Power distribution method and system of intelligent power distribution cabinet, storage medium and equipment

Abstract

The invention provides a power distribution method and system of an intelligent power distribution cabinet, a storage medium and equipment, and relates to the technical field of food safety management. The method comprises the following steps: acquiring electric power parameters corresponding to each electric device, and extracting historical change characteristics of the electric power parameters; calculating a time sequence correlation coefficient between the power parameters, and constructing a feature correlation matrix according to the time sequence correlation coefficient; on the basis of the historical change features and the feature incidence matrix, predicting electric power prediction parameters corresponding to each electric device in a future preset time period; determining an abnormal electric power parameter and an abnormal electric equipment range correspondingly influenced by the abnormal electric power parameter based on the electric power prediction parameter; and generating a target power distribution strategy based on the abnormal power parameters and the abnormal electric equipment range. By implementing the technical scheme provided by the invention, the overall power distribution efficiency is improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent power distribution technology, and in particular to a power distribution method, system, storage medium and device for an intelligent power distribution cabinet. Background Art

[0002] With the rapid development of intelligent manufacturing, the power distribution system in industrial parks is becoming increasingly complex, and the power supply relationship between various types of power-consuming equipment is highly coupled. In actual applications, abnormal power parameters of a certain device may be transmitted through the power supply network, causing chain failures of other devices and resulting in large-scale shutdown of the entire production system.

[0003] At present, industrial parks usually use a monitoring method based on preset thresholds for power distribution management. This method mainly monitors the voltage, current and other power parameters of each power-consuming device in real time. When a parameter exceeds the preset threshold, the corresponding protection measures are triggered. For example, when it is detected that the current of a certain device exceeds the threshold, the power supply of the device is directly cut off. However, this processing method lacks flexibility and hysteresis, and it is difficult to detect potential abnormal risks in time, which makes it difficult to adjust the power distribution strategy in time, resulting in low power distribution efficiency. Summary of the invention

[0004] The present application provides a power distribution method, system, storage medium and device for an intelligent power distribution cabinet, which improves the overall power distribution efficiency.

[0005] In a first aspect, the present application provides a power distribution method of an intelligent power distribution cabinet, the method comprising: Collecting power parameters corresponding to each electrical device and extracting historical change characteristics of the power parameters; Calculating the time series correlation coefficient between each of the power parameters, and constructing a feature association matrix according to the time series correlation coefficient; Based on the historical change characteristics and the characteristic association matrix, predict the power prediction parameters corresponding to each of the electrical equipment within a preset time period in the future; Determine abnormal power parameters and the range of abnormal power-consuming equipment affected accordingly based on the power prediction parameters; A target power distribution strategy is generated based on the abnormal power parameter and the abnormal power-consuming equipment range.

[0006] By adopting the above technical solution, by collecting the power parameters of each electrical equipment and extracting its historical change characteristics, and combining the calculated time series correlation coefficients to construct a feature association matrix, it is possible to effectively capture the power coupling relationship between devices, and predict the power prediction parameters in the future preset time period based on the historical change characteristics and the feature association matrix, so that potential abnormal risks can be discovered in time. By determining the abnormal power parameters and their impact range, and generating the target distribution strategy accordingly, the distribution plan can be adjusted in advance, avoiding the passive response problem caused by the single reliance on preset thresholds in the traditional method. This solution analyzes the correlation and change rules between power parameters, establishes a complete processing link from parameter monitoring, abnormal prediction to strategy generation, improves the distribution system's ability to predict abnormal situations and processing flexibility, effectively reduces the probability of cascading failures, and improves the overall distribution efficiency.

[0007] In a second aspect of the present application, a power distribution system of an intelligent power distribution cabinet is provided, the system comprising: A feature extraction module is used to collect power parameters corresponding to each power-consuming device and extract historical change characteristics of the power parameters; A correlation calculation module, used to calculate the time series correlation coefficient between the power parameters, and construct a characteristic correlation matrix according to the time series correlation coefficient; A power prediction module, used to predict the power prediction parameters corresponding to each of the power-consuming devices within a preset time period in the future based on the historical change characteristics and the characteristic association matrix; An abnormal parameter determination module, used to determine abnormal power parameters and a corresponding range of abnormal power-consuming equipment affected based on the power prediction parameters; A power distribution strategy generation module is used to generate a target power distribution strategy based on the abnormal power parameters and the range of abnormal power-consuming equipment.

[0008] In a third aspect of the present application, a computer storage medium is provided, wherein the computer storage medium stores a plurality of instructions, wherein the instructions are suitable for being loaded by a processor and executing the above method steps.

[0009] In a fourth aspect of the present application, an electronic device is provided, comprising: a processor and a memory; wherein the memory stores a computer program, and the computer program is suitable for being loaded by the processor and executing the above-mentioned method steps.

[0010] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: This application collects the power parameters of each electrical device and extracts their historical change characteristics, and constructs a feature association matrix based on the calculated time series correlation coefficients. It can effectively capture the power coupling relationship between devices, and predict the power prediction parameters in the future preset time period based on the historical change characteristics and the feature association matrix. Potential abnormal risks can be discovered in time, and by determining the abnormal power parameters and their impact range, and generating the target distribution strategy based on them, the distribution plan can be adjusted in advance, avoiding the passive response problem caused by the single reliance on preset thresholds in traditional methods. This solution analyzes the correlation and change rules between power parameters, establishes a complete processing chain from parameter monitoring, abnormal prediction to strategy generation, improves the distribution system's ability to predict abnormal situations and processing flexibility, effectively reduces the probability of cascading failures, and improves the overall distribution efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 It is a flow chart of a power distribution method of an intelligent power distribution cabinet provided in an embodiment of the present application; Figure 2 It is a module schematic diagram of a power distribution system of an intelligent power distribution cabinet provided in an embodiment of the present application; Figure 3 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application.

[0012] Description of reference numerals: 300, electronic device; 301, processor; 302, communication bus; 303, user interface; 304, network interface; 305, memory. DETAILED DESCRIPTION

[0013] In order to enable technicians in this field to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0014] In the description of the embodiments of the present application, words such as "for example" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "for example" or "for example" is intended to present related concepts in a specific way.

[0015] In the description of the embodiments of the present application, the meaning of the term "multiple" refers to two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "include", "comprise", "have" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0016] The following will provide a clear and complete description of the technical solutions in the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments.

[0017] Please refer to Figure 1 , a flow chart of a power distribution method of an intelligent power distribution cabinet is proposed, the method can be implemented by a computer program, can be implemented by a single-chip microcomputer, and can also be run on a power distribution system of an intelligent power distribution cabinet, the computer program can be integrated in a computer device, and can also be run as an independent tool application. Specifically, the method includes steps 10 to 50, and the above steps are as follows: Step 10: Collect the power parameters corresponding to each power-consuming device and extract the historical change characteristics of the power parameters.

[0018] Among them, electrical equipment in the embodiment of the present application refers to various types of equipment that require power supply in an industrial production environment, including but not limited to production equipment (such as CNC machine tools, injection molding machines), power equipment (such as air compressors, water pumps), environmental control equipment (such as air conditioning, ventilation systems), etc.

[0019] In the embodiment of the present application, power parameters refer to various electrical quantities that reflect the operating status of electrical equipment, including but not limited to voltage value, current value, active power, reactive power, power factor, harmonic content, etc.

[0020] In the embodiment of the present application, the historical change characteristics refer to the changing patterns of power parameters in the past period of time, including but not limited to statistical characteristics such as the mean, standard deviation, maximum, minimum, fluctuation cycle, mutation point, and trend characteristics of the parameters changing over time.

[0021] Specifically, a power collection device is installed at the power supply end of each power-consuming device, and the power collection device includes a voltage sensor and a current sensor. The voltage value of the power-consuming device is collected in real time by the voltage sensor, and the current value of the power-consuming device is collected in real time by the current sensor, and the active power, reactive power and power factor are calculated according to the voltage value and the current value. The power collection device samples the power parameters at a preset sampling period (for example, 1 minute) and transmits the sampled data to the data processing unit. After obtaining the power parameters, it is necessary to extract its historical change characteristics in order to analyze the change law of the power parameters later. The power parameter sampling data of the past 30 days can be selected as the analysis sample. First, the original sampled data is preprocessed, including data filling, outlier removal and data normalization. Then, the mean, standard deviation, maximum value and minimum value of the processed power parameters in each sampling period are calculated to obtain the statistical characteristics of the parameters. Next, the sliding time window method is used to segment the power parameter sequence, and the window length is set to 24 hours. The parameter fluctuation period and mutation point position in each time window are calculated to obtain the periodic characteristics of the parameters. Finally, based on statistical features and periodic features, a historical change feature set containing multidimensional features is constructed.

[0022] Step 20: Calculate the time series correlation coefficients between the power parameters, and construct a feature correlation matrix based on the time series correlation coefficients.

[0023] Specifically, there are often complex inter-correlations between power parameters, and these correlations will affect the overall operating state of the distribution system. In order to accurately describe and quantify this correlation, it is necessary to calculate the time series correlation coefficient between power parameters and construct a feature correlation matrix. The fluctuation characteristics of each power parameter are extracted within a time window of a preset length (for example, 24 hours), including statistical characteristics such as the mean, standard deviation, and peak value of the parameters, which can reflect the change law of the parameters in the time dimension. Subsequently, the dynamic change information of the parameters is obtained by calculating the difference sequence of power parameters in adjacent time windows. Based on the difference sequence, the synchronous change coefficient between power parameters is calculated using statistical methods such as the Pearson correlation coefficient, which reflects the consistency of the change trends of different parameters. Furthermore, the time series correlation coefficient is calculated based on the synchronous change coefficient and the fluctuation characteristics, thereby quantifying the correlation strength between the parameters. After obtaining the time series correlation coefficient, in order to construct a more reasonable feature correlation matrix, the time series correlation coefficient is first normalized and mapped to the [0,1] interval to obtain the normalized coefficient. At the same time, the fluctuation amplitude of each power parameter is calculated. A larger fluctuation amplitude indicates that the parameter has a greater impact on the system, and the corresponding weight coefficient is determined accordingly. The normalization coefficient is combined with the weight coefficient to construct the initial correlation matrix. In order to improve the reliability of the correlation matrix, the correlation strength in the initial correlation matrix is ​​tested, and the correlation items with a correlation strength lower than a preset threshold (for example, 0.3) are eliminated, and finally the characteristic correlation matrix is ​​obtained.

[0024] Based on the above embodiment, as an optional embodiment, the step of calculating the time series correlation coefficient between the power parameters may further include the following steps: Step 2011: extracting the fluctuation characteristics of each power parameter within a time window of a preset length.

[0025] Specifically, a time window of preset length (for example, 4 hours) is selected as the basic analysis unit, and feature extraction is performed on power parameters such as voltage, current, and power in each time window. First, the sampled data of each power parameter is preprocessed, including removal of outliers and data smoothing to reduce the impact of random noise. Then, the statistical characteristics of the power parameters are calculated in each time window, including mean μ, standard deviation σ, peak factor Kp (ratio of maximum value to mean), waveform factor Kf (ratio of root mean square value to arithmetic mean), etc. These characteristic values ​​together constitute the fluctuation characteristic vector in the time window. In order to enhance the expressive power of the features, the rate of change and trend factor of the parameters are also introduced, where the rate of change is obtained by calculating the difference between adjacent sampling points, and the trend factor is characterized by the slope obtained by least squares fitting.

[0026] Step 2012: Calculate the difference sequence of power parameters in adjacent time windows.

[0027] Specifically, after obtaining the fluctuation characteristics of each time window, in order to analyze the dynamic change law of the power parameters, it is necessary to calculate the difference sequence between adjacent time windows, and divide the time axis into several continuous time windows according to the preset length, recorded as W1, W2,..., Wn. For each power parameter, the difference between each characteristic quantity between adjacent time windows is calculated. For example, for time windows Wi and Wi+1, the mean difference Δμi=μi+1-μi, the standard deviation difference Δσi=σi+1-σi, and the difference of other characteristic quantities are calculated. These differences constitute the difference sequence {Δμi, Δσi, ΔKpi, ΔKfi} that describes the dynamic change of the parameters. In order to improve the comparability of the difference sequence, the difference is standardized so that the difference of different types of characteristic quantities has the same dimension.

[0028] Step 2013: Calculate the synchronous variation coefficients between the power parameters based on the difference sequence.

[0029] Specifically, for any two power parameters A and B, their difference sequences in the continuous time window are first recorded as DA={ΔμA,ΔσA,ΔKpA,ΔKfA} and DB={ΔμB,ΔσB,ΔKpB,ΔKfB}. The improved Pearson correlation coefficient method is used to calculate the correlation of the two sets of difference sequences, that is, the synchronous change coefficient Sync(A,B). In the calculation process, the time decay weight function w(t)=e^(-λt) is introduced, where λ is the decay coefficient and t is the time distance, which can highlight the importance of recent data. The calculation formula of the synchronous change coefficient is: Sync(A,B)=Σ[w(t)·(DA(t)-μDA)(DB(t)-μDB)] / sqrt(Σ[w(t)·(DA(t)-μDA)²]·Σ[w(t)·(DB(t)-μDB)²]), where μDA and μDB are the weighted averages of the difference sequences DA and DB, respectively.

[0030] Step 2014: Calculate the time series correlation coefficient based on the synchronous variation coefficient and the fluctuation characteristics.

[0031] Specifically, after obtaining the synchronous variation coefficient, it is necessary to calculate the final time series correlation coefficient in combination with the fluctuation characteristics of the power parameters. The fluctuation characteristics reflect the inherent variation law of the parameters, while the synchronous variation coefficient characterizes the dynamic correlation between the parameters. The combination of the two can more comprehensively describe the relationship between the parameters. Set the fluctuation characteristic weight factor α (0<α<1), and record the fluctuation characteristic similarity as Sim(A,B), then the calculation formula of the time series correlation coefficient R(A,B) is: R(A,B)=α·Sim(A,B)+(1-α)·Sync(A,B). Among them, the fluctuation characteristic similarity Sim(A,B) is obtained by calculating the cosine similarity of the characteristic vectors of the two parameters in a single time window. In order to improve the stability of the calculation, the similarity of multiple continuous time windows is smoothed by sliding average.

[0032] Based on the above embodiment, as an optional embodiment, the step of constructing a feature correlation matrix according to the time series correlation coefficient may further include the following steps: Step 2021: normalize the time series correlation coefficient to obtain a normalized coefficient.

[0033] Specifically, since the time series correlation coefficients calculated between different power parameters may have differences in dimensions and scales, in order to make the correlation strengths between the parameters comparable, the time series correlation coefficients need to be normalized. For the time series correlation coefficient R(i,j) between any two power parameters i and j, the Min-Max normalization method is used, that is: N(i,j)=(R(i,j)-Rmin) / (Rmax - Rmin), where Rmax and Rmin are the maximum and minimum values ​​of all time series correlation coefficients, respectively. In order to avoid the influence of extreme values ​​on the normalization results, a saturation threshold mechanism is introduced. When R(i,j) exceeds the preset range, it is limited to a reasonable range. At the same time, in order to improve the robustness of normalization, a piecewise linear mapping method is adopted, and different mapping coefficients are used in different value intervals, so that the normalized coefficient distribution is more uniform and reasonable.

[0034] Step 2022: Calculate the fluctuation amplitude of each power parameter and determine the weight coefficient according to the fluctuation amplitude.

[0035] Specifically, while obtaining the normalization coefficient, it is necessary to evaluate the importance of each power parameter, which can be achieved by calculating the fluctuation amplitude of the parameter. For each power parameter, first extract its fluctuation feature sequence within a preset observation period (for example, 7 days), including the instantaneous fluctuation amplitude v(t), the root mean square value Vrms and the peak value Vpeak. The calculation of the fluctuation amplitude needs to consider the frequency characteristics of the parameter change, so the frequency domain analysis method is introduced to obtain the spectrum distribution of the parameter through the fast Fourier transform (FFT). Based on the spectrum analysis results, the comprehensive fluctuation amplitude A = β1·Vrms+β2·Vpeak+β3·Σ(ak·|Xk|) is calculated, where β1, β2, and β3 are combination coefficients, ak is the weight coefficient of different frequency components, and |Xk| is the corresponding frequency amplitude. According to the calculated fluctuation amplitude, the soft maximization (Softmax) function is used to determine the weight coefficient of each parameter: W(i)=exp(γ·A(i)) / Σexp(γ·A(j)), where γ is an adjustment factor used to control the concentration of weight distribution. In order to make the weight coefficients adaptable over time, a sliding time window update mechanism is used to regularly recalculate the fluctuation amplitude and weight coefficients. At the same time, a smoothing factor is introduced to perform exponential smoothing on the weight coefficients to avoid the impact of sudden changes in weights on the system.

[0036] Step 2023: Construct an initial correlation matrix based on the normalization coefficients and weight coefficients.

[0037] Specifically, in order to fully describe the correlation between power parameters, it is necessary to organically combine the normalization coefficient and the weight coefficient to construct an initial correlation matrix. Specifically, for n power parameters, an n×n initial correlation matrix M is constructed, where the matrix element M(i,j) represents the correlation strength between parameter i and parameter j. The initial correlation strength is calculated using a weighted combination method: M(i,j)=η·N(i,j)+(1-η)·[W(i)+W(j)] / 2, where η is a balancing factor (0<η<1), which is used to adjust the relative importance of the normalization coefficient N(i,j) and the weight coefficients W(i) and W(j). In order to ensure the symmetry of the correlation matrix, the calculated matrix elements are symmetric: M(i,j)=M(j,i)=[M(i,j)+M(j,i)] / 2. At the same time, in order to eliminate the influence of the parameters themselves, the matrix diagonal elements are set to 1.

[0038] Step 2024: Detect the correlation strength in the initial correlation matrix, and remove the correlation items whose correlation strength is lower than the correlation strength threshold to obtain a feature correlation matrix.

[0039] Specifically, after constructing the initial association matrix, the association strength needs to be detected and optimized to improve the reliability and practicality of the matrix. First, set the association strength threshold θ (for example, 0.3), which can be dynamically adjusted according to system characteristics and actual needs. For each non-diagonal element M (i, j) in the matrix, if its value is less than the threshold θ, it is considered that the association is weak, and the corresponding matrix element is set to 0, that is, the association item is removed. In order to avoid the possible information loss caused by simple threshold truncation, a fuzzy threshold mechanism is introduced, that is, a transition interval [θ-δ, θ+δ] is set near the threshold θ. For the association strength falling within this interval, a nonlinear attenuation function is used for smoothing according to its distance from the threshold.

[0040] After removing the weakly correlated items, in order to maintain the structural stability of the matrix, an association transitivity test is required. If there is a strong correlation between parameters i and j, and j and k, and the correlation between i and k is removed, the correlation between i and k needs to be re-evaluated. Introduce the association transit τ(i,j,k)=min[M(i,j), M(j,k)], when τ(i,j,k) is greater than the secondary threshold θ', retain the association between i and k, and update its association strength. In this way, important indirect associations can be avoided from being mistakenly removed. Finally, the optimized matrix is ​​normalized to obtain the final feature association matrix.

[0041] Step 30: Based on the historical change characteristics and the characteristic association matrix, predict the power prediction parameters corresponding to each electrical device within a preset time period in the future.

[0042] Specifically, in an optional embodiment, a time series prediction basic model can be constructed using an LSTM deep learning model, the model input includes the historical power parameter sequence and time characteristic information of each power-consuming device. On this basis, the characteristic association matrix M is introduced into the prediction process as an association constraint, that is, for any parameter pair (i, j), its predicted values ​​P(i) and P(j) need to satisfy the association strength constraint: |P(i)-P(j)| ≤ λ·(1-M(i,j)), where λ is the relaxation factor. By solving the constrained optimization problem, a prediction result that satisfies the association relationship is obtained. In order to improve the reliability of the prediction, a dynamic error compensation mechanism is introduced to correct the predicted value according to the statistical characteristics of the most recent prediction error. This method not only ensures the consistency of the prediction results with the historical change law, but also ensures the stability of the association relationship between parameters. Practice shows that the prediction error can be controlled within 5%, providing a reliable basis for the intelligent operation and maintenance of the distribution system.

[0043] Based on the above embodiment, as an optional embodiment, the step of predicting the power prediction parameters corresponding to each electrical device in a preset time period in the future based on the historical change characteristics and the characteristic association matrix may further include the following steps: Step 301: Divide the power parameters into a core parameter group and a subordinate parameter group according to the correlation strength in the feature correlation matrix.

[0044] Specifically, the power parameters are first grouped based on the characteristic association matrix, the association strength distribution of each parameter in the characteristic association matrix is ​​analyzed, and the association centrality index C(i)=ΣjM(i,j) of each parameter is calculated, where M(i,j) is an element in the association matrix. The association threshold ξ is set. When the association centrality C(i) of the parameter is greater than ξ, it is divided into a core parameter group, otherwise it is divided into a subordinate parameter group. This grouping method can identify key parameters with strong influence in the system, which helps to reduce the complexity of the prediction problem.

[0045] Step 302: Calculate the independent prediction value of the core parameter group based on the time series prediction model constructed based on the historical change characteristics of the core parameter group.

[0046] Specifically, for the core parameter group, considering that its parameter changes have strong independence, a deep learning model is used for independent prediction, and a multi-layer LSTM network is constructed as a time series prediction model. The input layer contains historical data sequences and auxiliary features (such as time tags, environmental factors, etc.). Time series features are extracted through multiple LSTM layers, and finally the prediction output is obtained through the fully connected layer. In order to improve the generalization ability of the model, the dropout mechanism and L2 regularization are introduced during the training process. The loss function of the model uses an improved Huber loss, which can handle both small and large errors. Through this model, the independent prediction value VP of the core parameter group can be obtained.

[0047] Step 303: Establish an association mapping model according to the association relationship between the core parameter group and the subordinate parameter group in the feature association matrix.

[0048] Specifically, the correlation submatrix Ms between the core parameter group and the subordinate parameter group is extracted from the feature correlation matrix, and the element Ms(i,j) of the submatrix represents the correlation strength between the core parameter i and the subordinate parameter j. Based on the correlation submatrix, a nonlinear mapping function f(x)=Σ[wk·φ(||x-ck||)] is constructed, where wk is the weight coefficient, ck is the center point of the basis function, and φ(·) is the radial basis function. The parameters of the mapping function are optimized through training data so that it can accurately describe the conversion relationship between the parameters.

[0049] Step 304: Calculate the association prediction value of the dependent parameter group based on the association mapping model and the independent prediction value of the core parameter group.

[0050] Specifically, after obtaining the association mapping model, the independent prediction value VP of the core parameter group is used as input, and the associated prediction value VR=f(VP) of the subordinate parameter group is calculated through the mapping function. In order to improve the prediction reliability, an error feedback mechanism is introduced to dynamically correct the mapping result according to the historical prediction error. This association mapping model not only reduces the computational complexity, but also improves the rationality of the prediction result through the association constraints between parameters, providing reliable technical support for the state prediction of the distribution system. Through this hierarchical prediction method based on association relationship, the accuracy of the prediction is guaranteed and the execution efficiency of the algorithm is improved.

[0051] Step 305: Combining the independent prediction value and the associated prediction value by weighted fusion to generate power prediction parameters for each electrical device.

[0052] Specifically, in order to obtain the complete power prediction parameters of each power-consuming device, a fusion calculation method is used to generate the final prediction results. For each power-consuming device, its power prediction parameters include key indicators such as active power, reactive power, voltage and current. The predicted values ​​of these parameters are calculated separately by weighted fusion: for the parameters in the core parameter group (such as active power P and voltage V), their predicted values ​​are equal to the weighted sum of the independent prediction value VP and the associated prediction value VR, that is, P=α·VP+(1-α)·VR; for the parameters in the subordinate parameter group (such as reactive power Q and current I), their predicted values ​​mainly depend on the associated prediction values, that is, they are calculated based on the predicted values ​​of the core parameters through the association mapping model. The final generated power prediction parameter set is {P,Q,V,I}, where each parameter contains the time series value within the preset time period. For example, if the preset time period is the next 24 hours, each parameter will contain 96 prediction point values ​​at intervals of 15 minutes.

[0053] Step 40: Determine abnormal power parameters and the corresponding range of abnormal power-consuming equipment affected based on the power prediction parameters.

[0054] Specifically, it is necessary to first establish a topological relationship diagram that reflects the power supply relationship between electrical devices, and then compare the power prediction parameters with the preset normal operating range to determine the abnormal power parameters that exceed the corresponding normal operating range. Then, based on the electrical devices affected by the abnormal power parameters, the corresponding range of abnormal electrical devices can be determined.

[0055] Based on the above embodiment, as an optional embodiment, the step of determining the abnormal power parameters and the corresponding affected abnormal power equipment range based on the power prediction parameters may further include the following steps: Step 401: Establish a power supply topology diagram between various power-consuming devices.

[0056] Specifically, the electrical equipment in the power distribution system is represented as nodes in the graph, and the power supply connection relationship between the equipment is represented as directed edges to construct a directed graph G(V, E). Each node vi ∈ V contains the basic attribute information of the equipment, such as equipment type, rated capacity, etc.; each edge eij ∈ E represents the power supply path from equipment i to equipment j and records its key characteristic parameters, such as line impedance, rated current, etc.

[0057] Step 402: Compare the power prediction parameters with the preset normal operation range to determine abnormal power parameters.

[0058] Specifically, based on the established topological relationship graph, compare the power prediction parameters with the preset normal operation range. For the power prediction parameter set {P, Q, V, I} of each equipment, set its normal operation range as [Pmin, Pmax], [Qmin, Qmax], [Vmin, Vmax], [Imin, Imax]. When the predicted value of any parameter exceeds the corresponding normal operation range, mark it as an abnormal power parameter. For example, when the predicted voltage V < Vmin or V > Vmax, determine that the voltage parameter is abnormal.

[0059] Step 403: Identify the associated equipment that has a power supply connection with the equipment corresponding to the abnormal power parameter according to the power supply topological relationship graph.

[0060] Specifically, after determining the abnormal parameters, analyze the abnormal propagation path through the topological relationship graph. Assume that the abnormal equipment node is va, and use the graph traversal algorithm to identify the set of associated equipment Ra that has a power supply connection with va. The breadth-first search algorithm can be used to traverse the graph G starting from va to identify all reachable nodes. For each associated node vi ∈ Ra, calculate its electrical distance dia from the abnormal node va, and this distance value reflects the attenuation degree of the abnormal influence. According to the power supply hierarchy relationship of the associated equipment, further divide Ra into the upstream equipment set Ru (power supply equipment) and the downstream equipment set Rd (power receiving equipment), and analyze the influence characteristics of the abnormality on the upstream and downstream equipment respectively.

[0061] Step 404: Calculate the power parameter deviation value of the associated equipment. The power parameter deviation value is the deviation degree of the power parameter of the associated equipment from the corresponding preset standard value.

[0062] Specifically, for each associated device vi, the normalized offset value of its power parameters {P, Q, V, I} relative to the preset standard value {Ps, Qs, Vs, Is} is calculated. The offset value is calculated using the weighted Euclidean distance method: Di=sqrt(wp(P-Ps)² / Ps²+wq(Q-Qs)² / Qs²+wv(V-Vs)² / Vs²+wi(I-Is)² / Is²), where wp, wq, wv, wi are the weight coefficients of each parameter, reflecting the importance of different parameters on the operating status of the device.

[0063] Step 405: Filter out the electrical equipment combinations whose power parameter offset values ​​are greater than the offset threshold as the abnormal electrical equipment range.

[0064] Specifically, based on the calculated offset value, an adaptive offset threshold η is set to screen abnormal devices. The determination of the threshold η comprehensively considers the system operation requirements and historical statistical characteristics: η=μd+k·σd, where μd and σd are the mean and standard deviation of the historical offset values, respectively, and k is the safety factor. When the offset value Di of the device is greater than η, it is included in the range of abnormal power-consuming devices. For key devices close to the abnormal source, the threshold is appropriately lowered to improve the monitoring sensitivity.

[0065] Step 50: Generate a target power distribution strategy based on the abnormal power parameters and the range of abnormal power-consuming equipment.

[0066] Specifically, a multi-objective optimization model is first constructed, and the optimization objectives are set to include: minimizing the impact range of abnormalities, maximizing power supply reliability, and minimizing energy loss. The optimization variables include the state of each switch device {Si}, the operating parameters of the adjustable equipment {Pi, Qi}, and the load distribution plan {Li}. Based on the current state of the system, a hierarchical decision-making method is used to generate a power distribution strategy. For example, at the first level, an emergency state assessment is performed, and the abnormal scenarios are classified into three types: immediate removal, load transfer, and parameter adjustment according to the type and severity of abnormal power parameters. For each type, a corresponding disposal strategy template is designed, including equipment disconnection sequence, load transfer path, and parameter adjustment plan. At the second level, the details of the adjustment strategy are optimized in combination with the scope of abnormal power equipment. For example, for scenarios that require load transfer, a feasible transfer path is determined by power flow calculation: first, the backup power capacity {Ci} in the target area is identified, and then the optimal load distribution plan is calculated based on the principle of minimum path loss. The transfer plan must meet the constraints: ∑Li≤Ci (capacity constraint) and all node voltages meet Vmin≤Vi≤Vmax (voltage constraint).

[0067] Based on the above embodiment, as an optional embodiment, the step of generating a target power distribution strategy based on abnormal power parameters and the range of abnormal power-consuming equipment may further include the following steps: Step 501: Divide the anomaly level according to the deviation degree of the abnormal power parameters.

[0068] Specifically, based on the deviation degree D between the abnormal power parameter and the preset standard value, calculate the anomaly level L. The deviation degree is calculated using the normalization method: D = |X - Xs| / Xs, where X is the actual value of the abnormal parameter and Xs is the standard value. According to the size of the deviation degree, the anomaly level is divided into three levels: when D≤20%, it is a mild anomaly (L = 1); when 20%<D≤50%, it is a moderate anomaly (L = 2); when D>50%, it is a severe anomaly (L = 3).

[0069] Step 502: Determine the voltage regulation amplitude and current limit threshold based on the anomaly level.

[0070] Specifically, based on the determined anomaly level L, calculate the corresponding voltage regulation amplitude ΔV and current limit threshold Imax. The calculation formula for the voltage regulation amplitude is: ΔV =α·L·Vn, where α is the regulation coefficient (the value range is 0.02 - 0.05) and Vn is the rated voltage; the calculation formula for the current limit threshold is: Imax=(1-β·L)·In, where β is the limit coefficient (the value range is 0.1 - 0.2) and In is the rated current. This method of determining parameters based on the anomaly level can achieve an accurate match between the regulation intensity and the anomaly degree.

[0071] Step 503: Calculate the power distribution ratio of each abnormal electrical equipment within the range of abnormal electrical equipment, and generate the equipment start-stop time sequence according to the power distribution ratio.

[0072] Specifically, for the power distribution within the range of abnormal electrical equipment, a weighted distribution method based on equipment importance and electrical characteristics is adopted. First, calculate the weight coefficient wi of each device: wi =ki·pi·ri, where ki is the importance coefficient, pi is the load characteristic coefficient, and ri is the operating state coefficient. Then calculate the power distribution ratio γi: γi =wi / ∑wi. Determine the start-stop order of the equipment according to the distribution ratio: sort the equipment from large to small according to γi to generate the start sequence {S1, S2,...,Sn}, where the start time interval Δt between adjacent devices = f(γi), and f(γi) is a time mapping function based on the power ratio.

[0073] Step 504: Generate a target power distribution strategy based on the voltage regulation amplitude, current limit threshold, and equipment start-stop time sequence.

[0074] Specifically, in order to achieve coordinated control of multiple devices and ensure stable operation of the system, it is necessary to generate a scientific and reasonable target power distribution strategy based on the voltage regulation amplitude, current limit threshold and equipment start-stop sequence. First, according to the start-up time interval of the equipment in the equipment start-stop sequence, the power-consuming equipment with the same or similar start-up time is combined into a group of equipment running simultaneously. A time clustering threshold is set. When the start-up time difference of the equipment is less than the time clustering threshold, these equipment are divided into the same running equipment group, thereby forming an equipment group set.

[0075] For each group of equipment running simultaneously, calculate its total power demand P Ti The calculation method is: P Ti =∑P j +ΔP i , where P j is the rated power of the jth device in the group, ΔP i It is the power margin considering the start-up impact and load fluctuation. Power margin ΔP i The determination of needs to consider the equipment type and operating characteristics, usually the value is: ΔPi = max{λ·∑Pj, P max}, where λ is the margin factor (0.1-0.2), P max The starting power of the largest device in the group. Based on the voltage regulation amplitude ΔV and the current limit threshold I max , determine the operating constraints for each group of equipment running simultaneously. The constraints include: voltage constraint V i ∈[V nom -ΔV, V nom +ΔV], current constraint I i ≤I max , power constraint P i ≤P Ti At the same time, considering the mutual influence between devices, the coupling constraint is introduced: ΔV ij ≤εv (voltage mutual influence limit between devices), ΔI ij ≤εi (the limit of the mutual influence of current between devices). These constraints together constitute the operation constraint set C i .

[0076] Under the premise of satisfying the operating constraints, the optimization algorithm is used to generate the power allocation plan for each equipment group. The optimization objectives include: minimizing the total energy consumption min(∑Pi), minimizing the voltage fluctuation min(max|ΔVi|), and maximizing the load balance max(min(γi)). By solving the multi-objective optimization problem, the optimal power allocation plan Mi ={P i1 , P i2 , ..., P ij}, where P ijRepresents the allocated power of the jth device in the group. Finally, the power allocation plan is converted into specific collaborative control instructions. For each device group Gi, a control instruction set Ci = {ci1, ci2, ..., cik} is generated. Each instruction contains: device identification ID, target operating status, operating parameters (including power setting value, voltage adjustment value, start time, etc.). The control instructions of all device groups are integrated in time sequence to form a complete target power distribution strategy S = {C1, C2, ..., Cm}. The strategy also includes inter-group switching conditions and exception handling mechanisms to ensure the continuity and reliability of strategy execution.

[0077] The power distribution strategy achieves collaborative control of multiple devices through reasonable division of equipment groups, accurate power demand calculation, comprehensive constraint setting and optimized power allocation scheme. The group execution mechanism of the strategy reduces system impact and improves operational stability; comprehensive consideration of constraints ensures system safety; optimized power allocation improves energy efficiency; and the standardized encapsulation of collaborative control instructions facilitates the execution and management of the strategy.

[0078] See also Figure 2 , is a schematic diagram of a module of a power distribution system of an intelligent power distribution cabinet provided in an embodiment of the present application. The power distribution system of the intelligent power distribution cabinet may include: a feature extraction module, a correlation calculation module, a power prediction module, an abnormal parameter determination module and a power distribution strategy generation module, wherein: A feature extraction module is used to collect power parameters corresponding to each power-consuming device and extract historical change characteristics of the power parameters; A correlation calculation module, used to calculate the time series correlation coefficient between the power parameters, and construct a characteristic correlation matrix according to the time series correlation coefficient; A power prediction module, used to predict the power prediction parameters corresponding to each of the power-consuming devices within a preset time period in the future based on the historical change characteristics and the characteristic association matrix; An abnormal parameter determination module, used to determine abnormal power parameters and a corresponding range of abnormal power-consuming equipment affected based on the power prediction parameters; A power distribution strategy generation module is used to generate a target power distribution strategy based on the abnormal power parameters and the range of abnormal power-consuming equipment.

[0079] Optionally, the correlation calculation module is further used to extract the fluctuation characteristics of each of the power parameters within a time window of a preset length; Calculate the difference sequence of power parameters in adjacent time windows; Calculating synchronous variation coefficients between power parameters based on the difference sequence; The time series correlation coefficient is calculated according to the synchronous variation coefficient and the fluctuation characteristics.

[0080] Optionally, the correlation calculation module is further used to perform normalization processing on the time series correlation coefficient to obtain a normalized coefficient; Calculating the fluctuation amplitude of each of the power parameters, and determining a weight coefficient according to the fluctuation amplitude; constructing an initial correlation matrix based on the normalization coefficients and the weight coefficients; The correlation strength in the initial correlation matrix is ​​detected, and correlation items with correlation strength lower than a correlation strength threshold are eliminated to obtain a characteristic correlation matrix.

[0081] Optionally, the power prediction module is further used to divide the power parameters into a core parameter group and a subordinate parameter group according to the correlation strength in the feature correlation matrix; A time series prediction model constructed based on the historical change characteristics of the core parameter group is used to calculate the independent prediction value of the core parameter group; Establishing an association mapping model according to the association relationship between the core parameter group and the subordinate parameter group in the feature association matrix; Calculating the association prediction value of the dependent parameter group based on the association mapping model and the independent prediction value of the core parameter group; The independent prediction value and the associated prediction value are combined in a weighted fusion manner to generate power prediction parameters for each electrical device.

[0082] Optionally, the abnormal parameter determination module is further used to establish a power supply topology relationship diagram between the power-consuming devices; Comparing the power prediction parameters with the preset normal operating range to determine abnormal power parameters; Identify, according to the power supply topology diagram, an associated device that is connected to the device corresponding to the abnormal power parameter; Calculate the power parameter offset value of the associated device, where the power parameter offset value is the degree of deviation between the power parameter of the associated device and the corresponding preset standard value; The power-consuming equipment combinations whose power parameter offset values ​​are greater than the offset threshold are screened out as the abnormal power-consuming equipment range.

[0083] Optionally, the power distribution strategy generation module is further used to classify abnormal levels according to the degree of deviation of the abnormal power parameters; determining a voltage regulation amplitude and a current limit threshold based on the abnormality level; Calculating the power allocation ratio of each abnormal power-consuming device within the range of the abnormal power-consuming device, and generating a start-stop timing sequence of the device according to the power allocation ratio; A target power distribution strategy is generated based on the voltage regulation amplitude, the current limit threshold and the device start and stop timing.

[0084] Optionally, the power distribution strategy generation module is further used to divide the power-consuming devices into simultaneously running device groups according to the device start and stop timing sequence; Calculating the total power requirements of each of the simultaneously operating equipment groups; Determining the operation constraint conditions of each of the simultaneously operating device groups based on the voltage regulation amplitude and the current limit threshold; generating a power allocation scheme that satisfies the operating constraints; A collaborative control instruction is generated according to the power allocation scheme of the equipment group, and the collaborative control instructions are combined into a target power distribution strategy.

[0085] It should be noted that: when the system provided in the above embodiment realizes its functions, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the system and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0086] An embodiment of the present application also provides a computer storage medium, which can store multiple instructions. The instructions are suitable for being loaded by a processor and executing a power distribution method of an intelligent distribution cabinet in the above embodiment. The specific execution process can be found in the specific description of the above embodiment, which will not be repeated here.

[0087] Please refer to Figure 3 The application also discloses an electronic device. Figure 3 The electronic device 300 may include: at least one processor 301 , at least one network interface 304 , a user interface 303 , a memory 305 , and at least one communication bus 302 .

[0088] The communication bus 302 is used to realize the connection and communication between these components.

[0089] The user interface 303 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 303 may also include a standard wired interface and a wireless interface.

[0090] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0091] Among them, the processor 301 may include one or more processing cores. The processor 301 uses various interfaces and lines to connect various parts in the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 305, and calling data stored in the memory 305. Optionally, the processor 301 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 301 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 301, and it can be implemented separately through a chip.

[0092] Among them, the memory 305 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 305 may optionally also be at least one storage device located away from the aforementioned processor 301. Refer to Figure 3 , the memory 305 as a computer storage medium may include an operating system, a network communication module, a user interface module and an application program of a power distribution method of an intelligent power distribution cabinet.

[0093] exist Figure 3In the electronic device 300 shown, the user interface 303 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 301 can be used to call the application program of a power distribution method of an intelligent power distribution cabinet stored in the memory 305. When executed by one or more processors 301, the electronic device 300 executes one or more of the methods described in the above embodiments. It should be noted that for the aforementioned method embodiments, for the sake of simple description, they are all expressed as a series of action combinations, but those skilled in the art should know that the present application is not limited to the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application.

[0094] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0095] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0096] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0097] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0098] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: various media that can store program codes, such as USB flash drives, mobile hard drives, magnetic disks or optical disks.

[0099] The above is only an exemplary embodiment of the present disclosure and cannot be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the disclosure of the specification and the truth of practice, those skilled in the art will easily think of other embodiments of the present disclosure.

[0100] This application is intended to cover any variation, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the art not described in the present disclosure. The description and examples are to be regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A power distribution method for an intelligent power distribution cabinet, characterized in that: The method comprises: Collecting power parameters corresponding to each electrical device and extracting historical change characteristics of the power parameters; Calculating the time series correlation coefficient between each of the power parameters, and constructing a feature association matrix according to the time series correlation coefficient; Based on the historical change characteristics and the characteristic association matrix, predict the power prediction parameters corresponding to each of the electrical equipment within a preset time period in the future; Determine abnormal power parameters and the range of abnormal power-consuming equipment affected accordingly based on the power prediction parameters; A target power distribution strategy is generated based on the abnormal power parameter and the abnormal power-consuming equipment range.

2. The power distribution method of the intelligent power distribution cabinet according to claim 1, characterized in that: The calculating of the time series correlation coefficient between the power parameters comprises: Extracting the fluctuation characteristics of each of the power parameters within a time window of a preset length; Calculate the difference sequence of power parameters in adjacent time windows; Calculating synchronous variation coefficients between power parameters based on the difference sequence; A time series correlation coefficient is calculated according to the synchronous variation coefficient and the fluctuation characteristic.

3. The power distribution method of the intelligent power distribution cabinet according to claim 1, characterized in that: The step of constructing a feature association matrix according to the time series correlation coefficient includes: Normalizing the time series correlation coefficient to obtain a normalized coefficient; Calculating the fluctuation amplitude of each of the power parameters, and determining a weight coefficient according to the fluctuation amplitude; constructing an initial correlation matrix based on the normalization coefficients and the weight coefficients; The correlation strength in the initial correlation matrix is ​​detected, and correlation items with correlation strength lower than a correlation strength threshold are eliminated to obtain a characteristic correlation matrix.

4. The power distribution method of the intelligent power distribution cabinet according to claim 1, characterized in that: The predicting of the power prediction parameters corresponding to each of the electrical equipment within a preset time period in the future based on the historical change characteristics and the characteristic association matrix includes: Dividing the power parameters into a core parameter group and a subordinate parameter group according to the correlation strength in the characteristic correlation matrix; A time series prediction model constructed based on the historical change characteristics of the core parameter group is used to calculate the independent prediction value of the core parameter group; Establishing an association mapping model according to the association relationship between the core parameter group and the subordinate parameter group in the feature association matrix; Calculating the association prediction value of the dependent parameter group based on the association mapping model and the independent prediction value of the core parameter group; The independent prediction value and the associated prediction value are combined in a weighted fusion manner to generate power prediction parameters for each electrical device.

5. The power distribution method of the intelligent power distribution cabinet according to claim 1, characterized in that: The determining of abnormal power parameters and a corresponding range of abnormal power-consuming equipment affected based on the power prediction parameters includes: Establishing a power supply topology relationship diagram between the power-consuming devices; Comparing the power prediction parameters with the preset normal operating range to determine abnormal power parameters; Identify, according to the power supply topology diagram, an associated device that is connected to the device corresponding to the abnormal power parameter; Calculate the power parameter offset value of the associated device, where the power parameter offset value is the degree of deviation between the power parameter of the associated device and the corresponding preset standard value; The power-consuming equipment combinations whose power parameter offset values ​​are greater than the offset threshold are screened out as the abnormal power-consuming equipment range.

6. The power distribution method of the intelligent power distribution cabinet according to claim 1, characterized in that: The generating a target power distribution strategy based on the abnormal power parameter and the abnormal power-consuming equipment range includes: Classifying abnormality levels according to the degree of deviation of the abnormal power parameters; determining a voltage regulation amplitude and a current limit threshold based on the abnormality level; Calculating the power allocation ratio of each abnormal power-consuming device within the range of the abnormal power-consuming device, and generating a start-stop timing sequence of the device according to the power allocation ratio; A target power distribution strategy is generated based on the voltage regulation amplitude, the current limit threshold and the device start and stop timing.

7. The power distribution method of the intelligent power distribution cabinet according to claim 6, characterized in that: The generating a target power distribution strategy based on the voltage regulation amplitude, the current limit threshold and the device start-stop timing includes: Dividing the electrical equipment into groups of equipment running simultaneously according to the start and stop sequence of the equipment; Calculating the total power requirements of each of the simultaneously operating equipment groups; Determining the operation constraint conditions of each of the simultaneously operating device groups based on the voltage regulation amplitude and the current limit threshold; generating a power allocation scheme that satisfies the operating constraints; A collaborative control instruction is generated according to the power allocation scheme of the equipment group, and the collaborative control instructions are combined into a target power distribution strategy.

8. A power distribution system of an intelligent power distribution cabinet, characterized in that: The system comprises: A feature extraction module is used to collect power parameters corresponding to each power-consuming device and extract historical change characteristics of the power parameters; A correlation calculation module, used to calculate the time series correlation coefficient between the power parameters, and construct a characteristic correlation matrix according to the time series correlation coefficient; A power prediction module, used to predict the power prediction parameters corresponding to each of the power-consuming devices within a preset time period in the future based on the historical change characteristics and the characteristic association matrix; An abnormal parameter determination module, used to determine abnormal power parameters and a corresponding range of abnormal power-consuming equipment affected based on the power prediction parameters; A power distribution strategy generation module is used to generate a target power distribution strategy based on the abnormal power parameters and the range of abnormal power-consuming equipment.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the method according to any one of claims 1 to 7.

10. An electronic device, characterized in that: It includes a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes the method as described in any one of claims 1-7.

Images