Electricity collection intelligent anti-interference method and system in heterogeneous network environment

Abstract

The invention discloses a power utilization acquisition intelligent anti-interference method in a heterogeneous network environment, and the method comprises the following steps: S1, carrying out the information collection of a power utilization acquisition node through a heterogeneous network, and obtaining the power utilization acquisition information; s2, constructing a feature data set, and training a BP neural network until convergence; s3, acquiring electric power acquisition information in real time, preprocessing the data, and sending the data into the training network to obtain a decision result; s4, the engine judges whether the decision parameters meet the current requirements or not according to the feedback transmission performance, and real-time dynamic adjustment is conducted according to the judgment result to resist interference, the invention further discloses a system for achieving the method, and the system belongs to the technical field of electric power data collection. The neural network can receive the processed signal in real time and quickly generate a decision result in a complex environment, dynamic optimization adjustment of system parameters is achieved to effectively suppress interference, and therefore it is ensured that the system can still operate stably in the complex interference environment and efficient data transmission is achieved.

Description

Technical Field

[0001] The present invention belongs to the technical field of electric power data collection, and specifically relates to an intelligent anti-interference method and system for electric power collection in a heterogeneous network environment. Background Art

[0002] With the transformation and upgrading of smart grids, the power information collection system, as an important part of smart grids, undertakes the important task of real-time and accurate collection and transmission of power information. However, in heterogeneous network environments, power information collection equipment often faces a variety of interference problems, such as electromagnetic interference, communication channel congestion, and data loss and bit errors caused by complex network environments, which affect the reliability and accuracy of power information collection. Therefore, improving the anti-interference ability of the power system is crucial to ensure power supply quality and stable operation. Summary of the invention

[0003] Purpose of the invention: The present invention makes improvements to the problems existing in the above-mentioned prior art, that is, the present invention discloses an intelligent anti-interference method and system for electricity consumption collection in a heterogeneous network environment, which is used to effectively improve the accuracy and stability of data collection in a heterogeneous network environment.

[0004] To achieve the above object, the present invention adopts the following technical solutions: In the first aspect, the intelligent anti-interference method for power consumption collection in a heterogeneous network environment includes the following steps: S1 builds a heterogeneous network through broadband power carrier and micro-power wireless transmission dual-mode communication, builds a power consumption network based on historical power consumption information, sets power consumption collection nodes based on power consumption network information, collects information from power consumption collection nodes through heterogeneous networks, and obtains power consumption collection information; S2 continuously detects received signals, analyzes signal spectrum to identify interference types and characteristic parameters, constructs feature data sets, and trains BP neural network until convergence; S3 obtains power collection information in real time, and after data preprocessing, it is sent to the training network to obtain decision results; The S4 engine determines whether the decision parameters meet the current requirements based on the feedback of transmission performance, and makes real-time dynamic adjustments based on the judgment results to resist interference.

[0005] Preferably, the step S1 specifically includes: S11 builds a heterogeneous network through broadband power carrier and micro-power wireless transmission dual-mode communication, and the heterogeneous network includes multiple signal acquisition and transmission channels; S12 obtains historical electricity consumption information, builds an electricity consumption collection network based on the historical electricity consumption information, and determines electricity consumption collection nodes in the electricity consumption collection network; S13: marking the collection nodes in the heterogeneous network according to the connection relationship between the power consumption collection nodes and the channels in the heterogeneous network, and obtaining the collection marking nodes; S14 obtains the preset collection channel of the corresponding collection and annotation node in the heterogeneous network, collects power consumption information of the collection and annotation node, and obtains power consumption collection information.

[0006] Preferably, the step S2 specifically includes: S21 detects the received signal multiple times through spectrum analysis and energy detection algorithms, analyzes the signal spectrum to identify the interference type and characteristic parameters.

[0007] S22 uses interference type, interference-to-noise ratio, number of available frequency subbands, and interference suppression method as input to obtain system bit error rate and average information rate under different conditions and build a training sample library; S23 uses the sample library to train the BP neural network until convergence.

[0008] Preferably, the step S3 specifically includes: S31 obtains power information in real time through heterogeneous networks and normalizes it to ensure that the data is within a reasonable range; The input layer of the S32BP neural network receives the pre-processed interference information and power parameters, and the output layer generates decision results and determines the optimal system parameter settings to adapt to the current environment.

[0009] Preferably, the step S4 specifically includes: S41 According to the interference type and interference parameters, the network can decide the number of available frequency sub-bands, avoid the interference frequency bands, automatically adjust the system parameters, and select the appropriate interference suppression method to cope with different interference environments; S42 can also determine whether the current decision meets the requirements based on the feedback transmission performance. If not, the anti-interference strategy is further adjusted.

[0010] Second, the intelligent anti-interference system for power collection in a heterogeneous network environment includes: A network construction and collection module is configured to: construct a heterogeneous network through broadband power carrier and micro-power wireless transmission dual-mode communication, construct a power consumption network according to historical power consumption information, set power consumption collection nodes according to power consumption network information, collect power consumption information from power consumption collection nodes through the heterogeneous network, and obtain power consumption collection information; The signal detection and interference analysis module is configured as follows: in different scenarios, it detects the received signal multiple times, analyzes the signal spectrum characteristics, identifies the interference type and characteristic parameters, and constructs a characteristic data set for training the BP neural network; A BP neural network training module is configured as follows: using the interference feature data set to train the BP neural network until the network converges, designing the input layer, hidden layer and output layer of the BP neural network, using the interference feature data set to train the network, optimizing the network weights and biases and evaluating the network performance through the loss function and accuracy; The real-time decision-making and dynamic adjustment module is configured as follows: obtaining power collection information in real time, pre-processing the data and sending it to the trained BP neural network, obtaining the decision results, and dynamically adjusting the system parameters according to the transmission performance feedback to resist interference.

[0011] Preferably, the network construction acquisition module includes: A heterogeneous network construction module, which is configured to: construct a heterogeneous network through broadband power carrier and micro-power wireless transmission dual-mode communication, wherein the heterogeneous network includes multiple signal acquisition and transmission channels; A power consumption network construction module is configured to: obtain historical power consumption information, construct a power consumption collection network based on the historical power consumption information, and determine power consumption collection nodes in the power consumption collection network; The node marking module is configured to: mark the collection nodes in the heterogeneous network according to the connection relationship between the power consumption collection nodes and the channels in the heterogeneous network, and obtain the collection marking nodes; The power consumption collection module is configured to obtain a preset collection channel of a corresponding collection and annotation node in a heterogeneous network to collect power consumption information from the collection and annotation node to obtain power consumption collection information.

[0012] Preferably, the signal detection and interference analysis module includes: The signal detection and spectrum analysis module is configured to: detect the received signal multiple times in different scenarios, analyze the signal spectrum characteristics, and identify the interference type, characteristic parameters and power information; The feature data set construction module is configured as follows: using interference type, interference-to-noise ratio, number of available frequency sub-bands, and interference suppression method as input, obtaining system bit error rate and average information rate under different conditions, and constructing a training sample library.

[0013] Preferably, the BP neural network training module includes: A BP neural network training module is configured as follows: using the interference feature data set to train the BP neural network until the network converges, designing the input layer, hidden layer and output layer of the BP neural network, using the interference feature data set to train the network, optimizing the network weights and biases and evaluating the network performance through the loss function and accuracy; The signal preprocessing module is configured to obtain power collection information in real time, normalize the data, filter, denoise and other operations, and send it to the BP neural network.

[0014] Preferably, the real-time decision-making and dynamic adjustment module includes: The real-time decision-making and dynamic adjustment module is configured as follows: obtaining power collection information in real time, pre-processing the data and sending it to the trained BP neural network, obtaining the decision results, and dynamically adjusting the system parameters according to the transmission performance feedback to resist interference.

[0015] Beneficial effects: In the present invention, a broadband power carrier and micro-power wireless transmission dual-mode communication heterogeneous network and a power consumption network are constructed, and a power consumption collection node is set. The power consumption information of the power consumption collection node is collected through the heterogeneous network. At the same time, the received signal is detected multiple times in different scenarios, and the signal spectrum characteristics are analyzed to identify the interference type and characteristic parameters, and a characteristic data set is constructed for training the BP neural network. Through training, the weights and biases of the neural network are optimized so that it can converge quickly and generate the best anti-interference strategy for different interference scenarios. After the training is completed, the neural network can receive the processed signal in real time and quickly generate decision results in a complex environment, realize dynamic optimization and adjustment of the system parameters to effectively suppress interference, thereby ensuring that the system can still operate stably and achieve efficient data transmission in a complex interference environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a flow chart of the intelligent anti-interference technology for power collection in a heterogeneous network environment in the present invention; Figure 2 This is an anti-interference real-time decision diagram based on BP neural network in the present invention. DETAILED DESCRIPTION

[0017] The specific embodiments of the present invention are described in detail below.

[0018] The "range" disclosed in the present invention is defined in the form of a lower limit and an upper limit, and a given range is defined by selecting a lower limit and an upper limit, and the selected lower limit and upper limit define the boundaries of the particular range. The range defined in this way can be inclusive or exclusive of the end values, and can be arbitrarily combined, that is, any lower limit can be combined with any upper limit to form a range. For example, if a range of 10 to 50 is listed for a specific parameter, it is understood that the range of 10 to 40 and 20 to 50 is also expected. In addition, if the minimum range values ​​1 and 2 are listed, and if the maximum range values ​​3, 4 and 5 are listed, the following ranges can all be expected: 1 to 3, 1 to 4, 1 to 5, 2 to 3, 2 to 4 and 2 to 5. In this application, unless otherwise specified, the range of values ​​"a to b" represents an abbreviation of any real number combination between a and b, where a and b are both real numbers. For example, the range of values ​​"0 to 5" means that all real numbers between "0 to 5" have been fully listed in this article, and "0 to 5" is only an abbreviation of these numerical combinations.

[0019] Unless otherwise specified, all embodiments and optional embodiments of the present application can be combined with each other to form a new technical solution.

[0020] Unless otherwise specified, all technical features and optional technical features of this application can be combined with each other to form a new technical solution.

[0021] If there is no special explanation, all steps of the present application can be performed sequentially or randomly, preferably sequentially. For example, the method includes steps (a) and (b), which means that the method may include steps (a) and (b) performed sequentially, or may include steps (b) and (a) performed sequentially. For example, the method may further include step (c), which means that step (c) may be added to the method in any order. For example, the method may include steps (a), (b) and (c), or may include steps (a), (c) and (b), or may include steps (c), (a) and (b), etc.

[0022] If there is no special explanation, the "include" and "comprising" mentioned in this application represent open-ended or closed-ended expressions. For example, the "include" and "comprising" may represent that other components not listed may also be included or only the listed components may be included or only the listed components may be included.

[0023] Unless otherwise specified, the reaction is carried out at room temperature and pressure.

[0024] Unless otherwise specified, all parts or percentages are by weight.

[0025] In the present invention, all substances used are known substances and can be purchased or synthesized by known methods.

[0026] In the present invention, the devices or equipment used are all conventional devices or equipment known in the art and are commercially available.

[0027] The specific implementation of the intelligent anti-interference method and system for power collection in a heterogeneous network environment of the present invention is further described below in conjunction with the embodiments. The intelligent anti-interference method and system for power collection in a heterogeneous network environment of the present invention is not limited to the description of the following embodiments.

[0028] Embodiment 1: Intelligent anti-interference method for power consumption collection in heterogeneous network environment, such as Figure 1 As shown, the following steps are included: Step 1: Build a dual-mode heterogeneous network to obtain electricity consumption information.

[0029] Step 1: construct a heterogeneous network through broadband power carrier and micro-power wireless transmission dual-mode communication, wherein the heterogeneous network includes multiple signal acquisition and transmission channels; Step 2: Obtain historical electricity consumption information, build an electricity consumption collection network based on the historical electricity consumption information, and determine the electricity consumption collection nodes in the electricity consumption collection network; Step 3: According to the connection relationship between the power consumption collection node and each channel in the heterogeneous network, the collection nodes are marked in the heterogeneous network to obtain the collection marked nodes; Step 4: Obtain the preset collection channel of the corresponding collection and annotation node in the heterogeneous network to collect power consumption information of the collection and annotation node to obtain the power consumption collection information.

[0030] Step 2: Detect the received signal multiple times in different scenarios, analyze the signal spectrum to identify the interference type and characteristic parameters, build a feature data set, and train the BP neural network until convergence.

[0031] In the first step, the received signal is detected multiple times through spectrum analysis and energy detection algorithms, and the signal spectrum is analyzed to identify the interference type and characteristic parameters (such as interference power, frequency matching, frequency band factor, etc.). The interference type, interference-to-noise ratio, number of available frequency sub-bands, and interference suppression method are used as input to obtain the system bit error rate and average information rate under different conditions, and build a training sample library.

[0032] In the second step, the samples with the largest objective function values ​​under different interference types and JNR are used as training samples, and the objective function values ​​are used to measure the system performance, including anti-interference performance and transmission efficiency, which is expressed as: ; They are normalization by minimizing the bit error rate and normalization by maximizing the average information transmission rate. are their weights respectively. Use the sample library to train the BP neural network until convergence.

[0033] Step 3: Obtain power collection information in real time and send it to Figure 2 Train the network to get the decision result.

[0034] Step 1: Through heterogeneous networks, power information is acquired in real time and normalized to ensure that the data is within a reasonable range. The formula is as follows:

[0035] ; in, is the input parameter, and are the maximum and minimum values ​​of the parameter respectively.

[0036] In the second step, the BP neural network input layer receives the pre-processed interference information and power parameters, and the output layer generates a decision result, deciding on the best system parameter settings to adapt to the current environment, such as spectrum resource allocation, interference suppression methods (frequency domain interference suppression, time domain interference suppression, transform domain interference suppression), etc.

[0037] Step 4: Anti-interference decision and dynamic adjustment According to the interference type and interference parameters, the network can determine the number of available frequency sub-bands, avoid interference frequency bands, automatically adjust system parameters, and select appropriate interference suppression methods to cope with different interference environments. According to the feedback transmission performance (such as bit error rate, information transmission rate, etc.), it can also be judged whether the current decision meets the requirements. If not, the anti-interference strategy can be further adjusted.

[0038] The intelligent anti-interference system for power collection in a heterogeneous network environment includes: A heterogeneous network construction module, used to construct a heterogeneous network through broadband power carrier and micro-power wireless transmission dual-mode communication, wherein the heterogeneous network includes multiple signal acquisition and transmission channels; A power consumption network construction module is used to obtain historical power consumption information, construct a power consumption collection network based on the historical power consumption information, and determine the power consumption collection nodes in the power consumption collection network; A node labeling module is used to label the collection nodes in the heterogeneous network according to the connection relationship between the power consumption collection nodes and the channels in the heterogeneous network, and obtain the collection labeling nodes; The power consumption collection module is used to obtain the preset collection channel of the corresponding collection and marking node in the heterogeneous network to collect power consumption information of the collection and marking node to obtain the power consumption collection information.

[0039] The signal detection and spectrum analysis module detects the received signal multiple times in different scenarios, analyzes the signal spectrum characteristics, and identifies the interference type, characteristic parameters and power information.

[0040] The feature data set construction module takes the interference type, interference-to-noise ratio, number of available frequency sub-bands, and interference suppression method as inputs to obtain the system bit error rate and average information rate under different conditions and construct a training sample library.

[0041] The BP neural network training module uses the interference feature data set to train the BP neural network until the network converges, designs the input layer (interference type, interference parameters, etc.), hidden layer and output layer (anti-interference strategy) of the BP neural network, uses the interference feature data set to train the network, optimizes the network weights and biases, and evaluates the network performance through loss function and accuracy.

[0042] The signal preprocessing module obtains power collection information in real time, normalizes, filters, removes noise and other operations on the data, and sends it to the BP neural network; The real-time decision-making and dynamic adjustment module obtains power collection information in real time, pre-processes the data and sends it to the trained BP neural network to obtain the decision results, and dynamically adjusts the system parameters (such as channel selection, spectrum resource allocation, interference suppression method, etc.) according to the transmission performance feedback to resist interference.

[0043] In this application, a broadband power carrier and micro-power wireless transmission dual-mode communication heterogeneous network and power consumption network are constructed, power consumption collection nodes are set, and power consumption information is collected from the power consumption collection nodes through the heterogeneous network. At the same time, the received signal is detected multiple times in different scenarios, and the signal spectrum characteristics are analyzed to identify the interference type and characteristic parameters, and a characteristic data set is constructed for training the BP neural network. Through training, the weights and biases of the neural network are optimized so that it can converge quickly and generate the best anti-interference strategy for different interference scenarios. After the training is completed, the neural network can receive the processed signal in real time and quickly generate decision results in a complex environment, realizing dynamic optimization and adjustment of system parameters to effectively suppress interference, thereby ensuring that the system can still operate stably and achieve efficient data transmission in a complex interference environment.

[0044] The above describes the embodiments of the present invention in detail. However, the present invention is not limited to the above embodiments, and various changes can be made within the knowledge of ordinary technicians in the relevant technical field without departing from the purpose of the present invention.

Claims

1. An intelligent anti-interference method for power consumption collection in a heterogeneous network environment, characterized in that: The following steps are involved: S1 builds a heterogeneous network through broadband power carrier and micro-power wireless transmission dual-mode communication, builds a power consumption network based on historical power consumption information, sets power consumption collection nodes based on power consumption network information, collects information from power consumption collection nodes through heterogeneous networks, and obtains power consumption collection information; S2 continuously detects received signals, analyzes signal spectrum to identify interference types and characteristic parameters, constructs characteristic data sets, and trains BP neural network until convergence; S3 obtains power collection information in real time, and after data preprocessing, it is sent to the training network to obtain decision results; The S4 engine determines whether the decision parameters meet the current requirements based on the feedback of transmission performance, and makes real-time dynamic adjustments based on the judgment results to resist interference.

2. The intelligent anti-interference method for power collection in a heterogeneous network environment according to claim 1 is characterized in that: The step S1 specifically includes: S11 builds a heterogeneous network through broadband power carrier and micro-power wireless transmission dual-mode communication, and the heterogeneous network includes multiple signal acquisition and transmission channels; S12 obtains historical electricity consumption information, builds an electricity consumption collection network based on the historical electricity consumption information, and determines electricity consumption collection nodes in the electricity consumption collection network; S13: marking the collection nodes in the heterogeneous network according to the connection relationship between the power consumption collection nodes and the channels in the heterogeneous network, and obtaining the collection marking nodes; S14 obtains the preset collection channel of the corresponding collection and annotation node in the heterogeneous network, collects power consumption information of the collection and annotation node, and obtains power consumption collection information.

3. The intelligent anti-interference method for power collection in a heterogeneous network environment according to claim 1 is characterized in that: The step S2 specifically includes: S21 detects the received signal multiple times through spectrum analysis and energy detection algorithms, analyzes the signal spectrum to identify the interference type and characteristic parameters; S22 uses interference type, interference-to-noise ratio, number of available frequency subbands, and interference suppression method as input to obtain system bit error rate and average information rate under different conditions and build a training sample library; S23 uses the sample library to train the BP neural network until convergence.

4. The intelligent anti-interference method for power collection in a heterogeneous network environment according to claim 1 is characterized in that: The step S3 specifically includes: S31 obtains power information in real time through heterogeneous networks and normalizes it to ensure that the data is within a reasonable range; The input layer of the S32BP neural network receives the pre-processed interference information and power parameters, and the output layer generates decision results and determines the optimal system parameter settings to adapt to the current environment.

5. The intelligent anti-interference method for power collection in a heterogeneous network environment according to claim 1 is characterized in that: The step S4 specifically includes: S41 According to the interference type and interference parameters, the network can decide the number of available frequency sub-bands, avoid the interference frequency bands, automatically adjust the system parameters, and select the appropriate interference suppression method to cope with different interference environments; S42 can also determine whether the current decision meets the requirements based on the feedback transmission performance. If not, the anti-interference strategy is further adjusted.

6. The intelligent anti-interference system for power collection in a heterogeneous network environment is characterized by: The method for implementing any one of claims 1 to 5 comprises: A network construction and collection module is configured to: construct a heterogeneous network through broadband power carrier and micro-power wireless transmission dual-mode communication, construct a power consumption network according to historical power consumption information, set power consumption collection nodes according to power consumption network information, collect power consumption information from power consumption collection nodes through the heterogeneous network, and obtain power consumption collection information; The signal detection and interference analysis module is configured as follows: in different scenarios, it detects the received signal multiple times, analyzes the signal spectrum characteristics, identifies the interference type and characteristic parameters, and constructs a characteristic data set for training the BP neural network; A BP neural network training module is configured as follows: using the interference feature data set to train the BP neural network until the network converges, designing the input layer, hidden layer and output layer of the BP neural network, using the interference feature data set to train the network, optimizing the network weights and biases and evaluating the network performance through the loss function and accuracy; The real-time decision-making and dynamic adjustment module is configured as follows: obtaining power collection information in real time, pre-processing the data and sending it to the trained BP neural network, obtaining the decision results, and dynamically adjusting the system parameters according to the transmission performance feedback to resist interference.

7. The intelligent anti-interference system for power collection in a heterogeneous network environment as claimed in claim 6, characterized in that: The network construction acquisition module includes: A heterogeneous network construction module, which is configured to: construct a heterogeneous network through broadband power carrier and micro-power wireless transmission dual-mode communication, wherein the heterogeneous network includes multiple signal acquisition and transmission channels; A power consumption network construction module is configured to: obtain historical power consumption information, construct a power consumption collection network based on the historical power consumption information, and determine power consumption collection nodes in the power consumption collection network; The node marking module is configured to: mark the collection nodes in the heterogeneous network according to the connection relationship between the power consumption collection nodes and the channels in the heterogeneous network, and obtain the collection marking nodes; The power consumption collection module is configured to obtain a preset collection channel of a corresponding collection and annotation node in a heterogeneous network to collect power consumption information from the collection and annotation node to obtain power consumption collection information.

8. The intelligent anti-interference system for power collection in a heterogeneous network environment as claimed in claim 6, characterized in that: The signal detection and interference analysis module comprises: The signal detection and spectrum analysis module is configured to: detect the received signal multiple times in different scenarios, analyze the signal spectrum characteristics, and identify the interference type, characteristic parameters and power information; The feature data set construction module is configured as follows: using interference type, interference-to-noise ratio, number of available frequency sub-bands, and interference suppression method as input, obtaining system bit error rate and average information rate under different conditions, and constructing a training sample library.

9. The intelligent anti-interference system for power collection in a heterogeneous network environment as claimed in claim 6, characterized in that: The BP neural network training module includes: A BP neural network training module is configured as follows: using the interference feature data set to train the BP neural network until the network converges, designing the input layer, hidden layer and output layer of the BP neural network, using the interference feature data set to train the network, optimizing the network weights and biases and evaluating the network performance through the loss function and accuracy; The signal preprocessing module is configured to obtain power collection information in real time, normalize the data, filter, denoise and other operations, and send it to the BP neural network.

10. The intelligent anti-interference system for power collection in a heterogeneous network environment as claimed in claim 6, characterized in that: The real-time decision-making and dynamic adjustment module includes: The real-time decision-making and dynamic adjustment module is configured as follows: obtaining power collection information in real time, pre-processing the data and sending it to the trained BP neural network, obtaining the decision results, and dynamically adjusting the system parameters according to the transmission performance feedback to resist interference.

Images