Power line carrier and wireless communication combined power data transmission method and system

Abstract

The invention provides a power line carrier and wireless communication combined power data transmission method and system, and the method comprises the steps: collecting the operation data of terminal power equipment in real time through terminal collection equipment in a power distribution area, and adding a timestamp for the data; and the hybrid communication sub-equipment transmits the operation data with the timestamp to the hybrid communication main equipment of the substation by using the power line carrier. And after receiving the data, the main device calculates the communication distance between the power distribution area and the transformer substation according to the timestamp information, and selects a proper communication mode. And the master device continues to monitor and calculate the bit error rate, obtains parameters such as the signal-to-noise ratio, the attenuation value and the interference intensity of the communication channel, and inputs the parameters into the pre-trained support vector machine to predict the current bit error rate. And based on a prediction result, a communication distance, a load and other factors, a pre-trained reinforcement learning model is adopted to adaptively select an optimal communication mode, and the communication mode is dynamically adjusted to optimize a data transmission effect.

Description

Technical Field

[0001] The present invention belongs to the technical field of data communication in power systems, and in particular relates to a method and system for power data transmission combining power carrier and wireless communication. Background Art

[0002] In the power system, the communication between data acquisition equipment and substation gateways usually faces problems such as high cost, low efficiency and environmental interference. Power line carrier (HPLC) and low power wide area network (LoRa) communication technologies each have their own advantages: HPLC is suitable for short-distance high-speed transmission within the power system, while LoRa is suitable for remote areas and low-power transmission. However, how to intelligently select the most appropriate communication method based on parameters such as communication quality and bit error rate, and dynamically adjust to improve communication quality and reduce costs, is still a technical problem. Summary of the invention

[0003] The purpose of the present invention is to overcome the defects of the above-mentioned prior art and to provide a power data transmission method and system combining power carrier and wireless communication.

[0004] The purpose of the present invention can be achieved by the following technical solutions:

[0005] In one aspect, the present invention provides a method for power data transmission combining power carrier and wireless communication, comprising the following steps:

[0006] Step S1: collect the operation data of the terminal power equipment in real time through the terminal collection equipment in the power distribution station area of ​​the power system;

[0007] Step S2: The hybrid communication sub-device connected to the terminal acquisition device of the power system distribution substation adds a timestamp to the operation data, and the hybrid communication sub-device uses the existing power line to transmit the operation data with timestamp information to the hybrid communication main device of the substation through the power carrier;

[0008] Step S3: After receiving the operation data with timestamp information, the hybrid communication master device calculates the communication distance between the end of the power system distribution area and the substation according to the timestamp information, the arrival time of the operation data and the power carrier transmission speed, and selects the communication mode according to the communication distance;

[0009] Step S4: the hybrid communication main device receives in real time the operation data sent by the hybrid communication sub-device through the communication mode selected in step S3, and calculates the bit error rate of the received operation data;

[0010] Step S5: Detect the communication channel through a real-time detection device to obtain the signal-to-noise ratio, attenuation value, interference intensity and data transmission rate of the communication channel;

[0011] Step S6: input the bit error rate, signal-to-noise ratio, attenuation value, interference intensity and data transmission rate into the pre-trained support vector machine, and output the predicted bit error rate of the current communication;

[0012] Step S7: Based on the predicted bit error rate, communication distance, and communication load, a pre-trained reinforcement learning model is used to select an adaptive communication mode;

[0013] Step S8: Dynamically switch the communication mode according to the feedback of reinforcement learning.

[0014] Furthermore, the communication method includes power carrier communication and wireless communication.

[0015] Furthermore, the selecting of the communication mode according to the communication distance includes: if the communication distance is greater than a first preset value, selecting the wireless communication mode for data transmission; if the communication distance is less than or equal to the first preset value, selecting the power carrier communication mode for data transmission.

[0016] Furthermore, the bit error rate of the received operation data is calculated, wherein the bit error rate calculation formula of the power carrier communication mode is:

[0017]

[0018] Among them, BER HPLC is the bit error rate of the power carrier communication mode, erfc(x) is the complementary error function, and SNR is the signal-to-noise ratio;

[0019] The formula for calculating the bit error rate of wireless communication is:

[0020]

[0021] Among them, BER LORA is the wireless communication bit error rate, SNR is the signal-to-noise ratio, and SF is the spreading factor.

[0022] Furthermore, the support vector machine training process includes: monitoring the communication quality of different communication modes in real time in the power system, and recording the communication quality data to be processed in each case;

[0023] Extracting features and performing standardization processing on the collected communication quality data to be processed to obtain communication quality data;

[0024] Using the collected communication quality data, a support vector machine model is trained through a supervised learning algorithm. The input of the support vector machine model is the communication quality data, and the output is the predicted bit error rate. During the model training process, cross-validation and grid search techniques are used to optimize the model parameters.

[0025] The accuracy of the model is verified through the test set, and the model parameters are adjusted according to the test results.

[0026] Furthermore, the communication quality data includes bit error rate, signal-to-noise ratio, attenuation value, interference intensity and data transmission rate.

[0027] Furthermore, the state space of the reinforcement learning model includes: predicted bit error rate, communication distance, and communication load.

[0028] Furthermore, the reinforcement learning model action space includes: selecting a power carrier communication mode and selecting a wireless communication mode.

[0029] Furthermore, the reinforcement learning model reward function is:

[0030]

[0031] Among them, R t is the reward value at the tth moment, BER t is the bit error rate of the communication link at time t, Latency t is the delay at time t, Throughput t is the data transmission rate at time t, Load t is the communication load at the tth moment, w1, w2, w3 are the weighted coefficients in the reward function respectively.

[0032] On the other hand, the present invention provides a power data transmission system combining power carrier and wireless communication, including: one or more terminal data acquisition devices, used to collect operating data in the power system; a power line carrier communication module and a LoRa wireless communication module, respectively used to transmit data through a power line carrier or a wireless signal; a support vector machine model module, capable of receiving communication quality data from the power line carrier communication module and the LoRa wireless communication module, and predicting the bit error rate of the communication link; a reinforcement learning module, used to adaptively select the best communication mode through the predicted bit error rate, communication distance, and communication load data.

[0033] Compared with the prior art, the present invention has the following advantages:

[0034] (1) The present invention combines power line carrier and LoRa wireless communication, and the present invention can dynamically select the most suitable communication mode according to the actual situation. Power line carrier is suitable for environments with good power line network and less signal interference, while LoRa wireless communication is suitable for scenarios with large signal attenuation and long transmission distance. Through this flexible combination, the system can ensure the efficiency and stability of data transmission in different working environments, greatly improving the adaptability of communication.

[0035] (2) The present invention uses a support vector machine model to accurately predict the bit error rate of the communication link, which helps to identify communication quality problems in advance. By learning the communication link characteristics in historical data, SVM can predict the communication quality under different environmental conditions and help the system make scientific communication mode selection decisions. The ability to predict the bit error rate enables the system to make more accurate judgments before data transmission, avoiding data transmission failure or inefficiency caused by improper selection of communication methods.

[0036] (3) The present invention uses a reinforcement learning mechanism to dynamically adjust the communication mode according to real-time environmental changes. Reinforcement learning optimizes the communication mode selection strategy by learning from historical feedback, thereby selecting the best communication mode under different communication loads, environmental noise, distance and other conditions. Reinforcement learning can continuously self-optimize, ensuring that the performance of the system continues to improve in long-term operation, avoiding the singleness and limitations of traditional fixed communication methods.

[0037] (4) The present invention can comprehensively evaluate the communication quality by designing a reasonable reward function and combining multi-dimensional indicators such as bit error rate, delay, transmission efficiency and load. This comprehensive evaluation method ensures that the system considers more comprehensive and scientific factors when selecting the communication method, so that the optimal communication link can be selected, improving the efficiency and stability of data transmission. The dynamic adjustment capability of the reward function can better cope with complex conditions such as changes in system load and network environment.

[0038] (5) The present invention monitors the environmental noise, communication distance, load and other factors of the communication link in real time, and the system can optimize and select the communication mode based on this information. This optimization strategy based on environmental factors and load can effectively avoid performance degradation caused by excessive load or poor communication environment. The system can adaptively select the most suitable communication mode, reduce resource waste, and improve the overall performance of the system.

[0039] (6) By combining support vector machines and reinforcement learning, the present invention can more accurately predict the quality of communication links and dynamically select the appropriate communication mode based on the prediction results. The support vector machine provides accurate bit error rate prediction, while reinforcement learning adjusts the communication mode selection based on real-time feedback and environmental changes. This combination makes the selection of communication mode more scientific, flexible, and has strong adaptability. This combination improves the intelligence level of the system and can effectively cope with the complex and changing power system environment.

[0040] (7) The system of the present invention can adaptively switch between power line carrier communication and LoRa wireless communication to adapt to different environmental conditions. For example, when the communication distance is far or the power line network quality is poor, the system can automatically select LoRa wireless communication, and when the power line network environment is good, the system selects power line carrier communication. This adaptive switching function greatly improves the reliability and flexibility of communication, reduces manual intervention, and improves the automation and intelligence level of the system.

[0041] (8) The present invention optimizes the selection of communication links based on the evaluation of multi-dimensional performance such as bit error rate, transmission rate, and delay, which not only improves the quality and efficiency of data transmission, but also reduces unnecessary waste of resources. Selecting power line carrier communication under appropriate circumstances can save wireless communication bandwidth and reduce communication costs; while selecting LoRa wireless communication can avoid connection failures caused by unstable or unreachable power line networks. Therefore, the system can efficiently utilize existing resources and save operating costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 For the present invention DETAILED DESCRIPTION

[0043] 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 should fall within the scope of protection of the present invention.

[0044] Embodiment 1:

[0045] This embodiment provides a power data transmission method combining power carrier and wireless communication, such as Figure 1 As shown, the following steps are included:

[0046] Step S1: collect the operation data of the terminal power equipment in real time through the terminal collection equipment in the power distribution station area of ​​the power system;

[0047] Step S2: The hybrid communication sub-device connected to the terminal acquisition device of the power system distribution substation adds a timestamp to the operation data, and the hybrid communication sub-device uses the existing power line to transmit the operation data with timestamp information to the hybrid communication main device of the substation through the power carrier;

[0048] Step S3: After receiving the operation data with timestamp information, the hybrid communication master device calculates the communication distance between the end of the power system distribution area and the substation according to the timestamp information, the arrival time of the operation data and the power carrier transmission speed, and selects the communication mode according to the communication distance;

[0049] Step S4: the hybrid communication main device receives in real time the operation data sent by the hybrid communication sub-device through the communication mode selected in step S3, and calculates the bit error rate of the received operation data;

[0050] Step S5: Detect the communication channel through a real-time detection device to obtain the signal-to-noise ratio, attenuation value, interference intensity and data transmission rate of the communication channel;

[0051] Step S6: input the bit error rate, signal-to-noise ratio, attenuation value, interference intensity and data transmission rate into the pre-trained support vector machine, and output the predicted bit error rate of the current communication;

[0052] Step S7: Based on the predicted bit error rate, communication distance, and communication load, a pre-trained reinforcement learning model is used to select an adaptive communication mode;

[0053] Step S8: Dynamically switch the communication mode according to the feedback of reinforcement learning.

[0054] The communication modes include power carrier communication and wireless communication.

[0055] The communication method is selected according to the communication distance, including: if the communication distance is greater than a first preset value, a wireless communication method is selected for data transmission; if the communication distance is less than or equal to the first preset value, a power carrier communication method is selected for data transmission.

[0056] Calculate the bit error rate of the received operation data, where the bit error rate calculation formula for the power carrier communication mode is:

[0057]

[0058] Among them, BER HPLC is the bit error rate of the power carrier communication mode, erfc(x) is the complementary error function, and SNR is the signal-to-noise ratio;

[0059] The formula for calculating the bit error rate of wireless communication is:

[0060]

[0061] Among them, BER LORA is the wireless communication bit error rate, SNR is the signal-to-noise ratio, and SF is the spreading factor.

[0062] The support vector machine training process includes: monitoring the communication quality of different communication modes in the power system in real time and recording the communication quality data to be processed in each case;

[0063] Extracting features and performing standardization processing on the collected communication quality data to be processed to obtain communication quality data;

[0064] The collected communication quality data is used to train the support vector machine model through a supervised learning algorithm. The input of the support vector machine model is the communication quality data, and the output is the predicted bit error rate. During the model training process, cross-validation and grid search techniques are used to optimize the model parameters.

[0065] The accuracy of the model is verified through the test set, and the model parameters are adjusted according to the test results.

[0066] Communication quality data includes bit error rate, signal-to-noise ratio, attenuation value, interference intensity and data transmission rate.

[0067] The state space of the reinforcement learning model includes: predicted bit error rate, communication distance, and communication load.

[0068] The action space of the reinforcement learning model includes: selecting the power carrier communication method and selecting the wireless communication method.

[0069] The reinforcement learning model reward function is:

[0070]

[0071] Among them, R t is the reward value at the tth moment, BER t is the bit error rate of the communication link at time t, Latency t is the delay at time t, Throughput t is the data transmission rate at time t, Load t is the communication load at the tth moment, w1, w2, w3 are the weighted coefficients in the reward function respectively.

[0072] Embodiment 2:

[0073] The parts not mentioned in this embodiment are the same as those in Embodiment 1.

[0074] The power system data transmission system of this embodiment mainly includes the following parts:

[0075] Terminal data collection equipment: multiple power devices, such as smart meters, sensors, etc., are used to collect power data in real time and transmit the data to the substation gateway through a communication link.

[0076] Substation gateway: responsible for receiving data from multiple terminal data acquisition devices and forwarding the data to the central control system according to the selected communication method.

[0077] Power line carrier communication module: used for data transmission via power lines, suitable for scenarios with good power line network coverage and low bit error rate.

[0078] LoRa wireless communication module: used for wireless data transmission, suitable for scenarios with long communication distances, complex environments, or strong power line interference.

[0079] Support vector machine model module: Based on historical communication data, predict the bit error rate of each communication link, thereby providing data support for the selection of communication mode.

[0080] Reinforcement learning module: Based on real-time feedback and historical data, dynamically adjust and select the appropriate communication method to optimize the overall performance of the system.

[0081] Reward function module: The reward value is calculated based on multi-dimensional indicators such as bit error rate, latency, transmission efficiency and load to guide the decision-making process of the reinforcement learning model.

[0082] The system collects power data through terminal data collection devices. The devices include smart meters, sensors, etc. The collected data may include voltage, current, frequency, load and other information. These data will be sent to the substation gateway through the communication module. In the initial stage, the communication system will use the support vector machine model to predict the bit error rate based on factors such as the distance between the terminal device and the gateway and the signal quality.

[0083] The SVM model training process includes: by collecting historical data, the SVM model is trained based on the following features: signal-to-noise ratio; attenuation value; interference intensity; data transmission rate; communication distance; system load, etc.

[0084] Through these features, the SVM model predicts the bit error rate of each communication link and provides guidance for the subsequent selection of communication methods.

[0085] The decision-making process of the reinforcement learning module includes: the system introduces a reinforcement learning module to further optimize the choice of communication mode. The reinforcement learning module will evaluate the current communication mode and select the optimal strategy based on the environmental state and the performance of the current communication link.

[0086] State space: includes the following information: predicted bit error rate; current communication distance; environmental noise; system load.

[0087] Action space: The action selected based on the current state is switching to power line carrier (HPLC) or LoRa wireless communication (LoRa).

[0088] Reward function: The system is optimized according to the following reward function formula:

[0089]

[0090] Among them, R t is the reward value at the tth moment, BER t is the bit error rate of the communication link at time t, Latencyt is the delay at time t, Throughput t is the data transmission rate at time t, Load t is the communication load at the tth moment, w1, w2, w3 are the weighted coefficients in the reward function respectively.

[0091] By monitoring the network status in real time, the reinforcement learning module will dynamically adjust the communication mode selection based on performance evaluations in multiple dimensions such as bit error rate (BER), latency, transmission efficiency (Throughput), and system load (Load).

[0092] Based on the decision-making of the reinforcement learning model, the system dynamically selects the best communication method suitable for the current communication link status. Specifically, when the system evaluates that the current communication link has a low bit error rate, short latency and low load, the system may choose power line carrier (HPLC) for communication; when the communication distance is long, the bit error rate is high or the environmental noise is large, LoRa wireless communication is selected to ensure stability.

[0093] The system will adjust its decision-making strategy based on real-time feedback to improve the reliability and efficiency of data transmission.

[0094] The system continuously optimizes the communication mode selection based on the feedback of communication quality and transmission efficiency. After each communication, the system records data such as bit error rate (BER), latency, and transmission rate (Throughput) and inputs them into the reinforcement learning model. The reinforcement learning module continuously adjusts the selection strategy based on these feedback signals to optimize system performance.

[0095] Through continuous exploration-exploitation strategy, the system can adapt to different environmental changes and network loads and always choose the best communication method.

[0096] Assume that at a certain moment, the system finds that the bit error rate of the power line carrier communication (HPLC) is 0.01, the delay is 20ms, the data transmission rate is 100kbps, and the system load is 50%. At the same time, the bit error rate of the LoRa communication link is 0.1, the delay is 100ms, the data transmission rate is 10kbps, and the load is 30%.

[0097] Bit Error Rate (BER):

[0098]

[0099] Latency:

[0100]

[0101] Transmission efficiency (Throughput) / load (Load):

[0102]

[0103] Substituting these values ​​into the reward function, the system will get the following reward values:

[0104] HPLC:R HPLC =w1·0.9901+w2·0.0476+w3·2

[0105] LoRa:R LoRa =w1·0.9091+w2·0.0099+w3·0.3333

[0106] The system dynamically selects the communication mode according to the calculated reward value. If the reward value of HPLC is higher, the system will give priority to power line carrier communication; if the reward value of LoRa is higher, wireless communication will be given priority.

[0107] Through the implementation of the present invention, the power system can intelligently switch the communication mode according to real-time feedback in a complex communication environment, significantly improving the reliability, timeliness and efficiency of data transmission. The system can adapt to different network conditions and flexibly select the appropriate communication mode according to the predicted bit error rate, delay, load and other factors, reducing the bit error rate and delay in communication, and improving the intelligence level of the power system.

[0108] If the above functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program code.

[0109] The above 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 power data transmission method combining power carrier and wireless communication, characterized in that: The following steps are involved: Step S1: collect the operation data of the terminal power equipment in real time through the terminal collection equipment in the power distribution station area of ​​the power system; Step S2: The hybrid communication sub-device connected to the terminal acquisition device of the power system distribution substation adds a timestamp to the operation data, and the hybrid communication sub-device uses the existing power line to transmit the operation data with timestamp information to the hybrid communication main device of the substation through the power carrier; Step S3: After receiving the operation data with timestamp information, the hybrid communication master device calculates the communication distance between the end of the power system distribution area and the substation according to the timestamp information, the arrival time of the operation data and the power carrier transmission speed, and selects the communication mode according to the communication distance; Step S4: the hybrid communication main device receives in real time the operation data sent by the hybrid communication sub-device through the communication mode selected in step S3, and calculates the bit error rate of the received operation data; Step S5: Detect the communication channel through a real-time detection device to obtain the signal-to-noise ratio, attenuation value, interference intensity and data transmission rate of the communication channel; Step S6: input the bit error rate, signal-to-noise ratio, attenuation value, interference intensity and data transmission rate into the pre-trained support vector machine, and output the predicted bit error rate of the current communication; Step S7: Based on the predicted bit error rate, communication distance, and communication load, a pre-trained reinforcement learning model is used to select an adaptive communication mode; Step S8: Dynamically switch the communication mode according to the feedback of reinforcement learning.

2. The method for transmitting power data by combining power carrier and wireless communication according to claim 1, characterized in that: The communication method includes power carrier communication and wireless communication.

3. A power data transmission method combining power carrier and wireless communication according to claim 1 or 2, characterized in that: The selecting of the communication mode according to the communication distance includes: if the communication distance is greater than a first preset value, selecting the wireless communication mode for data transmission; if the communication distance is less than or equal to the first preset value, selecting the power carrier communication mode for data transmission.

4. The method for transmitting power data by combining power carrier and wireless communication according to claim 1, characterized in that: The bit error rate of the received operation data is calculated, wherein the bit error rate calculation formula of the power carrier communication mode is: erfc(x)=1-erf(x) Among them, BER HPLC is the bit error rate of the power carrier communication mode, erfc(x) is the complementary error function, and SNR is the signal-to-noise ratio; The formula for calculating the bit error rate of wireless communication is: Among them, BER LORA is the wireless communication bit error rate, SNR is the signal-to-noise ratio, and SF is the spreading factor.

5. The method for transmitting power data by combining power carrier and wireless communication according to claim 1, characterized in that: The support vector machine training process includes: monitoring the communication quality of different communication modes in real time in the power system, and recording the communication quality data to be processed in each case; Extracting features and performing standardization processing on the collected communication quality data to be processed to obtain communication quality data; Using the collected communication quality data, a support vector machine model is trained through a supervised learning algorithm. The input of the support vector machine model is the communication quality data, and the output is the predicted bit error rate. During the model training process, cross-validation and grid search techniques are used to optimize the model parameters. The accuracy of the model is verified through the test set, and the model parameters are adjusted according to the test results.

6. The method for transmitting power data by combining power carrier and wireless communication according to claim 1, characterized in that: The communication quality data includes bit error rate, signal-to-noise ratio, attenuation value, interference intensity and data transmission rate.

7. The method for transmitting power data by combining power carrier and wireless communication according to claim 1, characterized in that: The reinforcement learning model state space includes: predicted bit error rate, communication distance, and communication load.

8. The method for transmitting power data by combining power carrier and wireless communication according to claim 1, characterized in that: The reinforcement learning model action space includes: selecting a power carrier communication mode and selecting a wireless communication mode.

9. The method for transmitting power data by combining power carrier and wireless communication according to claim 1, characterized in that: The reinforcement learning model reward function is: Among them, R t is the reward value at the tth moment, BER t is the bit error rate of the communication link at time t, Latency t is the delay at time t, Throughput t is the data transmission rate at time t, Load t is the communication load at the tth moment, w1, w2, w3 are the weighted coefficients in the reward function respectively.

10. A power data transmission system combining power carrier and wireless communication, characterized in that: include: One or more terminal data collection devices for collecting operation data in the power system; The power line carrier communication module and the LoRa wireless communication module are used to transmit data through the power line carrier or the wireless signal respectively; the support vector machine model module can receive the communication quality data from the power line carrier communication module and the LoRa wireless communication module and predict the bit error rate of the communication link; The reinforcement learning module is used to adaptively select the best communication mode based on the predicted bit error rate, communication distance, and communication load data.

Images