A communication system and method based on Internet of Things information technology

Abstract

The present invention relates to the field of Internet of Things technology, specifically a communication system and method based on Internet of Things information technology, the system includes a network monitoring module, a scheduling optimization module, a transmission efficiency adjustment module and a retransmission management module, and the network monitoring module continuously captures the network access point of the Internet of Things device based on real-time bandwidth demand data. The present invention, through real-time monitoring and the use of LSTM prediction models, can adapt to the rapid changes in network conditions, dynamically adjust the data transmission process, thereby reducing delays and packet loss in data transmission, the introduction of the DQN model further strengthens the data analysis during the transmission process, and can effectively improve the overall success rate of the transmission by evaluating the success or failure of the transmission event. The random forest algorithm is used to customize the retransmission mechanism for each data packet and network condition, which improves the accuracy and efficiency of the retransmission, not only improving the processing speed and accuracy of the communication system, but also ensuring that the excellent efficiency can be maintained in a network environment with high demand changes.

Description

Technical Field

[0001] The present invention relates to the technical field of Internet of Things, and in particular to a communication system and method based on Internet of Things information technology. Background Art

[0002] The Internet of Things (IoT) refers to the technology that connects physical devices together through the Internet. These devices can collect and exchange data to achieve automation and intelligent functions. IoT technology is widely used in many fields such as home automation, smart cities, industrial automation and healthcare, enabling devices to sense environmental changes and communicate through the Internet for remote monitoring and management.

[0003] Among them, the communication system is a core component of the Internet of Things, used to exchange data between devices, including from wireless sensor networks to complex systems such as cellular networks, Wi-Fi and other low-power wide-area network (LPWAN) technologies, such as LoRa and SigFox. The communication system enables IoT devices to remotely monitor, collect data, receive commands and respond, and is widely used in remote health monitoring, smart energy management, agriculture, and smart city infrastructure. Its main purpose is to improve the reliability and efficiency of data transmission, thereby supporting real-time and efficient operation of IoT devices.

[0004] Traditional communication systems lack sufficient adaptive mechanisms and are difficult to adjust in real time when facing network fluctuations, which often leads to transmission delays and data loss. Especially in remote monitoring and real-time data processing scenarios, such delays and inaccuracies have a negative impact on decision-making and operations. In addition, the fixed retransmission mechanism cannot effectively distinguish between different types of data packets and network quality, which often leads to unsatisfactory retransmission effects, increasing the burden on the system and reducing communication efficiency. These technical limitations are particularly evident in high-standard IoT applications, affecting the stable operation and data processing capabilities of the system. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a communication system and method based on Internet of Things information technology.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: a communication system based on Internet of Things information technology, the system comprising:

[0007] The network monitoring module continuously captures the changes in the network access point status of IoT devices based on real-time bandwidth demand data, calculates bandwidth change values ​​and delay measurement data, and performs real-time statistics on the captured packet loss rate to generate a set of network status indicators;

[0008] The scheduling optimization module analyzes the historical and real-time data transmission success rates of IoT devices based on the network status indicator set, uses the LSTM network to predict the optimal sending time, adjusts the sending window size and priority of the data packet according to the prediction results, and generates optimized scheduling information;

[0009] The transmission efficiency adjustment module uses the DQN model to monitor the data transmission effect from the IoT device to the server based on the optimization scheduling information, analyzes successful and failed transmission events, evaluates the current transmission efficiency, optimizes the future transmission success rate, and generates efficiency improvement configuration;

[0010] Based on the efficiency improvement configuration, the retransmission management module adopts the random forest algorithm to analyze the network quality data and data packet types, implements the retransmission mechanism for various types of data packets, monitors the results of the retransmission operation, and compares the original transmission and retransmission effects to generate a retransmission performance evaluation result.

[0011] The present invention is improved in that the calculation steps of the bandwidth change value and the delay measurement data are specifically as follows:

[0012] Based on real-time bandwidth demand data, monitor the network access point status of IoT devices, record bandwidth usage and network latency every minute in real time, and generate network performance data every minute;

[0013] Based on the network performance data per minute, the bandwidth change percentage and delay change per minute are calculated using the formula:

[0014]

[0015] and

[0016]

[0017] Get bandwidth change value With delay measurement data ,in, Indicates the current minute bandwidth. Indicates the bandwidth of the previous minute. Indicates the current minute delay, Indicates the previous minute delay.

[0018] The present invention is improved in that the steps of acquiring the network status indicator set are specifically as follows:

[0019] Monitor the packet loss rate of the network access point of the IoT device, send data packets periodically, and capture the difference between sending and receiving test packets in real time. Use the formula:

[0020]

[0021] Calculating Packet Loss Rate ,in, is the number of packets that did not reach the destination within the target time window, is the total number of packets sent in the same time window, is the expected number of packet losses, is the adjustment coefficient, which indicates the sensitivity of packet loss rate;

[0022] Based on the packet loss rate data, the bandwidth and delay data are analyzed, including network stability, reliability and responsiveness, to construct a network status indicator set.

[0023] The present invention is improved in that the step of predicting the optimal sending timing is specifically as follows:

[0024] Based on the network status indicator set, historical and real-time data of IoT devices are integrated, including timestamps of each data transmission, success or failure status, and associated network condition parameters, to obtain a collected data set;

[0025] Based on the collected data set, the LSTM network is used for learning and analysis to identify the correlation between the data transmission success rate, time and network status, and obtain a dynamic prediction model;

[0026] Based on the dynamic prediction model, the data transmission efficiency under the current network conditions is evaluated in real time using the formula:

[0027]

[0028] Calculate the optimal sending time ,in, Indicates the current time. is the time increment adjusted based on network congestion, is the current failure rate, is the failure rate threshold.

[0029] The present invention is improved in that the step of obtaining the optimized scheduling information is specifically as follows:

[0030] According to the prediction results, evaluating the current network bandwidth utilization and the urgency level of the data packets, and establishing a sending priority and a window size for each data packet;

[0031] Adjust the packet sending window size using the formula:

[0032]

[0033] Calculate the adjusted window size , generate optimized scheduling information, including the priority setting of each data packet, where is the current window size, It is the best time to send. is the current time, is the time buffer factor.

[0034] The present invention is improved in that the analysis steps of the successful and failed transmission events are specifically as follows:

[0035] Based on the optimized scheduling information, a DQN model is used to record data transmission events from IoT devices to servers, and each success and failure event and associated timestamp are marked to obtain a transmission event log;

[0036] Based on the transmission event log, the formula is adopted:

[0037]

[0038] Calculate the volatility of success rate and failure rate to obtain the transmission efficiency analysis results ,in, Represents each successful event, Represents each failed event, Represents the total number of events during the monitoring period, Represents the average failure rate.

[0039] The present invention is improved in that the optimization steps of the future transmission success rate are specifically as follows:

[0040] Evaluate the current transmission efficiency by collecting existing transmission data, extracting key indicators of success rate, failure cases and communication delay, and obtaining transmission efficiency data;

[0041] Based on the transmission efficiency data, the key factors affecting the transmission efficiency are determined and analyzed, using the formula:

[0042]

[0043] Optimize future transmission success rate and generate efficiency-enhancing configurations, including: and Represent the new and old transmission efficiencies respectively, is the efficiency improvement ratio parameter, is the sensitivity adjustment factor, and They are the current time and the target delay time respectively.

[0044] The present invention is improved in that the step of obtaining the retransmission performance evaluation result is specifically as follows:

[0045] Based on the efficiency improvement configuration, a random forest algorithm is used to analyze network quality data and transmission characteristics of multiple types of data packets, collect and classify transmission events in the network, and obtain analysis information including transmission status and data packet classification;

[0046] According to the analysis information, a targeted retransmission mechanism is implemented to prioritize retransmission of data packets marked as frequently failed, using the formula:

[0047]

[0048] Improved transmission success rate , obtain the retransmission implementation plan, where, is the success rate before retransmission, is the failure rate, is the target failure rate, is the adjustment factor, used to adjust the sensitivity of retransmission;

[0049] Based on the retransmission implementation plan, the processing effect of the retransmission operation is monitored, and the transmission success rates before and after the retransmission are compared to obtain a retransmission performance evaluation result.

[0050] A communication method based on Internet of Things information technology, wherein the communication method based on Internet of Things information technology is performed based on the above-mentioned communication system based on Internet of Things information technology, and comprises the following steps:

[0051] S1: Based on real-time bandwidth demand data, monitor the network access point status of IoT devices, calculate bandwidth change values ​​and delay measurement data, perform real-time statistics on the captured packet loss rate, and generate a network status indicator set;

[0052] S2: Based on the network status indicator set, analyze the historical and real-time data transmission success rates of IoT devices, use the LSTM network to predict the optimal sending time, adjust the sending window size and priority of the data packet, and generate optimized scheduling information;

[0053] S3: Based on the optimized scheduling information, a DQN model is used to monitor the data transmission effect from the IoT device to the server, and successful and failed transmission events are analyzed to optimize the future transmission success rate and generate efficiency improvement configuration;

[0054] S4: Based on the efficiency improvement configuration, a random forest algorithm is used to analyze network quality data and data packet types, a retransmission mechanism is implemented for various types of data packets, and an optimized configuration of the retransmission mechanism is generated to match network fluctuations;

[0055] S5: Based on the retransmission mechanism optimization configuration, monitor the retransmission operation results, redefine the network status parameters, adjust the data transmission and retransmission mechanism, and compare the original transmission and retransmission effects to generate a retransmission performance evaluation result.

[0056] Compared with the prior art, the advantages and positive effects of the present invention are:

[0057] In the present invention, through real-time monitoring and the use of LSTM prediction models, it is possible to adapt to the rapid changes in network conditions and dynamically adjust the data sending process, thereby reducing delays and packet losses in data transmission. The introduction of the DQN model further strengthens the data analysis during the transmission process. By evaluating the success or failure of the transmission event, the overall success rate of the transmission can be effectively improved. The random forest algorithm is used to customize the retransmission mechanism for each data packet and network condition, which improves the accuracy and efficiency of the retransmission. This not only improves the processing speed and accuracy of the communication system, but also ensures that excellent efficiency can be maintained in a network environment with high demand changes. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 A communication system module diagram based on Internet of Things information technology is proposed for the present invention;

[0059] Figure 2 is a flow chart for calculating bandwidth change value and delay measurement data in the present invention;

[0060] Figure 3 A flowchart of obtaining a network status indicator set in the present invention;

[0061] Figure 4 This is a flow chart for predicting the optimal sending timing in the present invention;

[0062] Figure 5 This is a flowchart for obtaining optimized scheduling information in the present invention;

[0063] Figure 6 is a flow chart for analyzing successful and failed transmission events in the present invention;

[0064] Figure 7 It is a flow chart for optimizing the future transmission success rate in the present invention;

[0065] Figure 8 This is a flow chart of obtaining the retransmission performance evaluation result in the present invention. DETAILED DESCRIPTION

[0066] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0067] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating positions or positional relationships, are based on the positions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0068] Example

[0069] See also Figure 1 The present invention provides a technical solution: a communication system based on Internet of Things information technology includes:

[0070] The network monitoring module continuously captures the changes in the network access point status of IoT devices based on real-time bandwidth demand data, calculates bandwidth change values ​​and delay measurement data, and performs real-time statistics on the captured packet loss rate to generate a set of network status indicators;

[0071] The scheduling optimization module analyzes the historical and real-time data transmission success rates of IoT devices based on the network status indicator set, uses the LSTM network to predict the optimal sending time, adjusts the sending window size and priority of the data packet according to the prediction results, and generates optimized scheduling information;

[0072] The transmission efficiency adjustment module uses the DQN model to monitor the data transmission effect from IoT devices to servers based on the optimized scheduling information, analyzes successful and failed transmission events, evaluates the current transmission efficiency, optimizes the future transmission success rate, and generates efficiency improvement configurations;

[0073] The retransmission management module is based on efficiency improvement configuration and adopts random forest algorithm to analyze network quality data and packet types, implement retransmission mechanism for various types of packets, monitor the results of retransmission operations, and compare the original transmission and retransmission effects to generate retransmission performance evaluation results.

[0074] The network status indicator set includes bandwidth index, delay indicator, and packet loss indicator. The optimization scheduling information includes the adjusted window size, priority level, and predicted timeliness. The efficiency improvement configuration includes transmission speed improvement information, stability enhancement information, and efficiency evaluation indicators. The retransmission performance evaluation results include retransmission efficiency, effect contrast, and data recovery quality.

[0075] See also Figure 2 , the calculation steps of bandwidth change value and delay measurement data are as follows:

[0076] Based on real-time bandwidth demand data, monitor the network access point status of IoT devices, record bandwidth usage and network latency every minute in real time, and generate network performance data every minute;

[0077] Monitor the network access point status of IoT devices, record the bandwidth usage and network delay every minute in real time, and collect data involving performance indicators of multiple access points and different time periods. Through high-frequency samplers and sensors, the equipment can accurately capture the data flow and delayed response time every minute. For the monitoring of bandwidth usage, considering the instability of the network, especially in the case of large-scale deployment of IoT devices, real-time data acquisition is particularly critical. The bandwidth usage data every minute is captured in real time through network traffic monitoring to ensure the integrity and accuracy of the data. For the measurement of network delay, the round-trip time of the network is calculated by sending test packets at regular intervals. The equipment is set at different nodes of the network to ensure the comprehensiveness of the test and the representativeness of the data. It can generate network performance data every minute in real time, and the data provides a basis for the subsequent calculation of bandwidth change values ​​and network status analysis.

[0078] Based on the network performance data every minute, calculate the bandwidth change percentage and latency change every minute using the formula:

[0079]

[0080] and

[0081]

[0082] Get bandwidth change value With delay measurement data ,in, Indicates the current minute bandwidth. Indicates the bandwidth of the previous minute. Indicates the current minute delay, Indicates the previous minute delay;

[0083] Monitor to current minute Mbps, last minute Mbps, the bandwidth change value is calculated as follows:

[0084]

[0085] Similarly, monitoring the delay to the current minute ms, the previous minute ms, the calculation process of the delay change value is as follows:

[0086]

[0087] It shows that the bandwidth increased by 50% and the delay increased by 20ms, reflecting the change of network status within this minute. Further data analysis and processing will be carried out based on the calculation results.

[0088] See also Figure 3 , the specific steps for obtaining the network status indicator set are:

[0089] Monitor the packet loss rate of the network access point of the IoT device, send data packets periodically, and capture the difference between sending and receiving test packets in real time. Use the formula:

[0090]

[0091] Calculating Packet Loss Rate ,in, is the number of packets that did not reach the destination within the target time window, is the total number of packets sent in the same time window, is the expected number of packet losses, is the adjustment coefficient, which indicates the sensitivity of packet loss rate;

[0092] Monitor the total number of packets sent within a time window , where the unreached packets , the expected number of packet losses , adjustment coefficient , calculated as follows:

[0093]

[0094]

[0095]

[0096]

[0097] The results show that the actual packet loss rate is slightly higher than the expected packet loss rate, reflecting a slight stability problem in the network. This calculation provides a more flexible and sensitive network performance evaluation by comparing the difference between the actual and expected packet loss rates.

[0098] Based on the packet loss rate data, analyze the bandwidth and latency data, including network stability, reliability, and responsiveness, and build a set of network status indicators;

[0099] Based on the packet loss rate data set, the bandwidth and latency data are analyzed to calculate and generate network health indicators, including network stability, reliability and responsiveness. Through comprehensive indicators, a network status indicator set is constructed to provide real-time data support for network maintenance and decision-making. This process involves collecting a wide range of network performance data and applying statistical and analytical techniques to parse the data and extract key performance indicators, including average latency, maximum and minimum bandwidth usage, and other network health indicators. The results will be used to optimize network configuration and enhance network responsiveness. The generated network status indicator set provides a comprehensive snapshot of network health to identify and resolve potential network problems.

[0100] See also Figure 4 , the specific steps for predicting the optimal sending time are:

[0101] Based on the network status indicator set, historical and real-time data of IoT devices are integrated, including the timestamp of each data transmission, the success or failure status and the associated network condition parameters, to obtain the collected data set;

[0102] Integrate historical and real-time data of IoT devices, collect the timestamp of each data transmission, the success or failure status and related network condition parameters, and format and store the data to support subsequent data analysis. The construction of this dataset not only provides the necessary foundation for model training, but also provides support for real-time monitoring to ensure that the collected data is comprehensive and detailed, covering different types of network conditions and transmission situations.

[0103] Based on the collected data set, the LSTM network is used for learning and analysis to identify the correlation between data transmission success rate, time and network status, and obtain a dynamic prediction model;

[0104] The collected data is analyzed using a long short-term memory network, which involves setting various parameters of the model, such as the number of network layers, the number of neurons, the learning rate, etc., and performing multiple rounds of training to optimize the performance of the model. During the training process, the prediction error is minimized by continuously adjusting the internal weights to improve the fit to the time series data. The ability of LSTM lies in its unique structure for processing time series data, which enables it to capture long-term dependencies in the data and thus more accurately predict future data transmission timing. The generated model will be able to predict the optimal data transmission timing based on the input real-time data, thereby improving overall transmission efficiency.

[0105] Based on the dynamic prediction model, the data transmission efficiency under the current network conditions is evaluated in real time using the formula:

[0106]

[0107] Calculate the optimal sending time ,in, Indicates the current time. is the time increment adjusted based on network congestion, is the current failure rate, is the failure rate threshold;

[0108] Monitor the current time is 1500 seconds, Set to 300 seconds, the current failure rate is 0.2, the failure rate threshold is 0.5, substitute it into the formula to calculate the optimal sending time:

[0109]

[0110]

[0111]

[0112]

[0113]

[0114] The results show that, considering the failure rate under the current network conditions, the optimal time to send data is postponed to 1701.096 seconds, so that the data is sent when the network status is relatively stable, thereby improving the success rate.

[0115] See also Figure 5 ,The specific steps for obtaining optimized scheduling information are:

[0116] Based on the prediction results, the current network bandwidth utilization and packet urgency level are evaluated, and the sending priority and window size are established for each packet.

[0117] Based on the analysis of historical and real-time data, the future network status is predicted through the long short-term memory network. Features are extracted from the historical data collected by IoT devices and compared with the real-time data. The pattern of data transmission success rate is determined through time series analysis technology, which involves the calculation and adjustment of multiple parameters, such as window size, transmission rate and data priority. The sending strategy of each data packet is adjusted to match the prediction results to ensure that each data transmission can be carried out at the best time, so as to improve the overall network efficiency and optimize data transmission.

[0118] Adjust the packet sending window size using the formula:

[0119]

[0120] Calculate the adjusted window size , generate optimized scheduling information, including the priority setting of each data packet, where is the current window size, Is the best time to send, is the current time, is the time buffer factor;

[0121] If the current window size 50, the best time to send is 100ms, current time The time buffer factor is 90ms. is 10ms, the new window size The calculation is as follows:

[0122]

[0123]

[0124]

[0125] The results show that the window size needs to be increased by 100 to adapt to the upcoming best sending opportunity and optimize data transmission efficiency. The optimized scheduling information includes the adjusted data sending window and the priority of each data packet. The information is set according to the prediction results and the current network status. Through network scheduling implementation, the adjustment is dynamically optimized according to the real-time analysis of network conditions and predicted data transmission requirements, which improves the utilization of network resources and reduces the delay of data transmission.

[0126] See also Figure 6 , the analysis steps for successful and failed transmission events are as follows:

[0127] Based on the optimized scheduling information, the DQN model is used to record the data transmission events from IoT devices to the server, marking each success and failure event and the associated timestamp to obtain the transmission event log;

[0128] Real-time monitoring using the DQN model includes setting monitoring points on the communication link between IoT devices and servers, capturing and recording all transmission events, recording the success and failure of each data transmission, and marking the timestamp. Through data capture and logging, sufficient information can be collected for further data analysis, ensuring the integrity and traceability of the data, and providing the necessary raw data for subsequent efficiency analysis. This process is completely dependent on the on-site network facilities and the configuration of the monitoring software, and requires technical personnel to continuously monitor the operating status to ensure real-time updating and accuracy of the data.

[0129] Based on the transmission event log, the formula is used:

[0130]

[0131] Calculate the volatility of success rate and failure rate to obtain the transmission efficiency analysis results ,in, Represents each successful event, Represents each failed event, Represents the total number of events during the monitoring period, represents the average failure rate;

[0132] The data collected and monitored are as follows: , success event , failure event , the average failure rate , substitute the value into the formula to calculate the transmission efficiency, then:

[0133]

[0134] After multiplying the result by the percentage, it shows that the current transmission success rate is 80%, and the negative impact of the failure rate on the overall efficiency is currently zero, indicating that the current system stability is good.

[0135] See also Figure 7 , the optimization steps for future transmission success rate are as follows:

[0136] Evaluate the current transmission efficiency by collecting existing transmission data, extracting key indicators such as success rate, failure cases, and communication delay, and obtaining transmission efficiency data;

[0137] Monitor the communication link between IoT devices and servers to ensure that the transmission status of each data is captured, whether successful or failed, and timestamp each event to record event logs. The logs list the transmission results and corresponding time stamps of each data packet. The logs are used for subsequent data analysis and network performance evaluation to ensure data integrity and traceability. It is necessary to continuously monitor the operating status of the system and update the monitoring configuration in a timely manner to cope with network fluctuations and equipment changes, thereby ensuring the accuracy of real-time data and the continuity of monitoring activities.

[0138] Based on the transmission efficiency data, determine and analyze the key factors affecting the transmission efficiency, using the formula:

[0139]

[0140] Optimize future transmission success rate and generate efficiency-enhancing configurations, including: and Represent the new and old transmission efficiencies respectively, is the efficiency improvement ratio parameter, is the sensitivity adjustment factor, and They are the current time and the target delay time;

[0141] set up (i.e. the current 75% success rate), (Expected efficiency improvement is 5%), , ms, ms. Substituting the values ​​into the formula, the calculation process is as follows:

[0142]

[0143]

[0144]

[0145]

[0146]

[0147]

[0148]

[0149] The result shows that through adjustments, the new transmission success rate is expected to increase to about 78.7%, demonstrating the effectiveness of the optimization measures and enhancing the transmission performance of the network.

[0150] See also Figure 8 , the specific steps for obtaining the retransmission performance evaluation results are:

[0151] Based on the efficiency improvement configuration, the random forest algorithm is used to analyze the network quality data and the transmission characteristics of multiple types of data packets, collect and classify the transmission events in the network, and obtain analysis information including transmission status and data packet classification;

[0152] The random forest algorithm is used to analyze network quality data from various data packets, focusing on how to classify data packets according to the type of data packet and its performance in the network, such as latency and packet loss rate, so as to identify the types of data packets that frequently fail due to network congestion or configuration errors, and generate a network transmission report. The report reveals the transmission efficiency of each type of data packet and provides basic data for targeted improvement measures. This data provides a practical basis for optimizing network transmission strategies, and lists in detail the overall performance of the network and the influencing factors to ensure that subsequent strategies can improve network quality in a targeted manner.

[0153] According to the analysis information, a targeted retransmission mechanism is implemented to give priority to retransmission of data packets marked as frequently failed, using the formula:

[0154]

[0155] Improved transmission success rate , obtain the retransmission implementation plan, where, is the success rate before retransmission, is the failure rate, is the target failure rate, is the adjustment factor, used to adjust the sensitivity of retransmission;

[0156] set up (i.e. 70% original success rate), (i.e. 20% failure rate), (i.e. the goal is to reduce the failure rate to 10%), (a small adjustment factor used to fine-tune the reaction speed), substitute the value:

[0157]

[0158]

[0159]

[0160] The results show that the retransmission mechanism can greatly improve the success rate, indicating the potential for performance improvement and providing data support for further adjustments.

[0161] Based on the retransmission implementation plan, monitor the processing effect of the retransmission operation and compare the transmission success rate before and after retransmission to obtain the retransmission performance evaluation result;

[0162] After implementing the retransmission strategy, the actual effect of the retransmission operation is monitored, and the data transmission success rate before and after the improvement is compared to conduct performance evaluation and obtain the retransmission performance evaluation results, which show the specific changes in the success rate before and after the implementation of the retransmission mechanism. For example, the success rate increased from 85% to 88%, providing quantitative improvement evidence, proving the effectiveness of the retransmission strategy, and providing data support for further network optimization.

[0163] A communication method based on Internet of Things information technology comprises the following steps:

[0164] S1: Based on real-time bandwidth demand data, monitor the network access point status of IoT devices, calculate bandwidth change values ​​and delay measurement data, perform real-time statistics on the captured packet loss rate, and generate a network status indicator set;

[0165] S2: Based on the network status indicator set, analyze the historical and real-time data transmission success rates of IoT devices, use the LSTM network to predict the optimal sending time, adjust the sending window size and priority of the data packet, and generate optimized scheduling information;

[0166] S3: Based on the optimized scheduling information, the DQN model is used to monitor the data transmission effect from IoT devices to the server, analyze successful and failed transmission events, optimize the future transmission success rate, and generate efficiency improvement configurations;

[0167] S4: Based on the efficiency improvement configuration, the random forest algorithm is used to analyze the network quality data and packet types, implement the retransmission mechanism for various types of packets, match the network fluctuations, and generate the retransmission mechanism optimization configuration;

[0168] S5: Based on the retransmission mechanism optimization configuration, monitor the retransmission operation results, redefine the network status parameters, adjust the data transmission and retransmission mechanism, and compare the original transmission and retransmission effects to generate the retransmission performance evaluation results.

[0169] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A communication system based on Internet of Things information technology, characterized in that: The system comprises: The network monitoring module continuously captures the changes in the network access point status of IoT devices based on real-time bandwidth demand data, calculates bandwidth change values ​​and delay measurement data, and performs real-time statistics on the captured packet loss rate to generate a set of network status indicators; The scheduling optimization module analyzes the historical and real-time data transmission success rates of IoT devices based on the network status indicator set, uses the LSTM network to predict the optimal sending time, adjusts the sending window size and priority of the data packet according to the prediction results, and generates optimized scheduling information; The transmission efficiency adjustment module uses the DQN model to monitor the data transmission effect from the IoT device to the server based on the optimization scheduling information, analyzes successful and failed transmission events, evaluates the current transmission efficiency, optimizes the future transmission success rate, and generates efficiency improvement configuration; The retransmission management module uses a random forest algorithm based on the efficiency improvement configuration to analyze network quality data and data packet types, implement a retransmission mechanism for multiple types of data packets, monitor the retransmission operation results, and compare the original transmission and retransmission effects to generate a retransmission performance evaluation result; The steps for predicting the optimal sending timing are specifically as follows: Based on the network status indicator set, historical and real-time data of IoT devices are integrated, including timestamps of each data transmission, success or failure status, and associated network condition parameters, to obtain a collected data set; Based on the collected data set, the LSTM network is used for learning and analysis to identify the correlation between the data transmission success rate, time and network status, and obtain a dynamic prediction model; Based on the dynamic prediction model, the data transmission efficiency under the current network conditions is evaluated in real time using the formula: Calculate the optimal sending time ,in, Indicates the current time. is the time increment adjusted based on network congestion, is the current failure rate, is the failure rate threshold; The steps for obtaining the optimized scheduling information are specifically as follows: According to the prediction results, evaluating the current network bandwidth utilization and the urgency level of the data packets, and establishing a sending priority and a window size for each data packet; Adjust the packet sending window size using the formula: Calculate the adjusted window size , generate optimized scheduling information, including the priority setting of each data packet, where is the current window size, It is the best time to send. is the current time, is the time buffer factor; The optimization steps of the future transmission success rate are specifically as follows: Evaluate the current transmission efficiency by collecting existing transmission data, extracting key indicators of success rate, failure cases and communication delay, and obtaining transmission efficiency data; Based on the transmission efficiency data, the key factors affecting the transmission efficiency are determined and analyzed, using the formula: Optimize future transmission success rates and generate efficiency-enhancing configurations, including: and Represent the new and old transmission efficiencies respectively, is the efficiency improvement ratio parameter, is the sensitivity adjustment factor, and They are the current time and the target delay time respectively.

2. The communication system based on Internet of Things information technology according to claim 1 is characterized in that: The calculation steps of the bandwidth change value and the delay measurement data are specifically as follows: Based on real-time bandwidth demand data, monitor the network access point status of IoT devices, record bandwidth usage and network latency every minute in real time, and generate network performance data every minute; Based on the network performance data per minute, the bandwidth change percentage and delay change per minute are calculated using the formula: and Get bandwidth change value With delay measurement data ,in, Indicates the current minute bandwidth. Indicates the bandwidth of the previous minute. Indicates the current minute delay, Indicates the previous minute delay.

3. The communication system based on Internet of Things information technology according to claim 1 is characterized in that: The steps for obtaining the network status indicator set are specifically as follows: Monitor the packet loss rate of the network access point of the IoT device, send data packets periodically, and capture the difference between sending and receiving test packets in real time. Use the formula: Calculating Packet Loss Rate ,in, is the number of packets that did not reach the destination within the target time window, is the total number of packets sent in the same time window, is the expected number of packet losses, is the adjustment coefficient, which indicates the sensitivity of packet loss rate; Based on the packet loss rate, the bandwidth and delay data are analyzed, and network health indicators, including network stability, reliability and responsiveness, are calculated and generated to construct a network status indicator set.

4. The communication system based on Internet of Things information technology according to claim 1 is characterized in that: The analysis steps of the successful and failed transmission events are specifically as follows: Based on the optimized scheduling information, a DQN model is used to record data transmission events from IoT devices to servers, and each success and failure event and associated timestamp are marked to obtain a transmission event log; Based on the transmission event log, the formula is adopted: Calculate the volatility of success rate and failure rate to obtain the transmission efficiency analysis results ,in, Represents each successful event, Represents each failed event, Represents the total number of events during the monitoring period, Represents the average failure rate.

5. The communication system based on Internet of Things information technology according to claim 1 is characterized in that: The steps for obtaining the retransmission performance evaluation result are specifically as follows: Based on the efficiency improvement configuration, a random forest algorithm is used to analyze network quality data and transmission characteristics of multiple types of data packets, collect and classify transmission events in the network, and obtain analysis information including transmission status and data packet classification; According to the analysis information, a targeted retransmission mechanism is implemented to prioritize retransmission of data packets marked as frequently failed, using the formula: Improved transmission success rate , obtain the retransmission implementation plan, where, is the success rate before retransmission, is the failure rate, is the target failure rate, is the adjustment factor, used to adjust the sensitivity of retransmission; Based on the retransmission implementation plan, the processing effect of the retransmission operation is monitored, and the transmission success rates before and after the retransmission are compared to obtain a retransmission performance evaluation result.

6. A communication method based on Internet of Things information technology, characterized in that: The communication system based on Internet of Things information technology according to any one of claims 1 to 5 is implemented, comprising the following steps: Based on real-time bandwidth demand data, monitor the network access point status of IoT devices, calculate bandwidth change values ​​and delay measurement data, perform real-time statistics on the captured packet loss rate, and generate a set of network status indicators; Based on the network status indicator set, the historical and real-time data transmission success rates of IoT devices are analyzed, the optimal sending time is predicted using the LSTM network, the sending window size and priority of the data packet are adjusted, and optimized scheduling information is generated; Based on the optimized scheduling information, a DQN model is used to monitor the data transmission effect from IoT devices to the server, analyze successful and failed transmission events, optimize future transmission success rates, and generate efficiency improvement configurations; Based on the efficiency improvement configuration, a random forest algorithm is used to analyze network quality data and data packet types, implement a retransmission mechanism for multiple types of data packets, match network fluctuations, and generate an optimized configuration for the retransmission mechanism; Based on the retransmission mechanism optimization configuration, the retransmission operation results are monitored, the network status parameters are redefined, the data transmission and retransmission mechanism are adjusted, and the original transmission and retransmission effects are compared to generate a retransmission performance evaluation result.

Images