Hybrid network structure compatibility optimization method and device based on hybrid frog leaping algorithm

Abstract

The present invention relates to a hybrid network structure compatibility optimization method and device based on a hybrid frog leaping algorithm. The method comprises: identifying compatibility issues in a hybrid network and determining an optimization target; randomly generating a group of frogs, sorting the frogs by fitness, and dividing them into multiple subgroups for local search. Within each subgroup, frogs with low fitness are adjusted based on frogs with high fitness, with each frog representing a solution to the compatibility issue in the hybrid network; in response to the number of local search rounds meeting a preset mixing period, all frogs are remixed and a new subgroup is generated for local search to share information between the frogs; in response to the improvement in current fitness being less than a set fitness convergence threshold, or the maximum number of iterations having been reached, the frog with the highest fitness is output as the optimal solution. The method can effectively adjust network parameters and protocol settings, thereby achieving compatibility between different devices.

Description

Technical Field

[0001] The present invention relates to the field of hybrid network structures, and in particular to a hybrid network structure compatibility optimization method and device based on a hybrid frog leaping algorithm. Background Art

[0002] With the rapid development of information technology, hybrid network structures are becoming increasingly prevalent in various applications. These networks often consist of different types of devices and protocols, leading to increasingly prominent inter-device compatibility issues. For example, in a hybrid environment consisting of wireless sensor networks and wired networks, inconsistent data formats and protocol incompatibilities can arise, impacting the efficiency and reliability of data transmission. Furthermore, traditional optimization algorithms often struggle to simultaneously address multiple compatibility issues, resulting in suboptimal network performance. Therefore, improvements are needed. Summary of the Invention

[0003] Based on this, it is necessary to provide a hybrid network structure compatibility optimization method and device based on a hybrid frog leaping algorithm to address the problem that traditional optimization algorithms are difficult to handle multiple compatibility issues at the same time, resulting in network performance failing to meet expectations.

[0004] The present invention provides a hybrid network structure compatibility optimization method based on a hybrid frog leaping algorithm, the method comprising:

[0005] Identify compatibility issues in hybrid networks and determine optimization goals, including latency, throughput, and transmission reliability;

[0006] A group of frogs is randomly generated and sorted by fitness to form multiple subgroups for local search. Within each subgroup, frogs with low fitness are adjusted based on frogs with high fitness. Each frog represents a solution to the compatibility problem in the hybrid network.

[0007] In response to the number of rounds of local search satisfying a preset mixing period, all frogs are remixed and a new subgroup is generated to perform local search to share information among frogs;

[0008] In response to the improvement of the current fitness being less than the set fitness convergence threshold, or the maximum number of iterations having been reached, the frog with the highest fitness is output as the optimal solution.

[0009] In one embodiment, identifying compatibility issues in a hybrid network and determining optimization targets includes:

[0010] Obtain the current configuration, protocol type, and data format information of each device in the network;

[0011] Benchmark tests of latency, throughput, and data transfer reliability metrics generated by each device in the storage network under its current configuration;

[0012] Determine optimization goals based on acquired device information and stored benchmark results.

[0013] In one embodiment, determining the optimization target includes:

[0014] Get the average transmission time of data packets from source device to destination device to quantify latency;

[0015] and / or, calculating the number of data bytes successfully transmitted within a preset time period to evaluate throughput;

[0016] And / or, calculate the packet loss rate and retransmission rate to quantify reliability.

[0017] In one embodiment, the method of randomly generating a group of frogs, sorting the frogs by fitness and dividing them into multiple subgroups for local search, and adjusting the frogs with low fitness in each subgroup according to the frogs with high fitness, includes:

[0018] A set of frogs is randomly generated according to a preset number, and the characteristics of each frog are represented as a vector. Each feature vector contains parameters of the network protocol type, data format, and transmission rate.

[0019] Set the value range of each parameter based on the actual network environment and randomly generate parameter values ​​within the value range;

[0020] Perform fitness evaluation on each frog to determine the quality of its solution and output the fitness value of each frog;

[0021] Sort all frogs according to their fitness values, and put frogs with higher fitness values ​​at the front;

[0022] Divide the sorted frogs into multiple subgroups, each subgroup contains the same number of frogs;

[0023] A local search is performed within each subgroup, and the poorer frogs are made to imitate the behavior of frogs with higher fitness values ​​to adjust the fitness values ​​of the poorer frogs.

[0024] In one embodiment, the method of performing local search within each subgroup and causing the poorer frogs to imitate the behavior of frogs with higher fitness values ​​to adjust the fitness values ​​of the poorer frogs includes:

[0025] Re-evaluate the fitness of each frog to ensure that its fitness value for the current state is up to date;

[0026] In each subgroup, the frog with the highest fitness value is identified and marked as the excellent frog, and the poor frogs are adjusted according to the characteristic vector of the excellent frog;

[0027] Evaluate the fitness of each frog after updating the feature vector;

[0028] In response to the end of the local search, the feature vectors and fitness values ​​of the excellent frogs in each subgroup are stored.

[0029] In one embodiment, the method of performing local search within each subgroup and causing the poorer frogs to imitate the behavior of frogs with higher fitness values ​​to adjust the fitness values ​​of the poorer frogs further includes:

[0030] In response to an updated parameter exceeding a value range when updating the feature vector, the updated parameter is limited to a set value range.

[0031] In one embodiment, in response to the number of rounds of local search satisfying a preset mixing period, all frogs are remixed and a new subgroup is generated to perform local search to share information between frogs, including:

[0032] In response to the number of rounds of local search satisfying a preset mixing period, the feature vectors of all current frogs are randomly shuffled;

[0033] Divide the shuffled frogs into multiple new subgroups according to the preset number;

[0034] In each new subgroup, identify the feature vector of the frog with the highest fitness value as the shared feature vector of the subgroup, and store the feature vector of the frog with the highest fitness value;

[0035] A local search is performed in each new subpopulation, and the poor frogs are adjusted according to the shared feature vector, and the fitness of the adjusted frogs is evaluated.

[0036] The present invention also provides a hybrid network structure compatibility optimization device based on a hybrid frog leaping algorithm, comprising:

[0037] an identification module, configured to identify compatibility issues in a hybrid network and determine optimization objectives, wherein the optimization objectives include latency, throughput, and transmission reliability;

[0038] An adjustment module is used to randomly generate a group of frogs, sort them by fitness, and divide them into multiple subgroups for local search. In each subgroup, frogs with low fitness are adjusted according to frogs with high fitness. Each frog represents a solution to the compatibility problem in the hybrid network.

[0039] a mixing module, configured to remix all frogs in response to the number of rounds of local search satisfying a preset mixing period, and generate a new subgroup for local search to share information among frogs;

[0040] The output module is used to output the frog with the highest fitness as the optimal solution in response to the improvement of the current fitness being less than a set fitness convergence threshold or the maximum number of iterations being reached.

[0041] The present invention also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, it implements the hybrid network structure compatibility optimization method based on the hybrid frog leaping algorithm as described in any one of the above.

[0042] The present invention also provides a computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, the method for optimizing the compatibility of a hybrid network structure based on the hybrid frog leaping algorithm as described above is implemented.

[0043] The above-mentioned hybrid network structure compatibility optimization method and device based on the hybrid frog leaping algorithm can effectively adjust network parameters and protocol settings by defining clear optimization goals, such as minimizing latency, maximizing throughput, and improving data transmission reliability, thereby achieving compatibility between different devices. At the same time, through the combination of local search and global mixing, it can avoid falling into local optimality and ensure that the optimal solution is found, thereby improving the overall performance and adaptability of the hybrid network. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0045] Figure 1 1 is a flow chart of a hybrid network structure compatibility optimization method based on a hybrid frog leaping algorithm in one embodiment;

[0046] Figure 2 A schematic diagram of a process for identifying compatibility issues in a hybrid network according to one embodiment;

[0047] Figure 3 A schematic diagram of a process for determining an optimization target in one embodiment;

[0048] Figure 4 Schematic diagram of a process for sorting frogs by fitness and then dividing them into multiple subgroups for local search in one embodiment;

[0049] Figure 5 A schematic diagram of a process for adjusting the fitness value of a poor frog in one embodiment;

[0050] Figure 6 A schematic diagram of a process for remixing all frogs when a mixing cycle is reached in one embodiment;

[0051] Figure 7 Schematic diagram of a hybrid network structure compatibility optimization device based on a hybrid frog leaping algorithm in one embodiment;

[0052] Figure 8 FIG. 1 is a diagram showing the internal structure of an electronic device according to an embodiment. DETAILED DESCRIPTION

[0053] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0054] The following combination Figures 1-8 The present invention describes a hybrid network structure compatibility optimization method and device based on a hybrid frog leaping algorithm.

[0055] like Figure 1 As shown, in one embodiment, a hybrid network structure compatibility optimization method based on a hybrid frog leaping algorithm includes the following steps:

[0056] Step S100: Identify compatibility issues in the hybrid network and determine optimization targets, which include delay, throughput, and transmission reliability.

[0057] Compatibility issues often manifest themselves as inconsistent protocols and incompatible data formats between devices. Specifically, protocol inconsistencies can prevent different devices from communicating effectively. For example, one device might use TCP / IP while another uses UDP, leading to packet loss or delays. Data format incompatibilities can manifest themselves as different data encoding methods between devices. For example, one device might use JSON while another uses XML, leading to data parsing errors.

[0058] Step S200: randomly generate a group of frogs, sort them by fitness and divide them into multiple subgroups for local search. In each subgroup, frogs with low fitness are adjusted according to frogs with high fitness. Each frog represents a solution to the compatibility problem in the hybrid network.

[0059] It should be noted that these solutions can be different configuration parameters or protocol adjustment solutions for compatibility issues in hybrid networks.

[0060] By effectively generating frog groups and performing fitness evaluation and grouping, we lay the foundation for subsequent local searches. At the same time, we can ensure that when solving compatibility problems in hybrid networks, we can fully utilize the advantages of swarm intelligence and quickly find better solutions.

[0061] Step S300 , in response to the number of rounds of local search satisfying a preset mixing period, all frogs are remixed and a new subgroup is generated to perform local search to share information between frogs.

[0062] Frogs can effectively share information during the hybrid phase, promoting diversity and innovation in global search. This approach not only improves the adaptability of the frog population but also enhances the efficiency of resolving compatibility issues in complex hybrid networks.

[0063] Step S400 : In response to the improvement of the current fitness being less than the set fitness convergence threshold, or the maximum number of iterations being reached, the frog with the highest fitness is output as the optimal solution.

[0064] The maximum number of iterations is the upper limit of the algorithm, while the fitness convergence threshold is used to determine whether the improvement of the current solution is significant enough. Typically, the maximum number of iterations can be set to 100 to 500 times, and the fitness convergence threshold can be set to 0.01 to 0.001, depending on the complexity of the problem.

[0065] In each iteration, a local search is first performed on the frogs in each subgroup. The frogs adjust their positions according to their fitness values ​​using the jump update formula:

[0066]

[0067] in, is the new position of the frog, It's the old location of the frog, X best is the position of the frog with the highest fitness in the current subgroup, X random is the randomly selected frog position, and α and β are parameters that control the jump amplitude. In this way, the frog is able to explore better solutions in its local area.

[0068] After each local search, the new fitness values ​​of all frogs are evaluated. The fitness function can be defined based on the optimization objective, such as minimizing latency or maximizing throughput. The fitness value can be calculated using the following formula:

[0069]

[0070] Where Delay(X) is the delay of the frog’s corresponding solution, Throughput(X) is its throughput, and MaxThroughput is the maximum throughput of the network.

[0071] After each round of local search, the system checks whether the conditions for the mixing cycle are met. If so, a global mixing process is performed, regrouping all frogs. At this point, the frogs are sorted by fitness, and the frogs with the highest fitness are selected to share information and form a new subgroup.

[0072] At the end of each iteration, the termination condition is checked. If the improvement in the current fitness is less than the set fitness convergence threshold, or the maximum number of iterations has been reached, the algorithm stops. Otherwise, local search and global mixing continue.

[0073] Once the termination condition is reached, the frog with the highest fitness and its eigenvector are recorded as the optimal solution. This solution will be applied to the hybrid network to solve the compatibility problem.

[0074] The specific examples are as follows:

[0075] Assume that in a certain iteration, after local search, the frog's fitness value does not change much, and the fitness convergence threshold is set to 0.01. After 10 rounds of local search, the improvement in fitness is less than 0.01, and the number of iterations has reached the set maximum value of 100. At this point, the algorithm will stop and record the frog feature vector with the highest fitness (for example, the protocol type is TCP, the data format is JSON, and the transmission rate is 100Mbps) as the final solution. This solution will be applied to hybrid networks to ensure compatibility between devices and efficient data transmission. In this way, the frog group can continuously optimize its solution in a complex network environment and improve the overall performance of the network.

[0076] This hybrid network structure compatibility optimization method based on the hybrid frog leaping algorithm can effectively adjust network parameters and protocol settings by defining clear optimization goals, such as minimizing latency, maximizing throughput, and improving data transmission reliability, thereby achieving compatibility between different devices. At the same time, by combining local search with global mixing, it can avoid falling into local optimality and ensure that the optimal solution is found, thereby improving the overall performance and adaptability of the hybrid network.

[0077] In this embodiment, see Figure 2 ,Identifying compatibility issues in hybrid networks and determining optimization targets includes the following steps:

[0078] Step S110: Acquire the current configuration, protocol type, and data format information of each device in the network.

[0079] It should be noted that collecting the current configuration, protocol type, and data format information of each device in the network can be achieved through a network monitoring tool or a device management system.

[0080] Step S120 : storing the delay, throughput, and data transmission reliability indicators generated by performing a benchmark test on each device in the network under the current configuration.

[0081] The stored benchmark results can be used as a reference for subsequent optimization.

[0082] Step S130 : determining an optimization target based on the acquired device information and the stored benchmark test results.

[0083] For example, based on the acquired device information and stored benchmark test results, it is assumed that latency is reduced by 20%, throughput is increased by 30%, and data transmission reliability reaches more than 99%.

[0084] In this embodiment, see Figure 3 , determine the optimization goal, including the following steps:

[0085] Step S131 : obtaining the average transmission time of a data packet from a source device to a target device to quantify the delay.

[0086] By optimizing network configuration and protocol settings, the time it takes for data to travel across the network is reduced, thus minimizing latency.

[0087] And / or, step S132, calculating the number of data bytes successfully transmitted within a preset time period to evaluate throughput.

[0088] By increasing the amount of data successfully transmitted per unit time in the network, it is convenient to maximize throughput.

[0089] And / or, in step S133, the data packet loss rate and retransmission rate are calculated to quantify reliability.

[0090] By calculating the packet loss rate and retransmission rate, it is convenient to ensure that data is not lost during transmission and can reach the target device correctly, thereby improving the reliability of data transmission.

[0091] In this embodiment, see Figure 4, randomly generate a group of frogs, and sort the frogs by fitness and divide them into multiple subgroups for local search. In each subgroup, adjust the frogs with low fitness according to the frogs with high fitness, including the following steps:

[0092] Step S210 , randomly generating a group of frogs according to a preset number, and representing the characteristics of each frog as a vector, each characteristic vector including parameters of the network protocol type, data format and transmission rate.

[0093] For example, spawn 100 frogs.

[0094] Step S220: setting a value range for each parameter based on the actual network environment, and randomly generating a value for the parameter within the value range.

[0095] For example, the protocol type can be randomly selected from TCP, UDP, or HTTP, and the data format can be selected from JSON or XML.

[0096] Step S230 , performing fitness evaluation on each frog to determine the quality of its solution, and outputting the fitness value of each frog.

[0097] The fitness function can be designed according to the optimization goal. For example, the fitness can be a weighted combination of delay, throughput and reliability. Set the fitness function as:

[0098]

[0099] Where w1, w2, and w3 are weight coefficients, and x is the frog's eigenvector. By adjusting these weights, we can emphasize different optimization objectives according to specific needs.

[0100] Step S240: sort all frogs according to their fitness values, and put frogs with higher fitness values ​​at the front.

[0101] This facilitates the subsequent quick identification of the frog with the highest fitness value in each subgroup.

[0102] Step S250: Divide the sorted frogs into multiple subgroups, each subgroup containing the same number of frogs.

[0103] It should be noted that the division of subgroups can be done by roulette wheel selection or random allocation to ensure that the frogs in each subgroup have a certain diversity.

[0104] For example, 100 frogs are divided into 10 subgroups, each with 10 frogs.

[0105] Step S260 , performing local search in each subgroup, and making the frogs with poorer fitness imitate the behavior of frogs with higher fitness values, so as to adjust the fitness values ​​of the poorer frogs.

[0106] The poorer frogs can be made to imitate the behavior of frogs with higher fitness values ​​by adjusting the frogs' feature vectors, for example, by changing the choice of protocol type or data format.

[0107] In this embodiment, see Figure 5 , perform local search within each subgroup, and make the poor frogs imitate the behavior of frogs with higher fitness values ​​to adjust the fitness values ​​of the poor frogs, including the following steps:

[0108] Step S261 , re-evaluate the fitness of each frog to ensure that its fitness value of the current state is the latest.

[0109] It should be noted that when re-evaluating the fitness of each frog, the previously set fitness function is still used.

[0110] Step S262: In each subgroup, the frog with the highest fitness value is identified and marked as an excellent frog, and the poor frogs are adjusted according to the feature vector of the excellent frog.

[0111] These excellent frogs will serve as models for imitation and guide the adjustment process of other frogs.

[0112] The specific adjustment methods are as follows:

[0113] Set an imitation factor M, whose value is between 0 and 1, to indicate the degree of imitation. The larger the imitation factor, the greater the adjustment.

[0114] For each poor frog i, its feature vector x i According to the characteristic vector x of the excellent frog j j Update, the update formula is:

[0115]

[0116] in, is the updated feature vector.

[0117] Step S263: Perform fitness evaluation on each frog after the feature vector is updated.

[0118] It is convenient to ensure that its fitness value can reflect the latest feature vector.

[0119] Step S264 , in response to the completion of the local search, the feature vectors and fitness values ​​of the excellent frogs in each subgroup are stored.

[0120] This is convenient for use in the subsequent global mixing stage.

[0121] Frogs can effectively imitate the behavior of excellent individuals during local search, thereby improving their own fitness. This imitation mechanism not only promotes information sharing between individuals, but also enhances the overall optimization ability of the group, making the process of resolving compatibility issues in hybrid networks more efficient.

[0122] In this embodiment, local search is performed within each subgroup, and the poor frogs are made to imitate the behavior of frogs with higher fitness values ​​to adjust the fitness values ​​of the poor frogs, and the following steps are also included:

[0123] Step S265 , in response to the updated parameter exceeding the value range when the feature vector is updated, limiting the updated parameter to a set value range.

[0124] When updating the feature vector, it should be ensured that the value of each parameter is still within the predetermined range.

[0125] For example, the choice of protocol type should remain between TCP, UDP, or HTTP, and the data format should be chosen between JSON or XML.

[0126] In this embodiment, see Figure 6 , in response to the number of rounds of local search satisfying a preset mixing period, all frogs are remixed and a new subgroup is generated for local search to share information between frogs, including the following steps:

[0127] Step S310 , in response to the number of rounds of local search satisfying a preset mixing period, the feature vectors of all current frogs are randomly shuffled.

[0128] The mixing period determines how many rounds of local search are followed by a global mixing. This mixing period can be adjusted based on the dynamic changes of the network and is usually between 10 and 20 rounds.

[0129] By randomly shuffling the feature vectors of all current frogs, it is convenient to ensure that frogs can obtain different partners in new subgroups, thereby promoting information diversity and innovation.

[0130] Step S320: Divide the shuffled frogs into a plurality of new subgroups according to a preset number.

[0131] The size of each subgroup can be calculated based on the total number of frogs N and the desired number of subgroups M. Specifically, the size of each subgroup is:

[0132]

[0133] For example, if there are 100 frogs and you want to form 5 subgroups, each subgroup will contain 20 frogs.

[0134] Step S330 , in each new subgroup, identifying the feature vector of the frog with the highest fitness value as the shared feature vector of the subgroup, and storing the feature vector of the frog with the highest fitness value.

[0135] In the new subgroup, frogs will share information with each other. The frogs in each subgroup will communicate their respective feature vectors and fitness values ​​with each other. In particular, frogs with higher fitness will share their successful strategies and parameter settings.

[0136] Step S340 , performing local search in each new subgroup, adjusting the poor frogs according to the shared feature vector, and evaluating the fitness of the adjusted frogs.

[0137] The frogs will evaluate their fitness based on the shared feature vectors and make adjustments based on that. This way, the frogs can not only leverage their own experience but also learn from the successful experiences of other frogs, thereby improving the overall search efficiency.

[0138] The specific examples are as follows:

[0139] Suppose that in a certain iteration, there are 100 frogs, and the feature vector of each frog contains three parameters (such as protocol type, data format, and transmission rate). After 15 rounds of local search, set the mixing period T = 15. These 100 frogs are randomly shuffled and divided into 5 subgroups, each with 20 frogs. The frogs in each subgroup will share their respective feature vectors and fitness values, and ultimately select the feature vector of the frog with the highest fitness as the shared feature vector. Next, all frogs will conduct a new local search based on this shared feature vector and adjust their respective parameters to achieve better fitness. In this way, the frog group can continuously optimize its solution in a dynamically changing network environment.

[0140] The hybrid network structure compatibility optimization device based on the hybrid frog leaping algorithm provided by the present invention is described below. The hybrid network structure compatibility optimization device based on the hybrid frog leaping algorithm described below and the hybrid network structure compatibility optimization method based on the hybrid frog leaping algorithm described above can be referenced to each other.

[0141] like Figure 7 As shown, in one embodiment, a hybrid network structure compatibility optimization device based on a hybrid frog leaping algorithm includes an identification module 710 , an adjustment module 720 , a mixing module 730 and an output module 740 .

[0142] The identification module 710 is used to identify compatibility issues in the hybrid network and determine optimization targets, which include delay, throughput, and transmission reliability.

[0143] The adjustment module 720 is used to randomly generate a group of frogs, sort the frogs by fitness and divide them into multiple subgroups for local search. In each subgroup, the frogs with low fitness are adjusted according to the frogs with high fitness. Each frog represents a solution to the compatibility problem in the hybrid network.

[0144] The mixing module 730 is configured to remix all frogs in response to the number of rounds of local search satisfying a preset mixing period, and generate a new subgroup for local search to share information among frogs.

[0145] The output module 740 is configured to output the frog with the highest fitness as the optimal solution in response to the improvement of the current fitness being less than a set fitness convergence threshold, or the maximum number of iterations being reached.

[0146] In this embodiment, compatibility issues in a hybrid network are identified and optimization targets are determined, specifically for:

[0147] Obtain the current configuration, protocol type, and data format information of each device in the network;

[0148] Benchmark tests of latency, throughput, and data transfer reliability metrics generated by each device in the storage network under its current configuration;

[0149] Determine optimization goals based on acquired device information and stored benchmark results.

[0150] In this embodiment, the optimization target is determined, specifically for:

[0151] Get the average transmission time of data packets from source device to destination device to quantify latency;

[0152] and / or, calculating the number of data bytes successfully transmitted within a preset time period to evaluate throughput;

[0153] And / or, calculate the packet loss rate and retransmission rate to quantify reliability.

[0154] In this embodiment, a group of frogs is randomly generated and sorted by fitness to form multiple subgroups for local search. In each subgroup, frogs with low fitness are adjusted based on frogs with high fitness. Specifically, the following is used:

[0155] A set of frogs is randomly generated according to a preset number, and the characteristics of each frog are represented as a vector. Each feature vector contains parameters of the network protocol type, data format, and transmission rate.

[0156] Set the value range of each parameter based on the actual network environment and randomly generate parameter values ​​within the value range;

[0157] Perform fitness evaluation on each frog to determine the quality of its solution and output the fitness value of each frog;

[0158] Sort all frogs according to their fitness values, and put frogs with higher fitness values ​​at the front;

[0159] Divide the sorted frogs into multiple subgroups, each subgroup contains the same number of frogs;

[0160] A local search is performed within each subgroup, and the poorer frogs are made to imitate the behavior of frogs with higher fitness values ​​to adjust the fitness values ​​of the poorer frogs.

[0161] In this embodiment, a local search is performed within each subgroup, and the poorer frogs are made to imitate the behavior of frogs with higher fitness values ​​to adjust the fitness values ​​of the poorer frogs, specifically for:

[0162] Re-evaluate the fitness of each frog to ensure that its fitness value for the current state is up to date;

[0163] In each subgroup, the frog with the highest fitness value is identified and marked as the excellent frog, and the poor frogs are adjusted according to the characteristic vector of the excellent frog;

[0164] Evaluate the fitness of each frog after updating the feature vector;

[0165] In response to the end of the local search, the feature vectors and fitness values ​​of the excellent frogs in each subgroup are stored.

[0166] In this embodiment, local search is performed within each subgroup, and the poorer frogs are made to imitate the behavior of frogs with higher fitness values ​​to adjust the fitness values ​​of the poorer frogs, which is also specifically used for:

[0167] In response to an updated parameter exceeding a value range when updating the feature vector, the updated parameter is limited to a set value range.

[0168] In this embodiment, the mixing module 730 is specifically configured to:

[0169] In response to the number of rounds of local search satisfying a preset mixing period, the feature vectors of all current frogs are randomly shuffled;

[0170] Divide the shuffled frogs into multiple new subgroups according to the preset number;

[0171] In each new subgroup, identify the feature vector of the frog with the highest fitness value as the shared feature vector of the subgroup, and store the feature vector of the frog with the highest fitness value;

[0172] A local search is performed in each new subpopulation, and the poor frogs are adjusted according to the shared feature vector, and the fitness of the adjusted frogs is evaluated.

[0173] This hybrid network structure compatibility optimization device based on the hybrid frog leaping algorithm can effectively adjust network parameters and protocol settings by defining clear optimization goals, such as minimizing latency, maximizing throughput, and improving data transmission reliability, thereby achieving compatibility between different devices. At the same time, through the combination of local search and global mixing, it can avoid falling into local optimality and ensure that the optimal solution is found, thereby improving the overall performance and adaptability of the hybrid network.

[0174] Figure 8 The following is a schematic diagram of the physical structure of an electronic device. The electronic device may be a smart terminal, and its internal structure diagram may be as follows: Figure 8 As shown. The electronic device includes a processor, a memory and a network interface connected via a system bus. The processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the electronic device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a hybrid network structure compatibility optimization method based on a hybrid frog leaping algorithm is implemented, and the method includes:

[0175] Identify compatibility issues in hybrid networks and determine optimization targets, including latency, throughput, and transmission reliability;

[0176] A group of frogs is randomly generated and sorted by fitness to form multiple subgroups for local search. Within each subgroup, frogs with low fitness are adjusted based on frogs with high fitness. Each frog represents a solution to the compatibility problem in the hybrid network.

[0177] In response to the number of rounds of local search satisfying a preset mixing period, all frogs are remixed and a new subgroup is generated to perform local search to share information among frogs;

[0178] In response to the improvement of the current fitness being less than the set fitness convergence threshold, or the maximum number of iterations having been reached, the frog with the highest fitness is output as the optimal solution.

[0179] Those skilled in the art will understand that Figure 8The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present invention, and does not constitute a limitation on the electronic device to which the solution of the present invention is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0180] On the other hand, the present invention also provides a computer storage medium storing a computer program, which, when executed by a processor, implements a hybrid network structure compatibility optimization method based on a hybrid frog leaping algorithm, the method comprising:

[0181] Identify compatibility issues in hybrid networks and determine optimization targets, including latency, throughput, and transmission reliability;

[0182] A group of frogs is randomly generated and sorted by fitness to form multiple subgroups for local search. Within each subgroup, frogs with low fitness are adjusted based on frogs with high fitness. Each frog represents a solution to the compatibility problem in the hybrid network.

[0183] In response to the number of rounds of local search satisfying a preset mixing period, all frogs are remixed and a new subgroup is generated to perform local search to share information among frogs;

[0184] In response to the improvement of the current fitness being less than the set fitness convergence threshold, or the maximum number of iterations having been reached, the frog with the highest fitness is output as the optimal solution.

[0185] In another aspect, a computer program product or computer program is provided, the computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of an electronic device reads the computer instructions from the computer-readable storage medium, and when the processor executes the computer instructions, implements a hybrid network structure compatibility optimization method based on a hybrid frog leaping algorithm, the method comprising:

[0186] Identify compatibility issues in hybrid networks and determine optimization targets, including latency, throughput, and transmission reliability;

[0187] A group of frogs is randomly generated and sorted by fitness to form multiple subgroups for local search. Within each subgroup, frogs with low fitness are adjusted based on frogs with high fitness. Each frog represents a solution to the compatibility problem in the hybrid network.

[0188] In response to the number of rounds of local search satisfying a preset mixing period, all frogs are remixed and a new subgroup is generated to perform local search to share information among frogs;

[0189] In response to the improvement of the current fitness being less than the set fitness convergence threshold, or the maximum number of iterations having been reached, the frog with the highest fitness is output as the optimal solution.

[0190] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided by the present invention may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory.

[0191] By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0192] The technical features of the above embodiments can 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.

[0193] The above-described embodiments merely illustrate several embodiments of the present invention, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art would be able to make various modifications and improvements without departing from the spirit of the present invention, and these modifications and improvements fall within the scope of the present invention. Therefore, the scope of the present invention shall be determined by the appended claims.

Claims

1. A hybrid network structure compatibility optimization method based on a hybrid frog leaping algorithm, characterized in that: The method comprises: Identifying compatibility issues in a hybrid network and determining optimization goals, including latency, throughput, and transmission reliability, by obtaining current configuration, protocol type, and data format information for each device in the network; storing latency, throughput, and data transmission reliability metrics generated by benchmarking each device in the network under the current configuration; and determining optimization goals based on the obtained device information and the stored benchmark test results. A group of frogs is randomly generated and sorted by fitness to form multiple subgroups for local search. Within each subgroup, frogs with low fitness are adjusted based on frogs with high fitness. Each frog represents a solution to the compatibility problem in the hybrid network. In response to the number of rounds of local search satisfying a preset mixing period, all frogs are remixed and a new subgroup is generated to perform local search to share information among frogs; In response to the improvement of the current fitness being less than the set fitness convergence threshold, or the maximum number of iterations having been reached, the frog with the highest fitness is output as the optimal solution.

2. The hybrid network structure compatibility optimization method based on the hybrid frog leaping algorithm according to claim 1 is characterized in that: Determining the optimization target includes: Get the average transmission time of data packets from source device to destination device to quantify latency; and / or, calculating the number of data bytes successfully transmitted within a preset time period to evaluate throughput; And / or, calculate the packet loss rate and retransmission rate to quantify reliability.

3. The hybrid network structure compatibility optimization method based on the hybrid frog leaping algorithm according to claim 2 is characterized in that: The method randomly generates a group of frogs, sorts the frogs by fitness and divides them into multiple subgroups for local search, and adjusts the frogs with low fitness in each subgroup according to the frogs with high fitness, including: A set of frogs is randomly generated according to a preset number, and the characteristics of each frog are represented as a vector. Each feature vector contains parameters of the network protocol type, data format, and transmission rate. Set the value range of each parameter based on the actual network environment and randomly generate parameter values ​​within the value range; Perform fitness evaluation on each frog to determine the quality of its solution and output the fitness value of each frog; Sort all frogs according to their fitness values, and put frogs with higher fitness values ​​at the front; Divide the sorted frogs into multiple subgroups, each subgroup contains the same number of frogs; A local search is performed within each subgroup, and the poorer frogs are made to imitate the behavior of frogs with higher fitness values ​​to adjust the fitness values ​​of the poorer frogs.

4. The hybrid network structure compatibility optimization method based on the hybrid frog leaping algorithm according to claim 3 is characterized in that: The method of performing local search within each subgroup and making the poor frogs imitate the behavior of the frogs with higher fitness values ​​to adjust the fitness values ​​of the poor frogs includes: Re-evaluate the fitness of each frog to ensure that its fitness value for the current state is up to date; In each subgroup, the frog with the highest fitness value is identified and marked as the excellent frog, and the poor frogs are adjusted according to the characteristic vector of the excellent frog; Evaluate the fitness of each frog after updating the feature vector; In response to the end of the local search, the feature vectors and fitness values ​​of the excellent frogs in each subgroup are stored.

5. The hybrid network structure compatibility optimization method based on the hybrid frog leaping algorithm according to claim 4 is characterized in that: The method of performing local search in each subgroup and causing the poorer frogs to imitate the behavior of frogs with higher fitness values ​​to adjust the fitness values ​​of the poorer frogs further includes: In response to an updated parameter exceeding a value range when updating the feature vector, the updated parameter is limited to a set value range.

6. The hybrid network structure compatibility optimization method based on the hybrid frog leaping algorithm according to claim 5 is characterized in that: In response to the number of rounds of local search satisfying a preset mixing period, all frogs are remixed and a new subgroup is generated to perform local search to share information between frogs, including: In response to the number of rounds of local search satisfying a preset mixing period, the feature vectors of all current frogs are randomly shuffled; Divide the shuffled frogs into multiple new subgroups according to the preset number; In each new subgroup, identify the feature vector of the frog with the highest fitness value as the shared feature vector of the subgroup, and store the feature vector of the frog with the highest fitness value; A local search is performed in each new subpopulation, and the poor frogs are adjusted according to the shared feature vector, and the fitness of the adjusted frogs is evaluated.

7. A hybrid network structure compatibility optimization device based on a hybrid frog leaping algorithm, characterized in that: include: an identification module configured to identify compatibility issues in a hybrid network and determine optimization objectives, including latency, throughput, and transmission reliability, by obtaining information about the current configuration, protocol type, and data format of each device in the network; storing latency, throughput, and data transmission reliability metrics generated by benchmarking each device in the network under the current configuration; and determining optimization objectives based on the obtained device information and the stored benchmark test results; An adjustment module is used to randomly generate a group of frogs, sort them by fitness, and divide them into multiple subgroups for local search. In each subgroup, frogs with low fitness are adjusted according to frogs with high fitness. Each frog represents a solution to the compatibility problem in the hybrid network. a mixing module, configured to remix all frogs in response to the number of rounds of local search satisfying a preset mixing period, and generate a new subgroup for local search to share information among frogs; The output module is used to output the frog with the highest fitness as the optimal solution in response to the improvement of the current fitness being less than a set fitness convergence threshold or the maximum number of iterations being reached.

8. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the hybrid network structure compatibility optimization method based on the hybrid frog leaping algorithm according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the hybrid network structure compatibility optimization method based on the hybrid frog leaping algorithm according to any one of claims 1 to 6 are implemented.

Images