A ship network multi-channel intelligent communication method and system

Abstract

The present invention relates to the technical field of data transmission, and specifically to a method and system for multi-channel intelligent communication in a ship network, comprising: obtaining historical transmission data and data packets to be transmitted, obtaining a propagation delay sequence from the propagation delay data in the historical transmission data and obtaining an initial order, obtaining a predicted impact factor of any channel according to the historical transmission data, obtaining an order factor according to the propagation delay sequence and the initial order, and then obtaining a predicted transmission delay of any channel; obtaining a final predicted delay of any channel according to the predicted impact factor and the predicted transmission delay, and switching the transmission channel of the data packet to be transmitted according to the final predicted delay and the predicted impact factor. When transmitting a data packet, the present invention predicts the propagation delay of the data packet based on the existing data of the channel, automatically selects the best channel, and improves the transmission efficiency of the communication from the ship while realizing intelligent communication of the ship network.

Description

Technical Field

[0001] The present invention relates to the technical field of data transmission, and in particular to a multi-channel intelligent communication method and system for a ship network. Background Art

[0002] Water transportation has the advantages of large volume, low price, and green environmental protection. It is the most important mode of transportation in international logistics. Ships are important means of transportation for water transportation. Communication technology is indispensable in transoceanic navigation. While ensuring the safety alarm of distress, it enriches the ability of ship-shore information exchange. With the rapid development of navigation technology, smart ships integrate new technologies such as modern information technology and artificial intelligence. They have significant characteristics such as safety, reliability, energy saving, environmental protection, and economic efficiency. They are the key direction of future ship development. Compared with traditional ships, the intelligence of smart ships is mainly reflected in the intelligent navigation function based on autonomous situation perception, risk identification and intelligent decision-making. It relies to a large extent on ship-shore collaboration, that is, it requires efficient, reliable and stable ship-shore communication support. Smart navigation requires a large amount of ship-shore communication, which puts higher requirements on the robustness, reliability and intelligence of the communication network.

[0003] At present, ship communications mainly focus on distress communications to ensure safe navigation of ships and transmission of some commercial operations. Ships are equipped with different communication equipment according to the navigation area, such as satellite communication equipment, ground communication equipment, etc. Various communication equipment has unique characteristics, such as high transmission rate and wide coverage. However, each communication system operates independently and requires manual link switching according to actual needs. This communication mode limits the rate of ship-shore intelligent communication. Summary of the invention

[0004] In order to solve the above problems, the present invention provides a ship network multi-channel intelligent communication method and system.

[0005] A multi-channel intelligent communication method for a ship network of the present invention adopts the following technical solution:

[0006] An embodiment of the present invention provides a multi-channel intelligent communication method for a ship network, the method comprising the following steps:

[0007] Acquire historical transmission data and data packets to be transmitted of each channel in the ship multi-channel system, wherein the historical transmission data includes: a number of propagation delay data of historical data packets, channel load rate, channel signal-to-noise, channel bit error rate data, and channel bandwidth;

[0008] For the historical transmission data of any channel, the propagation delay data in the historical transmission data are arranged to obtain a propagation delay sequence, and the initial order of the propagation delay sequence is obtained. The predicted impact factor of any channel is obtained according to the channel load rate, the channel signal-to-noise ratio and the channel bit error rate in the historical transmission data. The predicted impact factor is used to describe the stability of channel transmission;

[0009] The initial order is recorded as q, and the window determined by the first q propagation delay data of the propagation delay sequence is obtained in time sequence, recorded as the initial window, and the initial window is slid to the right once in the propagation delay sequence with a sliding step of 1 to obtain a second initial window; an initial order factor is obtained according to the difference of the propagation delay data in the initial window and the propagation delay data in the second initial window, and the initial order is adjusted according to the initial order factor to obtain the second order;

[0010] The length of the second initial window is updated to the second order to obtain the second window, and the second window is slid to the right once in the propagation delay sequence with a sliding step of 1 to obtain the third initial window; the second order factor is obtained according to the propagation delay data in the third initial window, and the second order is adjusted according to the second order factor to obtain the third order;

[0011] The length of the third initial window is updated to the third order to obtain the third window; and so on, until the window slides in the propagation delay sequence, and the order finally obtained when the sliding is completed is recorded as the final order, and the predicted transmission delay of any channel is obtained by using the final order and the MA algorithm;

[0012] The final predicted delay of any channel is obtained according to the predicted impact factor and the predicted transmission delay, and the transmission channel of the data packet to be transmitted is switched according to the final predicted delay of any channel and the predicted impact factor.

[0013] Furthermore, the propagation delay sequence obtained by arranging the propagation delay data in the historical transmission data and obtaining the initial order of the propagation delay sequence includes the following specific steps:

[0014] The propagation delay data in the historical transmission data are arranged in time sequence to obtain a propagation delay sequence, an autocorrelation function of the propagation delay sequence is obtained, and the truncation of the autocorrelation function of the propagation delay sequence is used as the initial order of the propagation delay sequence.

[0015] Furthermore, the step of obtaining the predicted impact factor of any channel according to the channel load rate, the channel signal-to-noise ratio and the channel bit error rate in the historical transmission data includes the following specific steps:

[0016] ;

[0017] For any channel, is the number of transfer nodes under the channel, and the channel between every two transfer nodes is regarded as the sub-channel of the channel. is the load rate of the nth subchannel of the channel, is the signal-to-noise ratio of the nth subchannel of the channel, is the bit error rate of the nth subchannel of the channel, is the predicted impact factor of the channel.

[0018] Furthermore, the initial order factor is obtained according to the difference of the propagation delay data in the initial window and the propagation delay data in the second initial window, and the specific steps include the following:

[0019] Get the mean of q propagation delay data in the initial window, recorded as MAs;

[0020] ;

[0021] For q propagation delay data in the initial window, where: is the i-th propagation delay data among the q propagation delay data, To take the absolute value, To obtain the maximum value, To obtain the minimum value, is the propagation delay data with the largest difference from MAs among the q propagation delay data, is the propagation delay data with the smallest difference from MAs among the q propagation delay data, Represents the difference in propagation delay data within the initial window;

[0022] Construct an empty deviation sequence, Add to the deviation sequence to construct an empty approach sequence. Add to the approach sequence;

[0023] According to the propagation delay data in the second initial window, the offset value obtained by making the next MA prediction based on the initial order and the approximate value obtained by making the next MA prediction based on the initial order are obtained, and the initial order factor is obtained according to the offset value, approximate value, deviation sequence and approximate sequence.

[0024] Furthermore, the specific method for obtaining the offset value is as follows:

[0025] The mean of the q propagation delay data in the second initial window is recorded as MA1. ,in, is the jth propagation delay data among the q propagation delay data in the second initial window, The offset value obtained by making the next MA prediction based on the initial order.

[0026] Furthermore, the specific method for obtaining the approximate value is as follows:

[0027] The mean of the q propagation delay data in the second initial window is recorded as MA1. ,in, is the jth propagation delay data among the q propagation delay data in the second initial window, It is the approximate value obtained by making the next MA prediction based on the initial order.

[0028] Furthermore, the initial order factor is obtained according to the offset value, the approximate value, the deviation sequence and the approximate sequence, and the specific steps include the following:

[0029] ;

[0030] In the formula, is the mean of the propagation delay data in the deviation sequence, is the offset value obtained by making the next MA prediction based on the initial order, To be close to the mean of the propagation delay data in the sequence, is the approximate value obtained by making the next MA prediction based on the initial order, is the initial order factor.

[0031] Furthermore, the step of adjusting the initial order according to the initial order factor to obtain the second order includes the following specific steps:

[0032] ;

[0033] In the formula, is the initial order factor, is the initial order, is the second order, To round up, To round down.

[0034] Further, the method of obtaining the final predicted delay of any channel according to the predicted impact factor and the predicted transmission delay, and switching the transmission channel of the data packet to be transmitted according to the final predicted delay and the predicted impact factor of any channel, comprises the following specific steps:

[0035] ;

[0036] For any channel, is the predicted transmission delay of the channel, is the predicted impact factor of the channel, is the channel bandwidth of the channel, is the size of the data packet to be transmitted, is an exponential function with a natural constant as base, is the final predicted delay of the channel;

[0037] The final predicted delay and the predicted impact factor of each channel are obtained. If the data packet to be transmitted needs to be transmitted in real time, the channel corresponding to the minimum value of the final predicted delay is used as the transmission channel for the data packet to be transmitted. If the data packet to be transmitted needs to be transmitted stably, the channel corresponding to the maximum value of the predicted impact factor is used as the transmission channel for the data packet to be transmitted.

[0038] The present invention also proposes a ship network multi-channel intelligent communication system, comprising a memory and a processor, wherein the processor executes a computer program stored in the memory to implement the steps of the aforementioned method.

[0039] The beneficial effect of the technical solution of the present invention is that when transmitting data packets, the present invention does not use traditional manual link switching, but predicts the transmission delay of the data packet based on the historical transmission data of each channel, arranges the propagation delay data in the historical transmission data to obtain a propagation delay sequence and obtains the initial order, obtains the predicted impact factor of any channel according to the channel load rate, channel signal-to-noise ratio and channel bit error rate in the historical transmission data, and the predicted impact factor represents the stability of channel transmission, obtains the order factor according to the difference of propagation delay data in the propagation delay sequence and the initial order, continuously adjusts the order through the order factor, and then obtains the predicted transmission delay of the channel, considers the different requirements of the data packets to be transmitted, and intelligently switches to select the appropriate channel for transmission, thereby improving the multi-channel intelligent communication of the ship network, and while realizing the intelligent communication of the ship network, enhances the timeliness of information dissemination and improves the transmission efficiency of the communication from the ship. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0041] Figure 1 A flowchart of the steps of a multi-channel intelligent communication method for a ship network provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0042] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the ship network multi-channel intelligent communication method and system proposed by the present invention, its specific implementation method, structure, features and effects, in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0043] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0044] The specific scheme of the multi-channel intelligent communication method for a ship network provided by the present invention is described in detail below with reference to the accompanying drawings.

[0045] See also Figure 1 , which shows a flow chart of the steps of a multi-channel intelligent communication method for a ship network provided by an embodiment of the present invention, the method comprising the following steps:

[0046] Step S001: Obtain historical transmission data, data packets to be transmitted, and data packet sizes of each channel.

[0047] It should be noted that this embodiment mainly uses the past communication data of the channel to predict the channel propagation delay, so it is necessary to collect the required data first.

[0048] Specifically, the historical transmission data of each channel in the ship's multi-channel system is obtained. The duration of the historical transmission data obtained in this embodiment is 1.5 hours, wherein the historical transmission data includes: several propagation delay data of historical data packets, channel load rate, channel signal-to-noise ratio, channel bit error rate and other related data, as well as the inherent properties of the channel itself, such as channel bandwidth, etc., to obtain the data packet to be transmitted and the size of the data packet.

[0049] It should be noted that each channel contains several switching nodes. The channel between every two switching nodes can be regarded as a sub-channel of the channel. The load rate of the channel includes the load rate of the sub-channel. The signal-to-noise ratio of the channel includes the signal-to-noise ratio of the sub-channel. The signal-to-noise ratio can be obtained through the detector of the switching node. The bit error rate of the channel includes the bit error rate of the sub-channel.

[0050] At this point, the historical transmission data and the data packets to be transmitted are obtained.

[0051] Step S002: for the historical transmission data of any channel, arrange the propagation delay data in the historical transmission data to obtain a propagation delay sequence, obtain the initial order of the propagation delay sequence, and obtain the predicted impact factor of any channel according to the channel load rate, channel signal-to-noise ratio and channel bit error rate in the historical transmission data.

[0052] It should be noted that, since there are multiple communication channels in the ship multi-channel system, this embodiment evaluates the current communication status on all channels and selects the optimal channel. Therefore, the specific implementation case of the subsequent steps is a specific evaluation prediction of any communication channel.

[0053] Specifically, for the historical transmission data of any channel, the propagation delay data in the historical transmission data is arranged to obtain a propagation delay sequence, and the initial order of the propagation delay sequence is obtained, which is specifically as follows:

[0054] The propagation delay data in the historical transmission data are arranged in chronological order to obtain a propagation delay sequence, the autocorrelation function of the propagation delay sequence is obtained, and the truncation of the autocorrelation function of the propagation delay sequence is used as the initial order of the propagation delay sequence; the initial order is the initial order when the propagation delay sequence is moved averaged; and the moving average is a step in the MA algorithm.

[0055] It should be noted that obtaining the autocorrelation function of the propagation delay sequence is an existing method, which will not be described in detail in this embodiment.

[0056] It should be noted that, because the channel load, propagation path and other state factors at different times may cause the signal quality to decline, thereby affecting the propagation of the signal, it is necessary to obtain the predicted impact factor based on the basic information of the channel at this moment.

[0057] Specifically, the predicted impact factor of any channel is obtained according to the channel load rate, channel signal-to-noise ratio and channel bit error rate in the historical transmission data, where the predicted impact factor represents the stability of channel transmission, as follows:

[0058] ;

[0059] For any channel, is the number of transfer nodes under the channel, and the channel between every two transfer nodes is regarded as the sub-channel of the channel. is the load rate of the nth subchannel of the channel, is the signal-to-noise ratio of the nth subchannel of the channel, is the bit error rate of the nth subchannel of the channel, is the predicted impact factor of the channel, which reflects the stability of the channel. The larger the value, the higher the channel quality, the better the stability, and the faster the data transmission.

[0060] It should be noted that The larger the value of is, the higher the load rate of the nth subchannel is, the lower the transmission efficiency is, and the more serious the impact on the propagation delay of the data packet to be transmitted is. The larger the value, the higher the quality of the nth subchannel, and the faster the transmission. The larger the value of , the higher the bit error rate of the nth sub-channel, the lower the transmission quality of the sub-channel, and the lower the transmission efficiency.

[0061] At this point, the predicted impact factor of any channel is obtained.

[0062] Step S003, obtain an initial window with a length of the initial order in the propagation delay sequence, obtain a deviation sequence and a close sequence according to the difference of the propagation delay data in the initial window, obtain an offset value obtained by performing next MA prediction based on the initial order and a close value obtained by performing next MA prediction based on the initial order according to the propagation delay data in the second initial window, obtain an initial order factor according to the offset value, the close value, the deviation sequence and the close sequence, adjust the initial order according to the initial order factor to obtain a second order, repeat the calculation to obtain a final order, and obtain the predicted transmission delay of any channel according to the final order.

[0063] It should be noted that after the initial order is obtained, the channel delay needs to be predicted using the improved MA algorithm and the propagation delay sequence.

[0064] (1) Specifically, an initial window with a length equal to the initial order is obtained in the propagation delay sequence, and a deviation sequence and a close sequence are obtained according to the difference of the propagation delay data in the initial window, as follows:

[0065] The initial order is recorded as q, and the window determined by the first q propagation delay data of the propagation delay sequence is obtained in time sequence, which is recorded as the initial window. The mean of the q propagation delay data in the initial window is obtained, which is recorded as MAs.

[0066] ;

[0067] For q propagation delay data in the initial window, where: is the i-th propagation delay data among the q propagation delay data, To take the absolute value, To obtain the maximum value, To obtain the minimum value, is the propagation delay data with the largest difference from MAs among the q propagation delay data, is the propagation delay data with the smallest difference from MAs among the q propagation delay data, Indicates the difference in propagation delay data within the initial window.

[0068] Construct an empty deviation sequence, Add to the deviation sequence to construct an empty approach sequence. Add to the approach sequence.

[0069] It should be noted that the values ​​in the deviation sequence are the propagation delay data farthest from the moving average after each moving average, that is, after the above processing. The deviation sequence will not be deleted, but new propagation delay data will be added until the prediction of the entire propagation delay sequence is completed or the order changes; similarly, the values ​​in the close sequence are the propagation delay data closest to the moving average after each moving average. The close sequence will not be deleted, but new propagation delay data will be added until the prediction of the entire propagation delay sequence is completed or the order changes.

[0070] It should be noted that the above moving average calculation obtains the deviation sequence and the close sequence, and the moving average calculation is continued, and the next step of the moving average order is obtained by combining the deviation sequence and the close sequence.

[0071] Specifically, the initial window is slid rightward once in the propagation delay sequence with a sliding step of 1 to obtain a second initial window; according to the propagation delay data in the second initial window, an offset value obtained by performing the next MA prediction based on the initial order and a close value obtained by performing the next MA prediction based on the initial order are obtained, as follows:

[0072] The mean of the q propagation delay data in the second initial window is recorded as MA1. ,in, is the jth propagation delay data among the q propagation delay data in the second initial window, To take the absolute value, To obtain the maximum value, The offset value obtained by making the next MA prediction based on the initial order.

[0073] , To obtain the minimum value, It is the approximate value obtained by making the next MA prediction based on the initial order.

[0074] The initial order factor is obtained according to the offset value, the approach value, the deviation sequence and the approach sequence, as follows:

[0075] ;

[0076] In the formula, is the mean of the propagation delay data in the deviation sequence, is the offset value obtained by making the next MA prediction based on the initial order, To be close to the mean of the propagation delay data in the sequence, is the approximate value obtained by making the next MA prediction based on the initial order, is the initial order factor.

[0077] Furthermore, the initial order is adjusted according to the initial order factor to obtain the second order, as follows:

[0078] ;

[0079] In the formula, is the initial order factor, is the initial order, is the second order, To round up, To round down.

[0080] It should be noted that the deviation sequence and the approach sequence are used to evaluate the fluctuation of the subsequent propagation delay data. If a large change occurs, the order will change, making the subsequent prediction more appropriate.

[0081] (2) Further, the length of the second initial window is updated to the second order to obtain a second window, and the first deviation sequence and the first approach sequence are obtained according to the difference of the propagation delay data in the second window, as follows:

[0082] The second order is recorded as q1, and the mean of q1 propagation delay data in the second window is obtained, which is recorded as MAs1.

[0083] ;

[0084] For q1 propagation delay data in the second window, where: is the i-th propagation delay data among the q1 propagation delay data, To take the absolute value, To obtain the maximum value, To obtain the minimum value, is the propagation delay data with the largest difference from Mas1 among the q1 propagation delay data, is the propagation delay data with the smallest difference from Mas1 among the q1 propagation delay data, Represents the difference in propagation delay data within the second window.

[0085] Will Add to the deviation sequence to get the first deviation sequence, Add to the close sequence to obtain the first close sequence.

[0086] It should be noted that there are two deviation values ​​in the first deviation sequence, namely two propagation delay data, and the first approach sequence also contains two values. If the order changes, it means that the existing deviation sequence and approach sequence cannot accurately predict the subsequent changes. Therefore, it is necessary to clear the values ​​in the deviation sequence and approach sequence and store the average of all previous values ​​as the initial value in the sequence.

[0087] Further, the second window is slid rightward once in the propagation delay sequence with a sliding step of 1 to obtain a third initial window; according to the propagation delay data in the third initial window, a first offset value obtained by performing the next MA prediction based on the second order and a first approximation value obtained by performing the next MA prediction based on the second order are obtained, as follows:

[0088] The mean of the q propagation delay data in the third initial window is recorded as MA2. , where is the kth propagation delay data among the q propagation delay data in the third initial window, To take the absolute value, To obtain the maximum value, The first offset value is obtained by performing the next MA prediction according to the second order.

[0089] , To obtain the minimum value, It is the first approximation obtained by making the next MA prediction based on the second order.

[0090] Furthermore, a second order factor is obtained according to the first offset value, the first approximate value, the first deviation sequence and the first approximate sequence, the second order is adjusted according to the second order factor to obtain a third order, and the length of the third initial window is updated to the third order to obtain a third window.

[0091] The analogy between (1) and (2) is repeated until the window slides through the propagation delay sequence. The order obtained when the sliding is completed is recorded as the final order. The final order and the MA algorithm are used to obtain the predicted transmission delay of any channel.

[0092] It should be noted that the second order factor is obtained according to the first offset value, the first approximate value, the first deviation sequence and the first approximate sequence, and the second order is adjusted according to the second order factor to obtain the third order. The specific acquisition method is the same as the method for obtaining the second order, and this embodiment will not be elaborated on; the use of the final order and the MA algorithm to obtain the predicted transmission delay of any channel is an existing method of the MA algorithm, and this embodiment will not be elaborated on. When obtaining the predicted transmission delay of any channel, the order of the MA algorithm must be calculated each time to obtain a new order. Compared with the fixed order of the original algorithm, this embodiment performs adaptive adjustment according to the propagation delay data in the propagation delay sequence to make the prediction result better.

[0093] Step S004: obtaining a final predicted delay of any channel according to the predicted impact factor and the predicted transmission delay, and switching a transmission channel of the data packet to be transmitted according to the final predicted delay of any channel and the predicted impact factor.

[0094] It should be noted that the predicted transmission delay of any channel is obtained above. Since the present embodiment is analyzed by taking any channel as an example, the predicted transmission delay of any channel is also obtained by analyzing based on any channel as an example. The predicted influence factor of any channel is obtained above. The predicted influence factor reflects the stability of channel transmission. Therefore, the predicted influence factor is used as the weight of the predicted transmission delay of any channel, thereby obtaining the weighted predicted transmission delay.

[0095] Specifically, the final predicted delay of any channel is obtained according to the predicted impact factor and the predicted transmission delay, as follows:

[0096] ;

[0097] For any channel, is the predicted transmission delay of the channel, is the predicted impact factor of the channel, is the channel bandwidth of the channel, is the size of the data packet to be transmitted, is an exponential function with a natural constant as the base. The model is used for normalization processing, where U is the input value of the model. The implementer can set the normalization function according to the specific implementation situation. is the final predicted delay of the channel.

[0098] Furthermore, the transmission channel of the data packet to be transmitted is switched according to the final predicted delay and predicted impact factor of any channel, as follows:

[0099] The final predicted delay and predicted impact factor of each channel are obtained. If the data packet to be transmitted needs to be transmitted in real time, such as voice call data, the channel corresponding to the minimum final predicted delay is used as the transmission channel for the data packet to be transmitted. If the data packet to be transmitted needs to be transmitted stably, the channel corresponding to the maximum predicted impact factor is used as the transmission channel for the data packet to be transmitted. If special circumstances such as channel damage occur, the best channel among the remaining channels except the damaged channel is selected for transmission. By considering the different requirements of the data packet to be transmitted, intelligent switching selects the appropriate channel for transmission, thereby improving the intelligent communication of multi-channel ship network.

[0100] Through the above steps, a multi-channel intelligent communication method for ship network is completed.

[0101] Another embodiment of the present invention provides a ship network multi-channel intelligent communication system, the system comprising a memory and a processor, and when the processor executes a computer program stored in the memory, the processor performs the following operations:

[0102] The historical transmission data and data packets to be transmitted of each channel in the ship multi-channel system are obtained, wherein the historical transmission data include: a plurality of propagation delay data of the historical data packets, the load rate of the channel, the signal-to-noise ratio of the channel, the bit error rate data of the channel and the channel bandwidth; for the historical transmission data of any channel, the propagation delay data in the historical transmission data are arranged to obtain a propagation delay sequence, and the initial order of the propagation delay sequence is obtained, and the predicted impact factor of any channel is obtained according to the load rate of the channel, the signal-to-noise ratio of the channel and the bit error rate of the channel in the historical transmission data, and the predicted impact factor is used to describe the stability of channel transmission; the initial order is recorded as q, and the window determined by the first q propagation delay data of the propagation delay sequence is obtained in a time sequence order, recorded as the initial window, and the initial window is slid to the right once in the propagation delay sequence, with a sliding step of 1, to obtain a second initial window; according to the difference of the propagation delay data in the initial window and the second initial window, the predicted impact factor is obtained. The initial order factor is obtained from the propagation delay data in the window, and the initial order is adjusted according to the initial order factor to obtain the second order; the length of the second initial window is updated to the second order to obtain the second window, and the second window is slid right once in the propagation delay sequence with a sliding step of 1 to obtain the third initial window; the second order factor is obtained according to the propagation delay data in the third initial window, and the second order is adjusted according to the second order factor to obtain the third order; the length of the third initial window is updated to the third order to obtain the third window; and so on, until the window slides in the propagation delay sequence, the order finally obtained when the sliding is completed is recorded as the final order, and the predicted transmission delay of any channel is obtained using the final order and the MA algorithm; the final predicted delay of any channel is obtained according to the predicted influence factor and the predicted transmission delay, and the transmission channel of the data packet to be transmitted is switched according to the final predicted delay and the predicted influence factor of any channel.

[0103] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A multi-channel intelligent communication method for a ship network, characterized in that: The method comprises the following steps: Acquire historical transmission data and data packets to be transmitted of each channel in the ship multi-channel system, wherein the historical transmission data includes: a number of propagation delay data of historical data packets, a load rate of the channel, a signal-to-noise ratio of the channel, a bit error rate data of the channel, and a channel bandwidth; For the historical transmission data of any channel, the propagation delay data in the historical transmission data are arranged to obtain a propagation delay sequence, and the initial order of the propagation delay sequence is obtained. The predicted impact factor of any channel is obtained according to the channel load rate, the channel signal-to-noise ratio and the channel bit error rate in the historical transmission data. The predicted impact factor is used to describe the stability of channel transmission; The initial order is recorded as q, and the window determined by the first q propagation delay data of the propagation delay sequence is obtained in time sequence, recorded as the initial window, and the initial window is slid to the right once in the propagation delay sequence with a sliding step of 1 to obtain a second initial window; an initial order factor is obtained according to the difference of the propagation delay data in the initial window and the propagation delay data in the second initial window, and the initial order is adjusted according to the initial order factor to obtain the second order; The length of the second initial window is updated to the second order to obtain the second window, and the second window is slid to the right once in the propagation delay sequence with a sliding step of 1 to obtain the third initial window; the second order factor is obtained according to the propagation delay data in the third initial window, and the second order is adjusted according to the second order factor to obtain the third order; The length of the third initial window is updated to the third order to obtain the third window; and so on, until the window slides in the propagation delay sequence, and the order finally obtained when the sliding is completed is recorded as the final order, and the predicted transmission delay of any channel is obtained by using the final order and the MA algorithm; Obtaining a final predicted delay of any channel according to the predicted impact factor and the predicted transmission delay, and switching a transmission channel of a data packet to be transmitted according to the final predicted delay and the predicted impact factor of any channel; The step of obtaining the initial order factor according to the difference of the propagation delay data in the initial window and the propagation delay data in the second initial window includes the following specific steps: Get the mean of q propagation delay data in the initial window, recorded as MAs; ； For q propagation delay data in the initial window, where: is the i-th propagation delay data among the q propagation delay data, To take the absolute value, To obtain the maximum value, To obtain the minimum value, is the propagation delay data with the largest difference from MAs among the q propagation delay data, is the propagation delay data with the smallest difference from MAs among the q propagation delay data, Represents the difference in propagation delay data within the initial window; Construct an empty deviation sequence, Add to the deviation sequence to construct an empty approach sequence. Add to the approach sequence; According to the propagation delay data in the second initial window, the offset value obtained by making the next MA prediction based on the initial order and the approximate value obtained by making the next MA prediction based on the initial order are obtained, and the initial order factor is obtained according to the offset value, approximate value, deviation sequence and approximate sequence.

2. According to claim 1, a ship network multi-channel intelligent communication method is characterized in that: The propagation delay sequence obtained by arranging the propagation delay data in the historical transmission data and obtaining the initial order of the propagation delay sequence includes the following specific steps: The propagation delay data in the historical transmission data are arranged in time sequence to obtain a propagation delay sequence, an autocorrelation function of the propagation delay sequence is obtained, and the truncation of the autocorrelation function of the propagation delay sequence is used as the initial order of the propagation delay sequence.

3. According to claim 1, a ship network multi-channel intelligent communication method is characterized in that: The specific steps of obtaining the predicted impact factor of any channel according to the channel load rate, channel signal-to-noise ratio and channel bit error rate in the historical transmission data are as follows: ； For any channel, is the number of transfer nodes under the channel, and the channel between every two transfer nodes is regarded as the sub-channel of the channel. is the load rate of the nth subchannel of the channel, is the signal-to-noise ratio of the nth subchannel of the channel, is the bit error rate of the nth subchannel of the channel, is the predicted impact factor of the channel.

4. According to claim 1, a ship network multi-channel intelligent communication method is characterized in that: The specific method for obtaining the offset value is as follows: The mean of the propagation delay data in the second initial window is recorded as MA1. ,in, is the jth propagation delay data among the q propagation delay data in the second initial window, The offset value obtained by making the next MA prediction based on the initial order.

5. According to claim 1, a ship network multi-channel intelligent communication method is characterized in that: The specific method for obtaining the approximate value is as follows: The mean of the q propagation delay data in the second initial window is recorded as MA1. ,in, is the jth propagation delay data among the q propagation delay data in the second initial window, It is the approximate value obtained by making the next MA prediction based on the initial order.

6. According to claim 1, a ship network multi-channel intelligent communication method is characterized in that: The initial order factor is obtained according to the offset value, the approximate value, the deviation sequence and the approximate sequence, and the specific steps include the following: ； In the formula, is the mean of the propagation delay data in the deviation sequence, is the offset value obtained by making the next MA prediction based on the initial order, To be close to the mean of the propagation delay data in the sequence, is the approximate value obtained by making the next MA prediction based on the initial order, is the initial order factor.

7. A ship network multi-channel intelligent communication method according to claim 1, characterized in that: The step of adjusting the initial order according to the initial order factor to obtain the second order includes the following specific steps: ； In the formula, is the initial order factor, is the initial order, is the second order, To round up, To round down.

8. According to claim 1, a ship network multi-channel intelligent communication method is characterized in that: The method of obtaining a final predicted delay of any channel according to the predicted impact factor and the predicted transmission delay, and switching the transmission channel of the data packet to be transmitted according to the final predicted delay and the predicted impact factor of any channel, comprises the following specific steps: ； For any channel, is the predicted transmission delay of the channel, is the predicted impact factor of the channel, is the channel bandwidth of the channel, is the size of the data packet to be transmitted, is an exponential function with a natural constant as base, is the final predicted delay of the channel; The final predicted delay and the predicted impact factor of each channel are obtained. If the data packet to be transmitted needs to be transmitted in real time, the channel corresponding to the minimum value of the final predicted delay is used as the transmission channel for the data packet to be transmitted. If the data packet to be transmitted needs to be transmitted stably, the channel corresponding to the maximum value of the predicted impact factor is used as the transmission channel for the data packet to be transmitted.

9. A ship network multi-channel intelligent communication system, the system comprising a memory and a processor, characterized in that: The processor executes the computer program stored in the memory to implement the steps of a ship network multi-channel intelligent communication method as described in any one of claims 1-8.

Images