Flexible Power Supply Allocation Method and System Based on Load Prediction

Abstract

The present invention relates to a flexible power supply distribution method and system based on load prediction, which includes the following steps: extracting multi-dimensional features from the historical load data of the power supply system to obtain a load distribution feature matrix; analyzing the load distribution feature matrix to obtain load change trend parameters; based on the load change trend parameters, performing a supply-demand balance calculation on the power supply system to obtain a dynamic power supply distribution plan; performing stability evaluation and adjustment on the dynamic power supply distribution plan to obtain a safe and stable power supply distribution plan; based on the safe and stable power supply distribution plan, performing real-time correction calculation on the dynamic power supply distribution plan to obtain a flexible power supply control parameter group, and controlling the power supply system based on the flexible power supply control parameter group, solving the technical problem that traditional power supply distribution methods mainly rely on static models and historical data for planning and are difficult to adapt to rapidly changing load conditions and the fluctuation characteristics of intermittent power sources.

Description

Technical Field

[0001] The present invention relates to the technical field of power supply systems, and particularly to a flexible power supply distribution method and system based on load prediction. Background Art

[0002] In modern power supply systems, with the widespread access of distributed energy and the increasing growth of electricity demand, how to achieve efficient and stable power supply has become a major challenge. Traditional power supply distribution methods mainly rely on static models and historical data for planning, and it is difficult to adapt to rapidly changing load conditions and the fluctuating characteristics of intermittent power sources. This not only limits the flexibility and response speed of the power system, but also may lead to supply-demand imbalance and affect the stable operation of the power grid.

[0003] In addition, existing technologies usually adopt a single time series analysis or a simple regression model when dealing with load prediction. These methods cannot comprehensively capture the multi-dimensional characteristics of the load and its inherent changing trends. Especially in the face of complex and changeable user behavior patterns and extreme weather conditions, the prediction accuracy of traditional methods drops significantly, resulting in the power supply system being difficult to make timely and effective adjustments. Therefore, it is particularly important to develop a method that can accurately predict load changes and dynamically adjust power supply strategies accordingly.

[0004] Furthermore, with the rise of the concept of smart grids, higher requirements for the stability and security of power supply systems have been put forward. However, in actual operation, there is a lack of a complete set of mechanisms to real-time evaluate and correct the stability and security of power supply distribution schemes, increasing the operation risks of the power system. Especially during peak load periods, unreasonable power supply distribution may lead to problems such as voltage dips and frequency deviations, and in severe cases, it may even cause large-scale paralysis of the power system. For this reason, a flexible power supply distribution method based on load prediction is studied, aiming to improve the adaptive ability and anti-interference ability of the power system and ensure its safe and stable operation. Summary of the Invention

[0005] The main object of the present invention is to provide a flexible power supply distribution method and system based on load prediction, which solves the technical problem that traditional power supply distribution methods mainly rely on static models and historical data for planning and are difficult to adapt to rapidly changing load conditions and the fluctuating characteristics of intermittent power sources.

[0006] To achieve the above object, the present invention provides a flexible power supply distribution method based on load prediction, which is applied to a power supply system and includes the following steps:

[0007] Extract multi-dimensional features from the historical load data of the power supply system to obtain a load distribution feature matrix;

[0008] Perform multi-scale analysis on the load distribution feature matrix through wavelet transform decomposition to obtain load change trend parameters;

[0009] Predict whether there is supply-demand imbalance in the power supply system based on the load change trend parameters. If so, perform supply-demand balance calculation on the power supply system based on the load change trend parameters to obtain a dynamic power supply distribution plan;

[0010] Perform stability evaluation and adjustment on the dynamic power supply distribution plan through a preset power flow analysis method to obtain a safe and stable power supply distribution plan;

[0011] Perform real-time correction calculation on the dynamic power supply distribution plan based on the safe and stable power supply distribution plan to obtain a flexible power supply control parameter set, and control the power supply system based on the flexible power supply control parameter set.

[0012] Furthermore, the multi-dimensional feature extraction of the historical load data of the power supply system to obtain a load distribution feature matrix includes:

[0013] Perform time-segment sampling on the historical load data of the power supply system to obtain a load time-series data set, and perform spectrum decomposition processing on the load time-series data set to obtain a load frequency-domain feature sequence;

[0014] Perform correlation analysis on the power loads in the power supply system based on the load frequency-domain feature sequence to obtain a load correlation feature matrix, and perform singular value decomposition on the load correlation feature matrix to obtain a load principal component feature set. Among them, the load principal component feature set includes load change gradient, power factor distribution, and load density coefficient;

[0015] Perform instantaneous feature extraction on the load principal component feature set through Hilbert transform to obtain a load instantaneous feature vector, and perform multi-dimensional combination on the load instantaneous feature vector to obtain a load distribution feature matrix. Among them, the load distribution feature matrix includes power fluctuation features, load distribution density features, and power consumption cycle features.

[0016] Furthermore, the multi-scale analysis of the load distribution feature matrix through wavelet transform decomposition to obtain load change trend parameters includes:

[0017] Perform multi-resolution wavelet decomposition on the load distribution feature matrix through wavelet transform decomposition to obtain a multi-scale feature coefficient matrix, and perform singular spectrum analysis on the multi-scale feature coefficient matrix to obtain a load fluctuation feature vector;

[0018] Perform time-frequency joint analysis on the power supply system based on the load fluctuation feature vector to obtain a time-frequency feature tensor, and perform asymmetric orthogonal decomposition on the time-frequency feature tensor to obtain a load dynamic feature set;

[0019] Perform feature fusion processing on the load dynamic feature set through wavelet packet entropy value calculation to obtain a multi-dimensional trend feature matrix, and perform adaptive threshold segmentation on the multi-dimensional trend feature matrix to obtain load change trend parameters.

[0020] Further, based on the load change trend parameters, perform supply-demand balance calculation on the power supply system to obtain a dynamic power supply allocation plan, including:

[0021] Perform dynamic time series decomposition on the load change trend parameters to obtain a load power fluctuation sequence, and perform multi-dimensional phase compensation calculation on the load power fluctuation sequence to obtain a load power compensation feature group;

[0022] Perform power distribution calculation on the power supply system based on the load power compensation feature group to obtain a power distribution feature matrix, and perform topological structure optimization analysis on the power supply system based on the power distribution feature matrix to obtain a power supply network topological feature set, where the power supply network topological feature set includes node connection weights, branch impedance distributions, and voltage gradient coefficients;

[0023] Perform supply-demand matching degree calculation on the power supply network topological feature set through a multi-objective constraint optimization method to obtain a supply-demand balance feature vector, and perform dynamic weight allocation on the supply-demand balance feature vector to obtain a power dispatch parameter group;

[0024] Perform sub-region load distribution calculation on the power supply system based on the power dispatch parameter group to obtain a regional power supply feature sequence, and perform adaptive boundary constraint processing on the regional power supply feature sequence to obtain a power supply boundary feature set, where the power supply boundary feature set includes regional power limits, voltage fluctuation ranges, and load transfer thresholds;

[0025] Generate a dynamic power supply plan for the power supply boundary feature set through a hierarchical progressive optimization method to obtain a dynamic power supply allocation plan, where the dynamic power supply allocation plan includes a power distribution strategy, a voltage regulation plan, and load balancing parameters.

[0026] Further, the power distribution calculation on the power supply system based on the load power compensation feature group to obtain a power distribution feature matrix includes:

[0027] Perform multi-dimensional space mapping decomposition on the load power compensation feature group to obtain a power compensation vector set, and perform phase difference calculation on the power compensation vector set to obtain a voltage-power coupling matrix;

[0028] Based on the voltage-power coupling matrix, perform node power flow tracking on the power supply system to obtain a power distribution map, and perform topological sensitivity analysis on the power distribution map to obtain a power grid transmission characteristic vector;

[0029] By using a double-layer recursive partitioning method, perform power partition clustering on the power grid transmission characteristic vector to obtain a set of power sub-networks, and calculate the interconnection coupling degree of the set of power sub-networks to obtain an inter-region power exchange matrix;

[0030] Based on the inter-region power exchange matrix, perform hierarchical coordinated optimization calculation on the power supply system to obtain a multi-level power supply coordination parameter group, and perform robustness evaluation on the multi-level power supply coordination parameter group to obtain a set of power distribution elasticity coefficients;

[0031] Through an adaptive weight fusion mechanism, perform dynamic feature integration on the set of power distribution elasticity coefficients to obtain a power distribution feature matrix, where the power distribution feature matrix includes node power distribution ratios, voltage control strategy parameters, and load balance adjustment data.

[0032] Further, the power flow analysis method is the Newton-Raphson power flow iterative method. By using the preset power flow analysis method, perform stability evaluation and adjustment on the dynamic power supply distribution plan to obtain a safe and stable power supply distribution plan, including:

[0033] Perform non-linear power flow calculation on the dynamic power supply distribution plan through the Newton-Raphson power flow iterative method to obtain a set of system node voltage distribution characteristics, and perform power flow sensitivity analysis on the set of system node voltage distribution characteristics to obtain a power grid power transmission characteristic matrix;

[0034] When the minimum singular value of the power grid power transmission characteristic matrix is less than a preset threshold, then perform continuous power flow tracking analysis on the power supply system based on the power grid power transmission characteristic matrix to obtain a system voltage stability margin curve, and perform critical point identification on the system voltage stability margin curve to obtain a power grid vulnerable area characteristic map;

[0035] Optimize the power regulation plan for the power grid vulnerable area characteristic map through the AC power flow optimization analysis method to obtain a safe and stable power supply distribution plan, where the safe and stable power supply distribution plan includes an optimal power distribution strategy, dynamic reactive power compensation configuration, and voltage regulation control coefficients.

[0036] Further, based on the safe and stable power supply distribution plan, perform real-time correction calculation on the dynamic power supply distribution plan to obtain a flexible power supply control parameter group, including:

[0037] Perform high-order wavelet singular spectrum analysis on the safe and stable power supply distribution scheme to obtain a sequence of power supply scheme eigenvectors, and perform phase compensation calculation on the sequence of power supply scheme eigenvectors to obtain a real-time power supply control reference parameter set, where the real-time power supply control reference parameter set includes a power adjustment step coefficient, a node voltage control gain, and a load response time constant;

[0038] Based on the real-time power supply control reference parameter set, perform orthogonal decomposition processing on the dynamic power supply distribution scheme to obtain a power supply scheme difference eigenmatrix, and perform multi-scale entropy value calculation on the power supply scheme difference eigenmatrix to obtain a power supply correction quantization parameter set;

[0039] Through non-linear adaptive filtering, perform spatio-temporal domain feature fusion on the power supply correction quantization parameter set to obtain a power supply dynamic response feature sequence, and perform fuzzy inference optimization processing on the power supply dynamic response feature sequence to obtain a flexible power supply control parameter set, where the flexible power supply control parameter set includes a real-time power distribution instruction, a dynamic voltage regulation strategy, and a load response control signal.

[0040] The present invention also provides a flexible power supply distribution system based on load prediction, which is applied to a power supply system and includes:

[0041] An extraction module, configured to perform multi-dimensional feature extraction on historical load data of the power supply system to obtain a load distribution eigenmatrix;

[0042] An analysis module, configured to perform multi-scale analysis on the load distribution eigenmatrix through wavelet transform decomposition to obtain load change trend parameters;

[0043] A calculation module, configured to predict whether there is a supply-demand imbalance in the power supply system based on the load change trend parameters. If so, based on the load change trend parameters, perform supply-demand balance calculation on the power supply system to obtain a dynamic power supply distribution scheme;

[0044] An adjustment module, configured to perform stability evaluation and adjustment on the dynamic power supply distribution scheme through a preset power flow analysis method to obtain a safe and stable power supply distribution scheme;

[0045] A correction module, configured to perform real-time correction calculation on the dynamic power supply distribution scheme based on the safe and stable power supply distribution scheme to obtain a flexible power supply control parameter set, and control the power supply system based on the flexible power supply control parameter set.

[0046] The present invention also provides a computer device, including a memory and a processor, where a computer program is stored in the memory, and when the processor executes the computer program, the steps of the method described in any one of the above are implemented.

[0047] The present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method described in any one of the above are implemented.

[0048] A flexible power supply distribution method based on load prediction provided by the present invention includes the following steps: extracting multi-dimensional features from the historical load data of the power supply system to obtain a load distribution feature matrix; performing multi-scale analysis on the load distribution feature matrix through wavelet transform decomposition to obtain load change trend parameters; predicting whether there is an imbalance between supply and demand in the power supply system based on the load change trend parameters. If so, based on the load change trend parameters, performing a supply-demand balance calculation on the power supply system to obtain a dynamic power supply distribution plan; through a preset power flow analysis method, performing stability evaluation and adjustment on the dynamic power supply distribution plan to obtain a safe and stable power supply distribution plan; based on the safe and stable power supply distribution plan, performing real-time correction calculation on the dynamic power supply distribution plan to obtain a flexible power supply control parameter group, and controlling the power supply system based on the flexible power supply control parameter group, which solves the technical problem that the traditional power supply distribution method mainly relies on static models and historical data for planning and is difficult to adapt to rapidly changing load conditions and the fluctuation characteristics of intermittent power sources. It realizes the stability evaluation and adjustment of the dynamic power supply distribution plan by using a preset power flow analysis method, ensuring the safety and stability of the final power supply distribution plan. This method can effectively detect various factors that may affect the stability of the power grid and eliminate potential hazards through appropriate adjustment. Description of the Drawings

[0049] Figure 1 is a schematic diagram of the steps of the flexible power supply distribution method based on load prediction in an embodiment of the present invention;

[0050] Figure 2 is a structural block diagram of the flexible power supply distribution system based on load prediction in an embodiment of the present invention;

[0051] Figure 3 is a structural schematic block diagram of a computer device in an embodiment of the present invention.

[0052] The realization of the object, functional features and advantages of the present invention will be further described with reference to the embodiments and the accompanying drawings. Detailed Embodiment

[0053] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention and are not used to limit the present invention.

[0054] As Figure 1As shown in Figure 1 is a schematic diagram of the steps of a flexible power supply distribution method based on load prediction in an embodiment of the present invention;

[0055] An embodiment of the present invention provides a flexible power supply distribution method based on load prediction, which is applied to a power supply system and includes the following steps:

[0056] Step S1, perform multi-dimensional feature extraction on the historical load data of the power supply system to obtain a load distribution feature matrix.

[0057] Specifically, when exploring how to extract multi-dimensional features from the historical load data of a power supply system to obtain a load distribution feature matrix, we first need to understand that the core of this process lies in identifying key features from complex data sets that are helpful for understanding and predicting load behavior. This step is the basis of the flexible power supply allocation method based on load prediction because it provides the necessary input for subsequent wavelet transform decomposition, load change trend analysis, and supply-demand balance calculation. Specifically, this process involves extracting information from the vast amount of historical data of the power supply system, which may include electricity consumption, weather conditions, user types, etc. at different time scales, aiming to construct a matrix that comprehensively reflects load characteristics. The first step to achieve this goal is to collect various types of historical data related to the power supply system. These data are not limited to electricity consumption but also include various external factors that may cause load fluctuations, such as seasonal changes, holiday effects, temperature fluctuations, etc. For example, during the high-temperature period in summer, the usage of air conditioners increases significantly, which will directly affect electricity demand; while in winter, the use of heating equipment becomes the main load growth point. By integrating these different data sources, a preliminary data set can be formed, which contains various factors affecting the load of the power supply system. Next, in order to ensure the quality and applicability of the data, the original data must be preprocessed. This includes data cleaning (removing incorrect or incomplete records), normalization (making data at different scales comparable), and feature selection (determining which variables are most critical for load prediction). For example, when faced with a large amount of meteorological data, only select parameters directly related to the power load, such as temperature and humidity, as features, while ignoring those with lower correlation. In this way, we can reduce redundant information and improve the efficiency and accuracy of model training. Once the data preprocessing stage is completed, we enter the core link of multi-dimensional feature extraction. Here, "multi-dimensional" means analyzing load data from multiple perspectives to capture its internal laws and potential patterns. For example, in addition to considering changes in the time series, different regions can be divided according to geographical location to explore the differences in electricity consumption habits of users in each region; or classified according to user types (such as industrial users, commercial users, residential users) to understand the differences in electricity consumption patterns between different types of users. In this way, rich information in the load data can be revealed from different levels, thus constructing a more accurate load distribution feature matrix. The process of constructing the load distribution feature matrix is actually to synthesize the above various dimensions of information to form a structured representation. In this matrix, each row may represent a specific time period or user group, while each column corresponds to a feature attribute. For example, for a certain industrial area, a row in the matrix may be the average electricity consumption per hour on a certain day, and the corresponding columns include factors such as the highest temperature on that day, whether it is a weekday or weekend, and whether it is a special holiday.This structured representation not only facilitates subsequent wavelet transform decomposition but also helps researchers more intuitively understand the interactions among various factors and their impact on the load. For example, suppose we want to optimize the power supply system of a city. The city is divided into several regions, and within each region, there are diverse types of users, including residential areas, commercial centers, and industrial parks. By collecting and organizing data such as the daily average electricity consumption, weather conditions, and public holiday arrangements in each region over the past year, we can construct a detailed load distribution characteristic matrix. Then, by using techniques such as wavelet transform decomposition to conduct in-depth analysis of this matrix, we can not only identify the peak electricity consumption periods on a daily, weekly, or even annual basis but also discover the instantaneous pressure on the local power grid caused by certain special events (such as large-scale exhibitions and sports events). These insights provide a scientific basis for further formulating targeted power supply strategies, such as scheduling backup power sources in advance during periods of expected high load or adjusting electricity price policies to encourage off-peak electricity consumption. Ultimately, it realizes the efficient and stable operation of the power supply system. In short, through meticulous historical data analysis and constructing an accurate load distribution characteristic matrix, it is an important step towards realizing intelligent power grid management.

[0058] Step S2: Perform multi-scale analysis on the load distribution characteristic matrix through wavelet transform decomposition to obtain load change trend parameters.

[0059] Specifically, in the implementation of the flexible power supply distribution method based on load prediction, the process of performing multi-scale analysis on the load distribution feature matrix through wavelet transform decomposition to obtain load change trend parameters is crucial. This process aims to analyze the potential patterns and dynamic characteristics in the load data from different time scales, thereby providing key inputs for subsequent steps. Specifically, wavelet transform is a powerful tool that can perform signal analysis simultaneously in the time and frequency domains. It is particularly suitable for processing non-stationary signals, that is, those signals whose statistical characteristics change over time, which is a significant feature of power load data. First of all, it should be understood that the load distribution feature matrix contains historical data of the power supply system in multiple dimensions, and these data reflect the influence of different factors on the load. However, it is not easy to directly extract useful load change trends from these raw data because they usually contain a large amount of noise and irregular fluctuations. Therefore, by using the method of wavelet transform decomposition, these complex data can be effectively decomposed into different frequency components, and each component represents the load change pattern at different time scales. For example, in a typical daily power consumption cycle, there may be obvious differences between the peak hours during the day and the low hours at night; and in a longer time range, such as seasonal changes or holiday effects, it will lead to a slower change trend. Wavelet transform can identify and separate these change characteristics at different time scales. In actual operation, choosing the appropriate wavelet basis function is a crucial step. Different wavelet basis functions have different mathematical properties and application scenarios. For example, the Morlet wavelet is suitable for cases with better time-frequency localization, while the Haar wavelet is often used for fast calculation due to its simple structure. Selecting the most suitable wavelet basis function according to the specific characteristics of the load data and the analysis purpose is crucial for accurately capturing the load change trend. For example, when analyzing the daily peak load caused by air conditioner use in a city in summer, a wavelet basis function that can accurately reflect the rapid changes in a short time may be required; on the contrary, if the focus is on the annual electricity consumption growth trend, a wavelet basis function that can effectively capture the long-term change pattern is more suitable. Once the wavelet basis function is determined, the next step is to perform the wavelet transform decomposition process. In this process, the original load distribution feature matrix is converted into a series of wavelet coefficients, and these coefficients correspond to the load information at different scales. In this way, not only can the short-term fluctuations (such as daily or weekly changes) be clearly seen, but also the long-term trends (such as monthly or annual changes) can be observed. For example, when analyzing the electricity consumption records of an industrial park over a year, wavelet transform can help us find that in addition to the obvious weekly cycle (the difference between weekdays and weekends), there are also slower change trends caused by factors such as production plan adjustments and market supply and demand changes. In addition, by further processing the wavelet coefficients, we can extract the load change trend parameters.This typically involves statistical analysis of wavelet coefficients at different scales, such as mean, variance, etc., to quantify the change intensity and direction at each scale. These parameters not only reflect the specific patterns of load variation over time but also provide the necessary inputs for subsequent steps. For example, when predicting the load demand over a future period, using these trend parameters can more accurately estimate the possible peak or trough periods, enabling corresponding scheduling preparations in advance. To better understand the application scenarios of this process, consider an example: in a power supply area with multiple user types, including residential areas, commercial centers, and industrial parks. The power supply system in this area aims to improve efficiency and stability through optimized scheduling. By performing wavelet transform decomposition on the electricity consumption data over the past few years, the electricity consumption patterns of different user types and their variations over time can be revealed. For instance, it is found that the electricity consumption peak in residential areas mainly occurs from evening to late at night, while that in commercial centers reaches the peak during the day on weekdays; as for industrial parks, their electricity consumption patterns are greatly affected by the production cycle, showing relatively complex periodic fluctuations. Based on these in-depth analysis results, the power supply system can formulate more flexible and effective power supply strategies, such as increasing power generation capacity in advance or optimizing the grid configuration during periods of expected high load to ensure the stable operation of the entire system. In summary, obtaining load change trend parameters through wavelet transform decomposition provides a solid foundation for the efficient management and optimization of smart grids.

[0060] Step S3, based on the load change trend parameters, predict whether there is an imbalance between supply and demand in the power supply system. If so, based on the load change trend parameters, perform a supply-demand balance calculation on the power supply system to obtain a dynamic power supply allocation plan.

[0061] Specifically, based on the load change trend parameters, it is predicted whether there is an imbalance between supply and demand in the power supply system. This process is one of the key links in the entire flexible power supply distribution method. Its purpose is to predict the possible imbalance between power supply and demand in the future by analyzing historical data and the current operating state. Once it is confirmed that there is a risk of supply-demand imbalance, the load change trend parameters are further used to perform supply-demand balance calculations on the power supply system to formulate a dynamically adjusted power supply distribution plan to ensure the stable operation of the power system. First of all, to achieve this step, it is necessary to rely on the load change trend parameters obtained by wavelet transform decomposition before. These parameters detail the load fluctuation patterns at different time scales, including short-term daily changes and long-term trend changes. In the prediction stage, these trend parameters are input into one or more prediction models, which can be machine learning-based methods such as support vector machines, neural networks, etc., or traditional statistical methods such as regression analysis. The choice of model depends on the specific application scenario and the quality of the available data. For example, when facing a power supply area with multiple user types, considering the electricity consumption characteristics and change rules of residential areas, commercial centers, and industrial parks respectively, we can construct a multivariate prediction model that not only takes into account the load changes in the time series but also incorporates the influence of external factors such as weather conditions and holiday arrangements. When the prediction model receives the load change trend parameters as input, it will perform operations according to the pre-set algorithm logic to evaluate whether there will be an imbalance between supply and demand in the power supply system in a future period. Here, "supply-demand imbalance" refers to the state where the power supply capacity cannot meet the actual demand, which may be the power outage risk caused by insufficient supply or the resource waste caused by excessive supply. Therefore, accurately identifying this potential mismatch is crucial for maintaining the stability of the power grid. For example, during the high-temperature period in summer, with the sudden increase in air conditioner usage, the power demand in some areas may rise suddenly. If sufficient preparations are not made in advance, it may lead to overloading or even collapse of the local power grid. Once the prediction result shows that the power supply system faces the risk of supply-demand imbalance, the next step is to perform supply-demand balance calculations on the power supply system based on the load change trend parameters. This process involves complex mathematical optimization problems, aiming to find an optimal power supply distribution strategy that can minimize energy loss and improve the overall efficiency of the system while meeting the needs of all users. Specifically, the supply-demand balance calculation usually takes into account multiple constraints, such as the maximum output power of power plants, the transmission capacity limit of transmission lines, and the charge and discharge rates of energy storage devices. At the same time, some objective functions are also introduced, such as minimizing costs, maximizing reliability, or optimizing environmental impacts, to guide the decision-making process.For example, assume that in an urban power supply system with multiple user types, we have obtained detailed load change trend parameters through wavelet transform decomposition and predicted that there will be a significant demand peak during the upcoming weekend, mainly because a large music festival is held locally, attracting a large number of tourists. In this case, to address the possible imbalance between supply and demand, we need to formulate a dynamic power supply allocation plan. This plan not only needs to consider the existing power generation capacity and transmission infrastructure but also needs to flexibly mobilize distributed energy resources, such as solar panels and wind turbines, and even the energy storage batteries of electric vehicle charging stations. In addition, by adjusting the electricity price mechanism in real time, residents and enterprises can be encouraged to use electricity during off-peak hours, thereby alleviating the pressure during peak hours. Finally, after a series of precise calculations and simulation tests, the final dynamic power supply allocation plan will be implemented in the actual power supply management system. This plan has high flexibility and adaptability and can be continuously adjusted and optimized according to real-time monitoring data to ensure the safe and stable operation of the power supply system both under normal operating conditions and during emergencies. In short, by predicting the imbalance between supply and demand based on load change trend parameters and performing supply-demand balance calculations accordingly, a scientific and effective management method is provided for the smart grid, which helps to improve the adaptive and anti-interference capabilities of the power system.

[0062] Step S4, through a preset power flow analysis method, evaluate and adjust the stability of the dynamic power supply allocation plan to obtain a safe and stable power supply allocation plan.

[0063] Specifically, in implementing the flexible power supply distribution method based on load prediction, using a preset power flow analysis method to evaluate and adjust the stability of the dynamic power supply distribution plan is a crucial step to ensure a safe and stable power supply distribution plan in the end. This process not only involves complex mathematical models and algorithms but also requires an in-depth understanding of the internal working mechanism of the power system and the impact of external environmental factors. Specifically, power flow analysis is a technology used to study the voltage, current, power distribution, and their interrelationships in a power network. By accurately calculating these parameters, the stability and security of the power grid under different operating conditions can be effectively evaluated. First, after obtaining the dynamic power supply distribution plan, it needs to be input into a preset power flow analysis model. This model is usually constructed based on a series of assumptions, including but not limited to the maximum output power of the generating units, the transmission capacity limit of the transmission lines, the voltage regulation range of the substations, etc. These assumptions reflect the physical characteristics and operation limitations of the actual power grid, so they are crucial for accurately simulating the behavior of the power grid. For example, in an urban power supply system containing residential areas, commercial centers, and industrial parks, considering the electricity consumption characteristics and demand change rules of each area, we can set corresponding boundary conditions according to historical data. For instance, the industrial area may have high power consumption due to production activities and have strict requirements for voltage stability; while the residential area pays more attention to ensuring power supply during peak hours. Next, use the power flow analysis method to conduct detailed calculations and evaluations on the dynamic power supply distribution plan. In this process, the core task is to perform power balance analysis on each node (i.e., substation or load point) in the power grid to determine the voltage level, power flow situation, and potential overload risks of the entire system under the current power supply strategy. This step needs to comprehensively consider various factors, such as the coordination between power sources, the thermal limit of transmission lines, the rated capacity of transformers, etc. For example, during the high-temperature period in summer, with the sharp increase in air conditioner usage, some key transmission corridors may face overload risks. At this time, power flow analysis is needed to identify these problem areas and propose corresponding improvement measures. To improve the accuracy of the analysis results, modern power flow analysis often adopts advanced numerical algorithms, such as the Newton-Raphson method or the fast decoupled method. These algorithms can efficiently solve large-scale nonlinear equations to quickly obtain the state variables of each node in the power grid. In addition, simulation software tools, such as PSS / E or MATPOWER, can be combined to conduct more intuitive and comprehensive simulation experiments. These tools can not only provide detailed calculation results but also help engineers visually observe the performance of the power grid under different operating states to make more scientific and reasonable decisions. Once the preliminary power flow analysis is completed, the next step is to adjust and optimize the problems found. If the analysis results show that there are risks of voltage dips or line overloads in some areas, it is necessary to re-examine and adjust the original power supply distribution plan.For example, in the case of the above-mentioned urban power supply system, if it is found that the power demand of a certain industrial park exceeds expectations, causing the main transmission line connecting this area to approach its maximum carrying capacity, then this problem can be alleviated by increasing the input of backup power sources, adjusting the load distribution in other areas, or upgrading the existing transmission facilities. At the same time, the introduction of distributed energy resources (DERs), such as solar panels and wind turbines, can also be considered as supplementary power supply sources to further enhance the flexibility and reliability of the power grid. Finally, after multiple iterations and optimizations, when all potential safety hazards are properly handled, a safe power supply distribution plan that not only meets user needs but also ensures the stability of the power grid can be obtained. This plan should not only consider short-term operation efficiency but also take into account long-term development plans, such as the integration of renewable energy and the application of smart grid technologies. For example, by reasonably arranging the location and scale of energy storage devices, excess electrical energy can be stored during low electricity consumption periods and released during peak periods to smooth the overall load curve, reduce dependence on traditional power generation methods, and promote the widespread application of clean energy. In summary, stability assessment and adjustment of the dynamic power supply distribution plan through the preset power flow analysis method are important means to ensure the safe and stable operation of the power system. It can not only help us timely discover and solve problems existing in the power grid but also provide strong support for formulating scientific and reasonable power supply strategies. Just as when facing a complex power supply network with multiple user types, only through accurate power flow analysis can the dynamic balance between supply and demand be truly achieved, providing a solid energy guarantee for the development of the social economy.

[0064] Step S5: Based on the safe and stable power supply distribution plan, perform real-time correction calculations on the dynamic power supply distribution plan to obtain a flexible power supply control parameter group, and control the power supply system based on the flexible power supply control parameter group.

[0065] Specifically, based on the secure and stable power supply distribution plan, real-time correction calculations are performed on the dynamic power supply distribution plan, and finally a flexible power supply control parameter set is obtained. This process aims to ensure efficient, reliable, and flexible power supply under various conditions by continuously monitoring and adjusting the operating state of the power system. This step is one of the core links of the entire flexible power supply distribution method. It not only relies on the data and analysis results obtained in the previous steps but also combines the actual operating conditions of the current power grid and changes in external environmental factors to achieve optimal power dispatching and management. First, to perform real-time correction calculations, a powerful data acquisition and monitoring system (SCADA) needs to be established. This system can collect real-time operating data from various nodes (including power generation stations, substations, transmission lines, etc.), such as voltage levels, current intensities, power factors, etc. These data provide the necessary input for subsequent analysis, enabling us to keep track of the state changes of the power grid at any time. For example, in an urban power supply network that includes residential areas, commercial centers, and industrial parks, due to significant differences in the electricity consumption patterns of different types of users, it is necessary to closely monitor the load fluctuations in each area. Especially for industrial users, sudden changes in their production activities may lead to problems of supply-demand imbalance in the local power grid; while residential users may increase the use of air conditioners or heating equipment due to changes in weather conditions (such as extreme heat or cold), thus affecting the overall load distribution. Once the latest power grid operating data is obtained, the next step is to combine it with the previously determined secure and stable power supply distribution plan to perform real-time correction calculations. The goal of this step is to minimize the deviation between the actual operating state and the ideal state without violating any physical constraints. Specifically, this means dynamically adjusting the planned power generation, power transmission, and operation strategies of energy storage devices, etc., according to real-time data. For example, if it is found that the load rate of a certain main transmission line approaches its maximum capacity during a certain period, immediate measures need to be taken, such as reducing the output power of relevant generating units or transferring part of the load to other paths to avoid potential risks. In addition, distributed energy resources (DERs), such as solar panels and wind turbines, can be utilized as supplementary power supply sources to further enhance the flexibility of the power grid. When performing real-time correction calculations, advanced algorithms and technologies, such as model predictive control (MPC), adaptive control, etc., are usually adopted. These methods can quickly respond in a complex and changing environment and provide optimal solutions. Taking MPC as an example, it predicts the operating state of the power grid over a future period of time, then formulates a series of control action sequences based on the prediction results, and finally selects the best set to apply at the current moment. This method is particularly suitable for dealing with systems with obvious dynamic characteristics, such as power networks, because it not only takes into account the immediate impacts but also includes considerations of future trends.For example, during the approaching holiday peak period, it is possible to predict in advance the likely high-load situations and accordingly arrange the start-up time and location of backup power supplies to promptly respond to sudden demands. Based on the above calculation results, a set of flexible power supply control parameter groups is finally formed. This set of parameters covers multiple aspects, such as power generation scheduling instructions, charge-discharge plans for energy storage devices, demand-side response signals, etc. They jointly constitute the specific guidelines for guiding the operation of the power system. For example, in a power supply area with multiple user types, considering the differences in the electricity consumption habits of various users at different time periods, specific demand-side response signals can be sent to encourage residential users to use electrical equipment during off-peak hours, while requiring industrial enterprises to flexibly adjust production shifts according to the actual situation of the power grid. In addition, a reasonable electricity price mechanism can be set up to guide users to voluntarily participate in peak-shaving electricity consumption through price leverage, thereby effectively alleviating the pressure on the power grid. Finally, precise control of the power supply system based on the flexible power supply control parameter groups is the key to realizing a smart grid. Through automated control systems, such as remote terminal units (RTUs) and programmable logic controllers (PLCs), instructions can be directly sent to each control point and feedback information can be received to ensure that all operations are carried out smoothly according to the predetermined plan. For example, during the summer electricity peak period, when it is detected that the power grid faces an overload risk, pre-configured emergency response plans can be quickly activated, including enabling backup power generation facilities, adjusting the working mode of energy storage devices, and issuing emergency power curtailment notices, etc., to ensure the stable operation of the entire system. In short, through this continuous real-time correction and fine-tuning, not only the reliability of the power system is improved, but also a better service experience is provided for users.

[0066] In a specific embodiment, the multi-dimensional feature extraction of the historical load data of the power supply system to obtain a load distribution feature matrix includes:

[0067] Sampling the historical load data of the power supply system at different time intervals to obtain a load time-series data set, and performing spectral decomposition processing on the load time-series data set to obtain a load frequency-domain feature sequence;

[0068] Performing correlation analysis on the power loads in the power supply system based on the load frequency-domain feature sequence to obtain a load correlation feature matrix, and performing singular value decomposition on the load correlation feature matrix to obtain a load principal component feature set, where the load principal component feature set includes a load change gradient, a power factor distribution, and a load density coefficient;

[0069] Performing instantaneous feature extraction on the load principal component feature set through Hilbert transform to obtain a load instantaneous feature vector, and performing multi-dimensional combination on the load instantaneous feature vector to obtain a load distribution feature matrix, where the load distribution feature matrix includes a power fluctuation feature, a load distribution density feature, and an electricity consumption cycle feature.

[0070] Specifically, when exploring how to extract multi-dimensional features from the historical load data of a power supply system to obtain a load distribution feature matrix, we first need to clarify that this process is based on an in-depth analysis of the historical load data of the power supply system, aiming to identify key features from complex datasets that are helpful for understanding and predicting load behavior. This process first involves sampling the historical load data of the power supply system at different time intervals to obtain a load time series dataset, and through spectral decomposition processing, converting the load information in the time domain into a feature sequence in the frequency domain. This step not only lays the foundation for subsequent correlation analysis but also reveals the periodic and non-periodic components in the load data. Specifically, after obtaining a large amount of historical load data of the power supply system, the first step is to sample these data at different time intervals, which means extracting load data according to specific time intervals (such as every hour, day, or week) to form a load time series dataset. This time-interval method can help us better capture the load change patterns in different time periods, such as the differences between weekdays and weekends, and between day and night. Next, to comprehensively understand the inherent characteristics of these load data, spectral decomposition processing is required. Spectral decomposition is a technique for transforming a signal from the time domain to the frequency domain, and the commonly used one is the Fast Fourier Transform (FFT). Through this method, information on different frequency components can be extracted from the original load time series data to form a load frequency domain feature sequence. For example, when analyzing the annual electricity consumption records of a city, it can be found that certain fixed frequency components correspond to the electricity consumption patterns on a daily, weekly, or even annual basis. Based on the above-obtained load frequency domain feature sequence, the next step is to conduct a correlation analysis of the electrical loads in the power supply system to identify possible correlation relationships between different loads. This step is crucial for constructing a load correlation feature matrix because it can help us understand which load factors are significantly correlated and how these correlations change over time and external conditions. For example, in an urban power supply network that includes residential areas, commercial centers, and industrial parks, it can be found through analysis that the electricity consumption peak in the industrial park usually occurs during working hours on weekdays, while the residential area reaches its peak from evening to late at night. The identification of this correlation not only helps optimize the power dispatching strategy but also provides the necessary input for subsequent singular value decomposition. Singular value decomposition is a powerful linear algebra technique that can decompose a complex matrix into the form of the product of several simple matrices, and here it is used to process the load correlation feature matrix. By performing singular value decomposition on this matrix, we can extract a load principal component feature set, which includes key parameters such as the load change gradient, power factor distribution, and load density coefficient. These parameters respectively reflect the speed of load change over time, an important indicator of power quality, and the average load level per unit area.For example, by analyzing the electricity consumption data of a certain area in the past few years, the load change gradient can be calculated to understand the growth trend of electricity demand. At the same time, the power factor distribution of the area can also be evaluated to determine whether there is a problem of reactive power surplus, and then improvement measures can be proposed. Subsequently, in order to further explore the instantaneous characteristics in the load data, the Hilbert transform is used to process the load principal component feature set. The Hilbert transform is an effective tool for analyzing the instantaneous attributes of signals. It can extract the instantaneous amplitude and phase information of signals without losing the information of the original signals. In this process, by applying the Hilbert transform to the load principal component feature set, load instantaneous feature vectors can be obtained, which contain the specific states of the load at any given moment. For example, during the monitoring of a city power grid, the instantaneous changes of the load in a certain area can be monitored in real time to promptly discover and handle sudden high-load events. Finally, through multi-dimensional combination of the load instantaneous feature vectors, a load distribution feature matrix is ultimately obtained. This matrix synthesizes various features extracted in all previous steps, including but not limited to power fluctuation features, load distribution density features, and electricity consumption cycle features, etc. For example, when considering a city power supply system composed of multiple user types, by constructing such a detailed load distribution feature matrix, not only can the electricity consumption patterns of different types of users in each area and their variation laws over time be clearly seen, but also a scientific basis can be provided for formulating targeted power supply strategies. For instance, measures such as scheduling backup power sources in advance during periods of expected high load or adjusting electricity price policies to encourage off-peak electricity consumption are all effective coping strategies based on a profound understanding of these features. In short, through meticulous historical data analysis and constructing an accurate load distribution feature matrix, it is an important step towards realizing intelligent power grid management and the key to improving the efficiency and reliability of the entire power system.

[0071] In a specific embodiment, the multi-scale analysis of the load distribution feature matrix by wavelet transform decomposition to obtain load change trend parameters includes:

[0072] Performing multi-resolution wavelet decomposition on the load distribution feature matrix by wavelet transform decomposition to obtain a multi-scale feature coefficient matrix, and performing singular spectrum analysis on the multi-scale feature coefficient matrix to obtain load fluctuation feature vectors;

[0073] Performing time-frequency joint analysis on the power supply system based on the load fluctuation feature vectors to obtain a time-frequency feature tensor, and performing asymmetric orthogonal decomposition on the time-frequency feature tensor to obtain a load dynamic feature set;

[0074] Performing feature fusion processing on the load dynamic feature set by wavelet packet entropy value calculation to obtain a multi-dimensional trend feature matrix, and performing adaptive threshold segmentation on the multi-dimensional trend feature matrix to obtain load change trend parameters.

[0075] Specifically, when exploring how to perform multi-scale analysis on the load distribution feature matrix through wavelet transform decomposition to obtain load change trend parameters, we first need to understand that this process aims to analyze the potential patterns and dynamic characteristics in the load data from different time scales. This step is based on the previously constructed load distribution feature matrix, which contains multi-dimensional information such as power fluctuations, load distribution density, and electricity consumption cycles in the power supply system. Specifically, this process utilizes the powerful ability of wavelet transform to decompose complex load data into multiple frequency components and extract key features that help understand and predict load behavior. First, perform multi-resolution wavelet decomposition on the load distribution feature matrix through wavelet transform decomposition, which is the first step in the whole process. Wavelet transform, as a tool capable of performing signal analysis in both the time and frequency domains, is particularly suitable for processing non-stationary signals, that is, those signals whose statistical characteristics change over time. At this stage, the original load distribution feature matrix is converted into a feature coefficient matrix containing multi-scale information. For example, in a typical urban power supply network, there may be peak and trough electricity consumption periods on a daily, weekly, or even annual basis; through wavelet transform decomposition, we can identify and separate the change characteristics at these different time scales. Each scale corresponds to different frequency components, representing short-term fluctuations (such as intra-day changes) and long-term trends (such as seasonal changes) in the load data. In addition, in order to further extract the key information in these multi-scale feature coefficient matrices, perform singular spectrum analysis on them to obtain load fluctuation eigenvectors. Singular spectrum analysis is an effective dimensionality reduction technique that can help us extract the most representative features from complex multi-scale feature coefficient matrices, and these eigenvectors reflect the main patterns of load change over time. Next, based on the obtained load fluctuation eigenvectors above, perform time-frequency joint analysis on the power supply system to obtain a time-frequency feature tensor. This process combines the advantages of time series analysis and spectrum analysis, enabling us not only to observe the state of the load at different time points but also to understand its performance at different frequencies. For example, in the face of an urban power supply network containing residential areas, commercial centers, and industrial parks, time-frequency joint analysis can clearly reveal the electricity consumption patterns of different types of users and their interrelationships. For example, it is found that the electricity consumption peak in the industrial area usually occurs during the day on weekdays, while that in the residential area reaches its peak from evening to late at night; at the same time, it is also possible to identify instantaneous high-load phenomena caused by special events (such as large-scale exhibitions or sports events) during certain specific time periods. In order to better understand and utilize these time-frequency features, perform asymmetric orthogonal decomposition on the obtained time-frequency feature tensor to extract the load dynamic feature set. Asymmetric orthogonal decomposition is a technique for processing high-dimensional data that can effectively reduce data redundancy and highlight the most important dynamic characteristics.The result of this is a more concise and highly representative set of load dynamic features, which provides a solid foundation for subsequent feature fusion processing. Subsequently, feature fusion processing is performed on the load dynamic feature set through wavelet packet entropy value calculation to obtain a multi-dimensional trend feature matrix. Wavelet packet entropy is an index for measuring the complexity of a signal, which can quantify the degree of uncertainty of the signal in different frequency bands. In this process, by applying wavelet packet entropy value calculation to the load dynamic feature set, not only can the subtle changes in the load data be captured, but also the information from different frequency bands can be effectively fused to form a multi-dimensional trend feature matrix. This matrix synthesizes various features extracted in all previous steps, including but not limited to the short-term fluctuations, medium-term trends, and long-term change rules of the load. For example, in the process of monitoring a city's power grid, by constructing such a detailed multi-dimensional trend feature matrix, the changes in the load in each region can be monitored in real time, and corresponding adjustment measures can be taken in a timely manner. Finally, in order to ensure that the extracted features are of practical significance and useful for the management of the power system, adaptive threshold segmentation needs to be performed on the multi-dimensional trend feature matrix to obtain the final load change trend parameters. Adaptive threshold segmentation is a method that automatically determines the optimal segmentation point according to the characteristics of the data itself. It can dynamically adjust the threshold according to the current operating state to adapt to the changing load conditions. For example, during the high-temperature period in summer, with the sharp increase in air conditioner usage, the power demand in a certain area may suddenly rise; at this time, through the adaptive threshold segmentation method, this abnormal change can be accurately identified from the multi-dimensional trend feature matrix, and corresponding scheduling strategies can be formulated accordingly, such as increasing the power generation capacity in advance or optimizing the power grid configuration to ensure the stable operation of the entire system. In summary, through the above series of complex but orderly steps, from wavelet transform decomposition to adaptive threshold segmentation, we can accurately extract the load change trend parameters from the load distribution feature matrix. These parameters not only reflect the specific patterns of the load changing over time, but also provide a scientific basis for the efficient management and optimization of the smart grid. For example, in dealing with a complex power supply network with multiple user types, only through in-depth analysis and accurate prediction can the dynamic balance between supply and demand be truly achieved, providing a solid energy guarantee for the development of the social economy.

[0076] In a specific embodiment, based on the load change trend parameters, performing a supply-demand balance calculation on the power supply system to obtain a dynamic power supply allocation scheme, including:

[0077] Performing dynamic time series decomposition on the load change trend parameters to obtain a load power fluctuation sequence, and performing multi-dimensional phase compensation calculation on the load power fluctuation sequence to obtain a load power compensation feature group;

[0078] Based on the load power compensation feature group, power distribution calculation is performed on the power supply system to obtain a power distribution feature matrix, and based on the power distribution feature matrix, topological structure optimization analysis is performed on the power supply system to obtain a power supply network topological feature set, wherein the power supply network topological feature set includes node connection weights, branch impedance distribution, and voltage gradient coefficients;

[0079] Through a multi-objective constraint optimization method, the supply-demand matching degree of the power supply network topological feature set is calculated to obtain a supply-demand balance feature vector, and dynamic weight allocation is performed on the supply-demand balance feature vector to obtain a power dispatching parameter group;

[0080] Based on the power dispatching parameter group, sub-region load distribution calculation is performed on the power supply system to obtain a regional power supply feature sequence, and adaptive boundary constraint processing is performed on the regional power supply feature sequence to obtain a power supply boundary feature set, wherein the power supply boundary feature set includes regional power limit values, voltage fluctuation ranges, and load transfer thresholds;

[0081] Through a hierarchical progressive optimization method, a dynamic power supply scheme is generated for the power supply boundary feature set to obtain a dynamic power supply distribution scheme, wherein the dynamic power supply distribution scheme includes a power distribution strategy, a voltage regulation scheme, and load balancing parameters.

[0082] Specifically, the process of calculating the supply-demand balance of the power supply system based on the load change trend parameters to obtain a dynamic power supply distribution plan is a highly complex and delicate step, aiming to ensure the efficient and stable operation of the power system through precise analysis and optimization. First, it is necessary to perform dynamic time series decomposition on the load change trend parameters. This step decomposes the complex load change trend parameters into more manageable time series data, namely the load power fluctuation sequence. This process utilizes advanced mathematical models and technologies to accurately capture the change laws of the load at different time scales. For example, in an urban power supply network that includes residential areas, commercial centers, and industrial parks, dynamic time series decomposition can identify the peak and valley electricity consumption periods on a daily, weekly, or even annual basis, as well as the instantaneous high-load phenomena caused by special events (such as holidays or large-scale activities). Next, multi-dimensional phase compensation calculations are performed on the load power fluctuation sequence to eliminate errors caused by signal delay or distortion, thereby obtaining a load power compensation feature group. Phase compensation is a technique used to correct the phase of a signal, which can help us better understand and predict the change pattern of the load. In this process, considering the electricity consumption differences among different types of users, a more balanced power distribution can be achieved by adjusting the phase relationship between different regions. For example, during the peak electricity consumption period on weekdays in the industrial area, the impact on the peak electricity consumption period in the residential area at night can be reduced through phase compensation technology, thereby optimizing the load distribution of the entire power grid. Based on the load power compensation feature group, further power distribution calculations are performed on the power supply system to obtain a power distribution feature matrix. This matrix not only contains the power demand information of each node but also reflects the flow of electricity in the network. To improve the efficiency and reliability of power distribution, it is necessary to perform topology optimization analysis on the power supply system based on this power distribution feature matrix to obtain a power supply network topology feature set. Here, the power supply network topology feature set includes key parameters such as node connection weights, branch impedance distributions, and voltage gradient coefficients, which jointly determine the transmission efficiency and stability of electricity in the network. For example, in the face of an urban power supply system composed of multiple user types, by optimizing the power supply network topology, the line losses can be effectively reduced, the quality of electricity transmission can be improved, and the overall reliability of the system can be enhanced. Subsequently, a multi-objective constraint optimization method is used to calculate the supply-demand matching degree of the power supply network topology feature set to obtain a supply-demand balance feature vector. This method can find the optimal supply-demand balance point under the premise of meeting multiple constraint conditions. For example, during the high-temperature period in summer, with the sudden increase in air conditioner usage, the electricity demand in a certain area may suddenly rise; at this time, through the multi-objective constraint optimization method, the most suitable supply-demand balance strategy can be found from the topology feature set, which not only ensures the electricity demand of users but also avoids the risk of power grid overload. Then, dynamic weight allocation is performed on the supply-demand balance feature vector to obtain a power dispatch parameter group.This process dynamically adjusts the weights of various parameters according to the current actual operating state to adapt to changing load conditions. For example, when dealing with sudden high-load events, the pressure can be relieved by increasing the input weight of the backup power supply or adjusting the load distribution weights in other areas. Based on the power dispatch parameter group, a regional load distribution calculation is performed on the power supply system to obtain a regional power supply characteristic sequence. This process divides the entire power supply network into several regions and formulates specific power supply strategies for each region. To ensure the effectiveness and feasibility of these strategies, an adaptive boundary constraint process is also required for the regional power supply characteristic sequence to obtain a power supply boundary feature set. The power supply boundary feature set includes parameters such as regional power limits, voltage fluctuation ranges, and load transfer thresholds, which provide clear guiding principles for power dispatch within the region. For example, in the face of a possible power supply shortage under extreme weather conditions, the power supply plans for each region can be flexibly adjusted according to the preset regional power limits and voltage fluctuation ranges to ensure the normal operation of critical facilities. Finally, a dynamic power supply plan is generated for the power supply boundary feature set through a hierarchical progressive optimization method, and finally a dynamic power supply distribution plan is obtained. This optimization method regards the entire power supply network as a multi-level system, gradually refining the optimization strategy from macro to micro to achieve global optimization. For example, in a city power supply system, the overall power distribution strategy can be determined first, and then the voltage regulation scheme and load balancing parameters can be optimized according to the specific conditions of each region. The result of this is a dynamic power supply distribution plan that takes into account both short-term emergency response and long-term development planning. It not only improves the flexibility and adaptability of the power system but also lays a solid foundation for the efficient management of the smart grid. In summary, through the above series of complex but orderly steps, from wavelet transform decomposition to the generation of the final dynamic power supply distribution plan, we can effectively improve the operating efficiency and reliability of the power system and ensure that the energy needs of social and economic development are fully guaranteed.

[0083] In a specific embodiment, the power distribution calculation of the power supply system based on the load power compensation feature group to obtain a power distribution feature matrix includes:

[0084] Perform multi-dimensional space mapping decomposition on the load power compensation feature group to obtain a power compensation vector set, and perform phase difference calculation on the power compensation vector set to obtain a voltage-power coupling matrix;

[0085] Based on the voltage-power coupling matrix, track the node power flow of the power supply system to obtain a power distribution map, and perform topological sensitivity analysis on the power distribution map to obtain a power supply network transmission characteristic vector;

[0086] Perform power partition clustering on the transmission characteristic vector of the power supply network through a double-layer recursive partitioning method to obtain a set of power sub-networks, and calculate the interconnection coupling degree of the set of power sub-networks to obtain an inter-region power exchange matrix;

[0087] Based on the inter-region power exchange matrix, perform hierarchical coordination optimization calculation on the power supply system to obtain a multi-level power supply coordination parameter set, and perform robustness evaluation on the multi-level power supply coordination parameter set to obtain a power distribution elasticity coefficient set;

[0088] Perform dynamic feature integration on the power distribution elasticity coefficient set through an adaptive weight fusion mechanism to obtain a power distribution feature matrix, where the power distribution feature matrix includes node power distribution ratios, voltage control strategy parameters, and load balance adjustment data.

[0089] Specifically, the process of performing power distribution calculations on the power supply system based on the load power compensation feature group to obtain the power distribution feature matrix is a complex and meticulous step, aiming to ensure the efficient and stable operation of the power system through precise data processing and optimization algorithms. First, perform multi-dimensional space mapping decomposition on the load power compensation feature group, which is the first step in the whole process. At this stage, the load power compensation feature group is converted into a multi-dimensional spatial representation form, that is, the power compensation vector set. Each compensation vector represents a power adjustment strategy in a specific dimension, such as a load adjustment plan for different regions or different types of users. Then, by calculating the phase differences of these power compensation vector sets, the voltage-power coupling matrix can be obtained. The phase difference calculation helps to understand the mutual influence relationship between voltage and power among different nodes, which is crucial for subsequent power distribution analysis. Based on the voltage-power coupling matrix, the next step is to track the power flow direction of each node in the power supply system, thereby constructing a detailed power distribution map. This step involves in-depth analysis of the power flow situation among various nodes in the power grid and how they interact with each other. For example, in an urban power supply network containing residential areas, commercial centers, and industrial parks, through node power flow tracking, we can clearly see the power exchange patterns among different regions, including the power flow direction during peak hours and its impact on the overall power grid. To further optimize this power distribution, it is necessary to perform topological sensitivity analysis on the power distribution map to obtain the transmission characteristic vector of the power supply network. Topological sensitivity analysis can reveal the impact of the power grid structure on power transmission efficiency and stability, helping to identify potential bottlenecks or vulnerable points, such as the overload risk of certain key transmission lines. Subsequently, use the double-layer recursive partitioning method to perform power partition clustering on the transmission characteristic vector of the power supply network to form a set of power sub-networks. This method recursively divides the power grid into smaller and more manageable sub-networks, and each sub-network has relatively independent but interrelated power transmission characteristics. For example, in the above urban power supply network case, the power grid can be divided into multiple sub-networks in this way, and each sub-network focuses on meeting the electricity demand within a specific area (such as an industrial area, a commercial center, or a residential area). Then, calculate the interconnection coupling degree of the set of power sub-networks to obtain the inter-regional power exchange matrix. This step aims to quantify the amount of power exchange between different sub-networks and the degree of their mutual dependence, which is very important for formulating effective cross-regional coordination strategies. Based on the inter-regional power exchange matrix, further perform hierarchical coordination optimization calculations on the power supply system to obtain a multi-level power supply coordination parameter group. Here, "multi-level" refers to an optimization strategy that gradually refines from macro to micro, ensuring that the power distribution at each level can reach the optimal state. For example, in the face of the possible power consumption peak during the high-temperature period in summer, through multi-level coordination optimization, both the stability of the overall power grid can be ensured and the high-load demand in local areas can be flexibly addressed.In addition, it is necessary to perform a robustness assessment on the multi-level power supply coordination parameter group to obtain a set of power distribution elasticity coefficients. Robustness assessment is a method to test the performance of a scheme under various uncertain conditions, which ensures that even in extreme cases, the basic power supply and service quality can be maintained. Finally, through an adaptive weight fusion mechanism, dynamic feature integration is performed on the set of power distribution elasticity coefficients to finally obtain a power distribution feature matrix. The adaptive weight fusion mechanism allows the weights of various parameters to be dynamically adjusted according to real-time data to adapt to changing load conditions and external environments. For example, in an urban power supply system composed of multiple user types, the power distribution ratio, voltage control strategy parameters, and load balancing adjustment data of each region can be flexibly adjusted according to actual power consumption demands, weather forecasts, and other information. The result of this is a power distribution feature matrix that can not only reflect the current operating state of the power grid but also guide future operations, which not only contains specific numerical parameters but also provides detailed guidelines on how to optimize the performance of the power grid. In short, through this series of complex steps, from wavelet transform decomposition to the final generation of the power distribution feature matrix, we can effectively improve the flexibility and reliability of the power system, ensure that the energy needs of social and economic development are fully guaranteed, and provide strong support for the efficient management of smart grids.

[0090] In a specific embodiment, the power flow analysis method is the Newton-Raphson power flow iterative method. By using the preset power flow analysis method, the stability assessment and adjustment of the dynamic power supply distribution scheme are carried out to obtain a safe and stable power supply distribution scheme, including:

[0091] Perform a non-linear power flow calculation on the dynamic power supply distribution scheme through the Newton-Raphson power flow iterative method to obtain a set of system node voltage distribution characteristics, and perform a power flow sensitivity analysis on the set of system node voltage distribution characteristics to obtain a power grid power transmission characteristic matrix;

[0092] When the minimum singular value of the power grid power transmission characteristic matrix is less than a preset threshold, then based on the power grid power transmission characteristic matrix, a continuous power flow tracking analysis is performed on the power supply system to obtain a system voltage stability margin curve, and a critical point identification is performed on the system voltage stability margin curve to obtain a power grid vulnerable area characteristic map;

[0093] Optimize the power regulation scheme for the power grid vulnerable area characteristic map through the AC power flow optimization analysis method to obtain a safe and stable power supply distribution scheme, where the safe and stable power supply distribution scheme includes an optimal power distribution strategy, dynamic reactive power compensation configuration, and voltage regulation control coefficients.

[0094] Specifically, in implementing the flexible power supply distribution method based on load prediction, the dynamic power supply distribution scheme is evaluated and adjusted for stability through a preset power flow analysis method to obtain a safe and stable power supply distribution scheme. This process is crucial for ensuring the stable operation of the power grid. Specifically, the power flow analysis method uses the Newton-Raphson power flow iterative method, which is an efficient and widely used method for solving complex non-linear equations to calculate the node voltage distribution and power transmission characteristics in the power grid.

[0095] First, use the Newton-Raphson power flow iterative method to perform non-linear power flow calculations on the dynamic power supply distribution scheme, obtaining a set of system node voltage distribution characteristics. The Newton-Raphson method is an iterative solution technique that solves non-linear equations by continuously approaching the true solution. This method is particularly suitable for complex calculations in large-scale power systems. For example, in an urban power supply network that includes residential areas, commercial centers, and industrial parks, there are significant differences in electricity consumption patterns in different regions, which can lead to different voltage levels at each node. By performing detailed calculations on the voltage distribution of these nodes, potential voltage instability points can be identified and used as a basis for subsequent optimization. Next, perform a power flow sensitivity analysis on the set of system node voltage distribution characteristics to obtain the power grid power transfer characteristic matrix. The power flow sensitivity analysis aims to evaluate the degree of mutual influence between various nodes in the power grid, especially how changes in the load or power generation at a certain node affect the voltage and power distribution of the entire power grid. During this process, by calculating the power grid power transfer characteristic matrix, the coupling relationship between different nodes and its impact on the overall power grid stability can be quantified. For example, in the above example of the urban power supply network, if the load rate of a key transmission line is close to its maximum capacity, then this line may become a vulnerable point in the system. Through the analysis of the power grid power transfer characteristic matrix, these vulnerable points can be accurately determined and their impact on the power grid stability can be evaluated. When the minimum singular value of the power grid power transfer characteristic matrix is less than a preset threshold, it means that there may be voltage stability problems in the power grid and further analysis and optimization are required. In this case, perform a continuous power flow tracing analysis on the power supply system based on the power grid power transfer characteristic matrix to obtain the system voltage stability margin curve. Continuous power flow tracing is a process of simulating the gradual transition of the power grid from a normal state to an unstable state. Through this method, the turning points where the system changes from stable to unstable can be identified. For example, during the high-temperature period in summer, with the sudden increase in air conditioner usage, the power demand in some areas may suddenly rise; through continuous power flow tracing analysis, we can anticipate the impact of this high-load situation on the power grid and formulate corresponding countermeasures. Subsequently, perform critical point identification on the system voltage stability margin curve to obtain the characteristic map of the power grid vulnerable area. Critical point identification helps to find the areas in the system that are most prone to voltage collapse, thus providing guidance for targeted optimization measures. To improve the safety and stability of the power grid, use the AC power flow optimization analysis method to optimize the power regulation scheme for the characteristic map of the power grid vulnerable area, and finally obtain a safe and stable power supply distribution scheme. The AC power flow optimization analysis is an optimization method that comprehensively considers multiple objective functions and constraint conditions, aiming to find a solution that can satisfy all constraints and make the objective function reach the optimal solution. For example, in the above example of the urban power supply network case, through AC power flow optimization analysis, the basic electricity consumption needs of each region can be guaranteed while avoiding the risk of overloading of key transmission lines.Meanwhile, it is also necessary to ensure that the overall voltage level of the power grid is within a reasonable range and improve the system's security. The result of this is a power supply distribution plan that includes an optimal power distribution strategy, dynamic reactive power compensation configuration, and voltage regulation control coefficients, where: The optimal power distribution strategy aims to dynamically adjust the output power of the generating units according to real-time load changes to ensure the balance between supply and demand. The dynamic reactive power compensation configuration improves the voltage level and power factor of the power grid and reduces energy losses by intelligently adjusting the operating states of reactive power compensation devices (such as capacitors and reactors). The voltage regulation control coefficient is used to set the parameters of the automatic voltage regulator (AVR) to ensure that the power grid voltage remains within the specified range and prevent the voltage from being too high or too low from affecting the user's power consumption experience. In short, through this series of complex but orderly steps, from non-linear power flow calculation to the generation of the final safe and stable power supply distribution plan, we can effectively improve the flexibility and adaptability of the power system, ensure that the energy needs of social and economic development are fully guaranteed, and provide strong support for the efficient management of the smart grid. For example, in the face of a possible power supply shortage under extreme weather conditions, corresponding measures can be predicted and taken in advance through the above methods to ensure that the power grid can still operate stably under various uncertain conditions.

[0096] In a specific embodiment, based on the safe and stable power supply distribution plan, a real-time correction calculation is performed on the dynamic power supply distribution plan to obtain a flexible power supply control parameter set, including:

[0097] Perform high-order wavelet singular spectrum analysis on the safe and stable power supply distribution plan to obtain a power supply plan feature vector sequence, and perform phase compensation calculation on the power supply plan feature vector sequence to obtain a real-time power supply control reference parameter set, where the real-time power supply control reference parameter set includes a power regulation step coefficient, a node voltage control gain, and a load response time constant;

[0098] Based on the real-time power supply control reference parameter set, perform orthogonal decomposition processing on the dynamic power supply distribution plan to obtain a power supply plan difference feature matrix, and perform multi-scale entropy value calculation on the power supply plan difference feature matrix to obtain a power supply correction quantization parameter set;

[0099] Perform spatio-temporal domain feature fusion on the power supply correction quantization parameter set through non-linear adaptive filtering to obtain a power supply dynamic response feature sequence, and perform fuzzy inference optimization processing on the power supply dynamic response feature sequence to obtain a flexible power supply control parameter set, where the flexible power supply control parameter set includes a real-time power distribution instruction, a dynamic voltage regulation strategy, and a load response control signal.

[0100] Specifically, the process of performing real-time correction calculations on the dynamic power supply distribution scheme based on the secure and stable power supply distribution scheme to obtain a flexible power supply control parameter set aims to ensure the efficient and stable operation of the power system through precise data processing and advanced optimization algorithms. First, it is necessary to perform high-order wavelet singular spectrum analysis on the secure and stable power supply distribution scheme. This process converts the complex power supply distribution scheme into a sequence of eigenvector containing multi-scale information. High-order wavelet singular spectrum analysis is a powerful tool that combines wavelet transform and singular value decomposition, capable of extracting key features from the original data. These sequences of eigenvectors reflect the changes in power supply characteristics at different time scales. For example, in a typical urban power supply network, there may be peak and trough periods of electricity consumption daily, weekly, or even annually; through high-order wavelet singular spectrum analysis, we can identify and separate these change features at different time scales, thus better understanding and predicting the behavior of the power grid. Next, perform phase compensation calculations on the sequence of eigenvectors of the power supply scheme to eliminate errors caused by signal delay or distortion, thereby obtaining a real-time power supply control reference parameter set. Phase compensation calculations help adjust the voltage and power relationships between nodes, ensuring the synchronization and stability of the entire power grid. For example, during the peak electricity consumption period on weekdays in industrial areas, phase compensation technology can be used to reduce the impact on the peak electricity consumption period in residential areas at night, thus optimizing the load distribution of the entire power grid. The real-time power supply control reference parameter set includes key parameters such as power adjustment step coefficients, node voltage control gains, and load response time constants, which jointly determine the regulation accuracy and response speed of the power system in actual operation. Based on the real-time power supply control reference parameter set, further perform orthogonal decomposition processing on the dynamic power supply distribution scheme to obtain a power supply scheme difference feature matrix. Orthogonal decomposition is a technique used to simplify complex data structures, which can help us more clearly understand the main difference components in the power supply scheme. For example, in the face of a peak electricity consumption period that may occur during high temperatures in summer, by performing orthogonal decomposition on the dynamic power supply distribution scheme, we can identify which regions or user groups are the main factors causing load fluctuations and formulate targeted regulation strategies accordingly. Subsequently, perform multi-scale entropy value calculations on the power supply scheme difference feature matrix to obtain a power supply correction quantization parameter set. Multi-scale entropy value calculation is a method for measuring signal complexity, which can quantify the degree of uncertainty of signals in different frequency bands, thus helping us more accurately evaluate the effectiveness and stability of the power supply scheme. To further improve the adaptability and flexibility of the power supply scheme, non-linear adaptive filtering is used to perform spatio-temporal domain feature fusion on the power supply correction quantization parameter set to obtain a power supply dynamic response feature sequence. Non-linear adaptive filtering is a method that can automatically adjust its parameters to adapt to the characteristics of continuously changing input signals. This step not only captures the change laws of the load in different time and space dimensions but also effectively fuses information from different frequency bands.For example, during the monitoring of a city's power grid, through non-linear adaptive filtering, the changes in the load in each area can be monitored in real time, and corresponding adjustment measures can be taken in a timely manner. Then, the fuzzy inference optimization process is carried out on the power supply dynamic response feature sequence, and finally a flexible power supply control parameter group is obtained. Fuzzy inference is a technology that simulates the human decision-making process and can make reasonable judgments under conditions of uncertainty and incomplete information. In this process, by applying the fuzzy inference optimization process to the power supply dynamic response feature sequence, various control parameters can be dynamically adjusted according to the current actual operating state, so as to achieve more flexible and efficient power dispatching. The flexible power supply control parameter group includes key components such as real-time power distribution instructions, dynamic voltage regulation strategies, and load response control signals, which together constitute the specific guidelines for guiding the operation of the power system. For example, during the upcoming holiday peak period, the possible high-load situation can be predicted in advance, and the start time and location of the standby power supply can be arranged accordingly. At the same time, the output power of the generator set can be flexibly adjusted through real-time power distribution instructions; the grid voltage level can be ensured within a reasonable range through dynamic voltage regulation strategies to avoid affecting the user's power consumption experience due to too high or too low voltage; finally, the load response control signal is used to guide users to consciously participate in peak-shifting power consumption, thereby effectively relieving the grid pressure. In short, through the above series of complex but orderly steps, from wavelet singular spectrum analysis to the generation of the final flexible power supply control parameter group, we can effectively improve the flexibility and adaptability of the power system, ensure that the energy needs of social and economic development are fully guaranteed, and provide strong support for the efficient management of smart grids.

[0101] The above describes the flexible power supply distribution method based on load prediction in the embodiments of the present invention. Next, the flexible power supply distribution system based on load prediction in the embodiments of the present invention will be described. Please refer to Figure 2 , an embodiment of the flexible power supply distribution system based on load prediction in the embodiments of the present invention includes:

[0102] An extraction module 21, configured to perform multi-dimensional feature extraction on the historical load data of the power supply system to obtain a load distribution feature matrix;

[0103] An analysis module 22, configured to perform multi-scale analysis on the load distribution feature matrix through wavelet transform decomposition to obtain load change trend parameters;

[0104] A calculation module 23, configured to predict whether there is an imbalance between supply and demand in the power supply system based on the load change trend parameters. If so, based on the load change trend parameters, perform a supply-demand balance calculation on the power supply system to obtain a dynamic power supply distribution plan;

[0105] An adjustment module 24, configured to perform stability evaluation and adjustment on the dynamic power supply distribution scheme through a preset power flow analysis method, so as to obtain a safe and stable power supply distribution scheme;

[0106] A correction module 25, configured to perform real-time correction calculation on the dynamic power supply distribution scheme based on the safe and stable power supply distribution scheme, so as to obtain a flexible power supply control parameter group, and control the power supply system based on the flexible power supply control parameter group.

[0107] In this embodiment, for the specific implementation of each unit in the above system embodiment, please refer to that described in the above method embodiment, and details will not be repeated here.

[0108] Refer to Figure 3 , in an embodiment of the present invention, a computer device is further provided. The internal structure of the computer device may be as Figure 3 shown. The computer device includes a processor, a memory, a display screen, an input device, a network interface, and a database connected through a system bus. Among them, the processor of the computer design is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the corresponding data in this embodiment. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the above method is implemented.

[0109] Those skilled in the art can understand that Figure 3 the structure shown in

[0110] is only a block diagram of a part of the structure related to the solution of the present invention, and does not constitute a limitation on the computer device to which the solution of the present invention is applied.

[0111] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium provided by the present invention and used in the embodiments can include non-volatile and / or volatile memories. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM, etc.

[0112] It should be noted that in this article, the terms "including", "comprising", or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, device, article, or method including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or further includes elements inherent to such a process, device, article, or method. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of another identical element in the process, device, article, or method including that element.

[0113] The above are only the preferred embodiments of the present invention, and do not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the specification and drawings of the present invention, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present invention.

Claims

1. A flexible power supply distribution method based on load prediction, characterized in that Applied to a power supply system, including the following steps: Perform multi-dimensional feature extraction on the historical load data of the power supply system to obtain a load distribution feature matrix; Perform multi-scale analysis on the load distribution feature matrix through wavelet transform decomposition to obtain load change trend parameters; Based on the load change trend parameters, predict whether there is a supply-demand imbalance in the power supply system. If so, based on the load change trend parameters, perform supply-demand balance calculation on the power supply system to obtain a dynamic power supply allocation plan; Through a preset power flow analysis method, perform stability evaluation and adjustment on the dynamic power supply allocation plan to obtain a safe and stable power supply allocation plan; Based on the safe and stable power supply allocation plan, perform real-time correction calculation on the dynamic power supply allocation plan to obtain a flexible power supply control parameter group, and control the power supply system based on the flexible power supply control parameter group; Perform dynamic time series decomposition on the load change trend parameters to obtain a load power fluctuation sequence, and perform multi-dimensional phase compensation calculation on the load power fluctuation sequence to obtain a load power compensation feature group; Based on the load power compensation feature group, perform power distribution calculation on the power supply system to obtain a power distribution feature matrix, and based on the power distribution feature matrix, perform topological structure optimization analysis on the power supply system to obtain a power supply network topological feature set, where the power supply network topological feature set includes node connection weights, branch impedance distribution, and voltage gradient coefficients; Through a multi-objective constraint optimization method, perform supply-demand matching degree calculation on the power supply network topological feature set to obtain a supply-demand balance feature vector, and perform dynamic weight allocation on the supply-demand balance feature vector to obtain a power dispatch parameter group; Based on the power dispatch parameter group, perform sub-region load distribution calculation on the power supply system to obtain a regional power supply feature sequence, and perform adaptive boundary constraint processing on the regional power supply feature sequence to obtain a power supply boundary feature set, where the power supply boundary feature set includes regional power limits, voltage fluctuation ranges, and load transfer thresholds; Through a hierarchical progressive optimization method, generate a dynamic power supply plan for the power supply boundary feature set to obtain a dynamic power supply allocation plan, where the dynamic power supply allocation plan includes a power distribution strategy, a voltage regulation plan, and load balancing parameters; Perform multi-dimensional space mapping decomposition on the load power compensation feature group to obtain a power compensation vector set, and perform phase difference calculation on the power compensation vector set to obtain a voltage-power coupling matrix; Based on the voltage-power coupling matrix, perform node power flow tracking on the power supply system to obtain a power distribution map, and perform topological sensitivity analysis on the power distribution map to obtain a power supply network transmission characteristic vector; Through a double-layer recursive partitioning method, perform power sub-network clustering on the power supply network transmission characteristic vector to obtain a power sub-network set, and perform interconnection coupling degree calculation on the power sub-network set to obtain an inter-region power exchange matrix; Based on the inter-region power exchange matrix, hierarchical coordinated optimization calculation is performed on the power supply system to obtain a multi-level power supply coordination parameter group, and the robustness of the multi-level power supply coordination parameter group is evaluated to obtain a power distribution elasticity coefficient set; Through an adaptive weight fusion mechanism, dynamic feature integration is performed on the power distribution elasticity coefficient set to obtain a power distribution feature matrix, where the power distribution feature matrix includes node power distribution ratios, voltage control strategy parameters, and load balance adjustment data; Through the Newton-Raphson power flow iteration method, non-linear power flow calculation is performed on the dynamic power supply distribution scheme to obtain a system node voltage distribution feature set, and power flow sensitivity analysis is performed on the system node voltage distribution feature set to obtain a power grid power transmission characteristic matrix; When the minimum singular value of the power grid power transmission characteristic matrix is less than a preset threshold, continuous power flow tracking analysis is performed on the power supply system based on the power grid power transmission characteristic matrix to obtain a system voltage stability margin curve, and critical point identification is performed on the system voltage stability margin curve to obtain a power grid vulnerable area feature map; Through the AC power flow optimization analysis method, the power grid vulnerable area feature map is optimized for a power regulation plan to obtain a safe and stable power supply distribution plan, where the safe and stable power supply distribution plan includes an optimal power distribution strategy, dynamic reactive power compensation configuration, and voltage regulation control coefficients.

2. The flexible power supply distribution method based on load prediction according to claim 1, wherein The multi-dimensional feature extraction of the historical load data of the power supply system is performed to obtain a load distribution feature matrix, including: The historical load data of the power supply system is sampled by time period to obtain a load time series data set, and spectral decomposition processing is performed on the load time series data set to obtain a load frequency domain feature sequence; Based on the load frequency domain feature sequence, correlation analysis of the power loads in the power supply system is performed to obtain a load correlation feature matrix, and singular value decomposition is performed on the load correlation feature matrix to obtain a load principal component feature set, where the load principal component feature set includes load change gradients, power factor distributions, and load density coefficients; Through Hilbert transform, instantaneous feature extraction is performed on the load principal component feature set to obtain a load instantaneous feature vector, and multi-dimensional combination is performed on the load instantaneous feature vector to obtain a load distribution feature matrix, where the load distribution feature matrix includes power fluctuation features, load distribution density features, and power consumption cycle features.

3. The flexible power supply distribution method based on load prediction according to claim 1, characterized in that The multi-scale analysis of the load distribution feature matrix is performed through wavelet transform decomposition to obtain load change trend parameters, including: Through wavelet transform decomposition, multi-resolution wavelet decomposition is performed on the load distribution feature matrix to obtain a multi-scale feature coefficient matrix, and singular spectrum analysis is performed on the multi-scale feature coefficient matrix to obtain a load fluctuation feature vector; Based on the load fluctuation feature vector, time-frequency joint analysis of the power supply system is performed to obtain a time-frequency feature tensor, and asymmetric orthogonal decomposition is performed on the time-frequency feature tensor to obtain a load dynamic feature set; Feature fusion processing is performed on the load dynamic feature set through wavelet packet entropy value calculation to obtain a multi-dimensional trend feature matrix, and adaptive threshold segmentation is performed on the multi-dimensional trend feature matrix to obtain load change trend parameters.

4. The flexible power supply distribution method based on load prediction according to claim 1, wherein Based on the safe and stable power supply distribution scheme, real-time correction calculation is performed on the dynamic power supply distribution scheme to obtain a flexible power supply control parameter group, including: Performing high-order wavelet singular spectrum analysis on the safe and stable power supply distribution scheme to obtain a power supply scheme feature vector sequence, and performing phase compensation calculation on the power supply scheme feature vector sequence to obtain a real-time power supply control reference parameter group, where the real-time power supply control reference parameter group includes a power adjustment step coefficient, a node voltage control gain, and a load response time constant; Based on the real-time power supply control reference parameter group, orthogonal decomposition processing is performed on the dynamic power supply distribution scheme to obtain a power supply scheme difference feature matrix, and multi-scale entropy value calculation is performed on the power supply scheme difference feature matrix to obtain a power supply correction quantization parameter set; Through non-linear adaptive filtering, spatio-temporal domain feature fusion is performed on the power supply correction quantization parameter set to obtain a power supply dynamic response feature sequence, and fuzzy inference optimization processing is performed on the power supply dynamic response feature sequence to obtain a flexible power supply control parameter group, where the flexible power supply control parameter group includes a real-time power distribution instruction, a dynamic voltage regulation strategy, and a load response control signal.

5. A flexible power supply distribution system based on load prediction, characterized in that, Applied to a power supply system, including: An extraction module for performing multi-dimensional feature extraction on the historical load data of the power supply system to obtain a load distribution feature matrix; An analysis module for performing multi-scale analysis on the load distribution feature matrix through wavelet transform decomposition to obtain load change trend parameters; A calculation module for predicting whether there is a supply-demand imbalance in the power supply system based on the load change trend parameters. If so, based on the load change trend parameters, supply-demand balance calculation is performed on the power supply system to obtain a dynamic power supply distribution scheme; An adjustment module for performing stability evaluation and adjustment on the dynamic power supply distribution scheme through a preset power flow analysis method to obtain a safe and stable power supply distribution scheme; A correction module for performing real-time correction calculation on the dynamic power supply distribution scheme based on the safe and stable power supply distribution scheme to obtain a flexible power supply control parameter group, and controlling the power supply system based on the flexible power supply control parameter group; Performing dynamic time series decomposition on the load change trend parameters to obtain a load power fluctuation sequence, and performing multi-dimensional phase compensation calculation on the load power fluctuation sequence to obtain a load power compensation feature group; Performing power distribution calculation on the power supply system based on the load power compensation feature group to obtain a power distribution feature matrix, and performing topological structure optimization analysis on the power supply system based on the power distribution feature matrix to obtain a power supply network topology feature set, where the power supply network topology feature set includes node connection weights, branch impedance distributions, and voltage gradient coefficients; Calculate the supply-demand matching degree of the power supply network topology feature set through a multi-objective constraint optimization method to obtain a supply-demand balance feature vector, and perform dynamic weight allocation on the supply-demand balance feature vector to obtain a power dispatch parameter group; Based on the power dispatch parameter group, perform sub-region load distribution calculation on the power supply system to obtain a regional power supply feature sequence, and perform adaptive boundary constraint processing on the regional power supply feature sequence to obtain a power supply boundary feature set, where the power supply boundary feature set includes regional power limit values, voltage fluctuation ranges, and load transfer thresholds; Generate a dynamic power supply plan for the power supply boundary feature set through a hierarchical progressive optimization method to obtain a dynamic power supply distribution plan, where the dynamic power supply distribution plan includes a power distribution strategy, a voltage regulation plan, and load balancing parameters; Perform multi-dimensional space mapping decomposition on the load power compensation feature group to obtain a power compensation vector set, and perform phase difference calculation on the power compensation vector set to obtain a voltage-power coupling matrix; Based on the voltage-power coupling matrix, track the node power flow direction of the power supply system to obtain a power distribution map, and perform topological sensitivity analysis on the power distribution map to obtain a power supply network transmission characteristic vector; Perform power sub-network clustering on the power supply network transmission characteristic vector through a double-layer recursive partitioning method to obtain a set of power sub-networks, and calculate the interconnection coupling degree of the set of power sub-networks to obtain an inter-region power exchange matrix; Based on the inter-region power exchange matrix, perform hierarchical coordinated optimization calculation on the power supply system to obtain a multi-level power supply coordination parameter group, and perform robustness evaluation on the multi-level power supply coordination parameter group to obtain a power distribution elasticity coefficient set; Perform dynamic feature integration on the power distribution elasticity coefficient set through an adaptive weight fusion mechanism to obtain a power distribution feature matrix, where the power distribution feature matrix includes node power distribution ratios, voltage control strategy parameters, and load balancing adjustment data; Perform non-linear power flow calculation on the dynamic power supply distribution plan through the Newton-Raphson power flow iteration method to obtain a system node voltage distribution feature set, and perform power flow sensitivity analysis on the system node voltage distribution feature set to obtain a power grid power transmission characteristic matrix; When the minimum singular value of the power grid power transmission characteristic matrix is less than a preset threshold, perform continuous power flow tracking analysis on the power supply system based on the power grid power transmission characteristic matrix to obtain a system voltage stability margin curve, and perform critical point identification on the system voltage stability margin curve to obtain a power grid vulnerable area feature map; Optimize the power regulation plan for the power grid vulnerable area feature map through an AC power flow optimization analysis method to obtain a safe and stable power supply distribution plan, where the safe and stable power supply distribution plan includes an optimal power distribution strategy, dynamic reactive power compensation configuration, and voltage regulation control coefficients.

6. A computer device, comprising a memory and a processor, wherein a computer program is stored in the memory, characterized in that, When the processor executes the computer program, it implements the steps of the method described in any one of claims 1 to 4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 4.

Images