A coordinated control method for multi-energy power system in time and space

Abstract

The present application provides a method for coordinated control of a multi-energy power system at a spatiotemporal scale, and relates to the field of power dispatching technology, including: training based on energy historical data sets to construct a multi-energy joint distribution model; inputting energy real-time data sets and preset time series scales into the energy joint distribution model, outputting complementary probabilities between energy sources based on preset time series scales, and outputting complementary probability sets; identifying complementary paths for a first energy node topology network based on the complementary probability set, and outputting a second energy node topology network; and performing power coordinated control based on the second energy node topology network. The present application can solve the technical problem that in traditional methods, efficient energy coordinated dispatching cannot be achieved due to the inability to accurately quantify the complementary characteristics of multiple energy sources at a spatiotemporal scale, and can effectively quantify the correlation, complementarity, and fluctuation characteristics of multiple energy types at a spatiotemporal scale, and achieve scientific and flexible coordinated dispatching of multiple energy sources.

Description

Technical Field

[0001] The present application relates to the technical field of power dispatching, and in particular to a method for coordinated control of multi-energy power systems at spatiotemporal scales. Background Art

[0002] The multi-energy power dispatch method refers to optimizing the proportion of various energy sources (including traditional energy such as thermal power, nuclear power, natural gas, etc., and renewable energy such as wind power, solar power, hydropower, etc.) in the power system through scientific dispatching means to achieve the balance of power supply and demand, stable operation of the system and maximum energy efficiency. Multi-energy power dispatching must not only consider the real-time demand of power load, but also comprehensively consider the characteristics of various energy sources and flexibly respond to the changing power load and energy supply.

[0003] At present, traditional multi-energy power dispatching methods have certain limitations in practical applications. Especially when dealing with complex multi-energy systems, they cannot give full play to the complementary advantages of various energy sources and it is difficult to achieve efficient and stable coordinated dispatching. Summary of the invention

[0004] The purpose of this application is to provide a method for coordinated control of a multi-energy power system on a spatiotemporal scale, so as to solve the technical problem that in traditional multi-energy power dispatching methods, efficient energy coordinated dispatching cannot be achieved due to the inability to accurately quantify the complementary characteristics of multiple energy sources on a spatiotemporal scale.

[0005] In view of the above problems, the present application provides a method for coordinated control of a multi-energy power system at a spatiotemporal scale, including: identifying a first energy node topology network of the multi-energy power system, wherein the first energy node topology network is obtained based on the spatial positions of energy nodes in a target area; performing real-time monitoring on the first energy node topology network to obtain an energy real-time data set; training based on an energy historical data set to construct a multi-energy joint distribution model; obtaining a preset time series scale, inputting the energy real-time data set and the preset time series scale into the energy joint distribution model, outputting the complementary probability between each energy source under the preset time series scale, and outputting a complementary probability set; performing complementary path identification on the first energy node topology network according to the size of the complementary probability set, and outputting a second energy node topology network with a complementary path identification, wherein a complementary path is a path composed of energy type pairs with a complementary probability greater than a preset complementary probability; the multi-energy power system performs power coordinated control according to the second energy node topology network.

[0006] Optionally, the method for coordinated control of a multi-energy power system at spatiotemporal scales also includes: acquiring multiple time series scale samples, the multiple time series scale samples including short-term, medium-term, and long-term; performing feature convolution on the energy historical data set according to the multiple time series scale samples, and outputting an energy feature data set corresponding to each time series scale sample; using the energy feature data set corresponding to each time series scale sample, constructing a multi-energy joint distribution sub-model corresponding to each time series scale sample; integrating the multi-energy joint distribution sub-models corresponding to each time series scale sample to construct a multi-energy joint distribution model.

[0007] Optionally, the method for coordinated control of a multi-energy power system at spatiotemporal scales also includes: constructing an edge distribution of each energy source using an energy feature data set corresponding to each time series scale sample, and outputting multiple edge distributions; identifying the correlation between each energy source to obtain a correlation identification result; connecting the multiple edge distributions according to the correlation identification result, and outputting a multi-energy joint distribution sub-model, wherein the model parameters of the multi-energy joint distribution sub-model are obtained through gradient descent optimization.

[0008] Optionally, the multi-energy power system spatiotemporal scale coordinated control method further includes: outputting the complementary probability between the energy sources based on the preset time series scale, wherein the calculation formula of the complementary probability is: ;in, Based on the energy under the preset time series scale and energy The complementary probability between To preset the time scale, For energy and energy The joint marginal distribution of a and b are energy The upper and lower limits of the power index, c and d are energy The upper limit and lower limit of power indicators.

[0009] Optionally, the method for coordinated control of a multi-energy power system at spatiotemporal scales also includes: identifying the number of path identifiers of each node in the second energy node topology network, and obtaining power output data and power input data of each node; performing input and output load analysis on each node based on the power output data and power input data, and obtaining an input and output load index; if the input and output load index is greater than a preset input and output load index, updating the complementary path identifiers of the second energy node topology network based on the preset input and output load index, and outputting a third energy node topology network.

[0010] Optionally, the method for coordinated control of a multi-energy power system at spatiotemporal scales also includes: performing anomaly detection on the energy real-time data set according to the anomaly detection module, and returning an anomaly detection result; if the anomaly detection result returned is empty, the multi-energy power system performs power coordinated control according to the second energy node topology network; if the anomaly detection result returned is not empty, the multi-energy power system performs real-time update of the second energy node topology network according to the anomaly detection result.

[0011] Optionally, the method for coordinated control of time and space scales of a multi-energy power system also includes: obtaining a power load indicator of the target area according to the multi-energy power system; judging the power state of the target area according to the power load indicator, and if the power state of the target area is in a peak power state, adjusting the preset timing scale to a short term; if the power state of the target area is in a mid-peak power state, adjusting the preset timing scale to a medium term; if the power state of the target area is in a low-peak power state, adjusting the preset timing scale to a long term.

[0012] Optionally, the method for coordinated control of a multi-energy power system at spatiotemporal scales also includes: the second energy node topology network includes the energy type of each node, the transmission path between nodes, and control parameters, wherein the transmission path includes a transmission direction.

[0013] The technical solution provided in this application has at least the following technical effects or advantages:

[0014] By identifying the first energy node topology network of the multi-energy power system, the first energy node topology network is obtained based on the spatial position of the energy nodes in the target area; the first energy node topology network is monitored in real time to obtain an energy real-time data set; training is performed based on the energy historical data set to build a multi-energy joint distribution model; a preset time series scale is obtained, the energy real-time data set and the preset time series scale are input into the energy joint distribution model, and the complementary probability between each energy source based on the preset time series scale is output, and a complementary probability set is output; the first energy node topology network is identified with complementary paths according to the size of the complementary probability set, and a second energy node topology network with complementary path identification is output, wherein the complementary path is a path composed of energy type pairs with a complementary probability greater than the preset complementary probability; the multi-energy power system performs power coordination control according to the second energy node topology network; the correlation, complementarity and fluctuation characteristics of multiple energy types in the time and space scale can be effectively quantified, thereby realizing scientific and flexible multi-energy coordinated scheduling, significantly improving the utilization rate of renewable energy, reducing power system fluctuations, and ensuring efficient and stable operation of the power system.

[0015] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0017] Figure 1 A schematic flow chart of a method for coordinated control of time and space scales of a multi-energy power system for this application;

[0018] Figure 2 A schematic diagram of the process of constructing a multi-energy joint distribution model in a multi-energy power system spatiotemporal scale coordinated control method of the present application. DETAILED DESCRIPTION

[0019] This application provides a method for coordinated control of multi-energy power systems at spatiotemporal scales, which solves the technical problem that in traditional multi-energy power dispatching methods, efficient energy coordinated dispatching cannot be achieved due to the inability to accurately quantify the complementary characteristics of multiple energy sources at spatiotemporal scales. The correlation, complementarity and fluctuation characteristics of multiple energy types at spatiotemporal scales can be effectively quantified, thereby achieving scientific and flexible coordinated dispatching of multiple energy sources, significantly improving the utilization rate of renewable energy, reducing power system fluctuations, and ensuring efficient and stable operation of the power system.

[0020] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0021] For examples, please see the attached Figure 1 The present application provides a method for coordinated control of time and space scales of a multi-energy power system, which specifically includes the following steps:

[0022] S100: Identify a first energy node topology network of a multi-energy power system, where the first energy node topology network is obtained based on spatial locations of energy nodes in a target area.

[0023] Specifically, first, determine the various energy types of the multi-energy power system in the target area, such as renewable energy (such as wind power, solar energy), traditional energy (such as thermal power, nuclear power), energy storage facilities, load nodes, etc.; then, according to the geographical location of the energy types in the target area (such as wind farms, photovoltaic power stations, thermal power plants, energy storage systems, etc.), obtain the spatial coordinates of these energy nodes, and the location data of the nodes can be obtained through the geographic information system (GIS). Then, based on the geographical location and power grid structure, establish the connection relationship between energy nodes, connect each node through the power grid topology map, and construct the first energy node topology network, such as using the power system modeling tool to visualize the energy nodes and their connection relationships, and generate a topology map, in which each node includes a node ID (unique identifier of the node), a node type (such as wind power, photovoltaic, thermal power, energy storage, etc.) and a node location (specific coordinates of the node); in the topological network, the connection between nodes is usually carried out through power transmission lines or power grids, and these connection relationships are identified to form "edges" in the network, that is, the transmission path of power flow.

[0024] Then, the first energy node topology network is identified, and the structure of the topology network is further improved and optimized by deeply analyzing the connection relationship between nodes, energy flow and other characteristics.

[0025] S200: Perform real-time monitoring on the first energy node topology network to obtain a real-time energy data set.

[0026] Specifically, in order to achieve efficient multi-energy power dispatching and coordinated control, it is necessary to monitor the first energy node topology network in real time and obtain the real-time data of each energy node in time. First, through the sensors deployed at the key positions of energy nodes and power grids, the first energy node topology network is monitored in real time to obtain the energy real-time data set, wherein the energy real-time data set includes energy node power generation / load data, environmental data and energy storage equipment data, etc. Energy node power generation / load data refers to the real-time power generation power (such as wind power, photovoltaic, thermal power, etc.) or power consumption power (such as load node) of each energy node; environmental data refers to the environmental parameters for renewable energy nodes, such as wind speed data, solar radiation intensity, temperature, humidity and other meteorological data; energy storage equipment data refers to the charge and discharge status of energy storage equipment, battery voltage, remaining power, charge and discharge efficiency, etc. By obtaining the energy real-time data set, accurate data support is provided for the subsequent multi-energy coordinated dispatching analysis.

[0027] S300: Train based on energy historical data sets to build a multi-energy joint distribution model.

[0028] Further, if Figure 2 As shown, step S300 of the present application also includes:

[0029] S310: Acquire multiple time-scale samples, where the multiple time-scale samples include short-term, medium-term, and long-term. S320: Perform feature convolution on the energy history data set according to the multiple time-scale samples, and output an energy feature data set corresponding to each time-scale sample.

[0030] Specifically, first, query the power system operation log to obtain the energy history data set, where the energy history data includes energy type data, meteorological data, time range (short-term data, medium-term data, long-term data), etc.; then, obtain multiple time series scale samples, where the multiple time series scale samples include short-term, medium-term, and long-term. The short-term time series scale refers to the time range from a few minutes to a few hours (such as 1 minute to 24 hours). During this period, the load demand of the energy system and the generation of renewable energy (such as wind power and solar energy) fluctuate more obviously, but relatively short, and there will be no large-scale systemic changes; the medium-term time series scale usually refers to the time range of a few days to a few weeks (such as 1 day to 1 month). During this period, the load demand of the energy system fluctuates greatly, and at the same time, the impact of climate and seasonal factors on renewable energy gradually increases; the long-term time series scale usually refers to the time range of several months to several years (such as 1 month to 1 year). During this period, the dispatching and regulation capabilities of the energy system are mainly determined by large-scale power grid infrastructure, energy configuration and energy storage capacity, and climate change and long-term load trends are important factors affecting system operation.

[0031] Then, the energy historical data set is convolved according to the multiple time series scale samples. The process of feature convolution is to extract useful feature information from the historical data set through convolutional neural network (CNN) or convolution operation to realize the spatiotemporal scale analysis of the energy system. In the dispatch of multi-energy power system, energy data at different time scales (short-term, medium-term, and long-term) have different characteristics. By performing feature convolution on these data, we can extract valuable features, and then provide a basis for the coordinated dispatch of the power system. That is, the energy historical data set is convolved according to the multiple time series scale samples. The goal of the convolution operation is to extract local features (such as periodic changes, trends, volatility, etc.) from the historical data for subsequent analysis and dispatch. The convolution operation includes short-term convolution operation, medium-term convolution operation and long-term convolution operation. Short-term convolution operation refers to convolution of short-term time series data (such as power output and load changes per minute and hour) to capture instantaneous fluctuations; medium-term convolution operation refers to convolution of medium-term time series data (such as daily and weekly power generation data and load data) to identify periodic changes and trends; long-term convolution The operation refers to convolving long-term time series data (such as monthly and annual loads, power generation, etc.) to extract features such as long-term trends and seasonal changes; obtaining the energy characteristic data set corresponding to each time series scale sample, including short-term energy characteristic data sets (characteristics of energy fluctuations in the short term, such as load fluctuations, instantaneous fluctuations of wind power and photovoltaic power generation, etc.), medium-term energy characteristic data sets (periodic fluctuation characteristics in the medium term, such as daily load demand changes, seasonal fluctuations of photovoltaic and wind power, etc.) and long-term energy characteristic data sets (including long-term trend characteristics, such as the impact of climate change on renewable energy power generation, annual load growth trends, etc.).

[0032] S330: Using the energy feature data set corresponding to each time series scale sample, construct a multi-energy joint distribution sub-model corresponding to each time series scale sample.

[0033] Furthermore, step S330 of the present application also includes:

[0034] S331: Using the energy feature data set corresponding to each time series scale sample, construct the marginal distribution of each energy source and output multiple marginal distributions; S332: Identify the correlation between each energy source and obtain the correlation identification result; S333: Connect the multiple marginal distributions according to the correlation identification result and output a multi-energy joint distribution sub-model, wherein the model parameters of the multi-energy joint distribution sub-model are obtained by gradient descent optimization.

[0035] Specifically, first, the marginal distribution of each energy source is constructed based on the energy characteristic data set corresponding to each time series scale sample, that is, the marginal probability distribution of each energy source is calculated based on the short-term, medium-term and long-term time series data. The marginal distribution of each energy source is a probability distribution that describes the fluctuation characteristics and change laws of the energy source at different time scales. The goal is to identify the characteristics of energy through statistical methods, and then provide a reliable basis for the coordinated scheduling of multi-energy power systems. For example, marginal probability calculation can be performed through histograms, kernel density estimation, autoregressive models, etc. For example, the data can be divided into several intervals through histograms, the frequency in each interval is calculated, and then its probability density is estimated; multiple marginal distributions are output.

[0036] Next, the correlation between each energy source is identified. The correlation coefficient between different energy sources can be calculated to measure the correlation. For example, the Pearson correlation coefficient can be used to measure the strength of the linear correlation between two variables. In addition to quantifying the correlation through the correlation coefficient, cluster analysis or graph theory methods can also be used to identify the correlation pattern between energy sources. For example, cluster analysis can be used to divide energy sources into different groups based on their correlation to obtain correlation identification results.

[0037] Further, the multiple marginal distributions are connected according to the correlation identification results to construct a multi-energy joint distribution sub-model, wherein the joint distribution describes the probability of co-occurrence of multiple random variables (energy types). In a multi-energy power system, the joint distribution represents the common fluctuation characteristics and mutual influence of different energy types on different time scales. The marginal distribution of each energy is connected, and the synergistic effect between different energy sources is represented by the joint distribution; the marginal distribution of each energy is combined with the correlation between energies through a probability model (such as Gaussian distribution, mixed Gaussian model, etc.) to construct a multi-dimensional joint probability distribution, and the model parameters are adjusted through optimization methods such as gradient descent so that the model can Better fit historical data, accurately reflect the correlation and time series change law between energy sources, among which gradient descent is a common optimization method, which is used to update model parameters through back propagation to minimize the error or loss function. In the multi-energy joint distribution model, gradient descent can be used to minimize the prediction error of the model, so that the model can more accurately reflect the spatiotemporal correlation between energy sources. For example, according to the preliminary estimate of the marginal distribution, the parameters of the multi-energy joint distribution model are initialized; then the training data set (such as historical load data, power generation data, etc.) is used to continuously optimize the parameters through the gradient descent algorithm until convergence, and through continuous iteration, the optimized multi-energy joint distribution sub-model is finally obtained. Through the above steps, the multi-energy joint distribution sub-model finally output is an efficient probabilistic model, which can reflect the spatiotemporal correlation between different energy types and their joint distribution characteristics at different time scales. It can not only quantify the relationship between different energy sources, but also perform efficient energy scheduling optimization according to the needs of different time scales, and provide support for the stability, economy and maximum utilization of renewable energy of multi-energy power systems.

[0038] S340: Integrate the multi-energy joint distribution sub-models corresponding to each time series scale sample to construct a multi-energy joint distribution model.

[0039] Specifically, through the above training steps, multiple joint distribution sub-models corresponding to multiple time-scale samples are obtained, wherein each time-scale sub-model captures the energy fluctuation characteristics at different scales by modeling energy data at different time scales; then the multi-energy joint distribution sub-models corresponding to each time-scale sample are integrated, for example, for each time-scale sub-model, appropriate weights are assigned based on its contribution to the power system dispatch. Generally speaking, the short-term sub-model is used for immediate dispatch decisions, the medium-term sub-model is used for daily operations, and the long-term sub-model is used for seasonal dispatch and resource planning; finally, a global multi-energy joint distribution model is constructed. By integrating multi-energy joint distribution sub-models at different time scales, the energy fluctuation characteristics and their interrelationships can be accurately captured, thereby providing a more accurate dispatch decision basis for the power system.

[0040] S400: Acquire a preset time series scale, input the energy real-time data set and the preset time series scale into the energy joint distribution model, output the complementary probability between each energy source based on the preset time series scale, and output a complementary probability set.

[0041] Specifically, first, a preset time series scale is obtained, wherein the preset time series scale includes a short-term scale, a medium-term scale, or a long-term scale, which is set according to the regional power state; then, the energy real-time data set and the preset time series scale are input into the energy joint distribution model for analysis, and the complementary probability between each energy source based on the preset time series scale is output, wherein the complementary probability refers to the probability that the power generation or power supply capacity of two or more energy sources complement each other at a certain time series scale. For example, when the wind power is insufficient, solar energy may provide a supplement; when the wind power is sufficient, thermal power generation may need to be adjusted to maintain system stability; in the joint distribution model, the complementary probability is calculated by considering the marginal distribution of each energy source and the correlation between them, such as calculating the joint occurrence probability between multiple energy sources through the joint distribution function, thereby obtaining the complementary relationship between them, and obtaining a complementary probability set, which is a data structure containing the complementary information between each energy source, indicating the complementary probability between each pair of energy sources, for example, in the short-term time series scale, the complementary probability of wind energy and photovoltaic energy is 0.8, indicating that the two energy sources have an 80% probability of complementing each other in the short term. There may be different probability values ​​for medium-term and long-term time scales, because the fluctuation characteristics and complementary relationships of energy sources may change at different time scales.

[0042] Further, to obtain a preset time series scale, step S400 of the present application further includes:

[0043] S410: According to the multi-energy power system, the power load index of the target area is obtained; S420: The power state of the target area is determined according to the power load index. If the power state of the target area is in a peak power state, the preset timing scale is adjusted to a short term; S430: If the power state of the target area is in a mid-peak power state, the preset timing scale is adjusted to a medium term; S440: If the power state of the target area is in a low-peak power state, the preset timing scale is adjusted to a long term.

[0044] Specifically, first, according to the multi-energy power system, the power load indicators of the target area are obtained, wherein the power load indicators include load demand, power supply capacity, power fluctuation, etc.; load demand refers to the power consumption demand of the target area at a certain moment or time period (such as the total electricity consumption per unit time); power supply capacity refers to the power supply capacity in the target area, including the power generation from various energy sources (such as wind power, solar energy, thermal power generation, etc.); power fluctuation refers to the fluctuation range of the power system within a certain time period, reflecting the stability and load balance of the system; these power load indicators can be obtained through real-time monitoring equipment, smart meters or prediction models to help the power system evaluate the current power status.

[0045] Next, the power state of the target area is judged according to the power load index, wherein the power state includes a peak power state, a mid-peak power state and a low-peak power state. The peak power state means that when the load demand is close to or exceeds the supply capacity of the power system, the system is in a peak power state. At this time, it may be necessary to strengthen the response capability of the system and balance the load by dispatching efficient and stable energy; the mid-peak power state means that when the power load is close to the medium supply capacity of the system, it is a mid-peak power state. At this time, the load of the power system is relatively balanced, and a medium-term dispatching strategy can be adopted to cope with power fluctuations; the low-peak power state means that when the power demand is lower than the system supply capacity and the system is in a relatively stable state, it is a low-peak power state. At this time, the system load can be easily coped with, and resource allocation can usually be optimized through long-term dispatching strategies.

[0046] Then, the preset time scale is adjusted according to the power state of the power system to make energy scheduling more flexible and efficient. If the power state of the target area is in the peak power state, the preset time scale is adjusted to the short term. The short-term time scale can quickly respond to energy fluctuations and adjust energy output in real time to ensure that the system meets demand in a short time; if the power state of the target area is in the mid-peak power state, the preset time scale is adjusted to the medium term. The medium-term time scale is used to optimize energy utilization and scheduling efficiency within a certain time range and balance the power generation of different energy sources; if the power state of the target area is in the low-peak power state, the preset time scale is adjusted to the long term. The long-term time scale helps to plan and optimize the configuration of energy resources, reduce unnecessary energy waste, and make long-term load adjustment and planning in advance. By dynamically adjusting the preset time scale according to the power load index, it can be ensured that various types of energy can be flexibly dispatched under different power demand and supply conditions to improve the overall energy utilization and reduce operation risks.

[0047] Furthermore, step S400 of the present application also includes:

[0048] S450: Output the complementary probability between the energy sources based on the preset time series scale, wherein the calculation formula of the complementary probability is: ;in, Based on the energy under the preset time series scale and energy The complementary probability between To preset the time scale, For energy and energy The joint marginal distribution of a and b are energy The upper and lower limits of the power index, c and d are energy The upper limit and lower limit of power indicators.

[0049] Specifically, the calculation formula of the complementary probability is used to quantify the complementarity of different energy types at a specific time scale. If the complementary probability is close to 1, it means that at this time scale, the two energy types have strong complementarity, that is, they can complement each other and provide a stable power supply; if the complementary probability is close to 0, it means that the complementarity between the two energy types is poor, and their power generation capabilities cannot be effectively coordinated. It may be necessary to introduce more scheduling methods or backup energy sources to ensure a stable power supply.

[0050] S500: Perform complementary path identification on the first energy node topology network according to the size of the complementary probability set, and output a second energy node topology network with complementary path identification, wherein the complementary path is a path composed of energy type pairs with a complementary probability greater than a preset probability.

[0051] Specifically, first, a complementary path is defined, and the complementary path refers to the complementary probability between two energy nodes in the energy node topology network is greater than the preset complementary probability, and the connection path between these energy nodes can work effectively together (such as one-to-one or one-to-many), that is, at a specific time scale, they can jointly meet the power demand and complement each other; the preset complementary probability can be set according to the power system operation scenario, such as setting the preset complementary probability to 0.8. Then, the complementary path of the first energy node topology network is identified according to the size of the complementary probability set, that is, the path composed of energy type pairs that can work together with a probability greater than the preset complementary probability is identified as a complementary path, and the second energy node topology network with a complementary path identification is output.

[0052] Furthermore, step S500 of the present application also includes:

[0053] S510: The second energy node topology network includes the energy type of each node, the transmission path between nodes, and control parameters, wherein the transmission path includes a transmission direction.

[0054] Specifically, the second energy node topology network includes the energy type of each node (such as solar energy, wind energy, thermal power generation, hydropower generation, etc.); in the second energy node topology network, the connection between nodes is represented by a transmission path, which describes the power flow relationship between different nodes. The transmission path includes a transmission direction. For example, a transmission path means that the energy nodes at both ends of the path can transmit power to each other. For two complementary energy nodes, if one energy type has insufficient output, the other energy type can supplement the power to ensure that the load demand is met; the transmission direction refers to the direction of power flow between energy nodes. The transmission direction is crucial to the scheduling and control system because it determines the direction of power flow and how each node responds to changes in system demand.

[0055] At the same time, the second energy node topology network also includes control parameters between nodes, which are used to optimize the operation and dispatch of the power system, including power limit, transmission efficiency, energy storage strategy, etc. By identifying complementary paths according to complementary probability and combining the energy type, transmission path and control parameters of each node, a flexible and efficient power dispatch network is constructed, which provides technical support for the realization of intelligent and coordinated dispatch of energy and ensures the efficient and stable operation of the power system.

[0056] Further, after outputting the second energy node topology network with complementary path identifiers, step S500 of the present application further includes:

[0057] S520: Identify the number of path identifiers of each node in the second energy node topology network, and obtain the power output data and power input data of each node; S530: Perform input and output load analysis on each node based on the power output data and power input data, and obtain the input and output load index; S540: If the input and output load index is greater than the preset input and output load index, update the complementary path identifier of the second energy node topology network based on the preset input and output load index, and output the third energy node topology network.

[0058] Specifically, after outputting a second energy node topology network with complementary path identifiers, the number of path identifiers of each node in the second energy node topology network is identified. First, the number of path identifiers of each node in the second energy node topology network is identified. The path identifier refers to the power transmission path between each node and other nodes. The number of path identifiers indicates the number of paths through which the node, as an energy source point or load node, can transmit power to other nodes. The number of path identifiers reflects the diversity and flexibility of power transmission between nodes. The larger the number, the more complex the interconnection relationship between the nodes, and the more options for power flow. Further, for each node, its power output data and power input data are obtained. The power output data refers to the power output from the node to other nodes; the power input data refers to the power input from the node from other nodes. These data reflect the power flow between nodes. The output data indicates the power supply capacity of the node within a specific time, while the input data indicates the power demand of the node.

[0059] Next, an input and output load analysis is performed on each node based on the power output data and the power input data, that is, the dynamic balance between the power supply and demand of each node is analyzed, and the input and output load index is calculated. For example, the input and output load index is set to the ratio of power input to power output. This index helps to determine the role of the node in power supply and demand. According to the preset input and output load indicators, the load status of each node is judged. If the input and output load indicators are greater than the preset input and output load indicators, it means that the node load is too high or there is a shortage of power supply. It may be necessary to adjust the power scheduling or strengthen the complementarity with other nodes to balance the load. At this time, the complementary path identifier of the second energy node topology network is updated according to the preset input and output load indicators. That is, for nodes with heavy loads, the system may need to add more complementary paths to obtain power from other energy nodes, or transmit excess power to other nodes, such as increasing the path for power to flow to nodes with excessive loads, or enhancing the power transmission capacity between nodes; adjusting the transmission direction or power of the power flow path to ensure the supply and demand balance of the system, etc. After the complementary path identifier is updated, an updated third energy node topology network is obtained. This topology network reflects the connection paths and complementary relationships between nodes under the new load state.

[0060] S600: The multi-energy power system performs power coordination control according to the second energy node topology network.

[0061] Specifically, the multi-energy power system performs power coordination control according to the second energy node topology network, that is, by identifying the input and output loads, complementary paths and power transmission status of each node in the second energy node topology network, a power coordination control strategy is generated to perform power coordination control. For example, through accurate load analysis, the power demand and supply of each node in the system are balanced to avoid insufficient or excessive power supply; according to the real-time energy status and the complementarity between nodes, the system dynamically adjusts the proportion of energy use to ensure that various types of energy are maximized. Through effective power coordination control, efficient collaboration between different energy sources in the system is ensured, thereby achieving global load balance, maximum energy utilization and stable system operation.

[0062] Furthermore, step S600 of the present application also includes:

[0063] S610: Perform anomaly detection on the energy real-time data set according to the anomaly detection module and return the anomaly detection result. If the anomaly detection result returned is empty, the multi-energy power system performs power coordination control according to the second energy node topology network; S620: If the anomaly detection result returned is not empty, the multi-energy power system updates the second energy node topology network in real time according to the anomaly detection result.

[0064] Specifically, in a multi-energy power system, in order to ensure the efficiency of power coordinated control and system stability, the system must be monitored in real time and anomaly detected. This function is implemented by the anomaly detection module, which is used to identify problems that may affect the stable operation of the system. The role of the anomaly detection module is to monitor and analyze real-time data and promptly detect abnormal conditions in the power system (such as equipment failure, load abnormality, imbalance between power supply and demand, etc.). When an anomaly is detected, the system needs to process it and update the power coordinated control strategy in real time based on the detection results.

[0065] Among them, the multi-energy power system also includes an anomaly detection module; first, the energy real-time data set is detected for anomalies according to the anomaly detection module, such as equipment failure, load anomaly, imbalance of power supply and demand, etc., to obtain an anomaly detection result; if the anomaly detection result is returned as null, it indicates that no anomaly is detected, and the power system can continue to perform power coordination control according to the current strategy. At this time, the multi-energy power system performs power coordination control according to the second energy node topology network. If the anomaly detection result is not returned as null, it indicates that an anomaly or potential risk (such as equipment failure, imbalance of supply and demand, abnormal power flow, etc.) is detected, then the system needs to be adjusted; at this time, the multi-energy power system updates the second energy node topology network in real time according to the anomaly detection result, that is, when an anomaly occurs, the system can respond in time, and restore the normal operation of the system by adjusting the control strategy and optimizing power dispatching, so as to minimize the impact of the anomaly on the power system. For example, if a node fails, the system will reconfigure the power flow to bypass the failed node to ensure that the power supply of other nodes is not affected.

[0066] By introducing anomaly detection modules and real-time update mechanisms, the multi-energy power system can effectively respond to emergencies or system anomalies and ensure the efficient operation and stability of the power system. In the absence of anomalies, the system continues to coordinate power control as planned to ensure load balance and maximize energy utilization; when anomalies are detected, the system will quickly identify the type of anomaly and perform real-time updates to avoid power supply interruptions or imbalances, thereby improving the robustness and response speed of the entire power system.

[0067] In summary, the multi-energy power system spatiotemporal scale coordinated control method provided by the present application has the following technical effects:

[0068] By identifying the first energy node topology network of the multi-energy power system, the first energy node topology network is obtained based on the spatial position of the energy nodes in the target area; the first energy node topology network is monitored in real time to obtain an energy real-time data set; training is performed based on the energy historical data set to build a multi-energy joint distribution model; a preset time series scale is obtained, the energy real-time data set and the preset time series scale are input into the energy joint distribution model, and the complementary probability between each energy source based on the preset time series scale is output, and a complementary probability set is output; the first energy node topology network is identified with complementary paths according to the size of the complementary probability set, and a second energy node topology network with complementary path identification is output, wherein the complementary path is a path composed of energy type pairs with a complementary probability greater than the preset complementary probability; the multi-energy power system performs power coordination control according to the second energy node topology network; the correlation, complementarity and fluctuation characteristics of multiple energy types in the time and space scale can be effectively quantified, thereby realizing scientific and flexible multi-energy coordinated scheduling, significantly improving the utilization rate of renewable energy, reducing power system fluctuations, and ensuring efficient and stable operation of the power system.

[0069] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0070] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. A method for coordinated control of multi-energy power systems in time and space, characterized in that: Methods include: Identifying a first energy node topology network of a multi-energy power system, wherein the first energy node topology network is obtained based on spatial locations of energy nodes within a target area; Performing real-time monitoring on the first energy node topology network to obtain a real-time energy data set; Train based on historical energy data sets to build a multi-energy joint distribution model; Obtaining a preset time series scale, inputting the energy real-time data set and the preset time series scale into the energy joint distribution model, outputting the complementary probability between the energy sources based on the preset time series scale, and outputting a complementary probability set; According to the size of the complementary probability set, complementary paths are identified for the first energy node topology network, and a second energy node topology network having complementary path identifications is output, wherein the complementary paths are paths composed of energy type pairs with a complementary probability greater than a preset value; The multi-energy power system performs power coordination control according to the second energy node topology network.

2. A method for coordinated control of multi-energy power systems in time and space as claimed in claim 1, characterized in that: Training is performed based on energy historical data sets to construct a multi-energy joint distribution model. The method also includes: Acquire multiple time-scale samples, where the multiple time-scale samples include short-term, medium-term, and long-term; Performing feature convolution on the energy history data set according to the multiple time series scale samples, and outputting an energy feature data set corresponding to each time series scale sample; Based on the energy characteristic data set corresponding to each time series scale sample, a multi-energy joint distribution sub-model corresponding to each time series scale sample is constructed; The multi-energy joint distribution sub-models corresponding to each time series scale sample are integrated to construct a multi-energy joint distribution model.

3. A method for coordinated control of multi-energy power systems in time and space as claimed in claim 2, characterized in that: Construct a multi-energy joint distribution sub-model corresponding to each time series scale sample, the method includes: Based on the energy feature dataset corresponding to each time series scale sample, the marginal distribution of each energy source is constructed and multiple marginal distributions are output; Identify the correlation between each energy source and obtain the correlation identification result; The multiple edge distributions are connected according to the correlation identification result, and a multi-energy joint distribution sub-model is output, wherein the model parameters of the multi-energy joint distribution sub-model are obtained through gradient descent optimization.

4. A method for coordinated control of multi-energy power systems in time and space as claimed in claim 1, characterized in that: The complementary probability between the energy sources under the preset time series scale is output, wherein the calculation formula of the complementary probability is: ； in, Based on the energy under the preset time series scale and energy The complementary probability between To preset the time scale, For energy and energy The joint marginal distribution of a and b are energy The upper and lower limits of the power index, c and d are energy The upper limit and lower limit of power indicators.

5. A method for coordinated control of multi-energy power systems in time and space as claimed in claim 1, characterized in that: After outputting the second energy node topology network having the complementary path identifier, the method further includes: Identify the number of path identifiers of each node in the second energy node topology network, and obtain power output data and power input data of each node; Performing input and output load analysis on each node according to the power output data and the power input data to obtain an input and output load index; If the input / output load indicator is greater than a preset input / output load indicator, the complementary path identifier of the second energy node topology network is updated based on the preset input / output load indicator, and a third energy node topology network is output.

6. A method for coordinated control of multi-energy power systems in time and space as claimed in claim 1, characterized in that: The multi-energy power system further includes an abnormality detection module, and the method includes: Perform anomaly detection on the energy real-time data set according to the anomaly detection module, and return an anomaly detection result. If the anomaly detection result returned is empty, the multi-energy power system performs power coordination control according to the second energy node topology network; If the abnormality detection result returned is not empty, the multi-energy power system updates the second energy node topology network in real time according to the abnormality detection result.

7. A method for coordinated control of multi-energy power systems in time and space as claimed in claim 1, characterized in that: Obtaining a preset time series scale, the method further includes: According to the multi-energy power system, obtaining a power load index of the target area; Determine the power state of the target area according to the power load indicator, and if the power state of the target area is at a peak power state, adjust the preset time scale to a short term; If the power state of the target area is in the peak power state, adjusting the preset time scale to the medium term; If the power state of the target area is in a low-peak power state, the preset time scale is adjusted to a long term.

8. A method for coordinated control of multi-energy power systems in time and space as claimed in claim 1, characterized in that: The second energy node topology network includes the energy type of each node, the transmission path between nodes and control parameters, wherein the transmission path includes the transmission direction.

Images