Remote real-time control system for industrial internet

Abstract

The invention discloses a remote real-time control system for an industrial internet, particularly relates to the technical field of remote control, and comprises a self-adaptive network delay compensation module, a multi-path redundancy transmission module and an intelligent data compression and optimization module. The self-adaptive network delay compensation module monitors network delay through a high-frequency heartbeat packet, predicts by adopting a self-adaptive filtering algorithm, and dynamically corrects a prediction model in combination with a closed-loop feedback mechanism of a PI (Proportional Integral) controller to realize accurate delay compensation; and the multi-path redundancy transmission module dynamically distributes data packets based on the real-time calculated sending cost by establishing a plurality of transmission paths so as to realize intelligent load balancing and automatic switching of fault paths. The problems of poor real-time performance and low reliability caused by network delay, jitter and bandwidth limitation in industrial internet remote control are effectively solved, and the comprehensive performance of the system is remarkably improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of remote control, more particularly, the present application relates to a remote real-time control system for industrial internet. BACKGROUND

[0002] In the field of industrial internet, remote real-time control system is the core to realize intelligent manufacturing and unmanned operation. Such system transmits the instructions of control end to remote industrial equipment through public network, and recycles the equipment state data in real time. However, the unreliability and heterogeneity of network bring serious challenges to remote control. Traditional control system is mostly designed based on local area network, and its stable low delay and high bandwidth environment is difficult to reproduce in complex wide area network. The inherent delay, jitter and packet loss in network transmission will directly lead to that the control instructions cannot arrive on time, or the equipment state information cannot be updated in time, which seriously affects the control accuracy and stability of the system, and even may cause production safety accidents.

[0003] To cope with the above challenges, some solutions are proposed in the prior art. For example, fixed delay compensation value is used to send instructions in advance, or a single network redundancy path is configured for key data. At the data level, general lossless or lossy compression algorithms are commonly used to reduce network load. However, these methods have obvious limitations: static compensation mechanism cannot adapt to the dynamic changes of network conditions, often causing overcompensation or insufficient compensation; simple path redundancy lacks intelligent scheduling, and cannot fully utilize the bandwidth aggregation and fault tolerance advantages of multiple paths; and general compression algorithms are difficult to achieve a good balance between compression rate, processing speed and the preservation of the unique structure of industrial control data.

[0004] Therefore, the prior art lacks a comprehensive solution that can handle network delay, transmission reliability and data bandwidth limitations simultaneously. Most systems only provide improvements for a single problem, resulting in poor overall performance when facing complex and variable remote control scenarios in industrial internet, and real-time and reliability cannot be guaranteed at the same time. It has become a technical problem to be solved in the field to develop an integrated control system that can adapt to network fluctuations, has intelligent transmission scheduling and efficient data optimization capabilities. SUMMARY

[0005] In order to overcome the above defects of the prior art, the embodiments of the present application provide a remote real-time control system for industrial internet.

[0006] In order to achieve the above purpose, the present application provides the following technical scheme: A remote real-time control system for industrial internet comprises the following modules: An adaptive network delay compensation module is configured to monitor network delay through high-frequency heartbeat packets and predict delay trends using an adaptive filtering algorithm; control instructions are sent in advance according to the prediction results, and a closed-loop feedback mechanism is introduced to dynamically correct the prediction model; A multi-path redundant transmission module is configured to establish and evaluate the performance of multiple transmission paths, distribute data packets to the optimal path through dynamic calculation of transmission costs, and automatically switch paths and retransmit when transmission fails, thereby achieving load balancing and reliable transmission. An intelligent data compression and optimization module is configured to select a corresponding compression encoding mode according to the data type characteristics; a multi-objective optimization function is used to dynamically search for the best compression parameters, and a balance is achieved among compression rate, processing time and data quality; and a differentiated compression strategy is adopted for data of different priorities.

[0007] Specifically, the execution process of the adaptive network delay compensation module is as follows: First, time synchronization units are deployed at the control end and the device end respectively, high-frequency heartbeat packets are exchanged to calculate the current network delay value, and historical delay data is recorded to form a delay sequence; Second, an adaptive filtering algorithm is used to smooth the delay sequence, remove noise and jitter, and predict the delay trend in the next time period; Then, the sending time of the control instructions is adjusted according to the predicted delay, the instructions are sent in advance to offset the delay, and a dynamic buffer is set to store the instructions and release them according to the actual arrival time; A closed-loop feedback control mechanism is introduced, and the error between the predicted value and the actual measured value is used as a continuous feedback signal to correct the prediction model itself; Finally, the delay change is monitored in real time, and if the delay exceeds the threshold, an alarm is triggered and a backup control strategy is switched to.

[0008] Specifically, the closed-loop feedback control mechanism includes: Error calculation: in each control period, when the latest actual network delay measurement value is obtained through the heartbeat packet , the error between the predicted value and the actual measured value is calculated, wherein is the prediction error at the current time; Feedback control amount calculation: a digital PI, i.e., a proportional-integral controller, is used to process the error signal; the PI controller generates a model correction amount according to the current error, i.e., the proportional term, and the cumulative history of the error, i.e., the integral term; Proportional term P: provides a proportional response to the current error , aiming to immediately reduce the error; , for eliminating steady-state error; Control quantity The calculation formula is: Wherein, is the control quantity, is the cumulative sum of the error from time 0 to t, is a proportional gain, is an integral gain; Online calibration of model parameters: the calculated control quantity acts on the original adaptive filter prediction model; When the weight vector of the original adaptive filter is , the update rule can be modified as: Wherein, is the value of the weight vector of the adaptive filter at time t, is the step size of the original filter, is the input vector, is a mixing factor less than 1; Alternatively, directly modify the prediction output: Wherein is the new prediction value after feedback calibration, is the original prediction value; Monitoring and resetting: continuously monitor the absolute value or moving average value of the error When the error continuously exceeds the preset threshold for a preset time, it is judged that the network has undergone a drastic and fundamental change, at which time the prediction model is judged to be inapplicable; Automatically trigger the reset mechanism, clear the error accumulation item of the PI controller, and restore the filter weight to the default value, so that the model starts learning and adapting on a new basis.

[0009] Specifically, the execution process of the multi-path redundant transmission module is as follows: Establish multiple network connections including wired, wireless and mobile network paths between the control end and the device end, and evaluate the bandwidth, delay and packet loss rate of each path; Divide the control command into multiple data packets, and add a sequence number and a check code to each data packet, and perform dynamic data packet allocation and load balancing; Receive data packets at the device end, reassemble the command according to the sequence number, and verify the data integrity using the check code, when a certain path fails to transmit or the delay is greater than a threshold, automatically switch to other paths, and retransmit the lost data packets; Periodically optimize the path selection strategy, dynamically adjust the transmission path based on real-time network performance data, and ensure the lowest delay and the highest reliability.

[0010] Specifically, the process of performing dynamic data packet allocation and load balancing is as follows: Continuously monitor the key performance indicators of each transmission path, including: Available bandwidth Current load Current delay , denotes the first path; For each data packet to be sent, calculate the transmission cost on each path, as follows: wherein, is the dynamic load factor, used to balance the influence weight of load and delay; Select the path with the smallest transmission cost to send the current data packet; when the cost difference of multiple paths is less than a preset threshold, use a round-robin strategy to distribute data packets among these high-quality paths to avoid overloading a single path; Adjust the load factor dynamically according to the degree of network congestion : When the average delay of the network increases by more than 20% or the packet loss rate rises, automatically increase the value of λ by 0.1, so that the system pays more attention to load balancing; when the network condition meets the standard, decrease the value of λ by 0.05, so that the system pays more attention to transmission delay; Re-evaluate the cost of all paths every 100ms, and when the load of a certain path exceeds 50% of the average load of other paths, automatically redistribute some of the data packets to be sent to paths with lighter loads.

[0011] Specifically, the execution process of the intelligent data compression and optimization module is as follows: Analyze the type and characteristics of control data, and use differential encoding compression for periodic data and dictionary encoding compression for non-periodic data; Use machine learning algorithms to identify redundant patterns in data, dynamically adjust compression levels, and maximize compression ratios while ensuring data integrity; introduce a balance optimization mechanism for compression quality and efficiency; Add priority labels to compressed data before transmission, such as using low-delay compression algorithms for urgent control instructions and high-compression-ratio algorithms for historical logs; Decompress data at the receiving end and verify data consistency, and if decompression fails, request retransmission, while adaptively adjusting the compression strategy according to network conditions.

[0012] Specifically, the process of the compression quality and efficiency balance optimization mechanism is as follows: Three key performance indicators are monitored in real time: Compression rate ; Processing time (time from starting compression to completion); Data quality ; An integrated optimization objective function is constructed: Wherein: is a weight index, is the value of the integrated optimization objective function; Parameter space search and optimization: The compression parameter space is defined to include: Compression level l; Dictionary size d; Quantization step q; An annealing algorithm is used to search for the optimal solution in the parameter space: Initial temperature , cooling coefficient c=0.95; At each temperature, neighborhood search is performed, and the probability of accepting inferior solutions is Wherein is the probability of accepting inferior solutions, is the change in the objective function value, T is the current temperature in the simulated annealing algorithm; stop when the temperature drops to or the maximum number of iterations is reached; Dynamic weight adjustment mechanism: Adjust the weight index according to network conditions and application requirements: When the network bandwidth meets the standard: increase ; When the network delay exceeds the standard: increase ; Preset key control instructions: increase ; Weight adjustment formula: Wherein is the adjustment step, is the current bandwidth, is the bandwidth threshold; Continuously monitor the actual compression effect, if the compression performance decreases by more than 10%, re-trigger the optimization search, record the historical optimal parameter combination, and establish a scenario-based parameter library.

[0013] Technical effects and advantages of the present application: The adaptive network delay compensation module can dynamically predict and compensate the transmission delay caused by network fluctuation, significantly improves the real-time performance and accuracy of control instructions, and effectively overcomes the hysteresis problem of traditional fixed compensation strategy.

[0014] Through the intelligent load balancing and dynamic path switching mechanism of the multi-path redundant transmission module, the system realizes high reliability and stability of data transmission in complex network environment, and fully utilizes the aggregated bandwidth of multiple paths.

[0015] The intelligent data compression and optimization module realizes a substantial reduction of transmission load under the premise of ensuring data quality through a multi-objective optimization algorithm, so that the system can adaptively adjust the compression strategy according to the real-time network condition, and comprehensively improve the bandwidth utilization efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0016] Figure 1 The system block diagram of the present application is shown. DETAILED DESCRIPTION

[0017] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0018] As shown in Figure 1 A remote real-time control system module for industrial internet is as follows: The adaptive network delay compensation module monitors the network delay through high-frequency heartbeat packets and predicts the delay trend using an adaptive filtering algorithm. Then, it sends control instructions in advance according to the prediction results and introduces a closed-loop feedback mechanism to dynamically correct the prediction model to offset the delay impact and achieve high-precision compensation.

[0019] First, time synchronization units are deployed on the control end and the device end respectively, the current network delay value is calculated through high-frequency heartbeat packet exchange, and historical delay data is recorded to form a delay sequence. Second, an adaptive filtering algorithm is used to smooth the delay sequence, remove noise and jitter, and predict the delay trend in the next time period. Then, the sending time of the control instruction is adjusted according to the predicted delay, the instruction is sent in advance to offset the delay impact, and a dynamic buffer is set to store the instruction and release it according to the actual arrival time.

[0020] The error between the predicted value and the actual measured value is introduced as a continuous feedback signal to dynamically and slightly correct the prediction model itself, so that it can track and adapt to the dynamic changes of network delay, thereby gradually reducing the prediction bias and achieving higher accuracy compensation. The specific process is as follows: Error calculation: In each control cycle, when the system obtains the latest actual network delay measurement value through the heartbeat packet , it immediately calculates the error between it and the corresponding predicted value , where is the prediction error at the current time.

[0021] Feedback control amount calculation: The system uses a digital PI (proportional-integral) controller to process this error signal. The PI controller can generate a model correction amount according to the current error (proportional term) and the cumulative history of the error (integral term).

[0022] Proportional term (P): provides a proportional quick response to the current error , aiming to immediately reduce the error. Integral term (I): accumulates past errors to eliminate steady-state errors (i.e., long-term fixed biases). The calculation formula of the control amount is: where is the control amount (model correction amount) generated by the PI controller, is the cumulative sum of the error from time 0 to t (integral term), is the proportional gain, and the integral gain. These two parameters need to be adjusted according to the network characteristics during initialization, such as through the Ziegler-Nichols method or empirical values; Model parameter online calibration: the calculated control amount is applied to the original adaptive filter prediction model. Specifically, the control amount is used as a fine-tuning amount for the model weights or output values.

[0023] If the weight vector of the original adaptive filter (such as the LMS filter) is , then the update rule can be modified as: where is the value of the weight vector of the adaptive filter (such as the LMS filter) at time t, is the step size of the original filter, is the input vector, ​is a mixing factor less than 1, used to control the strength of the feedback control, to prevent over-correction.

[0024] Alternatively, the prediction output can be more directly corrected: where is the new prediction after feedback correction, is the original prediction (predicted by the adaptive filter algorithm).

[0025] Monitoring and Reset: The system continuously monitors the absolute value or moving average of the error . If the error consistently exceeds a high threshold (e.g., twice the normal threshold) for a certain period of time, it indicates that the network may have undergone a drastic, fundamental change (such as a primary link switch), at which point the prediction model may no longer be applicable. The system will automatically trigger a reset mechanism to clear the error accumulation term of the PI controller and possibly restore the filter weights to default values, allowing the model to start learning and adapting from a new basis.

[0026] Finally, real-time monitoring of delay changes, if the delay exceeds the threshold, triggers an alarm and switches to a backup control strategy, such as a local autonomous mode.

[0027] The multi-path redundant transmission module establishes and evaluates the performance of multiple transmission paths, intelligently distributes data packets to the optimal path by dynamically calculating the transmission cost, and automatically switches paths and retransmits when transmission fails, thereby achieving load balancing and reliable transmission.

[0028] First, establish multiple network connections at the control end and device end, including wired, wireless and mobile network paths, and evaluate the bandwidth, delay and packet loss rate of each path. Second, divide the control instructions into multiple data packets, and add sequence numbers and check codes to each data packet, then perform dynamic data packet distribution and load balancing, the process is as follows: Continuously monitor the key performance indicators of each transmission path, including: available bandwidth , current load , current delay , represents the th path; For each data packet to be sent, calculate the transmission cost on each path, the formula is as follows: where, is the dynamic load factor (range 0 to 1), used to balance the influence weight of load and delay; select the path with the smallest transmission cost to send the current data packet. If the cost difference of multiple paths is less than the preset threshold, use a round-robin strategy to distribute data packets among these high-quality paths to avoid overloading a single path; Dynamic adjustment of load factor according to network congestion level : When network congestion is detected (e.g., average delay increases by more than 20% or packet loss rate rises), automatically increase the value (e.g., λ = λ + 0.1) to make the system focus more on load balancing; when the network is in good condition, decrease the value (e.g., λ = λ - 0.05) to make the system focus more on transmission delay; Periodically (e.g., every 100ms) re-evaluate the cost of all paths, and if it is found that the load of a certain path is significantly higher than that of other paths (e.g., more than 50% of the average load), automatically reassign part of the data packets to be sent to a path with lighter load.

[0029] Then, at the device end, receive data packets, reassemble instructions according to sequence numbers, and verify data integrity using checksums. If a certain path fails to transmit or has too high a delay, automatically switch to another path and retransmit the lost data packets. Finally, periodically optimize the path selection strategy, dynamically adjust the transmission path based on real-time network performance data, and ensure the lowest delay and highest reliability.

[0030] The intelligent data compression and optimization module selects the appropriate compression encoding method according to the characteristics of the data type. Then, it dynamically searches for the best compression parameters through a multi-objective optimization function, balancing compression rate, processing time, and data quality, and adopts differentiated compression strategies for data of different priorities; First, analyze the type and characteristics of control data, and use differential encoding compression for periodic data and dictionary encoding compression for non-periodic data. Second, use machine learning algorithms to identify redundant patterns in the data, dynamically adjust the compression level, and maximize the compression ratio while ensuring data integrity; introduce a balance optimization mechanism for compression quality and efficiency, as follows: Real-time monitoring of three key performance indicators: Compression rate ; processing time (from the start of compression to completion); data quality ; construct a comprehensive optimization objective function: where: is the weight index reflecting the importance of each objective, with the default setting ; as the comprehensive optimization objective function value; Parameter space search and optimization: define the compression parameter space to include: Compression level l (1-9 levels); dictionary size d (32KB-1MB); quantization step q (1-50); ​​​Search for the optimal solution in the parameter space using the simulated annealing algorithm: initial temperature , cooling coefficient c = 0.95; neighborhood search at each temperature, accept poor solution probability , where is the probability of accepting a poor solution, is the change in the objective function value (the difference between the new solution and the current solution), T is the current temperature (in the simulated annealing algorithm); stop when the temperature drops to or the maximum number of iterations is reached; Dynamic weight adjustment mechanism: Adjust the weight index according to network conditions and application requirements: When the network bandwidth is sufficient: increase (pay attention to compression ratio); when the network delay is sensitive: increase (pay attention to processing speed); critical control instructions: increase (pay attention to data quality); Weight adjustment formula: , where is the adjustment step, is the current bandwidth, is the bandwidth threshold; continuously monitor the actual compression effect, if the compression performance decreases (O value decreases by more than 10%), retrigger the optimization search, record the historical optimal parameter combination, and establish a scenario-based parameter library.

[0031] Then, add priority labels to the compressed data before transmission, high-priority data (such as urgent control instructions) uses low-delay compression algorithm, low-priority data (such as historical logs) uses high-compression ratio algorithm. Finally, decompress the data at the receiving end and verify data consistency, if the decompression fails, request retransmission, and simultaneously adjust the compression strategy according to the network conditions.

[0032] The above formulas are dimensionless values, and specific dimensionless methods such as standardization can be used, which will not be described here. The formula is obtained by software simulation of a large amount of data to reflect the current real situation, and the preset parameters in the formula are set by the person skilled in the art according to the actual situation.

[0033] The above-described embodiments can be implemented in part or in whole through software, hardware, firmware or any combination thereof. When implemented in software, the above-described embodiments can be implemented using one or more computer programs written in any suitable programming language. Such programs can be stored in one or more storage media or memory devices (e.g., a computer readable medium) associated with the computer or other suitable devices. The memory devices can include, but are not limited to, RAM, ROM, EEPROM, flash memory or other suitable memory devices. The computer programs can be loaded and / or executed on the computer or other suitable devices to produce a computer implemented process, such that the actions specified in the computer programs are performed. The computer programs can be executed on a single computer or on multiple computers.

[0034] It should be understood that the sequence of the above processes is not intended to mean the execution order of the processes, and the execution order of the processes should be determined according to the functions and inherent logic of the processes, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0035] Those skilled in the art can understand that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0036] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. For example, the above-described device embodiments are merely illustrative, for example, the division of units is merely a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the shown or discussed units can be indirect coupling or communication connection through some interfaces, devices or units, and can be electrical, mechanical or other forms.

[0037] The units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, which may be located in one place or distributed on multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0038] In addition, the functional units in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit.

[0039] The functions, if realized in the form of software functional units and sold or used as independent products, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application or the part of the present application that essentially contributes to the prior art or the part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: a U disk, a mobile ATA hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various program code storage media.

[0040] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A remote real-time control system for the Industrial Internet, characterized in that, Includes the following modules: The adaptive network delay compensation module is used to monitor network delay through high-frequency heartbeat packets and predict delay trends using an adaptive filtering algorithm; it sends control commands in advance based on the prediction results and introduces a closed-loop feedback mechanism to dynamically correct the prediction model. The multi-path redundancy transmission module is used to establish and evaluate the performance of multiple transmission paths. By dynamically calculating the transmission cost, it allocates data packets to the optimal path and automatically switches paths and retransmits when transmission fails, thereby achieving load balancing and reliable transmission. The intelligent data compression and optimization module is used to select the appropriate compression encoding method according to the characteristics of data types. It dynamically searches for the best compression parameters through a multi-objective optimization function to achieve a balance between compression ratio, processing time and data quality, and adopts differentiated compression strategies for data with different priorities.

2. A remote real-time control system for the Industrial Internet according to claim 1, characterized in that, The execution process of the adaptive network latency compensation module is as follows: First, time synchronization units are deployed at both the control end and the device end to calculate the current network latency value through high-frequency heartbeat packet exchange and record historical latency data to form a latency sequence. Secondly, an adaptive filtering algorithm is used to smooth the delayed sequence, remove noise and jitter, and predict the delay trend of the next time period. Then, the sending time of the control command is adjusted according to the predicted delay, and the command is sent in advance to offset the effect of the delay. At the same time, a dynamic buffer is set to store the command and release it according to the actual arrival time. A closed-loop feedback control mechanism is introduced, which uses the error between the predicted value and the actual measured value as a continuous feedback signal to correct the prediction model itself. Finally, monitor latency changes in real time, and if the latency exceeds the threshold, trigger an alarm and switch to a backup control strategy.

3. A remote real-time control system for the Industrial Internet according to claim 2, characterized in that, The closed-loop feedback control mechanism includes: Error calculation: In each control cycle, when the latest actual network latency measurement is obtained via heartbeat packets... Then, calculate the corresponding predicted value. The error between them ,in, This is the prediction error at the current moment; Feedback control quantity calculation: A digital PI (proportional-integral) controller is used to process this error signal; the PI controller generates the model correction quantity based on the current error (proportional term) and the cumulative error history (integral term); Scale term P: Provides the current error A proportional response, designed to reduce errors immediately; Integral term I: Cumulative past errors , used to eliminate steady-state errors; Control quantity The calculation formula is: in, For production volume, This is the cumulative sum of errors from time 0 to t. It is proportional gain. Integral gain; Online calibration of model parameters: The calculated control inputs are then calibrated online. It applies to the existing adaptive filtering prediction model; When the weight vector of the original adaptive filter is The update rule can then be revised as follows: in, Let be the value of the weight vector of the adaptive filter at time t. It is the step size of the original filter. It is the input vector. It is a mixing factor less than 1; Alternatively, directly correct the predicted output: ,in These are the new predicted values ​​after feedback calibration. These are the original predicted values; Monitoring and Reset: Continuously monitor errors The absolute value or moving average; when the error continues to exceed the preset threshold for a preset time, it is determined that the network has undergone drastic and fundamental changes, and the prediction model is deemed inapplicable at this time; The automatic reset mechanism clears the error accumulation term of the PI controller and restores the filter weights to their default values, allowing the model to start learning and adapting anew on a new basis.

4. A remote real-time control system for the Industrial Internet according to claim 1, characterized in that, The execution process of the multi-path redundant transmission module is as follows: Establish multiple network connections at the control and device ends, including wired, wireless, and mobile network paths, and evaluate the bandwidth, latency, and packet loss rate of each path; The control commands are divided into multiple data packets, and a sequence number and checksum are added to each data packet to perform dynamic data packet allocation and load balancing. The device receives data packets, reassembles instructions according to the sequence number, and verifies data integrity using a checksum. If a transmission path fails or the delay exceeds a threshold, it automatically switches to another path and retransmits the lost data packets. Regularly optimize path selection strategies and dynamically adjust transmission paths based on real-time network performance data to ensure the lowest latency and highest reliability.

5. A remote real-time control system for the Industrial Internet according to claim 4, characterized in that, The process of performing dynamic packet allocation and load balancing is as follows: Continuously monitor key performance indicators for each transmission path, including: Available bandwidth Current load Current delay , Indicates the first Path; For each data packet to be sent, calculate the sending cost on each path. The formula is as follows: ,in, It is a dynamic load factor used to balance the weights of load and latency. Select sending cost The shortest path is used to send the current data packet; when the cost difference between multiple paths is less than a preset threshold, a round-robin strategy is used to distribute data packets among these high-quality paths to avoid overloading a single path. Dynamically adjust load factor based on network congestion level. : Automatically increase [the number of devices] when a network average latency increase of more than 20% or a packet loss rate increase is detected. A value of λ+0.1 makes the system focus more on load balancing; when network conditions meet the criteria, the value is reduced. The value is λ−0.05, which makes the system pay more attention to transmission delay; The cost of all paths is reassessed every 100ms, and the load on a particular path is detected. When the load exceeds 50% of the average load of other paths, some of the data packets to be sent will be automatically redistributed to the less loaded paths.

6. A remote real-time control system for the Industrial Internet according to claim 1, characterized in that, The execution process of the intelligent data compression and optimization module is as follows: Analyze the types and characteristics of control data, and use differential coding compression for periodic data and dictionary coding compression for non-periodic data; Machine learning algorithms are used to identify redundant patterns in the data and dynamically adjust the compression level to maximize the compression ratio while ensuring data integrity; a balance optimization mechanism between compression quality and efficiency is introduced. Priority tags are added to compressed data before transmission. For example, emergency control instructions use low-latency compression algorithms, while historical logs use high-compression-ratio algorithms. The receiving end decompresses the data and verifies its consistency. If decompression fails, it requests retransmission and adaptively adjusts the compression strategy based on network conditions.

7. A remote real-time control system for the Industrial Internet according to claim 6, characterized in that, The process of the optimization mechanism for balancing compression quality and efficiency is as follows: Real-time monitoring of three key performance indicators: Compression ratio ; Processing time (Time from start to finish of compression); Data quality ; Construct a comprehensive optimization objective function: ,in: It is a weighted index. To comprehensively optimize the objective function value; Parameter space search and optimization: The compression parameter space is defined as follows: Compression level l; Dictionary size d; Quantization step size q; The optimal solution is searched in the parameter space using the simulated annealing algorithm: initial temperature The cooling coefficient c = 0.95; Perform a neighborhood search at each temperature and accept the probability of a suboptimal solution. ,in The probability of accepting an inferior solution, The change in the objective function value is represented by T, where T is the current temperature in the simulated annealing algorithm; when the temperature drops to... Or stop when the maximum number of iterations is reached; Dynamic weight adjustment mechanism: Adjust the weighting index according to network conditions and application requirements: When network bandwidth meets the requirements: increase ; When network latency exceeds the limit: increase ; Preset key control commands: Add ; Weighting adjustment formula: ,in To adjust the step size, This is the current bandwidth. This is the bandwidth threshold; Continuously monitor the actual compression effect. If the compression performance drops by more than 10%, re-trigger the optimization search, record the historical best parameter combination, and establish a scenario-based parameter library.

Images