Method for complementary allocation of water-light resources predicted by meteorological big data

Abstract

The present invention discloses a complementary allocation method for water-light resources in meteorological big data prediction, which relates to the technical field of energy management. The method includes: obtaining water-light resource nodes participating in allocation, determining the resource access topology, performing short-term and long-term water-light resource prediction, and determining the predicted resource configuration; introducing moment information fuzzy sets to quantify the expected curtailment of light and water penalties under the worst uncertain scenarios, and constructing a complementary allocation unit based on the third-order complementary condition; receiving the power grid consumption demand and importing it into the complementary allocation unit, determining whether to trigger the third-order inter-domain complementary decision based on the resource balance state, and determining the resource allocation strategy. The present invention solves the technical problems existing in the prior art, such as inaccurate decision-making for water-light resource allocation, low resource utilization rate, and unstable power grid consumption, and achieves the technical effects of realizing accurate allocation decision-making for water-light resources, improving the utilization rate of water-light resources, and ensuring stable power grid consumption.

Description

Technical Field

[0001] The present invention relates to the technical field of energy management, and particularly to a complementary dispatching method for water-light resources based on meteorological big data prediction. Background Art

[0002] With the continuous increase in the global demand for clean energy, the proportion of renewable energy such as water and light in the power supply system is increasing day by day. However, the current dispatching of water-light resources faces many challenges. On the one hand, water-light resources have strong randomness and volatility. The light intensity and water resource volume are greatly affected by natural factors such as weather and seasons, resulting in unstable power generation and difficult to accurately predict the power generation power and electricity. On the other hand, the existing dispatching methods lack comprehensive consideration of various factors, often only focusing on a single index and ignoring other important factors such as resource cost, environmental impact, and grid load balance, making the dispatching decision not scientific and reasonable, resulting in a large amount of light abandonment and water abandonment, and low energy utilization rate. At the same time, when the power grid accepts water-light power, due to unreasonable dispatching, there are often situations of overload in local areas or insufficient power supply, seriously affecting the stable operation of the power grid.

[0003] The existing technology has technical problems such as inaccurate dispatching decisions for water-light resources, low resource utilization rate, and unstable grid accommodation. Summary of the Invention

[0004] The present application provides a complementary dispatching method for water-light resources based on meteorological big data prediction, which is used to solve the technical problems of inaccurate dispatching decisions for water-light resources, low resource utilization rate, and unstable grid accommodation in the existing technology.

[0005] In view of the above problems, the present application provides a complementary dispatching method for water-light resources based on meteorological big data prediction, and the method includes:

[0006] Obtain the water-light resource nodes participating in the dispatching, determine the resource access topology, connect the resource prediction module and perform long-term and short-term water-light resource prediction, determine the predicted resource configuration, where meteorology is the resource prediction orientation; introduce the moment information fuzzy set, quantify the expected penalty of light abandonment and water abandonment under the worst uncertain scenario, and construct a complementary dispatching unit based on the third-order complementary condition, where the third-order complementary condition includes first-order master-slave complementarity, second-order relaxation degree, and third-order inter-domain complementarity; receive the grid accommodation demand and import it into the complementary dispatching unit, and make a decision for the predicted resource configuration based on the first-order master-slave complementarity and second-order relaxation degree in the same domain, and determine whether to trigger the third-order inter-domain complementarity decision based on the resource equilibrium state to determine the resource dispatching strategy; where the dispatching decision method is: make a dispatching decision under low-dimensional projection with the first dominant index, and verify the decision based on whether the second dominated index is satisfied.

[0007] One or more technical solutions provided in the present application have at least the following technical effects or advantages:

[0008] Obtain the water-light resource nodes participating in the allocation, determine the resource access topology, connect the resource prediction module and perform short-term and long-term water-light resource prediction, and determine the predicted resource configuration; introduce the moment information fuzzy set, quantify the expected curtailment of light and water penalties under the worst uncertain scenarios, and construct a complementary allocation unit based on the third-order complementary condition; receive the grid consumption demand and import it into the complementary allocation unit, and for the predicted resource configuration, determine whether to trigger the third-order inter-domain complementary decision and determine the resource allocation strategy; among them, the allocation decision method is: make the allocation decision under the low-dimensional projection with the first domination index, and make the verification decision based on whether the second dominated index is satisfied. It achieves the technical effect of realizing precise allocation decision of water-light resources, improving the utilization rate of water-light resources, and ensuring the stable consumption of the power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0010] Figure 1 It is a schematic flowchart of the complementary allocation method of water-light resources predicted by meteorological big data provided by the embodiments of the present application;

[0011] Figure 2 It is a schematic flowchart of the allocation decision method in the complementary allocation method of water-light resources predicted by meteorological big data provided by the embodiments of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0012] The present application provides a complementary allocation method of water-light resources predicted by meteorological big data, which is used to solve the technical problems of inaccurate allocation decision of water-light resources, low resource utilization rate, and unstable grid consumption existing in the prior art.

[0013] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0014] Embodiment, as Figure 1 shown, the present application provides a complementary allocation method of water-light resources predicted by meteorological big data, and the method includes:

[0015] Step S100: Obtain the water-light resource nodes participating in the allocation, determine the resource grid connection topology, connect the resource prediction module and conduct short-term and long-term water-light resource predictions, and determine the predicted resource configuration, where the meteorology is used as the resource prediction guidance.

[0016] Specifically, comprehensively sort out the water-light resource nodes participating in the allocation, conduct detailed investigations and data collection on all relevant hydropower stations and photovoltaic power stations in the region, covering key information such as their geographical locations, installed capacities, and power generation efficiencies. Based on this information, determine the resource grid connection topology, depict the layout architecture of each water-light resource node accessing the power grid, clarify the electrical connection relationships, power transmission paths, and signal interaction methods between the nodes, so as to clearly understand the flow direction and distribution of resources in the network. Connect the pre-constructed resource prediction module, which is trained relying on meteorological big data and maintains real-time interactive communication with the meteorological data center, collect meteorological information such as light intensity, sunshine duration, precipitation frequency, precipitation amount, and wind speed, and conduct short-term and long-term predictions on water-light resources. The short-term prediction focuses on the resource changes in the next few hours to several days, capturing the fluctuations caused by factors such as sudden weather changes and temporary equipment failures; the long-term prediction focuses on the trends in the next few weeks, months, or even years. Through short-term and long-term predictions, accurately determine the predicted resource configuration, and clarify the quantity and quality of the water-light resources that can be allocated in different time periods.

[0017] Step S200: Introduce the moment information fuzzy set, quantify the expected curtailment of light and water penalties under the worst uncertain scenario, and construct a complementary allocation unit based on the third-order complementary conditions, where the third-order complementary conditions include first-order master-slave complementarity, second-order relaxation degree, and third-order inter-domain complementarity.

[0018] Specifically, in the complementary allocation process of water and light resources in meteorological big data prediction, due to the strong uncertainty of light resources affected by various factors such as weather and season, in order to more effectively cope with this uncertainty, moment information fuzzy sets are introduced. Moment information fuzzy sets transform those uncertain factors that are difficult to accurately describe into a quantifiable form, greatly simplifying the analysis process for uncertain situations. Using this tool, the expected penalties for curtailment of light and curtailment of water under the worst uncertain scenarios are quantified. This means that the potential losses caused by the inability to fully utilize light and water resources in adverse situations such as sudden changes in light or water flow conditions due to extreme weather can be clarified. On this basis, a complementary allocation unit based on the third-order complementary condition is constructed. This third-order complementary condition is the core basis for allocation decisions and includes three key elements: first-order master-slave complementarity, based on the dominance relationship of allocation indicators, making dominance decisions on the allocation of water and light resources in the same region, and clarifying the primary and secondary cooperation relationship between hydropower and photovoltaic resources; second-order relaxation, making decisions under the dominated verification through the analysis of allocation indicators, determining the reasonable ratio of water-light resource complementarity in the same domain, ensuring that the allocation process not only meets the resource utilization requirements but also has a certain degree of flexibility; third-order inter-domain complementarity, conducting third-order progressive analysis on the basis of grid-connected sub-domains, considering the resource scheduling complementarity between different regions, while ensuring the allocation accuracy, simplifying the processing process, and improving the logic and orderliness of the allocation process. These three elements cooperate with each other to jointly construct a scientific and efficient complementary allocation unit, providing strong support for the determination of subsequent resource allocation strategies.

[0019] Step S300: Receive the grid accommodation demand and import it into the complementary allocation unit. For the predicted resource configuration, make decisions based on the first-order master-slave complementarity and second-order relaxation within the same domain, and determine whether to trigger the third-order inter-domain complementarity decision based on the resource equilibrium state, so as to determine the resource allocation strategy.

[0020] Specifically, first, the grid accommodation demand is received. This demand reflects the grid's acceptance capacity for water and light resources and the actual power demand during a specific period, serving as an important guiding direction for the allocation work. Subsequently, this demand is imported into the complementary allocation unit constructed in the early stage, which integrates key elements such as the quantitative analysis of uncertainty and the third-order complementary conditions. Decision-making is carried out for the previously determined predicted resource allocation, using the first-order master-slave complementarity and the second-order relaxation degree in the same domain as the decision basis. In the same region, the primary and secondary allocation relationships between hydropower and photovoltaic resources are determined based on the first-order master-slave complementarity, and the specific proportion of their complementarity is determined using the second-order relaxation degree. While ensuring the reasonable utilization of resources within the region, flexibility is also taken into account. Through such a decision, a preliminary allocation strategy is initially formed. The resource equilibrium state of this preliminary allocation strategy is determined, that is, to evaluate whether this strategy can achieve a balanced and efficient allocation state of water and light resources among regions. If the resource equilibrium state is satisfied, this preliminary allocation strategy is directly determined as the final resource allocation strategy; if not, it means that the optimal resource allocation cannot be achieved solely by the allocation within the same domain. At this time, the third-order inter-domain complementary decision is triggered, and the preliminary allocation strategy is optimized and adjusted through the resource scheduling complementarity between different regions, and finally a scientific and reasonable resource allocation strategy is determined to achieve the dual goals of the efficient utilization of water and light resources and the stable accommodation of the grid.

[0021] Step S400: Among them, the allocation decision-making method is: making an allocation decision under the low-dimensional projection with the first domination index, and making a verification decision based on whether the second dominated index is satisfied.

[0022] Specifically, first, extract key information from various allocation-related indicators, and determine the first dominant indicator and the second subordinate indicator through cluster analysis. The first dominant indicator is usually those factors that have the most significant impact on the allocation result, such as the cost-benefit of resources, the current energy supply capacity, etc. Based on these first dominant indicators, make allocation decisions in the mode of low-dimensional projection. In the complex resource allocation space, focus on the key factors, simplify the high-dimensional and multi-factor allocation problem, and thus quickly generate a preliminary allocation strategy, initially planning the general direction and scale of the allocation of water and light resources at each node. However, the preliminary decision made only based on the first dominant indicator is not comprehensive enough, so it is necessary to use the second subordinate indicator to verify the decision. The second subordinate indicator covers other important factors except the first dominant indicator, such as the stability of energy supply, the degree of environmental impact, the balance of meeting the needs of different regions, etc. Evaluate the feasibility and comprehensiveness of the preliminary allocation strategy by checking whether the preliminary allocation strategy meets the second subordinate indicator one by one. If the preliminary strategy meets the requirements of the second subordinate indicator, it means that this allocation strategy comprehensively considers various factors and can be used as the final resource allocation plan; if it does not meet, it is necessary to make targeted adjustments and optimizations to the preliminary strategy until it meets the second subordinate indicator, so as to ensure that the finally determined resource allocation strategy not only highlights the key points but also takes into account comprehensively, realizing the scientific, efficient and reasonable allocation of water and light resources.

[0023] In a possible implementation manner, step S100 further includes:

[0024] Step S110: The resource prediction module is constructed by driving training through meteorological big data, and the resource prediction module establishes interactive communication with the meteorological data center; wherein, the resource prediction module and the complementary allocation unit adopt the same programming language, and are cascaded and interactively deployed by introducing a network protocol, and the resource prediction module and the complementary allocation unit are embedded and integratedly deployed in the processor array of the resource center, and establish interactive communication with the water and light base stations of each resource node.

[0025] Specifically, the resource prediction module is constructed by means of big data-driven training with the help of the long short-term memory network (LSTM) algorithm in deep learning. Meteorological data is obtained from the meteorological data center, which contains multi-dimensional meteorological information such as light intensity, temperature, humidity, wind speed, precipitation, etc. These data show complex sequence characteristics over time and are used as the input of the LSTM model. Through multiple iterations of training, the model learns the long-term dependencies and short-term fluctuation rules in the data, so as to accurately predict the water-light resources. To ensure the timeliness and accuracy of resource prediction, the resource prediction module establishes an interactive communication mechanism with the meteorological data center. The meteorological data center continuously updates the meteorological data and transmits the latest data to the resource prediction module in real time. The resource prediction module conducts real-time water-light resource prediction based on the received latest meteorological data and feeds back the prediction results to the meteorological data center, providing a reference for the further analysis and application of meteorological data, and realizing the dynamic interaction and collaborative work between meteorological data and resource prediction.

[0026] In terms of interactive deployment, the resource prediction module and the complementary deployment unit are written in Python language and cascaded and interactively deployed using the TCP / IP network protocol. The TCP / IP protocol ensures the reliability and orderliness of data transmission between the two, enabling the resource data predicted by the prediction module to be stably transmitted to the complementary deployment unit, and the feedback data of the complementary deployment unit to be accurately returned. In terms of the deployment location, the resource prediction module and the complementary deployment unit are deployed to the processor array of the resource center through embedded technology. Taking the processor array with ARM architecture as an example, it is managed using the embedded Linux operating system to achieve efficient data processing and task scheduling. When communicating with each water-light resource node water-light base station, the Modbus TCP protocol is adopted. Each water-light base station serves as a slave station of Modbus TCP, and the resource center serves as the master station. The resource center can read the real-time operation data of each water-light base station, such as equipment status, real-time power generation, etc. through this protocol; at the same time, it can also send control commands to the base station, such as adjusting the power generation power, etc., to ensure that the entire system realizes efficient and intelligent resource allocation.

[0027] In a possible implementation manner, step S100 further includes:

[0028] Step S120: For each water-light resource node, determine the microgrid area for grid connection scheduling.

[0029] Step S130: Use the microgrid area to mark the resource grid connection topology in domains, where each topology domain is marked with the node grid connection location and the resource node code.

[0030] Specifically, for each water-light resource node, accurately determine the microgrid area to which its grid connection scheduling belongs. This process requires comprehensive consideration of multiple factors, such as geographical location, power grid structure, resource transmission distance, etc. For example, water-light resource nodes with adjacent geographical locations and closely connected power transmission lines can be divided into the same microgrid area, which can reduce transmission losses and improve the efficiency of resource allocation. At the same time, the power load characteristics and stability requirements of each microgrid area also need to be considered to ensure that each microgrid area can operate independently and stably and has a certain degree of autonomy.

[0031] After determining the microgrid areas to which each water-light resource node belongs, based on these microgrid areas, perform domain marking on the resource grid connection topology. The resource grid connection topology depicts the connection relationship and structural layout between each water-light resource node and the power grid. Through domain marking, the entire resource grid connection topology is divided according to microgrid areas, and each topology domain has a clear identifier, which includes the node grid connection position and the resource node code. The node grid connection position clarifies the specific position where each water-light resource node in the microgrid area accesses the power grid, which helps to quickly locate specific nodes during resource allocation and fault troubleshooting; the resource node code is the unique identifier of each water-light resource node, which facilitates precise management and data recording of each node. Through such domain marking, the entire resource grid connection topology becomes clearer and more orderly, providing a solid foundation for subsequent resource prediction, allocation decision-making, and other work.

[0032] In a possible implementation manner, as Figure 2 shown, step S400 further includes:

[0033] Step S410: Obtain a deployment index matrix, perform clustering based on index correlation, and determine multiple clustering clusters.

[0034] Step S420: Traverse the multiple clustering clusters, add the maximum influence index within the cluster to the first dominant index, add the remaining indexes within the cluster to the second dominated index, and perform mapping on the first dominant index and the second dominated index based on the same cluster belonging.

[0035] Specifically, comprehensively collect various types of data that affect the allocation of water and light resources. These data cover multiple dimensions such as resource characteristics, grid conditions, and environmental factors. For example, the power generation efficiency of water and light resources, cost input, the stability of local light and water flow, the load demand of the grid, line transmission losses, and regional environmental policies. Integrate these data to construct an allocation index matrix, which is presented in tabular form. Each row represents a data record, and each column corresponds to a specific allocation index. Use clustering algorithms, such as the K-Means clustering algorithm, to calculate the similarity measures (such as Euclidean distance or cosine similarity) between different indicators, and group those indicators with high similarity and strong relevance into the same category. During the clustering process, the algorithm continuously adjusts the classification until an optimal clustering effect is achieved, that is, the indicators in the same category have high similarity, and the indicators between different categories have obvious differences. Through such clustering operations, the originally chaotic and disorderly numerous indicators are clearly divided into multiple clustering clusters, laying a solid foundation for further screening dominant indicators and dominated indicators and optimizing the allocation decision-making in the follow-up, and helping to improve the accuracy and effectiveness of the allocation strategy.

[0036] Traverse these clustering clusters in sequence. For each clustering cluster, an importance evaluation will be carried out on the indicators included in it. Calculate the weights of each indicator in historical allocation decisions and the sensitivity analysis of the allocation results to determine the indicator that has the greatest impact on the allocation decision within the cluster. This maximum impact indicator will be selected and added to the first set of dominant indicators because it will play a leading role in the subsequent low-dimensional projection allocation decision-making, helping to quickly determine the general direction and key strategies of the allocation. The remaining indicators in the cluster except the maximum impact indicator are added to the second set of dominated indicators. Although these indicators individually have less influence on the allocation decision than the maximum impact indicator, they jointly reflect other important aspects in the allocation process, such as resource stability, environmental impact, and long-term benefits. Finally, based on the principle of belonging to the same cluster, a mapping is made between the first set of dominant indicators and the second set of dominated indicators. That is, a corresponding relationship is established: each indicator in the first set of dominant indicators can find a subset of the second set of dominated indicators that belongs to the same clustering cluster as it. This mapping relationship enables in the subsequent allocation decision-making process, when a preliminary decision is made based on the first set of dominant indicators, the decision is comprehensively verified and supplemented by the corresponding second set of dominated indicators, ensuring that the final allocation strategy takes into account both key factors and other important aspects, thus realizing scientific, reasonable, and comprehensive complementary allocation of water and light resources.

[0037] In a possible implementation manner, step S300 further includes:

[0038] Step S310: Initialize the allocation space of the complementary allocation unit with the grid consumption demand and the predicted resource configuration.

[0039] Step S320: Perform a low-dimensional projection on the deployment space according to the first dominant index to determine the projected deployment space.

[0040] Step S330: Make a decision under first-order master-slave complementarity and second-order relaxation for the projected deployment space to determine the preliminary deployment strategy.

[0041] Specifically, two important factors, namely the grid absorption demand and the predicted resource allocation, are taken into consideration. The grid absorption demand reflects the grid's acceptance capacity and power demand for water and light resources within a certain period, while the predicted resource allocation is the future supply situation of water and light resources obtained through the resource prediction module. By combining this information from both aspects, an initial deployment range, that is, the deployment space, is delimited for the complementary deployment unit. This deployment space clarifies the types, quantities, and possible deployment directions of available water and light resources on the premise of meeting the grid absorption demand, providing a basic framework for subsequent decision-making.

[0042] The first dominant index is a set of indices selected from numerous deployment indices that have the greatest impact on the deployment decision. The deployment space is a high-dimensional and complex space that encompasses various possibilities and constraints for the deployment of water and light resources. Due to its high dimension and complex factors, directly making a decision within this space would face huge computational amounts and complexities, making it difficult to efficiently obtain the optimal deployment plan. Therefore, a low-dimensional projection is performed on the deployment space according to the first dominant index. Low-dimensional projection is a dimensionality reduction method that maps the high-dimensional deployment space into a low-dimensional subspace composed of the first dominant index. During the projection process, each point in the deployment space is repositioned according to the values of the first dominant index, thereby forming a new low-dimensional space, that is, the projected deployment space. The projected deployment space simplifies the original deployment problem, making the deployment decision more intuitive and efficient. In this low-dimensional space, decision-makers can more clearly see the performance of different deployment plans on key indices, and then quickly determine a general deployment direction and range.

[0043] After determining the projection allocation space, make decisions by means of two key elements, namely first-order master-slave complementarity and second-order slackness, and then determine the preliminary allocation strategy. First-order master-slave complementarity focuses on the complementary relationship between water and light resources in the same domain. In a specific region, according to the energy characteristics of the region, the grid demand, and the real-time situation of water and light resources, determine which of the hydropower and photovoltaic resources is the main and which is the auxiliary. For example, if the light is sufficient but the water resources are relatively scarce at a certain time period, and the grid has a high requirement for power stability, then the photovoltaic resources will be the main for power generation allocation, and the hydropower resources will assist in regulation to maintain the stability of power supply. The second-order slackness stipulates the proportional range of the complementarity between water and light resources in the same domain. It provides flexibility for resource allocation and avoids overly rigid allocation ratios. By setting a reasonable slackness, on the premise of ensuring stable energy supply and meeting the grid connection and consumption requirements, the allocation ratio of water and light resources is allowed to fluctuate within a certain range. For example, it is stipulated that the allocation ratio of hydropower to photovoltaic in a certain region can float between 6:4 and 4:6, so that it can be flexibly adjusted according to the actual situation to make full use of different types of energy. Considering first-order master-slave complementarity and second-order slackness comprehensively, conduct a comprehensive trade-off and analysis in the projection allocation space. Select the most suitable solution for the current conditions from various possible allocation solutions to determine the preliminary allocation strategy. This preliminary allocation strategy initially plans the allocation of water and light resources in different regions and different time periods, such as the power generation shares and transmission directions of water and light resources in each region, to ensure that the final resource allocation strategy is both efficient and reasonable.

[0044] In a possible implementation manner, step S300 further includes:

[0045] Step S340: Identify the preliminary allocation strategy and make a one-by-one determination of the second dominated index.

[0046] Step S350: When the second dominated index is satisfied, perform the determination of the resource balance state.

[0047] Step S360: If the second dominated index is not satisfied, compensate the preliminary allocation strategy with the stable and effective state of the dominated index.

[0048] Specifically, first, it is necessary to elaborate on the specific content of the pre-allocation strategy, including key information such as the allocated quantity of water-light resources in each region, the allocation time nodes, and the transmission paths. Then, taking the second dominated index as the measurement standard, conduct a detailed review of the pre-allocation strategy. The second dominated index covers multiple factors such as resource stability, environmental impact, and energy transmission loss. For example, in terms of resource stability, it is necessary to determine whether the strategy can ensure the stable supply of water-light resources at different times; in terms of environmental impact, evaluate whether it meets the local ecological protection requirements; in terms of energy transmission loss, calculate whether the energy loss during power transmission is within a reasonable range. Strictly judge each of these indicators to determine the overall feasibility of the pre-allocation strategy.

[0049] When the pre-allocation strategy meets all the second dominated indicators, perform the resource balance state determination, which focuses on the allocation of resources in the entire allocation system. Check whether the supply and demand of water-light resources in different regions match, avoiding the phenomenon of resource surplus in some regions and shortage in others; at the same time, also consider the load balance of the power grid when accepting these resources to ensure the stable operation of the power grid. Through this determination, further verify the rationality of the pre-allocation strategy in the overall resource allocation.

[0050] If it is found that the pre-allocation strategy does not meet the second dominated indicators, make targeted compensation for the pre-allocation strategy according to the stable and effective state of the dominated indicators. The stable and effective state of the dominated indicators includes upward adjustment effective, downward adjustment effective, or both upward and downward adjustment effective. For example, if the resource stability index fails to meet the standard, it is necessary to increase the allocation ratio of stable resources; if the energy transmission loss is too large, reduce the resource transmission volume of some high-loss paths; if there are multiple problems, comprehensively use the methods of upward and downward adjustment. Through this compensation mechanism, optimize the pre-allocation strategy to make it more in line with the actual needs of the complementary allocation of water-light resources, improve resource utilization efficiency, and ensure the stable operation of the power grid.

[0051] In a possible implementation manner, step S330 further includes:

[0052] Step S331: The stable and effective state includes upward adjustment effective, downward adjustment effective, or both upward and downward adjustment effective.

[0053] Specifically, in the process of complementary allocation of water-light resources predicted by meteorological big data, when the pre-allocation strategy does not meet the second dominated indicators, it is necessary to make compensation for it according to the stable and effective state of the dominated indicators, and the stable and effective state includes three situations: upward adjustment effective, downward adjustment effective, or both upward and downward adjustment effective.

[0054] Upward adjustment being effective means that when adjusting the pre-allocation strategy, appropriately increasing the allocation amount or allocation intensity of certain resources. For example, if it is found in the evaluation that the power supply stability index in a certain area does not meet the requirements of the second dominated index, and this area mainly relies on photovoltaic power generation, but the current allocation amount of photovoltaic resources is insufficient. At this time, by increasing the allocation ratio of photovoltaic resources in this area and increasing its power generation, the power supply stability in this area can be improved, making it reach a stable and effective state.

[0055] Downward adjustment being effective means reducing the allocation or allocation intensity of certain resources. For example, when reviewing the pre-allocation strategy, if it is found that the loss of a certain power transmission line is too large, exceeding the range specified by the second dominated index, and the power transmitted by this line is the hydropower resources in a specific area. To reduce the transmission loss, measures can be taken to reduce the amount of hydropower resources transmitted through this line in this area, so that the transmission loss meets the requirements and achieves stability and effectiveness.

[0056] Upward and downward adjustment being effective means comprehensively using the two methods of upward and downward adjustment to optimize the pre-allocation strategy. When there are multiple situations in the pre-allocation strategy that do not meet the second dominated index, a single upward or downward adjustment cannot comprehensively solve the problem, and it is necessary to simultaneously adjust the allocation amount or allocation intensity of multiple resources. For example, there is a shortage of power supply in some areas, while there is an excess of power in other areas, and the loss of some transmission lines is too high. At this time, on the one hand, increase the allocation amount of resources in the areas with insufficient power supply, on the other hand, reduce the amount of resources in the areas with excess power, and reduce the amount of resources transmitted by the high-loss lines. Through this comprehensive adjustment, the pre-allocation strategy can reach a stable and effective state in multiple aspects, thus better meeting the actual needs of the complementary allocation of water and light resources.

[0057] In a possible implementation manner, step S331 further includes:

[0058] Step S3311: If the pre-allocation strategy meets the resource balance state, use the pre-allocation strategy as the resource allocation strategy.

[0059] Step S3312: If the pre-allocation strategy does not meet the resource balance state, trigger a third-order inter-region complementary decision.

[0060] Specifically, when the determination of the resource balance state is completed, if it is found that the preliminary allocation strategy meets the resource balance state, this means that the strategy has achieved an ideal balance in all aspects of resource allocation. From the perspective of the supply side of water-light resources, the resource allocation ratios in different regions are reasonable, which not only makes full use of the natural energy advantages of each region but also avoids the situation of over-exploitation or idleness of resources in some regions. For example, in regions with sufficient sunlight, the allocated amount of photovoltaic resources can fully meet the local electricity demand without causing resource waste; in regions with abundant water resources, the development and allocation of hydropower resources are also appropriate. From the demand side, the electricity demand in each region can be stably and sufficiently supplied. Whether it is industrial electricity, residential electricity or commercial electricity, there will be no problems of power shortage or unstable supply. At the same time, when the power grid accepts these resources, the loads on each line are evenly distributed, and there is no phenomenon of some lines being overloaded and some lines being lightly loaded, ensuring the safety and stability of the power grid operation. Based on these good performances, the preliminary allocation strategy is directly determined as the final resource allocation strategy at this time. This decision not only simplifies the allocation process and improves work efficiency, but more importantly, the preliminary allocation strategy verified layer by layer can effectively achieve the complementary allocation of water-light resources in practical applications, achieving the goals of maximizing resource utilization and optimizing system operation, and providing strong support for the stable and sustainable development of energy supply.

[0061] When the preliminary allocation strategy fails to pass the resource balance state determination, a third-order inter-domain complementary decision is triggered. The activation of this decision-making mechanism aims to break through the limitations of intra-regional allocation and optimize the overall allocation plan through the complementary scheduling of resources between regions. If the preliminary allocation strategy does not meet the resource balance state, various situations may occur. For example, due to changes in sunlight or water flow conditions in some regions, there is an oversupply of water-light resources, and the excess electric energy cannot be effectively consumed locally; while in other regions, due to insufficient resources, it is difficult to meet the local electricity demand, resulting in a tight power supply. In addition, there may also be problems with uneven distribution of the power grid load. Some lines are overloaded due to the concentrated transmission of the excess electric energy in a certain region, affecting the safe and stable operation of the power grid. In this case, the third-order inter-domain complementary decision comes into play. According to the resource distribution, load demand and grid connection status in different regions, a cross-regional resource allocation plan is formulated. For example, the water-light power in the region with oversupply is transmitted to the region with resource shortage through the power grid to achieve the reasonable flow and optimal allocation of resources. During the implementation process, factors such as the capacity of the transmission line and transmission loss will also be comprehensively considered to ensure the feasibility and economy of cross-regional allocation. Through this inter-domain complementary method, the entire allocation system reaches the resource balance state again, improves the utilization efficiency of water-light resources, ensures the stability and reliability of power supply, and realizes the efficient allocation and sustainable development of energy.

[0062] In a possible implementation manner, step S300 further includes:

[0063] Step S370: The first - order master - slave complementarity is the complementary relationship of water - light resources in the same domain, the second - order relaxation is the complementary ratio of water - light resources in the same domain, and the third - order inter - domain complementarity is the scheduling complementarity between different domains.

[0064] Specifically, the first - order master - slave complementarity, the second - order relaxation, and the third - order inter - domain complementarity are key concepts for achieving scientific allocation. The first - order master - slave complementarity focuses on the complementary relationship of water - light resources within the same region. Since light and water flow conditions vary over time, different time periods are suitable for different types of energy generation. During the day when sunlight is sufficient, within the same domain, photovoltaic power generation is the main source, using its high - efficiency power generation characteristics to meet most of the power demand, and hydropower serves as an auxiliary, leveraging its flexible regulation advantage to maintain stable power supply; at night or when sunlight is insufficient, hydropower becomes the dominant energy source and photovoltaic power is in a secondary position, and the two cooperate with each other to ensure continuous and stable power supply within the region.

[0065] The second - order relaxation specifies the complementary ratio of water - light resources in the same domain, providing flexibility for allocation. Considering the uncertainty of energy supply and the dynamic changes in demand, a reasonable range of complementary ratios is set. For example, in a certain region, it is stipulated that the complementary ratio between hydropower and photovoltaic power can float between 4:6 and 6:4. When the light conditions are slightly lower than expected but still suitable for power generation, the proportion of hydropower can be appropriately increased; if the sunlight is more sufficient than expected, the power generation share of photovoltaic power can be increased. On the premise of ensuring stable energy supply, the advantages of the two resources are fully utilized to improve the overall energy utilization efficiency.

[0066] The third - order inter - domain complementarity breaks the regional boundaries and realizes the scheduling complementarity between different domains. The distribution of water - light resources and load demands vary in different regions. Some regions may be rich in water - light resources but have relatively low demand, while some regions are short of resources but have high electricity demands. Through the third - order inter - domain complementarity, the electricity in the resource - surplus region is allocated to the resource - shortage region. For example, if Region A has sufficient sunlight and an excess of photovoltaic power, and Region B has rich hydropower resources but insufficient sunlight and a high electricity load, then some of the photovoltaic power in Region A can be transported to Region B, and the excess hydropower in Region B can be transported to Region A, realizing the optimal allocation of resources on a larger scale, enhancing the overall allocation effect, and ensuring stable and efficient power supply in each region.

[0067] It should be noted that the above - mentioned order of the embodiments of the present application is only for description and does not represent the superiority or inferiority of the embodiments. And the above - mentioned specific embodiments of the present specification have been described. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be beneficial.

[0068] The above are only the preferred embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included within the protection scope of the present application.

[0069] This specification and the drawings are merely exemplary descriptions of the present application and are considered to cover any and all modifications, variations, combinations, or equivalents within the scope of the present application. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is intended to include these changes and modifications.

Claims

1. A method for complementary allocation of water and light resources based on meteorological big data prediction, characterized in that: The method comprises: Obtain the water and light resource nodes involved in the allocation, determine the resource access topology, connect the resource prediction module and conduct long-term and short-term water and light resource predictions, and determine the predicted resource configuration, with meteorology as the resource prediction guide; The moment information fuzzy set is introduced to quantify the expected penalty for abandoning light and water in the worst uncertain scenario, and a complementary allocation unit is constructed based on the third-order complementary condition, where the third-order complementary condition includes the first-order master-slave complementarity, the second-order relaxation, and the third-order inter-domain complementarity. Receive the grid consumption demand and import it into the complementary allocation unit, make a decision based on the predicted resource configuration based on the first-order master-slave complementarity and second-order relaxation in the same domain, determine whether to trigger the third-order inter-domain complementary decision based on the resource balance state, and determine the resource allocation strategy; The allocation decision method is as follows: the allocation decision is made under low-dimensional projection based on the first dominant indicator, and the verification decision is made based on whether the second dominated indicator is satisfied; Allocation decision-making methods, including: Obtain the allocation indicator matrix, perform clustering based on indicator correlation, and determine multiple clusters; Traversing the multiple clusters, adding the maximum influencing indicator in the cluster into the first dominating indicator, adding the remaining indicators in the cluster into the second dominated indicator, and mapping the first dominating indicator and the second dominated indicator based on belonging to the same cluster, wherein the allocation indicator is an indicator that affects the allocation of water and light resources, and the method of adding the maximum influencing indicator in the cluster into the first dominating indicator is to calculate the weight of each indicator in the historical allocation decision, perform sensitivity analysis on the allocation result, and determine the indicator in the cluster that has the greatest impact on the allocation decision; The first-order master-slave complementarity is the complementary relationship of water and light resources in the same domain, the second-order relaxation is the complementary ratio of water and light resources in the same domain, and the third-order inter-domain complementarity is the scheduling complementarity between different domains.

2. The method for complementary deployment of water and light resources based on meteorological big data prediction according to claim 1, characterized in that: The resource prediction module is constructed by driving training through meteorological big data, and the resource prediction module establishes interactive communication with the meteorological data center; Among them, the resource prediction module and the complementary allocation unit use the same programming language, and cascade interactive deployment is carried out by introducing network protocols. The resource prediction module and the complementary allocation unit are embedded and integrated and deployed in the processor array of the resource center, and interactive communication is established with the water-optical base station of each resource node.

3. The method for complementary deployment of water and light resources based on meteorological big data prediction according to claim 1, characterized in that: After determining the resource access topology, the following are included: For each hydro-photovoltaic resource node, determine the microgrid area for network access scheduling; The resource access topology is marked by domains in the microgrid area, wherein each topology domain is marked with a node access position and a resource node code.

4. The method for complementary deployment of water and light resources based on meteorological big data prediction according to claim 1, characterized in that: Decisions are made based on first-order master-slave complementarity and second-order relaxation in the same domain, including: Initializing the allocation space of the complementary allocation unit based on the power grid consumption demand and the predicted resource configuration; According to the first dominating indicator, performing low-dimensional projection on the allocation space to determine a projected allocation space; For the projected allocation space, a decision is made under first-order master-slave complementation and second-order relaxation to determine a pre-allocation strategy.

5. The method for complementary deployment of water and light resources based on meteorological big data prediction according to claim 4, characterized in that: Once you have determined your pre-provisioning strategy, include: Identify the pre-allocation strategy and determine the second dominated indicators one by one; When the second dominated indicator is met, executing resource balancing state determination; If the second controlled indicator is not satisfied, the pre-allocation strategy is compensated with the stable and effective state of the controlled indicator.

6. The method for complementary deployment of water and light resources based on meteorological big data prediction according to claim 5, characterized in that: The stable effective state includes up-regulation effective, down-regulation effective, or up-regulation and down-regulation effective.

7. The method for complementary deployment of water and light resources based on meteorological big data prediction according to claim 6, characterized in that: If the pre-allocation strategy satisfies the resource balancing state, using the pre-allocation strategy as the resource allocation strategy; If the pre-allocation strategy does not satisfy the resource balancing state, a third-order inter-domain complementary decision is triggered.

Images