Resource configuration method and apparatus for 5g mobile communication system

Abstract

This invention discloses a resource allocation method and apparatus for a 5G mobile communication system. The method includes: obtaining an objective function and constraint parameters, wherein the objective function aims to minimize the carbon emissions of the 5G mobile communication system, the 5G mobile communication system includes multiple base stations, each base station corresponding to at least one cell, and the constraint parameters include the amount of electricity purchased from the grid by each cell, the amount of renewable energy shared by each cell, the subcarrier allocation of each cell, the power allocation of each cell, and the base station status of each base station, including a dormant state and an active state; solving the objective function and constraint parameters using a two-step method to obtain a target configuration scheme for the 5G mobile communication system, the target configuration scheme including a base station dormant scheme for multiple base stations and a subcarrier allocation scheme for each cell; and configuring the resources of the 5G mobile communication system based on the target configuration scheme. It is evident that implementing this invention can reduce the carbon emissions of the 5G mobile communication system.

Description

Technical Field

[0001] This invention relates to the field of mobile communication technology, and in particular to a resource allocation method and apparatus for a 5G mobile communication system. Background Technology

[0002] Mobile communication is a modern technology for wireless communication, and it is one of the important achievements of the development of electronic computers and the mobile Internet. After the development of first-generation, second-generation, third-generation, and fourth-generation technologies, mobile communication technology has now entered the era of fifth-generation development (5G mobile communication technology), which is one of the major technologies that are changing the world.

[0003] However, the power consumption of 5G mobile communication systems is several times that of 4G communication systems, resulting in relatively high carbon emissions. Therefore, there is an urgent need for a solution to reduce the carbon emissions of 5G mobile communication systems. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to provide a resource allocation method and apparatus for a 5G mobile communication system, which can reduce the carbon emissions of the 5G mobile communication system.

[0005] The first aspect of this invention discloses a resource allocation method for a 5G mobile communication system, the method comprising:

[0006] Obtain the objective function and constraint parameters. The objective function aims to minimize the carbon emissions of the 5G mobile communication system. The 5G mobile communication system includes multiple base stations, each base station corresponding to at least one cell. The constraint parameters include the electricity purchased from the grid by each cell, the amount of renewable energy shared by each cell, the subcarrier allocation of each cell, the power allocation of each cell, and the base station status of each base station, including dormant state and active state.

[0007] The objective function and the constraint parameters are solved by a two-step method to obtain the target configuration scheme of the 5G mobile communication system. The target configuration scheme includes the base station dormancy scheme of multiple base stations and the subcarrier allocation scheme of each cell.

[0008] The resources of the 5G mobile communication system are configured based on the target configuration scheme.

[0009] As an optional implementation, in the first aspect of the present invention, the electricity purchased from the grid by each cell, the amount of renewable energy shared by each cell, and the power allocation of each cell are continuous variables, while the subcarrier allocation and base station sleep of each cell are discrete variables.

[0010] Here, Xij represents whether the i-th subcarrier is allocated to the j-th user. The variable Xij is encoded with 0 and 1. Xij = 1 means that it is allocated to the user, and otherwise Xij = 0. Yi represents the state of the i-th base station. Yi = 0 means that the base station is turned off and in a dormant state, and Yi = 1 means that the base station is in a working state.

[0011] As an optional implementation, in the first aspect of the present invention, the step of solving the objective function and the constraint parameters using a two-step method to obtain the target configuration scheme of the 5G mobile communication system includes:

[0012] A target allocation scheme is determined, which includes a subcarrier allocation scheme for each cell and a base station status scheme for each base station;

[0013] Each of the target allocation schemes is treated as an individual in the evolutionary algorithm. The electricity purchased from the grid by each cell, the renewable energy sharing amount of each cell, and the power allocation scheme of each cell are determined by KKT conditions.

[0014] A set of schemes is used as an initial population. The initial population is processed to obtain the final generation population. The set of schemes includes the target allocation scheme, the electricity purchased from the grid by each cell corresponding to the target allocation scheme, the renewable energy sharing amount of each cell corresponding to the target allocation scheme, and the power allocation scheme of each cell corresponding to each target allocation scheme.

[0015] The target configuration scheme of the 5G mobile communication system is determined based on the last generation of the population.

[0016] As an optional implementation, in the first aspect of the invention, the step of performing calculations on the initial population to obtain the final generation population includes:

[0017] Individual selection is performed on each generation of the population to obtain a second individual, and evolutionary deduction is performed on the second individual to obtain the corresponding next generation of the population.

[0018] The filtering process includes:

[0019] Determine the generation value of each individual in the contemporary population;

[0020] Based on the generation value of each individual, L first individuals are selected from the current population, wherein the generation value of any one of the L first individuals is not less than that of any non-first individuals in the current population.

[0021] The foreground region is determined based on L of the first individuals;

[0022] Some or all of the individuals in the foreground region are used as the second individual.

[0023] As an optional implementation, in the first aspect of the invention, determining the generation value of each individual in the current population includes:

[0024] The cost value of each entity is determined by a preset cost function;

[0025] The preset cost function includes:

[0026]

[0027]

[0028] Among them, CV ij Represents individual f i By another individual f j The cost of substitution, where m represents the number of targets, and N * This refers to an individual within the current population.

[0029] As an optional implementation, in the first aspect of the invention, the step of using some or all of the individuals in the foreground region as the second individual includes:

[0030] Determine whether the number of individuals in the region is greater than the size of the current population;

[0031] If the number of individuals in the region is less than the size of the current population, all individuals in the region shall be considered as the second individual;

[0032] If the number of individuals in a given region is greater than the size of the current population, individuals in that region are removed until the number of individuals in the removed region is equal to the size of the current population, and the remaining individuals in that region are taken as the second individuals.

[0033] As an optional implementation, in the first aspect of the present invention, the process of removing individuals from the region includes:

[0034] Normalize each of the aforementioned regions to a region.

[0035] The region Each individual target in each region is projected onto the hyperplane f1+...+fm=1, where m represents the number of targets;

[0036] Determine the Euclidean distance between any two individuals in the region on the hyperplane;

[0037] Based on the Euclidean distance between any two regions, the individuals in the region are eliminated, wherein the region with the lowest cost value among the two regions corresponding to the smallest Euclidean distance is eliminated.

[0038] Determine whether the number of individuals in the region after the removal process is consistent with the size of the current population;

[0039] If the number of individuals in the region after the removal process is consistent with the size of the current population, then the individuals in the region after the removal process will be regarded as the second individuals;

[0040] If the number of regional individuals after the removal process is greater than the size of the current population, then the operation of removing regional individuals based on the Euclidean distance between any two regional individuals in the hyperplane is re-executed.

[0041] Secondly, this invention discloses a resource allocation device for a 5G mobile communication system, the device comprising:

[0042] An acquisition module is used to acquire an objective function and constraint parameters. The objective function aims to minimize the carbon emissions of a 5G mobile communication system. The 5G mobile communication system includes multiple base stations, each base station corresponding to at least one cell. The constraint parameters include the amount of electricity purchased from the grid by each cell, the amount of renewable energy shared by each cell, the subcarrier allocation of each cell, the power allocation of each cell, and the base station status of each base station. The base station status includes a dormant state and an active state.

[0043] The solution module is used to solve the objective function and the constraint parameters in a two-step method to obtain the target configuration scheme of the 5G mobile communication system. The target configuration scheme includes the base station sleep scheme of multiple base stations and the subcarrier allocation scheme of each cell.

[0044] The configuration module is used to configure the resources of the 5G mobile communication system based on the target configuration scheme.

[0045] As an optional implementation, in the second aspect of the present invention, the electricity purchased from the grid by each cell, the amount of renewable energy shared by each cell, and the power allocation of each cell are continuous variables, while the subcarrier allocation and base station sleep of each cell are discrete variables.

[0046] Here, Xij represents whether the i-th subcarrier is allocated to the j-th user. The variable Xij is encoded with 0 and 1. Xij = 1 means that it is allocated to the user, and otherwise Xij = 0. Yi represents the state of the i-th base station. Yi = 0 means that the base station is turned off and in a dormant state, and Yi = 1 means that the base station is in a working state.

[0047] As an optional implementation, in a second aspect of the invention, the solving module includes:

[0048] The first scheme determination unit is used to determine the target allocation scheme, which includes the subcarrier allocation scheme for each cell and the base station status scheme for each base station.

[0049] The second scheme determination unit is used to treat each of the target allocation schemes as an individual of the evolutionary algorithm, and determine the electricity purchased from the grid by each cell corresponding to each target allocation scheme, the renewable energy sharing amount of each cell corresponding to each target allocation scheme, and the power allocation scheme of each cell corresponding to each target allocation scheme through KKT conditions.

[0050] The solution unit is used to take a set of schemes as an initial population, perform calculations on the initial population to obtain a final generation population. The set of schemes includes the target allocation scheme, the electricity purchased from the grid by each cell corresponding to the target allocation scheme, the renewable energy sharing amount of each cell corresponding to the target allocation scheme, and the power allocation scheme of each cell corresponding to each target allocation scheme; and determines the target configuration scheme of the 5G mobile communication system based on the final generation population.

[0051] As an optional implementation, in the second aspect of the present invention, the solving unit is used to perform individual screening in each generation of the population to obtain a second individual, and to perform evolutionary deduction through the second individual to obtain the corresponding next generation of the population.

[0052] The solution unit includes:

[0053] The generation value determination subunit is used to determine the generation value of each individual in the current population;

[0054] A screening subunit is used to select L first individuals from the current population based on the generation value of each individual, wherein the generation value of any one of the L first individuals is not less than that of any non-first individuals in the current population.

[0055] A foreground region determination subunit is used to determine the foreground region based on L of the first individuals;

[0056] Individual determination sub-units are used to select some or all of the individuals in the foreground region as the second individual.

[0057] As an optional implementation, in a second aspect of the present invention, the cost value determination subunit is used to determine the cost value of each individual through a preset cost function;

[0058] The preset cost function includes:

[0059]

[0060]

[0061] Among them, CV ij Represents individual f i By another individual f j The cost of substitution, where m represents the number of targets, and N * This refers to an individual within the current population.

[0062] As an optional implementation, in a second aspect of the invention, the individual determination subunit is used to determine whether the number of individuals in the region is greater than the size of the current population;

[0063] If the number of individuals in the region is less than the size of the current population, all individuals in the region shall be considered as the second individual;

[0064] If the number of individuals in a given region is greater than the size of the current population, individuals in that region are removed until the number of individuals in the removed region is equal to the size of the current population, and the remaining individuals in that region are taken as the second individuals.

[0065] As an optional implementation, in a second aspect of the invention, an individual determination subunit is used to normalize each of the said region individuals to a region.

[0066] The region Each individual target in each region is projected onto the hyperplane f1+...+fm=1, where m represents the number of targets;

[0067] Determine the Euclidean distance between any two individuals in the region on the hyperplane;

[0068] Based on the Euclidean distance between any two regions, the individuals in the region are eliminated, wherein the region with the lowest cost value among the two regions corresponding to the smallest Euclidean distance is eliminated.

[0069] Determine whether the number of individuals in the region after the removal process is consistent with the size of the current population;

[0070] If the number of individuals in the region after the removal process is consistent with the size of the current population, then the individuals in the region after the removal process will be regarded as the second individuals;

[0071] If the number of regional individuals after the removal process is greater than the size of the current population, then the operation of removing regional individuals based on the Euclidean distance between any two regional individuals in the hyperplane is re-executed.

[0072] A third aspect of the present invention discloses another resource allocation device for a 5G mobile communication system, the device comprising:

[0073] Memory containing executable program code;

[0074] A processor coupled to the memory;

[0075] The processor calls the executable program code stored in the memory to execute the resource allocation method of the 5G mobile communication system disclosed in the first aspect of the present invention.

[0076] The fourth aspect of the present invention discloses a computer-storable medium storing computer instructions, which, when invoked, are used to execute the resource allocation method for the 5G mobile communication system disclosed in the first aspect of the present invention.

[0077] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0078] The technical solution of this invention obtains an objective function and constraint parameters. The objective function aims to minimize the carbon emissions of a 5G mobile communication system. The 5G mobile communication system includes multiple base stations, each corresponding to at least one cell. The constraint parameters include the amount of electricity purchased from the grid by each cell, the amount of renewable energy shared by each cell, the subcarrier allocation of each cell, the power allocation of each cell, and the base station status of each base station, including a dormant state and an active state. A two-step method is used to solve the objective function and the constraint parameters to obtain a target configuration scheme for the 5G mobile communication system. The target configuration scheme includes a base station dormant scheme for the multiple base stations and a subcarrier allocation scheme for each cell. Based on the target configuration scheme, the resources of the 5G mobile communication system are configured. Since the target configuration scheme aims to minimize the carbon emissions of the 5G mobile communication system, the obtained target configuration scheme is also determined with the goal of minimizing carbon emissions. Therefore, configuring the resources of the 5G mobile communication system based on this target configuration scheme can reduce the carbon emissions of the 5G mobile communication system. Thus, this invention can reduce the carbon emissions of a 5G mobile communication system. Attached Figure Description

[0079] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0080] Figure 1 This is a flowchart illustrating a resource allocation method for a 5G mobile communication system disclosed in an embodiment of the present invention;

[0081] Figure 2 This is a schematic diagram of the structure of a resource allocation device for a 5G mobile communication system disclosed in an embodiment of the present invention;

[0082] Figure 3 This is a schematic diagram of the structure of another resource allocation device for a 5G mobile communication system disclosed in an embodiment of the present invention. Detailed Implementation

[0083] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0084] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, apparatus, product, or end that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or ends.

[0085] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0086] This invention discloses a resource allocation method and apparatus for a 5G mobile communication system, which can reduce the computing power of solving multi-objective models and improve the efficiency of solving multi-objective models.

[0087] Example 1

[0088] Please see Figure 1 , Figure 1 This is a flowchart illustrating a resource allocation method for a 5G mobile communication system disclosed in an embodiment of the present invention. Figure 1 The resource allocation method for a 5G mobile communication system described herein can be applied to a resource allocation device for a 5G mobile communication system, and this embodiment of the invention is not limited thereto. For example... Figure 1 As shown, the resource configuration method of this 5G mobile communication system may include the following steps 110-130:

[0089] Step 110: Obtain the objective function and constraint parameters. The objective function aims to minimize the carbon emissions of the 5G mobile communication system. The 5G mobile communication system includes multiple base stations, each base station corresponding to at least one cell. The constraint parameters include the electricity purchased from the grid by each cell, the renewable energy sharing amount of each cell, the subcarrier allocation of each cell, the power allocation of each cell, and the base station status of each base station. The base station status includes a dormant state and an active state.

[0090] The electricity purchased by a residential community from the grid can be the amount of electricity that the community purchases from the grid each month, which can be used to represent the community's actual electricity consumption. The renewable energy sharing amount for each community can be the amount of renewable energy electricity shared between communities.

[0091] Step 120: Solve the objective function and the constraint parameters using a two-step method to obtain the target configuration scheme of the 5G mobile communication system. The target configuration scheme includes the base station sleep scheme of multiple base stations and the subcarrier allocation scheme of each cell.

[0092] In this embodiment, the base station sleep mode scheme is used to indicate which base stations are in operation and which are in sleep mode, that is, to indicate which base stations need to sleep and which base stations need to be in operation. The subcarrier allocation scheme for each cell indicates how the cell allocates subcarriers, that is, which subcarrier is allocated to which user terminal.

[0093] Step 130: Configure the resources of the 5G mobile communication system based on the target configuration scheme.

[0094] In this embodiment, the target configuration scheme specifically includes a base station sleep scheme for multiple base stations and a subcarrier allocation scheme for each cell. The base station sleep scheme allows for the control of base stations that need to sleep to enter sleep mode, and the control of base stations that need to operate to operate. Simultaneously, the subcarriers allocated to user terminals are controlled according to the cell's subcarrier allocation scheme, thereby minimizing the carbon emissions of the 5G mobile communication system.

[0095] The technical solution of this embodiment obtains an objective function and constraint parameters. The objective function aims to minimize the carbon emissions of a 5G mobile communication system. The 5G mobile communication system includes multiple base stations, each corresponding to at least one cell. The constraint parameters include the electricity purchased from the grid by each cell, the renewable energy sharing amount of each cell, the subcarrier allocation of each cell, the power allocation of each cell, and the base station status of each base station, including dormant and active states. A two-step method is used to solve the objective function and the constraint parameters to obtain a target configuration scheme for the 5G mobile communication system. The target configuration scheme includes a base station dormant scheme for the multiple base stations and a subcarrier allocation scheme for each cell. Based on the target configuration scheme, the resources of the 5G mobile communication system are configured. Since the target configuration scheme aims to minimize the carbon emissions of the 5G mobile communication system, the obtained target configuration scheme is also determined with the goal of minimizing carbon emissions. Therefore, configuring the resources of the 5G mobile system based on this target configuration scheme can reduce the carbon emissions of the 5G mobile communication system. Thus, this embodiment can reduce the carbon emissions of the 5G mobile communication system.

[0096] In one embodiment, the electricity purchased from the grid by each cell, the amount of renewable energy shared by each cell, and the power allocation of each cell are continuous variables, while the subcarrier allocation and base station sleep of each cell are discrete variables.

[0097] Here, Xij represents whether the i-th subcarrier is allocated to the j-th user. The variable Xij is encoded with 0 and 1. Xij = 1 means that it is allocated to the user, and otherwise Xij = 0. Yi represents the state of the i-th base station. Yi = 0 means that the base station is turned off and in a dormant state, and Yi = 1 means that the base station is in a working state.

[0098] Specifically, the modeling process fully explores the inherent connections between inter-cell renewable energy cooperation, base station sleep strategies, and high-efficiency wireless resource allocation. Taking inter-cell renewable energy cooperation as the starting point, the model is built by combining base station sleep strategies and high-efficiency wireless resource allocation technologies. To highlight the concept of green communication, the objective function is to minimize the carbon emissions of each cell, with constraints including the throughput of each cell, the amount of electricity purchased from the grid by each cell, the amount of renewable energy shared, subcarrier power allocation, channel allocation, and base station sleep strategies. Due to the introduction of the energy cooperation mechanism, the carbon emissions of each cell are conflicting, and a large number of cells are considered simultaneously; therefore, this model is a constrained high-dimensional multi-objective optimization problem. In the model, the amount of renewable energy shared by a cell is represented by a continuous variable, which can be positive or negative. When the renewable energy shared amount of a cell is positive, it indicates that the cell is sharing its collected renewable energy with other cells; when the renewable energy shared amount of a cell is negative, it indicates that the cell is using renewable energy collected by other cells for its own use. The base station sleep strategy is represented by a 0-1 variable; 0 indicates that the base station is off, and 1 indicates that the base station is active. The decision to put a base station into sleep mode is based on the difference between cell revenue and traditional energy consumption. A high-efficiency wireless resource allocation technique is introduced within each cell, using continuous and discrete variables to represent power allocation and subcarrier allocation, respectively. The cell's energy utilization rate is represented by the ratio of transmission rate to total power consumption. The transmission rate and energy utilization rate of each cell are calculated based on power allocation and subcarrier allocation, ensuring that both are not less than pre-set constraints. Clearly, the constructed model contains both continuous and discrete variables, constituting a high-dimensional multi-objective mixed-integer programming problem.

[0099] Since the electricity purchased by each community's power grid, the amount of renewable energy shared by the community, and power allocation are continuous variables, these variables do not need to be encoded. The encoding approach for discrete variables is as follows: Let Xi represent whether the i-th subcarrier is allocated to the j-th user. The variable Xij is encoded using 0 and 1, where Xij = 1 represents allocation to a user, and Xij = 0 otherwise. Yi represents the state of the i-th base station; Yi = 0 indicates the base station is off and in a dormant state, and Yi = 1 indicates the base station is in an active state. For any subcarrier i, the cross-slot interference values ​​generated by two adjacent cells using different uplink and downlink time slot configurations are different, and different combinations can be represented using natural numbers. After hybridization and mutation operations, the resulting code, according to a pre-agreed correspondence, can decode the subcarrier allocation and base station dormant state.

[0100] In one possible implementation, the step of solving the objective function and the constraint parameters in a two-step method to obtain the target configuration scheme of the 5G mobile communication system includes:

[0101] A target allocation scheme is determined, which includes a subcarrier allocation scheme for each cell and a base station status scheme for each base station;

[0102] Each of the target allocation schemes is treated as an individual in the evolutionary algorithm. The electricity purchased from the grid by each cell, the renewable energy sharing amount of each cell, and the power allocation scheme of each cell are determined by KKT conditions.

[0103] A set of schemes is used as an initial population. The initial population is processed to obtain the final generation population. The set of schemes includes the target allocation scheme, the electricity purchased from the grid by each cell corresponding to the target allocation scheme, the renewable energy sharing amount of each cell corresponding to the target allocation scheme, and the power allocation scheme of each cell corresponding to each target allocation scheme.

[0104] The target configuration scheme of the 5G mobile communication system is determined based on the last generation of the population.

[0105] In this embodiment, the last generation of the population can be used as the target configuration scheme for the 5G mobile communication system.

[0106] KKT conditions apply to general optimization problems with equality and inequality constraints. Specifically, a two-step approach is used to reduce problem complexity. First, the subcarrier allocation scheme and base station sleep state strategy are determined according to certain rules. At this point, the problem can be transformed into nonlinear programming, and the objective function and constraints are differentiable. The subcarrier and base station sleep state schemes are treated as individuals in an evolutionary algorithm. The KKT conditions in nonlinear programming are used to calculate the corresponding grid purchase amount, renewable energy sharing amount, and power allocation scheme for each cell under each allocation scheme. Thus, a set of allocation schemes constitutes a population of evolutionary algorithms. This population is then subjected to crossover and mutation operations. While optimizing the grid purchase amount, renewable energy sharing amount, and power allocation for each cell, adjustments are made to the subcarrier allocation and base station sleep state. This ensures that the optimization process of grid purchase amount, renewable energy sharing amount, and power allocation for each cell can utilize information from the carrier allocation and base station sleep state optimizations, and conversely, the optimization process of carrier allocation and base station sleep state can utilize information from power allocation optimizations. The optimization information between these two types of variables can interact, which improves the solution accuracy and computational efficiency of the two-step method. Moreover, by utilizing the KKT conditions in optimization theory, the search space of the problem can be compressed, effectively handling mixed programming problems and greatly improving the convergence speed of the algorithm.

[0107] In one possible implementation, operations are performed on the initial population to obtain the final generation population, including:

[0108] Individual selection is performed on each generation of the population to obtain a second individual, and evolutionary deduction is performed on the second individual to obtain the corresponding next generation of the population.

[0109] The filtering process includes:

[0110] Determine the generation value of each individual in the contemporary population;

[0111] Based on the generation value of each individual, L first individuals are selected from the current population, wherein the generation value of any one of the L first individuals is not less than that of any non-first individuals in the current population.

[0112] The foreground region is determined based on L of the first individuals;

[0113] Some or all of the individuals in the foreground region are used as the second individual.

[0114] In this embodiment, each individual in the current population needs to have a generation value determined. The first individual is different from the non-first individuals. In this embodiment, the first individuals and the non-first individuals constitute all individuals in the current population. Specifically, L is less than the total number of all non-dominant individuals in the current population. L can be half the total number of all non-dominant individuals. Specifically, individuals can be sorted according to their generation values, and half the total number of all non-dominant individuals is selected as the first individual in this embodiment based on their generation values ​​from high to low. Since the foreground region is determined based on L first individuals, and the generation value of any first individual is not less than that of the non-first individuals in the current population, the determined foreground region also represents the region enclosed by individuals with higher generation values. Therefore, individuals in the foreground region can be considered valuable individuals, and individuals outside the foreground region can be considered worthless individuals.

[0115] In this embodiment, the technical solution selects L first individuals from the current population based on their generation value. Since L is less than the total number of all non-dominant individuals in the current population, the generation value of the regional individuals in the foreground region determined by the L first individuals will be relatively large. Individuals with lower generation values ​​will find it more difficult to enter the foreground region and will be eliminated. This embodiment can use fewer individuals to deduce the next generation population, which can reduce the computing power required for solving the problem and improve the efficiency of solving the problem.

[0116] In one possible implementation, determining the generation value of each individual in the contemporary population includes:

[0117] The cost value of each entity is determined by a preset cost function;

[0118] The preset cost function includes:

[0119]

[0120]

[0121] Among them, CV ij Represents individual f i By another individual f j The cost of substitution, where m represents the number of targets, and N * This refers to an individual within the current population.

[0122] Specifically, in this embodiment, high-dimensional multi-objective optimization suffers from the curse of dimensionality, leading to a situation where the vast majority of the population and its offspring are non-dominated solutions, thus weakening the algorithm's convergence. To improve the algorithm's convergence performance, this embodiment defines a cost function:

[0123]

[0124] Based on the above definition, individual, f i The cost function relative to the entire candidate set F can be defined as follows:

[0125]

[0126] Taking two objectives as an example, suppose there are six non-dominated individuals f(x1) = (0.35, 40), f(x2) = (0.5, 18), f(x3) = (0.8, 15), f(x4) = (1, 8), f(x5) = (2, 2), and f(x6) = (4, 19). According to the aforementioned formula (1) for the value of sacrifice, the values ​​of these six individuals can be calculated as 10 / 7, 8 / 5, 6 / 5, 15 / 8, 2, and 20 / 19, respectively. By gradually eliminating the individual with the smallest value, we know that the individuals with the largest value of sacrifice are x2, x4, and x5. These three individuals can form a region that we call a promising region. The value of sacrifice of an individual itself has a certain convergence and dispersion. Directly using it is not conducive to obtaining high-quality next-generation individuals. By using the above method to determine the promising region, many non-dominated individuals with only one small objective and other large objective values ​​can be eliminated, which can strengthen the selection pressure of the algorithm.

[0127] In one possible implementation, some or all of the individuals in the foreground region are used as the second individual, including:

[0128] Determine whether the number of individuals in the region is greater than the size of the current population;

[0129] If the number of individuals in the region is less than the size of the current population, all individuals in the region shall be considered as the second individual;

[0130] If the number of individuals in a given region is greater than the size of the current population, individuals in that region are removed until the number of individuals in the removed region is equal to the size of the current population, and the remaining individuals in that region are taken as the second individuals.

[0131] In this embodiment, it is determined whether the number of individuals in the region is greater than the number of individuals in the current population. If the number of individuals in the region is greater than the number of individuals in the current population, the individuals in the region are removed until the number of individuals in the region after removal is the same as the number of individuals in the current population. The removed individuals in the region are then used as the second individuals. In other words, by further reducing the number of individuals used for inference when the number of individuals in the region is greater than the number of individuals in the current population, the computational power can be further reduced and the efficiency improved. Furthermore, by using the individuals in the region as the second individuals when the number of individuals in the region is less than the number of individuals in the current population, the validity of the solution can be guaranteed, while minimizing the impact on the computational power of the solution.

[0132] In one possible implementation, the process of removing individuals from the region includes:

[0133] Normalize each of the aforementioned regions to a region.

[0134] The region Each individual target in each region is projected onto the hyperplane f1+...+fm=1, where m represents the number of targets;

[0135] Determine the Euclidean distance between any two individuals in the region on the hyperplane;

[0136] Based on the Euclidean distance between any two regions, the individuals in the region are eliminated, wherein the region with the lowest cost value among the two regions corresponding to the smallest Euclidean distance is eliminated.

[0137] Determine whether the number of individuals in the region after the removal process is consistent with the size of the current population;

[0138] If the number of individuals in the region after the removal process is consistent with the size of the current population, then the individuals in the region after the removal process will be regarded as the second individuals;

[0139] If the number of regional individuals after the removal process is greater than the size of the current population, then the operation of removing regional individuals based on the Euclidean distance between any two regional individuals in the hyperplane is re-executed.

[0140] The Euclidean metric (also known as Euclidean distance) is a commonly used definition of distance, referring to the true distance between two points in m-dimensional space, or the natural length of a vector (i.e., the distance from that point to the origin). In two-dimensional and three-dimensional space, the Euclidean distance is simply the actual distance between two points. In this embodiment, when the number of individuals in a region is greater than the population size, promising regions are normalized to regions. In this way, the range of variation for each individual in each region is between 0 and 1, thereby controlling the variation within the region. Individuals in the region are vertically projected onto the hyperplane f1+...+fm=1, thereby eliminating individuals in the region on the hyperplane.

[0141] For example, calculate the Euclidean distance between any two regional individuals in f(x1) = (0.35, 40), f(x2) = (0.5, 18), f(x3) = (0.8, 15), f(x4) = (1, 8), f(x5) = (2, 2), and f(x6) = (4, 19) on the hyperplane. Since the closest distance between points projected onto f1 + f2 = 1 is d12, which is the distance between f(x2) and f(x3), and the cost of f(x2) is greater than that of f(x3), in this example, if the number of regional individuals is greater than the number of the current population, then f(x2) needs to be removed.

[0142] In this embodiment, normalization to a specific region helps eliminate dimensional differences between different targets. Since the normalization method uses indices, the algorithm exhibits good stability. Furthermore, because the shape of the foreground interface is unknown beforehand, complex foreground interfaces may be discontinuous, with some parts being convex upwards and others downwards, among other possibilities. In this case, all regions with foreground are projected onto the hyperplane f1 + ... + fm = 1, and all individuals within the foreground region are projected onto the hyperplane. The Euclidean distances between these projections are calculated, and the two individuals with the closest projection distances are selected, while individuals with lower cost values ​​are deleted. Clearly, this selection strategy exhibits uniformity. Moreover, this strategy is a non-defective choice for all situations, thus enabling the solution to possess good robustness.

[0143] Example 2

[0144] Please see Figure 2 , Figure 2 This is a schematic diagram of the structure of a resource allocation device for a 5G mobile communication system disclosed in an embodiment of the present invention. Figure 2 As shown, the resource configuration device of the 5G mobile communication system may include an acquisition module 210, a solution module 220, and a configuration module 230, wherein:

[0145] The acquisition module 210 is used to acquire the objective function and constraint parameters. The objective function aims to minimize the carbon emissions of the 5G mobile communication system. The 5G mobile communication system includes multiple base stations, each base station corresponding to at least one cell. The constraint parameters include the electricity purchased from the grid by each cell, the amount of renewable energy shared by each cell, the subcarrier allocation of each cell, the power allocation of each cell, and the base station status of each base station. The base station status includes a dormant state and an active state.

[0146] The solution module 220 is used to solve the objective function and the constraint parameters in a two-step method to obtain the target configuration scheme of the 5G mobile communication system. The target configuration scheme includes the base station sleep scheme of multiple base stations and the subcarrier allocation scheme of each cell.

[0147] The configuration module 230 is used to configure the resources of the 5G mobile communication system based on the target configuration scheme.

[0148] In one embodiment, the electricity purchased from the grid by each cell, the amount of renewable energy shared by each cell, and the power allocation of each cell are continuous variables, while the subcarrier allocation and base station sleep of each cell are discrete variables.

[0149] Here, Xij represents whether the i-th subcarrier is allocated to the j-th user. The variable Xij is encoded with 0 and 1. Xij = 1 means that it is allocated to the user, and otherwise Xij = 0. Yi represents the state of the i-th base station. Yi = 0 means that the base station is turned off and in a dormant state, and Yi = 1 means that the base station is in a working state.

[0150] In one embodiment, the solving module 220 includes:

[0151] The first scheme determination unit is used to determine the target allocation scheme, which includes the subcarrier allocation scheme for each cell and the base station status scheme for each base station.

[0152] The second scheme determination unit is used to treat each of the target allocation schemes as an individual of the evolutionary algorithm, and determine the electricity purchased from the grid by each cell corresponding to each target allocation scheme, the renewable energy sharing amount of each cell corresponding to each target allocation scheme, and the power allocation scheme of each cell corresponding to each target allocation scheme through KKT conditions.

[0153] The solution unit is used to take a set of schemes as an initial population, perform calculations on the initial population to obtain a final generation population. The set of schemes includes the target allocation scheme, the electricity purchased from the grid by each cell corresponding to the target allocation scheme, the renewable energy sharing amount of each cell corresponding to the target allocation scheme, and the power allocation scheme of each cell corresponding to each target allocation scheme; and determines the target configuration scheme of the 5G mobile communication system based on the final generation population.

[0154] In one embodiment, the solving unit is used to perform individual screening in each generation of the population to obtain a second individual, and to perform evolutionary deduction through the second individual to obtain the corresponding next generation of the population.

[0155] The solution unit includes:

[0156] The generation value determination subunit is used to determine the generation value of each individual in the current population;

[0157] A screening subunit is used to select L first individuals from the current population based on the generation value of each individual, wherein the generation value of any one of the L first individuals is not less than that of any non-first individuals in the current population.

[0158] A foreground region determination subunit is used to determine the foreground region based on L of the first individuals;

[0159] Individual determination sub-units are used to select some or all of the individuals in the foreground region as the second individual.

[0160] In one embodiment, the cost value determination subunit is used to determine the cost value of each individual through a preset cost function;

[0161] The preset cost function includes:

[0162]

[0163]

[0164] Among them, CV ij Represents individual f i By another individual f j The cost of substitution, where m represents the number of targets, and N * This refers to an individual within the current population.

[0165] In one embodiment, the individual determination subunit is used to determine whether the number of individuals in the region is greater than the size of the current population;

[0166] If the number of individuals in the region is less than the size of the current population, all individuals in the region shall be considered as the second individual;

[0167] If the number of individuals in a given region is greater than the size of the current population, individuals in that region are removed until the number of individuals in the removed region is equal to the size of the current population, and the remaining individuals in that region are taken as the second individuals.

[0168] In one embodiment, an individual determination subunit is used to normalize each of the region individuals to a region.

[0169] The region Each individual target in each region is projected onto the hyperplane f1+...+fm=1, where m represents the number of targets;

[0170] Determine the Euclidean distance between any two individuals in the region on the hyperplane;

[0171] Based on the Euclidean distance between any two regions, the individuals in the region are eliminated, wherein the region with the lowest cost value among the two regions corresponding to the smallest Euclidean distance is eliminated.

[0172] Determine whether the number of individuals in the region after the removal process is consistent with the size of the current population;

[0173] If the number of individuals in the region after the removal process is consistent with the size of the current population, then the individuals in the region after the removal process will be regarded as the second individuals;

[0174] If the number of regional individuals after the removal process is greater than the size of the current population, then the operation of removing regional individuals based on the Euclidean distance between any two regional individuals in the hyperplane is re-executed.

[0175] It is understood that the relevant content of the device in this embodiment can be referred to the relevant description of the method, and will not be repeated here.

[0176] Example 3

[0177] Please see Figure 3 , Figure 3 This is a schematic diagram of the structure of another resource allocation device for a 5G mobile communication system disclosed in an embodiment of the present invention. For example... Figure 3 As shown, the resource configuration device of the 5G mobile communication system may include:

[0178] Memory 301 storing executable program code;

[0179] Processor 302 coupled to memory 301;

[0180] The processor 302 calls the executable program code stored in the memory 301 to execute the steps in the resource configuration method of the 5G mobile communication system described in Embodiment 1 of the present invention.

[0181] Example 4

[0182] This invention discloses a computer-storable medium storing computer instructions. When these computer instructions are invoked, they are used to execute the steps in the resource configuration method of the 5G mobile communication system described in Embodiment 1 of this invention.

[0183] Example 5

[0184] This invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to perform the steps in the resource allocation method of the 5G mobile communication system described in Embodiment 1.

[0185] The device embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0186] Through the detailed description of the above embodiments, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, including read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electrically-erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0187] Finally, it should be noted that the resource allocation method and apparatus for a 5G mobile communication system disclosed in the embodiments of the present invention are merely preferred embodiments of the present invention and are only used to illustrate the technical solutions of the present invention, not to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A resource allocation method for a 5G mobile communication system, characterized in that, The method includes: Obtain the objective function and constraint parameters. The objective function aims to minimize the carbon emissions of the 5G mobile communication system. The 5G mobile communication system includes multiple base stations, each base station corresponding to at least one cell. The constraint parameters include the electricity purchased from the grid by each cell, the amount of renewable energy shared by each cell, the subcarrier allocation of each cell, the power allocation of each cell, and the base station status of each base station, including dormant state and active state. A target allocation scheme is determined, which includes a subcarrier allocation scheme for each cell and a base station status scheme for each base station; Each of the target allocation schemes is treated as an individual in the evolutionary algorithm. The electricity purchased from the grid by each cell, the renewable energy sharing amount of each cell, and the power allocation scheme of each cell are determined by KKT conditions. A set of schemes is used as an initial population. The initial population is processed to obtain the final generation population. The set of schemes includes the target allocation scheme, the electricity purchased from the grid by each cell corresponding to the target allocation scheme, the renewable energy sharing amount of each cell corresponding to the target allocation scheme, and the power allocation scheme of each cell corresponding to each target allocation scheme. The target configuration scheme of the 5G mobile communication system is determined based on the last generation population. The target configuration scheme includes the base station dormancy scheme of multiple base stations and the subcarrier allocation scheme of each cell. The resources of the 5G mobile communication system are configured based on the target configuration scheme.

2. The method according to claim 1, characterized in that, For each cell, the electricity purchased from the grid, the renewable energy sharing amount, and the power allocation are continuous variables, while the subcarrier allocation and base station sleep are discrete variables. Here, Xij represents whether the i-th subcarrier is allocated to the j-th user. The variable Xij is encoded with 0 and 1. Xij=1 means that it is allocated to the user, and otherwise Xij=0. Yi represents the state of the i-th base station. Yi=0 means that the base station is turned off and in a dormant state, and Yi=1 means that the base station is in a working state.

3. The method according to claim 1, characterized in that, The process of performing operations on the initial population to obtain the final generation population includes: Individual selection is performed on each generation of the population to obtain a second individual, and evolutionary deduction is performed on the second individual to obtain the corresponding next generation of the population. The filtering process includes: Determine the generation value of each individual in the contemporary population; Based on the generation value of each individual, L first individuals are selected from the current population, wherein the generation value of any one of the L first individuals is not less than that of any non-first individuals in the current population. The foreground region is determined based on L of the first individuals; Some or all of the individuals in the foreground region are used as the second individual.

4. The method according to claim 3, characterized in that, Determining the generation value of each individual in the current population includes: The cost value of each entity is determined by a preset cost function; The preset cost function includes: ； ； Among them, CV ij Represents individual f i By another individual f j The cost of substitution, where m represents the number of targets, and N * This refers to an individual within the current population.

5. The method according to claim 3, characterized in that, The step of using some or all of the individuals in the foreground region as the second individual includes: Determine whether the number of individuals in the region is greater than the size of the current population; If the number of individuals in the region is less than the size of the current population, all individuals in the region shall be considered as the second individual; If the number of individuals in a given region is greater than the size of the current population, individuals in that region are removed until the number of individuals in the removed region is equal to the size of the current population, and the remaining individuals in that region are taken as the second individuals.

6. The method according to claim 5, characterized in that, The process of removing individuals from the region includes: Normalize each of the aforementioned regions to a region. ; The region Each individual target in each region is projected onto the hyperplane f1+...+fm=1, where m represents the number of targets; Determine the Euclidean distance between any two individuals in the region on the hyperplane; Based on the Euclidean distance between any two regions, the individuals in the region are eliminated, wherein the region with the lowest cost value among the two regions corresponding to the smallest Euclidean distance is eliminated. Determine whether the number of individuals in the region after the removal process is consistent with the size of the current population; If the number of individuals in the region after the removal process is consistent with the size of the current population, then the individuals in the region after the removal process will be regarded as the second individuals; If the number of regional individuals after the removal process is greater than the size of the current population, then the operation of removing regional individuals based on the Euclidean distance between any two regional individuals in the hyperplane is re-executed.

7. A resource allocation device for a 5G mobile communication system, characterized in that, The device includes: An acquisition module is used to acquire an objective function and constraint parameters. The objective function aims to minimize the carbon emissions of a 5G mobile communication system. The 5G mobile communication system includes multiple base stations, each base station corresponding to at least one cell. The constraint parameters include the amount of electricity purchased from the grid by each cell, the amount of renewable energy shared by each cell, the subcarrier allocation of each cell, the power allocation of each cell, and the base station status of each base station. The base station status includes a dormant state and an active state. A solution module is used to determine a target allocation scheme, which includes a subcarrier allocation scheme for each cell and a base station state scheme for each base station. Each target allocation scheme is treated as an individual in an evolutionary algorithm, and KKT conditions are used to determine the electricity purchase from the grid, the renewable energy sharing amount for each cell, and the power allocation scheme for each cell corresponding to each target allocation scheme. A set of schemes is used as an initial population, and calculations are performed on the initial population to obtain a final generation population. The set of schemes includes the target allocation scheme, the electricity purchase from the grid for each cell corresponding to the target allocation scheme, the renewable energy sharing amount for each cell, and the power allocation scheme for each cell. Based on the final generation population, a target configuration scheme for the 5G mobile communication system is determined, which includes base station dormancy schemes for multiple base stations and subcarrier allocation schemes for each cell. The configuration module is used to configure the resources of the 5G mobile communication system based on the target configuration scheme.

8. A resource allocation device for a 5G mobile communication system, characterized in that, The device includes: Memory containing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the resource configuration method of the 5G mobile communication system as described in any one of claims 1-6.

9. A computer storage medium, characterized in that, The computer storage medium stores computer instructions, which, when invoked, are used to execute the resource configuration method of the 5G mobile communication system as described in any one of claims 1-6.

Images