Power system analysis early warning method and system based on big data

Abstract

The invention discloses an electric power system analysis early warning method and system based on big data, and the method comprises the steps: collecting and obtaining electric power data, and storing the electric power data to a data storage system; performing statistical analysis on the power data to obtain distribution, trend and periodic analysis results of the power data; based on the analysis result, inputting the power data into a support vector machine model for prediction, and obtaining a prediction result; and judging whether the prediction result is abnormal or not by utilizing a decision function, and sending out a corresponding early warning signal. A support vector machine model is used for prediction, whether a prediction result is abnormal or not is judged through a decision function, and an early warning signal is sent out in time, so that the accuracy and reliability of power system prediction are improved, power load abnormity can be effectively recognized, and through the steps of feature extraction, model training, evaluation optimization and the like, the accuracy and reliability of power system prediction are improved. And the performance of the early warning system is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of power analysis, and in particular to a power system analysis and early warning method and system based on big data. Background Art

[0002] A power system based on big data refers to a system that uses big data technology and analysis methods to manage and optimize the operation of the power system. It collects, stores and analyzes a large amount of power data to provide real-time monitoring, prediction and decision support to improve the reliability, efficiency and safety of the power system. Applications and advantages of power systems based on big data: Through big data analysis, the power system can monitor the state, load, voltage and other parameters of the power grid in real time. This enables power grid operators to better understand the operation of the power system, promptly identify and solve potential problems, and improve the reliability and stability of the power grid. Using big data analysis and machine learning algorithms, the power system can predict power demand and help power companies and suppliers optimize power production and distribution to meet demand and reduce costs. Prediction models can provide accurate power demand forecasts based on historical data, weather data, user behavior and other factors, thereby optimizing the dispatch and operation of the power system. Big data analysis can monitor abnormal conditions and faults in the power system and issue alarms in a timely manner. By analyzing information such as equipment sensor data and power load, the risk of equipment failure can be predicted, maintenance measures can be taken in advance, and power outage time and maintenance costs can be reduced. Big data analysis can help users and energy managers better understand energy usage, identify areas of energy waste and inefficiency, and provide optimization suggestions. By real-time monitoring and analysis of energy data, the power system can help users formulate energy management strategies, reduce energy consumption, and achieve the goals of energy conservation and emission reduction.

[0003] However, it is currently impossible to detect power quality problems in advance and propose preventive measures, which comprehensively affects the power quality level of the power grid. It is also impossible to provide early warning information and propose corresponding preventive measures, increasing the impact of power quality disturbances on the transmission network. Summary of the invention

[0004] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0005] In view of the above existing problems, the present invention is proposed. Therefore, the present invention provides a power system analysis and early warning method based on big data to solve the problem that the existing technology cannot detect power quality problems in advance and propose preventive measures.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides a power system analysis and early warning method based on big data, comprising:

[0008] Collect and acquire power data, and store the power data in a data storage system;

[0009] Performing statistical analysis on the power data to obtain distribution, trend and periodicity analysis results of the power data;

[0010] Based on the analysis result, the power data is input into a support vector machine model for prediction to obtain a prediction result;

[0011] A decision function is used to determine whether the prediction result is abnormal, and a corresponding warning signal is issued.

[0012] As a preferred solution of the power system analysis and early warning method based on big data described in the present invention, wherein: inputting the power data into the support vector machine model for prediction includes:

[0013] Extracting effective features of historical power data, and using the effective features for support vector machine model training;

[0014] Using the trained support vector machine model to predict the power data;

[0015] The prediction includes two stages: the first stage is for 1h-1.5h, and the second stage is for 2h-2.5h of power data load. The prediction results are judged to determine whether there is any abnormality in the power load;

[0016] The results of phase 2 were compared with those of phase 1 to evaluate the model, and parameter adjustment and feature selection were used to improve the performance of the support vector machine model.

[0017] As a preferred solution of the power system analysis and early warning method based on big data described in the present invention, it also includes:

[0018] Use the trained model to predict future power data load. Based on the prediction results and the set thresholds, determine whether there is any power load abnormality and issue a corresponding warning signal.

[0019] As a preferred solution of the power system analysis and early warning method based on big data described in the present invention, the decision function includes:

[0020] The decision function calculation formula is expressed as:

[0021] f(x)=sign(w T *x+b)

[0022] Among them, w is the weight vector of the hyperplane, x is the feature vector of the power data sample, b is the bias value of the hyperplane, ^T represents the transpose of the vector, and the sign function represents the sign.

[0023] As a preferred solution of the big data-based power system analysis and early warning method described in the present invention, the effective characteristics include the average load, maximum load, minimum load, and load change rate per hour.

[0024] As a preferred solution of the power system analysis and early warning method based on big data described in the present invention, the support vector machine model training includes:

[0025] Performing pre-feature scaling and standardization on the effective features;

[0026] The support vector machine model uses the kernel function to correctly separate samples of different categories and find an optimal hyperplane;

[0027] By optimizing the objective function, the optimal hyperplane parameters are solved;

[0028] After the training is completed, the decision boundary is constructed according to the obtained hyperplane parameters. For new power data samples, the feature vector of the power data sample is substituted into the hyperplane equation, and the category of the sample is determined according to the positive or negative result, that is, the prediction is made by calculating its position on the decision boundary, and the power data sample point X is selected, and the signed distance from the power data sample point X to the hyperplane is calculated.

[0029] As a preferred solution of the power system analysis and early warning method based on big data described in the present invention, the collecting and obtaining of power data includes:

[0030] Use hardware equipment to collect power data and set the power data collection frequency and sampling interval;

[0031] Hardware equipment includes smart meters, sensors, remote terminal units, communication equipment, data storage equipment, control center systems, and monitoring equipment;

[0032] Power data includes power load, voltage, frequency, and temperature.

[0033] In a second aspect, the present invention provides a system for analyzing and early warning of a power system based on big data, comprising:

[0034] An acquisition module, used for collecting and acquiring power data, and storing the power data in a data storage system;

[0035] An analysis module, used to perform statistical analysis on the power data to obtain distribution, trend and periodicity analysis results of the power data;

[0036] A prediction module, used for inputting the power data into a support vector machine model for prediction based on the analysis result to obtain a prediction result;

[0037] The judgment module is used to use the decision function to judge whether the prediction result is abnormal and issue a corresponding warning signal.

[0038] In a third aspect, the present invention provides a computing device, comprising:

[0039] Memory and processor;

[0040] The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the power system analysis and early warning method based on big data are implemented.

[0041] In a fourth aspect, the present invention provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the power system analysis and early warning method based on big data.

[0042] Compared with the prior art, the invention has the following beneficial effects: the power system analysis and early warning method based on big data collects and stores power data, performs statistical analysis to obtain distribution, trend and periodic characteristics, and then uses the support vector machine model for prediction. It uses the decision function to determine whether the prediction result is abnormal, thereby issuing a warning signal in time. It not only improves the accuracy and reliability of power system prediction, but also can effectively identify power load anomalies. Through the steps of feature extraction, model training and evaluation optimization, the performance of the early warning system is ensured. At the same time, it uses a variety of hardware equipment and comprehensive power data collection to provide a strong guarantee for the safe and stable operation of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0044] Figure 1 The present invention is a schematic diagram of the overall process of a power system analysis and early warning method based on big data according to an embodiment of the present invention. DETAILED DESCRIPTION

[0045] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0046] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0047] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0048] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0049] At the same time, in the description of the present invention, it should be noted that the orientations or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the orientations or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the system or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0050] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0051] Example 1

[0052] Reference Figure 1, is an embodiment of the present invention, and provides a power system analysis and early warning method based on big data, comprising:

[0053] S100: Collect and acquire power data, and store the power data in a data storage system;

[0054] In the embodiment of the present application, the power data is collected by hardware equipment, and the power data collection frequency and sampling interval are set;

[0055] In the embodiment of the present application, the hardware device includes a smart meter, a sensor, a remote terminal unit, a communication device, a data storage device, a control center system, and a monitoring device;

[0056] In the embodiment of the present application, the power data includes power load, voltage, frequency, and temperature.

[0057] Clean the collected power data, remove outliers and noise, ensure data quality, use interpolation methods to fill in missing data, and use moving average or exponential smoothing methods to smooth the data to reduce data volatility.

[0058] S102: Perform statistical analysis on the power data to obtain distribution, trend and periodicity analysis results of the power data;

[0059] Specifically, we use descriptive statistical methods in statistics, such as calculating the mean, median, mode, standard deviation, quartiles, etc. of the data to reveal the central tendency and dispersion of the data. These statistics can help us understand the overall distribution pattern of the data, identify possible outliers or extreme situations, and provide important references for subsequent data processing and analysis.

[0060] In the embodiment of the present application, the core of the trend analysis of power data is to reveal the law of data change over time, and adopt the time series analysis method, such as drawing a line graph, calculating a moving average, and performing trend line fitting, to observe the change trend of data in different time periods. Through trend analysis, the possible trend of power load in the future period can be predicted;

[0061] In an embodiment of the present application, a periodic analysis is performed on the power data, and the periodic analysis aims to identify periodic patterns in the data, which is crucial for understanding the seasonal changes and periodic load demands of the power system. Statistical methods such as Fourier transform, autocorrelation function, and periodogram are used to detect the periodic components in the data and determine their cycle lengths. These periodic information helps to more accurately predict future power load fluctuations in the future.

[0062] S104: Based on the analysis results, the power data is input into the support vector machine model for prediction to obtain the prediction results;

[0063] Preferably, effective features of historical power data are extracted, the effective features are used for support vector machine model training, and the trained support vector machine model is used to predict the power data;

[0064] In the embodiment of the present application, the effective features include the average load, maximum load, minimum load, and load change rate per hour.

[0065] Preferably, the prediction includes two stages, the first stage is for predicting the power data load of 1h-1.5h, and the second stage is for predicting the power data load of 2h-2.5h, and the prediction result is judged to determine whether there is power load abnormality;

[0066] It should be noted that for forecasts of different time lengths, the requirements for model accuracy will be different. The accuracy requirements for medium-term forecast models will increase. Within this time frame, the system will be affected by more external factors and changes, and the forecast error will be relatively large.

[0067] Preferably, the results of stage 2 are compared with the results of stage 1 to evaluate the model, and parameter adjustment and feature selection are used to improve the performance of the support vector machine model;

[0068] In an optional embodiment, the parameter adjustment method can be a random search or a grid search; the grid search searches for the best parameter combination by traversing multiple parameter combinations and uses cross-validation to evaluate the performance of each parameter combination; the random search randomly selects a parameter combination in the parameter space and uses cross-validation to evaluate the performance of each parameter combination. Compared with the grid search, the random search is more efficient in finding the best parameter combination.

[0069] Preferably, the trained model is used to predict the future power data load, and based on the prediction results and the set threshold, it is determined whether there is a power load anomaly, and a corresponding warning signal is issued.

[0070] In the embodiment of the present application, the support vector machine model training process is specifically as follows:

[0071] S1: Pre-feature scaling and standardization of effective features;

[0072] S2: The support vector machine model uses the kernel function to correctly separate samples of different categories and find an optimal hyperplane;

[0073] S3: Solve the optimal hyperplane parameters by optimizing the objective function;

[0074] S4: After the training is completed, a decision boundary is constructed based on the obtained hyperplane parameters. For new power data samples, the feature vector of the power data sample is substituted into the hyperplane equation, and the category to which the sample belongs is determined based on the positive or negative result, that is, prediction is made by calculating its position on the decision boundary, selecting the power data sample point X, and calculating the signed distance from the power data sample point X to the hyperplane.

[0075] It should be noted that the present invention can realize the prediction of future power data load by extracting effective features of historical power data and using them for training support vector machine models. The prediction process is divided into two stages, which not only improves the accuracy of the prediction, but also evaluates the model by comparing the results of the two stages, and then optimizes the model performance through parameter adjustment and feature selection; advanced technologies such as pre-feature scaling, standardization and kernel functions used in the training process of the support vector machine model ensure that the model can correctly classify samples and find the optimal hyperplane; the trained model is used to predict the future power data load, and whether there is an abnormal power load is determined based on the prediction results and the preset threshold, so as to issue a warning signal in time and enhance the reliability of the safe operation of the power system.

[0076] S106: Using the decision function to determine whether the prediction result is abnormal, and issuing a corresponding warning signal;

[0077] Preferably, the decision function calculation formula is expressed as:

[0078] f(x)=sign(w T *x+b)

[0079] Where w is the weight vector of the hyperplane, x is the feature vector of the power data sample, b is the bias value of the hyperplane, ^T represents the transpose of the vector, and the sign function represents the sign.

[0080] In the embodiments of the present application, the sign is a positive sign or a negative sign;

[0081] In an embodiment of the present application, an abnormal power load triggers an automation system, and the automation system triggers switching to a backup power source and adjusting load distribution.

[0082] It should be noted that the present invention comprehensively collects and processes power data, including using smart meters, sensors and other hardware devices to obtain multi-dimensional information such as power load, voltage, frequency, temperature, etc., and performs data cleaning and smoothing to ensure data quality; then, statistical methods are used to deeply analyze the distribution, trend and periodicity of the data to provide a solid foundation for prediction; on this basis, effective features are extracted to train the support vector machine model, and through two-stage prediction and model evaluation optimization, high-precision prediction of future power data load is achieved; decision functions are used to determine whether the prediction results are abnormal, and early warning signals are issued in time to trigger the response of the automation system, such as switching backup power supplies and adjusting load distribution, thereby improving the safe operation reliability and stability of the power system, which not only improves the prediction accuracy, but also effectively responds to power load abnormalities through intelligent means.

[0083] The above is a schematic scheme of a power system analysis and early warning method based on big data in this embodiment. It should be noted that the technical scheme of the power system analysis and early warning system based on big data and the technical scheme of the power system analysis and early warning method based on big data belong to the same concept. The details of the technical scheme of the power system analysis and early warning system based on big data in this embodiment that are not described in detail can all be referred to the description of the technical scheme of the power system analysis and early warning method based on big data.

[0084] The power system analysis and early warning system based on big data in this embodiment includes:

[0085] An acquisition module is used to collect and acquire power data and store the power data in a data storage system;

[0086] The analysis module is used to perform statistical analysis on power data and obtain the distribution, trend and periodicity analysis results of power data;

[0087] A prediction module is used to input the power data into a support vector machine model for prediction based on the analysis results to obtain prediction results;

[0088] The judgment module is used to use the decision function to determine whether the prediction result is abnormal and issue a corresponding warning signal.

[0089] This embodiment also provides a computing device, which is applicable to power system analysis and early warning based on big data, including:

[0090] Memory and processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the power system analysis and early warning method based on big data as proposed in the above embodiment.

[0091] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the power system analysis and early warning method based on big data proposed in the above embodiment is implemented.

[0092] The storage medium proposed in this embodiment and the method for implementing power system analysis and early warning based on big data proposed in the above embodiment belong to the same inventive concept. The technical details not fully described in this embodiment can be referred to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0093] Through the above description of the implementation methods, the technicians in the relevant field can clearly understand that the present invention can be implemented by means of software and necessary general hardware, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ReadOnly, Memory, ROM), random access memory (RandomAccess Memory, RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform the methods of various embodiments of the present invention.

[0094] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A power system analysis and early warning method based on big data, characterized in that: include: Collect and acquire power data, and store the power data in a data storage system; Performing statistical analysis on the power data to obtain distribution, trend and periodicity analysis results of the power data; Based on the analysis result, the power data is input into a support vector machine model for prediction to obtain a prediction result; A decision function is used to determine whether the prediction result is abnormal, and a corresponding warning signal is issued.

2. The power system analysis and early warning method based on big data according to claim 1, characterized in that: Inputting the power data into the support vector machine model for prediction includes: Extracting effective features of historical power data, and using the effective features for support vector machine model training; Using the trained support vector machine model to predict the power data; The prediction includes two stages: the first stage is for 1h-1.5h, and the second stage is for 2h-2.5h of power data load. The prediction results are judged to determine whether there is any abnormality in the power load; The results of phase 2 were compared with those of phase 1 to evaluate the model, and parameter adjustment and feature selection were used to improve the performance of the support vector machine model.

3. The power system analysis and early warning method based on big data according to claim 1 or 2, characterized in that: Also includes, Use the trained model to predict future power data load. Based on the prediction results and the set thresholds, determine whether there is any power load abnormality and issue a corresponding warning signal.

4. The power system analysis and early warning method based on big data according to claim 3 is characterized in that: The decision function includes, The decision function calculation formula is expressed as: f(x)=sign(w T *x+b) Among them, w is the weight vector of the hyperplane, x is the feature vector of the power data sample, b is the bias value of the hyperplane, ^T represents the transpose of the vector, and the sign function represents the sign.

5. The power system analysis and early warning method based on big data according to claim 3 is characterized in that: Valid characteristics include average load, maximum load, minimum load, and rate of change of load per hour.

6. The power system analysis and early warning method based on big data according to claim 5, characterized in that: Support vector machine model training includes, Performing pre-feature scaling and standardization on the effective features; The support vector machine model uses the kernel function to correctly separate samples of different categories and find an optimal hyperplane; By optimizing the objective function, the optimal hyperplane parameters are solved; After the training is completed, the decision boundary is constructed according to the obtained hyperplane parameters. For new power data samples, the feature vector of the power data sample is substituted into the hyperplane equation, and the category of the sample is determined according to the positive or negative result, that is, the prediction is made by calculating its position on the decision boundary, and the power data sample point X is selected, and the signed distance from the power data sample point X to the hyperplane is calculated.

7. The power system analysis and early warning method based on big data according to claim 1, characterized in that: The collection and acquisition of power data includes: Use hardware equipment to collect power data and set the power data collection frequency and sampling interval; Hardware equipment includes smart meters, sensors, remote terminal units, communication equipment, data storage equipment, control center systems, and monitoring equipment; Power data includes power load, voltage, frequency, and temperature.

8. A system for power system analysis and early warning based on big data, characterized in that: include, An acquisition module, used for collecting and acquiring power data, and storing the power data in a data storage system; An analysis module, used to perform statistical analysis on the power data to obtain distribution, trend and periodicity analysis results of the power data; A prediction module, used for inputting the power data into a support vector machine model for prediction based on the analysis result to obtain a prediction result; The judgment module is used to use the decision function to judge whether the prediction result is abnormal and issue a corresponding warning signal.

9. An electronic device, comprising: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the power system analysis and early warning method based on big data as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the power system analysis and early warning method based on big data as described in any one of claims 1 to 7.

Images