Remote monitoring method for operation data of smart meter box

Abstract

The present invention discloses a method for remote monitoring of operating data of a smart meter box, which relates to the field of smart grid technology and includes the following steps: the smart meter sends a test data packet through an initially set transmission window to verify the communication quality; the communication quality data during the test data packet sending process is acquired in real time, and the acquired raw data is pre-processed to generate a data set containing a variety of communication quality indicators. By monitoring the communication quality in real time and intelligently evaluating the interference risk, the smart meter can adaptively adjust the transmission window and method to improve data transmission efficiency and reduce loss and delay. When the spectrum interference is strong, the transmission window is reduced and segmented transmission is used to ensure data stability and avoid communication interruption or data distortion. This method ensures that the power monitoring system obtains accurate data in a timely manner, improves monitoring capabilities, fault warning accuracy and energy management efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of smart grids, and in particular to a method for remotely monitoring operating data of a smart electricity meter box. Background Art

[0002] Smart meter box remote monitoring of operational data integrates sensors, communication modules, and processing units within the meter box to collect real-time data on energy metering (such as voltage, current, power, and energy consumption) and operating status (such as temperature, cover opening, tilt, and abnormal power usage). This data is then transmitted remotely to a backend management platform via wireless communications (such as NB-IoT, 4G, and LoRa), enabling remote monitoring, data analysis, and abnormality warnings of the meter box's operation. This approach enhances the intelligent management capabilities of the power supply system, helping operations and maintenance departments implement remote inspections, fault diagnosis, and energy consumption management, reducing labor costs and improving power supply safety and efficiency.

[0003] Existing technologies have the following shortcomings: The wireless communication modules of smart meters typically rely on specific wireless frequency bands (such as GPRS, NB-IoT, and LoRa) for data transmission, enabling remote monitoring and real-time feedback of meter data. However, existing technologies can expose wireless communication modules to spectrum interference from other devices, such as radio transmitters, communication towers, and radar systems. The electromagnetic wave signals emitted by these devices may overlap or be close to the operating frequency band of the smart meter, causing signal interference.

[0004] This spectrum interference can cause instability in the smart meter's wireless communication module during data transmission, manifesting as data transmission failures, data loss, or transmission delays. Due to the interference signal, the data communication link between the smart meter and the remote monitoring platform may not be established, or frequent transmission errors may occur during the communication process, resulting in the meter data being unable to be uploaded to the monitoring system in a timely and accurate manner. This not only affects the accuracy of real-time monitoring and data updates, but may also prevent the power management platform from obtaining information on the power system's operating status, further affecting critical decisions such as power dispatch, fault warning, and energy consumption management.

[0005] In severe cases, persistent spectrum interference can completely disable smart meter wireless communications, paralyzing the power monitoring system. In this case, the monitoring platform cannot access any data from the meter, making it unable to detect equipment failures or anomalies in a timely manner. This significantly increases the risks and potential risks of power system operations and maintenance, potentially leading to power supply disruptions, increased operating costs, and safety issues.

[0006] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not form the prior art that is already known to a person of ordinary skill in the art. Summary of the Invention

[0007] The purpose of the present invention is to provide a method for remotely monitoring the operating data of a smart meter box. By monitoring communication quality in real time and intelligently assessing interference risks, the smart meter can adaptively adjust the transmission window and mode to improve data transmission efficiency and reduce loss and delay. When spectrum interference is strong, the transmission window is narrowed and segmented transmission is used to ensure data stability and avoid communication interruptions or data distortion. This method ensures that the power monitoring system obtains accurate data in a timely manner, improving monitoring capabilities, fault warning accuracy, and energy management efficiency, thereby addressing the problems mentioned in the background technology.

[0008] In order to achieve the above object, the present invention provides the following technical solution: a method for remotely monitoring the operation data of a smart meter box, comprising the following steps:

[0009] The smart meter sends a test data packet through the initially set transmission window to verify the communication quality;

[0010] Acquire communication quality data in real time during the test data packet transmission process, and pre-process the acquired raw data to generate a data set containing multiple communication quality indicators;

[0011] Extract key indicators reflecting spectrum interference during data transmission from the data set, conduct comprehensive analysis on the extracted key indicators, and quantify the degree of interference during the current data transmission process;

[0012] The analyzed key indicators are input into a pre-trained machine learning model, which is used to intelligently evaluate the data transmission process and classify the transmission process based on the evaluation results.

[0013] Based on the evaluation results of the machine learning model, the data transmission process is divided into two categories: "with interference risk" and "without interference risk";

[0014] For situations where there is no interference risk, increase the data transmission window to improve transmission efficiency. For situations where there is interference risk, reduce the data transmission window, reduce the amount of data transmitted, and use a segmented transmission strategy to split the data into several equivalent data blocks and send them in batches to ensure stable data transmission.

[0015] Preferably, the initially set transmission window is set according to the communication network environment, data transmission requirements and the hardware performance of the electricity meter. The specific steps are as follows:

[0016] First, based on the communication technology supported by the meter, determine the data transmission rate range according to the bandwidth and latency characteristics of different technologies;

[0017] Second, evaluate the meter's hardware performance, including processing power, memory, and storage capacity, to ensure the set window size does not exceed the device's processing capabilities.

[0018] Next, select the packet size and transmission interval based on the stability and reliability of the network environment;

[0019] Finally, test data transmission is performed to evaluate the performance of the set transmission window in actual use, and the window size is adjusted based on the feedback to optimize the efficiency and stability of data transmission.

[0020] Preferably, key indicators reflecting spectrum interference during data transmission are extracted from the data set, and the extracted indicators include changes in modulation and demodulation process efficiency and wireless channel utilization. The changes in modulation and demodulation process efficiency and wireless channel utilization are comprehensively analyzed under the detection window to generate modulation and demodulation efficiency reference values ​​and channel utilization reference values, respectively. The degree of interference in the current data transmission process is quantified by the modulation and demodulation efficiency reference values ​​and channel utilization reference values.

[0021] Preferably, the specific steps of comprehensively analyzing the modulation and demodulation process efficiency changes within the detection window to generate a modulation and demodulation efficiency reference value are as follows:

[0022] During the modulation and demodulation process, each transmission unit is evaluated individually and the efficiency ratio is calculated. The efficiency ratio is used to measure the relationship between the number of signal blocks that are actually successfully demodulated and the theoretical transmission load and interference impact. The calculation expression is as follows: , where It is The modulation and demodulation efficiency ratio of each transmission unit, It is The number of successfully demodulated signal blocks in a transmission unit, It is The total number of data transmission blocks of the transmission unit, It is The number of wireless interference events detected during a transmission unit;

[0023] After obtaining the efficiency ratio of each transmission unit, the obtained efficiency ratios are integrated to generate a modulation and demodulation efficiency reference value to reflect the modulation and demodulation efficiency status of the entire monitoring window. The calculation expression is as follows: , where is the reference value of modulation and demodulation efficiency, It is The weight factor of each transmission unit, is the total number of transmission units.

[0024] Preferably, the specific steps of comprehensively analyzing the wireless channel utilization within the detection window to generate a channel utilization reference value are as follows:

[0025] The set of time slot numbers occupied by all data packet transmissions in the statistical detection window is recorded as , , It is The occupied time slot number, is the total number of time slot numbers. Time slots may be occupied discontinuously due to interference. To measure the density and continuity of occupancy, a data packet distribution characteristic factor is introduced. The calculation expression is as follows: , where is the packet distribution characteristic factor, It is The occupied time slot number;

[0026] To further quantitatively measure the difference between channel utilization and the ideal state, we introduce the effective data ratio deviation index. The deviation index calculation expression is as follows: , where The maximum number of data blocks that the current channel can theoretically accommodate, is the number of data blocks that are actually successfully transmitted and effectively received, is the effective data ratio deviation index;

[0027] Packet distribution characteristic factor and the effective data ratio deviation index The channel utilization reference value is generated by fusion. The generation formula is as follows: , where It is the reference value of channel utilization.

[0028] Preferably, the analyzed modulation and demodulation efficiency reference value and channel utilization reference value are input into a pre-trained machine learning model, a spectrum interference tolerance coefficient is generated by the machine learning model, the data transmission process is intelligently evaluated by the spectrum interference tolerance coefficient, and the transmission process is divided according to the evaluation results.

[0029] Preferably, the spectrum interference tolerance coefficient generated when the data transmission process is intelligently evaluated by a pre-trained machine learning model is compared and analyzed with a pre-set spectrum interference tolerance coefficient reference threshold, and the data transmission process is divided. The division steps are as follows:

[0030] If the spectrum interference tolerance coefficient is less than the preset spectrum interference tolerance coefficient reference threshold, the data transmission process is classified as having interference risk; if the spectrum interference tolerance coefficient is greater than or equal to the preset spectrum interference tolerance coefficient reference threshold, the data transmission process is classified as having no interference risk.

[0031] Preferably, for a situation where there is no interference risk, the specific steps for increasing the data transmission window and improving transmission efficiency are as follows:

[0032] When the current data transmission process is judged to be in a state without interference risk, it indicates that the communication link has good stability and anti-interference capabilities. To improve data transmission efficiency, the original data transmission strategy is optimized based on the communication status, and the data transmission window is dynamically expanded to transmit more data blocks in each communication round, thereby reducing the communication frequency and improving bandwidth utilization. The transmission window adjustment formula is as follows: , where is the optimized data transmission window size, is the default base window size, is the spectrum interference tolerance coefficient, is the reference threshold of the spectrum interference tolerance coefficient, is the natural logarithm function, is the base of natural logarithms.

[0033] Preferably, in case of interference risk, the data transmission window is narrowed, the amount of data transmitted is reduced, and the data is split into several equal data blocks through a segmented transmission strategy and sent in batches to ensure stable data transmission. The specific steps are as follows:

[0034] When the machine learning model determines that there is a risk of spectrum interference, the current data transmission window size is first adjusted to reduce the probability of failure in large data transmission due to interference. The data transmission window adjustment formula is as follows: , where is the data transmission window adjusted under interference environment, It is the maximum data transmission window in an interference-free environment. is the maximum compression ratio, is the compression nonlinear exponential factor;

[0035] After the window is narrowed, communication stability is further enhanced and retransmission costs are reduced. The data transmitted in a single transmission is split to reduce the risk of transmission failure caused by interference, thereby improving the reliability of data transmission. The splitting formula is as follows: , where is the number of data blocks, is the minimum data block size, is the minimum guaranteed section capacity coefficient, is the interference perception enhancement factor.

[0036] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0037] By monitoring communication quality in real time, intelligently assessing interference risks, and dynamically adjusting data transmission strategies, the present invention enables smart meters to adaptively adjust the transmission window size and transmission mode in different network environments, thereby maximizing data transmission efficiency and reducing data loss or delay. Especially in situations where spectrum interference is strong, reducing the transmission window and adopting a segmented transmission strategy can ensure data stability and avoid communication interruptions or data distortion caused by interference. Ultimately, this method can ensure that the power monitoring system obtains accurate and timely meter data, improving the power system's monitoring capabilities, fault warning accuracy, and energy management efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction to the drawings required for use in the embodiments will be given below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0039] Figure 1 This is a flow chart of the method for remote monitoring of operating data of a smart meter box according to the present invention. DETAILED DESCRIPTION

[0040] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of this disclosure will be thorough and complete and will fully convey the concepts of the example embodiments to those skilled in the art.

[0041] The present invention provides Figure 1 The remote monitoring method for the operation data of the smart meter box shown includes the following steps:

[0042] The smart meter sends a test data packet through the initially set transmission window to verify the communication quality;

[0043] The purpose of test packets is to initially verify the stability and signal quality of the wireless communication link. By sending a small number of packets, the meter can test the smoothness of communication under wireless network conditions and collect real-time communication quality data (such as signal strength, latency, and bit error rate). This preliminary test helps assess the current channel interference level and ensures that the meter can make appropriate adaptive adjustments during actual data transmission.

[0044] By testing data packets, smart meters can provide a basis for subsequent communication quality data collection, ensuring a preliminary understanding of the communication environment before starting large-scale data transmission.

[0045] The initial transmission window is set based on the communication network environment, data transmission requirements, and the hardware performance of the electricity meter. The specific steps are as follows: First, based on the communication technologies supported by the electricity meter (such as GPRS, NB-IoT, LoRa, etc.), determine the data transmission rate range according to the bandwidth and latency characteristics of different technologies; second, evaluate the hardware performance of the electricity meter, including processing power, memory, and storage capacity, to ensure that the set window size does not exceed the device processing capability; then, select the data packet size and transmission interval based on the stability and reliability of the network environment; for example, if the network environment is relatively stable, a larger transmission window can be set to improve efficiency; if the network fluctuates greatly, a smaller window can be set to reduce the impact of interference; finally, test data transmission is performed to evaluate the performance of the set transmission window in actual use, and the window size is adjusted based on feedback to optimize the efficiency and stability of data transmission.

[0046] Acquire communication quality data in real time during the test data packet transmission process, and pre-process the acquired raw data to generate a data set containing multiple communication quality indicators;

[0047] The acquired communication quality data includes key performance indicators such as signal strength, signal-to-noise ratio, data rate, latency, and bit error rate. This data reflects the actual conditions of the wireless channel and helps the system assess the stability of data transmission. Data collection is not only performed during the testing phase, but also monitored in real time throughout the entire data transmission process. By acquiring this data in real time, the meter can detect any signs of interference or signal degradation, providing data support for subsequent interference risk assessments.

[0048] Acquire and monitor communication quality data in real time to provide a basis for subsequent interference identification and adjustment of data transmission strategies, ensuring that smart meters can promptly identify network anomalies.

[0049] Acquired communication quality data may contain noise, outliers, or incomplete data, necessitating preprocessing. Preprocessing tasks include data cleaning, denoising, normalization, and data padding to ensure accurate and consistent data input into subsequent analysis models. This process typically employs filtering, smoothing, and interpolation techniques to standardize data from different sources, eliminating unnecessary interference and improving data quality.

[0050] Data preprocessing ensures the consistency, accuracy, and usability of data, which is crucial for subsequent analysis and avoids misjudgment or model training failure due to data noise or outliers.

[0051] Generating a data set containing multiple communication quality metrics provides comprehensive support for subsequent interference assessment and data transmission optimization. By collecting and aggregating key communication quality indicators such as signal strength, signal-to-noise ratio, transmission rate, latency, and bit error rate, a comprehensive understanding of the stability and performance of the current communication environment can be achieved. This data set enables smart meters to systematically monitor changes in network quality over time and under different conditions, providing an accurate data foundation for subsequent analysis. These metrics help identify potential issues such as signal degradation, network congestion, or spectrum interference, providing data support for adjusting the meter's data transmission strategy (such as increasing or decreasing the transmission window and adjusting the transmission rate), ensuring efficient and stable transmission performance in a dynamically changing communication environment.

[0052] Extract key indicators reflecting spectrum interference during data transmission from the data set, conduct comprehensive analysis on the extracted key indicators, and quantify the degree of interference during the current data transmission process;

[0053] Key indicators reflecting spectrum interference during data transmission are extracted from the data set. The extracted indicators include changes in modulation and demodulation process efficiency and wireless channel utilization. The changes in modulation and demodulation process efficiency and wireless channel utilization are comprehensively analyzed under the detection window to generate modulation and demodulation efficiency reference values ​​and channel utilization reference values, respectively. The modulation and demodulation efficiency reference values ​​and channel utilization reference values ​​are used to quantify the degree of interference in the current data transmission process.

[0054] Reduced efficiency in the modulation and demodulation process often indicates spectrum interference during data transmission. Modulation and demodulation are the processes of converting digital data into analog signals suitable for transmission over wireless channels (modulation) and converting the analog signals back into digital data at the receiving end (demodulation). The efficiency of this process is often closely related to signal quality and stability. In the presence of spectrum interference, signals on wireless channels are affected by noise, interference, and signal attenuation, resulting in degraded signal quality and, consequently, reduced efficiency in the modulation and demodulation process. Spectral interference often introduces additional noise, reducing the signal-to-noise ratio (SNR). This requires the modem to increase its energy and time to correctly decode the data when receiving. Furthermore, interference may lead to frequent modulation adjustments, which in turn affects demodulation efficiency. For example, a meter's modem may need to switch to a less efficient modulation method (such as from QPSK to BPSK) to mitigate interference. While this method maintains a certain degree of transmission reliability in noisy environments, it reduces the transmission rate, thus impacting the efficiency of the entire data transmission process. Therefore, reduced modulation and demodulation efficiency is a key indicator of spectrum interference, reflecting the deterioration of signal quality and the interference pressure faced by the communication system.

[0055] The specific steps for comprehensively analyzing the changes in the modulation and demodulation efficiency within the detection window to generate a modulation and demodulation efficiency reference value are as follows:

[0056] During the modulation and demodulation process, each transmission unit is evaluated individually and the efficiency ratio is calculated. The efficiency ratio is used to measure the relationship between the number of signal blocks that are actually successfully demodulated and the theoretical transmission load and interference impact. The calculation expression is as follows: , where It is The modulation and demodulation efficiency ratio of a transmission unit is an important indicator for measuring the degree to which the unit is affected by spectrum interference during the modulation and demodulation process. It is The number of successfully demodulated signal blocks in a transmission unit reflects the actual data recovery capability of the unit. It is The total number of data transmission blocks of a transmission unit, that is, the theoretical transmission load, It is The number of wireless interference events detected during a transmission unit, such as signal drops, bandwidth narrowing, burst noise, frequency drift, reception error flags, and other abnormal signal activities;

[0057] By calculating the efficiency ratio of each transmission unit, we accurately measure the deviation between the actual demodulation success rate and the theoretical transmission load under spectral interference conditions. This step reveals the specific impact of interference on unit-level data demodulation performance at a microscopic level, providing precise, fine-grained fundamental data for subsequent overall efficiency evaluation.

[0058] After obtaining the efficiency ratio of each transmission unit, the obtained efficiency ratios are integrated to generate a modulation and demodulation efficiency reference value to reflect the modulation and demodulation efficiency status of the entire monitoring window. The calculation expression is as follows: , where is the reference value of modulation and demodulation efficiency, It is The weight factor of each transmission unit, is the total number of transmission units, used to weight the importance or representativeness of each transmission unit, and to control the impact of each unit on the final degree of contribution.

[0059] The modulation and demodulation efficiency ratios of multiple transmission units are weighted and integrated to form a global, quantifiable modulation and demodulation efficiency reference value, which comprehensively reflects the communication quality status within the entire detection window. By introducing weighting factors, the impact of severely interfered areas can be highlighted, making the evaluation results more targeted and sensitive, and providing solid data support for the accurate identification of spectrum interference and dynamic transmission strategy adjustment.

[0060] A smaller modulation and demodulation efficiency reference value, generated by comprehensively analyzing the changes in modulation and demodulation efficiency within the detection window, indicates that the data transmission process is subject to spectrum interference. The modulation and demodulation efficiency reference value reflects the efficiency of the modulation and demodulation process under specific conditions. In particular, interference affects signal quality, resulting in reduced modulation and demodulation efficiency. When spectrum interference is present, the signal quality of the wireless channel degrades, reducing the signal-to-noise ratio (SNR), making the demodulation process more difficult and requiring more processing time and resources to accurately decode the signal. Therefore, in an interference environment, the modulation and demodulation efficiency reference value decreases, indicating that the system needs to use more complex modulation and demodulation methods to maintain stable data transmission. This typically results in a lower transmission rate, increased transmission time, and increased power consumption. Conversely, when data transmission is free of spectrum interference, the modulation and demodulation process operates at a higher efficiency, and the modulation and demodulation efficiency reference value typically shows a higher value, indicating better signal quality and smoother transmission.

[0061] Decreased wireless channel utilization often indicates spectrum interference during data transmission. Wireless channel utilization refers to the ratio of valid data transmitted over a wireless channel within a specific timeframe and reflects channel efficiency. When spectrum interference is present, signal quality is affected, resulting in decreased signal strength, increased noise, and higher bit error rates. These interference factors force wireless devices to retransmit data packets or reduce transmission rates to mitigate signal attenuation and errors, wasting bandwidth and resources, thereby reducing the effective utilization of wireless channels. In high-interference environments, a significant portion of the available wireless channel bandwidth is consumed to correct errors and retransmit lost packets, significantly reducing the time available for effective data transmission. This decrease in channel utilization is particularly pronounced in congested spectrum environments, where multiple devices compete for the same frequency band. Therefore, monitoring wireless channel utilization can indirectly identify the presence of spectrum interference and provide a basis for optimizing data transmission strategies (such as adjusting the transmission window or selecting a more optimal frequency band), thereby improving system transmission efficiency and stability.

[0062] The specific steps for comprehensively analyzing wireless channel utilization within the detection window to generate a reference value for channel utilization are as follows:

[0063] The set of time slot numbers occupied by all data packet transmissions in the statistical detection window is recorded as , , It is The occupied time slot number, is the total number of time slot numbers. Time slots may be occupied discontinuously due to interference. To measure the density and continuity of occupancy, a data packet distribution characteristic factor is introduced. The calculation expression is as follows: , where It is the characteristic factor of data packet distribution, that is, the “density” or “continuity” of data packet distribution in the channel within the detection window. It is The occupied time slot number;

[0064] The core idea of ​​this formula is to capture the density of data packets in the channel. If the data packets are distributed continuously and evenly in the time slots (i.e., high utilization and low interference), then the interval between adjacent time slots is will be very small, resulting in the overall On the contrary, if the data is sparsely distributed and there are channel holes (which often occur when there is strong interference), the value will become smaller. It reflects the "continuous compactness" of channel utilization and does not involve average density. Instead, it is a weighted inverse measure of spatial distribution characteristics.

[0065] To further quantitatively measure the difference between channel utilization and the ideal state, we introduce the effective data ratio deviation index. The deviation index measures the relative deviation between the number of data blocks actually transmitted and the theoretical maximum capacity within the current detection window. The deviation index calculation expression is as follows: , where The maximum number of data blocks that the current channel can theoretically accommodate (based on frequency resources, time slot configuration, etc.), is the number of data blocks that are actually successfully transmitted and effectively received (excluding retransmissions or error packets). It is the effective data ratio deviation index, which is used to quantify the deviation between the actual amount of data transmitted and the theoretical maximum transmission capacity within a specific detection window;

[0066] By calculating the effective data ratio deviation index, we quantify the deviation between actual data transmission and the theoretical maximum transmission rate, reflecting the impact of spectrum interference or other network issues on channel utilization. The deviation index provides a basis for subsequent channel utilization evaluation, helping smart meters adjust data transmission strategies based on interference levels and optimize network performance.

[0067] Packet distribution characteristic factor and the effective data ratio deviation index The channel utilization reference value is generated by fusion. The generation formula is as follows: , where It is the reference value of channel utilization.

[0068] This definition combines the two dimensions of channel space utilization density and transmission quantity deviation:

[0069] When the channel is densely used and data transmission is close to the theoretical optimum, big, Small, A larger value indicates less interference and higher utilization rate;

[0070] When the channel is sparse, there are many retransmissions, and there is little valid data, Small, big, A significant decrease reflects the possibility of spectrum interference.

[0071] The smaller the channel utilization reference value, generated by comprehensively analyzing wireless channel utilization within the detection window, the more likely it is that data transmission is subject to spectrum interference. The channel utilization reference value reflects the ratio of valid data transmitted by the wireless channel within a given monitoring window. When spectrum interference is present, communication quality is affected, resulting in higher error rates, delays, and retransmissions during data transmission. This interference reduces signal transmission efficiency, requiring more bandwidth to retransmit lost packets and perform error correction. Consequently, effective channel utilization decreases, manifesting as a smaller channel utilization reference value. Conversely, if wireless channel quality is good, interference is minimal or non-existent, enabling efficient data transmission and reducing the need for retransmissions and error correction, the channel utilization reference value will be higher, indicating that data transmission is not subject to significant spectrum interference.

[0072] The analyzed key indicators are input into a pre-trained machine learning model, which is used to intelligently evaluate the data transmission process and classify the transmission process based on the evaluation results.

[0073] The analyzed modulation and demodulation efficiency reference value and channel utilization reference value are input into a pre-trained machine learning model, and the spectrum interference tolerance coefficient is generated by the machine learning model. The data transmission process is intelligently evaluated by the spectrum interference tolerance coefficient, and the transmission process is divided according to the evaluation results.

[0074] A pre-trained machine learning model is one that has been trained during data collection and processing using extensive historical data and known interference scenarios, using machine learning algorithms (such as decision trees, support vector machines, and neural networks) to accurately predict the impact of spectrum interference on data transmission. During the training phase, the model analyzes the relationship between various input features (such as reference values ​​for modulation and demodulation efficiency and channel utilization) and spectrum interference, learning how to derive the interference tolerance factor based on these input features. The training process involves supervised learning, where input data (features) are associated with target outputs (such as the spectrum interference tolerance factor). Using a labeled training dataset, the model gradually adjusts its internal weights and parameters to improve the accuracy of predictions for new data.

[0075] The core goal of a trained machine learning model is to intelligently assess spectrum interference tolerance based on real-time data in practical applications. The model processes input reference values ​​(such as modulation and demodulation efficiency and channel utilization) to generate a spectrum interference tolerance coefficient (TIC) that reflects the current interference situation. This coefficient quantifies the smart meter's adaptability and tolerance to interference in specific environments. Based on this assessment, the system can categorize the current data transmission process into "no interference risk" and "interference risk" scenarios, dynamically adjusting the data transmission strategy, such as increasing or decreasing the data transmission window or adopting a segmented transmission strategy, to ensure stable data transmission. The model's accuracy and generalization capabilities depend significantly on the quality of the training data, the rationality of feature selection, and the complexity of the model itself. Therefore, pre-trained machine learning models are key to enabling adaptive adjustments in smart meters and improving data transmission efficiency and stability.

[0076] The machine learning model is not limited here and can achieve the modulation and demodulation efficiency reference value and channel utilization reference value Perform comprehensive analysis to generate spectrum interference tolerance coefficient The present invention provides a specific implementation method for realizing the technical solution of the present invention.

[0077] Spectrum interference tolerance factor The generation formula is as follows: , where and They are the reference values ​​of modulation and demodulation efficiency respectively and channel utilization reference value The preset scaling factor of and Both are greater than 0.

[0078] The preset scaling factor refers to the coefficient used in the formula and These two coefficients are used for the reference value of modulation and demodulation efficiency. and channel utilization reference value Tolerance to spectrum interference Specifically, and They represent the modulation and demodulation efficiency and channel utilization respectively. The two coefficients are pre-set, that is, determined through historical data, experiments or expert experience, and are used to reflect the importance of each parameter in interference tolerance. and Usually greater than 0, indicating that these two parameters are reference values ​​for modulation and demodulation efficiency and channel utilization reference value )right These preset proportional coefficients help the machine learning model better reflect different communication quality parameters (modulation and demodulation efficiency reference values and channel utilization reference value ) on spectrum interference tolerance and provide a quantitative basis for interference assessment during data transmission.

[0079] It can be seen from the spectrum interference tolerance coefficient that the smaller the modulation and demodulation efficiency reference value generated after comprehensive analysis of the modulation and demodulation process efficiency changes within the detection window, and the smaller the channel utilization reference value generated after comprehensive analysis of the wireless channel utilization within the detection window, the smaller the spectrum interference tolerance coefficient generated when the data transmission process is intelligently evaluated by the pre-trained machine learning model, indicating a greater probability that the data transmission process is affected by spectrum interference. Conversely, the smaller the probability that the data transmission process is affected by spectrum interference.

[0080] Based on the evaluation results of the machine learning model, the data transmission process is divided into two categories: "with interference risk" and "without interference risk";

[0081] The spectrum interference tolerance coefficient generated by the pre-trained machine learning model when intelligently evaluating the data transmission process is compared with the pre-set spectrum interference tolerance coefficient reference threshold to divide the data transmission process. The division steps are as follows:

[0082] If the spectrum interference tolerance coefficient is less than the preset spectrum interference tolerance coefficient reference threshold, the data transmission process is classified as having interference risk; if the spectrum interference tolerance coefficient is greater than or equal to the preset spectrum interference tolerance coefficient reference threshold, the data transmission process is classified as having no interference risk.

[0083] If there is no interference risk, the data transmission window is increased to improve transmission efficiency. If there is interference risk, the data transmission window is narrowed to reduce the amount of data transmitted. The data is then split into several equal data blocks through a segmented transmission strategy and sent in batches to ensure stable data transmission.

[0084] By intelligently adjusting the data transmission window size and employing a segmented transmission strategy, smart meters ensure transmission efficiency and stability in diverse communication environments, maximizing data reliability. In environments with good signal quality and minimal interference, smart meters can transmit more data blocks at once, reducing transmission overhead, improving bandwidth utilization, and minimizing delays caused by multiple transmissions. This accelerates data transmission and improves overall system efficiency and responsiveness. In environments with interference risk, shrinking the data transmission window can effectively minimize data loss or transmission errors. In conditions of poor signal quality, unstable networks, or strong interference, transmitting large amounts of data can result in signal distortion, data loss, or transmission errors. Therefore, it is necessary to reduce the amount of data transmitted each time to increase the probability of successful transmission. Furthermore, employing a segmented transmission strategy—splitting large amounts of data into multiple, equivalent data blocks and sending them in batches—can avoid retransmissions or failures caused by signal loss in high-interference environments. Even if some data blocks are lost, they can be replenished through subsequent retransmissions and batched transmissions, thus ensuring stable and complete data transmission. This strategy comprehensively considers changes in the communication environment. By flexibly adjusting the transmission strategy, it can not only improve efficiency in the absence of interference but also ensure stability in the presence of interference, thereby greatly enhancing the adaptability and reliability of the meter system in a dynamically changing environment.

[0085] To avoid interference risks, the specific steps to increase the data transmission window and improve transmission efficiency are as follows:

[0086] When the current data transmission process is judged to be in a state without interference risk, it indicates that the communication link has good stability and anti-interference capabilities. To improve data transmission efficiency, the original data transmission strategy is optimized based on the communication status, and the data transmission window is dynamically expanded to transmit more data blocks in each communication round, thereby reducing the communication frequency and improving bandwidth utilization. The transmission window adjustment formula is as follows: , where is the optimized data transmission window size, which indicates the transmission window size (unit: data blocks) that the smart meter should adopt in the current communication environment. is the default base window size, representing the conservative amount of transmission used before no evaluation. is the spectrum interference tolerance coefficient, is the reference threshold of the spectrum interference tolerance coefficient, It is a natural logarithmic function, which is used to compress the growth rate so that relatively large growth does not lead to excessive expansion. is the base of natural logarithms.

[0087] when When the meter has a strong resistance to interference, the transmission window will be enlarged accordingly, but the amplification ratio will tend to be flat as the margin increases, thereby avoiding the communication risk caused by excessive expansion and ensuring that the system stability and robustness are maintained while improving efficiency.

[0088] This mechanism embodies the design principle of "maximizing transmission efficiency under the premise of security" and is an adaptive, highly flexible and intelligent data transmission optimization strategy.

[0089] In the event of interference risk, the data transmission window is narrowed, the amount of data transmitted is reduced, and the data is split into several equal data blocks through a segmented transmission strategy and sent in batches to ensure stable data transmission. The specific steps are as follows:

[0090] When the machine learning model assesses that there is a risk of spectrum interference First, adjust the current data transmission window size to reduce the probability of failure of large data transmission under interference. The data transmission window adjustment formula is as follows: , where is the data transmission window adjusted under interference environment, It is the maximum data transmission window in an interference-free environment. is the maximum compression ratio, , defines the maximum ratio to which the window can be compressed in the presence of spectrum interference, It is the compression nonlinear exponential factor, which controls the speed of change and the slope of the curve of the window compression, and is used for amplification or buffering. Window adjustment effect brought about;

[0091] After identifying spectrum interference risks, the system dynamically and nonlinearly reduces the data transmission window, proactively reducing the amount of data transmitted at a time. This reduces the probability of packet loss and the risk of transmission failure in interference environments. This mechanism enables smart meters to flexibly adjust their transmission strategies based on the current communication environment, improving data transmission stability and the system's anti-interference capabilities.

[0092] After the window is narrowed, communication stability is further enhanced and retransmission costs are reduced. The data transmitted in a single transmission is split into smaller blocks to reduce the risk of transmission failure caused by interference, thereby improving the reliability of data transmission. Based on the adjusted window and interference assessment results, the number of data blocks required is calculated to effectively deal with interference in the network. The splitting formula is as follows: , where is the number of data blocks. By calculating, we can determine how many data blocks are needed to effectively transmit data, especially when the interference is high. It is the minimum data block size, which represents the minimum capacity of each data block, ensuring that the basic size of each data block will not be too small in the case of high interference. It is the minimum guaranteed segment capacity coefficient, which is used to set the minimum capacity of the data block to ensure that the data block will not be reduced to an unusable level even in the most interference-prone environment. Is the interference perception enhancement factor, the control system's response sensitivity to interference. When the interference is stronger, The number of data blocks will increase to cope with more complex transmission environments.

[0093] The number of data blocks required is dynamically calculated based on the current spectrum interference risk to ensure stable and reliable data transmission. In high-interference environments, after the data transmission window is narrowed, it may be necessary to further split the data into multiple smaller blocks for transmission. This is because large data blocks are more likely to be lost or erroneous in severe interference. By adjusting the number of data blocks, data transmission is more stable, packet loss is reduced, and data recovery is improved.

[0094] By monitoring communication quality in real time, intelligently assessing interference risks, and dynamically adjusting data transmission strategies, the present invention enables smart meters to adaptively adjust the transmission window size and transmission mode in different network environments, thereby maximizing data transmission efficiency and reducing data loss or delay. Especially in situations where spectrum interference is strong, reducing the transmission window and adopting a segmented transmission strategy can ensure data stability and avoid communication interruptions or data distortion caused by interference. Ultimately, this method can ensure that the power monitoring system obtains accurate and timely meter data, improving the power system's monitoring capabilities, fault warning accuracy, and energy management efficiency.

[0095] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0096] The above description is merely illustrative of certain exemplary embodiments of the present invention. It goes without saying that those skilled in the art will be able to modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and description are illustrative in nature and should not be construed as limiting the scope of protection of the claims.

[0097] It should be noted that, in this document, if there are relational terms such as first and second, etc., they are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprises", "comprising" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device that includes a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprising a ..." does not exclude the presence of other identical elements in the process, method, article or device that includes the element.

[0098] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0099] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0100] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0101] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0102] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0103] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0104] The above description is merely illustrative of certain exemplary embodiments of the present invention. It goes without saying that those skilled in the art will be able to modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and description are illustrative in nature and should not be construed as limiting the scope of protection of the claims.

Claims

1. A remote monitoring method for operation data of a smart meter box, characterized in that: The following steps are involved: The smart meter sends a test data packet through the initially set transmission window to verify the communication quality; Acquire communication quality data in real time during the test data packet transmission process, and pre-process the acquired raw data to generate a data set containing multiple communication quality indicators; Extract key indicators reflecting spectrum interference during data transmission from the data set, conduct comprehensive analysis on the extracted key indicators, and quantify the degree of interference during the current data transmission process; The analyzed key indicators are input into a pre-trained machine learning model, which is used to intelligently evaluate the data transmission process and classify the transmission process based on the evaluation results. Based on the evaluation results of the machine learning model, the data transmission process is divided into two categories: "interference risk" and "no interference risk"; If there is no interference risk, the data transmission window is increased to improve transmission efficiency. If there is interference risk, the data transmission window is narrowed to reduce the amount of data transmitted. The data is then split into several equal data blocks through a segmented transmission strategy and sent in batches to ensure stable data transmission. Key indicators reflecting spectrum interference during data transmission are extracted from the data set. The extracted indicators include changes in modulation and demodulation process efficiency and wireless channel utilization. The changes in modulation and demodulation process efficiency and wireless channel utilization are comprehensively analyzed under the detection window to generate modulation and demodulation efficiency reference values ​​and channel utilization reference values, respectively. The modulation and demodulation efficiency reference values ​​and channel utilization reference values ​​are used to quantify the degree of interference in the current data transmission process.

2. The remote monitoring method for operation data of a smart electric meter box according to claim 1 is characterized in that: The initial transmission window is set according to the communication network environment, data transmission requirements and the hardware performance of the meter. The specific steps are as follows: First, based on the communication technology supported by the meter, determine the data transmission rate range according to the bandwidth and latency characteristics of different technologies; Second, evaluate the meter's hardware performance, including processing power, memory, and storage capacity, to ensure the set window size does not exceed the device's processing capabilities. Next, select the packet size and transmission interval based on the stability and reliability of the network environment; Finally, test data transmission is performed to evaluate the performance of the set transmission window in actual use, and the window size is adjusted based on the feedback to optimize the efficiency and stability of data transmission.

3. The remote monitoring method for operation data of a smart electric meter box according to claim 1, characterized in that: The specific steps for comprehensively analyzing the changes in the modulation and demodulation efficiency within the detection window to generate a modulation and demodulation efficiency reference value are as follows: During the modulation and demodulation process, each transmission unit is evaluated individually and the efficiency ratio is calculated. The efficiency ratio is used to measure the relationship between the number of signal blocks that are actually successfully demodulated and the theoretical transmission load and interference impact. The calculation expression is as follows: , where It is The modulation and demodulation efficiency ratio of each transmission unit, It is The number of successfully demodulated signal blocks in a transmission unit, It is The total number of data transmission blocks of the transmission unit, It is The number of wireless interference events detected during a transmission unit; After obtaining the efficiency ratio of each transmission unit, the obtained efficiency ratios are integrated to generate a modulation and demodulation efficiency reference value to reflect the modulation and demodulation efficiency status of the entire monitoring window. The calculation expression is as follows: , where is the reference value of modulation and demodulation efficiency, It is The weight factor of each transmission unit, is the total number of transmission units.

4. The remote monitoring method for operation data of a smart electric meter box according to claim 1, characterized in that: The specific steps for comprehensively analyzing wireless channel utilization within the detection window to generate a reference value for channel utilization are as follows: The set of time slot numbers occupied by all data packet transmissions in the statistical detection window is recorded as , , It is The occupied time slot number, is the total number of time slot numbers. Time slots may be occupied discontinuously due to interference. To measure the density and continuity of occupancy, a data packet distribution characteristic factor is introduced. The calculation expression is as follows: , where is the packet distribution characteristic factor, It is The occupied time slot number; To further quantitatively measure the difference between channel utilization and the ideal state, we introduce the effective data ratio deviation index. The deviation index calculation expression is as follows: , where The maximum number of data blocks that the current channel can theoretically accommodate, is the number of data blocks that are actually successfully transmitted and effectively received, is the effective data ratio deviation index; Packet distribution characteristic factor and the effective data ratio deviation index The channel utilization reference value is generated by fusion. The generation formula is as follows: , where It is the reference value of channel utilization.

5. The remote monitoring method for operation data of a smart electric meter box according to claim 1, characterized in that: The analyzed modulation and demodulation efficiency reference value and channel utilization reference value are input into a pre-trained machine learning model, and the spectrum interference tolerance coefficient is generated by the machine learning model. The data transmission process is intelligently evaluated by the spectrum interference tolerance coefficient, and the transmission process is divided according to the evaluation results.

6. The remote monitoring method for operation data of a smart electric meter box according to claim 5 is characterized in that: The spectrum interference tolerance coefficient generated by the pre-trained machine learning model when intelligently evaluating the data transmission process is compared with the pre-set spectrum interference tolerance coefficient reference threshold to divide the data transmission process. The division steps are as follows: If the spectrum interference tolerance coefficient is less than the preset spectrum interference tolerance coefficient reference threshold, the data transmission process is classified as having interference risk; if the spectrum interference tolerance coefficient is greater than or equal to the preset spectrum interference tolerance coefficient reference threshold, the data transmission process is classified as having no interference risk.

7. The remote monitoring method for operation data of a smart electric meter box according to claim 6, characterized in that: To avoid interference risks, the specific steps to increase the data transmission window and improve transmission efficiency are as follows: When the current data transmission process is judged to be in a state without interference risk, it indicates that the communication link has good stability and anti-interference capabilities. To improve data transmission efficiency, the original data transmission strategy is optimized based on the communication status, and the data transmission window is dynamically expanded to transmit more data blocks in each communication round, thereby reducing the communication frequency and improving bandwidth utilization. The transmission window adjustment formula is as follows: , where is the optimized data transmission window size, is the default base window size, is the spectrum interference tolerance coefficient, is the reference threshold of the spectrum interference tolerance coefficient, is the natural logarithm function, is the base of natural logarithms.

8. The remote monitoring method for operation data of a smart electric meter box according to claim 6, characterized in that: In the event of interference risk, the data transmission window is narrowed, the amount of data transmitted is reduced, and the data is split into several equal data blocks through a segmented transmission strategy and sent in batches to ensure stable data transmission. The specific steps are as follows: When the machine learning model determines that there is a risk of spectrum interference, the current data transmission window size is first adjusted to reduce the probability of failure in large data transmission due to interference. The data transmission window adjustment formula is as follows: , where is the data transmission window adjusted under interference environment, It is the maximum data transmission window in an interference-free environment. is the maximum compression ratio, is the compression nonlinear exponential factor; After the window is narrowed, communication stability is further enhanced and retransmission costs are reduced. The data transmitted in a single transmission is split to reduce the risk of transmission failure caused by interference, thereby improving the reliability of data transmission. The splitting formula is as follows: , where is the number of data blocks, is the minimum data block size, is the minimum guaranteed section capacity coefficient, is the interference perception enhancement factor.

Images