5GtoB coverage optimization method, system and storage medium based on DOA

Abstract

The present invention discloses a 5GtoB coverage optimization method, system and storage medium based on DOA, which can be widely used in the field of Internet of Things technology. The present invention performs angle quantization within the coverage angle of a 5G base station, and obtains an angle quantization line after enhancing the angle edge, and then calculates the angle spectrum characteristics according to the angle quantization line and the observation value output by the array, and estimates the DOA of each angle quantization line in a serial manner according to the angle spectrum characteristics based on the context constraint of the MDP model, and then adjusts the beamforming according to the estimated DOA, so that the subsequent DOA detection in the quantization sequence can be based on the previous DOA value through the context constraint, speeding up the detection speed and accuracy, and timely and effectively reducing the angle deviation between the wave direction and the 5G base station coverage direction, thereby providing good network coverage for toB services.

Description

Technical Field

[0001] The present invention relates to the field of Internet of Things technology, and in particular to a 5GtoB coverage optimization method, system and storage medium based on DOA. Background Art

[0002] With the development of IoT services, some 5GtoC base stations have begun to carry the access of basic toB services. For example, chemical parks use base stations in non-explosion-proof areas to cover explosion-proof areas. Since the newly deployed IoT terminals often deviate from the toC user area, the working angle range of 5G base stations will be relatively wide. In order to ensure better coverage of edge services, 5G base stations need to adjust beamforming to direct the power of massive MIMO signals to dense areas. When a large number of terminals are relocated, new terminal clusters will appear. Therefore, there will be an angle deviation between the wave direction and the coverage direction of the 5G base station, which makes it impossible to provide good network coverage for toB services. Summary of the invention

[0003] The present invention aims to solve at least one of the technical problems existing in the prior art. To this end, the present invention proposes a 5GtoB coverage optimization method, system and storage medium based on DOA, which can provide good network coverage for toB services.

[0004] On the one hand, an embodiment of the present invention provides a 5GtoB coverage optimization method based on DOA, comprising the following steps:

[0005] Angle quantization is performed within the coverage angle of the 5G base station, and the angle edge is enhanced to obtain an angle quantization line;

[0006] Calculating angle spectrum characteristics according to the angle quantization line and the observation values ​​output by the array;

[0007] Based on the context constraint of the MDP model, the DOA of each of the angle quantization lines is estimated in a serial manner according to the angle spectrum features;

[0008] The beamforming is adjusted according to the estimated DOA.

[0009] In some embodiments, the performing angle quantization within the coverage angle of the 5G base station includes:

[0010] Taking the existing coverage direction of the 5G base station as the center line, angle quantification is performed within the entire coverage angle of the base station.

[0011] In some embodiments, the enhancing the angle edge comprises:

[0012] The coverage angle edge of the base station that covers both toB terminals and toC terminals is quantized in small steps.

[0013] In some embodiments, the step of calculating the angle spectrum feature based on the angle quantization line and the observation value output by the array includes:

[0014] Obtain observation values ​​of array output of 5G base station;

[0015] Projecting the observed value onto each of the angle quantization lines;

[0016] The angle spectrum features of each angle quantization line are calculated according to the projected observation values. The angle spectrum features include a quadratic space spectrum and a covariance spectrum. The quadratic space spectrum is used to characterize the angle orientation, and the covariance spectrum is used to characterize the signal correlation.

[0017] In some embodiments, the calculating the secondary spatial spectrum of each of the angle quantization lines according to the projected observation values ​​includes:

[0018] The secondary spatial spectrum of each of the angle quantization lines is calculated according to the projected observation value and the steering amount.

[0019] In some embodiments, the context constraint based on the MDP model, estimating the DOA of each of the angle quantization lines in a serial manner according to the angle spectrum features, includes:

[0020] The decoded DOA value and the angle spectrum feature are combined into an input vector for the next DOA estimation;

[0021] The input vectors of multiple angle quantization lines are decoded one by one to obtain DOA estimates of the directions of the angle quantization lines.

[0022] In some embodiments, adjusting beamforming according to the estimated DOA includes:

[0023] When the estimated DOA is a dense incoming wave, the beamforming is adjusted according to the angle deviation.

[0024] On the other hand, an embodiment of the present invention provides a 5GtoB coverage optimization system based on DOA, including:

[0025] The first module is used to perform angle quantization within the coverage angle of the 5G base station and enhance the angle edge to obtain an angle quantization line;

[0026] The second module is used to calculate the angle spectrum characteristics according to the angle quantization line and the observation value output by the array;

[0027] A third module is used to estimate the DOA of each of the angle quantization lines in a serial manner according to the angle spectrum features based on the context constraint of the MDP model;

[0028] The fourth module is used to adjust the beamforming according to the estimated DOA.

[0029] On the other hand, an embodiment of the present invention provides a 5GtoB coverage optimization system based on DOA, including:

[0030] at least one memory for storing a program;

[0031] At least one processor is used to load the program to execute the DOA-based 5GtoB coverage optimization method.

[0032] On the other hand, an embodiment of the present invention provides a storage medium, which stores a computer-executable program, and when the computer-executable program is executed by a processor, it is used to implement the DOA-based 5GtoB coverage optimization method.

[0033] The 5GtoB coverage optimization method based on DOA provided in an embodiment of the present invention has the following beneficial effects:

[0034] By performing angle quantization within the coverage angle of the 5G base station and enhancing the angle edge to obtain the angle quantization line, the angle spectrum characteristics are calculated based on the angle quantization line and the observation values ​​of the array output, and based on the context constraints of the MDP model, the DOA of each angle quantization line is estimated in a serial manner according to the angle spectrum characteristics, and then the beamforming is adjusted according to the estimated DOA. Through the context constraints, the subsequent DOA detection in the quantization sequence can be based on the previous DOA value, which speeds up the detection speed and accuracy, and timely and effectively reduces the angular deviation between the arrival direction and the 5G base station coverage direction, thereby providing good network coverage for toB services.

[0035] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The present invention will be further described below with reference to the accompanying drawings and embodiments, wherein:

[0037] Figure 1 This is a flowchart of a 5GtoB coverage optimization method based on DOA according to an embodiment of the present invention. DETAILED DESCRIPTION

[0038] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be understood as limiting the present invention.

[0039] In the description of the present invention, it should be understood that descriptions involving orientations, such as up, down, front, back, left, right, etc., and orientations or positional relationships indicated are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present invention.

[0040] In the description of the present invention, "several" means more than one, "many" means more than two, "greater than", "less than", "exceed", etc. are understood to exclude the number itself, and "above", "below", "within", etc. are understood to include the number itself. If there is a description of "first" or "second", it is only used for the purpose of distinguishing the technical features, and cannot be understood as indicating or implying the relative importance or implicitly indicating the number of the indicated technical features or implicitly indicating the order of the indicated technical features.

[0041] In the description of the present invention, unless otherwise clearly defined, terms such as setting, installing, connecting, etc. should be understood in a broad sense, and technicians in the relevant technical field can reasonably determine the specific meanings of the above terms in the present invention based on the specific content of the technical solution.

[0042] In the description of the present invention, the description with reference to the terms "one embodiment", "some embodiments", "illustrative embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0043] The terms used in the embodiments of the present application are explained as follows:

[0044] DOA: The full name of DOA is Direction Of Arrival, which is interpreted as direction of arrival estimation in Chinese. It is also called angle spectral estimation or angle of arrival estimation. A source has many possible propagation paths and angles of arrival. If several transmitters are working at the same time, each source forms a potential multipath component at the receiver. Therefore, it is very important for the receiving antenna to estimate these angles of arrival. The purpose is to estimate which transmitter is working and the direction of the transmitter. Simply put, it is to use the radar to receive the direction of the wave from the target transmitter for estimation. The principle of DOA positioning technology is to use the array antenna at the receiver and the direction of arrival (DOA) estimation technology to determine a direction of arrival line from the receiver to the source, which is the line of sight (LOB). Finally, the DOA estimated by multiple receivers is used for triangulation. The intersection of the direction lines is the estimated position of the source.

[0045] Massive MIMO: Large Scale MIMO in English and large-scale antenna technology in Chinese. It is a key technology for improving system capacity and spectrum utilization in the fifth generation of mobile communications (5G). It was first discovered that when the number of base station antennas in a cell tends to infinity, the negative effects of additive Gaussian white noise and Rayleigh fading can all be ignored, and the data transmission rate can be greatly improved.

[0046] toC and toB: For toB, its customers include various enterprises and organizations; for toC, it faces users, including the general public or consumers. For ToB products, it is to solve the needs of enterprises, such as customizing OA systems, ERP systems, CRM systems, medical systems, etc. for enterprises. ToB products are more complex and have little relevance to daily life. For ToC products, it is to solve individual needs. Common product forms are APPs, mini-programs, etc., such as shopping APPs, social APPs, game APPs, etc.

[0047] MDP: Markov Decision Process in English and Markov Decision Process in Chinese. It is a mathematical model of sequential decision making, which is used to simulate the stochastic strategies and rewards that can be achieved by intelligent agents in an environment where the system state has Markov properties.

[0048] During the application process, unlike the existing DOA detection for medium and long-distance edge coverage enhancement, the embodiment of the present application performs DOA detection to achieve coverage enhancement at the angle edge. First, the edge angle is quantized in small steps, and the angle spectrum characteristics are calculated to identify the incoming signal, so that the 5G base station can simultaneously provide better signal coverage for toB services and toC services distributed at different locations, realize network following terminal movement, and meet the coverage quality requirements of widening the wave angle.

[0049] In view of the fact that IoT terminals are often densely deployed, the incoming signals of densely packed terminals can be regarded as multi-source coherent signals. Different from the parallel DOA incoming direction detection of existing multi-source coherent signals, the embodiment of the present application utilizes the correlation characteristics of multi-source coherent signals and uses the context model MDP to convert it into a series DOA incoming direction detection.

[0050] Reference Figure 1 The embodiment of the present invention provides a 5GtoB coverage optimization method based on DOA. The method of this embodiment can be applied to edge servers or cloud servers. During the application process, the method of this embodiment includes but is not limited to the following steps:

[0051] Step S110: perform angle quantization within the coverage angle of the 5G base station, and enhance the angle edge to obtain an angle quantization line;

[0052] In the embodiment of the present application, when performing angle quantization within the coverage angle of the 5G base station, the existing coverage direction of the 5G base station can be used as the center line to perform angle quantization within the entire coverage angle of the base station, thereby forming an angle sequence. When enhancing the angle edge, the coverage angle edge of the base station that covers both the toB terminal and the toC terminal is quantized in small steps to improve the detection accuracy.

[0053] Step S120, calculating the angle spectrum characteristics according to the angle quantization line and the observation value output by the array;

[0054] In an embodiment of the present application, the array output of the 5G base station can be observed to obtain the observation value. The observation value is then projected on each angle quantization line; and the angle spectrum characteristics of each angle quantization line are calculated based on the projected observation value. It can be understood that the angle spectrum characteristics include a secondary spatial spectrum and a covariance spectrum, the secondary spatial spectrum is used to characterize the angle orientation, and the covariance spectrum is used to characterize the signal correlation. Among them, the secondary spatial spectrum can be calculated by the observation value after projection and the guidance amount, that is, the secondary spatial spectrum = the observation value after projection * the guidance amount.

[0055] Step S130, estimating the DOA of each angle quantization line in a serial manner according to the angle spectrum features based on the context constraint of the MDP model;

[0056] In an embodiment of the present application, the decoded DOA value and the angle spectrum feature can be combined into an input vector for the next DOA estimation; the input vectors of multiple angle quantization lines are decoded one by one to obtain DOA estimates in the directions of each angle quantization line. It can be understood that this embodiment uses the decoded DOA value and the observed spectral feature to combine into a new input vector to form an input vector on the kth quantization line to estimate the DOA on the kth quantization line. In this embodiment, when the observed spectral feature is the kth observed spectral feature, the decoded DOA value is the DOA estimate on the k-1th quantization line. After obtaining the input vector, the DOA estimates in the directions of each quantization line are obtained by decoding multiple quantization lines one by one.

[0057] In this embodiment, when the MDP model is in a certain state, the DOA agent will make decisions to perform corresponding actions according to changes in the signal environment. When the DOA agent performs an action, its state changes, and it transfers to a new state after performing the action.

[0058] When executing the previous DOA action a j After that, the system status changes from s j →s j+1 , that is, state s j :

[0059] (μ,A 1:j-1 )|A 1:j-1 =[a1,a2,L,a j-1 ]

[0060] Transition to next DOA state s j+1 :

[0061] (μ,A 1:j )|A 1:j =[a1,a2,L,a j ]

[0062] The state transition of the system describes the effect of the action in the sequential decision-making process. After L-1 DOA action decisions and L-1 state transitions, the system completes a serialized attempt and obtains the long-term reward of the MDP. Using the current strategy to collect multiple samples, multiple serialized attempts can be completed, and the DOA agent learns the policy gradient corresponding to the maximum expected reward of the MDP. After multiple iterations of training, the neural network converges to the optimal parameters, thereby providing the best strategy for the entire DOA prediction process.

[0063] Due to the constraints between the front and rear quantization directions, DOA estimation is easy to converge, the calculation speed is faster, and the beamforming accuracy is improved.

[0064] Step S140, adjusting beamforming according to the estimated DOA. Specifically, when the estimated DOA is a dense incoming wave, the beamforming is adjusted according to the angle deviation. It can be understood that beamforming, also known as beamforming and spatial filtering, is a signal processing technology that uses a sensor array to send and receive signals in a directional manner.

[0065] Therefore, the overall implementation process of the method of the embodiment of the present application is as follows:

[0066] Step 1: quantize the angle edge of the widening in small steps. That is, quantize the angle edge of the widening of the base station that covers both toB and toC terminals in small steps. After exceeding the threshold, the quantization step can be fixedly halved or linearly adjusted.

[0067] Step 2: Observe the output angle spectrum features. Specifically, observe the output of the base station array, project the power of the steering vector to the direction of the quantization sequence to obtain the secondary space angle spectrum features and the covariance matrix spectrum features. Combine the secondary space angle spectrum features and the covariance matrix spectrum features into an observation vector and input it into the module for estimating DOA.

[0068] Step 3: New input is formed in state transfer. Specifically, for multi-source coherent signals, the DOA estimation values ​​of each quantization direction will form a context relationship, and the estimated DOA values ​​in the sequence and the observation vector are combined to form a new vector as the input of the next DOA estimation in the sequence.

[0069] Step 4: Serialize and estimate DOA and adjust beamforming. Specifically, the DOA of each quantization direction is estimated one by one in a serialized manner. Due to the constraints between the previous and next quantization directions, it is easy to converge when estimating DOA, the calculation speed is faster, and the beamforming accuracy is improved.

[0070] In summary, due to the characteristics of dense terminals, the embodiment of the present application adopts context constraints, so that the subsequent DOA detection in the quantization sequence can be based on the previous DOA value, thereby greatly accelerating the detection speed and accuracy. In addition, according to the characteristics of angle deviation, the angle spectrum feature is used for DOA identification, which is more stable than the spatial feature facing distance deviation.

[0071] The embodiment of the present invention provides a 5GtoB coverage optimization system based on DOA, including:

[0072] The first module is used to perform angle quantization within the coverage angle of the 5G base station and enhance the angle edge to obtain an angle quantization line;

[0073] The second module is used to calculate the angle spectrum characteristics according to the angle quantization line and the observation value output by the array;

[0074] The third module is used to estimate the DOA of each angle quantization line in a serial manner according to the angle spectrum features based on the context constraints of the MDP model;

[0075] The fourth module is used to adjust the beamforming according to the estimated DOA.

[0076] The contents of the method embodiments of the present invention are all applicable to the system embodiments. The functions specifically implemented by the system embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method.

[0077] The embodiment of the present invention provides a 5GtoB coverage optimization system based on DOA, including:

[0078] at least one memory for storing a program;

[0079] At least one processor for loading the program to execute Figure 1 The DOA-based 5GtoB coverage optimization method is shown.

[0080] The contents of the method embodiments of the present invention are all applicable to the system embodiments. The functions specifically implemented by the system embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method.

[0081] An embodiment of the present invention provides a storage medium, wherein a computer executable program is stored, and when the computer executable program is executed by a processor, it is used to implement Figure 1 The DOA-based 5GtoB coverage optimization method is shown.

[0082] The contents of the method embodiments of the present invention are all applicable to the storage medium embodiments. The functions specifically implemented by the storage medium embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0083] In addition, an embodiment of the present invention further provides a computer program product or a computer program, wherein the computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. A processor of a computer device can read the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes Figure 1 The DOA-based 5GtoB coverage optimization method is shown.

[0084] The embodiments of the present invention are described in detail above in conjunction with the accompanying drawings, but the present invention is not limited to the above embodiments. Various changes can be made within the knowledge of ordinary technicians in the relevant technical field without departing from the purpose of the present invention. In addition, the embodiments of the present invention and the features in the embodiments can be combined with each other without conflict.

Claims

1. A 5GtoB coverage optimization method based on DOA, characterized in that: The following steps are involved: Angle quantization is performed within the coverage angle of the 5G base station, and the angle edge is enhanced to obtain an angle quantization line; Calculating angle spectrum characteristics according to the angle quantization line and the observation values ​​output by the array; Based on the context constraint of the MDP model, the DOA of each of the angle quantization lines is estimated in a serial manner according to the angle spectrum features; Adjust beamforming according to the estimated DOA; Wherein, the enhancing of the angle edge comprises: Quantize the coverage angle edge of the base station that covers both toB terminals and toC terminals with a small step size; The step of calculating the angle spectrum feature according to the angle quantization line and the observation value output by the array includes: Obtain observation values ​​of array output of 5G base station; Projecting the observed value onto each of the angle quantization lines; Calculate the angle spectrum features of each angle quantization line according to the projected observation value, wherein the angle spectrum features include a quadratic space spectrum and a covariance spectrum, wherein the quadratic space spectrum is used to characterize the angle orientation, and the covariance spectrum is used to characterize the signal correlation; The context constraint based on the MDP model estimates the DOA of each of the angle quantization lines in a serial manner according to the angle spectrum feature, including: The decoded DOA value and the angle spectrum feature are combined into an input vector for the next DOA estimation; The input vectors of multiple angle quantization lines are decoded one by one to obtain DOA estimates of the directions of the angle quantization lines.

2. According to a DOA-based 5GtoB coverage optimization method according to claim 1, it is characterized in that: The performing angle quantization within the coverage angle of the 5G base station includes: Taking the existing coverage direction of the 5G base station as the center line, angle quantification is performed within the entire coverage angle of the base station.

3. According to a DOA-based 5GtoB coverage optimization method according to claim 1, it is characterized in that: The calculating the secondary spatial spectrum of each of the angle quantization lines according to the projected observation values ​​comprises: The secondary spatial spectrum of each of the angle quantization lines is calculated according to the projected observation value and the steering amount.

4. According to a DOA-based 5GtoB coverage optimization method according to claim 1, it is characterized in that: The step of adjusting beamforming according to the estimated DOA includes: When the estimated DOA is a dense incoming wave, the beamforming is adjusted according to the angle deviation.

5. A 5GtoB coverage optimization system based on DOA, characterized in that: include: The first module is used to perform angle quantization within the coverage angle of the 5G base station and enhance the angle edge to obtain an angle quantization line; The second module is used to calculate the angle spectrum characteristics according to the angle quantization line and the observation value output by the array; A third module is used to estimate the DOA of each of the angle quantization lines in a serial manner according to the angle spectrum features based on the context constraint of the MDP model; A fourth module is used to adjust beamforming according to the estimated DOA; Wherein, the enhancing of the angle edge comprises: Quantize the coverage angle edge of the base station that covers both toB terminals and toC terminals with a small step size; The step of calculating the angle spectrum feature according to the angle quantization line and the observation value output by the array includes: Obtain observation values ​​of array output of 5G base station; Projecting the observed value onto each of the angle quantization lines; Calculate the angle spectrum features of each angle quantization line according to the projected observation value, wherein the angle spectrum features include a quadratic space spectrum and a covariance spectrum, wherein the quadratic space spectrum is used to characterize the angle orientation, and the covariance spectrum is used to characterize the signal correlation; The context constraint based on the MDP model estimates the DOA of each of the angle quantization lines in a serial manner according to the angle spectrum feature, including: The decoded DOA value and the angle spectrum feature are combined into an input vector for the next DOA estimation; The input vectors of multiple angle quantization lines are decoded one by one to obtain DOA estimates of the directions of the angle quantization lines.

6. A 5GtoB coverage optimization system based on DOA, characterized in that: include: at least one memory for storing a program; At least one processor is used to load the program to execute the DOA-based 5GtoB coverage optimization method as described in any one of claims 1-4.

7. A storage medium, characterized in that: A computer-executable program is stored therein, and when the computer-executable program is executed by a processor, it is used to implement the DOA-based 5GtoB coverage optimization method as described in any one of claims 1-4.

Images