Bandwidth resource allocation method, device and non-volatile storage medium

Abstract

The present invention discloses a bandwidth resource allocation method, device, and non-volatile storage medium. The method comprises: setting a constraint model for bandwidth resource allocation based on a target electric power business; randomly generating multiple initial bandwidth resource allocation schemes; using a coyote optimization algorithm to adjust the multiple initial bandwidth resource allocation schemes based on the constraint model to obtain multiple adjusted initial bandwidth resource allocation schemes; and selecting, from the multiple adjusted initial bandwidth resource allocation schemes, an adjusted initial resource allocation scheme whose fitness meets a first preset condition as a target bandwidth resource allocation scheme based on a preset fitness function, wherein the fitness function is determined based on the constraint model. The present invention solves the technical problem that bandwidth resource allocation without considering the electric power business is not rational, making it difficult to ensure the smooth operation of the electric power business.

Description

Technical Field

[0001] The present invention relates to the field of communication technology, and in particular to a bandwidth resource allocation method, device and non-volatile storage medium. Background Art

[0002] In scenarios where multiple power services share satellite communication networks, a bandwidth allocation mechanism is needed to effectively allocate and manage limited satellite network bandwidth to meet the heterogeneous needs of communication services. However, the current bandwidth resource allocation mechanism is overly simplistic and fails to consider the needs and priorities of different services, resulting in irrational bandwidth allocation and impacting the smooth operation of power services.

[0003] To address the above-mentioned problems, no effective solutions have been proposed so far. Summary of the Invention

[0004] The embodiments of the present invention provide a bandwidth resource allocation method, apparatus, and non-volatile storage medium to at least solve the technical problem that bandwidth resource allocation is not reasonable without considering the power business, making it difficult to ensure the smooth operation of the power business.

[0005] According to one aspect of an embodiment of the present invention, a bandwidth resource allocation method is provided, comprising: setting a constraint model for bandwidth resource allocation based on a target power service; randomly generating multiple initial bandwidth resource allocation schemes; using a coyote optimization algorithm to adjust the multiple initial bandwidth resource allocation schemes based on the constraint model to obtain multiple adjusted initial bandwidth resource allocation schemes; and selecting, based on a preset fitness function, from the multiple adjusted initial bandwidth resource allocation schemes an adjusted initial resource allocation scheme whose fitness meets a first preset condition as a target bandwidth resource allocation scheme, wherein the fitness function is determined based on the constraint model.

[0006] Optionally, a constraint model for bandwidth resource allocation is set according to the target power business, including: constructing a first objective function based on the data transmission time required for the target power business; constructing a second objective function based on the size of the bandwidth resources occupied by the target power business; setting constraint conditions based on the total bandwidth resources and bandwidth requirements corresponding to the target power business; and determining the constraint model based on the first objective function, the second objective function and the constraint conditions.

[0007] Optionally, randomly generating a plurality of initial bandwidth resource allocation schemes includes: randomly generating a plurality of groups of random sequences using a preset chaotic mapping function; and determining a plurality of initial bandwidth resource allocation schemes based on the plurality of groups of random sequences.

[0008] Optionally, a coyote optimization algorithm is used to adjust multiple initial bandwidth resource allocation schemes based on a constraint model to obtain multiple adjusted initial bandwidth resource allocation schemes, including: according to the coyote optimization algorithm, setting multiple coyotes, wherein the multiple coyotes have their own corresponding social factor sequences, and the social factor sequences corresponding to the multiple coyotes represent the multiple initial bandwidth resource allocation schemes; according to the fitness function, selecting the coyote whose fitness meets the first preset condition among the multiple coyotes as the optimal coyote; according to the constraint model and the social factor sequence corresponding to the optimal coyote, adjusting the social factor sequences corresponding to the multiple coyotes to obtain multiple target coyotes; and determining multiple adjusted initial bandwidth resource allocation schemes based on the multiple target coyotes.

[0009] Optionally, according to the constraint model and the social factor sequence corresponding to the optimal coyote, the social factor sequences corresponding to multiple coyotes are adjusted to obtain multiple target coyotes, including: generating a social factor sequence corresponding to a coyote cub based on the social factor sequences corresponding to multiple coyotes; judging whether there is a coyote among the multiple coyotes whose fitness is lower than that of the coyote cub based on the fitness function; in the case that there is a weak coyote among the multiple coyotes whose fitness is lower than that of the coyote cub, selecting the coyotes among the weak coyotes whose fitness meets the second preset condition and deleting them; based on the constraint model and the optimal coyote, adjusting the social factor sequences corresponding to the remaining coyotes and the social factor sequences corresponding to the coyotes cubs to obtain multiple target coyotes.

[0010] Optionally, a coyote optimization algorithm is used to adjust multiple initial bandwidth resource allocation schemes based on a constraint model to obtain multiple adjusted initial bandwidth resource allocation schemes, including: according to the coyote optimization algorithm, setting multiple coyotes, wherein the multiple coyotes have their own corresponding social factor sequences, and the social factor sequences corresponding to the multiple coyotes represent the multiple initial bandwidth resource allocation schemes; randomly dividing the multiple coyotes into multiple sub-populations; based on the constraint model, adjusting the social factor sequences corresponding to the coyotes in the multiple sub-populations respectively, performing multiple iterative adjustments to obtain multiple target sub-populations; and determining multiple adjusted initial bandwidth resource allocation schemes based on the coyotes corresponding to the multiple target sub-populations.

[0011] Optionally, based on the constraint model, the social factor sequences corresponding to the coyotes in each of the multiple subpopulations are adjusted respectively, and multiple iterative adjustments are performed to obtain multiple target subpopulations, including: obtaining the current number of iterations; determining the target probability based on the current number of iterations; based on the target probability, exchanging coyotes between the multiple subpopulations to obtain multiple new subpopulations; based on the constraint model, adjusting the social factor sequences corresponding to the coyotes in each of the multiple new subpopulations to obtain multiple adjusted new subpopulations; based on the above method of obtaining multiple adjusted new subpopulations, multiple iterative adjustments are performed to obtain multiple target subpopulations.

[0012] According to another aspect of an embodiment of the present invention, a bandwidth resource allocation device is provided, comprising: a setting module for setting a constraint model for bandwidth resource allocation based on a target power business; a generation module for randomly generating multiple initial bandwidth resource allocation schemes; an adjustment module for using a coyote optimization algorithm to adjust the multiple initial bandwidth resource allocation schemes based on the constraint model to obtain multiple adjusted initial bandwidth resource allocation schemes; and a selection module for selecting, from the multiple adjusted initial bandwidth resource allocation schemes, an adjusted initial resource allocation scheme whose fitness meets a first preset condition as a target bandwidth resource allocation scheme based on a preset fitness function, wherein the fitness function is determined according to the constraint model.

[0013] According to another aspect of an embodiment of the present invention, a non-volatile storage medium is provided. The non-volatile storage medium includes a stored program, wherein when the program is running, the device where the non-volatile storage medium is located is controlled to execute any one of the above-mentioned bandwidth resource allocation methods.

[0014] According to another aspect of an embodiment of the present invention, a computer device is provided. The computer device includes a processor, and the processor is configured to run a program. When the program is run, any one of the above-mentioned bandwidth resource allocation methods is executed.

[0015] According to yet another aspect of an embodiment of the present invention, a computer program product is provided, including a computer program. When the computer program is executed by a processor, any one of the above-mentioned bandwidth resource allocation methods is implemented.

[0016] In an embodiment of the present invention, a bandwidth resource allocation method is adopted. A constraint model for bandwidth resource allocation is set according to a target electric power business; multiple initial bandwidth resource allocation schemes are randomly generated; the multiple initial bandwidth resource allocation schemes are adjusted based on the constraint model using a coyote optimization algorithm to obtain multiple adjusted initial bandwidth resource allocation schemes; and based on a preset fitness function, an adjusted initial resource allocation scheme whose fitness meets a first preset condition is selected from the multiple adjusted initial bandwidth resource allocation schemes as a target bandwidth resource allocation scheme. The fitness function is determined based on the constraint model, thereby achieving the purpose of allocating bandwidth resources according to the needs of the electric power business itself, thereby achieving the technical effect of improving the stability of the electric power business operation, and further solving the technical problem that it is difficult to ensure the smooth operation of the electric power business due to unreasonable bandwidth resource allocation without considering the electric power business. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0018] Figure 1 A hardware structure block diagram of a computer terminal for implementing a bandwidth resource allocation method is shown;

[0019] Figure 2 is a flow chart of a bandwidth resource allocation method according to an embodiment of the present invention;

[0020] Figure 3 is an algorithm flow chart of a bandwidth resource allocation method provided according to an optional embodiment of the present invention;

[0021] Figure 4 It is a structural block diagram of a bandwidth resource allocation device provided according to an embodiment of the present invention. DETAILED DESCRIPTION

[0022] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described 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 should fall within the scope of protection of the present invention.

[0023] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. 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 necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0024] According to an embodiment of the present invention, a method embodiment of a bandwidth resource allocation method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0025] The method embodiment provided in the first embodiment of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1 FIG. 1 shows a hardware structure block diagram of a computer terminal for implementing a bandwidth resource allocation method. Figure 1As shown, the computer terminal 10 may include one or more (illustrated as 102a, 102b, ..., 102n in the figure) processors (the processor may include but is not limited to a microprocessor MCU or a programmable logic device FPGA and other processing devices), a memory 104 for storing data. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the BUS bus), a network interface, a power supply and / or a camera. It will be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components than shown, or with Figure 1 Different configurations shown.

[0026] It should be noted that the one or more processors and / or other data processing circuits described above may generally be referred to herein as "data processing circuitry." The data processing circuitry may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuitry may be a single, independent processing module, or may be incorporated in whole or in part into any of the other components of the computer terminal 10. As described in the embodiments of the present application, the data processing circuitry serves as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0027] Memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the bandwidth resource allocation method in the embodiment of the present invention. The processor executes the software programs and modules stored in memory 104 to execute various functional applications and data processing, thereby implementing the bandwidth resource allocation method for the above-mentioned application. Memory 104 may include high-speed random access memory and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, memory 104 may further include memory remotely located relative to the processor, and such remote memory may be connected to computer terminal 10 via a network. Examples of such networks include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0028] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computer terminal 10 .

[0029] Figure 2 FIG. 1 is a flow chart of a bandwidth resource allocation method according to an embodiment of the present invention. Figure 2 As shown, the method includes the following steps:

[0030] Step S202: Setting a bandwidth resource allocation constraint model according to the target power service.

[0031] In this step, a constraint model for bandwidth resource allocation can be set based on the target power business. The role of the constraint model is to limit the solution space of the problem and ensure that the resulting solution meets the specific constraints of the problem. Constraint models can be divided into two types: equality constraints and inequality constraints. By setting the constraint model based on the target power business, it can be ensured that the bandwidth resource allocation solution finally optimized based on the constraint model can meet the specific constraints, thereby ensuring that the solution is within the feasible domain and meets practical requirements. In addition to including constraints, the constraint model can also include the optimization goal of the problem, that is, the indicator for evaluating the pros and cons of a solution. Different power businesses often have different communication requirements, including priority, bandwidth, latency, reliability, etc. Therefore, by setting the constraint model based on the target power business, the bandwidth allocation solution can be customized according to the personalized needs of the power business, so as to achieve the most reasonable utilization of satellite network bandwidth resources and meet the network requirements when multiple power businesses are transmitted in parallel.

[0032] Step S204: randomly generate multiple initial bandwidth resource allocation schemes.

[0033] In this step, a random sequence generation method can be used to randomly generate multiple random sequences to serve as multiple initial bandwidth resource allocation schemes. When using a generation algorithm to generate random sequences, a constraint model can be employed to constrain the generated initial bandwidth resource allocation schemes to meet constraints, such as the total amount of allocable bandwidth resources and the minimum bandwidth resources required for each power service. The random sequence generation method can utilize a pseudo-random number generator (PNG), which can generate near-random sequences of numbers. These generators are based on deterministic algorithms, but with appropriate seed values, can produce seemingly random sequences of numbers. Common PNGs include the linear congruential generator and the Mersenne twister algorithm. Cryptographic hash functions, such as SHA-256 and MD5, can also be used to map input data into fixed-length hash values. Due to the properties of hash functions, the output hash values ​​appear random, making them suitable for use as pseudo-random number generators. Chaotic systems can also be used to generate highly unpredictable random sequences by leveraging their nonlinear dynamic characteristics.

[0034] Step S206 : Using the coyote optimization algorithm, the multiple initial bandwidth resource allocation schemes are adjusted based on the constraint model to obtain multiple adjusted initial bandwidth resource allocation schemes.

[0035] In this step, the coyote optimization algorithm can be used to adjust the parameters of multiple initial bandwidth resource allocations based on a constraint model to obtain an adjusted initial bandwidth resource allocation plan. The coyote optimization algorithm performs biomimetic optimization calculations by simulating the social activities of coyotes, such as growth, death, reproduction, and migration. The general steps of the coyote optimization algorithm are to first obtain a certain number of randomly generated individuals. Each individual represents a solution to the problem and is distributed in the solution space. In this embodiment, the individuals refer to bandwidth resource allocation plans. Then, for each individual, its fitness value is calculated based on the solution it represents. The fitness value reflects the quality of the solution, that is, the rationality of the bandwidth resource allocation plan. A leader and followers are then determined based on the individual's fitness value. The individual with the best fitness value is selected as the leader, while individuals with poor fitness values ​​are selected as followers. The position of each individual in the population is updated based on the positions of the leader and followers and the constraint model. This step is based on the social behavior of gray wolves. The leader gray wolf leads and influences other members of the group. The selection of leaders and followers and the updating of solutions are repeated until a stopping condition is met. When the stopping condition is met, the optimal solution or a near-optimal solution is output. The coyote optimization algorithm uses a unique mechanism to balance the exploration and development process in the algorithm, and has excellent global optimization performance.

[0036] Step S208 : Based on a preset fitness function, an adjusted initial bandwidth resource allocation scheme whose fitness meets a first preset condition is selected from multiple adjusted initial bandwidth resource allocation schemes as a target bandwidth resource allocation scheme, wherein the fitness function is determined according to a constraint model.

[0037] In this step, the fitness of each of the multiple adjusted initial bandwidth resource allocation schemes can be determined based on the fitness function. The fitness value can be used to evaluate the rationality of the bandwidth resource allocation scheme. The bandwidth resource allocation scheme whose fitness meets the preset conditions, that is, the bandwidth resource allocation scheme with the highest fitness, can be used as the target bandwidth resource allocation scheme. The fitness function can be set based on the constraints, because the constraint model includes not only the constraints but also the objective function, which can be used as an indicator to evaluate the quality of the allocation scheme. Therefore, the fitness function can be set based on the objective function in the constraint model. Selecting the bandwidth resource allocation method with the highest fitness as the target bandwidth resource allocation method can more reasonably and efficiently allocate bandwidth resources for the power service, improve the bandwidth resource utilization of the satellite network, and maximize the reliable transmission of power service data.

[0038] Through the above steps, the purpose of allocating bandwidth resources according to the needs of the power business itself is achieved, thereby achieving the technical effect of improving the stability of the power business operation, and further solving the technical problem that it is difficult to ensure the smooth operation of the power business due to unreasonable bandwidth resource allocation without considering the power business.

[0039] As an optional embodiment, a constraint model for bandwidth resource allocation is set according to the target power business, including: constructing a first objective function based on the data transmission time required for the target power business; constructing a second objective function based on the size of the bandwidth resources occupied by the target power business; setting constraint conditions based on the total bandwidth resources and bandwidth requirements corresponding to the target power business; and determining the constraint model based on the first objective function, the second objective function and the constraint conditions.

[0040] Optionally, setting a constraint model can first construct a first objective function based on the target power service's required data transmission time. The weighted average of the transmission times required for all data transmission services for the target power service is calculated. The lower this value, the shorter the required transmission time, indicating a more reasonable solution. A second objective function can also be constructed based on the bandwidth resources occupied by the target power service. When allocating bandwidth resources, it is important to avoid excessive bandwidth occupancy on individual links, which can lead to link congestion and increased packet queuing. Therefore, the second objective function is set to the bandwidth occupancy of a single link. Assuming other conditions are met, the lower the bandwidth occupancy of a single link, the better the solution. Constraints can also be set based on the total bandwidth resources and bandwidth requirements corresponding to the target power service. Because bandwidth allocation should not exceed the total bandwidth resources, constraints are set to ensure that the sum of the bandwidth resources allocated to the target power service does not exceed the total bandwidth resources. Furthermore, the bandwidth allocated to each power service should meet its corresponding minimum bandwidth requirement, which is essential for ensuring the normal operation of the power service.

[0041] Specifically, the power business communication scenario modeling can be carried out first, wherein the power business set is N = {1, 2, ..., N}, and the priority corresponding to each power business is Pri = {Pri1, Pri2, ..., Pri n}, the total amount of data transmitted by each power business is size = {size1, size2, ..., size n}, the minimum bandwidth requirement for each power service is Req={req1,req2,…,req n}, the set of available satellite network links is M = {1, 2, ..., M}, and the set of available bandwidths of each link is bw = {bw1, bw2, ..., bw m}, for each power business, its data can be transmitted by multiple links, and the bandwidth allocated to power business i on each link is allocation i={alloc i1 ,alloc i2 ,…,alloc im According to the target power business, the constraint model can be constructed by setting the first objective function as Among them, f1 represents the weighted average of the transmission time required for all data transmission services in the target power business, time i is the time required for the transmission of the i-th power business data, size i is the total amount of data transmitted for the i-th power business, alloc ij Pri is the bandwidth allocated to the i-th power business on the j-th link. i is the priority of the ith power business. The second objective function can also be set as f2 indicates that in the process of link bandwidth allocation, we should try to avoid excessive bandwidth usage of a single link to avoid link congestion and increased packet queuing. The smaller the values ​​of f1 and f2, the better the solution. You can also set the constraint condition req i ≤alloc ij ,1≤i≤n, this constraint means that the bandwidth allocated to the i-th power business on each link meets its minimum bandwidth requirement req i ; You can also set constraints This constraint is to constrain bandwidth resources, indicating that the bandwidth allocated to all services on the jth link does not exceed the total available bandwidth bw of the link. j ; You can also set constraints alloc ij ≥0, 1≤i≤n, 1≤j≤m. This constraint is positive, meaning the bandwidth allocated to any link must be non-negative. By mathematically modeling the network bandwidth resource allocation problem through these steps, setting optimization objectives and constraint functions, and preparing for subsequent optimization, we can better and more rationally utilize satellite network bandwidth resources to meet the needs of power services.

[0042] As an optional embodiment, randomly generating multiple initial bandwidth resource allocation schemes includes: randomly generating multiple groups of random sequences using a preset chaotic mapping function; and determining multiple initial bandwidth resource allocation schemes based on the multiple groups of random sequences.

[0043] Optionally, multiple initial bandwidth resource allocation schemes can be randomly generated by using a chaotic mapping function. For example, the Tent mapping function in the chaotic mapping function can be used to generate multiple random sequences. To generate, where is a factor, lb j and ub jRepresents the lower and upper bounds of the factor, μ t+1 is the random number generated by the Tent mapping equation, t is the number of iterations of the mapping equation, and by randomly generating multiple factors, multiple random sequences can be formed as multiple initial bandwidth resource allocation schemes. When the random sequence is used as an individual in the subsequent coyote optimization algorithm, represents the jth social status factor of the cth coyote individual in the pth population.

[0044] As an optional embodiment, a coyote optimization algorithm is used to adjust multiple initial bandwidth resource allocation schemes based on a constraint model to obtain multiple adjusted initial bandwidth resource allocation schemes, including: according to the coyote optimization algorithm, multiple coyotes are set, wherein the multiple coyotes have their own corresponding social factor sequences, and the social factor sequences corresponding to the multiple coyotes represent the multiple initial bandwidth resource allocation schemes; according to the fitness function, a coyote whose fitness meets a first preset condition among the multiple coyotes is selected as the optimal coyote; according to the constraint model and the social factor sequence corresponding to the optimal coyote, the social factor sequences corresponding to the multiple coyotes are adjusted to obtain multiple target coyotes; and according to the multiple target coyotes, multiple adjusted initial bandwidth resource allocation schemes are determined.

[0045] Alternatively, a coyote optimization algorithm can be used to adjust the initial bandwidth resource allocation plan. Multiple coyotes can be initialized, and the social factor sequences corresponding to each of these coyotes serve as the initial bandwidth resource allocation plan. The fitness of each of these coyotes can be calculated based on a fitness function, and the coyote with the highest fitness that meets a first pre-determined condition can be selected as the optimal coyote. The social factor sequences corresponding to the multiple coyotes can then be adjusted based on the constraint model and the social factor sequence corresponding to the optimal coyote, resulting in multiple target coyotes. Based on these multiple target coyotes, multiple adjusted initial bandwidth resource allocation plans can be determined.

[0046] Specifically, the fitness function can be set to in, are dimensionless normalized functions of objective functions f1 and f2 respectively; w1 and w2 are dimensionless normalized functions of objective functions The weights are constants, and con represents a constant that should be set based on the actual environment. Based on the fitness function, the optimal coyote is selected from multiple coyotes. The group cultural trend is then derived. The group cultural trend is calculated by taking the median of each social factor across all individual coyotes, sequentially generating a new sequence of social factors. Although the optimal coyote has the best fitness, during the adjustment process, it can only serve as a local optimal solution. Adjusting based solely on the optimal coyote can lead to a local optimal solution, making it difficult to obtain a high-quality solution. Therefore, the group cultural trend, derived by taking the median of social factors, reflects the evolutionary direction and trend of the subpopulation to a certain extent. This helps the entire population explore a wider range of excellent solutions from a single optimal solution, thereby avoiding over-reliance on a single optimal coyote and enhancing individual diversity. Furthermore, the optimal coyote, the group cultural trend, and two randomly selected coyotes can jointly determine the optimization trend of multiple coyotes. Using two randomly selected coyotes maintains population diversity and prevents regression into local optimal solutions. It also introduces a degree of randomness, facilitating the discovery of new solutions.

[0047] As an optional embodiment, according to the constraint model and the social factor sequence corresponding to the optimal coyote, the social factor sequences corresponding to multiple coyotes are adjusted to obtain multiple target coyotes, including: generating a social factor sequence corresponding to a coyote cub based on the social factor sequences corresponding to multiple coyotes; judging whether there is a coyote among the multiple coyotes whose fitness is lower than that of the coyote cub based on the fitness function; in the case that there is a weak coyote among the multiple coyotes whose fitness is lower than that of the coyote cub, selecting the coyotes among the weak coyotes whose fitness meets the second preset condition and deleting them; and adjusting the social factor sequences corresponding to the remaining coyotes and the social factor sequences corresponding to the coyotes cub based on the constraint model and the optimal coyote to obtain multiple target coyotes.

[0048] Alternatively, as the social factor sequences corresponding to multiple coyotes are continuously adjusted, individuals gradually become closer to each other, the diversity of the population gradually decreases, and it is easy to fall into a local optimum. Therefore, young coyotes can be introduced. Based on the social factor sequences corresponding to multiple coyotes, social factor sequences corresponding to young coyotes can be generated. Adding young coyotes can enhance the diversity of coyotes, that is, the diversity of bandwidth resource allocation schemes, increase the detection ability of the algorithm, and avoid falling into a local optimum. Specifically, to calculate the social factor sequences corresponding to young coyotes, you can first use the formula Calculate the social factor sequence alpha corresponding to the optimal coyote and the social factor sequence cult of the group culture trend and the social factor differences δ1 and δ2 of the two randomly selected coyotes cr1 and cr2, and then multiply them by two (0,1) random numbers r3 and r4 respectively and combine them with the social factor sequence soc of any coyote among multiple coyotes c Add, that is, the formula new_soc c =socc +r3×δ1+r4×δ2 to get the young coyote new_soc c . Since the coyote optimization algorithm is a continuously iterative process, the process of obtaining the young coyotes is actually the process of obtaining a new generation of allocation schemes based on the previous generation of allocation schemes. Based on the fitness function, the fitness of multiple coyotes and young coyotes is calculated. When there is a coyote with a lower fitness than the young coyote among multiple coyotes, the fitness of the coyote meets the second preset condition, that is, the lowest fitness, and the coyote dies, that is, the bandwidth resource allocation scheme corresponding to the social factor sequence corresponding to the coyote is deleted. When there are more than one coyotes with a lower fitness than the young coyote among multiple coyotes, the coyote with the worst ability can be selected to die, that is, the coyote with the lowest fitness can be selected to be deleted; the similarity of multiple coyotes can also be calculated, and the coyote with poor ability and the highest similarity can be selected to die, because the social factor sequences of the coyotes and other coyotes are highly similar and cannot constitute the diversity of coyote individuals, and cannot play a better role in the subsequent optimization process, so the coyote with poor ability and the highest similarity can be selected to die. When the fitness of multiple coyotes is higher than that of the young coyote, the young coyote dies, that is, the bandwidth resource allocation scheme of the social factor sequence corresponding to the young coyote is deleted. Among them, according to the formula To calculate the similarity between coyote c and other individuals in the subpopulation, aff(soc c ,soc j ) is the Euclidean distance between the social factor sequences of coyote c and coyote j, that is, the similarity between coyote c and coyote j, where N c is the number of coyotes in the subpopulation where coyote c is located. Determining the coyotes to be eliminated based on similarity better ensures the diversity of individuals in the population, thereby obtaining a bandwidth resource allocation method that is more in line with the needs of power business.

[0049] As an optional embodiment, a coyote optimization algorithm is used to adjust multiple initial bandwidth resource allocation schemes based on a constraint model to obtain multiple adjusted initial bandwidth resource allocation schemes, including: according to the coyote optimization algorithm, multiple coyotes are set, wherein the multiple coyotes have their own corresponding social factor sequences, and the social factor sequences corresponding to the multiple coyotes represent the multiple initial bandwidth resource allocation schemes; the multiple coyotes are randomly divided into multiple subpopulations; based on the constraint model, the social factor sequences corresponding to the coyotes in the multiple subpopulations are adjusted respectively, and multiple iterative adjustments are performed to obtain multiple target subpopulations; and multiple adjusted initial bandwidth resource allocation schemes are determined based on the coyotes corresponding to the multiple target subpopulations.

[0050] Optionally, in the coyote optimization algorithm, after setting up multiple coyotes, these coyotes can be divided into multiple subpopulations. Subpopulations are a unique mechanism in the coyote optimization algorithm that simulates the social structure of coyotes in nature. In solving the optimization strategy, the subpopulation mechanism is believed to enable subpopulation-based local search and information exchange between subpopulations. Each subpopulation is considered an independent search unit, capable of conducting local searches within a specific region of the solution space. Furthermore, interaction between subpopulations promotes information sharing, helping the algorithm escape local optima and discover the global optimal solution. This enables quasi-parallel search and significantly improves the algorithm's solution efficiency when solving large-scale optimization problems. Based on a constraint model, the corresponding social factor sequences of multiple subpopulations can be adjusted. After multiple iterative adjustments, a target subpopulation can be obtained, which includes multiple adjusted coyotes. Based on these multiple target subpopulations, multiple adjusted initial bandwidth resource allocation schemes can be determined. Specifically, within multiple subpopulations, the optimal coyote for each subpopulation can be selected based on a fitness function. Then, within each subpopulation, the corresponding social factor sequence of the coyotes can be adjusted based on the optimal coyote and group cultural trends. Similarly, within each subpopulation, individual coyotes can be generated, and the fitness function can be used to determine whether to retain the young coyotes and eliminate the existing coyotes.

[0051] As an optional embodiment, based on the constraint model, the social factor sequences corresponding to the coyotes of multiple sub-populations are adjusted respectively, and multiple iterative adjustments are performed to obtain multiple target sub-populations, including: obtaining the current number of iterations; determining the target probability based on the current number of iterations; based on the target probability, exchanging coyotes between the multiple sub-populations to obtain multiple new sub-populations; based on the constraint model, adjusting the social factor sequences corresponding to the coyotes in the multiple new sub-populations respectively to obtain multiple adjusted new sub-populations; based on the above method of obtaining multiple adjusted new sub-populations, performing multiple iterative adjustments to obtain multiple target sub-populations.

[0052] Optionally, the social factor sequences corresponding to the coyotes in each of the multiple subpopulations can be adjusted through multiple iterations. During each iteration, the number of iterations can be obtained, and a target probability can be determined based on the number of iterations. Based on the target probability, coyotes are then swapped between the multiple subpopulations to generate multiple new subpopulations. Then, based on the constraint model, the social factor sequences corresponding to the coyotes in each of the multiple new subpopulations are adjusted to generate multiple adjusted new subpopulations. Swapping coyotes among the multiple subpopulations can increase the diversity of individuals within the different subpopulations. Because the algorithm focuses on global exploration in the early stages, more information sharing between populations is required. However, in the later stages, the algorithm focuses more on optimal solution discovery, requiring less information exchange between subpopulations. The expulsion acceptance probability (target probability) is dynamically calculated based on the number of algorithm iterations, allowing the algorithm to balance global exploration and local development. The introduction of the expulsion acceptance probability ensures information exchange between subpopulations. By introducing coyotes from other populations, subpopulations can adjust their evolutionary direction in a timely manner, preventing them from falling into unfavorable ranges and wasting computing resources, thereby expanding the search range and ensuring search efficiency. Without the expulsion and acceptance mechanism, the algorithm may stagnate near the optimal solution found in the early stage. The expulsion mechanism ensures the continuous evolution of the algorithm and prevents it from falling into the local optimal solution. Specifically, the formula can be used Calculate the expulsion acceptance probability (target probability) P e , where t is the current iteration number, T is the maximum iteration number, and N c is the number of coyotes in the subpopulation. According to the expulsion acceptance probability (target probability) P e The algorithm determines whether to swap coyotes within a subpopulation. A higher probability indicates a higher likelihood of exchange. When the maximum number of iterations is reached, the algorithm stops and selects the social factor sequence of the coyotes with the best fitness within the entire population. This determines the optimal or suboptimal satellite bandwidth resource allocation strategy, thereby achieving dynamic allocation of satellite bandwidth. This approach results in a more rational bandwidth resource allocation method.

[0053] Figure 3 is an algorithm flow chart of a bandwidth resource allocation method according to an optional embodiment of the present invention, such as Figure 3As shown, the satellite bandwidth allocation problem for the electric power business scenario is first modeled. The solution space, objective function, and constraints are determined. A fitness function is set based on the objective function. Then, a tent mapping is used to initialize the coyote population. The population is then grown, updated, and migrated through a loop. Finally, the solution with the highest fitness is selected as the target bandwidth resource allocation solution. Through these steps, the diverse needs of different electric power businesses are comprehensively considered. An improved coyote optimization algorithm is employed, incorporating a coyote individual similarity factor to improve the coyote growth process. This effectively increases the individual diversity of the subpopulation and prevents the algorithm from falling into a local optimum. This improves the quality of the resulting bandwidth resource allocation method. Furthermore, the birth and death rules for young coyotes are improved. Instead of using age to determine culling, a similarity factor, which better reflects individual diversity, is used to select culled coyotes, thereby better ensuring individual diversity within the population. Furthermore, a dynamic coyote migration probability (target probability) is introduced to improve the algorithm's convergence efficiency, resulting in a more optimized bandwidth allocation strategy. This ensures the smooth operation of electric power businesses through a more rational and efficient bandwidth resource allocation method.

[0054] It should be noted that for the aforementioned method embodiments, for simplicity of description, they are all expressed as a series of action combinations. However, those skilled in the art should be aware that the present invention is not limited by the order of the actions described, because according to the present invention, 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 this specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0055] Through the description of the above embodiments, those skilled in the art will clearly understand that the bandwidth resource allocation method according to the above embodiments can be implemented using software plus the necessary general-purpose hardware platform. Of course, it can also be implemented through hardware, but in many cases the former is a more preferred embodiment. Based on this understanding, the technical solution of the present invention, or the part that contributes to the existing technology, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, or optical disk) and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in various embodiments of the present invention.

[0056] According to an embodiment of the present invention, a bandwidth resource allocation device for implementing the above-mentioned bandwidth resource allocation method is also provided. Figure 4 is a structural block diagram of a bandwidth resource allocation device provided according to an embodiment of the present invention. Figure 4As shown, the bandwidth resource allocation device includes: a setting module 42, a generating module 44, an adjusting module 46 and a selecting module 48. The bandwidth resource allocation device is described below.

[0057] The setting module 42 is used to set a constraint model for bandwidth resource allocation according to the target power business.

[0058] The generating module 44 is connected to the setting module 42 and is used to randomly generate a plurality of initial bandwidth resource allocation schemes.

[0059] The adjustment module 46 is connected to the generation module 44 and is configured to use the coyote optimization algorithm to adjust the multiple initial bandwidth resource allocation schemes based on the constraint model to obtain multiple adjusted initial bandwidth resource allocation schemes.

[0060] The selection module 48 is connected to the adjustment module 46 and is used to select an adjusted initial bandwidth resource allocation scheme whose fitness meets the first preset condition from multiple adjusted initial bandwidth resource allocation schemes as the target bandwidth resource allocation scheme based on a preset fitness function, wherein the fitness function is determined according to the constraint model.

[0061] It should be noted that the above-mentioned setting module 42, generation module 44, adjustment module 46, and selection module 48 correspond to steps S202 to S208 in the embodiment. The examples and application scenarios implemented by the various modules and the corresponding steps are the same, but are not limited to the contents disclosed in the above embodiment. It should be noted that the above-mentioned modules, as part of the device, can be run in the computer terminal 10 provided in the embodiment.

[0062] An embodiment of the present invention may provide a computer device. Optionally, in this embodiment, the computer device may be located in at least one of a plurality of network devices in a computer network. The computer device includes a memory and a processor.

[0063] The memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the bandwidth resource allocation method and device in the embodiments of the present invention. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, thereby implementing the above-mentioned bandwidth resource allocation method. The memory may include a high-speed random access memory and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include a memory remotely located relative to the processor, and these remote memories may be connected to the computer terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0064] The processor can call information and applications stored in the memory through the transmission device to perform the following steps: setting a constraint model for bandwidth resource allocation based on a target power business; randomly generating multiple initial bandwidth resource allocation plans; using a coyote optimization algorithm to adjust the multiple initial bandwidth resource allocation plans based on the constraint model to obtain multiple adjusted initial bandwidth resource allocation plans; and based on a preset fitness function, selecting an adjusted initial resource allocation plan whose fitness meets a first preset condition from the multiple adjusted initial bandwidth resource allocation plans as a target bandwidth resource allocation plan, wherein the fitness function is determined according to the constraint model.

[0065] Optionally, the processor may also execute the program code of the following steps: setting a constraint model for bandwidth resource allocation according to the target power business, including: constructing a first objective function based on the data transmission time required for the target power business; constructing a second objective function based on the size of the bandwidth resources occupied by the target power business; setting constraint conditions based on the total bandwidth resources and bandwidth requirements corresponding to the target power business; and determining the constraint model according to the first objective function, the second objective function and the constraint conditions.

[0066] Optionally, the processor may further execute program code of the following steps: randomly generating multiple initial bandwidth resource allocation schemes, including: randomly generating multiple groups of random sequences using a preset chaotic mapping function; and determining multiple initial bandwidth resource allocation schemes based on the multiple groups of random sequences.

[0067] Optionally, the processor may also execute program code for the following steps: using a coyote optimization algorithm, adjusting multiple initial bandwidth resource allocation schemes based on a constraint model to obtain multiple adjusted initial bandwidth resource allocation schemes, including: according to the coyote optimization algorithm, setting multiple coyotes, wherein each of the multiple coyotes has its own corresponding social factor sequence, and the social factor sequence corresponding to each of the multiple coyotes represents multiple initial bandwidth resource allocation schemes; according to the fitness function, selecting a coyote whose fitness meets a first preset condition among the multiple coyotes as the optimal coyote; according to the constraint model and the social factor sequence corresponding to the optimal coyote, adjusting the social factor sequences corresponding to the multiple coyotes to obtain multiple target coyotes; and determining multiple adjusted initial bandwidth resource allocation schemes based on the multiple target coyotes.

[0068] Optionally, the processor may also execute the program code for the following steps: adjusting the social factor sequences corresponding to multiple coyotes according to the constraint model and the social factor sequence corresponding to the optimal coyote to obtain multiple target coyotes, including: generating a social factor sequence corresponding to a coyote cub based on the social factor sequences corresponding to multiple coyotes; judging, based on the fitness function, whether there are coyotes among the multiple coyotes whose fitness is lower than that of the coyotes cubs; in the case where there are weak coyotes among the multiple coyotes whose fitness is lower than that of the coyotes cubs, selecting the coyotes among the weak coyotes whose fitness meets the second preset condition and deleting them; adjusting the social factor sequences corresponding to the remaining coyotes and the social factor sequences corresponding to the coyotes cubs based on the constraint model and the optimal coyote to obtain multiple target coyotes.

[0069] Optionally, the processor may also execute program code for the following steps: using a coyote optimization algorithm, adjusting multiple initial bandwidth resource allocation schemes based on a constraint model to obtain multiple adjusted initial bandwidth resource allocation schemes, including: setting multiple coyotes according to the coyote optimization algorithm, wherein the multiple coyotes have their own corresponding social factor sequences, and the social factor sequences corresponding to the multiple coyotes represent the multiple initial bandwidth resource allocation schemes; randomly dividing the multiple coyotes into multiple subpopulations; based on the constraint model, adjusting the social factor sequences corresponding to the coyotes corresponding to the multiple subpopulations respectively, performing multiple iterative adjustments to obtain multiple target subpopulations; and determining multiple adjusted initial bandwidth resource allocation schemes according to the coyotes corresponding to the multiple target subpopulations.

[0070] Optionally, the processor may also execute the program code for the following steps: based on the constraint model, adjusting the social factor sequences corresponding to the coyotes of each of the multiple subpopulations, performing multiple iterative adjustments to obtain multiple target subpopulations, including: obtaining the current number of iterations; determining the target probability based on the current number of iterations; based on the target probability, exchanging coyotes between the multiple subpopulations to obtain multiple new subpopulations; based on the constraint model, adjusting the social factor sequences corresponding to the coyotes of each of the multiple new subpopulations to obtain multiple adjusted new subpopulations; performing multiple iterative adjustments based on the above method of obtaining multiple adjusted new subpopulations to obtain multiple target subpopulations.

[0071] An embodiment of the present invention provides a bandwidth resource allocation method. The method includes setting a bandwidth resource allocation constraint model according to a target electric power business; randomly generating multiple initial bandwidth resource allocation schemes; using a coyote optimization algorithm to adjust the multiple initial bandwidth resource allocation schemes based on the constraint model to obtain multiple adjusted initial bandwidth resource allocation schemes; and selecting, based on a preset fitness function, an adjusted initial resource allocation scheme whose fitness meets a first preset condition from the multiple adjusted initial bandwidth resource allocation schemes as a target bandwidth resource allocation scheme. The fitness function is determined according to the constraint model, thereby achieving the purpose of allocating bandwidth resources according to the needs of the electric power business itself, thereby achieving the technical effect of improving the stability of the electric power business operation, and further solving the technical problem that it is difficult to ensure the smooth operation of the electric power business due to unreasonable bandwidth resource allocation without considering the electric power business.

[0072] A person skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the hardware related to the terminal device through a program, and the program can be stored in a non-volatile storage medium, which may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0073] The embodiment of the present invention further provides a non-volatile storage medium. Optionally, in this embodiment, the non-volatile storage medium can be used to store the program code executed by the bandwidth resource allocation method provided in the embodiment.

[0074] Optionally, in this embodiment, the non-volatile storage medium may be located in any computer terminal in a computer terminal group in a computer network, or in any mobile terminal in a mobile terminal group.

[0075] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for executing the following steps: setting a constraint model for bandwidth resource allocation based on a target power business; randomly generating multiple initial bandwidth resource allocation schemes; using a coyote optimization algorithm to adjust the multiple initial bandwidth resource allocation schemes based on the constraint model to obtain multiple adjusted initial bandwidth resource allocation schemes; based on a preset fitness function, selecting an adjusted initial resource allocation scheme whose fitness meets a first preset condition from the multiple adjusted initial bandwidth resource allocation schemes as the target bandwidth resource allocation scheme, wherein the fitness function is determined according to the constraint model.

[0076] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for executing the following steps: setting a constraint model for bandwidth resource allocation based on the target power business, including: constructing a first objective function based on the data transmission time required for the target power business; constructing a second objective function based on the size of the bandwidth resources occupied by the target power business; setting constraint conditions based on the total bandwidth resources and bandwidth requirements corresponding to the target power business; and determining the constraint model based on the first objective function, the second objective function and the constraint conditions.

[0077] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for executing the following steps: randomly generating multiple initial bandwidth resource allocation schemes, including: randomly generating multiple groups of random sequences using a preset chaotic mapping function; and determining multiple initial bandwidth resource allocation schemes based on the multiple groups of random sequences.

[0078] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for executing the following steps: using the coyote optimization algorithm, adjusting multiple initial bandwidth resource allocation schemes based on the constraint model to obtain multiple adjusted initial bandwidth resource allocation schemes, including: according to the coyote optimization algorithm, setting multiple coyotes, wherein the multiple coyotes have their own corresponding social factor sequences, and the social factor sequences corresponding to the multiple coyotes represent multiple initial bandwidth resource allocation schemes; according to the fitness function, selecting the coyote whose fitness meets the first preset condition among the multiple coyotes as the optimal coyote; according to the constraint model and the social factor sequence corresponding to the optimal coyote, adjusting the social factor sequences corresponding to the multiple coyotes to obtain multiple target coyotes; and determining multiple adjusted initial bandwidth resource allocation schemes based on the multiple target coyotes.

[0079] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for executing the following steps: adjusting the social factor sequences corresponding to multiple coyotes according to the constraint model and the social factor sequence corresponding to the optimal coyote to obtain multiple target coyotes, including: generating a social factor sequence corresponding to a coyote cub based on the social factor sequences corresponding to multiple coyotes; judging whether there are coyotes among the multiple coyotes whose fitness is lower than that of the coyotes cubs based on the fitness function; in the case that there are weak coyotes among the multiple coyotes whose fitness is lower than that of the coyotes cubs, selecting the coyotes among the weak coyotes whose fitness meets the second preset condition for deletion; adjusting the social factor sequences corresponding to the remaining coyotes and the social factor sequences corresponding to the coyotes cubs based on the constraint model and the optimal coyote to obtain multiple target coyotes.

[0080] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for executing the following steps: using a coyote optimization algorithm, adjusting multiple initial bandwidth resource allocation schemes based on a constraint model to obtain multiple adjusted initial bandwidth resource allocation schemes, including: according to the coyote optimization algorithm, setting multiple coyotes, wherein the multiple coyotes have their own corresponding social factor sequences, and the social factor sequences corresponding to the multiple coyotes represent the multiple initial bandwidth resource allocation schemes; randomly dividing the multiple coyotes into multiple sub-populations; based on the constraint model, adjusting the social factor sequences corresponding to the coyotes corresponding to each of the multiple sub-populations, performing multiple iterative adjustments, and obtaining multiple target sub-populations; and determining multiple adjusted initial bandwidth resource allocation schemes based on the coyotes corresponding to each of the multiple target sub-populations.

[0081] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for executing the following steps: based on the constraint model, adjusting the social factor sequences corresponding to the coyotes corresponding to each of the multiple subpopulations, performing multiple iterative adjustments, and obtaining multiple target subpopulations, including: obtaining the current number of iterations; based on the current number of iterations, determining the target probability; based on the target probability, exchanging coyotes between the multiple subpopulations to obtain multiple new subpopulations; based on the constraint model, adjusting the social factor sequences corresponding to the coyotes corresponding to each of the multiple new subpopulations to obtain multiple adjusted new subpopulations; based on the above method of obtaining multiple adjusted new subpopulations, performing multiple iterative adjustments to obtain multiple target subpopulations.

[0082] An embodiment of the present invention further provides a computer program product, comprising a computer program. Optionally, in this embodiment, when the computer program is executed by a processor, the following can be achieved: setting a constraint model for bandwidth resource allocation according to a target power business; randomly generating multiple initial bandwidth resource allocation schemes; using a coyote optimization algorithm to adjust the multiple initial bandwidth resource allocation schemes based on the constraint model to obtain multiple adjusted initial bandwidth resource allocation schemes; and based on a preset fitness function, selecting, from the multiple adjusted initial bandwidth resource allocation schemes, an adjusted initial resource allocation scheme whose fitness meets a first preset condition as a target bandwidth resource allocation scheme, wherein the fitness function is determined according to the constraint model.

[0083] The serial numbers of the above embodiments of the present invention are for description only and do not represent the advantages or disadvantages of the embodiments.

[0084] In the above embodiments of the present invention, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0085] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only exemplary. For example, the division of the units can be a logical function division. In actual implementation, there may be other division methods, 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 interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0086] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0087] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0088] 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 non-volatile storage medium. Based on this understanding, the technical solution of the present invention, 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. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk, and other media that can store program code.

[0089] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as within the scope of protection of the present invention.

Claims

1. A bandwidth resource allocation method, characterized in that: include: Set up a constraint model for bandwidth resource allocation based on target power business; Randomly generate multiple initial bandwidth resource allocation schemes; Adopting a coyote optimization algorithm to adjust the multiple initial bandwidth resource allocation schemes based on the constraint model to obtain multiple adjusted initial bandwidth resource allocation schemes; Based on a preset fitness function, selecting an adjusted initial bandwidth resource allocation scheme whose fitness meets a first preset condition from the multiple adjusted initial bandwidth resource allocation schemes as a target bandwidth resource allocation scheme, wherein the fitness function is determined according to the constraint model; The constraint model for bandwidth resource allocation is set according to the target power business, including: constructing a power business set, a priority set corresponding to each power business, a total amount of data transmitted by each power business, a minimum bandwidth requirement set for each power business, a bandwidth set for each satellite network link, and a bandwidth set allocated to each power business by each satellite network link; based on the data transmission time required by the target power business, constructing a first objective function as follows: Wherein, f1 represents the weighted average of the transmission time required for all data transmission services in the target power business, time i is the time required for the transmission of the i-th power business data, size i is the total amount of data transmitted by the ith power business in the total amount of data transmitted by each power business, alloc ij The bandwidth allocated to the i-th power business by the j-th satellite network link in the bandwidth set allocated to each power business by each satellite network link, Pri i is the priority of the i-th power business in the priority set corresponding to each power business; based on the size of the bandwidth resources occupied by the target power business, the second objective function is constructed as where bw j is the jth satellite network link bandwidth in each satellite network link bandwidth set, f2 represents the bandwidth occupancy rate of a single link in the link bandwidth allocation process; based on the total bandwidth resources and bandwidth requirements corresponding to the target power business, the constraint condition is set as req i ≤alloc ij 1≤i≤n, indicating that the bandwidth allocated to the i-th power service by each satellite network link meets the minimum bandwidth requirement of the i-th power service, where req i is the minimum bandwidth requirement of the ith power business in the minimum bandwidth requirement set of each power business; or the constraint condition for constraining bandwidth resources is set as The bandwidth allocated to each power service by the j-th satellite network link does not exceed the bandwidth of the j-th satellite network link; or the constraint condition for constraining the bandwidth allocated by the satellite network link to be a non-negative number is set as alloc ij ≥0, 1≤i≤n, 1≤j≤m; determining the constraint model according to the first objective function, the second objective function and the constraint condition; The method adopts the coyote optimization algorithm to adjust the multiple initial bandwidth resource allocation schemes based on the constraint model to obtain multiple adjusted initial bandwidth resource allocation schemes, including: setting multiple coyotes according to the coyote optimization algorithm, wherein the multiple coyotes have their own corresponding social factor sequences, and the social factor sequences corresponding to the multiple coyotes represent the multiple initial bandwidth resource allocation schemes; according to the fitness function, selecting the coyote whose fitness meets the first preset condition from the multiple coyotes as the optimal coyote, wherein the fitness function is are dimensionless normalized functions of the first objective function f1 and the second objective function f2; w1 and w2 are dimensionless normalized functions , con is a constant; according to the constraint model and the social factor sequence corresponding to the optimal coyote, the social factor sequences corresponding to the multiple coyotes are adjusted to obtain multiple target coyotes; according to the multiple target coyotes, the multiple adjusted initial bandwidth resource allocation schemes are determined.

2. The method according to claim 1, characterized in that The randomly generating multiple initial bandwidth resource allocation schemes includes: Using the preset chaotic mapping function, multiple groups of random sequences are randomly generated; The multiple initial bandwidth resource allocation schemes are determined based on the multiple groups of random sequences.

3. The method according to claim 1, characterized in that The step of adjusting the social factor sequences corresponding to the plurality of coyotes according to the constraint model and the social factor sequence corresponding to the optimal coyote to obtain a plurality of target coyotes includes: generating a social factor sequence corresponding to a young coyote based on the social factor sequences corresponding to the plurality of coyotes; Based on the fitness function, determining whether there is a coyote among the plurality of coyotes whose fitness is lower than the fitness of the young coyote; In the case where there is a weak coyote among the plurality of coyotes whose fitness is lower than that of the young coyote, selecting a coyote among the weak coyotes whose fitness meets a second preset condition and deleting it; Based on the constraint model and the optimal coyote, the social factor sequences corresponding to the remaining coyotes and the social factor sequences corresponding to the young coyotes are adjusted to obtain the multiple target coyotes.

4. The method according to claim 1, wherein The coyote optimization algorithm is used to adjust the multiple initial bandwidth resource allocation schemes based on the constraint model to obtain multiple adjusted initial bandwidth resource allocation schemes, including: According to the coyote optimization algorithm, a plurality of coyotes are set, wherein each of the plurality of coyotes has a corresponding social factor sequence, and the social factor sequence corresponding to each of the plurality of coyotes represents the plurality of initial bandwidth resource allocation schemes; randomly dividing the plurality of coyotes into a plurality of subpopulations; Based on the constraint model, adjusting the social factor sequences corresponding to the coyotes in the multiple subpopulations respectively, performing multiple iterative adjustments, and obtaining multiple target subpopulations; The multiple adjusted initial bandwidth resource allocation schemes are determined according to the coyotes corresponding to the multiple target subpopulations.

5. The method according to claim 4, characterized in that Based on the constraint model, the social factor sequences corresponding to the coyotes in the multiple subpopulations are adjusted respectively, and multiple iterative adjustments are performed to obtain multiple target subpopulations, including: Get the current iteration number; Determining a target probability based on the current number of iterations; Based on the target probability, coyote swapping is performed among the plurality of subpopulations to obtain a plurality of new subpopulations; Based on the constraint model, adjusting the social factor sequences corresponding to the coyotes in the multiple new subpopulations respectively to obtain multiple adjusted new subpopulations; Based on the above method for obtaining multiple adjusted new subpopulations, multiple iterative adjustments are performed to obtain the multiple target subpopulations.

6. A bandwidth resource allocation device, characterized in that: include: A setting module, used to set a constraint model for bandwidth resource allocation according to target power business; A generation module, used for randomly generating multiple initial bandwidth resource allocation schemes; an adjustment module, configured to use a coyote optimization algorithm to adjust the multiple initial bandwidth resource allocation schemes based on the constraint model to obtain multiple adjusted initial bandwidth resource allocation schemes; a selection module configured to select, from the plurality of adjusted initial bandwidth resource allocation schemes, an adjusted initial resource allocation scheme whose fitness meets a first preset condition as a target bandwidth resource allocation scheme based on a preset fitness function, wherein the fitness function is determined according to the constraint model; The setting module is further used to construct a set of power services, a set of priorities corresponding to each power service, a set of total data transmitted by each power service, a set of minimum bandwidth requirements for each power service, a set of bandwidths of each satellite network link, and a set of bandwidths allocated to each power service by each satellite network link; based on the data transmission time required by the target power service, a first objective function is constructed as follows: Wherein, f1 represents the weighted average of the transmission time required for all data transmission services in the target power business, time i is the time required for the transmission of the i-th power business data, size i is the total amount of data transmitted by the ith power business in the total amount of data transmitted by each power business, alloc ij The bandwidth allocated to the i-th power business by the j-th satellite network link in the bandwidth set allocated to each power business by each satellite network link, Pri i is the priority of the i-th power business in the priority set corresponding to each power business; based on the size of the bandwidth resources occupied by the target power business, the second objective function is constructed as where bw j is the jth satellite network link bandwidth in each satellite network link bandwidth set, f2 represents the bandwidth occupancy rate of a single link in the link bandwidth allocation process; based on the total bandwidth resources and bandwidth requirements corresponding to the target power business, the constraint condition is set as req i ≤alloc ij , 1≤i≤n, indicating that the bandwidth allocated to the i-th power service by each satellite network link meets the minimum bandwidth requirement of the i-th power service, where req i is the minimum bandwidth requirement of the ith power business in the minimum bandwidth requirement set of each power business; or the constraint condition for constraining bandwidth resources is set as The bandwidth allocated to each power service by the j-th satellite network link does not exceed the bandwidth of the j-th satellite network link; or the constraint condition for constraining the bandwidth allocated by the satellite network link to be a non-negative number is set as alloc ij ≥0, 1≤i≤n, 1≤j≤m; determining the constraint model according to the first objective function, the second objective function and the constraint condition; The adjustment module is further configured to set a plurality of coyotes according to the coyote optimization algorithm, wherein the plurality of coyotes each have a corresponding social factor sequence, and the social factor sequence corresponding to each of the plurality of coyotes represents the plurality of initial bandwidth resource allocation schemes; and according to the fitness function, select the coyote whose fitness satisfies the first preset condition from the plurality of coyotes as the optimal coyote, wherein the fitness function is are dimensionless normalized functions of the first objective function f1 and the second objective function f2; w1 and w2 are dimensionless normalized functions , con is a constant; according to the constraint model and the social factor sequence corresponding to the optimal coyote, the social factor sequences corresponding to the multiple coyotes are adjusted to obtain multiple target coyotes; according to the multiple target coyotes, the multiple adjusted initial bandwidth resource allocation schemes are determined.

7. A non-volatile storage medium, characterized in that: The non-volatile storage medium includes a stored program, wherein when the program is running, the device where the non-volatile storage medium is located is controlled to execute the bandwidth resource allocation method according to any one of claims 1 to 5.

8. A computer device, characterized in that: include: memory and processor, The memory stores a computer program; The processor is configured to execute a computer program stored in the memory, and when the computer program is run, the processor is enabled to execute the bandwidth resource allocation method according to any one of claims 1 to 5.

9. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the bandwidth resource allocation method according to any one of claims 1 to 5 is implemented.

Images