Ionized layer parameter prediction method and device based on sequence determination strategy

Abstract

The invention discloses an ionosphere parameter prediction method and device based on a sequence determination strategy, and relates to the technical field of ionosphere parameter prediction, and the method comprises the steps: obtaining ionosphere sequence data, and carrying out the signal decomposition processing, and obtaining a sub-signal set; determining a non-error component sub-sequence and an error component sub-sequence based on the sub-signal set; performing determination processing on the non-error component sub-sequence to obtain a first prediction result; performing neural network processing on the error component sub-sequence to obtain a second prediction result; and respectively adding the first prediction result and the second prediction result to obtain a sequence prediction result. The problem of extra operation complexity brought by a signal decomposition algorithm in a traditional method is solved, the operation complexity of the model is reduced on the basis of accurately predicting the ionosphere sequence, and powerful support is provided for short-wave communication frequency selection.

Description

Technical Field

[0001] The present application relates to the field of shortwave communication technology, and more specifically, to an ionospheric parameter prediction method and device based on a sequence determination strategy. Background Art

[0002] Shortwave communication mainly relies on the reflection of shortwave signals in the ionosphere to achieve long-distance communication without relays. Shortwave communication has the characteristics of simple network establishment and strong survivability. Shortwave communication can complete communication in the absence of communication infrastructure and has a wide range of application scenarios. Therefore, shortwave communication is widely used in military communications, civil aviation, shipping, meteorology, emergency rescue and other fields.

[0003] However, shortwave communication also has some shortcomings, which are reflected in the difficulty of frequency selection, small communication capacity, congestion caused by a large number of users, and narrow available frequency bands. These characteristics directly restrict the effectiveness of shortwave communication. The ionosphere is affected by many factors such as solar and geomagnetic activities, and its change law often presents a nonlinear change law that is difficult to characterize. In order to make more accurate predictions, a prediction method with stronger fitting ability is needed. The current prediction method increases the computational complexity of the model by superimposing the deep learning method, and the computing power of the current shortwave communication center operation node is limited. The current shortwave communication ionosphere prediction method combining deep learning and decomposition has the following shortcomings:

[0004] 1. The decomposition method has certain errors. The current signal decomposition method cannot fully extract the effective information in the ionospheric parameter sequence, resulting in the problem of reduced prediction accuracy of deep learning combined with decomposition method.

[0005] 2. The processing method is highly complex. The current deep learning combined with the signal decomposition method brings additional deep learning processing, which brings higher computing requirements to the shortwave communication center computing nodes, while the current computing power of the shortwave communication center computing nodes is limited. Summary of the invention

[0006] In response to at least one defect or improvement need in the prior art, the present invention provides an ionospheric parameter prediction method and device based on a sequence deterministic strategy, which solves the problem of additional computational complexity brought about by the signal decomposition algorithm in the traditional method. Deterministic processing is performed on the basis of completing the decomposed sub-signals, and the sub-signals with lower complexity generated in the decomposition process are replaced by neural network processing through a simple deterministic processing method, and only the error components with higher complexity are processed by a neural network processing method to obtain a prediction result with higher accuracy. The present invention can reduce the computational complexity of the model on the basis of accurately predicting the ionospheric sequence, and provide support for shortwave communication frequency selection.

[0007] To achieve the above object, according to a first aspect of the present invention, a method for predicting ionospheric parameters based on a sequence determination strategy is provided, comprising:

[0008] Acquire ionospheric sequence data to perform signal decomposition processing to obtain a sub-signal set;

[0009] Based on the sub-signal set, determining a non-error component sub-sequence and an error component sub-sequence;

[0010] Performing deterministic processing on the non-error component subsequence to obtain a first prediction result; performing neural network processing on the error component subsequence to obtain a second prediction result;

[0011] The first prediction result and the second prediction result are added together to obtain a sequence prediction result.

[0012] As described in the ionospheric parameter prediction method based on the sequence determination strategy, the ionospheric sequence data is obtained for signal decomposition processing to obtain a sub-signal set, including:

[0013] Acquire ionospheric sequence data;

[0014] The White Whale optimization algorithm is used to optimize the variational mode decomposition parameters to obtain the target variational mode decomposition model;

[0015] The ionospheric sequence data is input into the target variational mode decomposition model, and a sub-signal set is output.

[0016] As described in the ionospheric parameter prediction method based on the sequence deterministic strategy, the variational mode decomposition parameters include a penalty factor and a decomposition mode quantity parameter.

[0017] As described in the ionospheric parameter prediction method based on the sequence determination strategy, the non-error component subsequence and the error component subsequence are determined based on the sub-signal set, including:

[0018] Perform oscillation frequency detection based on the sub-signal set to obtain an error component sub-sequence, wherein the error component sub-sequence is the sub-signal with the highest oscillation frequency;

[0019] Based on the ionospheric sequence data, the sub-signal set and the error component sub-sequence, a non-error component sub-sequence is determined.

[0020] According to the ionospheric parameter prediction method based on the sequence determination strategy, the non-error component subsequence is determined based on the ionospheric sequence data, the sub-signal set and the error component subsequence, including:

[0021] Acquire a difference component between the ionospheric sequence data and the sub-signal set to obtain an information loss component;

[0022] Obtaining a difference component between the sub-signal set and the error component subsequence for deterministic processing to obtain a deterministic component;

[0023] Obtaining a difference component between the non-error component subsequence and the deterministic component to obtain the deterministic component;

[0024] The information loss component, the deterministic component and the sum component of the deterministic component are obtained to obtain a non-error component subsequence.

[0025] As described in the ionospheric parameter prediction method based on the sequence deterministic strategy, the deterministic processing includes:

[0026] Sine function fitting is used to perform deterministic processing to obtain a deterministic sequence.

[0027] As described above, the ionospheric parameter prediction method based on the sequence determination strategy, after adding the first prediction result and the second prediction result respectively to obtain the sequence prediction result, further comprises:

[0028] Error analysis and computational complexity analysis are performed on the sequence prediction results.

[0029] According to the second aspect of the present invention, there is also provided an ionospheric parameter prediction device based on a sequence deterministic strategy, which includes: a decomposition unit, used to acquire ionospheric sequence data for signal decomposition processing to obtain a sub-signal set; a processing unit, used to determine a non-error component sub-sequence and an error component sub-sequence based on the sub-signal set; a first prediction unit, used to perform deterministic processing on the non-error component sub-sequence to obtain a first prediction result; a second prediction unit, used to perform neural network processing on the error component sub-sequence to obtain a second prediction result; and an output unit, used to add the first prediction result and the second prediction result respectively to obtain a sequence prediction result.

[0030] According to a third aspect of the present invention, there is also provided a computer-readable storage medium, in which a computer program is stored, wherein the computer program is configured to execute the above-mentioned ionospheric parameter prediction method based on the sequence determination strategy when running.

[0031] According to a fourth aspect of the present invention, there is also provided an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the ionospheric parameter prediction method based on the sequence determination strategy through the computer program.

[0032] In general, the above technical solutions conceived by the present invention can achieve the following beneficial effects compared with the prior art:

[0033] (1) The present invention provides an ionospheric parameter prediction method based on a sequence deterministic strategy, which obtains a sub-signal set by acquiring ionospheric sequence data and performing signal decomposition processing; based on the sub-signal set, a non-error component sub-sequence and an error component sub-sequence are determined; the non-error component sub-sequence is subjected to deterministic processing to obtain a first prediction result; the error component sub-sequence is subjected to neural network processing to obtain a second prediction result; the first prediction result and the second prediction result are added together to obtain a sequence prediction result. The problem of additional computational complexity brought about by the signal decomposition algorithm in the traditional method is solved, and the computational complexity of the model is reduced on the basis of accurately predicting the ionospheric sequence, providing strong support for shortwave communication frequency selection.

[0034] (2) The present invention takes into account the problems of incomplete decomposition in current signal decomposition algorithms, and improves the feature extraction capability of the decomposition algorithm for ionospheric sequences by designing the Beluga optimization algorithm combined with the variational mode decomposition method. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0036] Figure 1 A schematic flow chart of an optional ionospheric parameter prediction method based on a sequence determination strategy provided in an embodiment of the present application;

[0037] Figure 2 A flow chart of another optional ionospheric parameter prediction method based on a sequence determination strategy provided in an embodiment of the present application;

[0038] Figure 3 A schematic diagram of an optional process flow of the White Whale optimization algorithm provided in an embodiment of the present application;

[0039] Figure 4 A schematic diagram of the structure of an optional ionospheric parameter prediction device based on a sequence determination strategy provided in an embodiment of the present application;

[0040] Figure 5 A schematic diagram of the structure of an optional electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0041] In order to make the purpose, technical solutions 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. In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0042] The terms "first", "second", "third", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0043] The ionosphere is part of the Earth's atmosphere and is located at an altitude of about 50 to 1000 kilometers from the Earth's surface. In this layer, due to the influence of solar radiation, atmospheric molecules are ionized to form a large number of free electrons and ions, thus forming a plasma state in the atmosphere. Since the composition and density distribution of the atmosphere at different altitudes are uneven, the frequency bands and spectral lines of the radiation sources that cause ionization due to solar radiation will also be different, resulting in uneven distribution of electron density at different altitudes in the ionosphere. This uneven distribution of electron density at different altitudes directly affects shortwave communication transmission.

[0044] Generally speaking, based on the distribution of ionospheric electron density at different altitudes as the basic standard, the ionosphere can be divided into D, E, F1, and F2 layers from low to high, and their corresponding electron densities also show a trend of change from low to high.

[0045] At the same time, the ionospheric time prediction process aims to fit the changing characteristics of the ionospheric parameter sequence. The prediction methods of ionospheric parameters are divided into two types: long-term prediction method and short-term prediction method.

[0046] The long-term prediction method is used to predict the monthly statistical values ​​of ionospheric parameters. The time scale covered is larger than the predicted time range, and the prediction time granularity is large. Its expected goal is to provide a trend forecast for the long-term changes in the ionosphere. However, its accuracy is limited due to its wide coverage and long time involved. The short-term ionospheric prediction method is also called the near-real-time prediction method. It covers a shorter time range and has a smaller prediction time granularity. Its purpose is to predict the precise ionospheric parameters for the next few days or even hours.

[0047] In view of the above situation, the present invention is based on the ionospheric history sequence. By designing a variational mode decomposition method optimized by the Beluga optimization algorithm, the signal subsequence generated after the decomposition is first obtained. Then, through the signal deterministic strategy, the signal components with lower complexity are subjected to deterministic prediction processing. Only the error components are predicted by the neural network method. The obtained prediction results are added respectively to obtain the final signal prediction result.

[0048] According to one aspect of the embodiments of the present application, a method for predicting ionospheric parameters based on a sequence determination strategy is provided. Figure 1 The present invention describes an ionospheric parameter prediction method based on a sequence determination strategy provided in an embodiment of the present application.

[0049] Figure 1 is a flow chart of an optional ionospheric parameter prediction method based on a sequence determination strategy provided in an embodiment of the present application, such as Figure 1 As shown, the process of the method may include the following steps:

[0050] S102, acquiring ionospheric sequence data, performing signal decomposition processing, and obtaining a sub-signal set.

[0051] S104: Determine a non-error component subsequence and an error component subsequence based on the sub-signal set.

[0052] S106, performing deterministic processing on the non-error component subsequence to obtain a first prediction result;

[0053] S108, performing neural network processing on the error component subsequence to obtain a second prediction result.

[0054] S110, adding the first prediction result and the second prediction result respectively to obtain a sequence prediction result.

[0055] An optional ionospheric parameter prediction method based on a sequence determination strategy in an embodiment of the present application can be applied to short-term ionospheric prediction to provide refined ionospheric parameters within a few days.

[0056] Figure 2 A flow chart of another optional ionospheric parameter prediction method based on a sequence determination strategy provided in an embodiment of the present application is as follows: Figure 2As shown, firstly, the ionospheric sequence data is subjected to signal decomposition processing, and different signal decomposition methods are used to decompose the obtained ionospheric sequence data to obtain different sub-signals, and obtain a sub-signal set. Secondly, the sub-signals are processed to determine the non-error component sub-sequence and the error component sub-sequence, and each sub-signal sequence including the error component is obtained; finally, only the error component sub-sequence is processed by a neural network to obtain the second prediction result, and the remaining signal components are processed by a deterministic processing method with lower complexity to obtain the first prediction result, and finally the first prediction result and the second prediction result are added together to obtain the final sequence prediction result, and error analysis and operation processing complexity analysis are performed.

[0057] The present invention performs deterministic processing on the basis of completing the decomposed sub-signals through the above steps S102 to S110, and replaces the neural network processing with a simple deterministic processing method for the sub-signals with low complexity generated in the decomposition process, and only uses the neural network processing method for the error components with high complexity to obtain a prediction result with high accuracy. It can reduce the computational complexity of the model on the basis of accurately predicting the ionospheric sequence, and provide strong support for the frequency selection of shortwave communication.

[0058] Based on the content of the above embodiment, as an optional embodiment, the ionospheric parameter prediction method based on the sequence determination strategy provided by the present invention obtains ionospheric sequence data for signal decomposition processing to obtain a sub-signal set, including:

[0059] Acquire ionospheric sequence data; optimize variational mode decomposition parameters using the Beluga optimization algorithm to obtain a target variational mode decomposition model; input the ionospheric sequence data into the target variational mode decomposition model to output a sub-signal set.

[0060] Specifically, the ionosphere sequence data of the ionosphere foF2 sequence is taken as an example for explanation below.

[0061] In variational mode decomposition, the ionospheric sequence is decomposed into different signal components. The specific decomposition process is as follows: First, the ionospheric sequence decomposition problem is converted into a variational problem. The specific expression is as follows:

[0062]

[0063] Among them, f(t) represents the input data, u k represents the decomposed signal subcomponent, w k Indicates the center frequencies of different signal subcomponents obtained during the decomposition process. * indicates convolution processing, δ t Represents the impulse function. In order to solve the above variational problem, the Lagrangian operator λ and penalty factor α are introduced. The Lagrangian algorithm strategy is as follows:

[0064]

[0065] Here, K represents the number of decomposed modes.

[0066] In order to solve the optimization problem existing in the above two formulas, the present invention adopts a multiplier alternating iteration method to derive the problem and obtain a variational mode decomposition model.

[0067] Among them, u k With w k The iterative process is as follows:

[0068]

[0069] in express The Fourier transform result of .

[0070] Specifically, the specific process of variational mode decomposition is summarized as follows:

[0071] 1) Let n = 1 and set the value of constant K, and initialize u in the first iteration loop k , w, and λ.

[0072] 2) Update u according to the formula mentioned above k With w k The value of .

[0073] 3) Lagrangian operator λ n The value of (w) is gradually updated during the training process:

[0074]

[0075] Where τ represents the noise tolerance.

[0076] 4) The iterative process continues until the decomposed component calculation result is less than the preset exact convergence tolerance criterion (i.e., ε), and the sub-signal set of the components generated after the output signal decomposition is specifically:

[0077]

[0078] Furthermore, the variational mode decomposition parameters in the above variational mode decomposition model are optimized using the Beluga optimization algorithm to obtain the target variational mode decomposition model.

[0079] The variational mode decomposition parameters include, for example, a penalty factor α and a decomposition mode quantity parameter K.

[0080] The White Whale optimization algorithm is based on a population mechanism. Assuming that each White Whale is a candidate solution, the candidate solutions are continuously updated during the optimization process. The optimization algorithm flow chart is as follows: Figure 3 As shown. The algorithm flow can be divided into four stages, which are described as follows:

[0081] (1) Population initialization stage

[0082] First, let X represent the population's overall position distribution matrix, x1, x2...x n Representing the individuals in the population, we set the initial positions of different individuals in the population:

[0083]

[0084] Where n represents the total number of populations, and d represents the number of variable dimensions to be explored. X represents the fitness value of the population, f(x 11 ,...x 1d ), the fitness values ​​corresponding to all individuals in the population are as follows:

[0085]

[0086] The present invention uses the envelope entropy of the foF2 sequence as a method for calculating the fitness value. A balance factor B is set in the algorithm f , whether the individuals in the population are suitable to continue exploring at the current location:

[0087] B f =B0(1-T / (2T max ))

[0088] Among them, T represents the number of iterations of the algorithm at the current time, T max Indicates the maximum number of iterations. B0 is a random number between 0 and 1. f When it is greater than 0.5, the individuals corresponding to the current population will enter the exploration phase (i.e., phase (2)). f When it is less than or equal to 0.5, the current individual will enter the development stage (i.e. stage (3)). As the number of iterations increases, B f The fluctuation range will gradually decrease, and the individual's behavior will tend to be stable.

[0089] (2) Exploration phase

[0090] In the exploration phase, the algorithm updates the location of the beluga population, and the update formula is as follows:

[0091] When j is an even number.

[0092] When j is an odd number.

[0093] Where T represents the current iteration number, represents the updated position of the i-th beluga whale in the population in the j-th dimension (relative to For example, P j (j=1,2,...,d) represents a dimension randomly selected from d dimensions. and represents the current position of the i-th and r-th beluga whales, r represents a randomly selected beluga whale, r1 and r2 represent random numbers between 0 and 1 to enhance the randomness of the exploration phase, sin(2πr2) and cos(2πr2) are used to simulate the synchronous mirroring behavior of beluga whales when swimming and diving, and also play the role of averaging random numbers.

[0094] (3) Development stage

[0095] In the development phase of the beluga optimization algorithm, beluga whales can cooperate in foraging based on the locations of neighboring beluga whales. Different beluga whales share location information with each other, and beluga whales move based on this information. Specifically, the algorithm is a process of finding the optimal solution. The updates in the development phase are as follows:

[0096]

[0097] Where T represents the current number of iterations, represents the updated position of the beluga individual, Represents a randomly selected beluga whale. Indicates the best position in the current stage. r3 and r4 are random numbers between 0 and 1, where C1 and L F To improve the convergence of the algorithm, the strategy definition functions are defined as follows (β is a constant set to 1.5):

[0098] C1=2r4(1-T / T max )

[0099] L F =0.05·u·δ / |v| 1 / β

[0100] Among them, u and v are parameters with normal distribution characteristics, and δ is defined as:

[0101]

[0102] (4) Whale Fall Stage

[0103] In the process of exploration and development of the beluga population, the population will face a corresponding probability of extinction, which is called "whale fall" in the algorithm, resulting in a slight change in the population size. We set the step size of the beluga whale fall to X step , the whale position is updated as follows:

[0104]

[0105] Among them, r5, r6 and r7 are random numbers between (0,1), and the step length X when the whale falls step Determined as:

[0106]

[0107] where u b With l b are the upper and lower bounds of the step length variable of the white whale, respectively. C2 is defined as: C2 = 2W f n, where W f The probability of whale fall occurring at each step in the algorithm:

[0108] W f =0.1-0.05T / T max

[0109] Whale fall probability W f It gradually decreases during the iteration process, which means that the white whales that survive longer are more likely to find the location of the optimal parameters.

[0110] Therefore, in order to avoid the uncertainty of artificially selected parameters, the White Whale optimization algorithm is used to optimize the variational mode decomposition parameters in the variational mode decomposition, aiming to make the variational mode decomposition results more reliable.

[0111] The present invention uses the above-mentioned Beluga optimization algorithm to input the initial settings of the parameters to be optimized and the ionospheric sequence data to be decomposed as the initial position of the population, and outputs the optimization results of the variational mode decomposition parameters to be optimized to construct a target variational mode decomposition model. The present invention takes into account the problems of incomplete decomposition in the current signal decomposition algorithm, and improves the feature extraction capability of the decomposition algorithm for the ionospheric foF2 sequence by designing the Beluga optimization algorithm combined with the variational mode decomposition method.

[0112] Based on the content of the above embodiment, as an optional embodiment, the present invention provides a method of determining a non-error component subsequence and an error component subsequence based on a sub-signal set, including:

[0113] Oscillation frequency detection is performed based on the sub-signal set to obtain an error component sub-sequence. Based on the ionosphere sequence data, the sub-signal set and the error component sub-sequence, a non-error component sub-sequence is determined.

[0114] Taking into account the additional neural network processing complexity brought by the current deep learning combined with signal decomposition algorithm, the present invention considers classifying and processing the components generated by signal decomposition, that is, the sub-signal set, to obtain non-error component sub-sequences and error component sub-sequences. Among them, the error component sub-sequence is the sub-signal with the highest oscillation frequency. The non-error component sub-sequence is the remaining sub-signals in the sub-signal set except the sub-signal with the highest oscillation frequency.

[0115] Optionally, after acquiring the ionospheric sequence data and performing signal decomposition processing on it, a method such as fast Fourier transform (FFT) or Hilbert-Huang transform can be used to find the sub-signal with the highest oscillation frequency to obtain an error component sub-sequence.

[0116] For the signal component with the highest oscillation frequency, a neural network is used for prediction;

[0117] For the remaining signal components, deterministic processing is used. Deterministic processing can obtain fitting expressions of the sinusoidal functions of the components. These expressions use the prediction time as the independent variable. Substituting the prediction time into the expression can generate prediction results for each component and obtain the first prediction result. The first prediction result of the deterministic processing is added to the second prediction result of the neural network to obtain the sequence prediction result under the deterministic strategy.

[0118] Optionally, the deterministic processing is performed by using sine function fitting to obtain a deterministic sequence.

[0119] In an exemplary embodiment, considering the advantage of the sine fitting algorithm in having an accurate fitting effect on periodic sequence data, a sine function fitting is used as a deterministic strategy method to perform deterministic fitting on the sub-signals generated after the signal decomposition processing using a sine fitting algorithm, thereby fitting different sub-signals into deterministic signals. Considering that the sub-signals obtained after, for example, time series decomposition have different non-stationarities, when the sequence decomposition results are deterministically processed, the remaining sub-signals except the sub-signal with the strongest non-stationarity (i.e., the error component sub-sequence) are subjected to sine fitting deterministic processing to obtain deterministic sub-signals. For the sub-signal with the strongest non-stationarity, considering that its variation characteristics are relatively complex, a deep learning method is still used to predict it. Through the above operations, only one deep learning model is required to complete the prediction, thereby reducing the implementation complexity.

[0120] Specifically, for the sub-signals generated by decomposition, the sine function fitting algorithm is used to decompose them into a combination of multiple sine functions with different amplitudes and phases. The fitting result sequence of the determined sub-signals is represented by g(x), and its combination form can be summarized as:

[0121]

[0122] Among them, x represents the change time a, b of the independent variable fitting sequence, and c represents the combination coefficient.

[0123] In an exemplary embodiment, the method for predicting ionospheric foF2 parameters by combining deep learning with signal decomposition is, for example:

[0124] Input: original foF2 sequence S

[0125] Output: Predicted foF2 sequence S′

[0126] Decompose the original foF2 sequence S and obtain the signal subcomponent set f N

[0127] For the signal subcomponent set f N Each signal subcomponent f x , x=1,2...,n-1, except f n :

[0128] Through the deterministic strategy, each sub-signal component f is obtained x The deterministic prediction result f′ x

[0129] Signal loss r = Sf' x

[0130] Determined component C = C + f' x

[0131] End the loop

[0132] The error component f generated by decomposition n =f n +r

[0133] The error component f is obtained by deep learning method n The prediction result f′ n

[0134] Predicted foF2 sequence result S′=C+f′ n

[0135] Return the predicted foF2 sequence S′

[0136] Among them, f′ n represents the second prediction result, and C represents the first prediction result

[0137] In summary, the present invention has the following characteristics:

[0138] 1. The additional computational complexity brought by deep learning combined with signal decomposition methods is considered, and the complexity of sequence processing is reduced through sequence determination strategies.

[0139] 2. Considering the problems of incomplete decomposition in the current signal decomposition algorithm, the decomposition algorithm is designed to improve its feature extraction capability for the ionospheric foF2 sequence by combining the Beluga optimization algorithm with the variational mode decomposition method.

[0140] According to another aspect of an embodiment of the present application, an ionospheric parameter prediction device for implementing the above-mentioned ionospheric parameter prediction method based on the sequence determination strategy is also provided. Figure 4 is a schematic diagram of the structure of an optional ionospheric parameter prediction device based on a sequence determination strategy according to an embodiment of the present application, such as Figure 4 As shown, the device may include:

[0141] A decomposition unit 402 is used to obtain ionospheric sequence data, perform signal decomposition processing, and obtain a sub-signal set;

[0142] A processing unit 404 is configured to determine a non-error component subsequence and an error component subsequence based on the sub-signal set;

[0143] A first prediction unit 406, configured to perform deterministic processing on the non-error component subsequence to obtain a first prediction result;

[0144] A second prediction unit 408, configured to perform neural network processing on the error component subsequence to obtain a second prediction result;

[0145] The output unit 410 is used to add the first prediction result and the second prediction result respectively to obtain a sequence prediction result.

[0146] It should be noted that the decomposition unit 402 in this embodiment can be used to execute the above step S102, the processing unit 404 in this embodiment can be used to execute the above step S104, the first prediction unit 406 in this embodiment can be used to execute the above step S106, the second prediction unit 408 in this embodiment can be used to execute the above step S108, and the output unit 410 in this embodiment can be used to execute the above step S110.

[0147] Through the above modules, the ionospheric sequence data is obtained to perform signal decomposition processing to obtain a sub-signal set; based on the sub-signal set, the non-error component sub-sequence and the error component sub-sequence are determined; the non-error component sub-sequence is subjected to deterministic processing to obtain a first prediction result; the error component sub-sequence is subjected to neural network processing to obtain a second prediction result; the first prediction result and the second prediction result are added respectively to obtain a sequence prediction result. The problem of additional computational complexity brought by the signal decomposition algorithm in the traditional method is solved, and the computational complexity of the model is reduced on the basis of accurately predicting the ionospheric sequence, providing strong support for the frequency selection of shortwave communication.

[0148] It should be noted here that the examples and scenarios implemented by the above-mentioned modules and corresponding steps are the same, but are not limited to the contents disclosed in the above-mentioned embodiments. It should be noted that the above-mentioned modules as part of the device can run in a hardware environment and can be implemented by software or hardware, wherein the hardware environment includes a network environment.

[0149] According to another aspect of the embodiment of the present application, a storage medium is further provided. Optionally, in this embodiment, the storage medium can be used to execute the program code of any of the above-mentioned ionospheric parameter prediction methods based on the sequence determination strategy in the embodiment of the present application.

[0150] Optionally, in this embodiment, the storage medium is configured to store program codes for executing the following steps:

[0151] S1, obtaining ionospheric sequence data for signal decomposition processing to obtain a sub-signal set;

[0152] S2, determining a non-error component subsequence and an error component subsequence based on the sub-signal set;

[0153] S3, performing deterministic processing on the non-error component subsequence to obtain a first prediction result;

[0154] S4, performing neural network processing on the error component subsequence to obtain a second prediction result;

[0155] S5, adding the first prediction result and the second prediction result respectively to obtain a sequence prediction result.

[0156] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments, which will not be described in detail in this embodiment.

[0157] Among them, computer-readable storage media may include, but are not limited to, any type of disk, including floppy disks, optical disks, DVDs, CD-ROMs, microdrives and magneto-optical disks, ROMs, RAMs, EPROMs, EEPROMs, DRAMs, VRAMs, flash memory devices, magnetic or optical cards, nanosystems (including molecular memory ICs), or any type of medium or device suitable for storing instructions and / or data.

[0158] According to another aspect of an embodiment of the present application, an electronic device for implementing the above-mentioned ionospheric parameter prediction method based on the sequence determination strategy is also provided. The electronic device may be a server, a terminal, or a combination thereof.

[0159] Figure 5 is a schematic diagram of the structure of an optional electronic device according to an embodiment of the present application, such as Figure 5As shown, it includes a processor 502, a communication interface 504, a memory 506 and a communication bus 508, wherein the processor 502, the communication interface 504, and the memory 506 communicate with each other through the communication bus 508, wherein:

[0160] Memory 506, used for storing computer programs;

[0161] The processor 502 is used to execute the computer program stored in the memory 506 to implement the following steps:

[0162] S1, obtaining ionospheric sequence data for signal decomposition processing to obtain a sub-signal set;

[0163] S2, determining a non-error component subsequence and an error component subsequence based on the sub-signal set;

[0164] S3, performing deterministic processing on the non-error component subsequence to obtain a first prediction result;

[0165] S4, performing neural network processing on the error component subsequence to obtain a second prediction result;

[0166] S5, adding the first prediction result and the second prediction result respectively to obtain a sequence prediction result.

[0167] Optionally, the communication bus may be a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5 The communication interface is used for communication between the electronic device and other devices.

[0168] The memory may include RAM, or may include non-volatile memory, such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0169] As an example, the memory 506 may include, but is not limited to, the receiving unit 402, the first verification unit 404, the second verification unit 406, and the adding unit 408 in the ionospheric parameter prediction device based on the sequence determination strategy. In addition, other module units in the ionospheric parameter prediction device based on the sequence determination strategy may also be included but are not limited to, which will not be repeated in this example.

[0170] The above-mentioned processor can be a general-purpose processor, which can include but not be limited to: CPU (Central Processing Unit), NP (Network Processor), etc.; it can also be DSP (Digital Signal Processing), ASIC (Application Specific Integrated Circuit), FPGA (Field-Programmable Gate Array) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0171] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments, and this embodiment will not be described in detail here.

[0172] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0173] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0174] In the several embodiments provided in the present application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0175] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0176] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0177] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM), random access memory (RAM), mobile hard disk, disk or optical disk and other media that can store program code.

[0178] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, which can include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0179] The above is only an exemplary embodiment of the present disclosure, and the scope of the present disclosure cannot be limited thereto. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the specification and practicing the disclosure here, those skilled in the art will easily think of the implementation scheme of the present disclosure. This application is intended to cover any modification, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the technical field not recorded in the present disclosure. The description and examples are regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

[0180] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0181] It will be easily understood by those skilled in the art that 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 and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for predicting ionospheric parameters based on a sequence determination strategy, characterized in that: include: Acquire ionospheric sequence data to perform signal decomposition processing to obtain a sub-signal set; Based on the sub-signal set, determining a non-error component sub-sequence and an error component sub-sequence; Performing deterministic processing on the non-error component subsequence to obtain a first prediction result; Performing neural network processing on the error component subsequence to obtain a second prediction result; The first prediction result and the second prediction result are added together to obtain a sequence prediction result.

2. The ionospheric parameter prediction method based on the sequence determination strategy according to claim 1, characterized in that: The step of acquiring the ionospheric sequence data and performing signal decomposition processing to obtain a sub-signal set includes: Acquire ionospheric sequence data; The White Whale optimization algorithm is used to optimize the variational mode decomposition parameters to obtain the target variational mode decomposition model; The ionospheric sequence data is input into the target variational mode decomposition model, and a sub-signal set is output.

3. The ionospheric parameter prediction method based on the sequence determination strategy according to claim 2, characterized in that: The variational mode decomposition parameters include a penalty factor and a decomposition mode quantity parameter.

4. The ionospheric parameter prediction method based on the sequence determination strategy according to claim 1, characterized in that: The determining, based on the sub-signal set, a non-error component sub-sequence and an error component sub-sequence comprises: Perform oscillation frequency detection based on the sub-signal set to obtain an error component sub-sequence, wherein the error component sub-sequence is the sub-signal with the highest oscillation frequency; Based on the ionospheric sequence data, the sub-signal set and the error component sub-sequence, a non-error component sub-sequence is determined.

5. The ionospheric parameter prediction method based on the sequence determination strategy according to claim 4, characterized in that: The determining of the non-error component subsequence based on the ionospheric sequence data, the sub-signal set and the error component subsequence comprises: Acquire a difference component between the ionospheric sequence data and the sub-signal set to obtain an information loss component; Obtaining a difference component between the sub-signal set and the error component subsequence and performing deterministic processing to obtain a deterministic component; Obtaining a difference component between the non-error component subsequence and the deterministic component to obtain the deterministic component; The information loss component, the deterministic component and the sum component of the deterministic component are obtained to obtain a non-error component subsequence.

6. The ionospheric parameter prediction method based on the sequence determination strategy according to claim 1 or 5, characterized in that ,The definite processing includes: Sine function fitting is used to perform deterministic processing to obtain a deterministic sequence.

7. The ionospheric parameter prediction method based on the sequence determination strategy according to any one of claims 1 to 6, characterized in that: After the first prediction result and the second prediction result are added together to obtain a sequence prediction result, the method further includes: Error analysis and computational complexity analysis are performed on the sequence prediction results.

8. An ionospheric parameter prediction device based on a sequence determination strategy, characterized in that: include: A decomposition unit is used to obtain ionospheric sequence data to perform signal decomposition processing to obtain a sub-signal set; A processing unit, configured to determine a non-error component subsequence and an error component subsequence based on the sub-signal set; A first prediction unit, configured to perform deterministic processing on the non-error component subsequence to obtain a first prediction result; A second prediction unit, configured to perform neural network processing on the error component subsequence to obtain a second prediction result; The output unit is used to add the first prediction result and the second prediction result respectively to obtain a sequence prediction result.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein the program executes the method according to any one of claims 1 to 7 when executed.

10. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to execute the method according to any one of claims 1 to 7 through the computer program.

Images