Highway operation state prediction system based on ETC gantry data

Abstract

The application relates to the technical field of Internet of Things, in particular to a highway running state prediction system based on ETC gantry data, which comprises a data acquisition module, a data processing module, a prediction module, a report adjustment module, a transmission adjustment module and a prediction adjustment module. The data acquisition module collects the running state data of the highway through the ETC gantry. The data processing module is used for preprocessing the running state data to output optimized road condition data. The prediction module is used for training an initial model according to the road condition characteristics to obtain a prediction model. The report adjustment module is used for determining a dynamic report interval triggered by a traffic flow change rate according to the lag length of the running state data transmission response. The transmission adjustment module is used for determining a dynamic offset of the transmission opportunity according to the packet loss rate of the running state data transmission in a unit time. The prediction adjustment module is used for determining a pre-compensation amount of the predictive power according to the misjudgment rate of no signal in a unit time. The application improves the prediction accuracy of the running state data.

Description

Technical Field

[0001] This invention relates to the field of Internet of Things (IoT) technology, and in particular to a highway operation status prediction system based on ETC gantry data. Background Technology

[0002] In existing technologies, with the rapid development of intelligent transportation systems, using IoT technology for real-time monitoring and congestion prediction of highway operation has become a key means to improve road network efficiency. Currently, based on the ETC gantry system deployed along highways, this system can accurately collect the precise time, location, and identity information of passing vehicles, providing a highly reliable data foundation for travel time calculation and route tracing. This data is then transmitted via narrowband IoT to a cloud platform for centralized processing and predictive analysis. However, existing technologies have significant limitations in practical applications. Highway scenarios are highly dynamic and complex; high-speed vehicle movement and undulating roadside terrain cause severe multipath fading and shadowing effects on wireless signals, resulting in unstable data transmission links and a significant increase in packet loss rate. High-voltage power lines and substations along highways generate strong electromagnetic noise, especially causing co-channel interference to the low-frequency subcarriers of narrowband IoT, leading to increased misjudgment rates at base stations and even frequent triggering of no-signal states and packet loss. These problems result in defects in the data foundation of existing systems, such as high latency, poor integrity, and low reliability, which in turn significantly reduces the accuracy of backend predictive models.

[0003] Chinese Patent Publication No. CN120431714A discloses a method, device, equipment, medium, and product for identifying highway congestion. The method includes the following steps: based on the terminal signaling dataset of multiple target base stations belonging to the highway, a base station speed prediction model is trained to obtain the base station speeds corresponding to multiple remaining base stations; the remaining base stations refer to the target base stations remaining after entering the highway, excluding the first target base station accessed; the base station speed is used to reflect the vehicle's movement speed between adjacent target base stations; the loss value of the base station speed prediction model during training is determined based on the predicted speed and the actual speed; the actual speed is determined based on the highest quality target historical signaling data trajectory set; the target historical signaling data trajectory set is determined based on the historical terminal signaling dataset; based on the speeds of each base station, the kilometer marker speeds corresponding to multiple kilometer markers in the highway are determined; based on the vehicle density of the road segment to which each kilometer marker belongs and the speed of each kilometer marker, the congestion identification result of each kilometer marker is determined, and the congestion identification result of the highway is generated. It is evident that the highway congestion identification method cannot effectively address the latency sensitivity of operational status data prediction, leading to error accumulation caused by computational delay and inaccurate spatial mapping, resulting in insufficient accuracy in predicting operational status data. Summary of the Invention

[0004] To address this issue, the present invention provides a highway operation status prediction system based on ETC gantry data, which overcomes the problem in the prior art where the highway congestion identification method cannot effectively cope with the delay sensitivity of operation status data prediction, resulting in error accumulation caused by computational delay and inaccurate spatial mapping, leading to insufficient prediction accuracy of operation status data.

[0005] To achieve the above objectives, the present invention provides a highway operation status prediction system based on ETC gantry data, comprising: The data acquisition module includes a data acquisition unit for collecting highway operation status data through an ETC gantry and a data transmission unit connected to the data acquisition unit for transmitting the operation status data to the location to be processed using narrowband Internet of Things technology. The data processing module is connected to the data acquisition module and includes a preprocessing unit for preprocessing the operating status data to output optimized road condition data and a feature extraction unit connected to the preprocessing unit for performing feature extraction based on the optimized road condition data to output road condition features. The prediction module, which is connected to the data processing module, includes a model training unit for training an initial model based on the road condition characteristics to obtain a prediction model, and a prediction unit connected to the model training unit for predicting the traffic conditions of the highway based on the prediction model to obtain a prediction result. The reporting and adjustment module is connected to the data acquisition module and is used to determine the dynamic reporting interval triggered by the traffic flow change rate based on the lag time of the data transmission response in the operating status. The transmission adjustment module is connected to the data acquisition module and the reporting adjustment module respectively, and is used to determine the dynamic offset of the transmission timing based on the packet loss rate of the running status data transmission per unit time. A prediction adjustment module, which is connected to both the prediction module and the transmission adjustment module, is used to determine the pre-compensation amount of predictive power based on the false positive rate of no signal per unit time.

[0006] Furthermore, if the lag time of the reporting adjustment module in responding to the data transmission of the operating status data is greater than the preset first lag time, it is determined that the prediction accuracy of the operating status data does not meet the requirements.

[0007] Furthermore, if the lag time of the reporting adjustment module in responding to the operation status data transmission response is greater than the preset first lag time and less than or equal to the preset second lag time, it is initially determined that the transmission reliability of the operation status data does not meet the requirements, and the transmission reliability of the operation status data is determined based on the packet loss rate of the operation status data transmission per unit time.

[0008] Furthermore, the lag time of the reporting adjustment module in responding to the operation status data transmission response is greater than the preset second lag time, thereby reducing the dynamic reporting interval triggered by the traffic flow change rate; The reduction in the dynamic reporting interval triggered by the traffic flow change rate is determined by the difference between the lag time of the operation status data transmission response and the preset second lag time.

[0009] Furthermore, the transmission adjustment module determines that the transmission reliability of the operating status data does not meet the requirements when the packet loss rate of the operating status data transmission per unit time is greater than the preset first packet loss rate.

[0010] Furthermore, the transmission adjustment module increases the dynamic offset of the transmission timing in response to the packet loss rate of the running state data transmission within the unit time being greater than the preset first packet loss rate and less than or equal to the preset second packet loss rate.

[0011] Furthermore, in response to the packet loss rate of the running status data transmission within a unit time being greater than the preset second packet loss rate, the transmission adjustment module initially determines that the electromagnetic interference resistance of the running status data transmission does not meet the requirements, and determines whether the electromagnetic interference resistance of the running status data transmission meets the requirements based on the false judgment rate of no signal within a unit time.

[0012] Furthermore, the increase in the dynamic offset of the transmission timing is determined by the difference between the packet loss rate of the running state data transmission per unit time and the preset first packet loss rate.

[0013] Furthermore, the prediction adjustment module responds to the fact that the false judgment rate of no signal per unit time is greater than the preset false judgment rate, determines that the anti-interference degree of electromagnetic interference of the data transmission in the operating state does not meet the requirements, and increases the pre-compensation amount of the predictive power.

[0014] Furthermore, the increase in the pre-compensation amount of the predictive power is determined by the difference between the false positive rate of no signal per unit time and the preset false positive rate.

[0015] Compared with existing technologies, the beneficial effects of this invention are as follows: The system of this invention, by setting up a data acquisition module, a data processing module, a prediction module, a reporting adjustment module, a transmission adjustment module, and a prediction adjustment module, adjusts the dynamic reporting interval triggered by the traffic flow change rate based on the lag time of the response to the data transmission of operational status data. Since the prediction of highway operational status data requires extremely high data freshness, but narrowband IoT, due to its narrowband modulation and non-real-time scheduling mechanism, suffers from increased transmission delay, it may lead to inaccurate predictions due to congestion already occurring. By reducing the dynamic reporting interval triggered by the traffic flow change rate, it ensures that key data such as sudden drops in vehicle speed and sudden changes in traffic flow arrive at the prediction system before congestion occurs, reserving sufficient prediction response time for the model and reducing the probability of inaccurate predictions due to data delay. The system also adjusts the dynamic offset of the transmission timing based on the packet loss rate of operational status data transmission per unit time. Since highways pass through… In mountainous areas, the shadows cast by mountains and the presence of elevated bridge piers can cause multipath fading of signals, leading to drastic fluctuations in signal strength at the receiving end. This can result in a sharp increase in demodulation error rate and a higher packet loss rate per transmission. By increasing the dynamic offset of transmission timing, the adjustment range of transmission time can be expanded, effectively avoiding periodic or random signal degradation windows, thereby reducing the packet loss rate per transmission. The pre-compensation amount of predictive power is adjusted based on the false positive rate of no signal per unit time. Since high-voltage power towers around highways generate low-frequency electromagnetic noise, which overlaps with the low-frequency subcarriers of narrowband IoT, causing base stations to mistakenly judge no signal and discard data packets, increasing the pre-compensation amount of predictive power can offset the impact of sudden noise enhancement by increasing the transmission power in advance and retaining redundancy. This compensates for the lag of traditional dynamic adjustment, reduces the false positive rate of base stations caused by the instantaneous inundation of signals by noise, and improves the prediction accuracy of operational status data.

[0016] Furthermore, the system of the present invention adjusts the dynamic reporting interval triggered by traffic flow change rate by setting a preset first lag time and a preset second lag time. Since the prediction of highway operation status data requires extremely high data freshness, but the narrowband Internet of Things uses narrowband modulation and non-real-time scheduling mechanisms, resulting in increased transmission delay, which may lead to inaccurate predictions due to congestion already formed. By reducing the dynamic reporting interval triggered by traffic flow change rate, it can ensure that key data such as sudden drop in vehicle speed and sudden change in traffic flow arrive at the prediction system before congestion forms, reserve sufficient prediction response time for the model, reduce the probability of prediction inaccuracy due to data delay, and further improve the prediction accuracy of operation status data.

[0017] Furthermore, the system described in this invention adjusts the dynamic offset of the transmission timing by setting a preset first packet loss rate and a preset second packet loss rate. Since highways pass through mountainous areas, the shadows of mountains and the presence of viaduct piers can cause multipath fading of signals, leading to drastic fluctuations in the signal strength at the receiving end. This may cause a sharp increase in the demodulation error rate and an increase in the packet loss rate of a single transmission. By increasing the dynamic offset of the transmission timing, the adjustment range of the transmission time can be expanded, effectively avoiding periodic or random signal degradation windows, thereby reducing the packet loss rate of a single transmission and further improving the prediction accuracy of the operating status data.

[0018] Furthermore, the system described in this invention adjusts the pre-compensation amount of predictive power by setting a preset misjudgment rate. Since the high-voltage power towers around highways generate low-frequency electromagnetic noise, which superimposes with the low-frequency subcarriers of narrowband IoT, causing base stations to misjudge no signal and discard data packets, by increasing the pre-compensation amount of predictive power, the impact of sudden noise enhancement can be offset by increasing the transmission power in advance and retaining redundancy, making up for the lag of traditional dynamic adjustment, reducing the base station misjudgment rate caused by the instantaneous submersion of the signal by noise, and further improving the prediction accuracy of operating status data. Attached Figure Description

[0019] Figure 1 This is a block diagram of the overall structure of the highway operation status prediction system based on ETC gantry data according to an embodiment of the present invention; Figure 2 This is a flowchart illustrating the process of determining the dynamic reporting interval triggered by the traffic flow change rate in the highway operation status prediction system based on ETC gantry data, according to an embodiment of the present invention. Figure 3 This is a flowchart illustrating the dynamic offset process for determining the transmission timing in the highway operation status prediction system based on ETC gantry data, according to an embodiment of the present invention. Figure 4 This is a flowchart illustrating the process of determining the pre-compensation amount of predictive power in a highway operation status prediction system based on ETC gantry data, according to an embodiment of the present invention. Detailed Implementation

[0020] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0021] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0022] Please see Figure 1 As shown, it is an overall structural block diagram of the highway operation status prediction system based on ETC gantry data according to an embodiment of the present invention.

[0023] This invention provides a highway operation status prediction system based on ETC gantry data, comprising: The data acquisition module includes a data acquisition unit for collecting highway operation status data through an ETC gantry and a data transmission unit connected to the data acquisition unit for transmitting the operation status data to the location to be processed using narrowband Internet of Things technology. The data processing module is connected to the data acquisition module and includes a preprocessing unit for preprocessing the operating status data to output optimized road condition data and a feature extraction unit connected to the preprocessing unit for performing feature extraction based on the optimized road condition data to output road condition features. The prediction module, which is connected to the data processing module, includes a model training unit for training an initial model based on the road condition characteristics to obtain a prediction model, and a prediction unit connected to the model training unit for predicting the traffic conditions of the highway based on the prediction model to obtain a prediction result. The reporting and adjustment module is connected to the data acquisition module and is used to determine the dynamic reporting interval triggered by the traffic flow change rate based on the lag time of the data transmission response in the operating status. The transmission adjustment module is connected to the data acquisition module and the reporting adjustment module respectively, and is used to determine the dynamic offset of the transmission timing based on the packet loss rate of the running status data transmission per unit time. A prediction adjustment module, which is connected to both the prediction module and the transmission adjustment module, is used to determine the pre-compensation amount of predictive power based on the false positive rate of no signal per unit time.

[0024] Specifically, narrowband IoT technology is a low-power, wide-coverage, and high-connectivity IoT communication technology, specifically designed to carry small data volumes and low-rate IoT service transmissions.

[0025] Specifically, the operational status data includes the vehicle's travel time between adjacent ETC gantries, the instantaneous speed of the vehicle passing through the ETC gantry, and the timestamp of the vehicle passing through the ETC gantry.

[0026] Specifically, preprocessing includes data cleaning, data integration, and data standardization.

[0027] Specifically, optimizing traffic data includes the time it takes for vehicles to travel between adjacent ETC gantries after data cleaning, the instantaneous speed of vehicles passing through ETC gantries after data integration, and the timestamp of vehicles passing through after data standardization.

[0028] Specifically, road condition characteristics include traffic volume per unit time, peak period duration, and speed standard deviation.

[0029] Specifically, the initial model is an initial framework with basic temporal feature learning capabilities and applicable to traffic state classification.

[0030] Specifically, the process of training the initial model based on road condition features to obtain the prediction model involves dividing the road condition features and corresponding traffic states into training sets, validation sets, and test sets; using the training set data to allow the model to learn the mapping relationship between road condition features and traffic states; adjusting the model parameters through the validation set; inputting the test set road condition features into the model after it has been optimized by the validation set for evaluation; if the model's performance index on the test set reaches a preset threshold, then the model is determined as the final usable prediction model.

[0031] Specifically, the prediction models include Long Short-Term Memory (LSTM) network models, Temporal Convolutional Network (TCNN) models, and Gradient Boosting Tree (GPRS) models, with the preferred embodiment being the LTM network model.

[0032] Specifically, the forecast results include smooth traffic conditions, congested traffic conditions, and predicted travel time.

[0033] Specifically, the lag time for the operation status data transmission response is the time interval between the ETC gantry capturing the highway operation status data and triggering the predictive response.

[0034] Specifically, the dynamic reporting interval triggered by the traffic flow change rate is the time interval at which the data reporting frequency is automatically adjusted based on the traffic flow change rate monitored in real time by the ETC gantry.

[0035] Specifically, the packet loss rate of operational status data transmission per unit time is the ratio of the number of lost data packets in operational status data to the total number of data packets per unit time.

[0036] Specifically, the dynamic offset of the transmission timing is the time deviation value that flexibly adjusts the preset transmission time of ETC gantry data according to the real-time traffic flow status.

[0037] Specifically, the pre-compensation amount for predictive power is the amount of compensation that increases the transmit power in advance based on the prediction of noise intensity 1-2 seconds in the future according to historical noise trends.

[0038] Specifically, the false positive rate for no signal per unit time is the ratio of the number of times a valid signal is actually present to the total number of times a signal is actually present per unit time.

[0039] In implementation, the system of this invention, by setting up a data acquisition module, a data processing module, a prediction module, a reporting adjustment module, a transmission adjustment module, and a prediction adjustment module, adjusts the dynamic reporting interval triggered by the traffic flow change rate based on the lag time of the response to the data transmission of operational status data. Since the prediction of highway operational status data requires extremely high data freshness, but narrowband IoT, due to its narrowband modulation and non-real-time scheduling mechanism, suffers from increased transmission delay, it may lead to inaccurate predictions due to congestion already occurring. By reducing the dynamic reporting interval triggered by the traffic flow change rate, it ensures that key data such as sudden drops in vehicle speed and sudden changes in traffic flow arrive at the prediction system before congestion occurs, reserving sufficient prediction response time for the model and reducing the probability of inaccurate predictions due to data delay. The system also adjusts the dynamic offset of the transmission timing based on the packet loss rate of operational status data transmission per unit time. Since highways often traverse mountainous areas, and the mountains... Shadows and elevated bridge piers can cause multipath fading of signals, leading to drastic fluctuations in signal strength at the receiving end. This can cause a sharp increase in demodulation error rate and packet loss rate in a single transmission. By increasing the dynamic offset of transmission timing, the adjustment range of transmission time can be expanded, effectively avoiding periodic or random signal degradation windows, thereby reducing the packet loss rate in a single transmission. The pre-compensation amount of predictive power is adjusted based on the false positive rate of no signal per unit time. Since high-voltage power towers around highways generate low-frequency electromagnetic noise, which superimposes with the low-frequency subcarriers of narrowband IoT, base stations may mistakenly judge no signal and discard data packets. By increasing the pre-compensation amount of predictive power, the impact of sudden noise enhancement can be offset by increasing the transmission power in advance and retaining redundancy. This compensates for the lag of traditional dynamic adjustment, reduces the false positive rate of base stations caused by the instantaneous inundation of signal by noise, and improves the prediction accuracy of operational status data.

[0040] Please see Figure 2 As shown, it is a logical flowchart of the dynamic reporting interval process triggered by the determination of traffic flow change rate in the highway operation status prediction system based on ETC gantry data according to an embodiment of the present invention.

[0041] Specifically, the lag time of the reporting and adjustment module in responding to the data transmission of the operating status is less than or equal to a preset first lag time, thus ensuring that the prediction accuracy of the operating status data meets the requirements. If the delay in the reporting adjustment module's response to the data transmission of the operating status is greater than the preset first delay, it is determined that the prediction accuracy of the operating status data does not meet the requirements.

[0042] Specifically, if the lag time of the reporting adjustment module in responding to the operation status data transmission response is greater than the preset first lag time and less than or equal to the preset second lag time, it is initially determined that the transmission reliability of the operation status data does not meet the requirements, and the transmission reliability of the data is determined based on the packet loss rate of the operation status data transmission per unit time.

[0043] It is understandable that the preset first lag time is shorter than the preset second lag time, and the three intervals divided by the preset first lag time and the preset second lag time correspond to three different situations: The first interval is when the lag time of the operation status data transmission response is less than or equal to the preset first lag time, which corresponds to the situation where the prediction accuracy of the operation status data meets the requirements. The second interval is the lag time of the data transmission response in the running state, which is greater than the preset first lag time and less than or equal to the preset second lag time. The corresponding situation is: because the highway passes through mountainous areas, the shadow of the mountain and the piers of the viaduct will cause multipath fading of the signal, resulting in drastic fluctuations in the signal strength at the receiving end, which may cause a sharp increase in the demodulation error rate and an increase in the packet loss rate of a single transmission. The third interval is when the lag time of the operation status data transmission response is greater than the preset second lag time. The corresponding situation is: because the prediction of highway operation status data requires extremely high data freshness, but the narrowband Internet of Things adopts narrowband modulation and non-real-time scheduling mechanism, resulting in increased transmission delay, which may lead to inaccurate prediction due to the formation of congestion.

[0044] Understandably, this system uses preset first and second lag durations to characterize the prediction accuracy of operational status data. Its core principle is to utilize quantifiable grading capabilities of system latency using lag thresholds to accurately distinguish between three states: acceptable prediction performance, need for root cause diagnosis, and need for emergency intervention. This avoids the recklessness of relying on a single threshold and adapts to the needs of highway scenarios for tiered control of prediction timeliness. The first preset duration can be set as the ideal response threshold acceptable to the system, ensuring that minor delays are not over-responded to. The second preset duration is set as the system's tolerable limit response threshold, ensuring that severe delays can be forcibly corrected. This setting balances the stability of traffic flow under normal conditions with the ability to accurately identify systemic deviations caused by data transmission issues, avoiding the impact of brief network jitter on the overall prediction performance assessment. The preset first and second lag durations can be set according to actual operating conditions. The setting of the preset first and second lag durations aims to ensure the accuracy and practicality of operational status data prediction. Optionally, the preset first lag time and the preset second lag time are determined through a limited number of experiments by evaluating the predictive effect of the lag time of data transmission response under different operating states on the operating state data. The determined preset first lag time and preset second lag time should satisfy the condition that they are neither too small nor cause excessive interference to the prediction process of operating state data. For example, the preset first lag time is generally selected in the range of [1s, 3s], and the preset second lag time is generally selected in the range of [4s, 6s].

[0045] Preferably, the first lag time is 2 seconds in a preferred embodiment, and the second lag time is 5 seconds in a preferred embodiment.

[0046] Specifically, the lag time of the reporting adjustment module in responding to the operation status data transmission response is greater than the preset second lag time, thereby reducing the dynamic reporting interval triggered by the traffic flow change rate; The reduction in the dynamic reporting interval triggered by the traffic flow change rate is determined by the difference between the lag time of the operation status data transmission response and the preset second lag time.

[0047] Specifically, when the difference between the lag time of the operational status data transmission response and the preset second lag time is within 3 seconds, the dynamic reporting interval triggered by the traffic flow change rate is reduced to 0.9 times the original value. When the difference between the lag time of the operational status data transmission response and the preset second lag time exceeds 3 seconds, in addition to reducing it to 0.9 times the original value, for every 1 second exceeding 3 seconds, the dynamic reporting interval triggered by the traffic flow change rate is reduced by 0.1 seconds. For example, if the difference between the lag time of the operational status data transmission response and the preset second lag time is 4 seconds, and the current dynamic reporting interval triggered by the traffic flow change rate is 1 second, the reduced dynamic reporting interval triggered by the traffic flow change rate is 1 × 0.9 - 0.1 × 1 = 0.8 seconds.

[0048] In implementation, the system of the present invention adjusts the dynamic reporting interval triggered by traffic flow change rate by setting a preset first lag time and a preset second lag time. Since the prediction of highway operation status data requires extremely high data freshness, but the narrowband Internet of Things uses narrowband modulation and non-real-time scheduling mechanisms, resulting in increased transmission delay, it may lead to inaccurate predictions due to congestion already formed. By reducing the dynamic reporting interval triggered by traffic flow change rate, it can ensure that key data such as sudden drop in vehicle speed and sudden change in traffic flow arrive at the prediction system before congestion forms, reserve sufficient prediction response time for the model, reduce the probability of prediction inaccuracy due to data delay, and further improve the prediction accuracy of operation status data.

[0049] Please continue reading. Figure 3 As shown, it is a logical flowchart of the dynamic offset process for determining the transmission timing in the highway operation status prediction system based on ETC gantry data according to an embodiment of the present invention.

[0050] Specifically, the transmission adjustment module determines that the transmission reliability of the operating status data meets the requirements when the packet loss rate of the operating status data transmission within the unit time is less than or equal to a preset first packet loss rate. The transmission adjustment module determines that the transmission reliability of the operating status data does not meet the requirements when the packet loss rate of the operating status data transmission within the unit time is greater than the preset first packet loss rate.

[0051] Specifically, the transmission adjustment module increases the dynamic offset of the transmission timing in response to the packet loss rate of the running state data transmission within the unit time being greater than the preset first packet loss rate and less than or equal to the preset second packet loss rate.

[0052] Specifically, the transmission adjustment module responds to the fact that the packet loss rate of the running status data transmission within a unit time is greater than the preset second packet loss rate, and initially determines that the electromagnetic interference resistance of the running status data transmission does not meet the requirements. It then determines whether the electromagnetic interference resistance of the running status data transmission meets the requirements based on the false judgment rate of no signal within a unit time.

[0053] It is understandable that the preset first packet loss rate is lower than the preset second packet loss rate. The three intervals divided by the preset first packet loss rate and the preset second packet loss rate correspond to three different scenarios: The first interval is when the packet loss rate of the running status data transmission per unit time is less than or equal to the preset first packet loss rate. The corresponding situation is: the transmission reliability of the running status data meets the requirements. The second interval is when the packet loss rate of the running status data transmission per unit time is greater than the preset first packet loss rate and less than or equal to the preset second packet loss rate. The corresponding situation is: because highways pass through mountainous areas, the shadows of mountains and the piers of viaducts can cause multipath fading of signals, resulting in drastic fluctuations in the signal strength at the receiving end, which may cause a sharp increase in the demodulation error rate and an increase in the packet loss rate of a single transmission. The third interval is when the packet loss rate of the running status data transmission per unit time is greater than the preset second packet loss rate. The corresponding situation is: because the high-voltage power towers around the highway will generate low-frequency electromagnetic noise, which will form co-frequency noise superposition with the low-frequency subcarrier of the narrowband Internet of Things, causing the base station to mistakenly judge that there is no signal and discard the data packet.

[0054] Understandably, using the first and second preset packet loss rates to characterize data transmission reliability is fundamentally about leveraging the quantification of channel quality by the packet loss rate. This allows for precise differentiation between three states: reliable communication links, the need for optimized transmission strategies, and the need for interference diagnosis. This avoids the blind application of single threshold judgments and aligns with the demands of narrowband IoT for tiered communication quality control in complex environments. The first preset packet loss rate can be set as the inherent channel fluctuation threshold, ensuring that normal packet loss caused by random noise is not misjudged as a fault. The second preset packet loss rate is set as the channel abnormal degradation threshold, ensuring that abnormal packet loss caused by persistent strong interference is effectively captured. This setting considers both the time-varying characteristics of the wireless channel and the accurate identification of systemic communication faults, avoiding the misjudgment of the overall communication link status due to brief signal fluctuations. The first and second preset packet loss rates can be set according to actual operating conditions. The setting of the first and second preset packet loss rates aims to ensure the accuracy and practicality of operational status data prediction. Optionally, the preset first packet loss rate and preset second packet loss rate are determined by evaluating the predictive effect of the packet loss rate of data transmission under different operating states on the operating state data through a limited number of experiments. The determined preset first packet loss rate and preset second packet loss rate should meet the requirement that they are neither too small nor cause excessive interference to the prediction process of operating state data.

[0055] For example, the preset first packet loss rate is generally selected in the range of [1%, 3%], and the preset second packet loss rate is generally selected in the range of [4%, 6%].

[0056] Preferably, the first packet loss rate is 2% in a preferred embodiment, and the second packet loss rate is 5% in a preferred embodiment.

[0057] Specifically, the increase in the dynamic offset of the transmission timing is determined by the difference between the packet loss rate of the running state data transmission per unit time and the preset first packet loss rate.

[0058] Specifically, when the difference between the packet loss rate of running status data transmission and the preset first packet loss rate is within 1%, the dynamic offset of the transmission timing increases to 1.2 times the original value. When the difference between the packet loss rate of running status data transmission and the preset first packet loss rate exceeds 1%, in addition to increasing to 1.2 times the original value, the dynamic offset increases by 10ms for every 0.2% increase. For example, if the difference between the packet loss rate of running status data transmission and the preset first packet loss rate is 1.4% per unit time, and the current dynamic offset of the transmission timing is 50ms, then the increased dynamic offset will be 50×1.2+10×2=80ms.

[0059] In practice, the system described in this invention adjusts the dynamic offset of the transmission timing by setting a preset first packet loss rate and a preset second packet loss rate. Since highways pass through mountainous areas, the shadows of mountains and the presence of viaduct piers can cause multipath fading of signals, resulting in drastic fluctuations in the signal strength at the receiving end. This may cause a sharp increase in the demodulation error rate and an increase in the packet loss rate of a single transmission. By increasing the dynamic offset of the transmission timing, the adjustment range of the transmission time can be expanded, effectively avoiding periodic or random signal deterioration windows, thereby reducing the packet loss rate of a single transmission and further improving the prediction accuracy of the operating status data.

[0060] Please continue reading. Figure 4 The diagram shown is a logical flowchart of the process for determining the pre-compensation amount of predictive power in the highway operation status prediction system based on ETC gantry data according to an embodiment of the present invention.

[0061] Specifically, the prediction and adjustment module responds to the fact that the false judgment rate of no signal within the unit time is less than or equal to the preset false judgment rate, and determines that the anti-interference degree of electromagnetic interference of the data transmission in the operating state meets the requirements. The prediction adjustment module responds when the false positive rate of no signal within a unit time is greater than the preset false positive rate, determines that the anti-interference level of the data transmission in the operating state does not meet the requirements for electromagnetic interference, and increases the pre-compensation amount of the predictive power.

[0062] It is understandable that the two intervals of the preset false positive rate correspond to two different situations: The first interval is when the false alarm rate for no signal per unit time is less than or equal to the preset false alarm rate. The corresponding situation is: the data transmission meets the requirements for electromagnetic interference resistance. The second interval is when the false positive rate of no signal per unit time is greater than the preset false positive rate. The corresponding situation is that the high-voltage power towers around the highway will generate low-frequency electromagnetic noise, which will be superimposed with the low-frequency subcarriers of the narrowband Internet of Things, causing the base station to mistakenly judge that there is no signal and discard data packets.

[0063] It is understandable that using a preset false positive rate to characterize the anti-interference performance of a data transmission system against electromagnetic interference is primarily based on its core properties of quantifying the degree of interference, accurately defining link quality thresholds, and achieving precise power control. The preset false positive rate is a threshold determined during the system design phase through electromagnetic environment analysis, receiver sensitivity testing, and signal-to-noise ratio (SNR) tolerance verification. Its core function is to define the critical point between acceptable and unacceptable interference; enabling the system to accurately judge the severity of electromagnetic interference, dynamically adjust the transmission power strategy, and ultimately ensure the reliability, connectivity, and real-time performance of data transmission during highway congestion prediction. The preset false positive rate can be set according to actual operating conditions. The setting of the preset false positive rate aims to ensure the accuracy and practicality of operational status data prediction. Optionally, the preset false positive rate is determined through a limited number of experiments by evaluating the prediction effect of the false positive rate without signal per unit time on operational status data. The determined preset false positive rate should be neither too low nor cause excessive interference to the operational status data prediction process.

[0064] For example, the preset false positive rate is generally selected in the range of [2%, 4%].

[0065] Preferably, the preset false positive rate is 3% in this embodiment.

[0066] Specifically, the increase in the pre-compensation amount of the predictive power is determined by the difference between the false positive rate of no signal per unit time and the preset false positive rate.

[0067] Specifically, when the difference between the false positive rate of no signal per unit time and the preset false positive rate is within 3%, the pre-compensation amount of predictive power is increased to 1.1 times the original amount. When the difference exceeds 3%, in addition to increasing to 1.1 times the original amount, the pre-compensation amount of predictive power increases by 0.5 dBm for every 1% exceeding the preset false positive rate. For example, if the difference between the false positive rate of no signal per unit time and the preset false positive rate is 4%, and the current pre-compensation amount of predictive power is 20 dBm, the increased pre-compensation amount of predictive power will be 20 × 1.1 + 0.5 × 1 = 22.5 dBm.

[0068] Specifically, dBm is the unit of pre-compensation for predictive power, which means decibels and milliwatts.

[0069] In practice, the system described in this invention adjusts the pre-compensation amount of predictive power by setting a preset misjudgment rate. Since the high-voltage power towers around highways generate low-frequency electromagnetic noise, which superimposes with the low-frequency subcarriers of narrowband Internet of Things, the base station may misjudge that there is no signal and discard data packets. By increasing the pre-compensation amount of predictive power, the impact of sudden noise enhancement can be offset by increasing the transmission power in advance and retaining redundancy. This compensates for the lag of traditional dynamic adjustment, reduces the base station misjudgment rate caused by the instantaneous submersion of the signal by noise, and further improves the prediction accuracy of the operating status data.

[0070] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

Claims

1. A highway operation status prediction system based on ETC gantry data, characterized in that, include: The data acquisition module includes a data acquisition unit for collecting highway operation status data through an ETC gantry and a data transmission unit connected to the data acquisition unit for transmitting the operation status data to the location to be processed using narrowband Internet of Things technology. The data processing module is connected to the data acquisition module and includes a preprocessing unit for preprocessing the operating status data to output optimized road condition data and a feature extraction unit connected to the preprocessing unit for performing feature extraction based on the optimized road condition data to output road condition features. The prediction module, which is connected to the data processing module, includes a model training unit for training an initial model based on the road condition characteristics to obtain a prediction model, and a prediction unit connected to the model training unit for predicting the traffic conditions of the highway based on the prediction model to obtain a prediction result. The reporting and adjustment module is connected to the data acquisition module and is used to determine the dynamic reporting interval triggered by the traffic flow change rate based on the lag time of the data transmission response in the operating status. The transmission adjustment module is connected to the data acquisition module and the reporting adjustment module respectively, and is used to determine the dynamic offset of the transmission timing based on the packet loss rate of the running status data transmission per unit time. A prediction adjustment module, which is connected to both the prediction module and the transmission adjustment module, is used to determine the pre-compensation amount of predictive power based on the false positive rate of no signal per unit time.

2. The highway operation status prediction system based on ETC gantry data according to claim 1, characterized in that, The delay time in the reporting and adjustment module's response to the data transmission of the operating status data is greater than the preset first delay time, indicating that the prediction accuracy of the operating status data does not meet the requirements.

3. The highway operation status prediction system based on ETC gantry data according to claim 2, characterized in that, If the lag time of the reporting adjustment module in responding to the operation status data transmission response is greater than the preset first lag time and less than or equal to the preset second lag time, it is initially determined that the transmission reliability of the operation status data does not meet the requirements, and the transmission reliability of the operation status data is determined based on the packet loss rate of the operation status data transmission per unit time.

4. The highway operation status prediction system based on ETC gantry data according to claim 3, characterized in that, The lag time of the reporting adjustment module in responding to the data transmission of the operating status is greater than the preset second lag time, thereby reducing the dynamic reporting interval triggered by the traffic flow change rate. The reduction in the dynamic reporting interval triggered by the traffic flow change rate is determined by the difference between the lag time of the operation status data transmission response and the preset second lag time.

5. The highway operation status prediction system based on ETC gantry data according to claim 4, characterized in that, The transmission adjustment module determines that the transmission reliability of the operating status data does not meet the requirements when the packet loss rate of the operating status data transmission per unit time is greater than the preset first packet loss rate.

6. The highway operation status prediction system based on ETC gantry data according to claim 5, characterized in that, The transmission adjustment module increases the dynamic offset of the transmission timing in response to the packet loss rate of the running status data transmission within the unit time being greater than the preset first packet loss rate and less than or equal to the preset second packet loss rate.

7. The highway operation status prediction system based on ETC gantry data according to claim 6, characterized in that, The transmission adjustment module responds to the fact that the packet loss rate of the running status data transmission within a unit time is greater than the preset second packet loss rate, and initially determines that the electromagnetic interference resistance of the running status data transmission does not meet the requirements. It then determines whether the electromagnetic interference resistance of the running status data transmission meets the requirements based on the false judgment rate of no signal within a unit time.

8. The highway operation status prediction system based on ETC gantry data according to claim 7, characterized in that, The increase in the dynamic offset of the transmission timing is determined by the difference between the packet loss rate of the running state data transmission per unit time and the preset first packet loss rate.

9. The highway operation status prediction system based on ETC gantry data according to claim 8, characterized in that, The prediction adjustment module responds when the false judgment rate of no signal per unit time is greater than the preset false judgment rate, determines that the anti-interference degree of electromagnetic interference of the data transmission in the operating state does not meet the requirements, and increases the pre-compensation amount of the predictive power.

10. The highway operation status prediction system based on ETC gantry data according to claim 9, characterized in that, The increase in the pre-compensation amount of the predictive power is determined by the difference between the false positive rate of no signal per unit time and the preset false positive rate.

Images