A power situation awareness and prediction method and system for a distribution network

Abstract

The present invention relates to the field of artificial intelligence technology, and discloses a power situation awareness prediction method and prediction system for a distribution network, including: calculating multi-dimensional power data of each node in the distribution network according to electrical data; extracting multi-dimensional power features corresponding to the multi-dimensional power data, and analyzing the power operation state of the distribution network through the multi-dimensional power features; using a time series model to perform situation awareness on the power time series to obtain a situation prediction value of the distribution network; updating the power time series within a moving time window, determining a power situation trigger condition according to the updated power time series, and updating the model parameters in the time series model according to the power situation trigger condition; using the updated time series model to optimize the situation prediction value, and analyzing the power situation awareness of the distribution network by using the situation optimization value to obtain a power situation awareness prediction result. The present invention can improve the accuracy of power situation awareness prediction for a distribution network.

Description

Technical Field

[0001] The present invention relates to the technical field of artificial intelligence, and particularly to a method and a system for predicting the power situation awareness of a distribution network. Background Art

[0002] With the development of social economy, the types of loads connected to the distribution network are becoming increasingly diverse. In addition to traditional residential, commercial, and industrial loads, a large number of new loads such as electric vehicle charging piles and distributed energy sources have emerged. The electrical consumption characteristics of these loads are complex and affected by various factors such as residential electricity consumption habits, weather changes, and economic activities, resulting in a significant increase in the uncertainty of the load, which brings great challenges to the power prediction and operation management of the distribution network.

[0003] The existing power situation awareness prediction technology for the distribution network analyzes historical power data to establish a time series model to predict future power values. In practical applications, it is assumed that the power data is stationary, which has poor adaptability to the complex and changeable power characteristics of modern distribution networks and is difficult to accurately capture the sudden changes and non-linear changes of power, resulting in low accuracy in predicting the power situation awareness of the distribution network. Summary of the Invention

[0004] The present invention provides a method and a system for predicting the power situation awareness of a distribution network, and its main purpose is to solve the problem of low accuracy in product recommendation.

[0005] To achieve the above object, a method for predicting the power situation awareness of a distribution network provided by the present invention includes:

[0006] Collect the electrical data corresponding to each node in the distribution network, and calculate the multi-dimensional power data of each node in the distribution network according to the electrical data;

[0007] Extract the multi-dimensional power features corresponding to the multi-dimensional power data, and analyze the power operation state of the distribution network through the multi-dimensional power features;

[0008] Construct a power time series of the distribution network according to the power operation state, and use a pre-constructed time series model to perform situation awareness on the power time series to obtain a situation prediction value of the distribution network;

[0009] Update the power time series within a preset moving time window, determine the power situation trigger condition according to the updated power time series, and update the model parameters in the time series model according to the power situation trigger condition;

[0010] Optimize the situation prediction value by using the updated time series model to obtain a situation optimization value, and analyze the power situation awareness of the distribution network by using the situation optimization value to obtain a power situation awareness prediction result.

[0011] Optionally, extracting the multi-dimensional power features corresponding to the multi-dimensional power data includes:

[0012] Dividing the multi-dimensional power data of each node into power data sets according to the same dimension;

[0013] Extracting the time-domain features and frequency-domain features in the power data sets;

[0014] Converting the power data sets into sequence sets and extracting the sequence pattern features of the sequence sets;

[0015] Collecting the time-domain features, the frequency-domain features and the sequence pattern features as multi-dimensional power features.

[0016] Optionally, analyzing the power operation state of the distribution network by the multi-dimensional power features includes:

[0017] Constructing an operation state matrix according to the power feature dimension in the multi-dimensional power features and the power operation state dimension of the pre-acquired distribution network;

[0018] Determining the power operation state value of the distribution network through the multi-dimensional power features and the pre-acquired multi-dimensional power historical features;

[0019] Filling the operation state matrix according to the power operation state value;

[0020] Calculating the power operation state quantization value of the distribution network by using the filled operation state matrix, where the calculation formula of the power operation state quantization value is:

[0021] ;

[0022] Wherein, is the power operation state quantization value, is the state standard value, is the matrix value of the th row and the th column in the operation state matrix, is the row dimension in the operation state matrix, is the column dimension in the operation state matrix, is the number of nodes in the distribution network, is the node serial number in the distribution network;

[0023] Determining the power operation state of the distribution network according to the power operation state quantization value.

[0024] Optionally, constructing the power time series of the distribution network according to the power operation state includes:

[0025] Extract the running time points corresponding to the power running states;

[0026] Map the running time points and the power running states to obtain a mapping sequence;

[0027] Convert the mapping sequence into a power time series of the distribution network.

[0028] Optionally, the using a pre - constructed time series model to perform situation awareness on the power time series to obtain a situation prediction value of the distribution network includes:

[0029] Convert the power time series into model sequence input data;

[0030] Extract the model parameters of the pre - constructed time series model;

[0031] Initialize the hidden state and cell state of the time series model;

[0032] Use the initialized time series model and the model parameters to calculate the target hidden state corresponding to the model sequence input data;

[0033] Determine the output data according to the target hidden state, and perform a linear transformation on the output data to obtain a situation prediction value of the distribution network.

[0034] Optionally, the determining the power situation trigger condition of the distribution network according to the updated power time series includes:

[0035] Detect the mutation factors in the updated power time series;

[0036] Determine the trigger factors of the distribution network according to the mutation factors;

[0037] Generate the power situation trigger condition of the distribution network through the trigger factors.

[0038] Optionally, the updating the model parameters in the time series model according to the power situation trigger condition includes:

[0039] Collect power sequence data within a preset time period according to the power situation trigger condition;

[0040] Extract the data change degree and data change direction in the power sequence data;

[0041] Determine the adjustment factor according to the data change degree and the data change direction;

[0042] Update the learning rate in the time series model through the adjustment factor, where the learning rate update formula is:

[0043] ;

[0044] Among them, is the learning rate of the th iteration, is the minimum value of the learning rate, is the maximum value of the learning rate, is the current iteration number, is the total number of iterations within a period, is a constant, is the cosine function, is the said adjustment factor;

[0045] Determine the updated model parameters in the time series model through the said learning rate.

[0046] Optionally, the optimizing the situation prediction value by using the updated time series model to obtain a situation optimization value includes:

[0047] Performing situation awareness on the power time series by using the updated time series model to obtain an updated situation prediction value of the distribution network;

[0048] Calculating the error value between the updated situation prediction value and the situation prediction value;

[0049] When the error value is less than or equal to a preset error threshold, taking the situation prediction value as the situation optimization value;

[0050] When the error value is greater than the preset error threshold, taking the updated situation prediction value as the situation optimization value.

[0051] Optionally, the analyzing the power situation awareness of the distribution network by using the situation optimization value to obtain a power situation awareness prediction result includes:

[0052] Extracting the target power situation value at the target moment;

[0053] Comparing the situation optimization value with the target power situation value to obtain a comparison result;

[0054] Determining the perception level of the power situation awareness of the distribution network according to the comparison result;

[0055] Determining the power situation awareness prediction result through the perception level.

[0056] To solve the above problems, the present invention also provides a distribution network power situation awareness prediction system, and the system includes:

[0057] A multi-dimensional power data calculation module, configured to collect electrical data corresponding to each node in the distribution network and calculate the multi-dimensional power data of each node in the distribution network according to the electrical data;

[0058] A power operation state analysis module, configured to extract multi-dimensional power features corresponding to the multi-dimensional power data, and analyze the power operation state of the distribution network through the multi-dimensional power features;

[0059] A situation prediction value analysis module, configured to construct a power time series of the distribution network according to the power operation state, and perform situation awareness on the power time series by using a pre-constructed time series model to obtain a situation prediction value of the distribution network;

[0060] A model parameter update module, configured to update the power time series within a preset moving time window, determine a power situation trigger condition of the distribution network according to the updated power time series, and update model parameters in the time series model according to the power situation trigger condition;

[0061] A power situation awareness analysis module, configured to optimize the situation prediction value by using the updated time series model to obtain a situation optimization value, and analyze the power situation awareness of the distribution network by using the situation optimization value to obtain a power situation awareness prediction result.

[0062] In the embodiment of the present invention, electrical data of each node is collected and multi-dimensional power data is calculated, which can comprehensively cover different aspects of the power of the distribution network; a power time series is constructed based on the power operation state, and situation awareness is performed by using a pre-constructed time series model, which can effectively capture the change rules and trends of power over time; the power time series is updated within a preset moving time window, so that the system can track the latest changes in the power of the distribution network in real time. Determining the power situation trigger condition according to the updated time series can timely capture abnormal fluctuations or mutations of the power; updating the parameters of the time series model based on the power situation trigger condition enables the model to dynamically adjust itself according to the real-time operation state of the distribution network and always maintain the accurate prediction ability for the power situation; using the updated time series model to optimize the situation prediction value, and by comparing the prediction values before and after the update with the actual power situation value, a better situation optimization value is selected, effectively correcting the prediction deviation, improving the matching degree between the prediction value and the actual power situation, and making the prediction result more accurate and reliable. Therefore, the distribution network power situation awareness prediction method and prediction system proposed by the present invention can solve the problem of low accuracy in product recommendation. Description of the Drawings

[0063] Figure 1 It is a schematic flowchart of a distribution network power situation awareness prediction method provided by an embodiment of the present invention;

[0064] Figure 2 It is a schematic flowchart of extracting multi-dimensional power features provided by an embodiment of the present invention;

[0065] Figure 3 A schematic flowchart of constructing a power time series provided by an embodiment of the present invention;

[0066] Figure 4 A functional module diagram of a distribution network power situation awareness and prediction system provided by an embodiment of the present invention;

[0067] The implementation, functional features, and advantages of the object of the present invention will be further described in conjunction with the embodiments with reference to the accompanying drawings. Specific embodiments

[0068] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0069] An embodiment of the present application provides a distribution network power situation awareness and prediction method. The execution subject of the distribution network power situation awareness and prediction method includes, but is not limited to, at least one of electronic devices such as a server, a terminal, etc. that can be configured to execute the method provided by the embodiment of the present application. In other words, the distribution network power situation awareness and prediction method can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes, but is not limited to: a single server, a server cluster, a cloud server, or a cloud server cluster, etc. The server can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, Content Delivery Network (CDN), and big data and artificial intelligence platforms.

[0070] Referring to Figure 1 As shown, it is a schematic flowchart of a distribution network power situation awareness and prediction method provided by an embodiment of the present invention. In this embodiment, the distribution network power situation awareness and prediction method includes:

[0071] S1. Collect electrical data corresponding to each node in the distribution network, and calculate multi-dimensional power data of each node in the distribution network according to the electrical data.

[0072] In the embodiment of the present invention, the electrical data refers to electrical parameters, and the electrical parameters include, but are not limited to, the effective value, phase, and frequency of voltage; the effective value and phase of current; active power, reactive power, apparent power, and power factor.

[0073] Specifically, electrical data of each node in the distribution network can be collected through sensors configured at each node in the distribution network. In the distribution network, the outgoing ends of substations, the branch points of feeders, the access points of important users, and the access points of distributed power sources are all key collection nodes. Current transformers and voltage transformers are used to accurately measure the current and voltage values of high-voltage and large-current lines, providing accurate data for power calculation; power sensors can directly measure the magnitude and direction of power, with high measurement accuracy and fast response speed, and can be installed at key nodes to monitor the change of power in real time.

[0074] Furthermore, according to the electrical parameters of the distribution network, the power balance situation of the distribution network can be monitored in real time. In order to monitor the power situation of the distribution network, it is necessary to analyze various power data in the distribution network, and then accurately analyze the power situation of the distribution network to improve the operation efficiency of the power grid.

[0075] In the embodiments of the present invention, the multi-dimensional power data refers to active power, reactive power, and apparent power. Among them, active power refers to the power consumed by resistive elements in an AC circuit. It is the part of the electric energy converted into other forms of energy (such as heat energy, mechanical energy, etc.). In the distribution network, active power is used to drive various electrical equipment to work normally, such as the operation of motors, the lighting of light bulbs, and the heating of electric furnaces; reactive power refers to the power occupied by inductive and capacitive elements during the energy conversion process in an AC circuit. It does not do external work but exchanges energy between the power supply and inductors and capacitors to establish magnetic and electric fields; apparent power refers to the product of the effective values of voltage and current in an AC circuit. It represents the total power provided by the power supply, including both active power and reactive power. Apparent power reflects the total electrical load capacity borne by the equipment in the distribution network.

[0076] In the embodiments of the present invention, calculating the multi-dimensional power data of each node in the distribution network according to the electrical data includes:

[0077] Extracting the circuit type corresponding to each node in the distribution network;

[0078] Quantifying the circuit type to obtain a type quantization value;

[0079] Calculating the power data of each node in the distribution network according to the type quantization value, where the power data calculation formula is:

[0080] ;

[0081] where, is the power data, is the effective voltage value at the node in the first circuit type, is the effective current value at the node in the first circuit type, is the phase difference between the voltage and current at a node in the first circuit type, is the type quantization value, is the effective value of the line voltage at a node in the second circuit type, is the effective value of the line current at a node in the second circuit type, is the phase difference between the phase voltage and phase current at a node in the second circuit type, is the first power change factor, is the second power change factor, is the third power change factor, is the cosine function, is the sine function;

[0082] Collect the power data according to the power change factors into multi-dimensional power data for each node in the distribution network.

[0083] Specifically, there are different types of circuits in the distribution network, and the circuit types include single-phase AC circuits and three-phase AC circuits. The power calculation methods for different circuit types are different. Accurately extracting the circuit type corresponding to each node is the basis for subsequent correct calculation of power data. Use intelligent monitoring equipment to obtain the circuit connection information of the node. For example, if the node is connected to a single-phase electrical equipment of a residential user, it can be determined that the node is a single-phase AC circuit; if the node is connected to a three-phase load such as a three-phase motor, it is a three-phase AC circuit. In order to reflect the influence of different circuit types on power calculation in a unified calculation formula, it is necessary to perform quantization processing on the circuit type and use specific numerical values to represent different circuit types. For example, set the type quantization value of the single-phase AC circuit , and the type quantization value of the three-phase AC circuit .

[0084] Specifically, when , it represents the first circuit type (single-phase AC circuit), and the power change factor can be set according to different physical meanings and calculation purposes. If calculating active power, then , if calculating reactive power, then , if calculating apparent power, then ; when , it represents the second circuit type (three-phase AC circuit). If calculating active power, then , if calculating reactive power, then , if calculating apparent power, then , and then calculate the power data considering different factors for each node according to different circuit types. However, in order to comprehensively reflect the power characteristics of the distribution network nodes, it is necessary to collect these power data into multi-dimensional power data.

[0085] Further, the multi-dimensional power data includes active power, reactive power, and apparent power. It is difficult to intuitively judge the overall operating state of the distribution network by only looking at the original data. Extracting multi-dimensional power features, such as the power change rate, power fluctuation amplitude, etc., can comprehensively describe the operation of the distribution network from multiple dimensions. For example, the power factor can reflect the utilization efficiency of electric energy, and the power change rate can reflect the change trend of the load. Through the power features, it is possible to comprehensively understand whether the distribution network is in a stable and efficient operating state.

[0086] S2. Extract the multi-dimensional power features corresponding to the multi-dimensional power data, and analyze the power operating state of the distribution network through the multi-dimensional power features.

[0087] In the embodiments of the present invention, the multi-dimensional power features include feature information in multiple aspects such as time domain, frequency domain, and sequence pattern, and can comprehensively and deeply describe the change law, fluctuation characteristics, periodicity, and temporal correlation relationship of the power in the distribution network, etc.

[0088] In the embodiments of the present invention, referring to Figure 2 as shown, the extraction of the multi-dimensional power features corresponding to the multi-dimensional power data includes:

[0089] S21. Divide the multi-dimensional power data of each node into power data sets according to the same dimension;

[0090] S22. Extract the time-domain features and frequency-domain features in the power data sets;

[0091] S23. Convert the power data sets into sequence sets, and extract the sequence pattern features of the sequence sets;

[0092] S24. Aggregate the time-domain features, the frequency-domain features, and the sequence pattern features into multi-dimensional power features.

[0093] Specifically, the multi-dimensional power data of each node in the distribution network includes different types of data such as active power, reactive power, and apparent power, and these data change continuously at different time points. For the convenience of subsequent analysis, it is necessary to classify and organize the power data of the same type (i.e., the same dimension). Based on the power type as the division basis, the active power data of each node is grouped into one data set, the reactive power data is grouped into another data set, and the apparent power data is grouped into a third data set.

[0094] Specifically, the time-domain features reflect the variation of power data over time. By analyzing the time-domain features, information such as the change trend, fluctuation, and extreme values of power can be understood, which helps to judge the operation status and load characteristics of the distribution network. The time-domain features include mean, maximum value, minimum value, standard deviation, change rate, etc. For example, calculating the mean of the active power dataset can understand the average level of power in this dimension; calculating the standard deviation can measure the dispersion degree of power data and reflect the fluctuation magnitude of power; calculating the change rate of power can observe the change speed of power over time. The frequency-domain features are used to analyze the frequency components of power data and can reveal the hidden periodic information in the power data. Different load types and operation states may generate power fluctuations of different frequencies. By using the Fourier transform to convert the power data in the time domain to the frequency domain, the power spectrum of the power data is obtained, and frequency-domain features such as the main frequency components and harmonic content can be extracted from the spectrum.

[0095] Furthermore, convert the power dataset into a sequence set, that is, regard the power data arranged in chronological order as a sequence, and arrange the data in the power dataset in sequence according to the time order to form a time series. For example, arrange the active power data of a certain node in chronological order to obtain an active power time series. Perform such a conversion on each power dataset to obtain multiple power sequence sets, and then extract the sequence pattern features. The sequence pattern features can reflect the chronological order and correlation relationship of power data in time, which helps to discover the laws and trends of power changes and predict the future power state. For example, by analysis, it is found that there will be a peak value in the active power of a certain node from 7 pm to 9 pm every day, which is the sequence pattern feature. Then, integrate the extracted time-domain features, frequency-domain features, and sequence pattern features into a feature vector or feature matrix to form multi-dimensional power features, which describe the characteristics of multi-dimensional power data from different angles and more accurately reflect the power operation status of the distribution network.

[0096] Even further, the multi-dimensional power features contain information in multiple dimensions such as time domain, frequency domain, and sequence pattern. By integrating the features of different dimensions, the power operation status of the distribution network can be comprehensively and meticulously characterized from multiple angles, avoiding the limitations of single-dimensional analysis.

[0097] In the embodiment of the present invention, the power operation status refers to the working conditions related to power at a certain moment in the distribution network, including the normal operation state, in which the power distribution in the distribution network is reasonable, the equipment operates stably, and all power indicators are within the normal range; the overload state, that is, the load in the distribution network exceeds the rated capacity of the equipment, which may cause problems such as equipment overheating and damage; the underload state, which means that the load of the distribution network is too low, the equipment is not fully utilized, resulting in waste of resources; the fault state, such as short-circuit faults and grounding faults.

[0098] In the embodiments of the present invention, the power operation state of the distribution network is analyzed through the multi-dimensional power characteristics, including:

[0099] Construct an operation state matrix according to the power characteristic dimensions in the multi-dimensional power characteristics and the power operation state dimensions of the pre-acquired distribution network;

[0100] Determine the power operation state value of the distribution network through the multi-dimensional power characteristics and the pre-acquired multi-dimensional power historical characteristics;

[0101] Fill the operation state matrix according to the power operation state value;

[0102] Calculate the power operation state quantization value of the distribution network by using the filled operation state matrix, where the calculation formula of the power operation state quantization value is:

[0103] ;

[0104] Wherein, is the power operation state quantization value, is the state standard value, is the matrix value of the th row and th column in the operation state matrix, is the row dimension in the operation state matrix, is the column dimension in the operation state matrix, is the number of nodes in the distribution network, is the node serial number in the distribution network;

[0105] Determine the power operation state of the distribution network according to the power operation state quantization value.

[0106] Specifically, the multi-dimensional power characteristics include characteristics extracted from multiple perspectives such as time domain, frequency domain, and sequence pattern, such as the mean value of power, standard deviation, main frequency component, periodic pattern, etc. Different types of characteristics constitute the power characteristic dimensions; various operation states that occur in the distribution network, such as normal operation, overload, underload, short circuit fault, ground fault, etc., different operation states constitute the power operation state dimensions. Taking the power characteristic dimensions as columns and the power operation state dimensions as rows, a matrix is constructed, and each element of the matrix represents the association information between a certain power characteristic and a certain operation state.

[0107] Specifically, the multi-dimensional power historical feature refers to the multi-dimensional power feature data of the distribution network collected and analyzed over a past period of time. The historical feature records the power feature performance of the distribution network under different operating states. Then, the currently obtained multi-dimensional power feature is compared and analyzed with the multi-dimensional power historical feature. By comparing the characteristics such as the fluctuation situation and frequency components of the current power with the characteristics in the historical normal operation, overload and other states, it is judged what operating state the current distribution network is in; according to the determined power operating state value, the corresponding matrix elements are assigned. If it is judged that the current distribution network is in an overload state, then in the row corresponding to the overload state in the operating state matrix, corresponding assignments are made according to different power feature dimensions.

[0108] Furthermore, there are n multi-dimensional power features and m power operating state dimensions. When the data corresponding to the normal operating state are all the value 1, it indicates normal operation, otherwise it is abnormal. In the calculation formula of the power operating state quantization value, the value 3 refers to active power, reactive power, and apparent power. Only when all three powers are normal values does it indicate that the node A, B, C has normal operating power at time T. If the characteristic value in each multi-dimensional power feature belongs to the normal range, it corresponds to the normal operating state, that is, the corresponding value of the normal operating state corresponding to each multi-dimensional power feature is the value 1, while overload, underload, short-circuit fault, and grounding fault are regarded as abnormal operating states. As long as the characteristic value in the multi-dimensional power feature does not belong to the normal range, it corresponds to the abnormal operating state, that is, the corresponding value of the operating state corresponding to each multi-dimensional power feature is the value 0. That is, only when all the values in the normal operating state row in the operating state matrix are 1 and all the values in the normal operating state row in the three power data are 1, the distribution network is in the normal operating state. Otherwise, in any other case, the distribution network is in the abnormal operating state. Then, when the power operating state quantization value is the value 1, it indicates that the power operating state of the distribution network is the normal operating state, and when the power operating state quantization value is the value 0, it indicates that the power operating state of the distribution network is the abnormal operating state.

[0109] Even further, the power operating state of the distribution network is not constant but fluctuates continuously with time. To clearly capture the real-time fluctuation situation of the power and intuitively display the change trend of the power over time, it is necessary to construct a power time series, arrange the power operating states at different times in chronological order, and then provide real-time information for the dispatching and control of the power grid to realize the intelligent operation management of the power grid.

[0110] S3. Construct a power time series of the distribution network according to the power operating state, and use the pre-constructed time series model to perform situation awareness on the power time series to obtain the situation prediction value of the distribution network.

[0111] In the embodiments of the present invention, the power time series is arranged in chronological order and reflects the sequence of changes in the information related to the power state of the distribution network. With time as the horizontal axis and the power operation state (such as normal, abnormal, etc.) as the vertical axis, through the power time series, the change trend, fluctuation condition, and periodic characteristics of the power of the distribution network over time can be intuitively observed, etc.

[0112] In the embodiments of the present invention, with reference to Figure 3 as shown, constructing the power time series of the distribution network according to the power operation state includes:

[0113] S31. Extract the operation time points corresponding to the power operation state;

[0114] S32. Map the operation time points and the power operation state to obtain a mapping sequence;

[0115] S33. Convert the mapping sequence into the power time series of the distribution network.

[0116] Specifically, during the operation of the distribution network, the monitoring of the power operation state is carried out at different time points, and these time points record the moments when the power operation state data is generated. For example, through the monitoring devices installed at each node, power-related data is collected at fixed time intervals (such as every minute, every hour, etc.), and these collection moments are the operation time points, while the power operation state includes normal operation, overload, underload, etc. Establish a corresponding relationship between each operation time point and the power operation state information corresponding to that moment, that is, one row records the time, and the other row records the power operation state data at the same moment to form a mapping. Furthermore, the mapping sequence represents the association between time and the power operation state to obtain the power time series of the distribution network, which is an ordered sequence with time as the index and power-related data or states as the values, and can be used for subsequent in-depth analysis, such as load forecasting, fault diagnosis, etc.

[0117] Furthermore, in order to predict the electricity demand in different periods, for example, during the high-temperature period in summer, it is predicted that the increase in air-conditioning load leads to an increase in power demand. The power department can adjust the power generation plan in advance, increase the power generation, ensure that the power supply meets the demand, and avoid power outages or power rationing situations. Therefore, it is necessary to conduct situation awareness prediction based on the power time series to be able to know in advance the electricity demand in different periods.

[0118] In the embodiments of the present invention, the situation prediction value of the distribution network refers to the predicted value of the power-related situation in the future operation state of the distribution network obtained by analyzing and processing the power time series using a time series model. This value can represent various power-related situations, such as the predicted values of active power and reactive power, or the load prediction value and voltage prediction value obtained based on power analysis, etc.

[0119] In the embodiments of the present invention, the situation awareness of the power time series by using the pre-constructed time series model to obtain the situation prediction value of the distribution network includes:

[0120] Converting the power time series into model sequence input data;

[0121] Extracting the model parameters of the pre-constructed time series model;

[0122] Initializing the hidden state and cell state of the time series model;

[0123] Calculating the target hidden state corresponding to the model sequence input data by using the initialized time series model and the model parameters;

[0124] Determining the output data according to the target hidden state, and performing a linear transformation on the output data to obtain the situation prediction value of the distribution network.

[0125] Specifically, the pre-constructed time series model is an LSTM model, and the LSTM model requires the input data to be a three-dimensional array with the format [number of samples, number of time steps, number of features]. Assume that the input power time series has samples, and each sample contains power values for the number of time steps, and there is only one feature, i.e., power. Then the shape of the input data is . If the input data does not meet this format, corresponding adjustment and reshaping operations are required. Then, after loading the pre-trained LSTM model, the weight and bias parameters of the model are initialized. These parameters have been learned during the training phase and are used to control the input gate, forget gate, and output gate of the LSTM cell, and the hidden state and cell state of the LSTM model are reset. At the start of prediction, the hidden state and cell state are usually initialized to zero vectors.

[0126] Specifically, the input data is sequentially input into the LSTM cell according to the number of time steps. Each LSTM cell updates the hidden state and cell state at the current moment through the calculations of the input gate, forget gate, and output gate based on the current input, the hidden state at the previous moment, and the cell state at the previous moment. Then the input gate , the forget gate , the candidate value of the cell state , the update of the cell state , the output gate , the update of the hidden state , where is the input at the current moment, is the hidden state at the previous moment, is the cell state at the previous moment, is the weight matrix, is the bias vector. is the sigmoid function, is the hyperbolic tangent function, represents element-wise multiplication, and the hidden state at the last time step is input to the output layer, and the predicted value is obtained through a linear transformation , where is the weight matrix of the output layer, is the bias vector of the output layer. In addition, prediction can be performed iteratively, that is, predicting the value at one time point each time, and then adding the predicted value as a new input to the input sequence to continue predicting the next time point; the other is direct prediction, that is, training an LSTM model that can directly output the predicted values at multiple time points, and obtaining the predicted results at multiple time points at once during prediction.

[0127] Furthermore, the load in the distribution network is in continuous dynamic change, and it is necessary to capture the power load change information in real time. When predicting the power situation, the newer the data, the more it can reflect the actual operation trend of the current distribution network. For example, in short-term load prediction, the newly incorporated real-time power data may contain load change information caused by sudden weather changes or special activities. Predicting based on the updated time series can enable the prediction model to better capture these changes, thereby improving the prediction accuracy.

[0128] S4. Update the power time series within a preset moving time window, determine the power situation trigger condition of the distribution network according to the updated power time series, and update the model parameters in the time series model according to the power situation trigger condition.

[0129] In the embodiment of the present invention, the moving time window is a time period with a fixed time length. It slides on the power time series and is used to select data within a specific time range for analysis. For example, setting a moving time window to 1 hour means selecting continuous 1-hour power data for processing each time. This time window is like a window that continuously moves on the time axis of the power time series, and each movement will cover a new segment of data. The moving time window continuously updates the power time series to ensure that the time series used for prediction always contains the latest power data.

[0130] Furthermore, the power time series records the change of power over time. By continuously updating this series, these dynamic changes can be captured in real time. Determining the trigger condition according to the updated series can keenly sense when the operation state of the distribution network changes significantly.

[0131] In the embodiments of the present invention, the power situation trigger condition is a regular setting for monitoring and managing the operating state of the distribution network. It is formulated based on the analysis of the power time series of the distribution network. After detecting abnormal situations such as power mutations and determining possible triggering factors.

[0132] In the embodiments of the present invention, determining the power situation trigger condition of the distribution network according to the updated power time series includes:

[0133] Detecting mutation factors in the updated power time series;

[0134] Determining the triggering factors of the distribution network according to the mutation factors;

[0135] Generating the power situation trigger condition of the distribution network through the triggering factors.

[0136] Specifically, the power time series reflects the change of the distribution network power over time. In actual operation, the distribution network power may mutate due to various reasons. Such a mutation may indicate a change in the operating state of the distribution network or potential problems. The mutation factor is a parameter used to quantify the degree and characteristics of the power mutation. The first derivative or the second derivative of the power time series can be calculated to measure the rate and acceleration of the power change. If there is a large numerical change in the derivative at a certain moment, it means that the power has mutated at that moment. In addition, the sliding window technique can also be used to calculate statistics such as the mean and standard deviation of the power data within the window. When the statistical characteristics of the data within the window are significantly different from those of the previous and subsequent windows, it also indicates that there may be a mutation. For example, within a sliding window with a length of 10 minutes, calculate the mean and standard deviation of the power. If the mean of the current window suddenly increases by 50% compared to the mean of the previous window and the standard deviation also increases significantly, this may be a mutation signal, thus accurately detecting the mutation factors in the updated power time series and providing key information for subsequent analysis.

[0137] Specifically, once a mutation factor is detected, analyze the reason behind the mutation to determine the triggering factors of the distribution network. Different types of mutation factors often correspond to different triggering factors. For example, if the mutation factor shows a sudden large increase in power, possible triggering factors may be the startup of large electrical equipment, the connection of new loads, or the faulty disconnection of distributed power sources, etc.; if the mutation factor shows a sharp decrease in power, it may be caused by line faults, equipment tripping, or power outages of important users, etc. Then analyze the updated power time series to determine the power situation triggering conditions. The triggering conditions can be set based on factors such as the change amplitude of power, the change rate, and the deviation from historical data. For example, when the change rate of the active power at a certain node exceeds a preset threshold within a short period of time, or the deviation of the power value from the historical data of the same period exceeds a certain range, the corresponding conditions are triggered. When the power situation triggering conditions are met, it indicates that the operating state of the distribution network has changed significantly, and the parameters in the time series model need to be updated. By re-inputting the updated power time series into the model for training, adjust the parameters of the model so that the model can better adapt to the new operating state and improve the prediction accuracy. If the real-time value of the active power exceeds 120% of its historical average, or the power change rate exceeds 30% within a short period of time, then the triggering conditions are met.

[0138] Furthermore, as the distribution network operates, there may be deviations in the model during the prediction process. The anomalies or newly emerging power situations reflected by the power situation triggering conditions may imply that there are deviations in the model prediction. For example, when the actual power exceeds the model prediction range and triggers the power situation conditions, it indicates that the model's estimation of the current power change is inaccurate. By updating the model parameters, these deviations can be corrected, making the model prediction more in line with the actual power change and improving the prediction accuracy.

[0139] In the embodiments of the present invention, updating the model parameters refers to adjusting the parameters used for calculation and prediction inside the model according to the newly obtained data characteristics (such as the degree and direction of change reflected by the power sequence data collected according to the power situation triggering conditions) during the training or operation of the time series model. The model parameters include, but are not limited to, the weight matrix and bias vector in the neural network. When predicting the future power value of the distribution network, the updated model parameters can enable the model to better capture the complex patterns and trends in the power data and improve the prediction accuracy.

[0140] In the embodiments of the present invention, updating the model parameters in the time series model according to the power situation triggering conditions includes:

[0141] Collect power sequence data within a preset time period according to the power situation triggering conditions;

[0142] Extract the degree of data change and the direction of data change from the power sequence data;

[0143] Determine an adjustment factor according to the degree of data change and the direction of data change;

[0144] Update the learning rate in the time series model through the adjustment factor, where the learning rate update formula is:

[0145] ;

[0146] Wherein, is the learning rate of the th iteration, is the minimum value of the learning rate, is the maximum value of the learning rate, is the current iteration number, is the total number of iterations within a period, is a constant, is the cosine function, is the adjustment factor;

[0147] Determine the updated model parameters in the time series model through the learning rate.

[0148] Specifically, the power situation trigger condition is a rule set based on the power change situation of the distribution network. When these conditions are triggered, it means that there are changes in the power state of the distribution network that need attention, such as power mutations, abnormal fluctuations, etc. At this time, in order to more accurately understand the operating conditions of the distribution network and optimize the time series model, it is necessary to collect power sequence data within a preset time period, and the power data within the preset time period contains sufficient information to reflect the characteristics of power changes, and can represent the process of power from stability to mutation and then to recovery. Furthermore, the degree of data change and the direction of data change in the power sequence data are extracted. The degree of data change is used to measure the severity of power change within this time period. For example, the degree of change is quantified by calculating the standard deviation, range, or difference between adjacent data points of the power sequence data. The larger the standard deviation, the greater the degree of dispersion of the power data, that is, the greater the degree of change; the range directly reflects the difference between the maximum and minimum values of the data, reflecting the fluctuation range of power within this time period; the direction of data change describes whether the power is rising or falling. It can be determined by observing the size relationship between adjacent data points. If the latter data point is greater than the former one, the change direction is rising; otherwise, it is falling. Accurately extracting the degree and direction of data change helps to understand the specific characteristics of power change and provides a basis for subsequent adjustment of the time series model.

[0149] Specifically, the degree and direction of data change will affect the adjustment of the learning rate. If the degree of change in power data is large, it indicates that the model needs to adapt to the new data pattern faster. At this time, a relatively large learning rate is expected to update the model parameters more quickly. Conversely, if the degree of change is small, the learning rate can be appropriately reduced to make the update of model parameters more stable. Different change directions may imply different power change mechanisms and may also affect the strategy for adjusting the learning rate. For example, if the power continuously rises and the degree of change is large, a more aggressive adjustment of the learning rate may be required. Then, the adjustment factor is set to 1.5 to keep up with the rhythm of power change. In this way, the learning rate is dynamically adjusted according to the characteristics of the power sequence data, enabling the model to better adapt to data changes during the training process. If the power continuously drops and the degree of change is large, the adjustment factor is set to 0.5. If the power continuously drops and the degree of change is small or the power continuously rises and the degree of change is small, the adjustment factor is set to 1. Then, the learning rate of the model is calculated according to the learning rate update formula. The learning rate changes in the form of a cosine function with the number of iterations, gradually decreasing from the maximum value to the minimum value within one period and then repeating this process periodically. This method helps the model jump out of the local optimal solution and find a better global optimal solution.

[0150] Furthermore, the learning rate is an important hyperparameter in the training process of the time series model. It determines the step size of the model when updating parameters in each iteration. A suitable learning rate is crucial for the convergence speed and prediction accuracy of the model. The learning rate plays a role in controlling the step size of parameter update in this process. After the learning rate is determined, in each iteration of the model, according to the calculated gradient (the gradient represents the rate of change of the error with respect to the model parameters), the model parameters are moved a certain distance in the opposite direction of the gradient. This distance is the product of the learning rate and the gradient. By continuously repeating this process and gradually adjusting the model parameters using the updated learning rate, the model can better fit the power sequence data and improve the prediction ability of the power situation of the distribution network. The model parameters determine how the model transforms, combines the input data, and finally generates the prediction result. By updating the model parameters, the model can adapt to the dynamic changes of the data and continuously optimize its prediction ability to more accurately reflect the change law of the power situation of the distribution network.

[0151] Even further, as time goes by, the time series model may show deviations during the prediction process. The abnormal power situation reflected by the power situation trigger condition often implies deficiencies in the model prediction. For example, when the corresponding condition is triggered due to a large deviation between the actual power and the predicted value, updating the model parameters and optimizing the situation prediction value can correct the model deviation, making the predicted value closer to the actual power situation and improving the prediction accuracy.

[0152] S5. Optimize the situation prediction value by using the updated time series model to obtain a situation optimization value, and analyze the power situation perception of the distribution network by using the situation optimization value to obtain a power situation perception prediction result.

[0153] In the embodiment of the present invention, the situation optimization value refers to a prediction value that can more accurately reflect the future power situation of the distribution network, which is finally determined through updating the time series model and comparative analysis of the prediction results between the updated model and the original model during the prediction process of the power situation of the distribution network.

[0154] In the embodiment of the present invention, the step of optimizing the situation prediction value by using the updated time series model to obtain a situation optimization value includes:

[0155] Perceive the situation of the power time series by using the updated time series model to obtain an updated situation prediction value of the distribution network;

[0156] Calculate the error value between the updated situation prediction value and the situation prediction value;

[0157] When the error value is less than or equal to a preset error threshold, use the situation prediction value as the situation optimization value;

[0158] When the error value is greater than the preset error threshold, use the updated situation prediction value as the situation optimization value.

[0159] Specifically, the updated time series model is obtained by updating the parameters of the original model based on the power situation trigger condition, and the updated model has better ability to adapt to the latest power change characteristics of the distribution network. Perceiving the situation of the power time series by using this model is to let the model predict the future power situation of the distribution network according to the current and historical power data, using the updated parameters and algorithms, so as to obtain an updated situation prediction value. According to the data pattern and law in the power time series, combined with the updated model parameters, predict the power situation related values at the next time point or in the future period of time, such as predicting the active power value in the next hour, and this prediction value is the updated situation prediction value.

[0160] Specifically, the situation prediction value is the prediction result of the power situation of the distribution network obtained before the model is updated. To evaluate whether the updated model improves the prediction accuracy, it is necessary to calculate the difference between the situation update prediction value and the situation prediction value. This difference is the error value. Methods for calculating the error value include the mean square error (MSE), mean absolute error (MAE), etc. The preset error threshold is a standard value set in advance according to actual needs and requirements for prediction accuracy. When the calculated error value is less than or equal to this threshold, it indicates that although the updated model adjusts the prediction value, it does not significantly improve the prediction accuracy, or in other words, the difference between the updated prediction value and the original prediction value is within an acceptable range. In this case, it is considered that the original situation prediction value can already meet the current prediction needs, so the situation prediction value is directly used as the situation optimization value. That is, in some cases, over-relying on the updated prediction value may introduce unnecessary fluctuations or instability factors, while the original prediction value may already be a relatively reliable result. If the error value is greater than the preset error threshold, it means that the updated time series model has made a large change to the prediction value, and this change exceeds the acceptable range, indicating that the updated model has captured some information not considered by the original model, resulting in a significant change in the prediction result. In this case, it is considered that the updated model has a better prediction effect and can more accurately reflect the power situation of the distribution network, so the situation update prediction value is used as the situation optimization value. In this way, after the model is updated, the more optimal prediction value can be flexibly selected as the final situation optimization value according to the actual prediction effect to improve the prediction accuracy and reliability.

[0161] Furthermore, the situation optimization value is obtained based on the updated time series model, comprehensively considering the latest change characteristics of the distribution network power. Compared with the initial situation prediction value, it can more accurately reflect the current real operation state and future development trend of the distribution network. The situation optimization value obtained by updating the model can capture these changes in a timely manner, providing a more accurate data basis for subsequent power situation perception analysis, thereby improving the prediction accuracy.

[0162] In the embodiment of the present invention, the power situation perception prediction result is an information set comprehensively reflecting the prediction accuracy of the distribution network power situation and related conclusions. It is not just a simple prediction value, but the prediction effect of the distribution network power situation obtained through a series of analysis steps (such as comparing with the target power situation value, determining the perception level, etc.).

[0163] In the embodiment of the present invention, analyzing the power situation perception of the distribution network by using the situation optimization value to obtain the power situation perception prediction result includes:

[0164] Extracting the target power situation value at the target moment;

[0165] Compare the situation optimization value with the target power situation value to obtain a comparison result;

[0166] Determine the perception level of the power situation perception of the distribution network according to the comparison result;

[0167] Determine the power situation perception prediction result through the perception level.

[0168] Specifically, when analyzing the power situation of the distribution network, it is necessary to pay attention to the power-related status at a specific time point, which is the target time point, and the target power situation value refers to the actual or expected power-related value presented by the distribution network at the target time point. Comparing the situation optimization value with the target power situation value can evaluate the accuracy of the prediction and the actual change of the power situation of the distribution network. Calculate the difference between the two (predicted value - actual value) to measure the deviation degree of the prediction or calculate the error rate (|predicted value - actual value| / actual value) × 100% to more intuitively represent the proportion of the prediction deviation from the actual. This difference or error rate is the comparison result.

[0169] Specifically, in order to more intuitively evaluate the effect of the power situation perception of the distribution network, different perception levels are divided according to the comparison result. The perception levels are usually preset and determined according to actual needs and requirements for the prediction accuracy of the power situation. For example, it can be set that an error rate within 5% is a high perception level, indicating that the predicted value is very close to the actual value and the perception of the power situation is relatively accurate; an error rate between 5% - 15% is a medium perception level, indicating that there is a certain deviation in the prediction but it is still within an acceptable range; an error rate exceeding 15% is a low perception level, meaning that the prediction deviation is large and the perception of the power situation is not accurate enough. By comparing the comparison result (such as the error rate) with these preset level ranges, the perception level of the power situation perception of the distribution network can be determined, and the perception level reflects the closeness between the predicted value and the actual value and the perception quality of the power situation. Furthermore, based on the perception level, the power situation perception prediction result is determined. For example, when the perception level is a high perception level, it indicates that the prediction is relatively reliable, and the power situation perception prediction result can be considered as an accurate prediction of the power situation of the distribution network. Relevant personnel can carry out regular power grid dispatching, equipment maintenance, etc. based on this prediction; if the perception level is a low perception level, it indicates that the prediction deviation is large, and it may be necessary to re-examine the prediction model, check the data accuracy or consider more influencing factors. At this time, the power situation perception prediction result prompts that the prediction process needs to be adjusted and optimized to improve the prediction ability of the power situation of the distribution network.

[0170] In the embodiments of the present invention, electrical data of each node is collected and multi-dimensional power data is calculated, which can comprehensively cover different aspects of the power of the distribution network; a power time series is constructed based on the power operation state, and a pre-constructed time series model is used for situation awareness, which can effectively capture the change rules and trends of power over time; the power time series is updated within a preset moving time window, enabling the system to track the latest changes in the power of the distribution network in real time. The power situation trigger condition is determined according to the updated time series, which can timely capture abnormal fluctuations or mutations of power; based on the power situation trigger condition, the parameters of the time series model are updated, enabling the model to dynamically adjust itself according to the real-time operation state of the distribution network and always maintain the accurate prediction ability for the power situation; the situation prediction value is optimized by using the updated time series model, and by comparing the prediction values before and after the update with the actual power situation value, a better situation optimization value is selected, effectively correcting the prediction deviation, improving the matching degree between the prediction value and the actual power situation, and making the prediction result more accurate and reliable. Therefore, the power situation awareness prediction method and prediction system for the distribution network proposed by the present invention can solve the problem of low accuracy in product recommendation.

[0171] As Figure 4 shown, it is a functional module diagram of a power situation awareness prediction system for a distribution network provided by an embodiment of the present invention.

[0172] The power situation awareness prediction system 100 of the present invention can be installed in an electronic device. According to the functions to be realized, the power situation awareness prediction system 100 can include a multi-dimensional power data calculation module 101, a power operation state analysis module 102, a situation prediction value analysis module 103, a model parameter update module 104, and a power situation awareness analysis module 105. The modules of the present invention can also be referred to as units, which refer to a series of computer program segments that can be executed by a processor of an electronic device and can complete fixed functions, and are stored in the memory of the electronic device.

[0173] In this embodiment, the functions of each module / unit are as follows:

[0174] The multi-dimensional power data calculation module 101 is used to collect electrical data corresponding to each node in the distribution network and calculate multi-dimensional power data of each node in the distribution network according to the electrical data;

[0175] The power operation state analysis module 102 is used to extract multi-dimensional power features corresponding to the multi-dimensional power data and analyze the power operation state of the distribution network through the multi-dimensional power features;

[0176] The situation prediction value analysis module 103 is configured to construct a power time series of the distribution network according to the power operation state, and perform situation awareness on the power time series by using a pre-constructed time series model to obtain a situation prediction value of the distribution network;

[0177] The model parameter update module 104 is configured to update the power time series within a preset moving time window, determine a power situation trigger condition of the distribution network according to the updated power time series, and update model parameters in the time series model according to the power situation trigger condition;

[0178] The power situation awareness analysis module 105 is configured to optimize the situation prediction value by using the updated time series model to obtain a situation optimization value, and analyze the power situation awareness of the distribution network by using the situation optimization value to obtain a power situation awareness prediction result.

[0179] Specifically, each module in the distribution network power situation awareness prediction system 100 in the embodiments of the present invention adopts the same technical means as those in the above Figures 1 to 3 The distribution network power situation awareness prediction method described, and can produce the same technical effects, which will not be elaborated here.

[0180] In several embodiments provided by the present invention, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

[0181] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0182] In addition, each functional module in each embodiment of the present invention can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware, or in the form of a combination of hardware and software functional modules.

[0183] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above exemplary embodiments, and without departing from the spirit or basic characteristics of the present invention, the present invention can be implemented in other specific forms.

[0184] Therefore, in all respects, the embodiments should be considered exemplary and non-limiting. The scope of the present invention is not limited solely by the above description. Thus, all changes within the meaning and scope of equivalent elements falling within the scope of protection are intended to be encompassed by the present invention.

[0185] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is a theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to obtain the best results.

[0186] In addition, it is obvious that the term "including" does not exclude other units or steps, and the singular does not exclude the plural. The multiple units or systems described in the system embodiments can also be implemented by one unit or system through software or hardware. Terms such as first, second, etc. are used to denote names and do not represent any specific order.

[0187] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not limiting. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A power distribution network power situation awareness prediction method, characterized in that: The method comprises: Collecting electrical data corresponding to each node in the distribution network, and calculating multi-dimensional power data of each node in the distribution network based on the electrical data; Extracting multidimensional power features corresponding to the multidimensional power data, and analyzing the power operation state of the distribution network through the multidimensional power features; Constructing a power time series of the distribution network according to the power operation state, and using a pre-constructed time series model to perform situation awareness on the power time series to obtain a situation prediction value of the distribution network; The power time series is updated within a preset moving time window, a power situation triggering condition of the distribution network is determined according to the updated power time series, and a model parameter in the time series model is updated according to the power situation triggering condition; The situation prediction value is optimized using the updated time series model to obtain a situation optimization value, and the power situation awareness of the distribution network is analyzed using the situation optimization value to obtain a power situation awareness prediction result.

2. The power distribution network power situation awareness prediction method according to claim 1, characterized in that: The extracting the multi-dimensional power features corresponding to the multi-dimensional power data includes: Divide the multi-dimensional power data of each node into power data sets according to the same dimension; Extracting time domain features and frequency domain features from the power data set; converting the power data set into a sequence set, and extracting sequence pattern features of the sequence set; The time domain features, the frequency domain features and the sequence pattern features are aggregated into a multi-dimensional power feature.

3. The power distribution network power situation awareness prediction method according to claim 1, characterized in that: The analyzing the power operation state of the distribution network by using the multi-dimensional power characteristics includes: Constructing an operation state matrix according to the power feature dimension in the multi-dimensional power feature and the power operation state dimension of the distribution network acquired in advance; Determining a power operation state value of the distribution network by using the multi-dimensional power characteristics and the multi-dimensional power history characteristics acquired in advance; Filling the operation state matrix according to the power operation state value; The populated operation state matrix is ​​used to calculate the power operation state quantization value of the distribution network, where the power operation state quantization value calculation formula is: ； in, is the quantized value of the power operation state, is the state standard value, is the first Line The matrix values ​​of the columns, is the row dimension in the running status matrix, is the column dimension in the running status matrix, is the number of nodes in the distribution network, is the node number in the distribution network; The power operation state of the power distribution network is determined according to the power operation state quantization value.

4. The power distribution network power situation awareness prediction method according to claim 1, characterized in that: The step of constructing a power time series of a power distribution network according to the power operation state includes: Extracting the operation time point corresponding to the power operation state; Mapping the operation time point with the power operation state to obtain a mapping sequence; The mapping sequence is converted into a power time series of the power distribution network.

5. The power distribution network power situation awareness prediction method according to claim 1, characterized in that: The method of using a pre-built time series model to perform situation awareness on the power time series to obtain a situation prediction value of the distribution network includes: converting the power time series into model sequence input data; Extract model parameters of pre-built time series models; Initializing the hidden state and cell state of the time series model; Calculating the target hidden state corresponding to the model sequence input data using the initialized time series model and the model parameters; Output data is determined according to the target hidden state, and a linear transformation is performed on the output data to obtain a state prediction value of the distribution network.

6. The power distribution network power situation awareness prediction method according to claim 1, characterized in that: The step of determining the power situation triggering condition of the distribution network according to the updated power time series includes: Detect mutation factors in the updated power time series; Determining a triggering factor of the distribution network according to the mutation factor; The power situation triggering condition of the power distribution network is generated by the triggering factor.

7. The power distribution network power situation awareness prediction method according to claim 1, characterized in that: The updating of the model parameters in the time series model according to the power situation triggering condition includes: Collecting power sequence data within a preset time period according to the power situation trigger condition; Extracting the data change degree and data change direction in the power sequence data; Determining an adjustment factor according to the degree of change of the data and the direction of change of the data; The learning rate in the time series model is updated by the adjustment factor, wherein the learning rate update formula is: ； in, For the The learning rate of the iteration, is the minimum value of the learning rate, is the maximum value of the learning rate, is the current iteration number, is the total number of iterations in one cycle, is a constant, is the cosine function, is the regulating factor; The updated model parameters in the time series model are determined by the learning rate.

8. The power distribution network power situation awareness prediction method according to claim 4, characterized in that: The method of optimizing the situation prediction value by using the updated time series model to obtain the situation optimization value includes: Using the updated time series model to perform situation awareness on the power time series, and obtain a situation update prediction value of the distribution network; Calculating an error value between the situation update prediction value and the situation prediction value; When the error value is less than or equal to a preset error threshold, the situation prediction value is used as the situation optimization value; When the error value is greater than a preset error threshold, the situation update prediction value is used as the situation optimization value.

9. The power distribution network power situation awareness prediction method according to claim 1, characterized in that: The method of analyzing the power situation awareness of the distribution network by using the situation optimization value to obtain a power situation awareness prediction result includes: Extract the target power situation value at the target time; Comparing the situation optimization value with the target power situation value to obtain a comparison result; Determine the power situation awareness level of the distribution network according to the comparison result; The power situation awareness prediction result is determined according to the awareness level.

10. A power distribution network power situation awareness prediction system, characterized in that: The system comprises: A multi-dimensional power data calculation module, used to collect electrical data corresponding to each node in the distribution network, and calculate the multi-dimensional power data of each node in the distribution network according to the electrical data; A power operation status analysis module, used to extract the multi-dimensional power features corresponding to the multi-dimensional power data, and analyze the power operation status of the distribution network through the multi-dimensional power features; A situation prediction value analysis module is used to construct a power time series of the distribution network according to the power operation state, and use a pre-constructed time series model to perform situation perception on the power time series to obtain a situation prediction value of the distribution network; A model parameter updating module, used to update the power time series within a preset moving time window, determine the power situation triggering condition of the distribution network according to the updated power time series, and update the model parameters in the time series model according to the power situation triggering condition; The power situation awareness analysis module is used to optimize the situation prediction value using the updated time series model to obtain the situation optimization value, and use the situation optimization value to analyze the power situation awareness of the distribution network to obtain the power situation awareness prediction result.

Images