Electric power system intelligent scheduling method and system based on big data

Abstract

The embodiment of the invention provides a power system intelligent scheduling method and system based on big data, and belongs to the technical field of data processing. The method comprises the following steps: acquiring initial operation data and initial generating capacity data corresponding to initial power equipment; performing operation abnormity analysis on the initial power equipment according to the initial operation data to obtain an initial operation state of the initial power equipment; when the initial operation state is a preset state, obtaining target power consumption data of the target user; and determining an emergency scheduling strategy corresponding to the initial power equipment according to the target power consumption data and the initial generating capacity data. According to the method, the problem that potential fault hidden dangers cannot be identified in time in related technologies is solved, and the situation that the shutdown risk of the power equipment is aggravated due to the fact that related decisions cannot be rapidly adjusted is avoided. By monitoring and analyzing the operation state of the equipment in real time, the method improves the accuracy and timeliness of fault early warning, thereby effectively reducing the risk of equipment shutdown and optimizing the operation management of the power equipment.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method and system for intelligent dispatching of an electric power system based on big data. Background Art

[0002] With the rapid development of the power system, the volatility and uncertainty of power loads are increasing, which makes traditional dispatch methods unable to cope with the complexity and dynamic needs of modern power systems. Existing emergency dispatch strategies often have a long response time, especially when sudden changes occur in the power system, which may lead to unstable power supply and even power outages. In addition, many existing emergency dispatch strategies lack effective fault prediction capabilities. Due to the failure to identify potential fault hazards in a timely manner, relevant decisions often cannot be adjusted quickly, which further increases the risk of power equipment downtime. Once the equipment is down, the power supply will be directly affected, which may lead to power shortages, thus affecting users' daily electricity consumption and the normal operation of enterprises. Summary of the invention

[0003] The main purpose of the embodiments of the present invention is to provide a method and system for intelligent dispatching of power systems based on big data, aiming to solve the problem of failure to timely identify potential fault hazards in related technologies, and to avoid the situation where related decisions often cannot be adjusted quickly, thereby exacerbating the risk of power equipment downtime.

[0004] In a first aspect, an embodiment of the present invention provides a method for intelligent dispatching of a power system based on big data, comprising:

[0005] Obtaining initial operation data and initial power generation data corresponding to the initial power equipment;

[0006] Performing an operation abnormality analysis on the initial power equipment according to the initial operation data to obtain an initial operation state corresponding to the initial power equipment;

[0007] When the initial operation state is a preset state, target power consumption data corresponding to the target user is obtained;

[0008] An emergency dispatch strategy corresponding to the initial power equipment is determined according to the target power consumption data and the initial power generation data.

[0009] In a second aspect, an embodiment of the present invention provides a power system intelligent dispatching system based on big data, including:

[0010] A data acquisition module, used to obtain initial operation data and initial power generation data corresponding to the initial power equipment;

[0011] A state determination module, configured to perform an operation abnormality analysis on the initial power equipment according to the initial operation data to obtain an initial operation state corresponding to the initial power equipment;

[0012] A state judgment module, used for obtaining target power consumption data corresponding to a target user when the initial operation state is a preset state;

[0013] A strategy determination module is used to determine the emergency dispatch strategy corresponding to the initial power equipment according to the target power consumption data and the initial power generation data.

[0014] In the third aspect, an embodiment of the present invention further provides a terminal device, comprising a processor, a memory, a computer program stored in the memory and executable by the processor, and a data bus for realizing connection and communication between the processor and the memory, wherein when the computer program is executed by the processor, the steps of any one of the methods for intelligent dispatching of power systems based on big data provided in the specification of the present invention are realized.

[0015] In a fourth aspect, an embodiment of the present invention further provides a storage medium for computer-readable storage, characterized in that the storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement any step of the intelligent dispatching method of the power system based on big data provided in the specification of the present invention.

[0016] The embodiment of the present invention provides a method and system for intelligent dispatching of a power system based on big data. The method first collects initial operation data and initial power generation data of initial power equipment, and then performs detailed operation abnormality analysis on the initial power equipment based on the initial operation data, so as to determine the initial operation state of the initial power equipment. If the initial operation state of the initial power equipment meets the preset state, the target power consumption data of the target user is further obtained. Using these target power consumption data and initial power generation data, a corresponding emergency dispatching strategy is formulated to ensure the stability and reliability of power supply. The method effectively solves the problem that potential fault hazards cannot be identified in time in the related technology. By real-time monitoring and analyzing the operation state of the equipment, possible faults of the equipment can be warned in advance, avoiding the risk of power equipment shutdown caused by decision lag. Through accurate fault warning and timely adjustment decision, this method significantly improves the reliability and efficiency of power equipment operation, thereby optimizing the management of the power system, reducing the downtime of the equipment, and improving the stability of power supply. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0018] Figure 1 A schematic diagram of a flow chart of a power system intelligent dispatching method based on big data provided by an embodiment of the present invention;

[0019] Figure 2 A schematic diagram of the module structure of a power system intelligent dispatching system based on big data provided by an embodiment of the present invention;

[0020] Figure 3 A schematic block diagram of the structure of a terminal device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0021] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0022] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.

[0023] It should be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0024] The embodiment of the present invention provides a method and system for intelligent dispatching of a power system based on big data. The method and system for intelligent dispatching of a power system based on big data can be applied to a terminal device, which can be an electronic device such as a tablet computer, a laptop computer, a desktop computer, a personal digital assistant, and a wearable device. The terminal device can be a server or a server cluster.

[0025] Some embodiments of the present invention are described in detail below in conjunction with the accompanying drawings. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0026] Please refer to Figure 1 , Figure 1 A schematic diagram of a flow chart of a method for intelligent dispatching of a power system based on big data provided in an embodiment of the present invention.

[0027] like Figure 1 As shown, the big data-based intelligent dispatching method for power system includes steps S101 to S104.

[0028] Step S101: Obtain initial operation data and initial power generation data corresponding to initial power equipment.

[0029] Exemplarily, necessary sensors and measuring instruments are installed on the initial power equipment to monitor various operating parameters of the initial power equipment in real time, such as temperature, pressure, current, voltage, etc. The sensors are connected to a data acquisition system or a monitoring platform so that real-time data of the equipment operation can be collected and recorded, thereby obtaining initial operating data corresponding to the initial power equipment.

[0030] Exemplarily, the initial power generation data of the initial power equipment can be effectively acquired through a power generation metering device equipped with the initial power equipment, or through real-time power generation monitoring by a data acquisition system connected thereto.

[0031] For example, the initial power equipment usually has built-in accurate metering sensors that can record the power generation output of the initial power equipment in real time. The data acquisition system is responsible for collecting, processing and storing this information to obtain the initial power generation data of the initial power equipment.

[0032] Step S102: performing an operation abnormality analysis on the initial power equipment according to the initial operation data to obtain an initial operation state corresponding to the initial power equipment.

[0033] For example, after obtaining the initial operation data, the collected initial operation data is cleaned and converted to ensure data quality and achieve effective data integration. Data cleaning mainly includes steps such as removing noise data and filling in missing data values, while data conversion requires unifying different types of data into a unified format for subsequent processing and analysis.

[0034] Exemplarily, after obtaining the running data after data cleaning and conversion, a neural network structure, such as a deep neural network (DNN), a convolutional neural network (CNN) or a recurrent neural network (RNN), is used to design the input layer, hidden layer and output layer of the model, and key parameters such as activation function and loss function are determined. The normal running data is used as a training sample to train the neural network model. The model parameters are adjusted by a back propagation algorithm and an optimizer (such as gradient descent) to minimize the prediction error. Thus, the corresponding neural network model is obtained.

[0035] Exemplarily, the initial operation data is input into a trained neural network model to obtain the predicted output of the model, and then the predicted output of the neural network model is compared with the initial operation data to calculate the difference or error between the two. If the difference or error exceeds a preset threshold, the initial operation state corresponding to the initial power equipment under the initial operation data is determined to be an abnormal state. If the difference or error is lower than a preset threshold, the initial operation state corresponding to the initial power equipment under the initial operation data is determined to be a normal state.

[0036] In some embodiments, the abnormality analysis of the initial operating data to obtain the initial operating state corresponding to the initial power equipment includes: performing data preprocessing on the initial operating data to obtain target operating data; determining a sliding window and a sliding step, and cutting the target operating data according to the sliding window and the sliding step to obtain window operating data; performing abnormality analysis on the window operating data using an abnormality recognition model to obtain the initial operating state corresponding to the initial power equipment.

[0037] Exemplarily, first, check whether there are missing values, outliers or noise in the initial operation data. These problems are dealt with, such as using interpolation to fill missing values, or removing outliers through statistical methods. Standardize or normalize the initial operation data to ensure that the numerical ranges between different features are consistent, which helps to improve the accuracy of subsequent analysis, and then extract useful features from the initial operation data, such as statistical features (mean, variance, etc.), frequency domain features (Fourier transform results), etc. These features can better describe the operating status of the equipment.

[0038] Exemplarily, a suitable sliding window is selected, which depends on the temporal resolution of the target operation data and the duration of the abnormal features. The sliding window size should be large enough to capture the key time dependencies, but not too large to avoid confusing different abnormal patterns. Determine the step size of the sliding window, which determines the degree of overlap between windows. A smaller step size can provide more fine-grained analysis, but increases the amount of computation; a larger step size may miss some detailed information.

[0039] Exemplarily, the target operating data is segmented using the determined sliding window and sliding step size. Each sliding window performs data segmentation under the target operating data using the sliding step size to obtain the window operating data corresponding to each sliding window.

[0040] Exemplarily, a suitable anomaly recognition model is selected, such as a model based on machine learning (such as a support vector machine, a random forest) or a model based on deep learning (such as an autoencoder, a neural network). The anomaly recognition model is trained using data in a normal state so that it can learn the normal operating mode. Thus, the window operation data is input into the trained anomaly recognition model, and the anomaly recognition model will analyze the window operation data and predict whether there is an anomaly. According to the output of the anomaly recognition model, the operating state of each sliding window is determined. If there is window operation data marked as abnormal by the anomaly recognition model, it can be inferred that the initial operating state of the initial operation device is determined to be an abnormal state. If the window operation data are all marked as normal by the anomaly recognition model, it can be inferred that the initial operating state of the initial operation device is determined to be a normal state.

[0041] Specifically, through data cleaning, normalization, and feature extraction, noise can be eliminated, data deviation can be reduced, and data consistency and accuracy can be ensured. This helps to improve the reliability of subsequent analysis and make model training and anomaly detection more effective. By properly setting the sliding window and sliding step size, dynamic changes and potential anomalies in time series data can be captured. The data within the window allows the model to perform detailed analysis within a smaller time frame, thereby more accurately identifying short-term or transient anomalies, thereby improving the sensitivity and accuracy of anomaly identification.

[0042] In some embodiments, the use of an abnormality recognition model to perform an abnormality analysis on the window operation data to obtain the initial operating state corresponding to the initial power equipment includes: using the center determination layer of the abnormality recognition model to obtain a first center point and a second center point from the window operation data; using the data clustering layer of the abnormality recognition model to perform cluster analysis on the window operation data based on the first center point and the second center point to obtain first cluster data and second cluster data; using the data analysis layer of the abnormality recognition model to perform data statistics on the first cluster data to obtain a first quantity and perform data statistics on the second cluster data to obtain a second quantity; using the abnormality determination layer of the abnormality recognition model to determine the initial operating state corresponding to the initial power equipment based on the first quantity and the second quantity.

[0043] Exemplarily, the anomaly identification model includes a center determination layer, a data clustering layer, a data analysis layer, and an anomaly determination layer.

[0044] Exemplarily, the center determination layer of the abnormal recognition model is used to randomly select two data from the window operation data and determine them as the first center point and the second center point respectively.

[0045] Exemplarily, the data clustering layer of the anomaly recognition model is used to perform cluster analysis on the window operation data according to the first center point and the second center point. For each data point in the window operation data, the first distance to the first center point and the second distance to the second center point are calculated respectively, so that each data point is assigned to the cluster represented by the center point closest to it according to the minimum value between the first distance and the second distance. After the data points are initially assigned, the mean (or median) of all data points in each cluster is calculated and used as the new center point, and then the positions of the first center point and the second center point are updated so that they more accurately reflect the data centers of their respective clusters. Repeat the above steps until the positions of the first center point and the second midline point no longer change significantly, or a predetermined number of iterations is reached. This marks the convergence of the clustering process. After the cluster analysis is completed, the cluster to which each data point belongs is output. At this point, the window operation data is divided into the first cluster data and the second cluster data.

[0046] Exemplarily, the data analysis layer of the anomaly recognition model is used to perform data statistics on the first cluster data to obtain the first quantity and to perform data statistics on the second cluster data to obtain the second quantity.

[0047] Exemplarily, the abnormal determination layer of the abnormal identification model is used to compare the first quantity and the second quantity. When the difference between the first quantity and the second quantity is less than a preset value, the initial operating state corresponding to the initial power equipment is determined to be a normal state; when the difference between the first quantity and the second quantity is greater than or equal to the preset value, the initial operating state corresponding to the initial power equipment is determined to be an abnormal state.

[0048] Specifically, the initial operating state of the initial power device can be more accurately determined by using the abnormality determination layer according to the first quantity and the second quantity, which helps to quickly identify whether the initial power device has an abnormality and enhance the accuracy and reliability of detection.

[0049] Step S103: When the initial operating state is a preset state, the target power consumption data corresponding to the target user is obtained.

[0050] Exemplarily, when the preset state is an abnormal state, when the initial operation state is an abnormal state, the maximum value is obtained according to the historical power consumption record of the target user, and then the historical power consumption record under the maximum value is determined as the target power consumption data corresponding to the target user. When the initial operation state is a normal state, the initial operation state of the initial power equipment continues to be monitored.

[0051] In some embodiments, obtaining the target electricity usage data corresponding to the target user includes: obtaining historical time and historical electricity usage data corresponding to the historical time; performing model training based on the historical time and the historical electricity usage data to obtain a time series prediction model; determining the target time, and performing power prediction for the target time based on the time series prediction model to obtain the target electricity usage data corresponding to the target user.

[0052] Exemplarily, historical electricity consumption data corresponding to historical time is extracted from a data source (such as a power company database, a smart meter, or a historical record system). The historical electricity consumption data is sorted in historical time order to ensure the integrity and consistency of the data. The electricity consumption corresponding to each time point is recorded. The sorted historical time and historical electricity consumption data are thus divided into a training set and a test set. The training set is used for model training, and the test set is used for model verification. Select a suitable time series prediction model. Common time series models include ARIMA (autoregressive integrated moving average model), LSTM (long short-term memory network), etc. Thus, the selected time series model is trained using historical time and historical electricity consumption data to obtain a time series prediction model. The time series prediction model will learn the changing pattern of electricity consumption data over time, so as to make future predictions.

[0053] Exemplarily, the target time corresponding to when the initial power equipment detects an abnormality is obtained, and then the target time is input into the time series prediction model for power prediction, thereby obtaining the target power consumption data corresponding to the target user at the target time.

[0054] Specifically, by using historical time and historical electricity consumption data for model training, a time series-based forecasting model can be created. The model is able to learn patterns and trends in historical data to accurately predict future electricity consumption. The electricity consumption forecast for the target time can provide the expected electricity consumption, which helps to better plan emergency dispatch strategies.

[0055] Step S104: determining an emergency dispatch strategy corresponding to the initial power equipment according to the target power consumption data and the initial power generation data.

[0056] Exemplarily, the initial power generation data includes the actual power generation capacity of the initial power equipment, while the target power consumption data is the expected power demand in the future time period. If the initial power generation data is greater than or equal to the target power consumption data, it means that the current power generation capacity is sufficient to meet the target power demand. In this case, the emergency dispatch strategy may consider replacing the initial power equipment with other power equipment with the same power generation capacity as the initial power equipment. By using other equipment with the same power generation capacity, it may be possible to improve the operating efficiency of the overall system and ensure the stability of power supply. If the initial power generation data is less than the target power consumption data, it means that the current power generation capacity is insufficient to meet the target power demand. In this case, the emergency dispatch strategy needs to enable power equipment with a power generation capacity greater than the initial power equipment to meet the demand. Select those devices with a power generation capacity greater than the initial power equipment from the backup equipment or other available equipment for operation. According to actual needs, these devices with larger power generation capacity are started to provide additional power generation to make up for the gap of insufficient initial power generation data.

[0057] Exemplarily, the initial power generation data is compared with the target power consumption data, and a corresponding emergency dispatch strategy is formulated to optimize the operation of the power system and ensure the stability and reliability of power supply.

[0058] In some embodiments, the method also includes: obtaining historical electricity price data and historical meteorological data; merging the historical electricity price data and the historical meteorological data to obtain the target electricity price and target weather corresponding to the target time point; analyzing the electricity price fluctuation pattern based on the target electricity price and the target weather to obtain the correlation between electricity demand and price fluctuations; determining the current meteorological data, and determining the target electricity price corresponding to the current meteorological data based on the current meteorological data and the correlation.

[0059] For example, historical electricity price data is obtained from the electricity market or power company. Usually, historical electricity price data includes electricity price information at each time point, which may be recorded at different time granularities such as hours, days, and weeks. Historical meteorological data is obtained from meteorological agencies or meteorological data providers. These data usually include meteorological variables such as temperature, humidity, wind speed, precipitation, etc., and may also be recorded at time granularities such as hours and days. The time dimension between historical electricity price data and historical meteorological data is the same.

[0060] Exemplarily, ensure that the timestamps of historical electricity price data and historical meteorological data are consistent. If the time granularity of the data is different (for example, one is recorded hourly and the other is recorded daily), the time granularity of the data needs to be unified. Match the historical electricity price data and historical meteorological data by timestamp to ensure that there are corresponding electricity price data and meteorological data at each time point. Merge the aligned electricity price data and meteorological data to obtain the target electricity price and target meteorological data corresponding to the target time point.

[0061] Exemplarily, a statistical method, such as calculating the Pearson correlation coefficient or the Spearman correlation coefficient, is used to evaluate the relationship between the target electricity price and the target weather. Identify which meteorological variables have a significant impact on the electricity price. Based on the characteristics of the data, a suitable regression model, such as linear regression, polynomial regression, etc., is selected to analyze the relationship between the electricity price and the meteorological factors. The correlation between the electricity price and the meteorological factors is extracted from the trained regression model. Identify the main influencing factors and their specific impact on the price (for example, for every 1 degree increase in temperature, the electricity price increases by X units).

[0062] For example, the current meteorological data is obtained, including the temperature, humidity, wind speed, etc. at the current time point. The current meteorological data is input into the established regression model. The regression model will use the previously extracted associations to calculate the target electricity price under the current meteorological conditions.

[0063] Specifically, by acquiring historical electricity price data and historical meteorological data, merging and analyzing them, an electricity price forecasting model based on historical trends can be established. This data-driven approach can more accurately capture the relationship between electricity prices and meteorological factors and improve the reliability of forecasts. Predicting electricity prices based on current meteorological data and established correlations can adjust electricity market strategies or electricity trading decisions in real time, helping power companies or market participants better cope with price fluctuations.

[0064] In some embodiments, the method also includes: determining a visualization tool, and displaying the initial operating status corresponding to the initial power equipment according to the visualization tool; determining the target power equipment according to the emergency dispatch strategy, and displaying the data of the target power equipment in the visualization tool to obtain the dispatch result corresponding to the emergency dispatch strategy.

[0065] For example, the initial operating status of the initial power equipment is displayed through big data visualization tools (such as PowerBI and Tableau), so that the dispatcher can intuitively understand the status information of the initial power equipment. At the same time, this visualization tool also displays the target power equipment started under the emergency dispatch strategy, so that the dispatch results corresponding to the emergency dispatch strategy can be obtained.

[0066] Specifically, visualization tools are used to display the initial operating status of the initial power equipment, and the target power equipment and its dispatch results are displayed according to the emergency dispatch strategy. This process helps to enhance the transparency of power equipment management and improve the efficiency and accuracy of decision-making.

[0067] In some embodiments, when the initial operating state is a preset state, the method further includes: performing an operation abnormality analysis on the initial operating data to obtain the abnormal position corresponding to the initial power equipment and the abnormal type corresponding to the abnormal position; determining an equipment repair strategy corresponding to the initial power equipment according to the abnormal position and the abnormal type.

[0068] Exemplarily, if the preset state is an abnormal state, then when the initial operating state is an abnormal state, statistical analysis, machine learning models, or rule engines are used to detect anomalies in the initial operating data. For example, determine the normal operating range of the initial power equipment, such as setting normal operating thresholds for equipment temperature, pressure, etc. These thresholds can be based on equipment specifications, historical data, or industry standards. By comparing the initial operating data with the set thresholds, data points that exceed the normal operating range are identified, and the abnormal locations of these abnormal data points (such as specific equipment components or sensors) are marked. Classify the detected abnormal data points and determine the abnormal type of each abnormal data point (such as overheating, overload, vibration abnormality, etc.). You can refer to the equipment's operating manual or failure mode analysis (FMEA) data to help with classification.

[0069] Exemplarily, all possible abnormal locations that need to be listed in the strategy mapping table are determined. For example, cooling system, generator set, transmission system, etc. All possible abnormal types are listed, such as overheating, overload, vibration abnormality, electrical failure, etc. Corresponding repair strategies are defined for each combination of abnormal location and abnormal type. Thus, a strategy mapping table is formed.

[0070] Exemplarily, the corresponding abnormal location is found in the strategy mapping table, such as the cooling system. The corresponding abnormal type is found in the row of the abnormal location, such as overheating. The corresponding device repair strategy is found at the intersection of the abnormal location and the abnormal type. For example, the repair strategy for overheating of the cooling system may be to clean the radiator and check the coolant.

[0071] Specifically, formulating a repair strategy based on the specific abnormality type and location can avoid blind repairs, thereby saving maintenance resources and costs. Clarifying the equipment repair strategy can avoid unnecessary repairs to the initial power equipment and reduce the cost of repairs and replacement parts. It can also improve the repair efficiency of the initial power equipment.

[0072] The embodiment of the present invention provides a method and system for intelligent dispatching of a power system based on big data. The method first collects initial operation data and initial power generation data of initial power equipment, and then performs detailed operation abnormality analysis on the initial power equipment based on the initial operation data, so as to determine the initial operation state of the initial power equipment. If the initial operation state of the initial power equipment meets the preset state, the target power consumption data of the target user is further obtained. Using these target power consumption data and initial power generation data, a corresponding emergency dispatching strategy is formulated to ensure the stability and reliability of power supply. The method effectively solves the problem that potential fault hazards cannot be identified in time in the related technology. By real-time monitoring and analyzing the operation state of the equipment, possible faults of the equipment can be warned in advance, avoiding the risk of power equipment shutdown caused by decision lag. Through accurate fault warning and timely adjustment decision, this method significantly improves the reliability and efficiency of power equipment operation, thereby optimizing the management of the power system, reducing the downtime of the equipment, and improving the stability of power supply.

[0073] See also Figure 2 , Figure 2 An embodiment of the present application provides an intelligent dispatching system 200 for an electric power system based on big data, and the intelligent dispatching system 200 for an electric power system based on big data includes a data acquisition module 201, a state determination module 202, a state judgment module 203, and a strategy determination module 204, wherein the data acquisition module 201 is used to obtain initial operation data and initial power generation data corresponding to the initial power equipment; the state determination module 202 is used to perform operation abnormality analysis on the initial power equipment according to the initial operation data to obtain the initial operation state corresponding to the initial power equipment; the state judgment module 203 is used to obtain target power consumption data corresponding to the target user when the initial operation state is a preset state; and the strategy determination module 204 is used to determine the emergency dispatching strategy corresponding to the initial power equipment according to the target power consumption data and the initial power generation data.

[0074] In some implementations, the state determination module 202 performs, during the process of performing abnormal analysis on the initial operation data to obtain the initial operation state corresponding to the initial power device:

[0075] Performing data preprocessing on the initial operation data to obtain target operation data;

[0076] Determine a sliding window and a sliding step, and cut the target operation data according to the sliding window and the sliding step to obtain window operation data;

[0077] An abnormality recognition model is used to perform abnormality analysis on the window operation data to obtain the initial operation state corresponding to the initial power equipment.

[0078] In some implementations, the state determination module 202 performs, during the process of performing abnormal analysis on the window operation data using the abnormal recognition model to obtain the initial operation state corresponding to the initial power device:

[0079] Obtaining a first center point and a second center point from the window operation data using a center determination layer of the anomaly recognition model;

[0080] Using the data clustering layer of the abnormality recognition model to perform cluster analysis on the window operation data according to the first center point and the second center point to obtain first cluster data and second cluster data;

[0081] Using the data analysis layer of the abnormality recognition model, performing data statistics on the first cluster data to obtain a first quantity and performing data statistics on the second cluster data to obtain a second quantity;

[0082] The initial operating state corresponding to the initial power equipment is determined according to the first quantity and the second quantity by using the abnormality determination layer of the abnormality recognition model.

[0083] In some implementations, the state determination module 203 performs, during the process of obtaining the target power consumption data corresponding to the target user:

[0084] Obtaining historical time and historical electricity consumption data corresponding to the historical time;

[0085] Performing model training according to the historical time and the historical electricity consumption data to obtain a time series prediction model;

[0086] Determine the target time, and perform power consumption prediction for the target time according to the time series prediction model to obtain the target power consumption data corresponding to the target user.

[0087] In some implementations, the big data-based power system intelligent dispatching system 200 further performs:

[0088] Obtain historical electricity price data and historical meteorological data;

[0089] Merging the historical electricity price data and the historical meteorological data to obtain a target electricity price and a target meteorological data corresponding to a target time point;

[0090] Analyze the fluctuation pattern of electricity price according to the target electricity price and the target weather, and obtain the correlation between electricity demand and price fluctuation;

[0091] Current meteorological data is determined, and a target electricity price corresponding to the current meteorological data is determined according to the current meteorological data and the association relationship.

[0092] In some implementations, the big data-based power system intelligent dispatching system 200 further performs:

[0093] Determine a visualization tool, and display the initial operating state corresponding to the initial power equipment according to the visualization tool;

[0094] The target power equipment is determined according to the emergency dispatch strategy, and the data of the target power equipment is displayed in the visualization tool to obtain the dispatch result corresponding to the emergency dispatch strategy.

[0095] In some implementations, when the initial operation state is a preset state, the state determination module 203 further executes:

[0096] Performing operation abnormality analysis on the initial operation data to obtain an abnormal position corresponding to the initial power equipment and an abnormal type corresponding to the abnormal position;

[0097] An equipment repair strategy corresponding to the initial power equipment is determined according to the abnormal location and the abnormal type.

[0098] In some embodiments, the big data-based power system intelligent dispatching system 200 can be applied to terminal devices.

[0099] It should be noted that technical personnel in the relevant field can clearly understand that, for the convenience and conciseness of description, the specific working process of the power system intelligent dispatching system 200 based on big data described above can refer to the corresponding process in the aforementioned power system intelligent dispatching method based on big data embodiment, and will not be repeated here.

[0100] See also Figure 3 , Figure 3 A schematic block diagram of the structure of a terminal device provided in an embodiment of the present invention.

[0101] like Figure 3 As shown, the terminal device 300 includes a processor 301 and a memory 302, and the processor 301 and the memory 302 are connected via a bus 303, such as an I2C (Inter-integrated Circuit) bus.

[0102] Specifically, the processor 301 is used to provide computing and control capabilities to support the operation of the entire terminal device. The processor 301 can be a central processing unit (CPU), and the processor 301 can also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0103] Specifically, the memory 302 may be a Flash chip, a read-only memory (ROM) disk, an optical disk, a USB flash drive, or a mobile hard disk.

[0104] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a partial structure related to the embodiment of the present invention, and does not constitute a limitation on the terminal device to which the embodiment of the present invention is applied. The specific server may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0105] The processor is used to run a computer program stored in a memory, and implement any one of the big data-based intelligent dispatching methods for a power system provided in an embodiment of the present invention when executing the computer program.

[0106] In one embodiment, the processor is used to run a computer program stored in the memory, and implements the following steps when executing the computer program:

[0107] Obtaining initial operation data and initial power generation data corresponding to the initial power equipment;

[0108] Performing an operation abnormality analysis on the initial power equipment according to the initial operation data to obtain an initial operation state corresponding to the initial power equipment;

[0109] When the initial operation state is a preset state, target power consumption data corresponding to the target user is obtained;

[0110] An emergency dispatch strategy corresponding to the initial power equipment is determined according to the target power consumption data and the initial power generation data.

[0111] In some implementations, the processor 301, during the process of performing abnormal analysis on the initial operation data to obtain the initial operation state corresponding to the initial power device, executes:

[0112] Performing data preprocessing on the initial operation data to obtain target operation data;

[0113] Determine a sliding window and a sliding step, and cut the target operation data according to the sliding window and the sliding step to obtain window operation data;

[0114] An abnormality recognition model is used to perform abnormality analysis on the window operation data to obtain the initial operation state corresponding to the initial power equipment.

[0115] In some implementations, the processor 301, in the process of performing abnormal analysis on the window operation data using the abnormal recognition model to obtain the initial operation state corresponding to the initial power equipment, executes:

[0116] Obtaining a first center point and a second center point from the window operation data using a center determination layer of the anomaly recognition model;

[0117] Using the data clustering layer of the abnormality recognition model to perform cluster analysis on the window operation data according to the first center point and the second center point to obtain first cluster data and second cluster data;

[0118] Using the data analysis layer of the abnormality recognition model, performing data statistics on the first cluster data to obtain a first quantity and performing data statistics on the second cluster data to obtain a second quantity;

[0119] The initial operating state corresponding to the initial power equipment is determined according to the first quantity and the second quantity using the abnormality determination layer of the abnormality recognition model.

[0120] In some implementations, during the process of obtaining the target power consumption data corresponding to the target user, the processor 301 executes:

[0121] Obtaining historical time and historical electricity consumption data corresponding to the historical time;

[0122] Performing model training according to the historical time and the historical electricity consumption data to obtain a time series prediction model;

[0123] Determine the target time, and perform power consumption prediction for the target time according to the time series prediction model to obtain the target power consumption data corresponding to the target user.

[0124] In some implementations, the processor 301 further executes:

[0125] Obtain historical electricity price data and historical meteorological data;

[0126] Merging the historical electricity price data and the historical meteorological data to obtain a target electricity price and a target meteorological data corresponding to a target time point;

[0127] Analyze the fluctuation pattern of electricity price according to the target electricity price and the target weather, and obtain the correlation between electricity demand and price fluctuation;

[0128] Current meteorological data is determined, and a target electricity price corresponding to the current meteorological data is determined according to the current meteorological data and the association relationship.

[0129] In some implementations, the processor 301 further executes:

[0130] Determine a visualization tool, and display the initial operating state corresponding to the initial power equipment according to the visualization tool;

[0131] The target power equipment is determined according to the emergency dispatch strategy, and the data of the target power equipment is displayed in the visualization tool to obtain the dispatch result corresponding to the emergency dispatch strategy.

[0132] In some implementations, the processor 301, when the initial operating state is a preset state, further executes:

[0133] Performing operation abnormality analysis on the initial operation data to obtain an abnormal position corresponding to the initial power equipment and an abnormal type corresponding to the abnormal position;

[0134] An equipment repair strategy corresponding to the initial power equipment is determined according to the abnormal location and the abnormal type.

[0135] It should be noted that technical personnel in the relevant field can clearly understand that, for the convenience and conciseness of description, the specific working process of the terminal device described above can refer to the corresponding process in the aforementioned embodiment of the intelligent dispatching method of the power system based on big data, and will not be repeated here.

[0136] An embodiment of the present invention also provides a storage medium for computer-readable storage, wherein the storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement any step of the power system intelligent dispatching method based on big data provided in the description of the embodiment of the present invention.

[0137] The storage medium may be an internal storage unit of the terminal device described in the foregoing embodiment, such as a hard disk or memory of the terminal device. The storage medium may also be an external storage device of the terminal device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc., equipped on the terminal device.

[0138] It will be appreciated by those skilled in the art that all or some of the steps, systems, and functional modules / units in the methods disclosed above may be implemented as software, firmware, hardware, and appropriate combinations thereof. In a hardware embodiment, the division between the functional modules / units mentioned in the above description does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed by several physical components in cooperation. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or implemented as hardware, or implemented as an integrated circuit, such as an application-specific integrated circuit. Such software may be distributed on a computer-readable medium, which may include a computer storage medium (or non-transitory medium) and a communication medium (or temporary medium). As known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer. In addition, it is well known to those of ordinary skill in the art that communication media typically contain computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0139] It should be understood that the term "and / or" used in the present specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, including these combinations. It should be noted that, in this article, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "including a..." does not exclude the presence of other identical elements in the process, method, article or system including the element.

[0140] The serial numbers of the embodiments of the present invention are only for description and do not represent the advantages and disadvantages of the embodiments. The above description is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A method for intelligent dispatching of power systems based on big data, It is characterized in that The method comprises: Obtaining initial operation data and initial power generation data corresponding to the initial power equipment; Performing an operation abnormality analysis on the initial power equipment according to the initial operation data to obtain an initial operation state corresponding to the initial power equipment; When the initial operation state is a preset state, target power consumption data corresponding to the target user is obtained; An emergency dispatch strategy corresponding to the initial power equipment is determined according to the target power consumption data and the initial power generation data.

2. The method according to claim 1, It is characterized in that The performing abnormal analysis on the initial operation data to obtain the initial operation state corresponding to the initial power equipment includes: Performing data preprocessing on the initial operation data to obtain target operation data; Determine a sliding window and a sliding step, and cut the target operation data according to the sliding window and the sliding step to obtain window operation data; An abnormality recognition model is used to perform abnormality analysis on the window operation data to obtain the initial operation state corresponding to the initial power equipment.

3. The method according to claim 2, It is characterized in that The using the abnormality recognition model to perform abnormality analysis on the window operation data to obtain the initial operation state corresponding to the initial power equipment includes: Obtaining a first center point and a second center point from the window operation data using a center determination layer of the anomaly recognition model; Using the data clustering layer of the abnormality recognition model to perform cluster analysis on the window operation data according to the first center point and the second center point to obtain first cluster data and second cluster data; Using the data analysis layer of the abnormality recognition model, performing data statistics on the first cluster data to obtain a first quantity and performing data statistics on the second cluster data to obtain a second quantity; The initial operating state corresponding to the initial power equipment is determined according to the first quantity and the second quantity using the abnormality determination layer of the abnormality recognition model.

4. The method according to claim 1, It is characterized in that The step of obtaining target electricity consumption data corresponding to the target user includes: Obtaining historical time and historical electricity consumption data corresponding to the historical time; Performing model training according to the historical time and the historical electricity consumption data to obtain a time series prediction model; Determine the target time, and perform power consumption prediction for the target time according to the time series prediction model to obtain the target power consumption data corresponding to the target user.

5. The method according to any one of claims 1 to 4, It is characterized in that The method further comprises: Obtain historical electricity price data and historical meteorological data; Merging the historical electricity price data and the historical meteorological data to obtain a target electricity price and a target meteorological data corresponding to a target time point; Analyze the fluctuation pattern of electricity price according to the target electricity price and the target weather, and obtain the correlation between electricity demand and price fluctuation; Current meteorological data is determined, and a target electricity price corresponding to the current meteorological data is determined according to the current meteorological data and the association relationship.

6. The method according to any one of claims 1 to 4, It is characterized in that The method further comprises: Determine a visualization tool, and display the initial operating state corresponding to the initial power equipment according to the visualization tool; The target power equipment is determined according to the emergency dispatch strategy, and the data of the target power equipment is displayed in the visualization tool to obtain the dispatch result corresponding to the emergency dispatch strategy.

7. The method according to any one of claims 1 to 4, It is characterized in that When the initial operating state is a preset state, the method further includes: Performing operation abnormality analysis on the initial operation data to obtain an abnormal position corresponding to the initial power equipment and an abnormal type corresponding to the abnormal position; An equipment repair strategy corresponding to the initial power equipment is determined according to the abnormal location and the abnormal type.

8. An intelligent dispatching system for power systems based on big data, It is characterized in that include: A data acquisition module, used to obtain initial operation data and initial power generation data corresponding to the initial power equipment; A state determination module, configured to perform an operation abnormality analysis on the initial power equipment according to the initial operation data to obtain an initial operation state corresponding to the initial power equipment; A state judgment module, used for obtaining target power consumption data corresponding to a target user when the initial operation state is a preset state; A strategy determination module is used to determine the emergency dispatch strategy corresponding to the initial power equipment according to the target power consumption data and the initial power generation data.

9. A terminal device, It is characterized in that The terminal device includes a processor and a memory; The memory is used to store computer programs; The processor is used to execute the computer program and implement the big data-based intelligent dispatching method for a power system as described in any one of claims 1 to 7 when executing the computer program.

10. A computer storage medium for computer storage, It is characterized in that The computer storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps of the big data-based power system intelligent dispatching method described in any one of claims 1 to 7.

Images