Wireless communication site planning method based on multi-target genetic algorithm

Abstract

The invention discloses a wireless communication site planning method based on a multi-target genetic algorithm, and relates to the technical field of communication. The method comprises the steps of firstly deploying an initial position of each communication site in a GIS platform, then determining a movable adjustment point corresponding to each communication site according to site adjustment parameters, and generating an initial population based on the initial position of the movable adjustment point corresponding to each communication site and the movable adjustment point; and selecting, crossing and mutating individuals in the population according to the genetic algorithm, and decoding the optimal individual when the number of iterations is reached or the fitness value of the optimal individual reaches a fitness threshold, thereby completing wireless communication site planning based on the multi-target genetic algorithm. According to the method, the site of the communication node in the large-scale complex wireless communication network can be efficiently planned, and the mobile wireless communication system can be rapidly constructed.

Description

Technical Field

[0001] The invention relates to the field of communication technology, and in particular to a wireless communication site planning method based on a multi-objective genetic algorithm. Background Art

[0002] In the field of mobile wireless communications, the communication effect of wireless communication links is greatly affected by factors such as terrain and environment. Reasonable site planning will maximize the efficiency of the wireless communication network. In a communication network containing multiple communication nodes and complex connection relationships between nodes, the feasible domain of planning communication node sites is rapidly expanded. Most existing technologies do not consider the influence of terrain when planning mobile communication node sites, or when considering the influence of terrain, the calculation speed is slow or no calculation results can be obtained when performing multi-node site planning due to the large amount of calculation. It is not suitable for use in wireless communication systems that require frequent site changes. Therefore, an efficient planning algorithm is urgently needed. Summary of the invention

[0003] In view of this, the present invention proposes a wireless communication site planning method based on a multi-objective genetic algorithm. The method can efficiently plan the site of communication nodes in a large and complex wireless communication network and assist in the rapid construction of a mobile wireless communication system.

[0004] In order to achieve the above object, the technical solution adopted by the present invention is as follows:

[0005] A wireless communication site planning method based on a multi-objective genetic algorithm comprises the following steps:

[0006] Step 1: According to the requirements for building a wireless communication network, deploy the initial position of each communication site in the GIS platform and obtain the corresponding longitude and latitude information, equip each communication site with corresponding communication equipment, set communication parameters, connect each communication site, and build a network topology;

[0007] Step 2: Set the site adjustment parameters: including the movable range of each communication site and the adjustment distance accuracy;

[0008] Step 3: Obtain the movable adjustment points corresponding to each communication site according to the movable range and the adjustment distance accuracy, and obtain the longitude and latitude information of the movable adjustment points according to the GIS platform elevation map; wherein the adjustment distance accuracy is not less than the GIS platform elevation map accuracy;

[0009] Step 4: Set the number of individuals in the population S, and encode the initial population according to the initial position and movable adjustment point corresponding to each communication site. Each individual in the population represents a plan that includes the site planning of all communication sites.

[0010] Step 5: Set the number of crossover points J and the mutation probability ρ m, fitness threshold, iteration threshold and variable t indicating the number of iterations, let t = 1;

[0011] Step 6, calculate the fitness value of each individual in the current population. If the maximum fitness value is greater than or equal to the fitness threshold, the corresponding individual is recorded as the best individual, and the best individual is decoded to obtain the site planning of all communication sites, completing the wireless communication site planning method based on the multi-objective genetic algorithm. If the maximum fitness value is less than the fitness threshold, execute step 7;

[0012] Step 7, according to the fitness value of each individual in the current population combined with the roulette method, the individuals of the current population are selected to obtain a new population;

[0013] Step 8: For the selected new population, according to the number of crossover points J and the mutation probability ρ m Perform crossover and mutation operations to obtain a new population after iteration;

[0014] Step 9, determine whether t is less than the iteration threshold. If so, set t=t+1 and return to step 6 based on the new population after the iteration. Otherwise, calculate the fitness value of each individual in the new population after the iteration, record the individual corresponding to the maximum fitness value as the best individual, decode the best individual, obtain the site planning of all communication sites, and complete the wireless communication site planning method based on multi-objective genetic algorithm.

[0015] Furthermore, the specific method of step 4 is:

[0016] Step 401: for the nth communication site, the corresponding initial position and movable adjustment point are numbered as a n , where n = 1, 2, 3, ..., N, N represents the total number of communication sites;

[0017] a n =0,1,2,……,A n , A n +1 indicates the total number of initial positions and movable adjustment points corresponding to the nth communication site;

[0018] Step 402, for the nth communication site, at 0, 1, 2, ..., A n Select a random number from M and convert it into n Bit binary number, where

[0019] Step 403: The M corresponding to each of the N communication sites n The binary numbers are concatenated in order to obtain a length of The binary chromosomes of , as one of the individuals;

[0020] Step 404, continuously executing steps 402 and 403 until the number of individuals generated reaches the number of individuals in the population S, and obtaining the initial population.

[0021] Furthermore, the specific method of calculating the fitness value of each individual in the current population in step 6 is:

[0022] Step 601: for a certain individual in the current population, according to the M corresponding to each of the N communication sites, n The length of the binary number is divided in sequence, and the corresponding binary number is converted into a decimal number, so as to obtain the site number corresponding to each of the N communication sites, and the corresponding longitude and latitude information is obtained according to the site number. According to the network topology, the longitude and latitude information of the N communication sites and the communication parameters, the communication margin and the on-off status of each wireless link are calculated in combination with the wireless channel prediction model;

[0023] Step 602, setting a communication margin threshold. If the communication margin corresponding to a certain wireless link is greater than or equal to the communication margin threshold, the communication margin calculation value is recorded as 1, otherwise the communication margin calculation value is recorded as the result of dividing the communication margin by the communication margin threshold; if a certain wireless link is connected, its on-off status is recorded as 1, otherwise its on-off status is recorded as 0;

[0024] Calculate the average value of the communication margin calculation value and the average value of the on-off conditions of all wireless links, and then calculate the weighted value of the average value of the communication margin calculation value and the average value of the on-off conditions, which is recorded as the fitness value of the current individual, where the average value of the communication margin calculation value corresponds to a weight of 20%, and the average value of the on-off conditions corresponds to a weight of 80%.

[0025] Furthermore, the specific method of step 7 is:

[0026] For a certain individual in the current population, its corresponding fitness value is divided by the sum of the fitness values ​​of all individuals in the current population. The calculation result is recorded as the roulette selection probability of the current individual. Based on the roulette selection probability of each individual in the current population and the roulette method, the individuals of the current population are selected until S individuals are selected, thereby obtaining a new population.

[0027] Furthermore, the specific method of step 8 is:

[0028] Step 801, for the selected new population, randomly select 2Q individuals, group them in pairs, and obtain Q groups of individuals;

[0029] For two individuals in each group, J crossover points are randomly set, and then gene exchange is performed in an interval exchange manner;

[0030] Based on the individuals in the selected new population that have not undergone gene exchange and the individuals that have undergone gene exchange, the population after crossover is formed;

[0031] Step 802: Generate a corresponding random number r for each binary bit of each individual in the population after crossover, r∈[0,1], if r≤ρ m , then the binary bit is inverted, otherwise the binary bit remains unchanged; the mutated population is obtained;

[0032] Step 803: for each individual in the mutated population, the M corresponding to each of the N communication sites is n The length of the binary number is divided into two parts in sequence, and for the nth communication station, the corresponding M n Convert the binary number to decimal, record it as A' n ;calculate The value of the calculation result is rounded off and recorded as the site number corresponding to the nth communication site; the site number is converted to M n After the binary number is set, the M corresponding to each of the N communication sites n The bit binary numbers are spliced ​​in sequence to obtain new individuals after iteration, and S new individuals after iteration constitute the new population after iteration.

[0033] Due to the adoption of the above technical solution, the beneficial effects of the present invention compared with the prior art are:

[0034] 1. The present invention constructs a mathematical model for the simultaneous planning of multiple communication site locations, constitutes the site selection of all communication sites into a chromosome, and realizes the site synchronization optimization function based on multi-objective constraints according to the calculation of corresponding fitness values.

[0035] 2. The present invention adopts a genetic algorithm to solve the site planning problem of large-scale complex mobile wireless communication networks, and can efficiently and quickly plan the communication node sites synchronously. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 The figure is a schematic diagram of the overall process of a wireless communication site planning method based on a multi-objective genetic algorithm in an embodiment of the present invention.

[0037] Figure 2 Schematic diagram of the principle of encoding and decoding chromosomes in an embodiment of the present invention.

[0038] Figure 3 Schematic diagram of the process of calculating the fitness value of a chromosome in an embodiment of the present invention.

[0039] Figure 4 Schematic diagram of crossover operation in an embodiment of the present invention. DETAILED DESCRIPTION

[0040] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0041] A wireless communication site planning method based on multi-objective genetic algorithm, such as Figure 1 As shown, the following steps are included:

[0042] Step 1: According to the requirements for building a wireless communication network, deploy the initial position of each communication site in the GIS platform and obtain the corresponding longitude and latitude information, equip each communication site with corresponding communication equipment, set communication parameters, connect each communication site, and build a network topology;

[0043] Step 2: Set the site adjustment parameters: including the movable range of each communication site and the adjustment distance accuracy;

[0044] Step 3: Obtain the movable adjustment points corresponding to each communication site according to the movable range and the adjustment distance accuracy, and obtain the longitude and latitude information of the movable adjustment points according to the GIS platform elevation map; wherein the adjustment distance accuracy is not less than the GIS platform elevation map accuracy;

[0045] Specifically, in this embodiment, for each communication site, within its corresponding movable range, sampling is performed with the adjustment distance accuracy as the sampling point distance, and multiple movable adjustment points are obtained. The distance between the initial position and each movable adjustment point and between two movable adjustment points are not less than the accuracy of the GIS platform elevation map; and the longitude and latitude information of the movable adjustment points are obtained according to the GIS platform elevation map;

[0046] Step 4: Set the number of individuals in the population S, and encode the initial population according to the initial position and movable adjustment point corresponding to each communication site. Each individual in the population represents a plan that includes the site planning of all communication sites.

[0047] Among them, each individual is regarded as a chromosome;

[0048] Step 5: Set the number of crossover points J and the mutation probability ρ m , fitness threshold, iteration threshold and variable t indicating the number of iterations, let t = 1;

[0049] Step 6, calculate the fitness value of each individual in the current population. If the maximum fitness value is greater than or equal to the fitness threshold, the corresponding individual is recorded as the best individual, and the best individual is decoded to obtain the site planning of all communication sites, completing the wireless communication site planning method based on the multi-objective genetic algorithm. If the maximum fitness value is less than the fitness threshold, execute step 7;

[0050] Step 7, according to the fitness value of each individual in the current population combined with the roulette method, the individuals of the current population are selected to obtain a new population;

[0051] Step 8: For the selected new population, according to the number of crossover points J and the mutation probability ρ m Perform crossover and mutation operations to obtain a new population after iteration;

[0052] Step 9, determine whether t is less than the iteration threshold. If so, set t=t+1 and return to step 6 based on the new population after the iteration. Otherwise, calculate the fitness value of each individual in the new population after the iteration, record the individual corresponding to the maximum fitness value as the best individual, decode the best individual, obtain the site planning of all communication sites, and complete the wireless communication site planning method based on multi-objective genetic algorithm.

[0053] Furthermore, if Figure 2 As shown, the specific method of step 4 is:

[0054] Step 401: for the nth communication site, the corresponding initial position and movable adjustment point are numbered as a n , where n = 1, 2, 3, ..., N, N represents the total number of communication sites;

[0055] a n =0,1,2,……,A n , A n +1 indicates the total number of initial positions and movable adjustment points corresponding to the nth communication site;

[0056] Step 402, for the nth communication site, at 0, 1, 2, ..., A n Select a random number from M and convert it into n Bit binary number, where

[0057] Step 403: The M corresponding to each of the N communication sites n The binary numbers are concatenated in order to obtain a length of The binary chromosomes of , as one of the individuals;

[0058] Step 404, continuously executing steps 402 and 403 until the number of individuals generated reaches the number of individuals in the population S, and obtaining the initial population.

[0059] Furthermore, if Figure 3 As shown, the specific method for calculating the fitness value of each individual in the current population in step 6 is:

[0060] Step 601: for a certain individual in the current population, according to the M corresponding to each of the N communication sites, n The length of the binary number is divided in sequence, and the corresponding binary number is converted into a decimal number, so as to obtain the site number corresponding to each of the N communication sites, and the corresponding longitude and latitude information is obtained according to the site number. According to the network topology, the longitude and latitude information of the N communication sites and the communication parameters, the communication margin and the on-off status of each wireless link are calculated in combination with the wireless channel prediction model;

[0061] Step 602, setting a communication margin threshold. If the communication margin corresponding to a certain wireless link is greater than or equal to the communication margin threshold, the communication margin calculation value is recorded as 1, otherwise the communication margin calculation value is recorded as the result of dividing the communication margin by the communication margin threshold; if a certain wireless link is connected, its on-off status is recorded as 1, otherwise its on-off status is recorded as 0;

[0062] Calculate the average value of the communication margin calculation value and the average value of the on-off conditions of all wireless links, and then calculate the weighted value of the average value of the communication margin calculation value and the average value of the on-off conditions, which is recorded as the fitness value of the current individual, where the average value of the communication margin calculation value corresponds to a weight of 20%, and the average value of the on-off conditions corresponds to a weight of 80%.

[0063] Furthermore, the specific method of step 7 is:

[0064] For a certain individual in the current population, its corresponding fitness value is divided by the sum of the fitness values ​​of all individuals in the current population. The calculation result is recorded as the roulette selection probability of the current individual. Based on the roulette selection probability of each individual in the current population and the roulette method, the individuals of the current population are selected until S individuals are selected, thereby obtaining a new population.

[0065] Furthermore, the specific method of step 8 is:

[0066] Step 801, for the selected new population, randomly select 2Q individuals, group them in pairs, and obtain Q groups of individuals;

[0067] like Figure 4 As shown, for two individuals in each group, J crossover points are randomly set, and then gene exchange is performed in an interval exchange manner;

[0068] Based on the individuals in the selected new population that have not undergone gene exchange and the individuals that have undergone gene exchange, the population after crossover is formed;

[0069] Step 802: Generate a corresponding random number r for each binary bit of each individual in the population after crossover, r∈[0,1], if r≤ρ m, then the binary bit is inverted, otherwise the binary bit remains unchanged; the mutated population is obtained;

[0070] Specifically, in this embodiment, two or more intersection points are set, 0<ρ m ≤0.05;

[0071] Step 803: for each individual in the mutated population, the M corresponding to each of the N communication sites is n The length of the binary number is divided into two parts in sequence, and for the nth communication station, the corresponding M n Convert the binary number to decimal, record it as A' n ;calculate The value of the calculation result is rounded off and recorded as the site number corresponding to the nth communication site; the site number is converted to M n After the binary number is set, the M corresponding to each of the N communication sites n The bit binary numbers are spliced ​​in sequence to obtain new individuals after iteration, and S new individuals after iteration constitute the new population after iteration.

[0072] Specifically, in this embodiment, Figure 2 As shown, decoding is performed for the best individual: according to the M corresponding to each of the N communication sites n The binary number length is divided in sequence, and the corresponding binary number is converted into decimal number to obtain the site number corresponding to each of the N communication sites. The corresponding longitude and latitude information is obtained according to the site number, and each communication site is adjusted to the longitude and latitude corresponding to the corresponding site number to complete the wireless communication site planning based on the multi-objective genetic algorithm.

[0073] In summary, the present invention can efficiently plan the sites of communication nodes in a large and complex wireless communication network, and assist in the rapid construction of a mobile wireless communication system.

[0074] Those skilled in the art will appreciate that the embodiments described are intended to help readers understand the principles of the present invention, and should be understood that the scope of protection of the present invention is not limited to the embodiments described. For those skilled in the art, the present invention may have various changes and variations. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of the claims of the present invention.

Claims

1. A wireless communication site planning method based on a multi-objective genetic algorithm, characterized in that: The following steps are involved: Step 1: According to the requirements for building a wireless communication network, deploy the initial position of each communication site in the GIS platform and obtain the corresponding longitude and latitude information, equip each communication site with corresponding communication equipment, set communication parameters, connect each communication site, and build a network topology; Step 2: Set the site adjustment parameters: including the movable range of each communication site and the adjustment distance accuracy; Step 3: Obtain the movable adjustment points corresponding to each communication site according to the movable range and the adjustment distance accuracy, and obtain the longitude and latitude information of the movable adjustment points according to the GIS platform elevation map; wherein the adjustment distance accuracy is not less than the GIS platform elevation map accuracy; Step 4: Set the number of individuals in the population S, and encode the initial population according to the initial position and movable adjustment point corresponding to each communication site. Each individual in the population represents a plan that includes the site planning of all communication sites. Step 5: Set the number of crossover points J and the mutation probability ρ m , fitness threshold, iteration threshold and variable t indicating the number of iterations, let t = 1; Step 6, calculate the fitness value of each individual in the current population. If the maximum fitness value is greater than or equal to the fitness threshold, the corresponding individual is recorded as the best individual, and the best individual is decoded to obtain the site planning of all communication sites, completing the wireless communication site planning method based on the multi-objective genetic algorithm. If the maximum fitness value is less than the fitness threshold, execute step 7; Step 7, according to the fitness value of each individual in the current population combined with the roulette method, the individuals of the current population are selected to obtain a new population; Step 8: For the selected new population, according to the number of crossover points J and the mutation probability ρ m Perform crossover and mutation operations to obtain a new population after iteration; Step 9, determine whether t is less than the iteration threshold. If so, set t=t+1 and return to step 6 based on the new population after the iteration. Otherwise, calculate the fitness value of each individual in the new population after the iteration, record the individual corresponding to the maximum fitness value as the best individual, decode the best individual, obtain the site planning of all communication sites, and complete the wireless communication site planning method based on multi-objective genetic algorithm.

2. A wireless communication site planning method based on a multi-objective genetic algorithm according to claim 1, characterized in that: The specific method of step 4 is: Step 401: for the nth communication site, the corresponding initial position and movable adjustment point are numbered as a n , where n = 1, 2, 3, ..., N, N represents the total number of communication sites; a n =0,1,2,……,A n , A n +1 indicates the total number of initial positions and movable adjustment points corresponding to the nth communication site; Step 402, for the nth communication site, at 0, 1, 2, ..., A n Select a random number from M and convert it into n Bit binary number, where Step 403: The M corresponding to each of the N communication sites n The binary numbers are concatenated in order to obtain a length of The binary chromosomes of , as one of the individuals; Step 404, continuously executing steps 402 and 403 until the number of individuals generated reaches the number of individuals in the population S, and obtaining the initial population.

3. A wireless communication site planning method based on a multi-objective genetic algorithm according to claim 2, characterized in that: The specific method for calculating the fitness value of each individual in the current population in step 6 is: Step 601: for a certain individual in the current population, according to the M corresponding to each of the N communication sites, n The length of the binary number is divided in sequence, and the corresponding binary number is converted into a decimal number, so as to obtain the site number corresponding to each of the N communication sites, and the corresponding longitude and latitude information is obtained according to the site number. According to the network topology, the longitude and latitude information of the N communication sites and the communication parameters, the communication margin and the on-off status of each wireless link are calculated in combination with the wireless channel prediction model; Step 602, setting a communication margin threshold. If the communication margin corresponding to a certain wireless link is greater than or equal to the communication margin threshold, the communication margin calculation value is recorded as 1, otherwise the communication margin calculation value is recorded as the result of dividing the communication margin by the communication margin threshold; if a certain wireless link is connected, its on-off status is recorded as 1, otherwise its on-off status is recorded as 0; Calculate the average value of the communication margin calculation value and the average value of the on-off conditions of all wireless links, and then calculate the weighted value of the average value of the communication margin calculation value and the average value of the on-off conditions, which is recorded as the fitness value of the current individual, where the average value of the communication margin calculation value corresponds to a weight of 20%, and the average value of the on-off conditions corresponds to a weight of 80%.

4. A wireless communication site planning method based on a multi-objective genetic algorithm according to claim 3, characterized in that: The specific method of step 7 is: For a certain individual in the current population, its corresponding fitness value is divided by the sum of the fitness values ​​of all individuals in the current population. The calculation result is recorded as the roulette selection probability of the current individual. Based on the roulette selection probability of each individual in the current population and the roulette method, the individuals of the current population are selected until S individuals are selected, thereby obtaining a new population.

5. A wireless communication site planning method based on a multi-objective genetic algorithm according to claim 4, characterized in that: The specific method of step 8 is: Step 801, for the selected new population, randomly select 2Q individuals, group them in pairs, and obtain Q groups of individuals; For two individuals in each group, J crossover points are randomly set, and then gene exchange is performed in an interval exchange manner; Based on the individuals in the selected new population that have not undergone gene exchange and the individuals that have undergone gene exchange, the population after crossover is formed; Step 802: Generate a corresponding random number r for each binary bit of each individual in the population after crossover, r∈[0,1], if r≤ρ m , then the binary bit is inverted, otherwise the binary bit remains unchanged; the mutated population is obtained; Step 803: for each individual in the mutated population, the M corresponding to each of the N communication sites is n The length of the binary number is divided into two parts in sequence, and for the nth communication station, the corresponding M n Convert the binary number to decimal, denoted as A' n ;calculate The value of the calculation result is rounded off and recorded as the site number corresponding to the nth communication site; the site number is converted to M n After the binary number is set, the M corresponding to each of the N communication sites n The bit binary numbers are spliced ​​in sequence to obtain new individuals after iteration, and S new individuals after iteration constitute the new population after iteration.

Images