WO2023082288A1 - 天线参数组合的确定方法及相关装置 - Google Patents

天线参数组合的确定方法及相关装置 Download PDF

Info

Publication number
WO2023082288A1
WO2023082288A1 PCT/CN2021/130770 CN2021130770W WO2023082288A1 WO 2023082288 A1 WO2023082288 A1 WO 2023082288A1 CN 2021130770 W CN2021130770 W CN 2021130770W WO 2023082288 A1 WO2023082288 A1 WO 2023082288A1
Authority
WO
WIPO (PCT)
Prior art keywords
antenna parameter
antenna
parameter combination
index
value
Prior art date
Application number
PCT/CN2021/130770
Other languages
English (en)
French (fr)
Inventor
胡琴涛
Original Assignee
华为技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Priority to CN202180103762.2A priority Critical patent/CN118160342A/zh
Priority to PCT/CN2021/130770 priority patent/WO2023082288A1/zh
Publication of WO2023082288A1 publication Critical patent/WO2023082288A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • H—ELECTRICITY
    • H01—ELECTRIC ELEMENTS
    • H01Q—ANTENNAS, i.e. RADIO AERIALS
    • H01Q3/00—Arrangements for changing or varying the orientation or the shape of the directional pattern of the waves radiated from an antenna or antenna system
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04B—TRANSMISSION
    • H04B7/00—Radio transmission systems, i.e. using radiation field
    • H04B7/02—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas
    • H04B7/04—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas
    • H04B7/06—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station

Definitions

  • the present application relates to the field of wireless communication technologies, and in particular to a method for determining an antenna parameter combination and a related device.
  • the antenna parameters such as azimuth, inclination, and weight of the cell antenna are closely related to the communication indicators such as the coverage rate of the signal of the cell antenna and the degree of signal interference.
  • the communication indicators such as the coverage rate of the signal of the cell antenna and the degree of signal interference.
  • no matter how to adjust the parameters of the antenna it is often impossible to find a set of parameters so that each communication index can be optimized at the same time. For example, when the coverage is greater, the degree of mutual interference between antenna signals may be more serious.
  • the antenna parameters of different cells among multiple sites need to be planned collaboratively to determine the appropriate combination of antenna parameters so that the communication indicators of the cell antenna signals can achieve relatively optimal values.
  • the embodiment of the present application provides a method for determining antenna parameter combinations and a related device. This method selects particles that match the user's needs from the particle population according to the user's needs as the parent particles of the subsequent offspring, which can be faster and more efficient. An antenna parameter combination that matches the user's actual needs is efficiently obtained from the offspring of each generation, and the determination speed of the antenna parameter combination is improved.
  • the embodiment of the present application provides a method for determining an antenna parameter combination, the method includes: obtaining the value of each antenna parameter combination in N groups of antenna parameter combinations, the first of the N groups of antenna parameter combinations The value of the antenna parameter combination represents the degree of adaptation between the first antenna parameter combination and the user's needs; among the N groups of antenna parameter combinations, the M groups of antenna parameter combinations with a larger value are used as the candidate antenna parameter set, and the M is less than the set N, the M is an integer greater than 0, and the N is an integer greater than 1; the antenna parameter combination in the candidate antenna parameter set is used as the parent to determine the target antenna parameter combination, and the target antenna parameter combination is used for The antenna transmits the signal.
  • the user requirements include the priority of the user's demand for antenna signals on multiple communication indicators and the requirements on the compliance rate of these multiple communication indicators.
  • the plurality of communication indicators may include antenna signal coverage, rate, degree of interference between signals, etc.
  • the quality of these communication indicators is determined by, for example, direction angle, downtilt angle, horizontal lobe width, vertical lobe width, One or more of antenna parameter combinations such as the number of beams and weight parameters are determined.
  • the antenna uses combination 1 to transmit The coverage rate of the signal is 90% and the rate is 58.5Mbit/s, and the coverage rate of the signal transmitted by the antenna using combination 2 is 88% and the rate is 65Mbit/s, then the device will select combination 1 as the candidate antenna parameter set Antenna parameter combinations in , and use combination 1 as other antenna parameter combinations in the parent candidate antenna parameter set for cross mutation to obtain the next offspring.
  • This method sets the value for each antenna parameter combination in combination with the user's intention. During the selection process of each generation of offspring, the antenna parameters that match the user's actual needs can be obtained from each generation of offspring more quickly and efficiently. Combination, to improve the speed of determining the combination of antenna parameters.
  • the obtaining the value of each group of antenna parameter combinations in the N groups of antenna parameter combinations includes: obtaining P incentives of the first antenna parameter combination on P communication indicators value, the incentive value of the first antenna parameter combination on the first indicator among the P communication indicators is the completion amount of the first antenna parameter combination on the first indicator, and the Q number of the first indicators The interval and the Q excitation coefficients corresponding to the Q intervals are determined, the completion amount represents the quality of the communication quality of the signal transmitted by the antenna using the first parameter combination on the first index, and the P and the Q is an integer greater than 1; and the value of the first antenna parameter combination is obtained according to the P incentive values of the first antenna parameter combination on the P communication indicators.
  • the P communication indicators may include indicators such as antenna signal coverage, rate, and degree of interference between signals.
  • the first indicator is an indicator among the P communication indicators, which may be any indicator among indicators such as antenna signal coverage, rate, and signal.
  • the Q intervals of the first index can be set according to the user's requirement.
  • the optimal value of the first index (that is, the best degree that the first index can achieve) is 100
  • the user's requirement for the first index is that the value of the first index cannot be lower at 90.
  • the aforementioned Q intervals may be [0, 80], [80, 90], and [90, 100]
  • the corresponding excitation coefficients may be 10, 1, and 0, respectively.
  • the incentive value of the first antenna parameter combination on the first index can be calculated through the relationship between the completion amount and the Q intervals.
  • the difference between the completion amount of the antenna parameter combination on each of the P indicators and the user's expected value is obtained. Calculate the incentive value of the antenna parameter combination on each index, so that the value of the antenna parameter combination can fully reflect the degree of adaptation between the antenna parameter combination and the user's intention.
  • the method before acquiring the P incentive values of the first antenna parameter combination on the P communication indicators, the method further includes: acquiring the first parameter and the second parameter;
  • the first parameter includes a target threshold for each communication indicator in the P communication indicators, the second parameter includes the weight of each communication indicator in the P communication indicators, and the P is an integer greater than 1;
  • the first parameter and the second parameter are used to determine Q intervals of the first indicator, and Q excitation coefficients corresponding to the Q intervals.
  • the Q intervals of the first index and the incentive coefficients corresponding to the Q intervals may be set according to the user requirements.
  • the following examples give four specific user requirements:
  • User requirement 1 Prioritize the optimization degree of the first goal, and the user's requirement for the first index is that the value of the first index cannot be lower than N1.
  • the Q intervals of the first index can be set as [0, N1] and [N1, 100], and the corresponding incentive coefficients can be 1 and 0 respectively.
  • the above Q intervals can be set as [0, N1-10], [N1-10, N1] and [N1-10, 100], and the corresponding excitation coefficients can be w1, w2 and w3 respectively , and w1>w2>w3.
  • the Q indicators also include multiple indicators such as the second indicator and the third indicator.
  • the user requires the first index to be the expected value of the first index N2, but it is allowed to deteriorate, but the degree of deterioration cannot exceed a lower limit (that is, the antenna parameters in the child generation are allowed to be combined on the first index
  • the completion amount of the antenna parameter combination in the offspring is less than the completion amount of the antenna parameter combination in the first index, but the completion amount of the antenna parameter combination in each subsequent generation on the first index cannot be less than a certain
  • the preset threshold here it is assumed that the threshold is N3), focuses on ensuring the degree of optimization of the second index, the third index and other indexes in subsequent generations.
  • the completion amount on the first index is at most N4.
  • N4 is less than N3 (that is, when the completion amount of all antenna parameter combinations on the first index in the G1 generation is less than N3)
  • the Q intervals of the first index can be set to [0, N4], [N4, N3], [N3, 100]
  • the corresponding excitation coefficients can be w4, w5 and w6 respectively, and w4>w5>w6.
  • N4 is greater than N3 (that is, in all antenna parameter combinations in the G1 generation, the completion amount of the antenna parameter combination on the first index is greater than N3)
  • the Q intervals can be set arbitrarily, and the excitation coefficients corresponding to the Q intervals are all negative infinity; if the completion amount of the first antenna parameter combination on the first index is not less than N3, then the first The Q intervals of the index can be set as [0, N2], [N2, 100], and the corresponding incentive coefficients can be w7 and w8 respectively, and w7 ⁇ w8.
  • the Q indicators also include multiple indicators such as the second indicator and the third indicator.
  • the user requires the first indicator to have an expected value of N5, and the user hopes to focus on ensuring all Describe the optimization degree of the second indicator, the third indicator and other indicators in the subsequent offspring.
  • the user wishes to optimize the Q indicators at the same time. And if the antenna parameter combination in the parent parent has reached the user's expectation for a certain indicator, then in the subsequent process, the degree of optimization for this indicator can be reduced.
  • the maximum amount of completion on the first index is N6.
  • the Q intervals of the first index can be set as [0, N6-N7], [N6-N7, N5] and [N5, 100], where N7 can be any positive integer smaller than N6;
  • the corresponding excitation coefficients may be w7, w8 and w9 respectively, and w8>w7>w9.
  • the Q indicators also include multiple indicators such as the second indicator and the third indicator, and the user hopes that the value of the parameter combination finally used for the antenna can be the largest.
  • the maximum completion amount on the first index is N8.
  • the Q intervals of the first index can be set as [0, N8-N9], [N8-N9, 100], wherein N9 can be any positive integer smaller than N8; the corresponding incentive coefficients can be respectively are w10 and w11, and w11>w10.
  • the above-mentioned Q intervals of the first indicator and the corresponding Q excitation coefficients need to be set before the antenna parameter combination starts to be optimized (that is, the first-generation antenna parameter combination is generated). That is to say, in the subsequent process of antenna parameter combination optimization, the device only needs to set the Q intervals of the first index and the corresponding Q excitations for the antenna parameter combination in the child generation according to user requirements. coefficient.
  • the Q intervals of the first index include the first interval and the second interval, and the right endpoint value of the first interval is less than or equal to the left end of the second interval point value, the excitation coefficient corresponding to the second interval is the second excitation coefficient, the excitation coefficient corresponding to the first interval is the first excitation coefficient, and the second excitation coefficient is smaller than the first excitation coefficient.
  • the optimization degrees of multiple objectives are contradictory. For example, when the coverage ratio of antenna signals is larger, the interference between signals tends to be stronger. Therefore, in this embodiment, when the completion amount of the certain antenna parameter combination on the first index is greater, the antenna parameter combination is closer to the customer's expectation on the first index.
  • the Q excitation coefficients corresponding to the Q intervals are set to decrease with the increase of the interval value, so as to avoid the continuous optimization of the index in the subsequent sub-generations (that is, the antenna parameter combinations generated subsequently) , in exchange for the subsequent optimization of the antenna parameter combination on other indicators, and obtain an antenna parameter combination with better overall communication quality in each indicator.
  • the value of the left end point of the second interval is the completion amount of the first antenna parameter combination on the first index, and the completion amount indicates that the antenna adopts The quality of the communication quality of the signal transmitted by the first parameter combination on the first indicator.
  • the Q intervals of the first index may further include multiple intervals such as a third interval and a fourth interval.
  • the left endpoint value in the second interval is greater than any value contained in other (Q-1) intervals. Setting the left end point value of the second interval as the completion amount of combining the first antenna parameters on the first index can control more precisely while satisfying the user's demand for the first index.
  • the gap between the completion amount of the first indicator in the antenna parameter combination in the subsequent offspring and the user's demand for the first indicator is exchanged for the greater performance of the antenna parameter combination generated subsequently in other indicators. degree of optimization.
  • the second excitation coefficient is less than or equal to zero.
  • any value in the second interval corresponding to the second incentive coefficient is greater than the user's demand for the first index.
  • the completion amount of the first antenna parameter combination on the first index exceeds the user's demand for the first index, by adjusting the second excitation coefficient to 0 or a negative number, it is possible to avoid the situation similar to the first
  • An antenna parameter combination that is overoptimized on the first index is determined to be the parent of the next generation. In this way, in the case of satisfying the user's demand for the first index, it is possible to more precisely control the completion amount of the antenna parameter combination in the subsequent offspring on the first index and the user's requirement for the first index. In exchange for the gap in the requirements of the antenna parameter combination generated in the future, a greater degree of optimization in other indicators.
  • using the M groups of antenna parameter combinations with higher value in the N groups of antenna parameter combinations as the candidate antenna parameter set includes: The value is in the top M antenna parameter combinations as a set of candidate antenna parameters.
  • the value of the top M antenna parameter combinations is used as a candidate antenna parameter set, and in the process of crossover and mutation of subsequent antenna parameter combinations (that is, generation of offspring by genetic algorithm) In , the matching degree of antenna parameter combinations in offspring and user requirements can be ensured to the greatest extent.
  • the embodiment of the present application provides a device for determining an antenna parameter combination
  • the device includes: a calculation unit, configured to obtain the value of each group of antenna parameter combinations in N groups of antenna parameter combinations, and the N groups of antenna parameter combinations
  • the value of the first antenna parameter combination in the combination represents the degree of adaptation between the first antenna parameter combination and the user's needs
  • the determining unit is configured to use the M group of antenna parameter combinations with a larger value among the N groups of antenna parameter combinations as A set of candidate antenna parameters, the M is smaller than the N, the M is an integer greater than 0, and the N is an integer greater than 1
  • a genetic unit is used to combine the antenna parameters in the candidate antenna parameter set as a parent
  • a target antenna parameter combination is determined, which is used for the antenna to transmit signals.
  • the calculation unit is specifically configured to: obtain P excitation values of the first antenna parameter combination on P communication indicators, and the first antenna parameter combination is in The completion amount of the incentive value on the first indicator among the P communication indicators combined with the first antenna parameters on the first indicator, and the Q intervals of the first indicator and the Q intervals corresponding to the Q intervals.
  • the number of excitation coefficients is determined, the completion amount characterizes the quality of the communication quality of the signal transmitted by the antenna using the first parameter combination on the first index, and the P and the Q are integers greater than 1;
  • the value of the first antenna parameter combination is obtained according to the P incentive values of the first antenna parameter combination on the P communication indicators.
  • the device further includes: an acquiring unit, configured to acquire a first parameter and a second parameter; the first parameter includes each communication indicator in the P communication indicators target threshold, the second parameter includes the weight of each communication indicator in the P communication indicators, and the P is an integer greater than 1; the first parameter and the second parameter are used to determine the first Q intervals of an indicator, and Q incentive coefficients corresponding to the Q intervals.
  • the Q intervals of the first index include a first interval and a second interval, and the right endpoint value of the first interval is less than or equal to the left end of the second interval point value, the excitation coefficient corresponding to the second interval is the second excitation coefficient, the excitation coefficient corresponding to the first interval is the first excitation coefficient, and the second excitation coefficient is smaller than the first excitation coefficient.
  • the value of the left end point of the second interval is the completion amount of the first antenna parameter combination on the first index, and the completion amount indicates that the antenna adopts The quality of the communication quality of the signal transmitted by the first parameter combination on the first indicator.
  • the second excitation coefficient is less than or equal to zero.
  • the determining unit is specifically configured to: use the top M antenna parameter combinations among the N groups of antenna parameter combinations as candidate antenna parameter sets.
  • the embodiment of the present application provides an electronic device, including: a memory for storing a program; a processor for executing the program stored in the memory, and when the program is executed, the processing The device is used to execute the method according to the first aspect and any optional implementation manner.
  • an embodiment of the present application provides a computer-readable storage medium, the computer storage medium stores a computer program, the computer program includes program instructions, and when executed by a processor, the program instructions cause the processor to Execute the method in the first aspect and any optional implementation manner.
  • FIG. 1A is a Pareto front diagram of an antenna parameter combination optimization solution provided by an embodiment of the present application
  • FIG. 1B is a schematic diagram of a set of candidate antennas provided by an embodiment of the present application.
  • FIG. 2 is a flowchart of a method for determining an antenna parameter combination provided in an embodiment of the present application
  • FIG. 3 is a flow chart of a method for determining a candidate parameter set provided in an embodiment of the present application
  • FIG. 4 is a diagram of the relationship between an index interval and an incentive coefficient provided by an embodiment of the present application.
  • Fig. 5 is a relationship diagram between the overall completion amount of an antenna parameter combination on an index and the optimization efficiency of the index provided by the embodiment of the present application;
  • FIG. 6 is a schematic diagram of particle population distribution in a two-dimensional search space provided by an embodiment of the present application.
  • FIG. 7 is a diagram of the relationship between the number of particle iterations and the degree of index optimization provided by the embodiment of the present application.
  • FIG. 8 is a relationship diagram between the number of particle iterations and the coverage optimization degree provided by the embodiment of the present application.
  • FIG. 9 is a schematic structural diagram of a device for determining an antenna parameter combination provided in an embodiment of the present application.
  • FIG. 10 is a schematic structural diagram of an electronic device provided by an embodiment of the present application.
  • Cell parameters include parameters representing the location area of the cell and parameters representing the communication quality of the cell, such as mobile network code, tracking area code, received signal strength, reference signal received power, and sector code.
  • RF means the electromagnetic frequency (300K Hz-300G Hz) that can radiate into space.
  • RF parameters include azimuth, inclination, station height, gain coefficient, beam width, and direction coefficient.
  • Beamforming is the combination of antenna technology and digital signal processing technology for directional signal transmission or reception.
  • BF parameters include weight parameters in large-scale antenna technology.
  • the multi-objective optimization problem is described in words as an optimization problem composed of D decision variable parameters, N objective functions, and (m+n) constraint conditions.
  • the decision variables are functionally related to the objective function and constraint conditions.
  • the decision maker can only choose a satisfactory non-inferior solution as the final solution according to the specific problem requirements.
  • Genetic algorithms originated from computer simulation studies of biological systems. It is a random global search and optimization method developed by imitating the biological evolution mechanism in nature, drawing on Darwin's theory of evolution and Mendel's genetic theory. Its essence is an efficient, parallel, and global search method, which can automatically acquire and accumulate knowledge about the search space during the search process, and adaptively control the search process to obtain the best solution.
  • Pareto optimal solutions constitute the Pareto optimal solution set, and these solutions are mapped by the objective function to form the Pareto optimal front or Pareto front of the problem, that is, the value of the objective function corresponding to the Pareto optimal solution is Pareto optimal frontier.
  • its Pareto front is usually a hypersurface.
  • the completion amount represents the communication quality of the signal transmitted by the antenna using a certain antenna parameter combination on a certain index, which can be quantified into a specific value.
  • the greater the completion amount the better the communication quality.
  • the best effect that the coverage rate of the antenna signal can achieve is 100% coverage, then when the coverage rate of the signal transmitted by the antenna using a certain antenna parameter combination is 90% in the coverage rate, Then the signal transmitted by the antenna using a certain combination of antenna parameters has a coverage rate of 90%.
  • the antenna parameters (RF/BF parameters, etc.) of different cells between multiple sites need to be planned collaboratively to achieve a balance between ensuring coverage and reducing interference.
  • the antenna parameters such as azimuth, inclination, and weight of the cell antenna are closely related to the communication indicators such as the coverage rate of the signal of the cell antenna and the degree of signal interference.
  • no matter how to adjust the parameters of the antenna it is often impossible to find a set of parameters so that each communication index can be optimized at the same time. For example, when the coverage is greater, the degree of mutual interference between antenna signals may be more serious.
  • the antenna parameters of different cells among multiple sites need to be planned collaboratively to determine the appropriate combination of antenna parameters so that the communication indicators of the cell antenna signals can achieve relatively optimal values.
  • FIG. 1A is a Pareto front diagram of an antenna parameter combination optimization solution provided by an embodiment of the present application.
  • FIG. 1A there are a large number of particles in the search space, and these particles are all offspring particles of the same generation produced by the parent of the same generation.
  • the dimensionality of the search space is the same as the number of objective functions in multi-objective optimization problems. That is to say, when there are P communication indicators in the antenna signal, the corresponding search space should be P-dimensional.
  • the search shown in Fig. 1A is a two-dimensional space.
  • particles A-H are selected from the particle population by using the traditional dominant solution quick sorting algorithm. These particles are all Pareto optimal solutions, and A-H also forms the frontier of the search space.
  • the particle A-H will be crossed and mutated as the parent to produce the particle set of the next generation (that is, the offspring); while the remaining particles in the same generation as the particle A-H (such as particle K and particle I Such particles) will be eliminated and will no longer participate in subsequent reproduction processes such as crossover and mutation.
  • each parameter particle from A to H shown in Fig. 1A is an optimal solution in a certain aspect from a relative point of view. If optimization is performed directly based on these relatively optimal solutions, a large amount of optimization computing power will be consumed. In addition, in the actual use process, users have different requirements for various communication indicators of the antenna. The particles determined by the universal sorting and searching method adopted in the above-mentioned method based on the quick sorting of dominant solutions often do not match the actual needs of users.
  • the embodiment of the present application provides a method for determining the combination of antenna parameters. This method selects particles that are suitable for the user's needs from the particle population according to the user's needs as subsequent sub- The parent particle of the first generation can obtain the antenna parameter combination that matches the user's actual needs from the offspring of each generation more quickly and efficiently, and improve the determination speed of the antenna parameter combination.
  • this method can select particles C and D from the particle population that are more suitable for user needs (that is, determine particles C and D as particles in the candidate parameter set), and based on particle C and particle D D continues to cross and mutate until the final antenna parameter combination is generated, which improves the speed of determining the antenna parameter combination.
  • the method may include the following steps:
  • the electronic device obtains the value of each antenna parameter combination in N sets of antenna parameter combinations.
  • the above-mentioned electronic devices can be computers (such as notebook computers, palmtop computers, etc.), mobile phones, tablet computers (pads), mobile Internet devices (mobile internet device, MID), industrial control (industrial control)
  • computers such as notebook computers, palmtop computers, etc.
  • mobile phones such as notebook computers, palmtop computers, etc.
  • tablet computers such as notebook computers, palmtop computers, etc.
  • mobile Internet devices mobile internet device, MID
  • industrial control industrial control
  • PLMN public land mobile network
  • the above N sets of antenna parameter combinations may be initializing particle swarms, that is, the electronic device may first randomly initialize particle swarms in a given solution space, and the number of variables of the problem to be optimized determines the dimensionality of the solution space. Each particle has an initial position and initial velocity, and then iteratively optimizes.
  • the above N sets of antenna parameter combinations may also be a particle swarm of a certain generation in the subsequent iterative optimization process of the initialized particle swarm. It should be noted that these N sets of antenna combinations should belong to particles in the same generation of particle swarms.
  • the value of any antenna parameter combination in the above N groups of antenna parameter combinations represents the degree of adaptation between this group of antenna parameter combinations and user needs.
  • the first antenna parameter combination and the second antenna parameter combination in the above N groups of antenna parameter combinations as an example, when the value of the first antenna parameter combination is greater than the value of the second antenna parameter combination, it means that the first antenna parameter combination Compared with the second antenna parameter combination, it is more in line with user requirements.
  • the above-mentioned first antenna combination is used as an example for illustration.
  • the incentive value of the first antenna parameter combination on the first indicator among the P communication indicators is the completion amount of the first antenna parameter combination on the first indicator, and the Q intervals of the first indicator and the Q intervals
  • P and Q are integers greater than 1.
  • the P communication indicators may include indicators such as antenna signal coverage, rate, and degree of interference between signals.
  • the first indicator is an indicator among the P communication indicators, which may be any indicator among indicators such as antenna signal coverage, rate, and signal.
  • the Q intervals of the first index can be set according to the user's requirement.
  • the above completion amount represents the quality of the communication quality of the signal transmitted by the antenna using the above first parameter combination on the above first indicator.
  • the above-mentioned first index is the coverage rate of the antenna signal
  • the best result it can achieve is 100% (assuming that the completion amount corresponding to this coverage rate is 100)
  • the above-mentioned first index of the antenna adopts the above-mentioned first
  • the signal coverage rate of the parameter combination transmission is 90%
  • the completion amount of the above-mentioned first antenna parameter combination on the above-mentioned first index is 90, and so on.
  • the calculation method of the incentive value of the first indicator above can be expressed as:
  • P1 is the incentive value of the first indicator above
  • W p1 represents the multi-objective weight corresponding to the first indicator among the above P communication indicators, which can be customized by the user.
  • each indicator in the P communication indicators corresponds to The multi-objective weights of all are the same, which is set to 1.
  • "*" indicates a multiplication operation
  • the above Q intervals of the first indicator may be set according to user requirements. For example, assuming that the optimal value of the above-mentioned first index (that is, the best degree that the first index can achieve) is 100, the user's requirement for the first index is that the value of the first index cannot be lower than 90. Then the aforementioned Q intervals may be [0, 80], [80, 90], and [90, 100], and the corresponding excitation coefficients may be 10, 1, and 0, respectively.
  • the completion amount of the first antenna parameter combination on the first indicator is 88, and the above completion amount falls into the interval [80, 90] at this time, then according to the above expression and Q intervals and Q
  • the foregoing Q intervals may be continuous Q intervals, or may be discontinuous Q intervals, which is not limited in this embodiment of the present application.
  • the calculation method of the value of the above-mentioned first antenna parameter combination can be expressed as:
  • P w1 is the value of the above-mentioned first antenna parameter combination
  • the calculation method of Pi can refer to the above-mentioned first An antenna parameter combination in the calculation expression of the excitation value of the first index above.
  • the method before acquiring the P incentive values combined with the above-mentioned first antenna parameters on the P communication indicators, the method will also acquire the first parameter and the second parameter; the first parameter includes the The target threshold of each communication indicator in the P communication indicators, the second parameter includes the weight of each communication indicator in the P communication indicators, and the above-mentioned P is an integer greater than 1; the above-mentioned first parameter and the above-mentioned second parameter are used To determine the Q intervals of the first index and the Q incentive coefficients respectively corresponding to the Q intervals.
  • the Q intervals of the first indicator and the incentive coefficients corresponding to the Q intervals may be set according to the above user requirements.
  • the following examples give four specific user requirements:
  • the Q intervals of the above-mentioned first index can be set as [0, N1] and [N1, 100], and the corresponding incentive coefficients can be 1 and 0 respectively.
  • the above Q intervals can be set as [0, N1-10], [N1-10, N1] and [N1-10, 100], and the corresponding excitation coefficients can be w1, w2 and w3 respectively , and w1>w2>w3.
  • the above Q indicators also include multiple indicators such as the second indicator and the third indicator.
  • the user requires the expected value of the above-mentioned first index to be N2, but it is allowed to deteriorate, but the degree of deterioration cannot exceed a lower limit (that is, the amount of completion of the combination of antenna parameters in the child generation on the above-mentioned first index is allowed.
  • the threshold is N3
  • the completion amount of the above first index is at most N4.
  • N4 is less than N3 (that is, when all antenna parameter combinations in the G1 generation have completed less than N3 on the above-mentioned first index)
  • the Q intervals of the above-mentioned first index can be set as [0, N4], [N4 , N3], [N3, 100]
  • the corresponding excitation coefficients can be w4, w5 and w6 respectively, and w4>w5>w6.
  • N4 is greater than N3 (that is, in all antenna parameter combinations in the G1 generation, the completion amount of the antenna parameter combination on the first index is greater than N3)
  • the Q intervals can be set arbitrarily, and the excitation coefficients corresponding to the Q intervals are negative infinity; if the completion amount of the first antenna parameter combination on the first index is not less than N3, then the Q The intervals can be set as [0, N2], [N2, 100], and the corresponding excitation coefficients can be w7 and w8 respectively, and w7 ⁇ w8.
  • the above Q indicators also include multiple indicators such as the second indicator and the third indicator.
  • the user’s requirement for the above first indicator is that the expected value of the above first indicator is N5, and the user hopes to focus on ensuring the above second indicator , the third indicator and other indicators are optimized in subsequent offspring.
  • the user wishes to optimize the above Q indicators at the same time. And if the antenna parameter combination in the parent parent has reached the user's expectation for a certain indicator, then in the subsequent process, the degree of optimization for this indicator can be reduced.
  • the completion amount of the above-mentioned first indicator is at most N6.
  • the Q intervals of the first index above can be set as [0, N6-N7], [N6-N7, N5] and [N5, 100], where N7 can be any positive integer smaller than N6; its corresponding
  • the excitation coefficients of can be w7, w8 and w9 respectively, and w8>w7>w9.
  • the above-mentioned Q indicators also include multiple indicators such as the second indicator and the third indicator. The user hopes that the value of the parameter combination finally used for the antenna can be the largest.
  • the completion amount of the above-mentioned first indicator is at most N8.
  • the Q intervals of the first index above can be set as [0, N8-N9], [N8-N9, 100], where N9 can be any positive integer smaller than N8; the corresponding incentive coefficients can be respectively w10, w11, and w11>w10.
  • the above-mentioned Q intervals of the first indicator and the corresponding Q excitation coefficients need to be set before the antenna parameter combination starts to be optimized (that is, the first-generation antenna parameter combination is generated). That is to say, in the subsequent process of antenna parameter combination optimization, the user cannot change the settings of the Q intervals of the above-mentioned first index and the corresponding Q excitation coefficients, and the device will set The antenna parameter combination sets the above-mentioned Q intervals of the above-mentioned first indicator and their corresponding Q excitation coefficients.
  • the Q intervals of the first index include the first interval and the second interval, the right endpoint value of the first interval is less than or equal to the left endpoint value of the second interval, and the second interval
  • the corresponding excitation coefficient is the second excitation coefficient
  • the excitation coefficient corresponding to the first interval is the first excitation coefficient
  • the second excitation coefficient is smaller than the first excitation coefficient. That is, the Q incentive coefficients corresponding to the Q intervals of the first indicator are set to decrease as the interval value increases.
  • the above-mentioned Q intervals may also include a third interval.
  • the above-mentioned second excitation coefficient is smaller than the third excitation coefficient corresponding to the third interval. coefficient.
  • the optimization degrees of multiple objectives are contradictory. For example, when the coverage ratio of antenna signals is larger, the interference between signals tends to be stronger. Therefore, in this embodiment, when the completion amount of the above-mentioned certain antenna parameter combination on the first index is greater, the antenna parameter combination is closer to the client's expectation on the above-mentioned first index.
  • the Q excitation coefficients corresponding to the above Q intervals are set to decrease with the increase of the interval value, so as to avoid the continuous optimization of subsequent generations on this index, in exchange for the subsequent antenna parameter combination
  • the optimization on other indicators can obtain the antenna parameter combination with better overall communication quality on each indicator.
  • the left endpoint value of the second interval is the completion amount of the first antenna parameter combination on the first index, and the completion amount represents the signal transmitted by the antenna using the first antenna parameter combination
  • the degree of quality of communication in the above-mentioned first index may also include multiple intervals such as the third interval and the fourth interval.
  • the value of the left end point in the above-mentioned second interval is greater than any numerical value included in the other (Q-1) intervals.
  • Setting the left end point value of the above-mentioned second interval as the completion amount of the above-mentioned first antenna parameter combination on the above-mentioned first index can more accurately control
  • the difference between the completion amount of the above-mentioned first index in the antenna parameter combination and the user's demand for the above-mentioned first index is exchanged for a greater degree of optimization of the subsequent antenna parameter combination on other indicators.
  • the above-mentioned second excitation coefficient is less than or equal to zero.
  • any value in the second interval corresponding to the second incentive coefficient is greater than the user's demand for the first index. That is to say, when the completion amount of the above-mentioned first antenna parameter combination on the above-mentioned first index exceeds the user's demand for the above-mentioned first index, by adjusting the above-mentioned second excitation coefficient to 0 or a negative number, it is possible to avoid the situation similar to the above-mentioned first antenna.
  • Such a parameter combination that is over-optimized on the above-mentioned first index is determined as the parent of the next generation.
  • the above-mentioned electronic device uses M groups of antenna parameter combinations with higher value among the above-mentioned N groups of antenna parameter combinations as a candidate antenna parameter set.
  • the electronic device After obtaining the value of each group of antenna parameter combinations in the above N groups of antenna parameter combinations, the electronic device will compare the value of each group of antenna parameter combinations in the above N groups of antenna parameter combinations, and the value of the above N group of antenna parameter combinations is the largest
  • the M groups of antenna parameter combinations are used as a candidate antenna parameter set.
  • the above-mentioned electronic device may use the antenna parameter combinations whose value is in the top M among the N groups of antenna parameter combinations as the candidate antenna parameter sets.
  • the electronic device uses the antenna parameter combination in the candidate antenna parameter set as a parent to determine a target antenna parameter combination.
  • the above-mentioned electronic device is based on a genetic algorithm, that is, the antenna parameter combinations in the above-mentioned candidate antenna parameter sets are used as parent particles, and crossover and mutation are performed with each other to generate a new generation of particles.
  • the particle population generated in each generation can calculate the value of each particle based on the method provided by the embodiment of the present application, and based on the value of each particle, select from the particle population of this generation Particles that are used as fathers for reproduction are selected.
  • the electronic device determines the particles in the G x generation or the particles in the G x-1 generation that have a higher value as the target antenna parameter combination.
  • the above-mentioned electronic device when the difference between the average value of each particle in the above-mentioned G x generation and or the average value of the value of each particle in the above-mentioned G x-1 generation is less than a preset threshold; or, when the above-mentioned G x generation When the difference between the value of the particle with the highest value among the particles and the value of the particle with the highest value among the particles in the above-mentioned G x-1 generation is less than the preset threshold value, the above-mentioned electronic device will determine that the optimization of the antenna parameter combination has reached the optimal value. optimal level, the above-mentioned electronic device may determine the particle with the highest value among the particles in the above-mentioned Gx generation or the above-mentioned Gx -1 generation as the above-mentioned target antenna parameter combination.
  • this method selects the particles that match the user's needs from the particle population as the parent particles of the subsequent offspring, and can obtain the particles that match the user's actual needs from the offspring of each generation more quickly and efficiently.
  • the combination of antenna parameters improves the speed of determining the combination of antenna parameters.
  • an embodiment of the present application provides a method for determining a candidate parameter set.
  • the above candidate parameter sets in FIG. 2 may be determined based on the method for determining the candidate parameter sets provided in the embodiment of the present application. Please refer to Figure 3 for details. As shown in Figure 3, the method may include the following steps:
  • the electronic device acquires a first parameter and a second parameter.
  • the above-mentioned electronic devices can be computers (such as notebook computers, palmtop computers, etc.), mobile phones, tablet computers (pads), mobile Internet devices (mobile internet device, MID), industrial control (industrial control)
  • computers such as notebook computers, palmtop computers, etc.
  • mobile phones such as notebook computers, palmtop computers, etc.
  • tablet computers pads
  • mobile Internet devices mobile internet device, MID
  • industrial control industrial control
  • the electronic device may be the electronic device described above with respect to FIG. 2 .
  • the above-mentioned first parameter may include a target threshold for each of the P communication indicators, the second parameter includes the weight of each of the above-mentioned P communication indicators, and the above-mentioned P is an integer greater than 1; the above-mentioned first parameter and The above-mentioned second parameter is used to determine a plurality of intervals of each index in the above-mentioned P indexes, and a plurality of incentive coefficients respectively corresponding to a plurality of intervals of each index.
  • the first parameter and the second parameter may be used to determine Q intervals of the first index among the above P indexes, and Q incentive coefficients respectively corresponding to the Q intervals of the first index.
  • the above-mentioned electronic device obtains P excitation values combined with the first antenna parameters on the P communication indicators.
  • the above-mentioned electronic device may combine the above-mentioned first antenna parameters with P excitation values on P communication indicators, and according to the first antenna The value of the first antenna parameter combination is obtained by combining the P incentive values on the P communication indicators with parameters.
  • the P communication indicators may include indicators such as antenna signal coverage, rate, and degree of interference between signals.
  • the first indicator is an indicator among the P communication indicators, which may be any indicator among indicators such as antenna signal coverage, rate, and signal.
  • the Q intervals of the first index can be set according to the user's requirement.
  • the above completion amount represents the quality of the communication quality of the signal transmitted by the antenna using the above first parameter combination on the above first indicator.
  • the above-mentioned first index is the coverage rate of the antenna signal
  • the best result it can achieve is 100% (assuming that the completion amount corresponding to this coverage rate is 100)
  • the above-mentioned first index of the antenna adopts the above-mentioned first
  • the signal coverage rate of the parameter combination transmission is 90%
  • the completion amount of the above-mentioned first antenna parameter combination on the above-mentioned first index is 90, and so on.
  • the calculation method of the incentive value of the first indicator above can be expressed as:
  • P1 is the incentive value of the first indicator above
  • W p1 represents the multi-objective weight corresponding to the first indicator among the above P communication indicators, which can be customized by the user.
  • each indicator in the P communication indicators corresponds to The multi-objective weights of all are the same, which is set to 1.
  • "*" indicates a multiplication operation
  • the above Q intervals of the first indicator may be set according to user requirements. For example, assuming that the optimal value of the above-mentioned first index (that is, the best degree that the first index can achieve) is 100, the user's requirement for the first index is that the value of the first index cannot be lower than 90. Then the aforementioned Q intervals may be [0, 80], [80, 90], and [90, 100], and the corresponding excitation coefficients may be 10, 1, and 0, respectively.
  • the completion amount of the first antenna parameter combination on the first indicator is 88, and the above completion amount falls into the interval [80, 90] at this time, then according to the above expression and Q intervals and Q
  • the above-mentioned electronic device obtains the value of the above-mentioned first antenna parameter combination according to the P incentive values of the above-mentioned P communication indicators combined with the above-mentioned first antenna parameters.
  • the calculation method of the value of the above-mentioned first antenna parameter combination can be expressed as:
  • P w1 is the value of the above-mentioned first antenna parameter combination
  • the calculation method of Pi can refer to the above-mentioned first An antenna parameter combination in the calculation expression of the excitation value of the first index above.
  • the electronic device obtains the value of each antenna parameter combination in the N sets of antenna parameter combinations.
  • the foregoing first antenna parameter combination is a group of antenna parameter combinations in the foregoing N groups of antenna parameter combinations.
  • the above-mentioned first parameter and the above-mentioned second parameter can also be used to determine a plurality of intervals of other indexes in the above-mentioned P indexes except the first index, and a plurality of incentive coefficients respectively corresponding to a plurality of intervals of other indexes.
  • the above-mentioned first parameter and the above-mentioned second parameter can also be used to determine the R intervals of the second index and the corresponding R incentive coefficients among the above-mentioned P indexes, and the S intervals of the third index and the corresponding S incentive coefficients.
  • the above-mentioned electronic device can also calculate the above-mentioned N groups of antenna parameter combinations The value of each antenna parameter combination is not listed here.
  • the above-mentioned electronic device uses the top M antenna parameter combinations among the above-mentioned N groups of antenna parameter combinations as the candidate antenna parameter sets.
  • the above-mentioned electronic device After obtaining the value of each antenna combination in the above N groups of antenna parameter combinations, in order to ensure the antenna parameter combination in the offspring to the greatest extent during the subsequent crossover and mutation of antenna parameter combinations (that is, generation of offspring through genetic algorithms), The degree of matching with user needs, the above-mentioned electronic device will compare the value of each group of antenna parameter combinations in the above-mentioned N groups of antenna parameter combinations, and the value of the top M antenna parameter combinations from the above-mentioned N groups of antenna parameter combinations will be used as the upper candidate antenna parameters gather.
  • the embodiment of the present application specifically quantifies the degree of adaptation between the antenna parameter combination and the user degree by setting the incentive intervals of the various communication indicators of the cell antenna and the incentive coefficients of each indicator in different incentive intervals according to the needs of the users, which can be more rapid and efficient. Efficiently obtain the antenna parameter combination that matches the user's actual needs from the offspring of each generation.
  • the optimization degrees of multiple objectives are contradictory.
  • the coverage ratio of antenna signals is larger, the interference between signals tends to be stronger. Therefore, in the present application, when the completion amount of a certain antenna parameter combination on a certain indicator is greater, it means that the antenna parameter combination is closer to the customer's expectation on the first indicator.
  • the multiple intervals corresponding to the index and the corresponding multiple incentive coefficients can be set to decrease with the increase of the interval value, and even the incentive coefficients of some intervals can be adjusted to 0 or negative numbers to avoid subsequent offspring in this interval.
  • the continuous optimization of indicators is exchanged for the optimization of subsequent antenna parameter combinations on other indicators, and an antenna parameter combination with better overall communication quality in each indicator is obtained. Accordingly, the embodiment of the present application provides a relationship diagram between the target interval and the excitation coefficient and a relationship diagram between the overall completion amount of the antenna parameter combination on the target and the optimization efficiency of the target, please refer to Figure 4 and Figure 4. 5.
  • FIG. 4 provides a relationship diagram between index intervals and incentive coefficients according to the embodiment of the present application.
  • the abscissa indicates the completion amount of the Tianxia parameter combination corresponding to a certain indicator
  • the ordinate indicates the incentive coefficient corresponding to each interval of the indicator. It should be understood that for different indicators, the intervals and incentive coefficients corresponding to the indicators may be different. Explain for three.
  • the excitation coefficient corresponding to the interval [0, T1] is the first excitation coefficient, and its value is 10; the excitation coefficient corresponding to the interval [T1, T2] is the second excitation coefficient, and its value is 1; the interval [T2, 100 ] is the third excitation coefficient, whose value is 0; in an optional manner, the excitation coefficient corresponding to the interval [T2, 100] may also be the fourth excitation coefficient, whose value is -1.
  • the incentive coefficients corresponding to the three intervals are calculated. For details, please refer to the foregoing description, which will not be repeated here.
  • the completion amount of the particles of the particle population in this generation is far from T2 on the above-mentioned first index (for example, the completion amount is less than T1)
  • the selected particles have a large amount of completion on the first index, so as to Complete the accelerated optimization of the first indicator.
  • FIG. 5 is a relationship diagram of the overall completion amount of an antenna parameter combination on an index and the optimization efficiency of the index.
  • the abscissa indicates the number of iterations of the particle population
  • the ordinate indicates the overall completion of the particle population on a certain indicator
  • the overall completion can be the particle population of each generation
  • the first index and the second index in FIG. 5 may be the first index and the second index in the foregoing description.
  • the user expectation value of the first indicator is 95. It can be seen from Figure 5 that before the overall completion amount is less than 95, with the increase of the number of iterations of the total particle swarm (that is, the evolution of the genetic algorithm), the overall completion of the first index and the second index of the particle population of each generation The amount is also gradually increasing, but after the overall completion amount reaches 95, with the increase of the number of iterations of the total particle population, the overall completion amount of each generation of particle populations on this indicator will tend to be stable or slightly decrease. Moreover, in the sub-generation corresponding to the t1-t2 section in the figure, the total completion amount of the particles in the particle population on the first index is far from the user's expectation.
  • the incentive coefficient of the index in this interval is large, and the particle population of each generation
  • the optimization rate on the first index (that is, the growth rate of the total completion amount) is extremely fast; but in the offspring corresponding to the t2-t3 segment, the total completion amount of the particles in the particle population on the first index is closer to the user's expectation, and every Although the overall completion of the first index of the particle population of the first generation continues to increase, the optimization rate is significantly lower than that in the sub-generations corresponding to the t1-t2 segment; until the sub-generations corresponding to the t3-t4 segment After the total amount of the total particle population of the particle group has reached the user's demand, the overall completion amount of the particle population of each generation on the first index meets the user's expectation.
  • the incentive coefficient of this interval is 0, and the particle population of each generation on the index The overall completion volume will tend to be stable, and the optimization on the first index will stop.
  • the user expectation value of the second indicator is also 95.
  • the total completion amount of the particles in the particle population on the first index has exceeded the user's expectation, and the overall completion amount of the particle population on the first index in each generation is negatively growing, and the optimization rate is negative.
  • FIG. 6 is a schematic diagram of particle population distribution in a two-dimensional search space provided by an embodiment of the present application.
  • the two dimensions represented by the two-dimensional search space may be coverage and rate among the aforementioned Q communication indicators.
  • the optimal value of these two indicators is 100, and the particle 61, particle 62, particle 63 and particle 64 in Fig.
  • the amount of completion on these two indicators of rate is shown in Table 1 below:
  • User intent 1 Prioritize the optimization of the coverage rate, and the user's requirement for the coverage rate should not be lower than 90%.
  • the multiple intervals corresponding to the coverage rate can be set as [0, 90] and [90, 100], and the corresponding incentive coefficients can be 100 and 0 respectively; the multiple intervals corresponding to the rate can be is set to [0, 90] and [90, 100], and the corresponding excitation coefficients can be 1 and 0 respectively.
  • the expected value of the coverage rate is 90, but it is allowed to deteriorate, but the degree of deterioration cannot exceed a lower limit (that is, the completion of the antenna parameter combination in the child generation is allowed to be less than the antenna parameter combination in the child generation.
  • the completion amount of the above-mentioned first index is good or bad, but the completion amount of the antenna parameter combination in each subsequent child generation on the above-mentioned first index cannot be less than a certain preset threshold, here it is assumed that the threshold is 87), the key point Guarantee the degree of optimization of the rate in the subsequent offspring and the user's requirement for the rate should not be lower than 90.
  • the multiple intervals corresponding to the coverage rate can be set to [0, 90] and [90, 100], and the corresponding excitation coefficients can be respectively for 1 and 0.
  • the multiple intervals corresponding to the rate can be set as [0, 90] and [90, 100], and the corresponding excitation coefficients can be 10 and 0 respectively.
  • User intent 3 The expected value of coverage and rate is 90, and the key point is to ensure the degree of optimization of the rate in subsequent generations. And users want to optimize both rate and coverage. When the amount of completion of a certain indicator in the parent parent has reached the user's expectation for the indicator, the degree of optimization for the indicator can be reduced in the subsequent process.
  • the multiple intervals of coverage can be set as [0, 88-2], [88-2, 90] and [90, 100], and the corresponding excitation coefficients can be 1, 10 and 0 respectively;
  • the corresponding intervals may be set as [0, 85-2], [85-2, 90] and [90, 100], and the corresponding excitation coefficients may be 1, 10 and 0 respectively.
  • the multiple intervals of the coverage rate can be set as [0, 88-2], [88-2, 100], and the corresponding excitation coefficients can be 1, 10 respectively; the multiple intervals corresponding to the rate can be set to Set as [0, 85-2], [85-2, 100], the corresponding excitation coefficients can be 1, 10 respectively.
  • the matched antenna parameter combination improves the determination speed of the antenna parameter combination, please refer to FIG. 7 and FIG. 8 for details.
  • FIG. 7 is a diagram of the relationship between the number of particle iterations and the degree of index optimization provided by the embodiment of the present application.
  • the abscissa of the coordinate system in Figure 7 represents the completion of the antenna parameter combination in terms of coverage
  • the ordinate represents the completion of the antenna parameter combination in rate
  • the curve 701 represents the traditional Pareto After 500 iterations of the dominance sorting method, the coverage and speed of each antenna parameter combination are completed.
  • Curve 702, curve 703 and curve 704 represent the method for determining the antenna parameter combination provided by the embodiment of the present application for 50 iterations and 150 iterations respectively. The completion amount of each antenna parameter combination in terms of coverage and rate obtained after the second and 500th times.
  • Fig. 8 provides a relationship diagram between the number of particle iterations and the degree of coverage optimization.
  • the abscissa of the coordinate system in FIG. 7 represents the number of iterations of the particle, and the ordinate represents the completion amount of the antenna parameter combination in terms of coverage.
  • Curve 801 represents the relationship between the amount of coverage completion and the number of iterations of each antenna parameter combination obtained through iteration using the traditional Pareto-dominated sorting method; curve 802 represents the iteration using the antenna parameter combination determination method provided by the embodiment of the present application The relationship between the obtained coverage completion amount and the number of iterations of each antenna parameter combination. Likewise, it can be generally seen that, in the case of the same number of iterations, the antenna parameter combination determination method provided in the embodiment of the present application can obtain a better antenna parameter combination.
  • the apparatus for determining the combination of antenna parameters in FIG. 9 may execute the flow of the method for determining the combination of antenna parameters in FIG. 2, and may also execute the flow of the method for determining the set of candidate parameters in FIG. 3. As shown in FIG. 9, the apparatus may include:
  • the calculation unit 901 is configured to obtain the value of each antenna parameter combination in the N groups of antenna parameter combinations, and the value of the first antenna parameter combination in the above N groups of antenna parameter combinations represents the degree of adaptation between the above-mentioned first antenna parameter combination and user needs ;
  • the determining unit 902 is configured to use M groups of antenna parameter combinations with greater value in the above N groups of antenna parameter combinations as a candidate antenna parameter set, the above M is smaller than the above N, the above M is an integer greater than 0, and the above N is greater than 1 Integer;
  • the genetic unit 903 is configured to use the antenna parameter combination in the candidate antenna parameter set as a parent to determine a target antenna parameter combination, and the target antenna parameter combination is used for transmitting signals by the antenna.
  • the calculation unit 901 is specifically configured to: obtain P incentive values of the first antenna parameters combined on the P communication indicators, and the first antenna parameters combined on the P communication indicators
  • the incentive value on the first index is determined by the completion amount of the above-mentioned first antenna parameter combination on the first index, and the Q intervals of the above-mentioned first index and the Q excitation coefficients corresponding to the above-mentioned Q intervals.
  • the above completion amount represents The above-mentioned antenna adopts the communication quality of the signal transmitted by the above-mentioned first parameter combination on the above-mentioned first indicator, the above-mentioned P and the above-mentioned Q are integers greater than 1; according to the above-mentioned first antenna parameter combination on the above-mentioned P communication indicators P excitation values to obtain the value of the first antenna parameter combination above.
  • the apparatus further includes: an acquiring unit 904, configured to acquire a first parameter and a second parameter; the first parameter includes a target threshold of each communication indicator among the P communication indicators, The above-mentioned second parameter includes the weight of each communication index in the above-mentioned P communication indexes, and the above-mentioned P is an integer greater than 1; the above-mentioned first parameter and the above-mentioned second parameter are used to determine the Q intervals of the above-mentioned first index, and the above-mentioned Q Q incentive coefficients corresponding to each interval.
  • an acquiring unit 904 configured to acquire a first parameter and a second parameter
  • the first parameter includes a target threshold of each communication indicator among the P communication indicators
  • the above-mentioned second parameter includes the weight of each communication index in the above-mentioned P communication indexes, and the above-mentioned P is an integer greater than 1
  • the above-mentioned first parameter and the above-mentioned second parameter are used
  • the Q intervals of the first index include a first interval and a second interval, the right endpoint value of the first interval is less than or equal to the left endpoint value of the second interval, and the second interval
  • the excitation coefficient corresponding to the interval is the second excitation coefficient
  • the excitation coefficient corresponding to the first interval is the first excitation coefficient
  • the second excitation coefficient is smaller than the first excitation coefficient
  • the left endpoint value of the second interval is the completion amount of the first antenna parameter combination on the first index
  • the completion amount represents the signal transmitted by the antenna using the first parameter combination The degree of quality of communication in the above-mentioned first index.
  • the above-mentioned second excitation coefficient is less than or equal to zero.
  • the determining unit 902 is specifically configured to: use the antenna parameter combinations with the highest value among the above N groups of antenna parameter combinations as the candidate antenna parameter sets.
  • each unit of the apparatus for determining an antenna parameter combination is only a division of logical functions, and may be fully or partially integrated into one physical entity or physically separated during actual implementation.
  • each of the above units can be a separate processing element, or can be integrated into the same chip, and can also be stored in the storage element of the controller in the form of program code, called by a certain processing element of the processor and Execute the functions of the above units.
  • each unit can be integrated together or implemented independently.
  • the processing element here may be an integrated circuit chip, which has a signal processing capability.
  • each step of the method or each of the above units can be completed by an integrated logic circuit of hardware in the processor element or an instruction in the form of software.
  • the processing element may be a general-purpose processor, such as a CPU, and may also be one or more integrated circuits configured to implement the above method, for example: one or more specific integrated circuits (application-specific integrated circuit, ASIC), or , one or more microprocessors (digital signal processor, DSP), or, one or more field-programmable gate arrays (field-programmable gate array, FPGA), etc.
  • ASIC application-specific integrated circuit
  • DSP digital signal processor
  • FPGA field-programmable gate array
  • FIG. 10 is a schematic structural diagram of an electronic device provided by an embodiment of the present application.
  • the electronic device 100 includes a processor 1001, a memory 1002, and a communication interface 1003; the processor 1001, the memory 1002, and the communication interface 1003 are connected to each other through a bus.
  • the electronic device may be the device for determining the combination of antenna parameters in the foregoing description.
  • Memory 1002 includes, but is not limited to, random access memory (random access memory, RAM), read-only memory (read-only memory, ROM), erasable programmable read-only memory (erasable programmable read only memory, EPROM), or portable Read-only memory (compact disc read-only memory, CDROM), the memory 1002 is used for related instructions and data.
  • the communication interface 1003 is used to receive and send data, and it can realize the function of the acquisition unit 904 in FIG. 9 .
  • the processor 1001 may be one or more central processing units (central processing unit, CPU).
  • CPU central processing unit
  • the CPU may be a single-core CPU or a multi-core CPU.
  • the steps performed by the apparatus for determining an antenna parameter combination in the foregoing embodiment may be based on the structure of the electronic device shown in FIG. 10 .
  • the processor 1001 can realize the functions of the calculation unit 901 , the determination unit 902 and the genetic unit 903 in FIG. 9 .
  • the processor 1001 in the electronic device 100 is configured to read the program code stored in the memory 1002, and execute the method for determining the combination of antenna parameters in the foregoing embodiments.
  • the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, it realizes: acquiring each antenna parameter combination in N groups of antenna parameter combinations
  • the value of the first antenna parameter combination in the N groups of antenna parameter combinations represents the degree of adaptation between the first antenna parameter combination and the user's needs; the M group of antenna parameter combinations with a larger value in the N groups of antenna parameter combinations
  • the M is smaller than the N, the M is an integer greater than 0, and the N is an integer greater than 1;
  • the antenna parameter combination in the candidate antenna parameter set is used as the parent to determine the target antenna parameter combination, and the target The combination of antenna parameters is used to transmit signals from the antenna.
  • the embodiment of the present application also provides a computer program product containing instructions, which, when run on a computer, enables the computer to execute the method for determining the antenna parameter combination provided in the foregoing embodiments.
  • words such as “exemplary” or “for example” are used as examples, illustrations or descriptions. Any embodiment or design described herein as “exemplary” or “for example” is not to be construed as preferred or advantageous over other embodiments or designs. Rather, the use of words such as “exemplary” or “such as” is intended to present related concepts in a concrete manner.
  • At least one refers to one or more, and the “multiple” refers to two or more.
  • At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items.
  • at least one item (piece) of a, b, or c may represent: a, b, c, (a and b), (a and c), (b and c), or (a and b and c), where a, b, c can be single or multiple.
  • first and second use ordinal numerals such as "first" and “second” to distinguish multiple objects, and are not used to limit the order, timing, priority or importance of multiple objects degree.
  • first device and the second device are only for the convenience of description, and do not represent the differences in the structure and importance of the first device and the second device.
  • the first device and the second device It can also be the same device.
  • the term "when” may be interpreted to mean “if" or "after” or “in response to determining" or “in response to detecting... ".
  • the above are only optional embodiments of the application, and are not intended to limit the application. Any modifications, equivalent replacements, improvements, etc. made within the concept and principles of the application shall be included in the protection of the application. within range.
  • Those of ordinary skill in the art can understand that all or part of the steps for implementing the above embodiments can be completed by hardware, and can also be completed by instructing related hardware through a program.
  • the program can be stored in a computer-readable storage medium.
  • the above-mentioned The storage medium mentioned may be a read-only memory, a magnetic disk or an optical disk, and the like.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

一种天线参数组合的确定方法及相关装置，该方法包括：获取N组天线参数组合中每组天线参数组合的价值，所述N组天线参数组合中的第一天线参数组合的价值表征所述第一天线参数组合与用户需求的适配程度；将所述N组天线参数组合中价值较大的M组天线参数组合作为候选天线参数；将所述候选天线参数集合中的天线参数组合作为父本来确定目标天线参数组合。该方法可以更加快速、高效地从每一代的子代中获取与用户实际的需求相匹配的天线参数组合，提高天线参数组合的确定速度。

Description

天线参数组合的确定方法及相关装置 技术领域
本申请涉及无线通信技术领域，尤其涉及一种天线参数组合的确定方法及相关装置。
背景技术
小区天线的方位角、倾角、权值等天线参数和小区天线的信号的覆盖率、信号干扰程度等通信指标有着密切的关系。但是无论如何调节天线的参数，往往都不能找到一组参数使每个通信指标都同时达到最优。例如，当覆盖率越大时，天线信号之间的互相干扰程度可能也更严重。随着无线技术的迭代更新和站址的逐步加密，多站点间不同小区的天线参数需要协同规划，确定适合的天线参数组合，让小区天线的信号的各项通信指标取得相对最优值。
因此，寻找高效的天线参数组合的确定方法是本领域技术人员亟待解决的问题。
发明内容
本申请实施例提供了一种天线参数组合的确定方法及相关装置，本方法通过根据用户的需求从粒子种群中选择与用户需求适配的粒子作为后续子代的父本粒子，能更加快速、高效地从每一代的子代中获取与用户实际的需求相匹配的天线参数组合，提高天线参数组合的确定速度。
第一方面，本申请实施例提供了一种天线参数组合的确定方法，所述方法包括：获取N组天线参数组合中每组天线参数组合的价值，所述N组天线参数组合中的第一天线参数组合的价值表征所述第一天线参数组合与用户需求的适配程度；将所述N组天线参数组合中价值较大的M组天线参数组合作为候选天线参数集合，所述M小于所述N，所述M为大于0的整数，所述N为大于1的整数；将所述候选天线参数集合中的天线参数组合作为父本来确定目标天线参数组合，所述目标天线参数组合用于天线发射信号。
在本方法中，所述用户需求包括用户对天线信号在多个通信指标上需求的优先级以及对这多个通信指标达标率的要求。其中所述多个通信指标可以包括天线信号的覆盖率、速率、信号之间的干扰程度等，这些通信指标的优劣程度由例如方向角、下倾角、水平波瓣宽度，垂直波瓣宽度、波束数量以及权值参数等天线参数组合中的一个或多个确定。
应理解，不同的用户对这些通信指标可能有不同的需求。例如，用户A可能希望天线信号的覆盖率达到90％以上，速率需要达到65Mbit/s以上；但是用户B可能并不优先关注天线信号的覆盖率和速率，而是希望多天线信号之间相互干扰的程度可以控制在某个范围内。因此，在本方法中，在通过遗传算法得到多个天线参数组合之后，可以计算这些天线参数组合各自的价值(即这些天线参数组合与用户意图的适配程度)。例如，当用户希望先天线信号的覆盖率达到90％以上但并不关注天线信号的速率时，如果存在两个天线参数组合(以下分别称为组合1和组合2)，天线采用组合1发射的信号的覆盖率为90％且速率为58.5Mbit/s，而天线采用组合2发射的信号的覆盖率为88％且速率为65Mbit/s，则设备将选定组合1作为所述候选天线参数集合中的天线参数组合，并将组合1作为父本候选天线参数集合中的其他天线参数组合进行交叉变异，得到下一个子代。
本方法结合用户意图为每一个天线参数组合设定了价值，在每一代子代的挑选过程中， 能更加快速、高效地从每一代的子代中获取与用户实际的需求相匹配的天线参数组合，提高天线参数组合的确定速度。
在第一方面一种可选的实施方式中，所述获取N组天线参数组合中每组天线参数组合的价值，包括：获取所述第一天线参数组合在P个通信指标上的P个激励值，所述第一天线参数组合在所述P个通信指标中第一指标上的激励值由所述第一天线参数组合在第一指标上的完成量，以及所述第一指标的Q个区间和所述Q个区间对应的Q个激励系数确定，所述完成量表征所述天线采用所述第一参数组合发射的信号在所述第一指标上通信质量的优劣程度，所述P和所述Q为大于1的整数；根据所述第一天线参数组合在所述P个通信指标上的P个激励值，得到所述第一天线参数组合的价值。
在本实施方式中，所述P个通信指标可以包括天线信号的覆盖率、速率、信号之间的干扰程度等指标。所述第一指标为所述P个通信指标中的指标，其可以为天线信号的覆盖率、速率、信号等指标中的任意一个指标。所述第一指标的Q个区间可以根据所述用户需求进行设定。
例如，假设所述第一指标的最优值(即所述第一指标所能达到的最好的程度)为100，用户对所述第一指标的要求为所述第一指标的值不能低于90。则上述Q个区间可以为[0，80]、[80，90]以及[90，100]，其所对应的激励系数可以分别为10、1和0。则所述第一天线参数组合在所述第一指标上的激励值可以通过所述完成量与所述Q个区间的关系计算。举例说明，当所述第一天线参数组合在所述第一指标上的完成量为88时，此时所述完成量落入区间[80，90]中，则所述第一天线参数组合在所述P个通信指标中第一指标上的激励值为：(80×10)+(88-80)×1＝808；当所述第一天线参数组合在所述第一指标上的完成量为92时，此时所述完成量落入区间[90，100]中，则所述第一天线参数组合在所述P个通信指标中第一指标上的激励值为：(80-0)×10+(90-80)×1+(92-90)×0＝810；以此类推。
在本实施方式中，通过获取天线参数组合在所述P个指标上的激励值，来获取天线参数组合在所述P个指标中每个指标上的完成量与用户期望值之间的差距，来计算天线参数组合在各个指标上的激励值，使天线参数组合的价值能充分反映天线参数组合与用户意图的适配程度。
在第一方面一种可选的实施方式中，在获取所述第一天线参数组合在P个通信指标上的P个激励值之前，所述方法还包括：获取第一参数以及第二参数；所述第一参数包括所述P个通信指标中每个通信指标的目标阈值，所述第二参数包括所述P个通信指标中每个通信指标的权重，所述P为大于1的整数；所述第一参数以及所述第二参数用于确定所述第一指标的Q个区间，以及所述Q个区间分别对应的Q个激励系数。
所述第一指标的Q个区间以及Q个区间对应的激励系数可以根据所述用户需求进行设定。下列示例性的给出了四个具体的用户需求：
用户需求①：优先保障所述第一目标的优化程度，且用户对所述第一指标的要求为所述第一指标的值不能低于N1。
对于用户需求①，所述第一指标的Q个区间可以被设定为[0，N1]以及[N1，100]，其所对应的激励系数可以分别为1和0。或者，则上述Q个区间可以被设定为[0，N1-10]、[N1-10，N1]以及[N1-10，100]，其所对应的激励系数可以分别为w1、w2和w3，且w1>w2>w3。
用户需求②：所述Q个指标中还包括第二指标、第三指标等多个指标。此时用户对所述第一指标要求为所述第一指标的期望值为N2，但是允许其恶化，但恶化程度不能超过一个下限(即允许子代中的天线参数组合在所述第一指标上的完成量小于子代中的天线参数组合在 所述第一指标上的优劣的完成量，但后续每个子代中的天线参数组合在所述第一指标上的完成量均不能小于某个预设的阈值，这里假设该阈值为N3)，重点保障所述第二指标、第三指标等指标在后续子代中的优化程度。
对于用户需求②，假设与所述第一天线参数组合的父本(假设这一代为第G1代)的所有天线参数组合中，在所述第一指标上的完成量最大为N4。当N4小于N3(即第G1代中所有天线参数组合在所述第一指标上的完成量均小于N3时)，所述第一指标的Q个区间可以被设定为[0，N4]、[N4，N3]，[N3，100]，其所对应的激励系数可以分别为w4、w5和w6，且w4>w5>w6。当N4大于N3(即第G1代中所有天线参数组合中存在天线参数组合在所述第一指标上的完成量大于N3时)，若所述第一天线参数组合在第一指标上的完成量小于N3，则Q个区间可以随意设定，且Q个区间对应的激励系数均为负无穷；若所述第一天线参数组合在第一指标上的完成量不小于N3，则所述第一指标的Q个区间可以被设定为[0，N2]、[N2，100]，其所对应的激励系数可以分别为w7和w8，且w7<w8。
用户需求③：所述Q个指标中还包括第二指标、第三指标等多个指标，此时用户对所述第一指标要求为所述第一指标的期望值为N5，用户希望重点保障所述第二指标、第三指标等指标在后续子代中的优化程度。此时用户希望所述Q个指标同时进行优化。且父本中的天线参数组合若在某个指标上已经达到用户对该指标的期望值，则后续过程中，对于该指标的优化程度可以降低。
对于用户需求③，假设与所述第一天线参数组合同代(假设这一代为第G2代)的所有天线参数组合中，在所述第一指标上的完成量最大为N6。所述第一指标的Q个区间可以被设定为[0，N6-N7]、[N6-N7，N5]以及[N5，100]，其中，N7可以为小于N6的任意正整数；其所对应的激励系数可以分别为w7、w8和w9，且w8>w7>w9。
用户需求④：所述Q个指标中还包括第二指标、第三指标等多个指标，用户希望最后用于天线使用的参数组合的价值可以最大。
对于用户需求④，假设与所述第一天线参数组合同代(假设这一代为第G3代)的所有天线参数组合中，在所述第一指标上的完成量最大为N8。所述第一指标的Q个区间可以被设定为[0，N8-N9]、[N8-N9，100]，其中，N9可以为小于N8的任意正整数；其所对应的激励系数可以分别为w10、w11，且w11>w10。
上面只是示例性地给出了几个具体的用户需求以及在该用户需求下所述第一指标的Q个区间以及其对应的Q个激励系数的设定规则。对于不同的用户需求而言，所述第一指标的Q个区间的以及其对应的Q个激励系数可以不同，这里不再一一列举。
应理解，上述第一指标的Q个区间以及其对应的Q个激励系数的设定需要在天线参数组合开始优化(即产生第一代天线参数组合)之前设定完成。也就是说，在后续的天线参数组合优化的过程中，设备只需要根据用户需求为子代中的天线参数组合设定所述第一指标的所述Q个区间的以及其对应的Q个激励系数。
在第一方面一种可选的实施方式中，所述第一指标的Q个区间包括第一区间以及第二区间，所述第一区间的右端点值小于或等于所述第二区间的左端点值，所述第二区间对应的激励系数为第二激励系数，所述第一区间对应的激励系数为第一激励系数，所述第二激励系数小于所述第一激励系数。
可以理解的，在天线参数的多目标优化问题中，多个目标的优化程度是相互矛盾的。例如，当天线信号的覆盖率越大时，往往信号相互之间干扰也越强。因此，在本实施方式中，由于当所述某个天线参数组合在第一指标上的完成量越大时，该天线参数组合在所述第一指 标上距离客户预期越近。此时，将所述Q个区间对应的Q个激励系数设定为随着区间数值的增大而减小，来避免后续子代(即后续产生的天线参数组合)在该指标上的持续优化，以此换取后续产生的天线参数组合在其它指标上的优化，得到在各个指标上通信质量综合更优的天线参数组合。
在第一方面一种可选的实施方式中，所述第二区间的左端点值为所述第一天线参数组合在所述第一指标上的完成量，所述完成量表征所述天线采用所述第一参数组合发射的信号在所述第一指标上通信质量的优劣程度。
在本实施方式中，所述第一指标的Q个区间还可以包括第三区间、第四区间等多个区间。其中，所述第二区间中的左端点值大于其他(Q-1)个区间中包含的任意数值。将所述第二区间的左端点值为所述第一天线参数组合在所述第一指标上的完成量，可以在满足用户对所述第一指标的需求的情况下，更为精确地控制后续子代中的天线参数组合中在所述第一指标上的完成量与用户对所述第一指标的需求的差距，以此来换取后续产生的天线参数组合在其它指标上的更大的优化程度。
在第一方面一种可选的实施方式中，所述第二激励系数小于或等于0。
所述第二激励系数对应的第二区间中任意一个数值均大于用户对所述第一指标的需求。当所述第一天线参数组合在所述第一指标上的完成量超过用户对所述第一指标的需求之后，通过将所述第二激励系数调整0或者负数，可以避免类似所述第一天线参数组合这样在所述第一指标上过度优化的参数组合被确定为下一代的父本。这样，可以在满足用户对所述第一指标的需求的情况下，更为精确地控制后续子代中的天线参数组合中在所述第一指标上的完成量与用户对所述第一指标的需求的差距，以此来换取后续产生的天线参数组合在其它指标上的更大的优化程度。
在第一方面一种可选的实施方式中，所述将所述N组天线参数组合中价值较大的M组天线参数组合作为候选天线参数集合，包括：将所述N组天线参数组合中价值居于前M个天线参数组合作为候选天线参数集合。
在本申请实施例中，确定所述N组天线参数组合中价值居于前M个天线参数组合作为候选天线参数集合，在后续天线参数组合的交叉、变异(即通过遗传算法产生子代)的过程中，可以最大程度保障子代中的天线参数组合与用户需求的匹配程度。
第二方面，本申请实施例提供了一种天线参数组合的确定装置，所述装置包括：计算单元，用于获取N组天线参数组合中每组天线参数组合的价值，所述N组天线参数组合中的第一天线参数组合的价值表征所述第一天线参数组合与用户需求的适配程度；确定单元，用于将所述N组天线参数组合中价值较大的M组天线参数组合作为候选天线参数集合，所述M小于所述N，所述M为大于0的整数，所述N为大于1的整数；遗传单元，用于将所述候选天线参数集合中的天线参数组合作为父本来确定目标天线参数组合，所述目标天线参数组合用于天线发射信号。
在第二方面一种可选的实施方式中，所述计算单元，具体用于：获取所述第一天线参数组合在P个通信指标上的P个激励值，所述第一天线参数组合在所述P个通信指标中第一指标上的激励值由所述第一天线参数组合在第一指标上的完成量，以及所述第一指标的Q个区间和所述Q个区间对应的Q个激励系数确定，所述完成量表征所述天线采用所述第一参数组合发射的信号在所述第一指标上通信质量的优劣程度，所述P和所述Q为大于1的整数；根据所述第一天线参数组合在所述P个通信指标上的P个激励值，得到所述第一天线参数组合的价值。
在第二方面一种可选的实施方式中，所述装置还包括：获取单元，用于获取第一参数以及第二参数；所述第一参数包括所述P个通信指标中每个通信指标的目标阈值，所述第二参数包括所述P个通信指标中每个通信指标的权重，所述P为大于1的整数；所述第一参数以及所述第二参数用于确定所述第一指标的Q个区间，以及所述Q个区间分别对应的Q个激励系数。
在第二方面一种可选的实施方式中，所述第一指标的Q个区间包括第一区间以及第二区间，所述第一区间的右端点值小于或等于所述第二区间的左端点值，所述第二区间对应的激励系数为第二激励系数，所述第一区间对应的激励系数为第一激励系数，所述第二激励系数小于所述第一激励系数。
在第二方面一种可选的实施方式中，所述第二区间的左端点值为所述第一天线参数组合在所述第一指标上的完成量，所述完成量表征所述天线采用所述第一参数组合发射的信号在所述第一指标上通信质量的优劣程度。
在第二方面一种可选的实施方式中，所述第二激励系数小于或等于0。
在第二方面一种可选的实施方式中，所述确定单元，具体用于：将所述N组天线参数组合中价值居于前M个天线参数组合作为候选天线参数集合。
第三方面，本申请实施例提供了一种电子设备，包括：存储器，用于存储程序；处理器，用于执行所述存储器存储的所述程序，当所述程序被执行时，所述处理器用于执行如第一方面及任一种可选的实现方式的方法。
第四方面，本申请实施例提供一种计算机可读存储介质，所述计算机存储介质存储有计算机程序，所述计算机程序包括程序指令，所述程序指令当被处理器执行时使所述处理器执行如第一方面及任一种可选的实现方式的方法。
本申请第二至第四方面所提供的技术方案，其有益效果可以参考第一方面所提供的技术方案的有益效果，此处不再赘述。
附图说明
下面将对实施例描述中所需要使用的附图作简单的介绍。
图1A为本申请实施例提供的一种天线参数组合优化解的帕累托前沿图；
图1B为本申请实施例提供的一种候选天线集合的示意图；
图2为本申请实施例提供的一种天线参数组合的确定方法的流程图；
图3为本申请实施例提供的一种候选参数集合的确定方法的流程图；
图4为本申请实施例提供的一种指标区间与激励系数之间的关系图；
图5为本申请实施例提供的一种天线参数组合在指标上的总体完成量与该指标的优化效率的关系图；
图6为本申请实施例提供的二维搜索空间中粒子种群分布的示意图；
图7为本申请实施例提供的一种粒子迭代次数和指标优化程度之间的关系图；
图8为本申请实施例提供的一种粒子迭代次数和覆盖率优化程度之间的关系图；
图9为本申请实施例提供的一种天线参数组合的确定装置的结构示意图；
图10为本申请实施例提供的一种电子设备的结构示意图。
具体实施方式
下面结合附图对本申请实施例进行详细介绍。
为了便于理解，以下示例地给出了部分与本申请实施例相关概念的说明以供参考。如下所述：
1.粒子
多个小区参数、射频(Radio Frequency，RF)参数以及波束形成(Beamforming，BF)参数的一个组合，称为一个粒子。小区参数包括表征小区的位置区域的参数以及表征小区的通信质量的参数，例如移动网络代码、跟踪区域码、接收信号强度、参考信号接收功率以及扇区代码等。RF表示可以辐射到空间的电磁频率(300K Hz-300G Hz)。RF参数包括方位角，倾角，站高、增益系数、波束宽度、方向系数。波束成形是天线技术与数字信号处理技术的结合，目的用于定向信号传输或接收。BF参数包括大规模天线技术中的权值参数。
2.多目标优化
人们会经常遇到使多个目标在给定区域同时尽可能最佳的优化问题，也就是多目标优化问题。实际中优化问题大多数是多目标优化问题，一般情况下，多目标优化问题的各个子目标之间是矛盾的，一个目标的改善有可能会引起另一个或者另几个目标的性能降低，要同时使多个子目标一起达到最优值是不可能的，而只能在它们中间进行协调和折中处理，使各个子目标都尽可能地达到最优化。其与单目标优化问题的本质区别在于，它的解并非唯一，而是存在一组由众多Pareto最优解组成的最优解集合中的各个元素称为Pareto最优解或非劣最优解。多目标优化问题用文字描述为D个决策变量参数、N个目标函数、(m+n)个约束条件组成一个优化问题，决策变量与目标函数、约束条件是函数关系。在非劣解集中决策者只能根据具体问题要求选择令其满意的一个非劣解作为最终解。
3.遗传算法(Genetic Algorithm，GA)
遗传算法起源于对生物系统所进行的计算机模拟研究。它是模仿自然界生物进化机制发展起来的随机全局搜索和优化方法，借鉴了达尔文的进化论和孟德尔的遗传学说。其本质是一种高效、并行、全局搜索的方法，能在搜索过程中自动获取和积累有关搜索空间的知识，并自适应地控制搜索过程以求得最佳解。
4.帕累托Pareto最优解集及帕累托前沿
如果向量u＝(u1,…,um)和向量v＝(v1,…,vm)满足uk≤vk，
Figure PCTCN2021130770-appb-000001
Figure PCTCN2021130770-appb-000002
则称向量u支配向量v，记为u＜v。如果向量u不支配向量v且向量v也不支配向量u，则我们称u和v互相不支配，记作
Figure PCTCN2021130770-appb-000003
或
Figure PCTCN2021130770-appb-000004
如果解空间S内的一个可行解x*满足：
Figure PCTCN2021130770-appb-000005
s.t.F(y)<F(x*)，则我们称x*为解空间S内的一个帕累托最优解。所有的帕累托最优解构成帕累托最优解集，这些解经目标函数映射构成了该问题的Pareto最优前沿或Pareto前沿面，即帕累托最优解对应的目标函数值就是帕累托最优前沿。对于多个目标，其Pareto前沿通常是一个超曲面。
5.完成量
完成量表征天线采用某个天线参数组合发射的信号在某个指标上通信质量的优劣程度，其可以被量化为具体的数值，完成量越大，通信质量越好。例如，在本申请实施例中，天线信号的覆盖率能达到的最好的效果为100％覆盖，则当天线采用某个天线参数组合发射的信号在覆盖率上的覆盖率为90％时，则该天线采用某个天线参数组合发射的信号在覆盖率上的完成量为90％。
随着无线技术的迭代更新和站址的逐步加密，多站点间不同小区的天线参数(RF/BF参数等)需要协同规划，在保障覆盖和减少干扰之间取得均衡。小区天线的方位角、倾角、权值等 天线参数和小区天线的信号的覆盖率、信号干扰程度等通信指标有着密切的关系。但是无论如何调节天线的参数，往往都不能找到一组参数使每个通信指标都同时达到最优。例如，当覆盖率越大时，天线信号之间的互相干扰程度可能也更严重。随着无线技术的迭代更新和站址的逐步加密，多站点间不同小区的天线参数需要协同规划，确定适合的天线参数组合，让小区天线的信号的各项通信指标取得相对最优值。
目前，在天线各个通信指标涉及的多目标优化问题中，天线参数组合的确定一般基于支配解快速排序的方法，从子代中众多的参数组合挑选出相对最优参数组合。图1A为本申请实施例提供的一种天线参数组合优化解的帕累托前沿图。如图1A所示，在搜索空间中，存在大量的粒子，这些粒子都是有同一代的父本所产生的同代的子代粒子。实际上，搜索空间的维度与多目标优化问题中目标函数的个数相同。也就是说，当天线信号存在P个通信指标时，其对应的搜索空间应该是P维的。但是为了方便读者理解，图1A中所示出的搜索为二维空间。在该搜索空间中，粒子A-H为利用传统的支配解快速排序算法从粒子种群中挑选出的粒子，这些粒子均为帕累托最优解，A-H也形成了该搜索空间的前沿面。在后续遗传算法的演进中，粒子A-H将作为父本进行交叉和变异，产生下一代(即子代)的粒子集合；而与粒子A-H同代中的剩余的其他粒子(例如粒子K和粒子I这样的粒子)将被淘汰，不再参与后续的交叉、变异等繁衍过程。
但是，图1A中所示的A到H每一个参数粒子，都是相对来看的某个方面的最优解。如果直接基于这些相对最优解来寻优，将耗费大量寻优算力。此外，在实际的使用过程中，用户对于天线的各项通信指标的需求水平是存在差异的。上述基于支配解快速排序的方法所采用普适性的排序搜索方法所确定的粒子，其最后达到的效果往往和用户实际的需求不匹配。
针对上述天线参数组合的确定方法中存在的不足，本申请实施例提供了一种天线参数组合的确定方法，本方法通过根据用户的需求从粒子种群中选择与用户需求适配的粒子作为后续子代的父本粒子，能更加快速、高效地从每一代的子代中获取与用户实际的需求相匹配的天线参数组合，提高天线参数组合的确定速度。如图1B所示，该方法可以从粒子种群中挑选出与用户需求更为匹配的粒子C和粒子D(即将粒子C和粒子D确定为候选参数集合中的粒子)，并基于粒子C和粒子D继续交叉变异，直至产生最终使用的天线参数组合，在提高天线参数组合的确定速度。如图2所示，该方法可以包括以下步骤：
201.电子设备获取N组天线参数组合中每组天线参数组合的价值。
上述电子设备可以是带数据收发功能的电脑(如笔记本电脑、掌上电脑等)、手机(mobile phone)、平板电脑(pad)、移动互联网设备(mobile internet device，MID)、工业控制(industrial control)中的终端、智慧城市(smart city)中的终端5G网络中的终端设备或者未来演进的公用陆地移动通信网络(public land mobile network，PLMN)中的终端设备等，本申请对该电子设备的具体形态不作限制。
上述N组天线参数组合可以为初始化粒子群，即上述电子设备可以首先在给定的解空间中随机初始化粒子群，待优化问题的变量数决定了解空间的维数。每个粒子有了初始位置与初始速度，然后迭代寻优。此外，上述N组天线参数组合还可以为初始化粒子群在后续迭代寻优过程中某一代的粒子群。需注意，这N组天线组合应属于同一代粒子群中的粒子。
在申请实施例中，上述N组天线参数组合中的任意一组天线参数组合的价值均表征这组天线参数组合与用户需求的适配程度。以上述N组天线参数组合中的第一天线参数组合和第二天线参数组合为例，当第一天线参数组合的价值大于该第二天线参数组合的价值时，则表示该第一天线参数组比该第二天线参数组合更符合用户需求。
具体的，为了能量化上述N个天线参数组合中每个天线参数组合的价值，以上述第一天线组合为例进行说明，在一个可选的实施方式中，上述电子设备可以通过获取上述第一天线参数组合在P个通信指标上的P个激励值，并根据该第一天线参数组合在该P个通信指标上的P个激励值，得到所述第一天线参数组合的价值。该第一天线参数组合在该P个通信指标中第一指标上的激励值由该第一天线参数组合在第一指标上的完成量，以及该第一指标的Q个区间和该Q个区间对应的Q个激励系数确定，P和Q为大于1的整数。
其中，所述P个通信指标可以包括天线信号的覆盖率、速率、信号之间的干扰程度等指标。所述第一指标为所述P个通信指标中的指标，其可以为天线信号的覆盖率、速率、信号等指标中的任意一个指标。所述第一指标的Q个区间可以根据所述用户需求进行设定。上述完成量表征所述天线采用述上第一参数组合发射的信号在上述第一指标上通信质量的优劣程度。例如，当上述第一指标为天线信号的覆盖率时，其可以达到的最好结果为100％(假设此覆盖率对应的完成量为100)，则当天线上述第一指标采用述上第一参数组合发射的信号覆盖率为90％，则上述第一天线参数组合在上述第一指标上的完成量即为90，以此类推。
具体的，上述第一指标的激励值的计算方式可以表示为：
P 1＝W p1*L[T 0，T 1]*J 1+W p1*L[T 1，T 2]*J 2+……+W p1*L[T Q-1，T Q]*J Q；
其中，P 1上述第一指标的激励值，W p1表示上述P个通信指标中第一指标对应的多目标权重，其可以由用户自定义，默认情况下，P个通信指标中每个指标对应的多目标权重均相同，设定为1。“*”表示乘法运算，[T N-1，T N](N＝1，2，3，……，Q)表示上述第一指标的Q个区间中的第N个区间。J N(N＝1，2，3，……，Q)即为上述第一指标的Q个区间中第N个区间对应的激励值。L[T N-1，T N]表示上述完成量覆盖在第N个区间上的长度；例如，假设上述完成量为60，当T N-1＝30，T N＝80时，则L[30，80]＝60-30＝30；当T N-1＝0，T N＝50时，则L[0，80]＝60-0＝60；当T N-1＝30，T N＝40时，则L[30，40]＝40-30＝10；当T N-1＝80，T N＝90时，则L[30，80]＝0；以此类推。
应理解，上述第一指标的Q个区间可以根据用户需求进行设定。例如，假设上述第一指标的最优值(即所述第一指标所能达到的最好的程度)为100，用户对所述第一指标的要求为所述第一指标的值不能低于90。则上述Q个区间可以为[0，80]、[80，90]以及[90，100]，其所对应的激励系数可以分别为10、1和0。假设所述第一天线参数组合在所述第一指标上的完成量为88时，此时上述完成量落入区间[80，90]中，则根据上述表达式和Q个区间的以及Q个激励系数的设定况情可以算出，所述第一天线参数组合在所述P个通信指标中第一指标上的激励值为：(80×10)+(88-80)×1＝808；假设所述第一天线参数组合在所述第一指标上的完成量为92时，此时所述完成量落入区间[90，100]中，则所述第一天线参数组合在所述P个通信指标中第一指标上的激励值为：(80-0)×10+(90-80)×1+(92-90)×0＝810。
此外，上述Q个区间可以为连续的Q个区间，也可以为不连续的Q个区间，本申请实施例对此不作限定。
进一步的，基于上述第一天线参数组合在上述第一指标的激励值的计算表达式，上述第一天线参数组合的价值的计算方式可以表示为：
Figure PCTCN2021130770-appb-000006
其中，P w1为上述第一天线参数组合的价值，W pi表示P个通信指标中第i(i＝1,2,3,……,P)个指标对应的多目标权重，其可以由用户自定义，默认情况下，P个通信指标中每个指标对 应的多目标权重均相同，设定为1。P i为上述第一天线参数组合在上述P个通信指标中的第i(i＝1,2,3,……,P)个通信指标上的激励值，P i的计算方式可以参考上述第一天线参数组合在上述第一指标的激励值的计算表达式。
具体的，为了根据用户需求对上述第一指标的Q个区间以及其对应的Q个激励系数进行灵活的设定。在一个可选的实施方式中，在获取上述第一天线参数组合在P个通信指标上的P个激励值之前，本方法还将获取第一参数以及第二参数；该第一参数包括所述P个通信指标中每个通信指标的目标阈值，该第二参数包括所述P个通信指标中每个通信指标的权重，上述P为大于1的整数；上述第一参数以及上述第二参数用于确定上述第一指标的Q个区间，以及上述Q个区间分别对应的Q个激励系数。
上述第一指标的Q个区间以及Q个区间对应的激励系数可以根据上述用户需求进行设定。下列示例性的给出了四个具体的用户需求：
用户需求①：优先保障上述第一目标的优化程度，且用户对上述第一指标的要求为上述第一指标的值不能低于N1。
对于用户需求①，上述第一指标的Q个区间可以被设定为[0，N1]以及[N1，100]，其所对应的激励系数可以分别为1和0。或者，则上述Q个区间可以被设定为[0，N1-10]、[N1-10，N1]以及[N1-10，100]，其所对应的激励系数可以分别为w1、w2和w3，且w1>w2>w3。
用户需求②：上述Q个指标中还包括第二指标、第三指标等多个指标。此时用户对上述第一指标要求为上述第一指标的期望值为N2，但是允许其恶化，但恶化程度不能超过一个下限(即允许子代中的天线参数组合在上述第一指标上的完成量小于子代中的天线参数组合在上述第一指标上的优劣的完成量，但后续每个子代中的天线参数组合在上述第一指标上的完成量均不能小于某个预设的阈值，这里假设该阈值为N3)，重点保障上述第二指标、第三指标等指标在后续子代中的优化程度。
对于用户需求②，假设与上述第一天线参数组合的父本(假设这一代为第G1代)的所有天线参数组合中，在上述第一指标上的完成量最大为N4。当N4小于N3(即第G1代中所有天线参数组合在上述第一指标上的完成量均小于N3时)，上述第一指标的Q个区间可以被设定为[0，N4]、[N4，N3]，[N3，100]，其所对应的激励系数可以分别为w4、w5和w6，且w4>w5>w6。当N4大于N3(即第G1代中所有天线参数组合中存在天线参数组合在上述第一指标上的完成量大于N3时)，若上述第一天线参数组合在第一指标上的完成量小于N3，则Q个区间可以随意设定，且Q个区间对应的激励系数均为负无穷；若上述第一天线参数组合在第一指标上的完成量不小于N3，则上述第一指标的Q个区间可以被设定为[0，N2]、[N2，100]，其所对应的激励系数可以分别为w7和w8，且w7<w8。
用户需求③：上述Q个指标中还包括第二指标、第三指标等多个指标，此时用户对上述第一指标要求为上述第一指标的期望值为N5，用户希望重点保障上述第二指标、第三指标等指标在后续子代中的优化程度。此时用户希望上述Q个指标同时进行优化。且父本中的天线参数组合若在某个指标上已经达到用户对该指标的期望值，则后续过程中，对于该指标的优化程度可以降低。
对于用户需求③，假设上述第一天线参数组合父本的(假设这一代为第G2代)的所有天线参数组合中，在上述第一指标上的完成量最大为N6。上述第一指标的Q个区间可以被设定为[0，N6-N7]、[N6-N7，N5]以及[N5，100]，其中，N7可以为小于N6的任意正整数；其所对应的激励系数可以分别为w7、w8和w9，且w8>w7>w9。
用户需求④：上述Q个指标中还包括第二指标、第三指标等多个指标，用户希望最后用于天线使用的参数组合的价值可以最大。
对于用户需求④，假设上述第一天线参数组合的父本的(假设这一代为第G3代)的所有天线参数组合中，在上述第一指标上的完成量最大为N8。上述第一指标的Q个区间可以被设定为[0，N8-N9]、[N8-N9，100]，其中，N9可以为小于N8的任意正整数；其所对应的激励系数可以分别为w10、w11，且w11>w10。
上面只是示例性地给出了几个具体的用户需求以及在这些用户需求下上述第一指标的Q个区间以及其对应的Q个激励系数的设定规则。对于不同的用户需求而言，上述第一指标的Q个区间的以及其对应的Q个激励系数可以不同，这里不再一一列举。
应理解，上述第一指标的Q个区间以及其对应的Q个激励系数的设定需要在天线参数组合开始优化(即产生第一代天线参数组合)之前设定完成。也就是说，在后续的天线参数组合优化的过程中，用户无法对上述第一指标的Q个区间以及其对应的Q个激励系数的设定进行更改，设备将根据用户需求为子代中的天线参数组合设定上述第一指标的上述Q个区间的以及其对应的Q个激励系数。
在一个可选的实施方式中，上述第一指标的Q个区间包括第一区间以及第二区间，上述第一区间的右端点值小于或等于上述第二区间的左端点值，上述第二区间对应的激励系数为第二激励系数，上述第一区间对应的激励系数为第一激励系数，上述第二激励系数小于上述第一激励系数。即上述第一指标的Q个区间对应的Q个激励系数设定为随着区间数值的增大而减小。此外，上述的Q个区间还可以包括第三区间，当第三区间的右端点值小于或等于上述第一区间的左端点值时，上述第二激励系数小于改第三区间对应的第三激励系数。可以理解的，在天线参数的多目标优化问题中，多个目标的优化程度是相互矛盾的。例如，当天线信号的覆盖率越大时，往往信号相互之间干扰也越强。因此，在本实施方式中，由于当上述某个天线参数组合在第一指标上的完成量越大时，该天线参数组合在上述第一指标上距离客户预期越近。此时，将上述Q个区间对应的Q个激励系数设定为随着区间数值的增大而减小，来避免后续子代在该指标上的持续优化，以此换取后续产生的天线参数组合在其它指标上的优化，得到在各个指标上通信质量综合更优的天线参数组合。
在一个可选的实施方式中，上述第二区间的左端点值为上述第一天线参数组合在上述第一指标上的完成量，上述完成量表征上述天线采用上述第一天线参数组合发射的信号在上述第一指标上通信质量的优劣程度。在本实施方式中，上述第一指标的Q个区间还可以包括第三区间、第四区间等多个区间。其中，上述第二区间中的左端点值大于其他(Q-1)个区间中包含的任意数值。将上述第二区间的左端点值为上述第一天线参数组合在上述第一指标上的完成量，可以在满足用户对上述第一指标的需求的情况下，更为精确地控制后续子代中的天线参数组合中在上述第一指标上的完成量与用户对上述第一指标的需求的差距，以此来换取后续产生的天线参数组合在其它指标上的更大的优化程度。
在一个可选的实施方式中，上述第二激励系数小于或等于0。在本实施方式中，上述第二激励系数对应的第二区间中任意一个数值均大于用户对上述第一指标的需求。也就是说，当上述第一天线参数组合在上述第一指标上的完成量超过用户对上述第一指标的需求之后，通过将上述第二激励系数调整0或者负数，可以避免类似上述第一天线参数组合这样在上述第一指标上过度优化的参数组合被确定为下一代的父本。这样，可以在满足用户对上述第一指标的需求的情况下，更为精确地控制后续子代中的天线参数组合中在上述第一指标上的完成量与用户对上述第一指标的需求的差距，以此来换取后续产生的天线参数组合在其它指标 上的更大的优化程度。
202.上述电子设备将上述N组天线参数组合中价值较大的M组天线参数组合作为候选天线参数集合。
在得到上述N组天线参数组合中每组天线组合的价值之后，上述电子设备将对上述N组天线参数组合中每组天线参数组合的价值进行比较，从上述N组天线参数组合中价值较大的M组天线参数组合作为候选天线参数集合。
在一种可选的实施方式中，为了在后续天线参数组合的交叉、变异(即通过遗传算法产生子代)的过程中，可以最大程度保障子代中的天线参数组合与用户需求的匹配程度，上述电子设备可以将所述N组天线参数组合中价值居于前M个天线参数组合作为候选天线参数集合。
203.上述电子设备将上述候选天线参数集合中的天线参数组合作为父本来确定目标天线参数组合。
在确定上述候选天线参数组合之后，上述电子设备上基于遗传算法，即将上述候选天线参数集合中的天线参数组合作为父本粒子，彼此之间进行交叉、变异，以此产生新一代的粒子。
可以理解的，在遗传算法不断迭代的过程中，每一代产生的粒子种群都可以基于本申请实施例提供的方法计算出每个粒子的价值，并基于每个粒子的价值从该代粒子种群中挑选出用做父本进行繁衍的粒子。
具体的，当为G x代和G x-1代(G x代和G x-1代为连续两代，即G x代中的粒子为G x-1代中粒子的父本)中的粒子价值变化程度小于预设的范围时，则上述电子设备将上述G x代中的粒子或者上述G x-1代中的粒子中价值较高的粒子确定为上述目标天线参数组合。例如，当上述G x代中的各个粒子的价值的平均值与或者上述G x-1代中的各个粒子的价值的平均值的差距小于预设的阈值时；或，当上述G x代中的粒子中价值最高的粒子的价值与上述G x-1代中的粒子中价值最高的粒子的价值之差小于预设的阈值时，则上述电子设备将判定天线参数组合的寻优已经达到最优水平，则上述电子设备可以将上述G x代中的粒子或者上述G x-1代中的粒子中价值最高的粒子确定为上述目标天线参数组合。
本方法通过根据用户的需求从粒子种群中选择与用户需求适配的粒子作为后续子代的父本粒子，能更加快速、高效地从每一代的子代中获取与用户实际的需求相匹配的天线参数组合，提高天线参数组合的确定速度。
基于上述天线参数组合的确定方法，本申请实施例提供了一种候选参数集合的确定方法。上述图2中的候选参数集合可以基于本申请实施例提供的候选参数集合的确定方法进行确定。具体请参阅图3。如图3所示，该方法可以包括以下步骤：
301.电子设备获取第一参数以及第二参数。
上述电子设备可以是带数据收发功能的电脑(如笔记本电脑、掌上电脑等)、手机(mobile phone)、平板电脑(pad)、移动互联网设备(mobile internet device，MID)、工业控制(industrial control)中的终端、智慧城市(smart city)中的终端5G网络中的终端设备或者未来演进的公用陆地移动通信网络(public land mobile network，PLMN)中的终端设备等，本申请对该电子设备的具体形态不作限制。具体的，该电子设备可以是前述对图2说明中的电子设备。
上述第一参数可以包括P个通信指标中每个通信指标的目标阈值，该第二参数包括上述P个通信指标中每个通信指标的权重，上述P为大于1的整数；上述第一参数以及上述第二参数用于确定上述P个指标中每个指标的多个区间，以及每个指标的多个区间分别对应的多 个激励系数。例如，述第一参数以及上述第二参数可以用于确定上述P个指标中第一指标的Q个区间，以及该第一指标的Q个区间分别对应的Q个激励系数。
302.上述电子设备获取第一天线参数组合在P个通信指标上的P个激励值。
具体的，为了从N个天线参数组合中确定作为下一代父本的候选参数集合，需要量化上述N个天线参数组合中每个天线参数组合的价值，该价值表示天线参数组合与用户需求的适配程度。以上述第一天线组合为例进行说明，在一个可选的实施方式中，上述电子设备可以通过获取上述第一天线参数组合在P个通信指标上的P个激励值，并根据该第一天线参数组合在该P个通信指标上的P个激励值，得到所述第一天线参数组合的价值。
其中，所述P个通信指标可以包括天线信号的覆盖率、速率、信号之间的干扰程度等指标。所述第一指标为所述P个通信指标中的指标，其可以为天线信号的覆盖率、速率、信号等指标中的任意一个指标。所述第一指标的Q个区间可以根据所述用户需求进行设定。上述完成量表征所述天线采用述上第一参数组合发射的信号在上述第一指标上通信质量的优劣程度。例如，当上述第一指标为天线信号的覆盖率时，其可以达到的最好结果为100％(假设此覆盖率对应的完成量为100)，则当天线上述第一指标采用述上第一参数组合发射的信号覆盖率为90％，则上述第一天线参数组合在上述第一指标上的完成量即为90，以此类推。
具体的，上述第一指标的激励值的计算方式可以表示为：
P 1＝W p1*L[T 0，T 1]*J 1+W p1*L[T 1，T 2]*J 2+……+W p1*L[T Q-1，T Q]*J Q；
其中，P 1上述第一指标的激励值，W p1表示上述P个通信指标中第一指标对应的多目标权重，其可以由用户自定义，默认情况下，P个通信指标中每个指标对应的多目标权重均相同，设定为1。“*”表示乘法运算，[T N-1，T N](N＝1，2，3，……，Q)表示上述第一指标的Q个区间中的第N个区间。J N(N＝1，2，3，……，Q)即为上述第一指标的Q个区间中第N个区间对应的激励值。L[T N-1，T N]表示上述完成量覆盖在第N个区间上的长度；例如，假设上述完成量为60，当T N-1＝30，T N＝80时，则L[30，80]＝60-30＝30；当T N-1＝0，T N＝50时，则L[0，80]＝60-0＝60；当T N-1＝30，T N＝40时，则L[30，40]＝40-30＝10；当T N-1＝80，T N＝90时，则L[30，80]＝0；以此类推。
应理解，上述第一指标的Q个区间可以根据用户需求进行设定。例如，假设上述第一指标的最优值(即所述第一指标所能达到的最好的程度)为100，用户对所述第一指标的要求为所述第一指标的值不能低于90。则上述Q个区间可以为[0，80]、[80，90]以及[90，100]，其所对应的激励系数可以分别为10、1和0。假设所述第一天线参数组合在所述第一指标上的完成量为88时，此时上述完成量落入区间[80，90]中，则根据上述表达式和Q个区间的以及Q个激励系数的设定况情可以算出，所述第一天线参数组合在所述P个通信指标中第一指标上的激励值为：(80×10)+(88-80)×1＝808；假设所述第一天线参数组合在所述第一指标上的完成量为92时，此时所述完成量落入区间[90，100]中，则所述第一天线参数组合在所述P个通信指标中第一指标上的激励值为：(80-0)×10+(90-80)×1+(92-90)×0＝810。
303.上述电子设备根据上述第一天线参数组合在上述P个通信指标上的P个激励值，得到上述第一天线参数组合的价值。
进一步的，基于上述第一天线参数组合在上述第一指标的激励值的计算表达式，上述第一天线参数组合的价值的计算方式可以表示为：
Figure PCTCN2021130770-appb-000007
其中，P w1为上述第一天线参数组合的价值，W pi表示P个通信指标中第i(i＝1,2,3,……,P)个指标对应的多目标权重，其可以由用户自定义，默认情况下，P个通信指标中每个指标对应的多目标权重均相同，设定为1。P i为上述第一天线参数组合在上述P个通信指标中的第i(i＝1,2,3,……,P)个通信指标上的激励值，P i的计算方式可以参考上述第一天线参数组合在上述第一指标的激励值的计算表达式。
304.上述电子设备获取N组天线参数组合中每组天线参数组合的价值。
可以理解的，上述第一天线参数组合为上述N组天线参数组合中的一组天线参数组合。上述第一参数以及上述第二参数还可以用于确定上述P个指标中除第一指标外的其他指标的多个区间，以及其他指标的多个区间分别对应的多个激励系数。例如，上述第一参数以及上述第二参数还可以用于确定上述P个指标中第二指标的R个区间以及对应的R个激励系数，以及第三指标的S个区间以及对应的S个激励系数，以此类推。相应的，参考步骤303-步骤304中第一天线参数组合在第一指标的激励值P 1以及第一天线参数组合P w1的计算方法，上述电子设备还可以计算出上述N组天线参数组合中每组天线参数组合的价值，这里不再一一列举。
305.上述电子设备将上述N组天线参数组合中价值居于前M个天线参数组合作为候选天线参数集合。
在得到上述N组天线参数组合中每组天线组合的价值之后，为了在后续天线参数组合的交叉、变异(即通过遗传算法产生子代)的过程中，最大程度保障子代中的天线参数组合与用户需求的匹配程度，上述电子设备将对上述N组天线参数组合中每组天线参数组合的价值进行比较，从上述N组天线参数组合中价值居于前M个天线参数组合作为上候选天线参数集合。
本申请实施例通过根据用户的需求设置小区天线各项通信指标的激励区间和每个指标在不同激励区间下的激励系数，具体量化了天线参数组合与用户程度的适配度，能更加快速、高效地从每一代的子代中获取与用户实际的需求相匹配的天线参数组合。
由前述说明可知，在天线参数的多目标优化问题中，多个目标的优化程度是相互矛盾的。例如，当天线信号的覆盖率越大时，往往信号相互之间干扰也越强。因此，在本申请中，当上述某个天线参数组合在某个指标上的完成量越大时，表示该天线参数组合在上述第一指标上距离客户预期越近。此时，可以将该指标对应的多个区间以及对应多个激励系数设定为随着区间数值的增大而减小，甚至一些区间的激励系数调整0或者负数，来避免后续子代在该指标上的持续优化，以此换取后续产生的天线参数组合在其它指标上的优化，得到在各个指标上通信质量综合更优的天线参数组合。据此，本申请实施例提供了一种指标区间与激励系数之间的关系图以及一种天线参数组合在指标上的总体完成量与该指标的优化效率的关系图，请参考图4和图5。
首先请参阅图4。图4为本申请实施例提供了一种指标区间与激励系数之间的关系图。如图4所示，在图4中的坐标系中，横坐标表示天下参数组合在某个指标对应的完成量，纵坐标表示该指标各个区间对应的激励系数。应理解，对于不同的指标而言，指标对应的区间以及激励系数可以不同，为便于读者理解，本实施例以该指标为上述第一指标，且上述第一指标的对应的区间和激励系数均为三个进行说明。
在图4中，上述第一指标对应的区间分为[0，T1]、[T1，T2]以及[T2，100]，其中T2为用户在该指标上的期望值，“100”为该指标实际可以达到的最优值对应的完成量。相应的，区间[0，T1]对应的激励系数为第一激励系数，其值为10；区间[T1，T2]对应的激励系数为第二激励系数，其值为1；区间[T2，100]对应的激励系数为第三激励系数，其值为0；在一个可选的方式中，区间[T2，100]对应的激励系数也可以为第四激励系数，其值为-1。在计算各个天线参数组合在第一指标上激励值时，只需要根据各个天线参数组合在该指标上的完成量以及[0，T1]、[T1，T2]以及[T2，100]三个区间和三个区间对应的激励系数进行计算，具体可以参考前述说明，这里不再赘述。
这样，在从每一代粒子中挑选出作为下一次迭代的父本粒子时，当这一代中的粒子种群的粒子在上述第一指标上的完成量与T2相差较远(例如完成量小于T1)时，则从该粒子种群中挑选价值较大的粒子时，由于[0，T1]区间对应的激励系数较大，则挑选出来的粒子在第一指标上的完成量也较大，以此来完成对第一指标的加速优化。同理，当这一代中的粒子种群的大部分粒子在上述第一指标上的完成量已经达到T2时，则从该粒子种群中挑选价值较大的粒子时，由于[T2，100]区间对应的激励系数为0或者为负，则挑选出来的粒子在保证用户需求的情况下，也不会将在第一指标上完成过大的粒子选为下一代的父本粒子，在抑制后续子代在第一指标上的持续优化的同时，换取后续产生的天线参数组合在其它指标上的优化。
图5为一种天线参数组合在指标上的总体完成量与该指标的优化效率的关系图。如图5所示，在图5中的坐标系中，横坐标表示粒子种群的迭代次数，纵坐标表示粒子种群在某个指标上的总体完成量，该总体完成量可以为每一代的粒子种群中所有粒子总群在该指标上完成量的平均值。具体的，图5中的第一指标和第二指标可以为前述说明中的第一指标和第二指标。
在图5中，第一指标的用户期望值为95。从图5可以看出，在总体完成量小于95之前，随着粒子总群的迭代次数的增加(即遗传算法的演进)，每一代的粒子种群在第一指标和第二指标上的总体完成量也在逐渐提高，但是在总体完成量达到95之后，随着粒子总群的迭代次数的增加，每一代的粒子种群在该指标上的总体完成量将趋于平稳或者略有下降。而且在图中t1-t2段对应的子代中，粒子种群中的粒子在第一指标上的总完成量离用户期望较远，此区间内指标的激励系数大，每一代的粒子种群在第一指标上的优化速率(即总完成量的增长速率)极快；但是t2-t3段对应的子代中，粒子种群中的粒子在第一指标上的总完成量离用户期望较近，每一代的粒子种群在第一指标上的总体完成量虽然也在持续增长，但是优化速率相较于t1-t2段对应的子代中的优化速率明显降低；直至t3-t4段对应的子代中的粒子总群的总完量已经达到用户需求之后，每一代的粒子种群在第一指标上的总体完成量达到用户期望，此区间段激励系数为0，每一代的粒子种群在该指标上的总体完成量将趋于平稳，在第一指标上的优化停止。
同理，参考图5中第二指标对应的曲线，第二指标的用户期望值也为95。在t5-t6段对应的子代中粒子种群中的粒子在第一指标上的总完成量已经超出用户期望，每一代的粒子种群在第一指标上的总体完成量负增长，优化速率为负。
接下来结合用户意图来对上述候选天线集合的确定过程进行说明，请参阅图6。
图6为本申请实施例提供的二维搜索空间中粒子种群分布的示意图。其中，二维搜索空间代表的两个维度可以是前述Q个通信指标中的覆盖率和速率。现在假设用户对于天线信号的只有这两个指标方面的需求，这两个指标能达到的最优值均为100，且图6中粒子61、粒子62、粒子63以及粒子64的在覆盖率和速率这两个指标上的完成量如下列表1所示：
表1
  粒子61 粒子62 粒子63 粒子64
覆盖率 86 87 92 91
速率 70 90 50 51
而用户1，用户2，用户3以及用户4对上述两个指标的用户意图分别为：
用户意图①：优先保障覆盖率的优化程度，且用户对覆盖率的要求为不能低于90。
则对于用户需求①，覆盖率对应的多个区间可以被设定为[0，90]以及[90，100]，其所对应的激励系数可以分别为100和0；速率对应的多个区间可以被设定为[0，90]以及[90，100]，其所对应的激励系数可以分别为1和0。基于前述说明可知：粒子61的价值P1 w61＝86×100+70×1＝8670(这里假设两个指标对应的多目标权重均为1，下同)；粒子62的价值P1 w62＝87×100+90×1＝8790；粒子63的价值P1 w63＝90×100+2×0+70×1＝9050；粒子64的价值P1 w64＝90×100+1×0+51×1＝9051；则粒子64被确定为候选天线集合中的粒子。
用户意图②：对覆盖率的期望值为90，但是允许其恶化，但恶化程度不能超过一个下限(即允许子代中的天线参数组合在覆盖率上的完成量小于子代中的天线参数组合在上述第一指标上的优劣的完成量，但后续每个子代中的天线参数组合在上述第一指标上的完成量均不能小于某个预设的阈值，这里假设该阈值为87)，重点保障速率在后续子代中的优化程度且用户对速率的要求为不能低于90。
则对于用户需求②，假设粒子61-粒子64的父本粒子中，在覆盖率上完成量最大的粒子的完成量为88，则对于在覆盖率上的完成量小于87的粒子，其价值为负无穷；对于在覆盖率上的完成量不小于87的粒子，则覆盖率对应的多个区间可以被设定为[0，90]以及[90，100]，其所对应的激励系数可以分别为1和0。速率对应的多个区间可以被设定为[0，90]以及[90，100]，其所对应的激励系数可以分别为10和0。基于前述说明可知：粒子61的价值P2 w61＝-∞；粒子62的价值P2 w62＝87×1+90×10＝987；粒子63的价值P2 w63＝90×1+50×10＝590；粒子64的价值P2 w64＝90×1+51×10＝600；则粒子62被确定为候选天线集合中的粒子。
用户意图③：对覆盖率和速率的期望值为90，重点保障速率在后续子代中的优化程度。且用户希望对速率和覆盖率均进行优化。当父本中对某个指标的完成量已经达到用户对该指标的期望值之后，则后续过程中，对于该指标的优化程度可以降低。
则对于用户需求③，假设粒子61-粒子64的父本粒子中，在覆盖率上完成量最大的粒子的完成量为88，在速率上完成量最大的粒子的完成量为85。则覆盖率的多个区间可以备设定为[0，88-2]、[88-2，90]以及[90，100]，其所对应的激励系数可以分别为1、10和0；速率对应的多个区间可以被设定为[0，85-2]、[85-2，90]以及[90，100]，其所对应的激励系数可以分别为1、10和0。基于前述说明可知：粒子61的价值P3 w61＝86×1+70×1＝156；粒子62的价值P3 w62＝86×1+1×10+83×1+7×10＝249；粒子63的价值P3 w63＝86×1+4×10+2×0+50×1＝176；粒子64的价值P3 w64＝86×1+4×10+1×0+51×1＝177；则粒子64被确定为候选天线集合中的粒子。
用户意图④：最后用于天线使用的天参数组合的价值可以最大。
则对于用户需求④，假设粒子51-粒子54的父本粒子中，在覆盖率上完成量最大的粒子的完成量为88，在速率上完成量最大的粒子的完成量为85。则覆盖率的多个区间可以备设定为[0，88-2]、[88-2，100]，其所对应的激励系数可以分别为1、10；速率对应的多个区间可以被设定为[0，85-2]、[85-2，100]，其所对应的激励系数可以分别为1、10。基于前述说明可知：粒子61的价值P4 w61＝86×1+70×1＝156；粒子62的价值P4 w62＝86×1+1×10+83×1+7×10＝249； 粒子63的价值P4 w63＝86×1+6×10+50×1＝196；粒子64的价值P4 w64＝86×1+5×10+51×1＝187；则粒子63被确定为候选天线集合中的粒子。
本方法通过根据用户的需求设置小区天线各项通信指标的激励区间和每个指标在不同激励区间下的激励系数，能更加快速、高效地从每一代的子代中获取与用户实际的需求相匹配的天线参数组合，提高天线参数组合的确定速度，具体请参考图7和图8。
图7为本申请实施例提供的一种粒子迭代次数和指标优化程度之间的关系图。如图6所示，图7中的坐标系的横坐标表示天线参数组合在覆盖率上的完成量，纵坐标表示天线参数组合在速率上的完成量，其中曲线701表示采用传统的帕累托支配排序方法迭代500之后所得的各个天线参数组合在覆盖率和速率上的完成量，曲线702、曲线703以及曲线704分别表示采用本申请实施例提供的天线参数组合的确定方法迭代50次、150次以及500次之后所得的各个天线参数组合在覆盖率和速率上的完成量。从总体上可以看出，在迭代次数相同的情况下，本申请实施例提供的天线参数组合的确定方法可以得到更优良的天线参数组合。相应的，图8提供了一种粒子迭代次数和覆盖率优化程度之间的关系图。图7中的坐标系的横坐标表示粒子的迭代次数，纵坐标表示天线参数组合在覆盖率上的完成量。曲线801表示采用传统的帕累托支配排序方法进行迭代所得的各个天线参数组合在覆盖率完成量随迭代次数的变化关系；曲线802表示采用本申请实施例提供的天线参数组合的确定方法进行迭代所得的各个天线参数组合在覆盖率完成量随迭代次数的变化关系。同样的，从总体上可以看出，在迭代次数相同的情况下，本申请实施例提供的天线参数组合的确定方法可以得到更优良的天线参数组合。
下面介绍本申请实施例提供的一种天线参数组合的确定装置的结构示意图，请参阅图9。图9中的天线参数组合的确定装置可以执行图2中天线参数组合的确定方法的流程，还可以执行图3中候选参数集合的确定方法的流程，如图9所示，该装置可以包括：
计算单元901，用于获取N组天线参数组合中每组天线参数组合的价值，上述N组天线参数组合中的第一天线参数组合的价值表征上述第一天线参数组合与用户需求的适配程度；确定单元902，用于将上述N组天线参数组合中价值较大的M组天线参数组合作为候选天线参数集合，上述M小于上述N，上述M为大于0的整数，上述N为大于1的整数；遗传单元903，用于将上述候选天线参数集合中的天线参数组合作为父本来确定目标天线参数组合，上述目标天线参数组合用于天线发射信号。
在一种可选的实施方式中，上述计算单元901，具体用于：获取上述第一天线参数组合在P个通信指标上的P个激励值，上述第一天线参数组合在上述P个通信指标中第一指标上的激励值由上述第一天线参数组合在第一指标上的完成量，以及上述第一指标的Q个区间和上述Q个区间对应的Q个激励系数确定，上述完成量表征上述天线采用上述第一参数组合发射的信号在上述第一指标上通信质量的优劣程度，上述P和上述Q为大于1的整数；根据上述第一天线参数组合在上述P个通信指标上的P个激励值，得到上述第一天线参数组合的价值。
在一种可选的实施方式中，所述装置还包括：获取单元904，用于获取第一参数以及第二参数；上述第一参数包括上述P个通信指标中每个通信指标的目标阈值，上述第二参数包括上述P个通信指标中每个通信指标的权重，上述P为大于1的整数；上述第一参数以及上述第二参数用于确定上述第一指标的Q个区间，以及上述Q个区间分别对应的Q个激励系数。
在一种可选的实施方式中，上述第一指标的Q个区间包括第一区间以及第二区间，上述 第一区间的右端点值小于或等于上述第二区间的左端点值，上述第二区间对应的激励系数为第二激励系数，上述第一区间对应的激励系数为第一激励系数，上述第二激励系数小于上述第一激励系数。
在一种可选的实施方式中，上述第二区间的左端点值为上述第一天线参数组合在上述第一指标上的完成量，上述完成量表征上述天线采用上述第一参数组合发射的信号在上述第一指标上通信质量的优劣程度。
在一种可选的实施方式中，上述第二激励系数小于或等于0。
在一种可选的实施方式中，上述确定单元902，具体用于：将上述N组天线参数组合中价值居于前M个天线参数组合作为候选天线参数集合。
应理解，以上天线参数组合的确定装置的各个单元的划分仅仅是一种逻辑功能的划分，实际实现时可以全部或部分集成到一个物理实体上，也可以物理上分开。例如，以上各个单元可以为单独设立的处理元件，也可以集成同一个芯片中实现，此外，也可以以程序代码的形式存储于控制器的存储元件中，由处理器的某一个处理元件调用并执行以上各个单元的功能。此外各个单元可以集成在一起，也可以独立实现。这里的处理元件可以是一种集成电路芯片，具有信号的处理能力。在实现过程中，所述方法的各步骤或以上各个单元可以通过处理器元件中的硬件的集成逻辑电路或者软件形式的指令完成。所述处理元件可以是通用处理器，例如CPU，还可以是被配置成实施以上方法的一个或多个集成电路，例如：一个或多个特定集成电路(application-specific integrated circuit，ASIC)，或，一个或多个微处理器(digital signal processor，DSP)，或，一个或者多个现场可编程门阵列(field-programmable gate array，FPGA)等。
图10为本申请实施例提供的一种电子设备的结构示意图。如图10所示，该电子设备100包括处理器1001、存储器1002以及通信接口1003；该处理器1001、存储器1002以及通信接口1003通过总线相互连接。该电子设备可以是前述说明中天线参数组合的确定装置。
存储器1002包括但不限于是随机存储记忆体(random access memory，RAM)、只读存储器(read-only memory，ROM)、可擦除可编程只读存储器(erasable programmableread only memory，EPROM)、或便携式只读存储器(compact disc read-only memory，CDROM)，该存储器1002用于相关指令及数据。通信接口1003用于接收和发送数据，其可以实现图9中获取单元904的功能。
处理器1001可以是一个或多个中央处理器(central processing unit，CPU)，在处理器1001是一个CPU的情况下，该CPU可以是单核CPU，也可以是多核CPU。上述实施例中由天线参数组合的确定装置所执行的步骤可以基于该图10所示的电子设备的结构。具体的，处理器1001可实现图9中计算单元901、确定单元902以及遗传单元903的功能。
该电子设备100中的处理器1001用于读取该存储器1002中存储的程序代码，执行前述实施例中的天线参数组合的确定方法。
在本申请的实施例中提供另一种计算机可读存储介质，该计算机可读存储介质存储有计算机程序，该计算机程序被处理器执行时实现：获取N组天线参数组合中每组天线参数组合的价值，该N组天线参数组合中的第一天线参数组合的价值表征该第一天线参数组合与用户需求的适配程度；将该N组天线参数组合中价值较大的M组天线参数组合作为候选天线参数集合，该M小于该N，该M为大于0的整数，该N为大于1的整数；将该候选天线参数集合中的天线参数组合作为父本来确定目标天线参数组合，该目标天线参数组合用于天线发射信号。
本申请实施例还提供了一种包含指令的计算机程序产品，当其在计算机上运行时，使得计算机执行前述实施例所提供的天线参数组合的确定方法。
本申请实施例中，“示例性的”或者“例如”等词用于表示作例子、例证或说明。本申请中被描述为“示例性的”或者“例如”的任何实施例或设计方案不应被解释为比其他实施例或设计方案更优选或更具优势。确切而言，使用“示例性的”或者“例如”等词旨在以具体方式呈现相关概念。
本申请中实施例提到的“至少一个”是指一个或者多个，“多个”是指两个或两个以上。“以下至少一项(个)”或其类似表达，是指的这些项中的任意组合，包括单项(个)或复数项(个)的任意组合。例如，a、b、或c中的至少一项(个)，可以表示：a、b、c、(a和b)、(a和c)、(b和c)、或(a和b和c)，其中a、b、c可以是单个，也可以是多个。“和/或”，描述关联对象的关联关系，表示可以存在三种关系，例如，A和/或B，可以表示：单独存在A、同时存在A和B、单独存在B这三种情况，其中A、B可以是单数或者复数。字符“/”一般表示前后关联对象是一种“或”的关系。
以及，除非有相反的说明，本申请实施例使用“第一”、“第二”等序数词是用于对多个对象进行区分，不用于限定多个对象的顺序、时序、优先级或者重要程度。例如，第一设备和第二设备，只是为了便于描述，而并不是表示这第一设备和第二设备的结构、重要程度等的不同，在某些实施例中，第一设备和第二设备还可以是同样的设备。
上述实施例中所用，根据上下文，术语“当……时”可以被解释为意思是“如果……”或“在……后”或“响应于确定……”或“响应于检测到……”。以上所述仅为本申请的可选实施例，并不用以限制本申请，凡在本申请的构思和原则之内，所作的任何修改、等同替换、改进等，均应包含在本申请的保护范围之内。本领域普通技术人员可以理解实现上述实施例的全部或部分步骤可以通过硬件来完成，也可以通过程序来指令相关的硬件完成，所述的程序可以存储于一种计算机可读存储介质中，上述提到的存储介质可以是只读存储器，磁盘或光盘等。

Claims (16)

  1. 一种天线参数组合的确定方法，其特征在于，包括：
    获取N组天线参数组合中每组天线参数组合的价值，所述N组天线参数组合中的第一天线参数组合的价值表征所述第一天线参数组合与用户需求的适配程度；
    将所述N组天线参数组合中价值较大的M组天线参数组合作为候选天线参数集合，所述M小于所述N，所述M为大于0的整数，所述N为大于1的整数；
    将所述候选天线参数集合中的天线参数组合作为父本来确定目标天线参数组合，所述目标天线参数组合用于天线发射信号。
  2. 根据权利要求1所述的方法，其特征在于，所述获取N组天线参数组合中每组天线参数组合的价值，包括：
    获取所述第一天线参数组合在P个通信指标上的P个激励值，所述第一天线参数组合在所述P个通信指标中第一指标上的激励值由所述第一天线参数组合在第一指标上的完成量，以及所述第一指标的Q个区间和所述Q个区间对应的Q个激励系数确定，所述完成量表征所述天线采用所述第一参数组合发射的信号在所述第一指标上通信质量的优劣程度，所述P和所述Q为大于1的整数；
    根据所述第一天线参数组合在所述P个通信指标上的P个激励值，得到所述第一天线参数组合的价值。
  3. 根据权利要求2所述的方法，在获取所述第一天线参数组合在P个通信指标上的P个激励值之前，所述方法还包括：
    获取第一参数以及第二参数；所述第一参数包括所述P个通信指标中每个通信指标的目标阈值，所述第二参数包括所述P个通信指标中每个通信指标的权重，所述P为大于1的整数；所述第一参数以及所述第二参数用于确定所述第一指标的Q个区间，以及所述Q个区间分别对应的Q个激励系数。
  4. 根据权利要求2或3所述的方法，其特征在于，所述第一指标的Q个区间包括第一区间以及第二区间，所述第一区间的右端点值小于或等于所述第二区间的左端点值，所述第二区间对应的激励系数为第二激励系数，所述第一区间对应的激励系数为第一激励系数，所述第二激励系数小于所述第一激励系数。
  5. 根据权利要求4所述的方法，其特征在于，所述第二区间的左端点值为所述第一天线参数组合在所述第一指标上的完成量，所述完成量表征所述天线采用所述第一参数组合发射的信号在所述第一指标上通信质量的优劣程度。
  6. 根据权利要求4或5所述的方法，其特征在于，所述第二激励系数小于或等于0。
  7. 根据权利要求1-6任一项所述的方法，其特征在于，所述将所述N组天线参数组合中价值较大的M组天线参数组合作为候选天线参数集合，包括：
    将所述N组天线参数组合中价值居于前M个天线参数组合作为候选天线参数集合。
  8. 一种天线参数组合的确定装置，其特征在于，包括：
    计算单元，用于获取N组天线参数组合中每组天线参数组合的价值，所述N组天线参数组合中的第一天线参数组合的价值表征所述第一天线参数组合与用户需求的适配程度；
    确定单元，用于将所述N组天线参数组合中价值较大的M组天线参数组合作为候选天线参数集合，所述M小于所述N，所述M为大于0的整数，所述N为大于1的整数；
    遗传单元，用于将所述候选天线参数集合中的天线参数组合作为父本来确定目标天线参数组合，所述目标天线参数组合用于天线发射信号。
  9. 根据权利要求8所述的装置，其特征在于，所述计算单元，具体用于：
    获取所述第一天线参数组合在P个通信指标上的P个激励值，所述第一天线参数组合在所述P个通信指标中第一指标上的激励值由所述第一天线参数组合在第一指标上的完成量，以及所述第一指标的Q个区间和所述Q个区间对应的Q个激励系数确定，所述完成量表征所述天线采用所述第一参数组合发射的信号在所述第一指标上通信质量的优劣程度，所述P和所述Q为大于1的整数；
    根据所述第一天线参数组合在所述P个通信指标上的P个激励值，得到所述第一天线参数组合的价值。
  10. 根据权利要求9所述的方法，其特征在于，所述装置还包括：
    获取单元，用于获取第一参数以及第二参数；所述第一参数包括所述P个通信指标中每个通信指标的目标阈值，所述第二参数包括所述P个通信指标中每个通信指标的权重，所述P为大于1的整数；所述第一参数以及所述第二参数用于确定所述第一指标的Q个区间，以及所述Q个区间分别对应的Q个激励系数。
  11. 根据权利要求9或10所述的装置，其特征在于，所述第一指标的Q个区间包括第一区间以及第二区间，所述第一区间的右端点值小于或等于所述第二区间的左端点值，所述第二区间对应的激励系数为第二激励系数，所述第一区间的激励值为第一激励系数，所述第二激励系数小于所述第一激励系数。
  12. 根据权利要求11所述的装置，其特征在于，所述第二区间的左端点值为所述第一天线参数组合在所述第一指标上的完成量，所述完成量表征所述天线采用所述第一参数组合发射的信号在所述第一指标上通信质量的优劣程度。
  13. 根据权利要求11或12所述的装置，其特征在于，所述第二激励系数小于或等于0。
  14. 根据权利要求8-13任一项所述的装置，其特征在于，所述确定单元，具体用于：
    将所述N组天线参数组合中价值居于前M个天线参数组合作为候选天线参数集合。
  15. 一种电子设备，其特征在于，包括：存储器，用于存储程序；处理器，用于执行所述存储器存储的所述程序，当所述程序被执行时，所述处理器用于执行如权利要求1至7中任一项所述的方法。
  16. 一种计算机可读存储介质，其特征在于，所述计算机存储介质存储有计算机程序，所述计算机程序包括程序指令，所述程序指令当被处理器执行时使所述处理器执行如权利要求1至7任一项所述的方法。
PCT/CN2021/130770 2021-11-15 2021-11-15 天线参数组合的确定方法及相关装置 WO2023082288A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN202180103762.2A CN118160342A (zh) 2021-11-15 2021-11-15 天线参数组合的确定方法及相关装置
PCT/CN2021/130770 WO2023082288A1 (zh) 2021-11-15 2021-11-15 天线参数组合的确定方法及相关装置

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2021/130770 WO2023082288A1 (zh) 2021-11-15 2021-11-15 天线参数组合的确定方法及相关装置

Publications (1)

Publication Number Publication Date
WO2023082288A1 true WO2023082288A1 (zh) 2023-05-19

Family

ID=86334976

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/130770 WO2023082288A1 (zh) 2021-11-15 2021-11-15 天线参数组合的确定方法及相关装置

Country Status (2)

Country Link
CN (1) CN118160342A (zh)
WO (1) WO2023082288A1 (zh)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2000216619A (ja) * 1998-11-20 2000-08-04 Matsushita Electric Ind Co Ltd アダプティブアレ―アンテナ
CN101651982A (zh) * 2009-08-07 2010-02-17 重庆邮电大学 一种基于New-Memetic算法的波束成型方法
CN102316469A (zh) * 2010-06-30 2012-01-11 华为技术有限公司 配置天线参数的方法及系统
CN102625322A (zh) * 2012-02-27 2012-08-01 北京邮电大学 多制式智能可配的无线网络优化的实现方法
CN104079328A (zh) * 2014-06-19 2014-10-01 广州杰赛科技股份有限公司 Wlan天线组合方法和系统

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2000216619A (ja) * 1998-11-20 2000-08-04 Matsushita Electric Ind Co Ltd アダプティブアレ―アンテナ
CN101651982A (zh) * 2009-08-07 2010-02-17 重庆邮电大学 一种基于New-Memetic算法的波束成型方法
CN102316469A (zh) * 2010-06-30 2012-01-11 华为技术有限公司 配置天线参数的方法及系统
CN102625322A (zh) * 2012-02-27 2012-08-01 北京邮电大学 多制式智能可配的无线网络优化的实现方法
CN104079328A (zh) * 2014-06-19 2014-10-01 广州杰赛科技股份有限公司 Wlan天线组合方法和系统

Also Published As

Publication number Publication date
CN118160342A (zh) 2024-06-07

Similar Documents

Publication Publication Date Title
JP4946867B2 (ja) 無線ネットワーク設計装置および方法
CN111585816B (zh) 一种基于自适应遗传算法的任务卸载决策方法
CN109840154B (zh) 一种移动云环境下基于任务依赖的计算迁移方法
JP2009065394A (ja) センサネットワーク用減衰定数推定システム、ノード位置推定システム、推定方法、及びそのプログラム
Almutairi et al. Particle swarm optimization application for multiple attribute decision making in vertical handover in heterogenous wireless networks
CN109639833A (zh) 一种基于无线城域网微云负载均衡的任务调度方法
CN116089091A (zh) 基于物联网边缘计算的资源分配和任务卸载方法
Jayaprakasam et al. Genetic algorithm based weight optimization for minimizing sidelobes in distributed random array beamforming
Zimmermann et al. ENCON: an evolutionary algorithm for the antenna placement problem
CN110504555A (zh) 一种网络幅相可分解的赋形阵列天线设计方法
WO2023082288A1 (zh) 天线参数组合的确定方法及相关装置
Nguyen et al. Real-time optimized clustering and caching for 6G satellite-UAV-terrestrial networks
CN110071747A (zh) 一种大规模mimo系统上行链路低复杂度量化比特选择方法
CN108848519B (zh) 一种基于交叉熵学习的异构网络用户接入方法
Zhao et al. Joint content placement, RRH clustering and beamforming for cache-enabled cloud-RAN
CN114501480B (zh) 毫米波分布式网络中用户关联和波束成形联合多目标优化方法
WO2021057723A1 (zh) 波束配置方法、装置和存储介质
CN115361052A (zh) 一种兼顾能效和谱效的卫星波束成形方法及装置
Das et al. Optimization of antenna arrays for SLL reduction towards Pareto objectivity using GA variants
CN116546531B (zh) 一种双可重构智能表面辅助的无线传输能量效率优化方法
WO2024140507A1 (zh) 网络覆盖优化方法、电子设备、及存储介质
CN116702514B (zh) 基于近电场优化的天线阵列优化方法、装置、介质和设备
Liu et al. Pattern synthesis of sparse concentric circular array based on the niche genetic algorithm
CN110705680B (zh) 一种分布式阵列的子阵列位置优化方法及系统
Liu et al. An improved multi-objective artificial bee colony algorithm for pattern synthesis of conformal arrays

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21963734

Country of ref document: EP

Kind code of ref document: A1