading according to claim 4 is characterized in that: Initializing the negative pressure unloading twin simulation model according to the power consumption portrait set and the plurality of power supply regulation feature sets, the execution steps include: Interact with target distribution areas to obtain real-time grid time and real-time connectivity information; Based on the real-time grid time and the power consumption image set, updating the negative pressure parameters of the plurality of negative pressure unloading ports; Based on the real-time connectivity information, updating the plurality of material pathways of the material plane; Interact with a plurality of the power supply objects to obtain real-time power supply data; Based on the real-time power supply data and the plurality of power supply control feature sets, the supply parameters of the plurality of twin material sources and the particle size parameters of the twin materials of corresponding particle sizes are updated.

Images