Topological structure design method of indoor distributed antenna system and related equipment

Abstract

The embodiment of the invention discloses a topological structure design method of an indoor distributed antenna system and related equipment. The method comprises the following steps: generating a parent population according to device parameters, building parameters and signal source information; obtaining N weight vectors and a neighborhood of each weight vector, and associating the nth weight vector with the nth parent individual; according to the weight vector associated with each parent individual in the parent population and the neighborhood thereof, performing crossover variation processing on the parent individuals in the parent population to generate a filial population; obtaining selection indexes of each parent individual and each child individual, wherein each parent individual and each child individual correspond to an interlayer network structure of the indoor distributed antenna system; on the basis of the selection indexes of the filial generation individuals and the selection indexes of the parent individuals in the neighborhood of the weight vectors associated with the corresponding filial generation individuals, updating the parent population by adopting the filial generation population; and determining a target interlayer network structure of the indoor distributed antenna system according to the updated parent population.

Description

Technical Field

[0001] The present disclosure relates to the field of communication and computer technology, and in particular to a topology design method for an indoor distributed antenna system, a topology design device for an indoor distributed antenna system, a computer device, a computer-readable storage medium, and a computer program product. Background Art

[0002] With the continuous improvement of mobile communication demand, the number of connected devices and the scale of data transmission have shown explosive growth, and various mobile communication technologies (such as 5G (5th Generation Mobile Communication Technology, the fifth generation mobile communication technology), 5G is used as an example below, but the present disclosure is not limited to this) have emerged. 5G technology provides three application scenarios: large-scale input connection, ultra-reliable low latency, and enhanced mobile bandwidth to meet user needs. According to the report, nearly 80% of data transmission occurs in indoor scenarios. However, due to the severe attenuation of 5G high-frequency signals in terms of distance and penetration, it is difficult for outdoor base station antennas to provide indoor users with a high-quality, high-coverage communication environment. There are large differences in the coverage of 5G signals in different scenarios. For example, on outdoor urban trunk roads, the signal coverage rate can reach 90%. However, in many indoor scenarios, the signal coverage rate is less than 60%, and even in some more closed environments, such as underground parking lots and elevators, the signal coverage rate is less than 50%. Therefore, providing reliable wireless signal coverage for indoors is an important step in achieving ubiquitous 5G signal coverage. Summary of the invention

[0003] The embodiments of the present disclosure provide a topology design method for an indoor distributed antenna system, a topology design device for an indoor distributed antenna system, a computer device, a computer-readable storage medium, and a computer program product, which can provide an effective target inter-layer network structure for the indoor distributed antenna system to improve the indoor wireless signal coverage.

[0004] The embodiment of the present disclosure provides a method for designing a topology structure of an indoor distributed antenna system, the method comprising: obtaining building parameters, device parameters and signal source information; generating a parent population according to the device parameters, the building parameters and the signal source information, wherein the parent population includes N parent individuals, where N is an integer greater than 1; obtaining N weight vectors and a neighborhood of each weight vector, associating the nth weight vector with the nth parent individual, where n is an integer greater than or equal to 1 and less than or equal to N; and generating a parent population according to the weight vector associated with each parent individual in the parent population. The invention relates to a method for updating the parent population by using the child population as the control group, and a method for determining the target inter-layer network structure of the indoor distributed antenna system. The method comprises the following steps: performing crossover mutation processing on the parent individuals in the parent population to generate a child population including N child individuals; obtaining selection indicators of each parent individual and each child individual, each parent individual and each child individual corresponding to the inter-layer network structure of the indoor distributed antenna system; updating the parent population by using the child population based on the selection indicators of the child individuals and the selection indicators of the parent individuals in the neighborhood of the weight vector associated with the corresponding child individuals; and determining the target inter-layer network structure of the indoor distributed antenna system according to the updated parent population.

[0005] The embodiment of the present disclosure provides a topology design device for an indoor distributed antenna system, the device comprising: an acquisition unit, for acquiring building parameters, device parameters and signal source information; the processing unit, further for generating a parent population according to the device parameters, the building parameters and the signal source information, the parent population comprising N parent individuals, N being an integer greater than 1; the processing unit, further for obtaining N weight vectors and the neighborhood of each weight vector, associating the nth weight vector with the nth parent individual, n being an integer greater than or equal to 1 and less than or equal to N; the processing unit, further for generating a parent population according to the association of each parent individual in the parent population The weight vector and its neighborhood are used to perform crossover mutation processing on the parent individuals in the parent population to generate a child population including N child individuals; the processing unit is also used to obtain selection indicators for each parent individual and each child individual, and each parent individual and each child individual corresponds to the inter-layer network structure of the indoor distributed antenna system; the processing unit is also used to update the parent population with the child population based on the selection indicator of the child individual and the selection indicator of the parent individual in the neighborhood of the weight vector associated with the corresponding child individual; the processing unit is also used to determine the target inter-layer network structure of the indoor distributed antenna system according to the updated parent population.

[0006] An embodiment of the present disclosure provides a computer device, including a processor, a memory, and an input / output interface; the processor is connected to the memory and the input / output interface, respectively, wherein the input / output interface is used to receive and output data, the memory is used to store a computer program, and the processor is used to call the computer program so that the computer device including the processor executes the topology structure design method of the indoor distributed antenna system in any embodiment of the present disclosure.

[0007] An embodiment of the present disclosure provides a computer-readable storage medium storing a computer program, which is suitable for being loaded and executed by a processor so that a computer device having the processor executes the topology structure design method of an indoor distributed antenna system in any embodiment of the present disclosure.

[0008] The embodiments of the present disclosure provide a computer program product or a computer program, which includes a computer instruction stored in a computer-readable storage medium. A processor of a computer device reads the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the computer device executes the method provided in various optional modes in any embodiment of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0010] Figure 1 It is a schematic diagram of an indoor distributed antenna system provided by an embodiment of the present disclosure.

[0011] Figure 2 It is a schematic diagram of an inter-layer network structure using Prufer string encoding provided in the related art.

[0012] Figure 3 It is a schematic diagram of another inter-layer network structure using Prufer string encoding provided in the related art.

[0013] Figure 4 It is a schematic diagram of an inter-layer network structure using binary string encoding provided in the related art.

[0014] Figure 5 It is a flow chart of a topology structure design method of an indoor distributed antenna system provided by an embodiment of the present disclosure.

[0015] Figure 6 It is a schematic diagram of an inter-layer network structure using tree coding provided by an embodiment of the present disclosure.

[0016] Figure 7 It is a schematic diagram of a crossover operator provided by an embodiment of the present disclosure.

[0017] Figure 8 It is a schematic diagram of a mutation operator provided by an embodiment of the present disclosure.

[0018] Fig. 9 It is a schematic diagram of an inter-layer network structure obtained using relevant technologies.

[0019] Fig.10 It is a schematic diagram of an inter-layer network structure obtained by using another related technology.

[0020] Fig.11 It is a schematic diagram of an inter-layer network structure obtained by adopting the method provided by an embodiment of the present disclosure.

[0021] Fig.12 It is a schematic diagram of a topology structure design device for an indoor distributed antenna system provided in an embodiment of the present disclosure.

[0022] Fig.13 It is a network interaction architecture diagram of a topology structure design method for an indoor distributed antenna system provided in an embodiment of the present disclosure.

[0023] Fig.14 It is a structural diagram of a computer device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0024] The following will be combined with the drawings in the embodiments of the present disclosure to clearly and completely describe the technical solutions in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0025] It should be understood that the "several" mentioned in this article refers to one or more, and "multiple" refers to two or more. "And / or" describes the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the associated objects before and after are in an "or" relationship.

[0026] Indoor distributed antenna systems (IB-DAS, also referred to as indoor distributed systems, 5G indoor distributed antenna systems are used as examples below, but the present disclosure is not limited to this) are an effective method to improve signal coverage in indoor scenarios. The system connects the 5G signal from an external signal source to the indoor through devices such as coaxial cables, power dividers, couplers, etc., and transmits the signal through indoor ceiling antennas. The topological structure between the devices in the 5G IB-DAS system is directly related to the performance indicators of the system such as signal coverage range, signal coverage quality and cost. The 5G network planning software in the related technology is mainly aimed at outdoor base station distribution network planning, and rarely specifically for indoor distribution systems. 5G network planning. Deploying indoor distributed antenna systems is a key step in achieving ubiquitous wireless services.

[0027] like Figure 1 As shown, IB-DAS 100 includes an inter-floor network 110 and an intra-floor network 120. The inter-floor network 110 connects the signal source to each floor (e.g., Figure 1 In the example shown in FIG. 1 , the distributed antennas on each floor are connected by an intra-layer network 120. This architecture shortens the transmission distance and covers the dead zone, thereby providing a higher data rate in indoor scenarios. IB-DAS also has better reachability, lower bit error rate and delay spread. Figure 1 Reference numeral 130 indicates a signal access point on each floor, ie, a low-voltage room.

[0028] like Figure 1 As shown, the inter-layer network 110 of the IB-DAS includes the following components:

[0029] 1) Signal source: IB-DAS usually does not generate cellular signals, so it needs to be fed with a signal source from the outside. The signal source is one of the most critical factors in determining coverage area and capacity. The signal source can be any external signal source such as a base station, and this disclosure does not limit this.

[0030] 2) Power splitter: It divides one input signal into two or more output signals of equal power. Therefore, the power loss of all output ports of a power splitter is the same. A power splitter with n1 output ports is called an n1-way power splitter, where n1 is an integer greater than or equal to 2. In the following embodiments, a 2-way power splitter, a 3-way power splitter, a 4-way power splitter, and a 6-way power splitter are considered.

[0031] For example Figure 1 The inter-floor network 110 in the 5-floor building shown includes 3 PDs, wherein the first PD is a coupler, the second PD is a 3-way power splitter, and the third PD is a 2-way power splitter.

[0032] 3) Coupler: It divides an input signal into two output signals of unequal power. Therefore, the power loss of the two output ports of a coupler is different from that of the input port. In order to distinguish the two output ports, the port with smaller output power is called the coupled port.

[0033] 4) Coaxial cable: It connects the signal source, PD (such as couplers and power dividers) and all floors of the building. IB-DAS is divided into two types: active and passive. In the embodiment of the present disclosure, passive IB-DAS is taken as an example, and the feeder is taken as a coaxial cable, but the present disclosure is not limited to this.

[0034] In the disclosed embodiment, the interlayer network V of IB-DAS is defined as V={B,F,M}, where B represents the location of the signal source. It should be noted that the location of the signal source will affect the calculation of subsequent target values ​​(such as the first performance indicator and the second performance indicator) and the algorithm results, so it needs to be defined in advance. F represents the floor set of the building. |F| is the number of floors of the building |F|, where |F| is an integer greater than or equal to 1. M={{T r ,F r ,P r ,S r}|r=1,…,I} represents the interlayer network structure from the signal source such as the base station to all floors of the building, I represents the number of power devices in the interlayer network, i.e., the number of PDs (such as power dividers and couplers), and I represents an integer greater than or equal to 1. r ∈T represents the type of the rth PD in the interlayer network (i.e., the power device type), and r is an integer greater than or equal to 1 and less than or equal to I. T represents the candidate power device set, that is, the power device settings in the interlayer network can only be selected from T. F r ∈F represents the floor where the rth PD in the inter-layer network is located, P rRepresents the set of PDs located before the r-th PD in the inter-layer network, that is, including the PDs located before the r-th PD and directly connected to the r-th PD. r Represents the set of PDs / floors located after the r-th PD in the inter-layer network, that is, including the PDs or floors located after the r-th PD and directly connected to the r-th PD. For example, Figure 1 In the example, P3 includes the first PD, that is, only the first PD is directly connected to the third PD before the third PD. S3 includes the fourth floor and the fifth floor. In the embodiment of the present disclosure, "direct connection" means that no other components are included between the two interconnected floors.

[0035] For example, in Figure 1 On this basis, assuming that there is a fourth PD, the fourth PD has a second PD directly connected before it, and the second PD has a first PD directly connected before it, then P4 only includes the second PD but not the first PD.

[0036] In the IB-DAS studied, the method provided by the embodiment of the present disclosure can optimize the inter-layer network structure M={{T r ,F r ,P r ,S r}|r=1,…,I}, by optimizing the inter-layer network structure to achieve the purpose of optimizing multiple (two or two) objectives at the same time, the following takes the optimization of construction cost and average power loss as an example, but the present disclosure is not limited to this. Therefore, a multi-objective inter-layer network planning is expressed by the following formula:

[0037]

[0038] s T r ∈T={1,2,3,4,6},r=1,…,I (1b)

[0039] F r ∈F,r=1,…,I (1c)

[0040] Among them, 1, 2, 3, 4 and 6 in T represent a coupler, a 2-way power splitter, a 3-way power splitter, a 4-way power splitter and a 6-way power splitter respectively. r ∈T={1,2,3,4,6},r=1,…,I is used to ensure that the PD in the interlayer network structure can only be selected from T, that is, in the following example, it is set that the PD in the interlayer network structure can only be selected from T, otherwise the generated interlayer network structure is invalid. The specific setting of T can be set according to actual needs, and this disclosure does not limit this. F r∈F,r=1,…,I ensures that each PD in the inter-layer network structure can only be placed on the floors in F. Note that an n1-way power splitter must be subsequently connected to n1 PDs or floors, and a coupler must be subsequently connected to 2 PDs or floors.

[0041] In the related art, decision makers need to clearly indicate their preference for each target (the so-called preference information). By giving a preference information, a Pareto optimal solution is obtained. However, such biased information is usually difficult to determine. Different from the related art, the method provided in the embodiment of the present disclosure can generate a set of Pareto optimal solutions when preference information is not available. The main challenge in solving this problem is to effectively represent the inter-layer network structure.

[0042] Since the optimization problem in the above formula is NP-hard, some heuristic algorithms, mainly evolutionary algorithms, have been developed to find a near-optimal inter-layer network structure within a reasonable computational budget. The main difference between these algorithms lies in the representation of the inter-layer network structure. The representations in related technologies include Prufer string encoding and binary string encoding. Next, the characteristics of these two encodings are analyzed.

[0043] 1) Prufer string encoding. It uses a string of length (|F|-2) to represent the inter-layer network structure. Figure 2 and Figure 3 All are inter-layer network structures of 6-story buildings using Prufer string encoding. Figure 2 An inter-layer network structure 200 is shown, whose Prufer string is [2 1 3 3]. Figure 3 The inter-layer network structure 300 is shown, and its Prufer string is [23 3 3]. It can be seen that although the two network structures are different, Figure 2 The inter-layer network structure 200 shown uses two 3-way power splitters and one 2-way power splitter. Figure 3 The interlayer network structure 300 shown uses a 3-way power splitter and a 4-way power splitter, but their Prufer strings are very similar. This means that the Prufer string encoding lacks the basic properties of locality and heredity. Therefore, it is difficult for the offspring solution (i.e., the offspring individual) to combine the characteristics of its parent solution (i.e., the parent individual).

[0044] 2) Binary string encoding. It uses a binary string of length (2|F|-1) to represent the inter-layer network structure. When an element in the binary string is 1, it indicates the start of a new set of floors in the inter-layer network structure. Similar to index encoding, this encoding may also produce invalid inter-layer network structures. For example, the binary string [1 0 0 0 0 1 10 0] corresponds to Figure 4 Invalid inter-layer network structure, where a 5-way power splitter is required to connect the 1st and 5th floors, but this is not provided in T.

[0045] Please refer to Figure 5 , which shows a flow chart of a method for designing a topology structure of an indoor distributed antenna system provided by an exemplary embodiment of the present disclosure. The method can be executed by a computer device running an application, for example, the computer device can be a terminal device, and optionally, each step in the solution shown in the embodiment of the present disclosure can be executed by an application running in the terminal device.

[0046] Figure 5 1 is a flow chart of a method for designing a topology structure of an indoor distributed antenna system provided by an embodiment of the present disclosure. Figure 5 As shown, the method provided by the embodiment of the present disclosure may include the following steps.

[0047] In S510, building parameters, device parameters and signal source information are obtained.

[0048] In the embodiment of the present disclosure, the building parameter refers to any information related to the building where the indoor distributed antenna system is deployed. For example, it may include at least one of the set of floors F of the building, the number of floors |F|, the floor height h of each floor, etc. |F| is an integer greater than or equal to 1. h is a real number greater than 0.

[0049] In the disclosed embodiment, the device parameter refers to any relevant information about power devices and feeders set in the interlayer network of the indoor distributed system. For example, it may include at least one of the power device type (e.g., power splitter or coupler, if it is a power splitter, how many power splitters), the number of output ports of the power device, the price of the power device, the power loss of the power device (e.g., the attenuation coefficient of the power device), the candidate power device set, the feeder type (e.g., coaxial cable), the feeder length (e.g., coaxial cable length), the power loss of the feeder (e.g., the attenuation coefficient of the feeder), the feeder price (e.g., the coaxial cable price), etc.

[0050] In the embodiment of the present disclosure, the signal source information may include any information related to the signal source of the indoor distributed antenna system, such as at least one of the type of signal source, the location of the signal source, the connection relationship between the signal source and the power device and the coaxial cable, etc.

[0051] In S520, a parent population is generated according to the device parameters, the building parameters and the signal source information, wherein the parent population includes N parent individuals, where N is an integer greater than 1.

[0052] In the embodiment of the present disclosure, setting N parent individuals is equivalent to decomposing the above multi-objective optimization problem into N sub-problems, and N can be set according to actual needs, for example, N=100. The larger the N setting, the better the optimization effect, and the smaller the N setting, the smaller the required calculation amount. N is set to 100, which can achieve a good balance between the optimization effect and the calculation amount, but the present disclosure is not limited to this.

[0053] In an exemplary embodiment, a parent population is generated according to the device parameters, the building parameters and the signal source information, including: establishing a power device set according to the device parameters and the building parameters, the number of power devices included in the power device set is |D|, and |D| is an integer greater than or equal to 1; determining a target power device from the power device set as the parent node of the parent individual, and deleting the target power device from the power device set, and for the first time using the root node of the parent individual as the parent node, the root node being selected from the power device set and corresponding to the signal source. source-connected power devices; selecting z1 power devices from the power device set as child nodes of the parent node in the parent individual, z1 is an integer greater than or equal to 0, and deleting the z1 power devices from the power device set, the number of output ports of the target power device corresponding to the parent node is p, and p is an integer greater than or equal to 2; selecting p-z1 floors from the floor set as child nodes of the parent node, and deleting the selected p-z1 floors from the floor set, until each power device in the parent individual is assigned a child node to generate the parent individual.

[0054] In an exemplary embodiment, a power device set is established according to the device parameters and the building parameters, including: selecting a power device from the candidate power device set as a power device in the power device set; making the sum of the number of output ports of all power devices in the power device set minus |D| equal to |F|-1.

[0055] In an exemplary embodiment, when the power device set is not empty, z1 is an integer between a first value and a second value, the first value is the maximum value in {p-|F|,1}, and the second value is the minimum value in {p,|D|}; when the power device set is empty, z1 takes the value of 0.

[0056] S520 can randomly initialize N tree-coded topological structures as N inter-layer network structures to form a parent population G = {G1, ..., G N}, G n represents the nth parent individual, where n is an integer greater than or equal to 1 and less than or equal to N.

[0057] S520 initializes the parent population G = {G1, ..., G N} may include the following steps 2.1) to 2.6):

[0058] 2.1) Randomly establish a power device set D consisting of optional power dividers and couplers, that is, the power devices in D are all selected from T.

[0059] In the embodiment of the present disclosure, in order to ensure that all floors in the building can be connected, the power devices in D meet two conditions:

[0060] 2.1.1) The power device type of each PD belongs to T, for example, it can only be a coupler, a 2-way power splitter, a 3-way power splitter, a 4-way power splitter, or a 6-way power splitter;

[0061] 2.1.2) The sum of the number of output ports of all PDs minus the number of PDs in D |D| equals (|F|-1), which satisfies the following formula:

[0062] ∑ i∈|D| p i -|D|+1=|F| (2)

[0063] where p i is the number of output ports of the i-th power device in the power device set D. |D| is the number of power devices in D, |D| is an integer greater than or equal to 1, and i is an integer greater than or equal to 1 and less than or equal to |D|. F is a floor set, |F| is the number of floors, and |F| is an integer greater than or equal to 1.

[0064] For example, for an inter-floor network in a 5-floor building, D may include two 3-way power splitters, or one 3-way power splitter and two couplers.

[0065] 2.2) Randomly select a power device from the power device set D, use it as the root node d and delete it from the power device set D, and use the root node d as the first parent node d of the following step 2.3).

[0066] 2.3) Randomly select z1 devices from the power device set D as child nodes of the parent node d. When the power device set D is not empty, z1 is a random integer between max{p-|F|,1} and min{p,|D|}; when the power device set D is empty, z1=0. In addition, p is the number of output ports of the power device corresponding to the parent node d, and p is an integer greater than or equal to 2. The selected z1 power devices are then deleted from the power device set D.

[0067] 2.4) Randomly select (p-z1) floors from the floor set F as child nodes of the parent node d, and delete the selected (p-z1) floors from the floor set F.

[0068] 2.5) Randomly select a power device with no child nodes assigned from the inter-layer network as the new parent node d, jump back to step 2.3) and execute 2.3) to 2.4) repeatedly until all power devices in the inter-layer network are assigned child nodes, and the nth parent individual G is obtained. n , n is an integer greater than or equal to 1 and less than or equal to N. It can be understood that before each loop execution of 2.3) to 2.4), the floor set F is restored to the floors originally included in the building.

[0069] The nth parent individual can be a spanning tree G n , each non-leaf node (i.e. G n The PD type and position corresponding to the power devices in the network are added to the non-leaf nodes.

[0070] In an exemplary embodiment, the location of each PD may be set to the lowest floor among all subsequent floors directly and indirectly connected to the PD. Figure 1 In the example, if the subsequent floors connected to the first PD include the first to fifth floors, the first PD is set on the first floor, which is the lowest. If the subsequent floors connected to the second PD include the first to third floors, the second PD is set on the first floor, which is the lowest. If the subsequent floors connected to the third PD include the fourth and fifth floors, the third PD is set on the fourth floor, which is the lowest. This setting can reduce the transmission loss of the signal.

[0071] 2.6) Repeat steps S2.1) to S2.5) until N parent individuals are generated, forming a parent population G = {G1, ..., G N}.

[0072] In S530, N weight vectors and the neighborhood of each weight vector are obtained, and the nth weight vector is associated with the nth parent individual, where n is an integer greater than or equal to 1 and less than or equal to N.

[0073] In an exemplary embodiment, obtaining N weight vectors and the neighborhood of each weight vector includes: uniformly sampling to obtain N weight vectors w={w1,…,w N}, where the nth weight vector is Determine T1 weight vectors with the smallest distance to the nth weight vector from the N weight vectors, and use the index of the T1 weight vector as the neighborhood B of the nth weight vector n , where T1 is a positive integer greater than or equal to 1 and less than or equal to N.

[0074] S530 initializes N weight vectors and constructs a neighborhood B1, ..., B of each weight vector N , and associating the topological structure with the corresponding weight vector, which may include the following steps 3.1) to 3.3).

[0075] 3.1) Uniformly sample N weight vectors w = {w1,…,w N}, where the nth weight vector is expressed as w n is a two-dimensional vector in the range [0,1].

[0076] 3.2) Create each weight vector w n Neighborhood index set B n , used to retain the N weight vectors with w n The indices of the T1 weight vectors with the smallest Euclidean distance.

[0077] In the embodiment of the present disclosure, the nth sub-problem refers to the nth sub-problem among the N sub-problems obtained by decomposing the original multi-objective problem, and each sub-problem corresponds to a weight vector. The neighborhood of the nth sub-problem is B n is the distance nth weight vector w n The nearest T1 weight vectors, n=1, ..., N, that is, n is a positive integer greater than or equal to 1 and less than or equal to N. T1 is an integer greater than or equal to 1 and less than or equal to N, that is, the neighborhood of the nth weight vector can include its own index n.

[0078] In the embodiment of the present disclosure, the Euclidean distance can be used to measure the distance between two different weight vectors, but the present disclosure is not limited to this. For example, the Euclidean distance between the 1st to Nth weight vectors and the nth weight vector can be calculated respectively, and then the 1st to Nth weight vectors are arranged in ascending order according to the size of the Euclidean distance, and then the index of the first T1 weight vectors is selected and stored in B n So B n It can also be called a neighborhood index set. T1 can be, for example, 20, but the present disclosure is not limited thereto.

[0079] 3.3) The weight vector w n and the parent individual G in the parent population n Associated with the weight vector w n Neighborhood B n The parent individual associated with the weight vector in is called the parent individual G n 's neighborhood.

[0080] For example, suppose B n ={1,3,5}, that is, w nThe weight vectors with the closest Euclidean distance are w1, w3, and w5 respectively. Then the parent individuals G1, G3, and G5 in the parent population are called parent individuals G n 's neighborhood.

[0081] In S540, according to the weight vector associated with each parent individual in the parent population and its neighborhood, a crossover mutation process is performed on the parent individuals in the parent population to generate a child population including N child individuals.

[0082] In an exemplary embodiment, according to the weight vector associated with each parent individual in the parent population and its neighborhood, the parent individuals in the parent population are subjected to crossover mutation processing to generate a child population containing N child individuals, including: determining the first neighboring parent individual G in the neighborhood of the nth parent individual according to the neighborhood of the nth weight vector associated with the nth parent individual k and the second neighbor parent individual G l ; Get the first neighborhood set C k and the second neighborhood set G l , the first neighborhood set includes the number of floors subsequently connected by non-leaf nodes in the first neighborhood parent individual, and the second neighborhood set includes the number of floors subsequently connected by non-leaf nodes in the second neighborhood parent individual; obtain the intersection of the first neighborhood set and the second neighborhood set; if the intersection is an empty set, take the nth parent individual as the nth child individual; if the intersection is a non-empty set, select z2 from the intersection, where z2 is an integer greater than or equal to 1, and select the first power device and the second power device connecting z2 floors from the first neighborhood parent individual and the second neighborhood parent individual respectively; use the second power device and its subsequent nodes to replace the first power device and its subsequent nodes to obtain the nth child individual.

[0083] In an exemplary embodiment, crossover mutation processing is performed on the parent individuals in the parent population according to the weight vector associated with each parent individual in the parent population and its neighborhood to generate a child population including N child individuals, and also includes: if there are repeated floors in the nth child individual, then the repeated floors in the part of the nth child individual that is not replaced by the second power device and its subsequent nodes are replaced by other floors, and the other floors are floors in the floor set that are not included in the nth child individual.

[0084] In an exemplary embodiment, crossover mutation processing is performed on the parent individuals in the parent population according to the weight vector associated with each parent individual in the parent population and its neighborhood to generate a child population including N child individuals, and also includes: selecting a first power device to be replaced from the nth child individual, and if the first power device to be replaced includes a subsequent power device, selecting a second power device to be replaced from the subsequent power devices; introducing a new power device type into the nth child individual according to the power device type of the first power device to be replaced, or the power device types of the first power device to be replaced and the second power device to be replaced.

[0085] In an exemplary embodiment, according to the power device type of the first power device to be replaced, or the power device types of the first power device to be replaced and the second power device to be replaced, introducing a new power device type into the nth child individual includes: selecting and performing any one of the following:

[0086] If the first power device to be replaced is a 2-way power splitter, the first power device to be replaced is replaced with a coupler;

[0087] If the first power device to be replaced is a 3-way power splitter, the first power device to be replaced is replaced with two 2-way power splitters;

[0088] If the first power device to be replaced is a 4-way power splitter, the first power device to be replaced is replaced with a 2-way power splitter and a 3-way power splitter;

[0089] If the first power device to be replaced is a 6-way power splitter, the first power device to be replaced is replaced with a 3-way power splitter and a 4-way power splitter;

[0090] If the first power device to be replaced is a coupler, the first power device to be replaced is replaced with a 2-way power splitter;

[0091] If the first power device to be replaced and the second power device to be replaced are two 2-way power splitters, the first power device to be replaced and the second power device to be replaced are replaced with one 3-way power splitter;

[0092] If the first power device to be replaced and the second power device to be replaced are a 2-way power splitter and a 3-way power splitter, the first power device to be replaced and the second power device to be replaced are replaced with a 4-way power splitter;

[0093] If the first power device to be replaced and the second power device to be replaced are a 3-way power splitter and a 4-way power splitter, the first power device to be replaced and the second power device to be replaced are replaced with a 6-way power splitter.

[0094] Standard replication operators are usually designed to generate solutions for real or integer coding, and therefore cannot be used to generate solutions for tree coding. To solve this problem, the disclosed embodiment proposes a new replication operator, including a crossover operator and a mutation operator, to generate a solution for tree coding, that is, the target inter-layer network structure finally obtained.

[0095] S540 uses the crossover operator and the mutation operator to generate N new topological structures to form a descendant population, which may include the following steps 4.1) to 4.8).

[0096] 4.1) Randomly select the nth parent individual G n Two parent individuals G in the neighborhood k and G l , respectively referred to as the first neighborhood parent individual and the second neighborhood parent individual, where k∈B n , l∈B n .

[0097] 4.2) Record G k The number of all floors that all non-leaf nodes subsequently connect to and are retained in C k In, record G l The number of all floors that all non-leaf nodes subsequently connect to and are retained in C l and get C k and C l The intersection C.

[0098] 4.3) If C is an empty set, directly add the nth parent individual G n As the nth offspring individual O n Otherwise, randomly select an integer z2 from C and select two integers from the two parent individuals G. k and G l Randomly select a first power device d that connects z2 floors k and the second power device d l . Using G l The first power device in l and its subsequent nodes replace G k The second power device d k And its subsequent nodes get the nth offspring individual O n .

[0099] 4.4) The nth offspring individual O nThe repeated floors in are replaced by other floors in F. This makes the nth generation individual O n Therefore, the repeated floors in the unchanged part (i.e., the part of the nth generation individual that is not replaced by the second power device and its subsequent nodes) are randomly replaced by those not included in the nth generation individual O. n Other floors in.

[0100] Then, in the nth generation individual O n The PD type and position corresponding to each non-leaf node are added in. Here, each PD type remains the same, but the position of the PD is set to the lowest floor among all subsequent floors to which the PD is connected.

[0101] 4.1) to 4.4) are crossover operators, and the following is a mutation operator. In order to effectively explore the design space, the mutation operator is designed to introduce the nth offspring individual O obtained from the current solution (e.g., step 4.4 above). n ) to maintain the diversity of the population.

[0102] 4.5) Randomly select individual O from the nth generation n Select a power device from m , called the first power device to be replaced, if d m If there are subsequent power devices, randomly select d m Any one of d m Subsequent devices d j , referred to as the second power device to be replaced.

[0103] 4.6) Randomly execute one of the following feasible situations to obtain the new nth offspring individual O' n :

[0104] If d m It is a 2-way power splitter, replace it with a coupler;

[0105] If d m It is a 3-way power splitter, replace it with 2 2-way power splitters;

[0106] If d m It is a 4-way power splitter, replace it with a 2-way power splitter and a 3-way power splitter;

[0107] If d m It is a 6-way power splitter, replace it with a 3-way power splitter and a 4-way power splitter;

[0108] If dm It is a coupler, replace it with a 2-way power splitter;

[0109] If d m and d j There are 2 2-way power splitters, replace them with 1 3-way power splitter;

[0110] If d m and d j It is a 2-way power splitter and a 3-way power splitter, replace them with a 4-way power splitter;

[0111] If d m and d j It is a 3-way power splitter and a 4-way power splitter, replace them with a 6-way power splitter.

[0112] Each of the above can ensure that after replacing 1 or 2 PDs, the new nth offspring individual O' n The number of connected floors remains unchanged. It is understandable that the above eight feasible implementations are only one design method, and those skilled in the art can design other feasible implementations according to actual needs, and the present disclosure does not limit this, as long as the purpose of introducing a new type of power device can be achieved.

[0113] 4.7) The power device to be replaced (for example, it can be d m , or, d m and d j ) is transferred to the child node of the newly connected power device after mutation, generating a new nth generation individual O' n The new PD type and position can then be added to the new nth offspring individual O' n The non-leaf nodes in .

[0114] 4.8) Repeat the above steps 4.1) to 4.7) until N new offspring individuals are generated to form the offspring population O = {O'1, ..., O' N}.

[0115] In S550, a selection index of each parent individual and each child individual is obtained, and each parent individual and each child individual corresponds to an inter-layer network structure of the indoor distributed antenna system.

[0116] In 5G indoor distribution projects, multiple objectives often need to be considered, such as construction costs (materials used, construction period) and network quality (power loss, signal coverage). However, 5G network planning in related technologies is based on single-objective optimization methods, which cannot provide users with the best compromise planning scheme between different objectives. The multi-objective topology structure design method of the 5G indoor distribution system based on tree coding proposed in the embodiment of the present disclosure can provide decision makers and construction parties with a variety of optimal compromise planning schemes after one run (that is, the N parent individuals contained in the parent population obtained by the final iteration, and these N parent individuals correspond to N target inter-layer network structures), so as to better meet actual engineering needs.

[0117] In an exemplary embodiment, obtaining the selection index of each parent individual and each offspring individual includes: obtaining a union Q of the parent population and the offspring population, wherein the union Q includes |Q| individuals, each of which is a parent individual or an offspring individual; obtaining a first performance index and a second performance index of each individual; determining an ideal target vector and a minimum point target vector of the union Q based on the first performance index and the second performance index of each individual, wherein the first ideal target value in the ideal target vector is the minimum value of the first performance indexes of |Q| individuals, the second ideal target value is the minimum value of the second performance indexes of |Q| individuals, and the first minimum point target value in the minimum point target vector is the first performance index of |Q| individuals. The maximum value among the targets, the second lowest point target value in the lowest point target vector is the maximum value among the second performance indicators of |Q| individuals; the first aggregate candidate value of the e-th individual is obtained according to the first ideal target value, the first lowest point target value, the first performance indicator of the e-th individual and the e-th weight vector associated with the e-th individual; the second aggregate candidate value of the e-th individual is obtained according to the second ideal target value, the second lowest point target value, the second performance indicator of the e-th individual and the e-th weight vector associated with the e-th individual; e is a positive integer greater than or equal to 1 and less than or equal to |Q|; the selection indicator of the e-th individual is determined according to the first aggregate candidate value and the second aggregate candidate value of the e-th individual.

[0118] In an exemplary embodiment, the device parameters include power device prices and feeder prices. The first performance indicator includes the construction cost of the individual, and the second performance indicator includes the average power loss of the individual. Wherein, obtaining the first performance indicator and the second performance indicator of each individual includes: obtaining the construction cost of the individual according to the power devices and their power device prices contained in the individual, and the feeder length and its feeder price contained in the individual; obtaining the power consumption of the connection path from the signal source in the individual to each floor of the building, and obtaining the average power loss of the individual according to the power consumption of the connection path from the signal source in the individual to each floor of the building.

[0119] S550 can calculate performance indicators such as system cost (eg, construction cost) and transmission loss (eg, average power loss) of the planning scheme.

[0120] It can be understood that the first performance indicator and the second performance indicator in the embodiment of the present disclosure are used to refer to multiple objectives that need to be optimized simultaneously for the indoor distributed antenna system. The construction cost and the average power loss are taken as an example below, but it is not limited to this. For example, the multiple objectives optimized simultaneously can be two or more, and are not limited to the construction cost and the average power loss. For example, they can also include coverage range, coverage quality, etc.

[0121] The calculation of performance indicators may include the following steps:

[0122] 5.1) The construction cost includes the cost of all PDs and coaxial cables in an individual (for example, a parent individual or a child individual). The construction cost f1 is calculated as follows:

[0123]

[0124] in represents the power device price of the rth power device in the individual, pr c represents the feeder price per unit length of coaxial cable, dl represents the length of coaxial cable in the individual, I represents the number of power devices in the individual, I is a positive integer greater than or equal to 1, and r is a positive integer greater than or equal to 1 and less than or equal to 1.

[0125] For a given inter-layer network V, the length dl of the coaxial cable used to connect the signal source, PD and all floors can be calculated by the following formula:

[0126]

[0127] where d r,j1 represents the rth power device d in the individual r and the j3rd power device d j3 / the low-voltage room, d0 represents the distance between the signal source and the first power device directly connected to the signal source in the individual, S r Represents the individual with the rth power device d r A collection of connected subsequent floors and power devices.

[0128] Assumptions here:

[0129] d r,j3 =|F r -F j3 |*h (5)

[0130] d0=F1*h (6)

[0131] Where h represents the height of the corresponding floor. It can be assumed that the height of each floor of the building is equal, for example, 5 meters, but the present disclosure is not limited to this. It is only used for illustration. The heights of different floors can also be different. d0 represents the distance between the signal source and the PD directly connected to the signal source. For example, for Figure 1 For the first and second PDs in the diagram, both are located on the first floor, then d 1,2 =0. The coaxial cable topology design optimization of passive IB-DAS generally includes two aspects: (1) inter-layer optimization: topological structure optimization of the wiring between floors, that is, in the vertical direction; (2) intra-layer optimization: topological structure optimization of the wiring within a single floor, in the horizontal direction, and it is necessary to know the specific location of the indoor antenna within the floor. The problem faced in the embodiment of the present disclosure is inter-layer optimization, so only the vertical length of the coaxial cable needs to be concerned.

[0132] 5.2) The calculation method of the average power loss definition f2 of the connection path from the signal source to all floors is as follows:

[0133]

[0134] The connection path of the fth floor includes the power devices and coaxial cables from the signal source to the fth floor. f represents the power loss of the fth floor, where f is an integer greater than or equal to 1 and less than or equal to |F|. f It is calculated by the following formula:

[0135]

[0136] in, Indicates the i2th power device d i2 Power loss in the corresponding connection path, n f Indicates the number of power devices in the corresponding connection path, n f is an integer greater than 0, i2 is greater than or equal to 1 and less than or equal to n f An integer, l c Represents the power loss per unit distance of the coaxial cable, d f Indicates the length of the coaxial cable connecting the signal source and the low-voltage room on the fth floor. f It is the number of floors crossed by the coaxial cable in the corresponding connection path multiplied by the floor height.

[0137] 5.3) The purpose of the selection operator is to use the offspring individuals to update the neighborhood parent individuals (also called neighborhood solutions). The aggregation function values ​​of the parent individuals and offspring individuals are calculated separately as the selection indicators of the parent individuals and offspring individuals. The calculation formula is as follows:

[0138]

[0139] The union of the parent population G and the offspring population O is represented by Q, that is, Q = G ∪ O, and the e-th individual Q in the union is e ∈G∪O, e is a positive integer greater than or equal to 1 and less than or equal to |Q|, |Q| is the number of individuals contained in Q. The w in formula (9) represents the number of individuals Q e The associated weight vector contains the same number of weights as the number of performance indicators used. For example, taking the two performance indicators construction cost and average power loss as an example, each weight vector contains two weights, w j1 Represents the j1th weight in the weight vector w.

[0140] In the embodiment of the present disclosure, the ideal target vector z can be calculated by the following formula * :

[0141]

[0142]

[0143]

[0144] represents the first ideal target value, Indicates the second ideal target value.

[0145] The lowest point target vector z can be calculated by the following formula nad :

[0146]

[0147]

[0148]

[0149] Indicates the first lowest point target value, Indicates the second lowest point target value.

[0150] The disclosed embodiment first obtains the union of the parent population and the child population, and then calculates the aggregation function value of the individuals in the union. In actual situations, some of the parent individuals in the parent population may be the same as the child individuals in the child population. By obtaining the union, the amount of calculation can be reduced and computing resources can be saved.

[0151] It is understandable that the calculation of the individual selection index is not limited to the above-mentioned example, as long as it can be used to measure whether the performance index of the parent individual or the offspring individual is better.

[0152] Designing an interlayer network for a distributed antenna system in a building usually involves multiple objectives, such as minimizing construction cost and average power loss. The disclosed embodiment formulates the interlayer network planning problem as a multi-objective optimization problem and proposes a multi-objective evolutionary algorithm that enables the decision maker to obtain a set of optimal solutions in a single run. Experimental results show that the obtained solutions have good convergence and diversity among different objectives.

[0153] In S560, the parent population is updated using the offspring population based on the selection index of the offspring individual and the selection index of the parent individual in the neighborhood of the weight vector associated with the corresponding offspring individual.

[0154] In an exemplary embodiment, the offspring population is used to update the parent population based on the selection index of the offspring individual and the selection index of the parent individual in the neighborhood of the weight vector associated with the corresponding offspring individual, including: if the selection index of the nth offspring individual is smaller than the selection index of the parent individual in the neighborhood of the nth offspring individual, then the nth offspring individual is used to replace the parent individual in the neighborhood of the nth offspring individual.

[0155] S560 may adopt an environment selection strategy (selection operator) to update the parent population, which may include the following steps.

[0156] 6.1) Compare the nth offspring individual O' n The aggregation function value of is equal to each parent individual G in its neighborhood j2 (j2∈B n ) aggregate function value, if the nth offspring individual O' n If the aggregate function value is smaller, use the nth child individual O' n Replace the parent individual G j2 If the nth offspring individual O' n There are multiple parent individuals G in the neighborhood of j2 , then we can use the nth offspring individual O' n Simultaneously replace these multiple parent individuals G j2 .

[0157] 6.2) Repeat step 6.1) for all offspring individuals to obtain a new parent population.

[0158] In S570, a target inter-layer network structure of the indoor distributed antenna system is determined according to the updated parent population.

[0159] In S570, the process can jump back to step S540, and execute the loop until the preset number of loops is reached, and the resulting parent population is output, and each parent individual in the parent population corresponds to an optimal topological structure as the target inter-layer network structure. In the embodiment of the present disclosure, the preset number of loops can be set according to actual needs, and the present disclosure does not limit this.

[0160] The method provided by the embodiment of the present disclosure can, after generating a parent population based on the building parameters, device parameters and signal source information of the indoor distributed antenna system, perform crossover mutation processing on the parent individuals in the parent population according to the weight vector associated with each parent individual in the parent population and its neighborhood, so as to generate a child population including multiple child individuals, thereby ensuring the heritability and diversity of the child population; based on the selection index of the child individual and the selection index of the parent individual in the neighborhood of the weight vector associated with the corresponding child individual, the child individuals in the child population are used to update the parent individuals in the parent population, thereby continuously optimizing the parent individuals, so that the optimized target inter-layer network structure can be finally obtained.

[0161] Interlayer network planning is a multi-objective optimization problem, whose goal is to minimize the construction cost and average power loss at the same time. The method provided by the embodiment of the present disclosure can solve the multi-objective interlayer network planning problem with the goal of minimizing the construction cost and average power loss. The main challenge in solving this problem is to effectively represent the interlayer network structure. Then, a tree-encoded evolutionary algorithm called TEA (tree-encoded evolutionary algorithm) is proposed. Since standard operators cannot be applied, problem-specific crossover and mutation operators are designed to generate tree-encoded solutions. In addition, the above method is also used to update the solution. The method provided by the embodiment of the present disclosure can provide a set of Pareto optimal solutions for decision makers to select the optimal solution.

[0162] The disclosed embodiment proposes an efficient 5G indoor distribution system topology design method, which can significantly improve the signal coverage and quality of the 5G indoor distribution system and reduce the construction cost as much as possible. In order to solve this problem, the inter-layer network structure is encoded as a spanning tree (referred to as tree coding), the root node is connected to the signal source, and the leaf nodes and non-leaf nodes represent all floors and power devices PD of the indoor distributed antenna system respectively. Compared with the coding in the related art, the tree coding has good locality and can easily generate an effective solution / inter-layer network structure.

[0163] The embodiment of the present disclosure uses a spanning tree G(V1,E) to represent the inter-layer network structure M={{T r ,F r ,Pr ,S r}|r=1,…,I}, where V1 and E represent the node set and edge set respectively. The root node of the spanning tree is connected to the signal source, and the non-leaf nodes and leaf nodes in V1 represent PDs and floors respectively. According to formula (1b), the degree of each non-leaf node should be one of 2, 3, 4 and 6. In addition, the type of PD (e.g. T r ) and location (e.g. F r ) is added to each non-leaf node. By analyzing E, the parent node and child node of each non-leaf node can be identified. Therefore, the set of predecessor PDs of each PD (e.g., P r ) and the set of subsequent PDs / floors for each PD (e.g. S r ). As a result, in the spanning tree G(V1,E) and the inter-layer network structure M={{T r ,F r ,P r ,S r A one-to-one correspondence is established between}|r=1,…,I}.

[0164] like Figure 6 As shown in Figure 1, a spanning tree is used to represent the inter-layer network structure of an IB-DAS including a 5-story building. In general, this encoding can bring two benefits:

[0165] 1) Obviously, a slight modification of the spanning tree G(V1,E) corresponds to the inter-layer network structure M = {{T r ,F r ,P r ,S r}|r=1,…,I}, thus demonstrating the locality of the tree encoding.

[0166] 2) Since the degree of each non-leaf node is the same as the number of output ports of each PD in T, at least one PD in T can be adopted. Therefore, this encoding method can easily generate an effective inter-layer network structure.

[0167] The disclosed embodiment also provides a tree-encoded evolutionary algorithm TEA for multi-objective inter-layer network planning of IB-DAS. Since standard operators cannot generate tree-encoded solutions, crossover and mutation operators are designed in TEA for the problem.

[0168] Figure 7 It is a schematic diagram of a crossover operator provided by an embodiment of the present disclosure.

[0169] For example Figure 7 As shown, from the parent individual G k and G l , there is C k={4,6}, C l ={2,3,4}; then, C = {4}, so z2 = 4. Because G k The third PD and G l The second PD in each of the four subsequent floors is connected to G l The second PD in (e.g. d l ) and its subsequent nodes replace G k The third PD in (e.g. d k ) and its subsequent nodes, generating offspring individuals O n At this time, for the offspring individual O n The repeated floors in the unchanged part are not included in the offspring individual O n For example, the 5th and 7th floors in the unchanged part are replaced by the 2nd and 4th floors. Then, in the offspring individual O n Add the type and position of the PD corresponding to each non-leaf node.

[0170] Figure 8 It is a schematic diagram of a mutation operator provided by an embodiment of the present disclosure.

[0171] like Figure 8 As shown, a 3-way power splitter and a 4-way power splitter are replaced by a 6-way power splitter, and the number of connected floors remains unchanged.

[0172] Fig. 9 It is a schematic diagram of an inter-layer network structure 900 obtained by using relevant technologies (such as PEA (Prufer evolutionary algorithm)). Fig.10 It is a schematic diagram of an inter-layer network structure 1000 obtained by using another related technology (such as BEA (binary string-encodedevolutionary algorithm)). Fig.11 It is a schematic diagram of an inter-layer network structure 1100 obtained by using the TEA method provided in an embodiment of the present disclosure.

[0173] Compare Figure 9-11 The inter-layer network structure shown in Figure 1 selects the solution G* associated with w = [0.5, 0.5] from the final parent populations obtained by PEA, BEA, and TEA, respectively. Figure 9-11The interlayer network structures corresponding to the solutions G* obtained by PEA, BEA and TEA are shown respectively. The target values ​​(i.e., construction cost and average power loss) of the three interlayer network structures obtained by PEA, BEA and TEA are [320, 18.875], [360, 17.955] and [315, 12.665] respectively. Therefore, the interlayer network structure obtained by TEA is better than that obtained by PEA and BEA, and TEA achieves better performance in the interlayer network structure.

[0174] The disclosed embodiment uses 11 different test instances to evaluate the performance of TEA, each with a different number of floors. Specifically, |F| is set to a range of 10 to 30 with an increment of 2. The height of each floor is fixed at 5 meters. The prices of couplers, 2-way, 3-way, 4-way and 6-way power splitters are 25 yuan, 20 yuan, 30 yuan, 40 yuan and 60 yuan, respectively. The coaxial cable is 2 yuan per meter. It is assumed that the power loss of each output port of the 2-way, 3-way, 4-way and 6-way power splitters is 3.5dB, 5.3dB, 6.5dB and 7.8dB, respectively, while the power loss of the output port of the coupler is 3.0dB and 0.5dB, respectively. The power loss of the coaxial cable is 0.25dB / m. Comprehensive experiments on 11 test instances with up to 30 floors show that the TEA outperforms other algorithms.

[0175] The disclosed embodiment provides a tree-coded 5G indoor distributed system multi-objective topology design method, which encodes the topology of a group of indoor distributed antenna systems into a tree-structured population, and uses crossover operators and mutation operators to generate child populations, and selects and updates the parent population in combination with indicators such as the construction cost and transmission loss of the 5G indoor distributed system, and finally obtains a group of optimal topology structures or near-optimal topology structures. Compared with the indoor distribution system planning method in the related art, the disclosed method realizes the multi-objective topology optimization of the 5G indoor distributed system. The proposed method can provide decision makers and construction parties with a variety of optimal compromise planning schemes after one run, so as to better meet the actual engineering needs.

[0176] Fig.12 , Fig.12 Schematic diagram of a topology design device for an indoor distributed antenna system provided by an embodiment of the present disclosure. The topology design device for an indoor distributed antenna system may be a computer program (including program code, etc.) running in a computer device. For example, the topology design device for an indoor distributed antenna system may be an application software. The device may be used to execute the corresponding steps of the method provided by an embodiment of the present disclosure. Fig.12As shown, the topology structure design device 1200 of the indoor distributed antenna system can be used for the computer device in the embodiment corresponding to the above figure. Specifically, the device can include: an acquisition unit 1210 and a processing unit 1220.

[0177] The acquisition unit 1210 can be used to acquire building parameters, device parameters and signal source information. The processing unit 1220 can be used to generate a parent population according to the device parameters, the building parameters and the signal source information, wherein the parent population includes N parent individuals, where N is an integer greater than 1. The processing unit 1220 can also be used to obtain N weight vectors and the neighborhood of each weight vector, and associate the nth weight vector with the nth parent individual, where n is an integer greater than or equal to 1 and less than or equal to N. The processing unit 1220 can also be used to perform crossover mutation processing on the parent individuals in the parent population according to the weight vectors and their neighborhoods associated with each parent individual in the parent population, to generate a child population including N child individuals. The processing unit 1220 can also be used to obtain selection indicators for each parent individual and each child individual, and each parent individual and each child individual correspond to the inter-layer network structure of the indoor distributed antenna system. The processing unit 1220 may also be configured to update the parent population using the child population based on the selection index of the child individual and the selection index of the parent individual in the neighborhood of the weight vector associated with the corresponding child individual. The processing unit 1220 may also be configured to determine the target inter-layer network structure of the indoor distributed antenna system according to the updated parent population.

[0178] An embodiment of the present disclosure provides a device for designing a topology structure of an indoor distributed antenna system, and the device can be run in a computer device.

[0179] Fig.13 FIG. 1 is a schematic diagram of an operating environment in some embodiments of the present disclosure. Fig.13 As shown, the terminal devices of multiple users (eg, including user devices 131a, 131b, and 131c) are connected to the server 132 via a network 136. The server 132 maintains a database 134, which stores network data for providing data to the user devices.

[0180] The user equipment may provide the server 132 with the building parameters, device parameters, and signal source information. Alternatively, the server 132 may read the building parameters, device parameters, and signal source information from the database 134 . The server 132 may generate a parent population according to the device parameters, the building parameters and the signal source information, wherein the parent population includes N parent individuals, where N is an integer greater than 1; obtain N weight vectors and the neighborhood of each weight vector, associate the nth weight vector with the nth parent individual, where n is an integer greater than or equal to 1 and less than or equal to N; perform crossover mutation processing on the parent individuals in the parent population according to the weight vector and its neighborhood associated with each parent individual in the parent population, and generate a child population including N child individuals; obtain selection indicators for each parent individual and each child individual, wherein each parent individual and each child individual corresponds to the inter-layer network structure of the indoor distributed antenna system; based on the selection indicators of the child individuals and the selection indicators of the parent individuals in the neighborhood of the weight vector associated with the corresponding child individual, use the child population to update the parent population; and determine the target inter-layer network structure of the indoor distributed antenna system according to the updated parent population. The server 132 may output the target inter-layer network structure to the user device.

[0181] The user device may be a mobile phone (such as user device 131c) or a laptop (such as user device 131b), or a playback device (such as user device 131a), etc., which is not limited here. Fig.13 The user equipment in the example is only a part of the equipment, and the user equipment in the present disclosure is not limited to the Fig.13 The equipment listed in .

[0182] It is understandable that the user device mentioned in the embodiment of the present disclosure may be a computer device, and the computer device in the embodiment of the present disclosure includes but is not limited to a terminal device or a server. In other words, the computer device may be a server or a terminal device, or a system composed of a server and a terminal device. Among them, the terminal device mentioned above may be an electronic device, including but not limited to a mobile phone, a tablet computer, a desktop computer, a laptop computer, a PDA, a vehicle-mounted device, an augmented reality / virtual reality (AR / VR) device, a helmet display, a smart TV, a wearable device, a smart speaker, a digital camera, a camera, and other mobile Internet devices (mobile internet device, MID) with network access capabilities, or terminal devices in scenarios such as trains, ships, and flights. Among them, the server mentioned above may be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, vehicle-road collaboration, content delivery networks (Content Delivery Network, CDN), and big data and artificial intelligence platforms.

[0183] Optionally, the data involved in the embodiments of the present disclosure may be stored in a computer device, or the data may be stored based on cloud storage technology, which is not limited here.

[0184] See also Fig.14 , Fig.14 Schematic diagram of a computer device provided by an embodiment of the present disclosure. Fig.14 As shown, the computer device in the embodiment of the present disclosure may include: one or more processors 141, a memory 142, and an input-output interface 143. The processor 141, the memory 142, and the input-output interface 143 are connected via a bus 144. The memory 142 is used to store a computer program, which includes program instructions. The input-output interface 143 is used to receive and output data, such as for data interaction between a host machine and a computer device, or for data interaction between various virtual machines in a host machine; the processor 141 is used to execute the program instructions stored in the memory 142.

[0185] The processor 141 can perform the following operations: obtaining building parameters, device parameters and signal source information; generating a parent population according to the device parameters, the building parameters and the signal source information, wherein the parent population includes N parent individuals, where N is an integer greater than 1; obtaining N weight vectors and the neighborhood of each weight vector, associating the nth weight vector with the nth parent individual, where n is an integer greater than or equal to 1 and less than or equal to N; performing crossover mutation processing on the parent individuals in the parent population according to the weight vector associated with each parent individual in the parent population and its neighborhood, to generate a child population including N child individuals; obtaining selection indicators for each parent individual and each child individual, wherein each parent individual and each child individual corresponds to the inter-layer network structure of the indoor distributed antenna system; updating the parent population using the child population based on the selection indicators of the child individuals and the selection indicators of the parent individuals in the neighborhood of the weight vector associated with the corresponding child individuals; and determining the target inter-layer network structure of the indoor distributed antenna system according to the updated parent population.

[0186] In some feasible implementations, the processor 141 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.

[0187] The memory 142 may include a read-only memory and a random access memory, and provide instructions and data to the processor 141 and the input / output interface 143. A portion of the memory 142 may also include a non-volatile random access memory. For example, the memory 142 may also store information on the device type.

[0188] In a specific implementation, the computer device can execute the implementation methods provided in the steps in the above figure through its built-in functional modules. For details, please refer to the implementation methods provided in the steps in the above figure, which will not be repeated here.

[0189] The embodiment of the present disclosure provides a computer device, including: a processor, an input and output interface, and a memory. The processor obtains a computer program in the memory to execute each step of the method shown in the above figure.

[0190] The embodiment of the present disclosure also provides a computer-readable storage medium, which stores a computer program. The computer program is suitable for being loaded by the processor and executing the topology design method of the indoor distributed antenna system provided in each step of the above figure. For details, please refer to the implementation method provided in each step of the above figure, which will not be repeated here. In addition, the description of the beneficial effects of using the same method will not be repeated. For technical details not disclosed in the computer-readable storage medium embodiment involved in the present disclosure, please refer to the description of the method embodiment of the present disclosure. As an example, the computer program can be deployed to be executed on a computer device, or on multiple computer devices located in one location, or on multiple computer devices distributed in multiple locations and interconnected by a communication network.

[0191] The computer-readable storage medium may be the topology design device for the indoor distributed antenna system provided by any of the aforementioned embodiments or the internal storage unit of the computer device, such as the hard disk or memory of the computer device. The computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a smart memory card (smart media card, SMC), a secure digital (secure digital, SD) card, a flash card (flash card), etc. equipped on the computer device. Furthermore, the computer-readable storage medium may also include both the internal storage unit of the computer device and an external storage device. The computer-readable storage medium is used to store the computer program and other programs and data required by the computer device. The computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.

[0192] The embodiment of the present disclosure also provides a computer program product or a computer program, which includes a computer instruction stored in a computer-readable storage medium. The processor of the computer device reads the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the computer device executes the method provided in the various optional modes in the above figure.

[0193] The terms "first", "second", etc. in the specification, claims, and drawings of the embodiments of the present disclosure are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, device, product, or equipment that includes a series of steps or units is not limited to the listed steps or modules, but may optionally include steps or modules that are not listed, or may optionally include other step units inherent to these processes, methods, devices, products, or equipment.

[0194] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in this description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this disclosure.

[0195] The method and related apparatus provided by the embodiments of the present disclosure are described with reference to the method flow chart and / or structural diagram provided by the embodiments of the present disclosure. Specifically, each process and / or block in the method flow chart and / or structural diagram, as well as the combination of the processes and / or blocks in the flow chart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable search device to generate a machine, so that the instructions executed by the processor of the computer or other programmable search device generate instructions for implementing the process in the process. Figure 1 Schematic diagram of one or more processes and / or structures Figure 1 These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable search device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including the instruction device, which implements the function specified in the process. Figure 1 Schematic diagram of one or more processes and / or structures Figure 1 These computer program instructions can also be loaded onto a computer or other programmable search device, so that a series of operation steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide for implementing the process in the process. Figure 1 A flow or multiple flows and / or structures illustrate the steps of the functions specified in one block or multiple blocks.

[0196] The above disclosure is only a preferred embodiment of the present disclosure, which certainly cannot be used to limit the scope of rights of the present disclosure. Therefore, equivalent changes made according to the claims of the present disclosure are still within the scope of the present disclosure.

Claims

1. A topology design method for an indoor distributed antenna system, characterized in that: include: Obtain building parameters, device parameters and signal source information; Generate a parent population according to the device parameters, the building parameters and the signal source information, wherein the parent population includes N parent individuals, where N is an integer greater than 1; Obtain N weight vectors and the neighborhood of each weight vector, and associate the nth weight vector with the nth parent individual, where n is an integer greater than or equal to 1 and less than or equal to N; According to the weight vector associated with each parent individual in the parent population and its neighborhood, the parent individuals in the parent population are subjected to crossover mutation processing to generate a child population including N child individuals; Obtaining a selection index for each parent individual and each child individual, each parent individual and each child individual corresponding to an inter-layer network structure of the indoor distributed antenna system; Based on the selection index of the offspring individual and the selection index of the parent individual in the neighborhood of the weight vector associated with the corresponding offspring individual, updating the parent population with the offspring population; The target inter-layer network structure of the indoor distributed antenna system is determined according to the updated parent population.

2. The method according to claim 1, characterized in that The building parameters include a set of floors of the building; the device parameters include the number of output ports of the power device; The step of generating a parent population according to the device parameters, the building parameters and the signal source information includes: Establishing a power device set according to the device parameters and the building parameters, wherein the number of power devices included in the power device set is |D, where |D is an integer greater than or equal to 1; Determine a target power device from the power device set as the parent node of the parent individual, delete the target power device from the power device set, and use the root node of the parent individual as the parent node for the first time, wherein the root node is a power device selected from the power device set and connected to a signal source; Selecting z1 power devices from the power device set as child nodes of the parent node in the parent generation individual, where z1 is an integer greater than or equal to 0, and deleting the z1 power devices from the power device set, where the number of output ports of the target power device corresponding to the parent node is p, where p is an integer greater than or equal to 2; Select p-z1 floors from the floor set as child nodes of the parent node, and delete the selected p-z1 floors from the floor set until each power device in the parent individual is assigned a child node to generate the parent individual.

3. The method according to claim 2, characterized in that The building parameters also include the number of floors of the building |F|, where |F| is an integer greater than or equal to 1; the device parameters also include a candidate power device set; Wherein, establishing a power device set according to the device parameters and the building parameters comprises: Selecting a power device from the candidate power device set as a power device in the power device set; The sum of the number of output ports of all power devices in the power device set minus |D| equals |F|-1.

4. The method according to claim 2, characterized in that The building parameters also include the number of floors of the building |F|, where |F| is an integer greater than or equal to 1; When the power device set is not empty, z1 is an integer between a first value and a second value, the first value is a maximum value in {p-|F|,1}, and the second value is a minimum value in {p,|D|}; When the power device set is empty, z1 takes the value of 0.

5. The method according to claim 1, characterized in that Get N weight vectors and the neighborhood of each weight vector, including: Uniform sampling obtains N weight vectors w={w1,…,w N }, where the nth weight vector is Determine T1 weight vectors with the smallest distance to the nth weight vector from the N weight vectors, and use the index of the T1 weight vector as the neighborhood B of the nth weight vector n , where T1 is a positive integer greater than or equal to 1 and less than or equal to N.

6. The method according to claim 1, characterized in that According to the weight vector associated with each parent individual in the parent population and its neighborhood, the parent individuals in the parent population are subjected to crossover mutation processing to generate a child population containing N child individuals, including: According to the neighborhood of the nth weight vector associated with the nth parent individual, determine the first neighboring parent individual and the second neighboring parent individual in the neighborhood of the nth parent individual; Obtaining a first neighborhood set and a second neighborhood set, wherein the first neighborhood set includes the number of floors to which non-leaf nodes in the first neighborhood parent individual are subsequently connected, and the second neighborhood set includes the number of floors to which non-leaf nodes in the second neighborhood parent individual are subsequently connected; Obtaining an intersection of the first neighborhood set and the second neighborhood set; If the intersection is an empty set, the n-th parent individual is used as the n-th child individual; If the intersection is a non-empty set, select z2 from the intersection, where z2 is an integer greater than or equal to 1, and select the first power device and the second power device connecting z2 floors from the first neighborhood parent individual and the second neighborhood parent individual respectively; use the second power device and its subsequent nodes to replace the first power device and its subsequent nodes to obtain the nth child individual.

7. The method according to claim 6, characterized in that The building parameters include a set of floors of the building; According to the weight vector associated with each parent individual in the parent population and its neighborhood, the parent individuals in the parent population are subjected to crossover mutation processing to generate a child population containing N child individuals, and further comprising: If there are repeated floors in the nth child individual, the repeated floors in the part of the nth child individual that is not replaced by the second power device and its subsequent nodes are replaced by other floors, and the other floors are floors in the floor set that are not included in the nth child individual.

8. The method according to claim 6 or 7, characterized in that According to the weight vector associated with each parent individual in the parent population and its neighborhood, the parent individuals in the parent population are subjected to crossover mutation processing to generate a child population including N child individuals, and further comprising: Selecting a first power device to be replaced from the nth generation individual, and if the first power device to be replaced includes subsequent power devices, selecting a second power device to be replaced from the subsequent power devices; According to the power device type of the first power device to be replaced, or the power device types of the first power device to be replaced and the second power device to be replaced, a new power device type is introduced into the nth child generation individual.

9. The method according to claim 8, characterized in that According to the power device type of the first power device to be replaced, or the power device types of the first power device to be replaced and the second power device to be replaced, introducing a new power device type into the nth child individual, comprising: Choose to do any of the following: If the first power device to be replaced is a 2-way power splitter, the first power device to be replaced is replaced with a coupler; If the first power device to be replaced is a 3-way power splitter, the first power device to be replaced is replaced with two 2-way power splitters; If the first power device to be replaced is a 4-way power splitter, the first power device to be replaced is replaced with a 2-way power splitter and a 3-way power splitter; If the first power device to be replaced is a 6-way power splitter, the first power device to be replaced is replaced with a 3-way power splitter and a 4-way power splitter; If the first power device to be replaced is a coupler, the first power device to be replaced is replaced with a 2-way power splitter; If the first power device to be replaced and the second power device to be replaced are two 2-way power splitters, the first power device to be replaced and the second power device to be replaced are replaced with one 3-way power splitter; If the first power device to be replaced and the second power device to be replaced are a 2-way power splitter and a 3-way power splitter, the first power device to be replaced and the second power device to be replaced are replaced with a 4-way power splitter; If the first power device to be replaced and the second power device to be replaced are a 3-way power splitter and a 4-way power splitter, the first power device to be replaced and the second power device to be replaced are replaced with a 6-way power splitter.

10. The method according to claim 1, characterized in that Get the selection index of each parent individual and each offspring individual, including: Obtaining a union Q of the parent population and the offspring population, wherein the union Q includes |Q| individuals, each of which is a parent individual or a offspring individual; Obtaining a first performance indicator and a second performance indicator for each individual; Based on the first performance index and the second performance index of each individual, an ideal target vector and a minimum point target vector of the union Q are determined, wherein a first ideal target value in the ideal target vector is a minimum value among the first performance indexes of |Q| individuals, a second ideal target value is a minimum value among the second performance indexes of |Q| individuals, a first minimum point target value in the minimum point target vector is a maximum value among the first performance indexes of |Q| individuals, and a second minimum point target value in the minimum point target vector is a maximum value among the second performance indexes of |Q| individuals; Obtain a first aggregate candidate value of the e-th individual according to the first ideal target value, the first minimum target value, the first performance indicator of the e-th individual, and the e-th weight vector associated with the e-th individual; obtain a second aggregate candidate value of the e-th individual according to the second ideal target value, the second minimum target value, the second performance indicator of the e-th individual, and the e-th weight vector associated with the e-th individual; e is a positive integer greater than or equal to 1 and less than or equal to |Q|; A selection index for the e-th individual is determined according to the first aggregate candidate value and the second aggregate candidate value of the e-th individual.

11. The method according to claim 10, characterized in that The device parameters include power device price and feeder price; The first performance indicator includes the construction cost of the individual, and the second performance indicator includes the average power loss of the individual; The first performance index and the second performance index of each individual are obtained, including: Obtaining the construction cost of the individual according to the power devices contained in the individual and the prices of the power devices, and the length of the feeder contained in the individual and the price of the feeder; The power consumption of the connection path from the signal source in the individual to each floor of the building is obtained, and the average power loss of the individual is obtained according to the power consumption of the connection path from the signal source in the individual to each floor of the building.

12. The method according to claim 1, characterized in that Based on the selection index of the offspring individual and the selection index of the parent individual in the neighborhood of the weight vector associated with the corresponding offspring individual, the offspring population is used to update the parent population, comprising: If the selection index of the nth offspring individual is smaller than the selection index of the parent individual in the neighborhood of the nth offspring individual, the nth offspring individual is used to replace the parent individual in the neighborhood of the nth offspring individual.

13. A topology design device for an indoor distributed antenna system, characterized in that: include: An acquisition unit, used for acquiring building parameters, device parameters and signal source information; A processing unit, configured to generate a parent population according to the device parameters, the building parameters and the signal source information, wherein the parent population includes N parent individuals, where N is an integer greater than 1; The processing unit is further used to obtain N weight vectors and a neighborhood of each weight vector, and associate the nth weight vector with the nth parent individual, where n is an integer greater than or equal to 1 and less than or equal to N; The processing unit is further used to perform crossover mutation processing on the parent individuals in the parent population according to the weight vector associated with each parent individual in the parent population and its neighborhood, so as to generate a child population including N child individuals; The processing unit is further used to obtain a selection index for each parent individual and each child individual, each parent individual and each child individual corresponding to an inter-layer network structure of the indoor distributed antenna system; The processing unit is further configured to update the parent population using the offspring population based on the selection index of the offspring individual and the selection index of the parent individual in the neighborhood of the weight vector associated with the corresponding offspring individual; The processing unit is further used to determine the target inter-layer network structure of the indoor distributed antenna system according to the updated parent population.

14. A computer device, characterized in that: Includes processor, memory, input and output interfaces; The processor is connected to the memory and the input / output interface respectively, wherein the input / output interface is used to receive and output data, the memory is used to store a computer program, and the processor is used to call the computer program so that the computer device executes the method described in any one of claims 1-12.

15. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and the computer program is suitable for being loaded and executed by a processor, so that a computer device having the processor executes the method according to any one of claims 1 to 12.

Images