CN113973339B - Load coordination method and device for 4G cell and 5G cell and computer storage medium - Google Patents
Load coordination method and device for 4G cell and 5G cell and computer storage medium Download PDFInfo
- Publication number
- CN113973339B CN113973339B CN202010663779.0A CN202010663779A CN113973339B CN 113973339 B CN113973339 B CN 113973339B CN 202010663779 A CN202010663779 A CN 202010663779A CN 113973339 B CN113973339 B CN 113973339B
- Authority
- CN
- China
- Prior art keywords
- cell
- load
- threshold
- index
- daily
- Prior art date
- Legal status (The legal status 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 status listed.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W28/00—Network traffic management; Network resource management
- H04W28/02—Traffic management, e.g. flow control or congestion control
- H04W28/08—Load balancing or load distribution
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/147—Network analysis or design for predicting network behaviour
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/06—Testing, supervising or monitoring using simulated traffic
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W28/00—Network traffic management; Network resource management
- H04W28/16—Central resource management; Negotiation of resources or communication parameters, e.g. negotiating bandwidth or QoS [Quality of Service]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Abstract
The invention discloses a load coordination method, equipment and computer storage medium for a 4G cell and a 5G cell, wherein the method comprises the following steps: for each cell, predicting the wireless utilization rate of the cell in a plurality of preset time periods by using a prediction model selected for the cell to obtain a plurality of groups of wireless utilization rates corresponding to a plurality of cells; judging whether any one same coverage group simultaneously comprises a 4G cell and a 5G cell, if so, detecting whether at least one load imbalance between the 5G cell and the 4G cell exists in the same coverage group according to the multiple groups of wireless utilization rates; if the network parameters exist, generating a load cooperation task according to the imbalance type and the imbalance time interval of the at least one 5G cell and the 4G cell, and adjusting the network parameters of the at least one 5G cell according to the load cooperation task. Therefore, the scheme of the invention can realize the load coordination of the 4G cell and the 5G cell under the condition that the 4G network and the 5G network coexist, so as to improve the utilization efficiency of resources and avoid resource waste.
Description
Technical Field
The invention relates to the technical field of wireless, in particular to a load coordination method, equipment and a computer storage medium for a 4G cell and a 5G cell.
Background
In recent years, as the construction of 5G is gradually increased, the scale of 5G terminals in a wireless communication network is increasing, and the number of users and the load of the 5G network are steadily increasing. The 5G network is used as the most prior network where the 5G user resides, and can bring the best user experience to the user; the 4G network is used as a main network at present and in a future period of time, and can provide good use perception for users under the condition of normal load and the like.
Under the condition that the current 4G network and the 5G network coexist, due to reasons such as insufficient density of local area 5G sites, the 5G site load may be too high, and similarly, due to parameter setting reasons, the 5G user may not occupy the 5G cell, and the 5G site is idle, and both of the two conditions may seriously affect the use experience of the 5G user. In this case, how to reasonably perform load coordination of the 4G cell and the 5G cell to improve the perception experience of the 4/5G user is an important issue for a long period of time in the future.
In the prior art, the loads of the 4G cell and the 5G cell are adjusted cooperatively mainly in a manual manner, and an operator manually analyzes the load conditions of the 4G cell and the 5G cell for a period of time and formulates a load balancing scheme according to experience.
However, the inventor finds that the prior art cooperative adjustment method has at least the following technical problems in the process of implementing the embodiment of the present invention: first, the existing means do not predict and judge the conditions of future 4G and 5G loads, but adjust based on the past, and have certain hysteresis; secondly, the frequency of load balancing in the prior art is insufficient, and the load of the network is continuously changed, so that the prior art cannot adapt to the change, and continuous load coordination cannot be performed.
Disclosure of Invention
In view of the above problems, embodiments of the present invention are proposed to provide a load coordination method, apparatus, and computer-storage medium for 4G cells and 5G cells that overcome or at least partially solve the above problems.
According to an aspect of the embodiments of the present invention, there is provided a load coordination method for a 4G cell and a 5G cell, including:
for each cell, predicting the wireless utilization rate of the cell in a plurality of preset time periods by using a prediction model selected for the cell to obtain a plurality of groups of wireless utilization rates corresponding to a plurality of cells;
judging whether any one same coverage group simultaneously comprises a 4G cell and a 5G cell, if so, detecting whether at least one load imbalance between the 5G cell and the 4G cell exists in the same coverage group according to the multiple groups of wireless utilization rates;
if the load of at least one 5G cell and 4G cell is unbalanced, generating a load cooperative task according to the type of the unbalance of the at least one 5G cell and the 4G cell and the unbalanced time interval, and adjusting the network parameters of the at least one 5G cell according to the load cooperative task.
According to another aspect of the embodiments of the present invention, there is provided a load coordination apparatus for a 4G cell and a 5G cell, including:
the prediction module is suitable for predicting the wireless utilization rate of each cell in a plurality of preset time periods by using the prediction model selected for the cell to obtain a plurality of groups of wireless utilization rates corresponding to the cells;
the judging module is suitable for judging whether any one same covering group simultaneously comprises a 4G cell and a 5G cell;
the detection module is suitable for detecting whether load imbalance exists between at least one 5G cell and a 4G cell in the same coverage group according to the multiple groups of wireless utilization rates if the same coverage group simultaneously comprises the 4G cell and the 5G cell;
the generation module is suitable for generating a load coordination task according to the unbalance type and the unbalance time period of at least one 5G cell and 4G cell if the load of the at least one 5G cell and the 4G cell is unbalanced;
and the adjusting module is suitable for adjusting the network parameters of the at least one 5G cell according to the load coordination task.
According to still another aspect of an embodiment of the present invention, there is provided a computing device including: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;
the memory is used for storing at least one executable instruction, and the executable instruction enables the processor to execute the operation corresponding to the load coordination method of the 4G cell and the 5G cell.
According to still another aspect of the embodiments of the present invention, a computer storage medium is provided, where at least one executable instruction is stored, and the executable instruction causes a processor to perform an operation corresponding to the load coordination method for the 4G cell and the 5G cell.
According to the load coordination method, the equipment and the computer storage medium of the 4G cell and the 5G cell, the wireless utilization rate of the cell in the future time period is predicted by using the correspondingly selected prediction model, so that the prediction accuracy is improved while the prediction of the cell load in the future time period is realized; and then, judging whether a 4G cell and a 5G cell exist in the same coverage group at the same time or not, further judging whether at least one load imbalance of the 5G cell and the 4G cell exists in the same coverage group or not when the judgment result is yes, and if so, adjusting network parameters of the 5G cell according to the type of the imbalance so as to realize load balancing of the 4G network and the 5G network in the same coverage group according to the prediction result. Therefore, the scheme of the invention can accurately predict the load conditions of the future 4G cell and the future 5G cell in time without hysteresis, can continuously predict continuous balance and realize continuous load balance; moreover, load balancing can be performed on the same coverage group with the 4G cell and the 5G cell existing at the same time and load imbalance between the 5G cell and the 4G cell, so that the pertinence of the load balancing is improved, and the balancing efficiency is further improved.
The foregoing description is only an overview of the technical solutions of the embodiments of the present invention, and the embodiments of the present invention can be implemented according to the content of the description in order to make the technical means of the embodiments of the present invention more clearly understood, and the detailed description of the embodiments of the present invention is provided below in order to make the foregoing and other objects, features, and advantages of the embodiments of the present invention more clearly understandable.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the embodiments of the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
fig. 1 shows a flowchart of a load coordination method for a 4G cell and a 5G cell according to an embodiment of the present invention;
fig. 2 is a flowchart illustrating a load coordination method for a 4G cell and a 5G cell according to another embodiment of the present invention;
fig. 3 is a schematic structural diagram of a load coordination apparatus for a 4G cell and a 5G cell according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a computing device provided in an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
Fig. 1 shows a flowchart of a load coordination method for a 4G cell and a 5G cell according to an embodiment of the present invention. The method is applied to the condition that a 4G network and a 5G network coexist to realize the load balance of the 4G cell and the 5G cell, and can be executed by any computing equipment with data processing capacity. As shown in fig. 1, the method comprises the steps of:
step S110: and aiming at each cell, predicting the wireless utilization rate of the cell in a plurality of preset time periods by using the prediction model selected for the cell to obtain a plurality of groups of wireless utilization rates corresponding to a plurality of cells.
Wherein, the cell is a 4G cell or a 5G cell.
In this embodiment, different prediction models are selected for cells with different wireless utilization rate variation degrees, so as to take modeling efficiency and prediction accuracy into consideration. The core of the selection is as follows: the method has the advantages that the stable model is used for predicting the cell with small business load fluctuation, so that the prediction accuracy is guaranteed, and the efficiency is greatly improved; for a cell with large fluctuation degree, a prophet time series model is utilized, so that the prediction accuracy can be improved on the basis of meeting the prediction efficiency; and modeling is carried out on a cell with large partial fluctuation degree by utilizing an LSTM long-term and short-term memory network model, so that the prediction accuracy is improved.
Specifically, for different cells, the wireless utilization rate of the cell in a plurality of future preset time periods can be predicted by inputting the wireless utilization rate data of the current day into the selected prediction model, so that the accurate prediction of the future wireless utilization rate can be realized. For example, the radio utilization rates for 24 hours today are input into the prediction model, and the radio utilization rates for 24 hours tomorrow are output, i.e., a set of radio utilization rates is obtained.
Step S120: judging whether any same covering group simultaneously comprises a 4G cell and a 5G cell; if yes, go to step S130; if not, go to step S150.
The same coverage group refers to a cell group formed by 4G cells and/or 5G cells, and load balancing can be performed between cells in the cell group. It should be noted that, in this embodiment, a specific manner of identifying the same coverage group is not limited, and all manners that can be used for performing cell set division on the 4G cell and/or the 5G cell are included in the scope protected by this embodiment, for example, identification division is performed by using a distance, an azimuth, and the like.
In the present invention, if load balancing needs to be performed between a 4G cell and a 5G cell, it is necessary to ensure that one same coverage group has both the 4G cell and the 5G cell, in a specific implementation, for any one same coverage group, a step of determining whether both the 4G cell and the 5G cell exist and subsequent steps thereof need to be performed, and if so, there is a possibility of performing load balancing between the 4G cell and the 5G cell, at this time, step S130 is performed to perform relevant processing of balancing; if not, then there is no need for load balancing between the 4G cell and the 5G cell, and then step S150 is performed for the same coverage group.
Step S130: detecting whether at least one load imbalance between the 5G cell and the 4G cell exists in the same coverage group according to the multiple groups of wireless utilization rates; if yes, go to step S140; if not, go to step S150.
The load condition of each cell in each preset time period can be reflected by one group of wireless utilization rate of each cell, and correspondingly, the load difference of multiple cells in each preset time period can be reflected by multiple groups of wireless utilization rates of multiple cells.
It should be noted that, in the present invention, it is only necessary to determine whether there is a load imbalance between each 5G cell in the same coverage group and the 4G cell in the same coverage group when there is a load imbalance between each 5G cell in the same coverage group and the 4G cell in the same coverage group. For example, if two 5G cells, cell-a and cell-B, exist in a same coverage group, it needs to determine whether the loads of cell-a and cell-B and 4G cells are balanced.
And if there is a load imbalance and there is a demand for load balancing, executing step S140 to perform balancing processing for at least one 5G cell that is not balanced with the 4G cell; otherwise, if there is no load imbalance, it indicates that there is no load balancing requirement for the same coverage group, and then step S150 is executed.
Step S140: and generating a load coordination task according to the unbalance type and the unbalance time period of the at least one 5G cell and the 4G cell, and adjusting the network parameters of the at least one 5G cell according to the load coordination task.
The balance mainly aims at 5G users, and meanwhile, in order to avoid confusion of 4G and 5G interoperation parameter setting caused by excessive adjustment of load balance, 5G network parameters are adjusted to expand or contract a coverage area, 5G users are absorbed or released, and 4G and 5G network loads are balanced.
Specifically, when the adjustment is performed, different adjustment strategies are adopted in the imbalance time period for different imbalance types, so as to achieve load balancing of the 4G cell and the 5G cell in the same coverage group. The unbalance types mainly include the following two types: firstly, the load of a 5G cell is higher than a 5G high load threshold, and the load of a 4G cell is lower than a 4G low load threshold; second, the load of the 5G cell is below the 5G low load threshold, while the load of the 4G cell is above the 4G high load threshold.
Step S150: no load cooperative task is generated.
According to the load coordination method of the 4G cell and the 5G cell provided by the embodiment, the wireless utilization rate of the cell in the future time period is predicted by using the correspondingly selected prediction model, so that the prediction accuracy is improved while the prediction of the cell load in the future time period is realized; and then, judging whether a 4G cell and a 5G cell exist in the same coverage group at the same time or not, further judging whether the load of at least one 5G cell and the load of the 4G cell are unbalanced or not in the same coverage group when the judgment result is yes, and adjusting the network parameters of the 5G cell according to the type of the unbalance if the load of the 5G cell and the load of the 4G network and the 5G network in the same coverage group are unbalanced so as to realize load balancing of the 4G network and the 5G network in the same coverage group according to the prediction result. Therefore, the scheme of the embodiment can accurately predict the load conditions of the future 4G cell and the future 5G cell in time, has no lag, can continuously predict continuous balance and realizes continuous load balance; moreover, load balancing can be performed on the same coverage group with the 4G cell and the 5G cell existing at the same time and load imbalance between the 5G cell and the 4G cell, so that the pertinence of the load balancing is improved, and the balancing efficiency is further improved.
Fig. 2 is a flowchart illustrating a load coordination method for a 4G cell and a 5G cell according to another embodiment of the present invention. In the present embodiment, the 24 time slots corresponding to 24 hours of a day are mainly described, but the implementation is not limited to this, and for example, the preset time slots may be divided in units of 2 hours or 30 minutes. As shown in fig. 2, the method comprises the steps of:
step S210: and performing same-coverage identification on the 4G cell and the 5G cell.
The identification of 4G and 5G networks with coverage groups consists in forming groups of cells with load coordination between 4G and 5G cells.
In this embodiment, the same coverage identification is performed on the 4G network to obtain the same coverage group, i.e., the 4G multi-layer network, and then a layer of 5G network is added on the basis, so as to form the final same coverage group. The specific identification process is as follows:
firstly, the same coverage judgment is carried out on the 4G cells by utilizing the working parameters to form a plurality of same coverage groups. Wherein, the same coverage cell is judged when the following conditions are met: the inter-frequency macro station distance is less than 50 meters, the deviation of the azimuth angle of the cell is less than 15 degrees, a first cell is selected clockwise from the azimuth angle of 0 degree, the first cell is taken as a reference cell, and if the difference between the azimuth angle and the cell is within 15 degrees, the first cell and the other cells are brought into a first same-coverage sector; and then, selecting a second cell clockwise, if the cell has the same coverage sector before, not considering the second cell, otherwise, taking the second cell as a second reference cell, and judging whether other cells have the same coverage with the reference cell. Through the above manner, a plurality of mutually exclusive 4G cell sets Gi are formed, that is, a plurality of same coverage groups are formed, each set has at least 1 4G cell according to a rule, only the cell in the set of 1 cell is called a single-layer network cell, and more than 1 cell is a multi-layer network cell.
Then, aiming at any 5G cell, determining a target same-coverage group to which the 5G cell belongs according to the azimuth angle difference and/or the distance between the 5G cell and a 4G cell contained in each same-coverage group; adding the 5G cell to the target co-coverage group. And utilizing the 5G cells to match the same coverage group, and dividing each 5G cell into the identified same coverage group, so that the cells capable of performing load coordination are positioned in the same coverage group for subsequent adjustment.
Further, when matching the same coverage group to which the 5G cell belongs, if Max (F1, F2, … Fn) < F0 and Max (D1, D2, … Dn) < D0 are satisfied for the current same coverage group, determining that the current same coverage group is the target same coverage group; wherein n is the number of 4G cells included in the current same coverage group, fi is the difference of azimuth angles of each 4G cell and the 5G cell in the current same coverage group, F0 is a difference threshold, di is the distance between each 4G cell and the 5G cell in the current same coverage group, and D0 is a distance threshold. In other words, for any 5G cell, when the maximum value of the difference between the azimuth angles of each 4G cell in the current same coverage group and the 5G cell is smaller than the difference threshold, for example, smaller than 15 degrees, and the maximum value of the distances between each 4G cell in the current same coverage group and the 5G cell is smaller than the distance threshold, for example, smaller than 50 meters, the 5G cell can be classified into the current same coverage group. When a plurality of target same-coverage groups are identified for the same 5G cell, that is, when the plurality of same-coverage groups satisfy the above condition, the number of 4G cells included in the plurality of target same-coverage groups is compared, and the 5G cell is divided into the target same-coverage group having the largest number of included 4G cells according to the comparison result, and further, when there are a plurality of target same-coverage groups having the largest number of included 4G cells, the 5G cell is divided into the group having the smallest mean (D1, D2, … Dn), that is, the target same-coverage group having the smallest distance average. By the method, the 5G cells can be accurately divided into the same coverage groups capable of carrying out load balancing, and the division into the unique same coverage groups can be ensured.
Step S220: determining attribute information of a date to be predicted, wherein the attribute information comprises a jump date attribute and a daily date attribute; a prediction model is selected for each cell based on the attribute information.
When the prediction model is selected, the selection is performed according to the traffic load fluctuation degree of the cell as a whole, but in practice, the selection is further performed by further combining the attribute information of the date to be predicted so as to further improve the accuracy of the prediction.
Specifically, the attribute information of the date to be predicted is determined according to whether the date to be predicted and the current day are switched between a working day and a holiday, if the date to be predicted and the current day are not switched between the working day and the holiday, namely both the current day and the date to be predicted are working days or both holidays, the attribute information of the date to be predicted is determined to be the daily date, and if the date to be predicted and the holiday are switched between the working day and the holiday, namely one of the current day and the date to be predicted is the working day and the other is the holiday, the attribute information of the date to be predicted is determined to be the jump date.
Further, when the attribute information of the date to be predicted and the fluctuation degree of the cell service load are considered comprehensively to select the prediction model, the specific selection process is as follows: and if the attribute is the jumping date attribute, selecting a prediction model for the cell according to the jumping stationarity index and the daily stationarity index of the cell, and if the attribute is the daily date attribute, selecting the prediction model for the cell according to the daily stationarity index of the cell.
The jumping stationarity index may reflect a fluctuation degree of a cell service load on a jumping date, and specifically refers to a ratio of a preset time period in which an absolute value of a wireless utilization rate difference is less than or equal to a first preset difference value (value J) to a total preset time period number in J calculation days in load prediction on J calculation days corresponding to the latest J jumping dates.
For example, 20200410 (friday) and 20200411 (saturday) are jump dates and are 1 calculation day, the number of hours of wireless utilization rate 20200410 i-wireless utilization rate 20200411i | is less than or equal to value J is counted, i is 0-23 taken as 24 hours of a day, corresponding to 24 preset time periods, value J is a first preset difference value, the number of hours of hour-level wireless utilization rate difference in other J-1 jump days is calculated according to the method, and the total number of hours of hour-level wireless utilization rate difference in the middle-hour-level calculation days is less than or equal to value J is divided by (J24), so that the jump smoothness index can be obtained.
And the daily stationarity index may reflect a fluctuation degree of a cell service load on a daily date, and specifically refers to a ratio of a preset time period in which an absolute value of a wireless utilization rate difference is less than or equal to a second preset difference value (value R) to a total preset time period number in R calculation days in load prediction on R calculation days corresponding to the latest R daily dates. In addition, the second predetermined difference may be the same as or different from the first predetermined difference, and if different, the first predetermined difference is usually greater than the second predetermined difference to allow for greater load fluctuations during the jump date; and R and L can be flexibly selected according to actual requirements, for example, if the prediction model is required to meet the requirement of timeliness, smaller R and L are set, and if the requirement on the accuracy of the prediction model is higher, larger R and L are set.
Further, if the attribute information of the date to be predicted is a jump date attribute, selecting a prediction model for the cell according to the jump stationarity index and the daily stationarity index of the cell specifically includes: if the jumping stationarity index is higher than a first high index threshold (high _ J, the same below), and the daily stationarity index is higher than a second high index threshold (high _ R, the same below), selecting a stationarity model, namely determining that the load fluctuation degree is small when the occupation ratios of the preset time periods with small absolute values of wireless utilization differences are high, and selecting the stationarity model at the moment; if the jumping stationarity index is lower than a first low index threshold (low _ J, the same below), or the daily stationarity index is lower than a second low index threshold (low _ R, the same below), selecting an LSTM model, namely when the occupation ratio of one of the low index indexes is lower, determining that the load fluctuation degree is large, and selecting the LSTM model at the moment; in addition, for other cases where the above two possibilities are not met, it is determined that the degree of load fluctuation is large, and the prophet model is selected at this time. By the mode, the jumping stationarity index is further considered on the basis of considering the daily stationarity index aiming at the jumping date, and unreasonable model selection caused by neglecting special fluctuation of the jumping date is avoided.
And if the attribute information of the date to be predicted is a daily date attribute, selecting a prediction model for the cell according to the daily stationarity index of the cell specifically comprises the following steps: if the daily stationarity index is higher than a second high index threshold, selecting a stable model; if the daily stationarity index is higher than a second low index threshold and lower than or equal to a second high index threshold, selecting a prophet model; and if the daily stationarity index is lower than a second low index threshold, selecting an LSTM model. By the method, a reasonable prediction model can be selected according to daily dates based on consideration of daily fluctuation.
It should be noted that, the first high indicator threshold (high _ J), the second high indicator threshold (high _ R), the first low indicator threshold (low _ J), and the second low indicator threshold (low _ R) may be set according to experience values corresponding to the fluctuation degrees reflected by the big data, and the specific values are not limited in the present invention.
Step S230: and aiming at each cell, predicting the wireless utilization rate of the cell in a plurality of preset time periods by using the prediction model selected for the cell to obtain a plurality of groups of wireless utilization rates corresponding to a plurality of cells.
For each cell, the selected prediction model may be a stationary model, a prophet model or an LSTM model, and the prediction process of different models is different when performing prediction.
(1) A stable model: the load condition of the cell conforming to the stationary model in the future day is extremely similar to that of the cell in the previous day, so that the system directly outputs the wireless utilization rate of the corresponding time period in the previous day as the wireless utilization rate of the corresponding preset time period in the next day. For example, the radio utilization rates for 24 hours on 6 days 7/6 in 2020 are output as predicted radio utilization rates for 24 hours in 6 days 0 to 23 on 7/6 in 2020.
(2) prophet model: the model is realized by python, modeling is carried out on each cell which accords with the prophet model, and 1 cell corresponds to 1 prophet time series model. The prediction by day is realized by extracting the radio utilization rate of the hour granularity of the historical time period before the date to be predicted of the cell as training data, for example, extracting the data of the previous 1 month as training data, and setting model parameters, including setting yearly _ search availability, weekly _ search availability as False and setting date _ search availability as True.
(3) LSTM model: the system realizes LSTM by utilizing a Keras deep learning framework of python language, and 1 cell corresponds to 1 LSTM model. The method comprises the following steps of extracting the wireless utilization rate of the hour granularity of the historical time period before the date to be predicted of a cell to serve as training data, setting model parameters, wherein the model parameters comprise a visible input layer, a hidden layer comprises 4 LSTM modules (neurons), and an output layer, and the set codes are as follows:
model＝Sequential()
model.add(LSTM(4,input_shape＝(1,look_back)))
model.add(Dense(1))
model.compile(loss＝'mean_squared_error',optimizer＝'adam')。
in the practical implementation process, the future hour granularity load condition of each cell can be predicted in a daily period of 01-02.
Step S240: judging whether any same covering group simultaneously comprises a 4G cell and a 5G cell; if yes, go to step S250; if not, go to step S270.
Since load coordination should occur between cells "covering the same", the load coordination of the 4G cell and the 5G cell is performed within the identified same coverage group. For the same coverage group with only 4G or only 5G cells, the objective requirement of 4G and 5G load cooperation is not met, and the cooperative task is not generated.
Step S250: detecting whether at least one load imbalance between the 5G cell and the 4G cell exists in the same coverage group according to the multiple groups of wireless utilization rates; if yes, go to step S260; if not, go to step S270.
Specifically, whether continuous preset time periods exceeding a preset number of time periods exist or not is detected for each 5G cell in the same coverage group, the wireless utilization rate of the 5G cell in the continuous preset time periods is greater than a 5G high load threshold (high _ load _ 5G), and the average value of the wireless utilization rate of all 4G cells in the same coverage group in each preset time period in the continuous preset time periods is less than a 4G low load threshold (low _ load _ 4G); or, detecting whether there are consecutive preset time periods exceeding a preset number of time periods, wherein the wireless utilization rates of the 5G cells in the consecutive preset time periods are all smaller than a 5G low load threshold (low _ load _ 5G), and the wireless utilization rates of all 4G cells in the same coverage group in each preset time period in the consecutive preset time period are all larger than a 4G high load threshold (high _ load _ 4G); if there is a continuous predetermined time period (one of the "before and after" is satisfied), it is determined that the loads of the 5G cell and the 4G cell in the same coverage group are unbalanced. The 5G high load threshold (high _ load _ 5G), the 4G low load threshold (low _ load _ 4G), the 5G low load threshold (low _ load _ 5G) and the 4G high load threshold (high _ load _ 4G) may be empirical values recognized by those skilled in the art, for example, the 5G cell is recognized by those skilled in the art to reach a high load state if the load exceeds a value, and then high _ load _5G is set to a value a.
If the preset time period is a small time period, and the predicted wireless utilization rate is 21 small time periods corresponding to 3 hours to 23 hours, the two unbalanced conditions are as follows:
the predicted radio utilization (i) > high _ load _5G of the 5G cell, and the number of consecutive periods of mean (predicted radio utilization of the 4G cell) (i) < low _ load _4G is larger than Z. Alternatively, the radio utilization ratio (i) < low _ load _5G predicted by the 5G cell, and the number of consecutive periods of mean (4G cell predicted radio utilization ratio) (i) > high _ load _4G is larger than Z. Wherein mean (predicted wireless utilization rate of 4G cells) represents the average of the predicted wireless utilization rates of all 4G cells in the group, i is an integer of [3,23] and represents 3 points to 23 points of prediction, Z is a preset number, high _ load _5G is a 5G high load threshold, low _ load _4G is a 4G low load threshold, low _ load _5G is a 5G low load threshold, and high _ load _4G is a 4G high load threshold.
For example, if the predetermined number is 3, at 8: in 4 hours from 00 to 11.
It should be noted that in a same coverage group, there may be multiple imbalance time intervals between the same 5G cell and 4G cell, for example, imbalance between 8 o 'clock and 12 o' clock, imbalance between 4 o 'clock and 8 o' clock in the afternoon, and there may be multiple imbalance loads between 5G cell and 4G cell in the same coverage group.
Step S260: and generating a load coordination task according to the imbalance type and the imbalance time interval of the at least one 5G cell and the 4G cell, and adjusting the network parameters of the at least one 5G cell according to the load coordination task.
The balance mainly aims at the 5G users, and simultaneously, in order to avoid confusion of setting of interoperation parameters of the 4G network and the 5G network caused by excessive adjustment, only the 5G network parameters are adjusted to expand or contract the coverage area and absorb or release the 5G users so as to balance the loads of the 4G network and the 5G network.
There are two types of imbalance, one is that the load of the 5G cell is higher than the 5G high load threshold, and the load of the 4G cell is lower than the 4G low load threshold, that is, corresponding to the following cases: the wireless utilization rates of the 5G cells in the continuous preset time period are all larger than a 5G high load threshold, and the average value of the wireless utilization rates of all 4G cells in the same coverage group in each preset time period in the continuous preset time period is smaller than a 4G low load threshold. In this case, the following load coordination task is generated for the 5G cell: during the unbalanced time period (i.e. during the continuous preset time period), the transmission power of the 5G cell is adjusted downward, the inter-system measurement threshold of the 5G cell is adjusted upward, and/or the inter-system handover threshold of the 5G cell is adjusted upward. By way of example in the foregoing, if the 5G cell and the 4G cell are unbalanced from 8 to 12 points, and belong to an unbalanced type where the load of the 5G cell is higher than the 5G high load threshold and the load of the 4G cell is lower than the 4G low load threshold, the generated load coordination task is as follows: the transmission power, the inter-system measurement threshold and/or the inter-system handover threshold of the 5G cell are adjusted up at 8.
The other is that the load of the 5G cell is lower than the 5G low load threshold, and the load of the 4G cell is higher than the 4G high load threshold, which corresponds to the following cases: the wireless utilization rates of the 5G cells in the continuous preset time period are all smaller than a 5G low-load threshold, and the wireless utilization rates of all 4G cells in the same coverage group in each preset time period in the continuous preset time period are all larger than a 4G high-load threshold. In this case, the following load coordination task is generated for the 5G cell: and during the unbalanced time period (namely the continuous preset time period), the transmission power of the 5G cell is adjusted up, the inter-system measurement threshold of the 5G cell is adjusted down, and/or the inter-system switching threshold of the 5G cell is adjusted down.
In addition, in general, when a corresponding time period is reached, the load coordination task corresponding to the time period may be executed, but in an actual implementation process, whether the corresponding load coordination task is executed may be determined according to a real-time cell load condition, so that the execution of the load coordination task is more consistent with the real-time load condition. Specifically, after the unbalanced time interval is reached, whether the real-time 5G cell load and the real-time 4G cell load meet the condition of triggering execution of the load coordination task is judged, and if yes, the load coordination task is executed. Wherein the predicted and determined imbalance type is: when the load of the 5G cell is higher than the 5G high load threshold and the load of the 4G cell is lower than the 4G low load threshold, the condition for triggering and executing the load coordination task is as follows: load _ now _5g > (high _ load _5g + low _load _5g)/2 and load _ now _4g < (high _ load _4g + low _load _4g)/2, otherwise not executing; for the predicted and determined imbalance type: when the load of the 5G cell is higher than the 5G high load threshold and the load of the 4G cell is lower than the 4G low load threshold, the condition for triggering and executing the load coordination task is as follows: load _ now _5G < (high _ load _5g + low \ u load _5g)/2 and load _ now _4G > (high _ load _4g + low _load _4g)/2, otherwise not executing, wherein load _ now _5G refers to the real-time load of the 5G cell and load _ now _4G refers to the real-time load of the 4G cell, for example, the real-time load is the load within 15 minutes of the nearest distance from the current time.
In an alternative embodiment, the load coordination tasks for a plurality of small time periods in the future are generated in a period in which load imbalance is not likely to occur in the early morning, and then when the corresponding time period is reached, the load coordination tasks are executed, for example, in the following steps of 02. In this way, the load cooperative task can be executed in each time period in time.
Step S270: no collaborative task is generated.
According to the load coordination method of the 4G cell and the 5G cell provided by the embodiment, the defects of the existing load coordination scheme are overcome, firstly, the concept of the 4G and 5G same coverage group is innovatively provided, and the object and the acting point of the 4G and 5G load coordination are clarified; secondly, the cells are classified according to the characteristics of the wireless communication network, and the cell load is predicted by using different models, so that the modeling efficiency is greatly improved, and the accuracy is ensured; thirdly, a balancing scheme is formulated according to the predicted data, and whether the balancing scheme is executed or not is judged by combining with real-time data, so that the frequency of 4 5G network load balancing is ensured, and the influence of an unreasonable scheme on a wireless network is avoided; fourthly, a whole set of method processes from data collection, data analysis, task generation to task execution is established, and efficiency is greatly improved.
Fig. 3 is a schematic structural diagram of a load coordination apparatus for a 4G cell and a 5G cell according to an embodiment of the present invention. As shown in fig. 3, the apparatus includes:
the prediction module 310 is adapted to predict, for each cell, the radio utilization of the cell in a plurality of preset time periods by using a prediction model selected for the cell, so as to obtain a plurality of groups of radio utilization corresponding to the plurality of cells;
a determining module 320, adapted to determine whether any of the same coverage groups includes both a 4G cell and a 5G cell;
a detecting module 330, adapted to detect whether there is a load imbalance between at least one 5G cell and a 4G cell in the same coverage group according to the multiple groups of wireless utilization rates if the same coverage group includes both the 4G cell and the 5G cell;
a generating module 340, adapted to generate a load coordination task according to an imbalance type and an imbalance time period of at least one 5G cell and a 4G cell if there is a load imbalance between the at least one 5G cell and the 4G cell;
an adjusting module 350, adapted to adjust a network parameter of the at least one 5G cell according to the load coordination task.
In an optional manner, the apparatus further comprises: a selection module adapted to:
determining attribute information of a date to be predicted, wherein the attribute information comprises a jump date attribute and a daily date attribute;
if the attribute is the jumping date attribute, selecting a prediction model for the cell according to the jumping stationarity index and the daily stationarity index of the cell;
and if the attribute is the daily date attribute, selecting a prediction model for the cell according to the daily stationarity index of the cell.
In an alternative form, the selection module is further adapted to:
if the jumping stationarity index is higher than a first high index threshold and the daily stationarity index is higher than a second high index threshold, selecting a stable model; if the jumping stationarity index is lower than a first low index threshold or the daily stationarity index is lower than a second low index threshold, selecting an LSTM model;
if the daily stationarity index is higher than a second high index threshold, selecting a stationarity model; if the daily stationarity index is higher than a second low index threshold and lower than or equal to a second high index threshold, selecting a prophet model; and if the daily stationarity index is lower than a second low index threshold, selecting an LSTM model.
In an optional manner, the apparatus further comprises: an identification module adapted to:
carrying out same coverage judgment on the 4G cells by using the industrial parameters to form a plurality of same coverage groups;
for any 5G cell, determining a target same-coverage group to which the 5G cell belongs according to the azimuth angle difference and/or the distance between the 5G cell and a 4G cell contained in each same-coverage group; adding the 5G cell to the target co-coverage group.
In an alternative, the identification module is further adapted to:
for the current same coverage group, if Max (F1, F2, … Fn) < F0 is satisfied and Max (D1, D2, … Dn) < D0 is satisfied, determining the current same coverage group as the target same coverage group;
wherein n is the number of 4G cells included in the current same coverage group, fi is the difference of azimuth angles of each 4G cell and the 5G cell in the current same coverage group, F0 is a difference threshold, di is the distance between each 4G cell and the 5G cell in the current same coverage group, and D0 is a distance threshold.
In an alternative form, the detection module is further adapted to:
detecting whether a continuous preset time period exceeding a preset number of time periods exists or not for each 5G cell in the same coverage group, wherein the wireless utilization rate of the 5G cell in the continuous preset time period is greater than a 5G high-load threshold, and the average value of the wireless utilization rate of all 4G cells in the same coverage group in each preset time period is less than a 4G low-load threshold; alternatively, the first and second electrodes may be,
detecting whether continuous preset time periods exceeding a preset number of time periods exist or not, wherein the wireless utilization rate of the 5G cells in the continuous preset time periods is smaller than a 5G low-load threshold, and the wireless utilization rate of all 4G cells in the same coverage group in each continuous preset time period is larger than a 4G high-load threshold;
and if the continuous preset time interval exists, judging that the loads of the 5G cell and the 4G cell in the same coverage group are unbalanced.
In an optional manner, the generating module is further adapted to:
for any 5G cell in the at least one 5G cell, if the wireless utilization rates of the 5G cells in the continuous preset time period are all greater than a 5G high load threshold, and the average value of the wireless utilization rates of all 4G cells in the same coverage group in each preset time period in the continuous preset time period is less than a 4G low load threshold, generating the following load coordination task: adjusting the transmission power of the 5G cell down, adjusting the inter-system measurement threshold of the 5G cell up and/or adjusting the inter-system switching threshold of the 5G cell up in an unbalanced time period; alternatively, the first and second electrodes may be,
if the wireless utilization rates of the 5G cells in the continuous preset time period are all smaller than a 5G low-load threshold, and the wireless utilization rates of all 4G cells in the same coverage group in each continuous preset time period are all larger than a 4G high-load threshold, generating the following load coordination task: and in an unbalanced time period, the transmitting power of the 5G cell is adjusted up, the inter-system measurement threshold of the 5G cell is adjusted down, and/or the inter-system switching threshold of the 5G cell is adjusted down.
An embodiment of the present invention provides a non-volatile computer storage medium, where the computer storage medium stores at least one executable instruction, and the computer executable instruction may execute the load coordination method for the 4G cell and the 5G cell in any method embodiment described above.
Fig. 4 is a schematic structural diagram of a computing device according to an embodiment of the present invention, and the specific embodiment of the present invention does not limit the specific implementation of the computing device.
As shown in fig. 4, the computing device may include: a processor (processor) 402, a Communications Interface 404, a memory 406, and a Communications bus 408.
Wherein: the processor 402, communication interface 404, and memory 406 communicate with each other via a communication bus 408. A communication interface 404 for communicating with network elements of other devices, such as clients or other servers. The processor 402 is configured to execute the program 410, and may specifically execute the relevant steps in the embodiment of the load coordination method for the 4G cell and the 5G cell of the computing device.
In particular, program 410 may include program code comprising computer operating instructions.
The processor 402 may be a central processing unit CPU, or an Application Specific Integrated Circuit (ASIC), or one or more Integrated circuits configured to implement an embodiment of the invention. The computing device includes one or more processors, which may be the same type of processor, such as one or more CPUs; or may be different types of processors such as one or more CPUs and one or more ASICs.
And a memory 406 for storing a program 410. Memory 406 may comprise high-speed RAM memory, and may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
The program 410 may specifically be configured to cause the processor 402 to perform the following operations:
for each cell, predicting the wireless utilization rate of the cell in a plurality of preset time periods by using a prediction model selected for the cell to obtain a plurality of groups of wireless utilization rates corresponding to a plurality of cells;
judging whether any one same coverage group simultaneously comprises a 4G cell and a 5G cell, if so, detecting whether at least one 5G cell and 4G cell are unbalanced in the same coverage group according to the multiple groups of wireless utilization rates;
and if the load imbalance of the at least one 5G cell and the 4G cell exists, generating a load coordination task according to the imbalance type and the imbalance time interval of the at least one 5G cell and the 4G cell, and adjusting the network parameters of the at least one 5G cell according to the load coordination task.
In an alternative, the program 410 further causes the processor 402 to:
determining attribute information of a date to be predicted, wherein the attribute information comprises a jump date attribute and a daily date attribute;
if the attribute is the jumping date attribute, selecting a prediction model for the cell according to the jumping stationarity index and the daily stationarity index of the cell;
and if the attribute is the daily date attribute, selecting a prediction model for the cell according to the daily stationarity index of the cell.
In an alternative, the program 410 further causes the processor 402 to:
if the jumping stationarity index is higher than a first high index threshold and the daily stationarity index is higher than a second high index threshold, selecting a stable model; if the jumping stationarity index is lower than a first low index threshold or the daily stationarity index is lower than a second low index threshold, selecting an LSTM model;
if the daily stationarity index is higher than a second high index threshold, selecting a stable model; if the daily stationarity index is higher than a second low index threshold and lower than or equal to a second high index threshold, selecting a prophet model; and if the daily stationarity index is lower than a second low index threshold, selecting an LSTM model.
In an alternative, the program 410 further causes the processor 402 to:
carrying out same coverage judgment on the 4G cells by using the industrial parameters to form a plurality of same coverage groups;
for any 5G cell, determining a target same-coverage group to which the 5G cell belongs according to the azimuth angle difference and/or the distance between the 5G cell and a 4G cell contained in each same-coverage group; adding the 5G cell to the target co-coverage group.
In an alternative, the program 410 further causes the processor 402 to:
for the current same coverage group, if Max (F1, F2, … Fn) < F0 is satisfied and Max (D1, D2, … Dn) < D0 is satisfied, determining the current same coverage group as the target same coverage group;
wherein n is the number of 4G cells included in the current same coverage group, fi is the difference of azimuth angles of each 4G cell and the 5G cell in the current same coverage group, F0 is a difference threshold, di is the distance between each 4G cell and the 5G cell in the current same coverage group, and D0 is a distance threshold.
In an alternative, the program 410 further causes the processor 402 to:
detecting whether a continuous preset time period exceeding a preset number of time periods exists or not for each 5G cell in the same coverage group, wherein the wireless utilization rate of the 5G cell in the continuous preset time period is greater than a 5G high-load threshold, and the average value of the wireless utilization rate of all 4G cells in the same coverage group in each preset time period is less than a 4G low-load threshold; alternatively, the first and second electrodes may be,
detecting whether continuous preset time periods exceeding a preset number of time periods exist or not, wherein the wireless utilization rate of the 5G cell in the continuous preset time periods is smaller than a 5G low-load threshold, and the wireless utilization rate of all 4G cells in the same coverage group in each preset time period in the continuous preset time periods is larger than a 4G high-load threshold;
and if the continuous preset time interval exists, judging that the loads of the 5G cell and the 4G cell in the same coverage group are unbalanced.
In an alternative, the program 410 further causes the processor 402 to:
for any 5G cell in the at least one 5G cell, if the wireless utilization rates of the 5G cells in the continuous preset time period are all greater than a 5G high load threshold, and the average value of the wireless utilization rates of all 4G cells in the same coverage group in each preset time period in the continuous preset time period is less than a 4G low load threshold, generating the following load coordination task: adjusting the transmission power of the 5G cell down, adjusting the inter-system measurement threshold of the 5G cell up and/or adjusting the inter-system switching threshold of the 5G cell up in an unbalanced time period; alternatively, the first and second electrodes may be,
if the wireless utilization rates of the 5G cells in the continuous preset time period are all smaller than a 5G low-load threshold, and the wireless utilization rates of all 4G cells in the same coverage group in each continuous preset time period are all larger than a 4G high-load threshold, generating the following load coordination task: and in an unbalanced time period, the transmitting power of the 5G cell is adjusted up, the inter-system measurement threshold of the 5G cell is adjusted down, and/or the inter-system switching threshold of the 5G cell is adjusted down.
The algorithms or displays presented herein are not inherently related to any particular computer, virtual system, or other apparatus. Various general purpose systems may also be used with the teachings herein. The required structure for constructing such a system is apparent from the description above. In addition, embodiments of the present invention are not directed to any particular programming language. It is appreciated that a variety of programming languages may be used to implement the teachings of embodiments of the present invention as described herein, and any descriptions of specific languages are provided above to disclose the best modes of embodiments of the invention.
In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the embodiments of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: that is, the claimed embodiments of the invention require more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and disposed in one or more devices different from the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component, and furthermore they may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.
The various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that a microprocessor or Digital Signal Processor (DSP) may be used in practice to implement some or all of the functionality of some or all of the components according to embodiments of the present invention. Embodiments of the invention may also be implemented as apparatus or device programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such programs implementing embodiments of the present invention may be stored on computer-readable media or may be in the form of one or more signals. Such a signal may be downloaded from an internet website or provided on a carrier signal or in any other form.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. Embodiments of the invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names. The steps in the above embodiments should not be construed as limiting the order of execution unless specified otherwise.
Claims (8)
1. A load coordination method of a 4G cell and a 5G cell comprises the following steps:
for each cell, predicting the wireless utilization rate of the cell in a plurality of preset time periods by using a prediction model selected for the cell to obtain a plurality of groups of wireless utilization rates corresponding to a plurality of cells;
judging whether any one same coverage group simultaneously comprises a 4G cell and a 5G cell, if so, detecting whether at least one 5G cell and 4G cell are unbalanced in the same coverage group according to the multiple groups of wireless utilization rates;
if the load of at least one 5G cell and 4G cell is unbalanced, generating a load cooperative task according to the type of the unbalance of the at least one 5G cell and the 4G cell and the unbalanced time interval, and adjusting the network parameters of the at least one 5G cell according to the load cooperative task;
wherein before the predicting the radio utilization of the cell in a plurality of preset time periods by using the prediction model selected for the cell, the method further comprises:
determining attribute information of a date to be predicted, wherein the attribute information comprises a jump date attribute and a daily date attribute;
if the attribute is the jumping date attribute, selecting a prediction model for the cell according to the jumping stationarity index and the daily stationarity index of the cell;
if the attribute is the daily date attribute, selecting a prediction model for the cell according to the daily stationarity index of the cell;
wherein, if the attribute is the jumping date attribute, the selecting and predicting model for the cell according to the jumping stationarity index and the daily stationarity index of the cell specifically comprises:
if the jumping stationarity index is higher than a first high index threshold and the daily stationarity index is higher than a second high index threshold, selecting a stable model; if the jumping stationarity index is lower than a first low index threshold or the daily stationarity index is lower than a second low index threshold, selecting an LSTM model;
if the attribute is the daily date attribute, selecting a prediction model for the cell according to the daily stationarity index of the cell specifically comprises the following steps:
if the daily stationarity index is higher than a second high index threshold, selecting a stable model; if the daily stationarity index is higher than a second low index threshold and lower than or equal to a second high index threshold, selecting a prophet model; and if the daily stationarity index is lower than a second low index threshold, selecting an LSTM model.
2. The method of claim 1, wherein before the determining whether there is at least one load imbalance between 5G cells and 4G cells in any of the same coverage groups according to the multiple sets of radio utilization, the method further comprises:
carrying out same coverage judgment on the 4G cells by using the industrial parameters to form a plurality of same coverage groups;
for any 5G cell, determining a target same-coverage group to which the 5G cell belongs according to the azimuth angle difference and/or the distance between the 5G cell and a 4G cell contained in each same-coverage group; adding the 5G cell to the target co-coverage group.
3. The method according to claim 2, wherein the determining, according to the azimuth angle difference and/or the distance between the 5G cell and the 4G cells included in each co-coverage group, the target co-coverage group to which the 5G cell belongs specifically comprises:
for the current same-coverage group, if Max (F1, F2, … Fn) < F0 and Max (D1, D2, … Dn) < D0 are satisfied, determining that the current same-coverage group is the target same-coverage group;
wherein n is the number of 4G cells included in the current same coverage group, fi is the difference of azimuth angles of each 4G cell and the 5G cell in the current same coverage group, F0 is a difference threshold, di is the distance between each 4G cell and the 5G cell in the current same coverage group, and D0 is a distance threshold.
4. The method of claim 2 or 3, wherein the detecting whether there is at least one load imbalance between 5G cells and 4G cells in the same coverage group according to the multiple groups of radio utilization further comprises:
detecting whether a continuous preset time period exceeding a preset number of time periods exists or not for each 5G cell in the same coverage group, wherein the wireless utilization rate of the 5G cell in the continuous preset time period is greater than a 5G high-load threshold, and the average value of the wireless utilization rate of all 4G cells in the same coverage group in each preset time period is less than a 4G low-load threshold; alternatively, the first and second electrodes may be,
detecting whether continuous preset time periods exceeding a preset number of time periods exist or not, wherein the wireless utilization rate of the 5G cells in the continuous preset time periods is smaller than a 5G low-load threshold, and the wireless utilization rate of all 4G cells in the same coverage group in each continuous preset time period is larger than a 4G high-load threshold;
and if the continuous preset time interval exists, judging that the loads of the 5G cell and the 4G cell in the same coverage group are unbalanced.
5. The method of claim 4, wherein the generating a load coordination task according to the imbalance type and imbalance period of the at least one 5G cell and the 4G cell further comprises:
for any 5G cell in the at least one 5G cell, if the wireless utilization rates of the 5G cells in the continuous preset time period are all greater than a 5G high load threshold, and the average value of the wireless utilization rates of all 4G cells in the same coverage group in each preset time period in the continuous preset time period is less than a 4G low load threshold, generating the following load coordination task: adjusting the transmission power of the 5G cell downwards, adjusting the inter-system measurement threshold of the 5G cell upwards and/or adjusting the inter-system switching threshold of the 5G cell upwards in an unbalanced time period; alternatively, the first and second electrodes may be,
if the wireless utilization rates of the 5G cells in the continuous preset time period are all smaller than a 5G low-load threshold, and the wireless utilization rates of all 4G cells in the same coverage group in each preset time period in the continuous preset time period are all larger than a 4G high-load threshold, generating the following load coordination tasks: and in an unbalanced time period, the transmitting power of the 5G cell is adjusted up, the inter-system measurement threshold of the 5G cell is adjusted down, and/or the inter-system switching threshold of the 5G cell is adjusted down.
6. A load coordination apparatus of a 4G cell and a 5G cell, comprising:
the prediction module is suitable for predicting the wireless utilization rate of each cell in a plurality of preset time periods by using the prediction model selected for the cell to obtain a plurality of groups of wireless utilization rates corresponding to the cells;
the judging module is suitable for judging whether any one same covering group simultaneously comprises a 4G cell and a 5G cell;
the detection module is suitable for detecting whether load imbalance exists between at least one 5G cell and a 4G cell in the same coverage group according to the multiple groups of wireless utilization rates if the same coverage group simultaneously comprises the 4G cell and the 5G cell;
the generation module is suitable for generating a load coordination task according to the unbalance type and the unbalance time period of at least one 5G cell and 4G cell if the load of the at least one 5G cell and the 4G cell is unbalanced;
the adjusting module is suitable for adjusting the network parameters of the at least one 5G cell according to the load coordination task;
wherein the apparatus further comprises: a selection module adapted to: determining attribute information of a date to be predicted, wherein the attribute information comprises a jump date attribute and a daily date attribute; if the attribute is the jumping date attribute, selecting a prediction model for the cell according to the jumping stationarity index and the daily stationarity index of the cell; if the attribute is the daily date attribute, selecting a prediction model for the cell according to the daily stationarity index of the cell;
the selection module is further adapted to: if the jumping stationarity index is higher than a first high index threshold and the daily stationarity index is higher than a second high index threshold, selecting a stable model; if the jumping stationarity index is lower than a first low index threshold or the daily stationarity index is lower than a second low index threshold, selecting an LSTM model; if the daily stationarity index is higher than a second high index threshold, selecting a stationarity model; if the daily stationarity index is higher than a second low index threshold and lower than or equal to a second high index threshold, selecting a prophet model; and if the daily stationarity index is lower than a second low index threshold, selecting an LSTM model.
7. A computing device, comprising: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;
the memory is used for storing at least one executable instruction, and the executable instruction causes the processor to execute the operation corresponding to the load coordination method of the 4G cell and the 5G cell in any one of claims 1-5.
8. A computer storage medium having stored therein at least one executable instruction for causing a processor to perform operations corresponding to the load coordination methods for 4G cells and 5G cells according to any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010663779.0A CN113973339B (en) | 2020-07-10 | 2020-07-10 | Load coordination method and device for 4G cell and 5G cell and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010663779.0A CN113973339B (en) | 2020-07-10 | 2020-07-10 | Load coordination method and device for 4G cell and 5G cell and computer storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113973339A CN113973339A (en) | 2022-01-25 |
| CN113973339B true CN113973339B (en) | 2023-04-18 |
Family
ID=79584637
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010663779.0A Active CN113973339B (en) | 2020-07-10 | 2020-07-10 | Load coordination method and device for 4G cell and 5G cell and computer storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113973339B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117896807A (en) * | 2022-10-08 | 2024-04-16 | 中兴通讯股份有限公司 | Method and device for controlling energy-saving state of cell, storage medium and electronic device |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102711177A (en) * | 2012-04-26 | 2012-10-03 | 北京邮电大学 | Service prediction based load balancing method |
| US9900790B1 (en) * | 2016-12-08 | 2018-02-20 | Futurewei Technologies, Inc. | Prediction of performance indicators in cellular networks |
| WO2018196297A1 (en) * | 2017-04-24 | 2018-11-01 | 上海中兴软件有限责任公司 | Method and apparatus for adjusting load balance execution threshold, and terminal |
| CN109495318A (en) * | 2018-12-17 | 2019-03-19 | 广东宜通世纪科技股份有限公司 | A kind of mobile communications network method for predicting, device and readable storage medium storing program for executing |
| CN110234133A (en) * | 2019-05-13 | 2019-09-13 | 中国联合网络通信集团有限公司 | A kind of network control method and device |
| CN110913401A (en) * | 2019-11-26 | 2020-03-24 | 南京华苏科技有限公司 | Method for optimizing imbalance of network same coverage load based on user data |
-
2020
- 2020-07-10 CN CN202010663779.0A patent/CN113973339B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102711177A (en) * | 2012-04-26 | 2012-10-03 | 北京邮电大学 | Service prediction based load balancing method |
| US9900790B1 (en) * | 2016-12-08 | 2018-02-20 | Futurewei Technologies, Inc. | Prediction of performance indicators in cellular networks |
| WO2018196297A1 (en) * | 2017-04-24 | 2018-11-01 | 上海中兴软件有限责任公司 | Method and apparatus for adjusting load balance execution threshold, and terminal |
| CN109495318A (en) * | 2018-12-17 | 2019-03-19 | 广东宜通世纪科技股份有限公司 | A kind of mobile communications network method for predicting, device and readable storage medium storing program for executing |
| CN110234133A (en) * | 2019-05-13 | 2019-09-13 | 中国联合网络通信集团有限公司 | A kind of network control method and device |
| CN110913401A (en) * | 2019-11-26 | 2020-03-24 | 南京华苏科技有限公司 | Method for optimizing imbalance of network same coverage load based on user data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113973339A (en) | 2022-01-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108829494B (en) | Container cloud platform intelligent resource optimization method based on load prediction | |
| CN109919514B (en) | Transformer area line loss abnormity detection method and device based on line loss marker post threshold value | |
| CN105912436A (en) | Method and device for predicting system computing resource based on exponential smoothing prediction | |
| CN113286315B (en) | Load balance judging method, device, equipment and storage medium | |
| CN111198808A (en) | Method, device, storage medium and electronic equipment for predicting performance index | |
| CN112508306A (en) | Self-adaptive method and system for power production configuration | |
| CN104156786A (en) | Non-working day maximum daily load forecasting system considering meteorological multi-factor influences | |
| CN113256022B (en) | Method and system for predicting electric load of transformer area | |
| CN115034519A (en) | Method and device for predicting power load, electronic equipment and storage medium | |
| CN102953936A (en) | Unit commitment for wind power generation | |
| CN113973339B (en) | Load coordination method and device for 4G cell and 5G cell and computer storage medium | |
| CN111680841A (en) | Short-term load prediction method and system based on principal component analysis and terminal equipment | |
| CN104008426A (en) | Distributed computing environment performance predicting method based on integrated learning | |
| CN105636088A (en) | Method and device for processing inter-cell interference, control device and base station | |
| CN115271218A (en) | Carbon emission prediction method, device, equipment and medium based on electric carbon factor | |
| CN111143070A (en) | Resource scheduling method and device | |
| CN108846505A (en) | The grid-connected consumption information various dimensions check method of renewable energy and equipment | |
| US20200044446A1 (en) | System and method for management of an electricity distribution grid | |
| CN114971428B (en) | Multi-source work order data-based engineer busy pre-estimation method and system | |
| Prado et al. | On providing quality of service in grid computing through multi-objective swarm-based knowledge acquisition in fuzzy schedulers | |
| CN114461299A (en) | Unloading decision determining method and device, electronic equipment and storage medium | |
| CN112637904B (en) | Load balancing method and device and computing equipment | |
| CN115396244A (en) | Bandwidth scheduling management method and device, electronic equipment and storage medium | |
| CN112965795A (en) | Cluster scheduling method, electronic device and storage medium | |
| CN113807654B (en) | Evaluation method of network operation index, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |