Method for collecting and managing electric energy information of electric power system

Abstract

The invention discloses an electric energy information acquisition and management method for an electric power system, and the method is characterized in that the method comprises the steps: S1, obtaining electric quantity, voltage and current data in real time through an electric energy acquisition device, and transmitting the data to a data acquisition system; s2, performing data cleaning, calibration, denoising and data visualization operation on the acquired electric quantity, voltage and current data; s3, performing energy consumption monitoring analysis according to the processed electric energy data, identifying an energy consumption peak period, and executing corresponding energy-saving measures for optimization; and S4, based on an optimization result, performing energy supply prediction by using a neural network. According to the invention, the neural network is introduced for power data acquisition, intelligent prediction of future energy demands is realized, and the problem of energy use optimization based on data driving is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of power management, and in particular to a method for collecting and managing electric energy information of a power system. Background Art

[0002] Electric energy information collection and management involves multiple aspects such as electric energy data collection, storage, processing, analysis, management, monitoring and prediction; effectively collecting, analyzing and managing electric energy data is of great significance for optimizing energy utilization, improving energy efficiency and realizing smart grids.

[0003] However, the security and reliability of traditional power system data collection are insufficient. Local storage is vulnerable to security threats, and data loss or tampering may have serious consequences. The existing power system data collection lacks the support of neural network algorithms, lacks the ability to intelligently predict future energy demand, and is difficult to achieve data-driven energy use optimization. Summary of the invention

[0004] To solve the above problems, the present invention provides a method for collecting and managing electric energy information in an electric power system. By introducing a neural network for electric power data collection, intelligent prediction of future energy demand is achieved, solving the problem of data-driven energy utilization optimization.

[0005] The present invention provides a method for collecting and managing electric energy information in an electric power system. The specific technical solution is as follows:

[0006] S1: Obtain power, voltage and current data in real time through the power collection device and transmit it to the data collection system;

[0007] S2: Perform data cleaning, calibration, denoising and data visualization operations on the collected power, voltage and current data;

[0008] S3: Based on the processed power data, perform energy consumption monitoring and analysis, identify the peak period of energy consumption, and implement corresponding energy-saving measures for optimization;

[0009] S4: Based on the optimization results, neural network is used to predict energy supply.

[0010] Furthermore, in step S1, the data cleaning includes missing value identification and processing, duplicate data removal and outlier processing; the calibration includes linear calibration, nonlinear calibration and calibration using calibration factors; the denoising includes smoothing denoising, filtering denoising and wavelet transform denoising.

[0011] Furthermore, the data collected in step S1 is stored on a local server and / or a cloud platform.

[0012] Furthermore, the data acquisition system is also connected to the user end data via Ethernet, and the user end obtains the actual energy consumption by accessing the data platform of the data acquisition system.

[0013] Furthermore, the electric energy collection device adopts an electric energy sensor or a smart meter.

[0014] Furthermore, the electric energy sensor and the smart meter are connected to at least one group of independent power supply units, and the power supply units include a light energy conversion power supply module, a thermal energy conversion power supply module and a mechanical vibration energy conversion power supply module.

[0015] Furthermore, in step S4, the energy supply forecast is performed in the following specific process:

[0016] Build a neural network model and train it, and input the result data optimized in step S3 into the forward propagation module of the trained model;

[0017] The data output by the forward module is input into the loss function to calculate the difference between the predicted value and the true value;

[0018] According to the calculated output results of the loss function, the weights and biases between the layers of the model are updated through the back-propagation module.

[0019] Furthermore, the forward propagation module is calculated as follows:

[0020] [z [l] =W [l] a [l-1] +b [l] ][a [l] =g(z [l] )]

[0021] Where [l] represents the number of layers in the network, W [l] is the weight matrix between the [l]th layer and the [l-1]th layer, b [l] is the bias, a [l-1] is the activation value of the previous layer, z [l] is the weighted input and g(·) is the activation function.

[0022] The beneficial effects of the present invention are as follows:

[0023] 1. The present invention collects data such as power consumption, voltage, current, etc. through power sensors or smart meters, monitors power usage in real time, and transmits the collected data to a data acquisition system through wireless communication or a wired network. The collected data is stored on a local server or a cloud platform to ensure the security and reliability of the data, which is convenient for future analysis and application. Users can obtain the actual energy consumption in a timely manner by accessing the cloud platform; the power sensor or smart meter is connected to an independent power supply unit, and provides stable power by collecting environmental energy. It is independent of the external power grid to a certain extent, reducing the operating cost of the power system, while increasing the stability and anti-interference ability of the system and reducing the frequency of replacement and maintenance.

[0024] 2. The present invention provides a reliable data basis for subsequent energy consumption monitoring and optimization by cleaning, calibrating, denoising and visualizing the collected data, which facilitates the analysis of data for real-time energy consumption monitoring, identification of energy consumption peaks, discovery of energy waste, and taking corresponding energy-saving measures based on the real-time energy consumption monitoring results to reduce energy costs and improve energy utilization efficiency.

[0025] 3. The present invention uses a neural network to predict energy supply, realize predictive management of the entire energy supply chain, optimize energy use, and improve energy efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 It is a schematic flow chart of the method of the present invention. DETAILED DESCRIPTION

[0027] The following description clearly and completely describes the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only 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.

[0028] In the description of the embodiments of the present invention, it should be noted that the indicated orientation or positional relationship is based on the orientation or positional relationship shown in the accompanying drawings, or the orientation or positional relationship in which the invention product is usually placed when in use, or the orientation or positional relationship commonly understood by those skilled in the art, or the orientation or positional relationship in which the invention product is usually placed when in use, which is only for the convenience of describing the present invention and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. In addition, the terms "first" and "second" are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

[0029] In the description of the embodiments of the present invention, it is also necessary to explain that, unless otherwise clearly specified and limited, the terms "set" and "connection" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a direct connection, or an indirect connection through an intermediate medium. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0030] Example 1

[0031] Embodiment 1 of the present invention discloses a method for collecting and managing electric energy information of an electric power system, such as Figure 1 As shown, the details are as follows:

[0032] S1: Obtain power, voltage and current data in real time through the power collection device and transmit it to the data collection system;

[0033] As a preferred embodiment, the collected data is stored on a local server and / or a cloud platform, ensuring the security and reliability of the data.

[0034] As a preferred embodiment, the data acquisition system is also connected to the user end data via Ethernet, and the user end obtains the actual energy consumption by accessing the data platform of the data acquisition system.

[0035] As a preferred embodiment, the electric energy collection device adopts an electric energy sensor or a smart meter.

[0036] As a preferred embodiment, the electric energy sensor and the smart meter are connected to at least one set of independent power supply units, and the power supply units include a light energy conversion power supply module, a thermal energy conversion power supply module and a mechanical vibration energy conversion power supply module;

[0037] By converting solar energy, thermal energy and mechanical vibration energy into electrical energy, a continuous and stable energy supply is provided to the power collection device, ensuring long-term and stable power information collection.

[0038] Specifically, by installing power sensors on power lines or electrical equipment, real-time data on power consumption, voltage and current can be obtained to achieve real-time monitoring of power usage.

[0039] S2: Perform data cleaning, calibration, denoising and data visualization operations on the collected power, voltage and current data;

[0040] Data cleaning is to remove or correct erroneous, duplicate or incomplete data in the data set to improve data quality.

[0041] As a preferred embodiment, the data cleaning includes:

[0042] Identify missing values: Check for missing values ​​in the dataset, usually represented by NaN or NULL;

[0043] Count the number and distribution of missing values ​​to determine whether they need to be filled or deleted;

[0044] Handling missing values:

[0045] If the proportion of missing values ​​is small, they can be deleted directly;

[0046] Specifically, the missing values ​​can be filled using the mean, median, or mode, or estimated using interpolation methods (e.g., linear interpolation);

[0047] Remove duplicate data:

[0048] Check the data set for duplicate rows and remove duplicates;

[0049] Handling outliers:

[0050] Identify outliers using statistical methods such as Z-score or IQR, and choose to delete or replace them with appropriate values.

[0051] As a preferred embodiment, data calibration is a process of adjusting the measured value to a standard or reference value to ensure data accuracy. First, a standard reference value (for example, a standard voltage or current source) is determined for calibration. Data calibration includes:

[0052] Linear calibration: If the data is linearly related to the standard value, a linear regression model can be used for calibration to adjust the measured value.

[0053] Non-linear calibration:

[0054] For nonlinear relationships, polynomial regression or other nonlinear models can be used for calibration.

[0055] Apply the calibration factor:

[0056] Calculate the calibration factor (ratio of calibrated value to measured value) and apply it to all measurements.

[0057] As a preferred embodiment, the data denoising operation is used to reduce the noise in the data to improve the clarity and accuracy of the signal, including:

[0058] Smoothing method:

[0059] Use moving average method to smooth the data, choose the window size to adapt to the characteristics of the data; use exponential smoothing to reduce random fluctuations.

[0060] filter:

[0061] A low-pass filter (such as a Butterworth filter) is used to remove high-frequency noise. Specifically, a Savitzky-Golay filter can be used to reduce noise while maintaining signal characteristics.

[0062] Wavelet Transform:

[0063] Using wavelet transform technology for denoising can effectively retain signal characteristics while removing noise.

[0064] As a preferred embodiment, the data visualization operation is to display the cleaned and processed data in a graphical manner for easy analysis and understanding, including:

[0065] Draw a timing diagram:

[0066] Use a line graph to plot the changing trends of power, voltage, and current, with time on the X-axis and the measured value on the Y-axis.

[0067] Plot a histogram:

[0068] Use histograms to display the distribution of power, voltage, and current to help identify central tendency and skewness in the data.

[0069] Draw a scatter plot:

[0070] Show the relationship between current and voltage through a scatter plot to observe linear or nonlinear relationships.

[0071] Draw a box plot:

[0072] Use box plots to show the distribution of data, including median, quartiles, and outliers.

[0073] Draw a heat map:

[0074] For multi-dimensional data, heat maps can be used to show the relationship between power, voltage, and current to facilitate identification of correlations.

[0075] S3: Based on the processed power data, perform energy consumption monitoring and analysis, identify the peak period of energy consumption, and implement corresponding energy-saving measures for optimization, reduce energy costs and improve energy utilization efficiency;

[0076] Specifically, after identifying the peak energy consumption periods, corresponding energy-saving measures can be taken for these time periods, such as:

[0077] Adjust equipment operating hours: adjust the operating hours of equipment with higher energy consumption to off-peak hours;

[0078] Optimize load management: limit the power output of certain equipment during peak hours;

[0079] Implement demand response strategies: guide users to reduce energy consumption during peak hours.

[0080] S4: Based on the optimization results, neural networks are used to predict energy supply, including predictions of energy market prices, supply volumes, and demand patterns, to help users make more effective energy purchasing decisions and optimize energy use.

[0081] As a preferred embodiment, the energy supply forecasting process is as follows:

[0082] Build a neural network model and train it, and input the result data optimized in step S3 into the forward propagation module of the trained model;

[0083] The forward propagation module is calculated as follows:

[0084] [z [l] =W [l] a [l-1] +b [l] ][a [l] =g(z [l] )]

[0085] Where [l] represents the number of layers in the network, W [l] is the weight matrix between the [l]th layer and the [l-1]th layer, b [l] is the bias, a [l-1] is the activation value of the previous layer, z [l] is the weighted input and g(·) is the activation function.

[0086] The data output by the forward module is input into the loss function to calculate the difference between the predicted value and the true value;

[0087] Specifically, the loss function may adopt mean square error loss or cross entropy loss.

[0088] According to the calculated output of the loss function, the weights and biases between the layers of the model are updated through the back-propagation module; the back-propagation module updates the parameters in the opposite direction of the gradient by calculating the partial derivative of the loss function for each weight and bias;

[0089] Specifically, edge computing can also be introduced to update parameters and improve the efficiency and real-time performance of data processing.

[0090] The present invention is not limited to the above-mentioned specific embodiments, but extends to any new features or any new combination disclosed in this specification, as well as any new method or process steps or any new combination disclosed.

Claims

1. A method for collecting and managing electric energy information in a power system, characterized in that: include: S1: Obtain power, voltage and current data in real time through the power collection device and transmit it to the data collection system; S2: Perform data cleaning, calibration, denoising and data visualization operations on the collected power, voltage and current data; S3: Based on the processed power data, perform energy consumption monitoring and analysis, identify the peak period of energy consumption, and implement corresponding energy-saving measures for optimization; S4: Based on the optimization results, neural network is used to predict energy supply.

2. The method for collecting and managing electric energy information of a power system according to claim 1, characterized in that: In step S1, the data cleaning includes missing value identification and processing, duplicate data removal and outlier processing; the calibration includes linear calibration, nonlinear calibration and calibration using calibration factors; the denoising includes smoothing denoising, filtering denoising and wavelet transform denoising.

3. The method for collecting and managing electric energy information of a power system according to claim 1, characterized in that: In step S1, the collected and processed data is stored on a local server and / or a cloud platform.

4. The method for collecting and managing electric energy information of a power system according to claim 3, characterized in that: The data acquisition system is also connected to the user end data via Ethernet, and the user end obtains the actual energy consumption by accessing the data platform of the data acquisition system.

5. The method for collecting and managing electric energy information of a power system according to claim 1, characterized in that: The electric energy collection device adopts an electric energy sensor or a smart electric meter.

6. The method for collecting and managing electric energy information of a power system according to claim 5, characterized in that: The electric energy sensor and the smart electric meter are connected to at least one group of independent power supply units, and the power supply units include a light energy conversion power supply module, a thermal energy conversion power supply module and a mechanical vibration energy conversion power supply module.

7. The method for collecting and managing electric energy information of a power system according to claim 1, characterized in that: In step S4, the energy supply forecast is performed in the following specific process: Build a neural network model and train it, and input the result data optimized in step S3 into the forward propagation module of the trained model; The data output by the forward module is input into the loss function to calculate the difference between the predicted value and the true value; According to the calculated output results of the loss function, the weights and biases between the layers of the model are updated through the back-propagation module.

8. The method for collecting and managing electric energy information of a power system according to claim 7, characterized in that: The forward propagation module is calculated as follows: [z [l] =W [l] a [l-1] +b [l] [a [l] =g(z [l] )] Where [l] represents the number of layers in the network, W [l] is the weight matrix between the [l]th layer and the [l-1]th layer, b [l] is the bias, a [l-1] is the activation value of the previous layer, z [l] is the weighted input and g(·) is the activation function.

Images