CN113766523A - Network resource utilization rate prediction method and device for serving cell and electronic equipment - Google Patents
Network resource utilization rate prediction method and device for serving cell and electronic equipment Download PDFInfo
- Publication number
- CN113766523A CN113766523A CN202010490415.7A CN202010490415A CN113766523A CN 113766523 A CN113766523 A CN 113766523A CN 202010490415 A CN202010490415 A CN 202010490415A CN 113766523 A CN113766523 A CN 113766523A
- Authority
- CN
- China
- Prior art keywords
- serving cell
- user
- time period
- network
- target
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 45
- 230000011664 signaling Effects 0.000 claims description 15
- 238000012549 training Methods 0.000 claims description 14
- 230000006870 function Effects 0.000 claims description 11
- 238000013439 planning Methods 0.000 claims description 8
- 238000013528 artificial neural network Methods 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 7
- 238000010586 diagram Methods 0.000 description 7
- 238000004891 communication Methods 0.000 description 5
- 238000012360 testing method Methods 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000004590 computer program Methods 0.000 description 3
- 238000012731 temporal analysis Methods 0.000 description 3
- 238000000700 time series analysis Methods 0.000 description 3
- 230000006855 networking Effects 0.000 description 2
- 230000008447 perception Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- YHXISWVBGDMDLQ-UHFFFAOYSA-N moclobemide Chemical compound C1=CC(Cl)=CC=C1C(=O)NCCN1CCOCC1 YHXISWVBGDMDLQ-UHFFFAOYSA-N 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000013468 resource allocation Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W16/00—Network planning, e.g. coverage or traffic planning tools; Network deployment, e.g. resource partitioning or cells structures
- H04W16/22—Traffic simulation tools or models
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/70—Admission control; Resource allocation
- H04L47/83—Admission control; Resource allocation based on usage prediction
-
- 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
- H04W24/08—Testing, supervising or monitoring using real traffic
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The application discloses a method and a device for predicting network resource utilization rate of a serving cell and electronic equipment, and aims to solve the problem that the serving cell cannot timely and effectively implement resource adjustment due to the existing mode of predicting the network resource utilization rate in a post-process mode. The method comprises the following steps: determining a network coverage type of a serving cell; acquiring user type distribution information of the serving cell in a target time period and service type distribution information of each user in the target time period, wherein the user types comprise stable users and unstable users; determining the type of a terminal used by each stable user in the service cell; and predicting the resource utilization rate of the serving cell to a target network in the target time period based on the network coverage type of the serving cell, the user type distribution information of the serving cell in the target time period, the service type distribution information of each user and the terminal type used by each stable user in the serving cell.
Description
Technical Field
The present application relates to the field of communications technologies, and in particular, to a method and an apparatus for predicting a network resource utilization rate of a serving cell, and an electronic device.
Background
With the continuous development of mobile network technology, the types of the mobile network bearer services are more and more complex. Taking a 5G network as an example, along with access of a large amount of internet of things devices in the 5G era, uncertainty of network service for network resource requirements is more serious. Therefore, the network resource utilization rate of the mobile network service cell is predicted in advance, and then a resource planning strategy is actively adopted, so that the perception that a mobile phone user in the service cell uses a high-quality network is ensured, and the method is of great importance to the 5G network planning construction.
At present, for the prediction of the network Resource utilization rate of a serving cell, a postcursor passive trend prediction method is usually adopted, for example, the network Resource utilization rate is predicted by network performance indexes such as an effective RRC (Radio Resource Control) connection average number, an uplink and Downlink PRB (Physical Resource Block) utilization rate, a PDCCH (Physical Downlink Control Channel) utilization rate and the like of a real-time monitoring network element; or, the service growth condition of the serving cell in the next hour is estimated based on the service use condition of the user in the serving cell and the like, so that the network resource utilization rate is predicted, and real-time dynamic adjustment is performed in advance through intelligent optimization modes such as load balancing, carrier automatic scheduling, permission (License) resource opening and the like through a preset threshold.
However, due to the limited resource allocation of the serving cell, the subsequent network resource utilization trend prediction method will cause that the serving cell cannot effectively implement resource adjustment in time, thereby affecting the use perception of the user service.
Disclosure of Invention
An object of the embodiments of the present application is to provide a method and an apparatus for predicting a network resource utilization rate of a serving cell, and an electronic device, so as to solve a problem that a serving cell cannot implement resource adjustment timely and effectively in an existing manner of predicting a network resource utilization rate retrospectively.
In order to solve the technical problem, the embodiment of the application adopts the following technical scheme:
in a first aspect, an embodiment of the present application provides a method for predicting network resource utilization of a serving cell, including:
determining a network coverage type of a serving cell;
acquiring user type distribution information of the serving cell in a target time period and service type distribution information of each user in the target time period, wherein the user types comprise stable users and unstable users;
determining the type of a terminal used by each stable user in the service cell;
and predicting the resource utilization rate of the serving cell to a target network in the target time period based on the network coverage type of the serving cell, the user type distribution information of the serving cell in the target time period, the service type distribution information of each user and the terminal type used by each stable user in the serving cell.
Optionally, determining the network coverage type of the serving cell includes:
determining a scene type of the serving cell based on network engineering parameters;
determining a network coverage type of the serving cell based on the scene category to which the serving cell belongs and planning construction information of the target network, wherein the network coverage type includes: target network overlay, other network overlay, target network and other network joint overlay, potential target network overlay.
Optionally, the user type distribution information includes a user type to which each user belongs and a proportion of each user type;
acquiring user type distribution information of the serving cell in a target time period, wherein the user type distribution information comprises:
acquiring call information of each user in a service cell in a specified historical time period matched with a target time period based on S1-U interface signaling data;
for each user in the serving cell, determining the user type to which the user belongs based on the call information of the user in the specified historical time period;
determining the proportion of each user type of the service cell in the designated historical time period based on the user type of each user of the service cell;
and predicting the proportion of each user type of the serving cell in the target time period based on the ratio of each user type of the serving cell in the designated historical time period.
Optionally, the obtaining service type distribution information of each user in the serving cell in the target time period includes:
acquiring service type distribution information of each user in the serving cell in a specified historical time period matched with the target time period based on S1-U interface signaling data;
and predicting the service type distribution information of each user in the target time period based on the service type distribution information of each user in the designated historical time period in the service cell.
Optionally, the predicting resource utilization rate of the serving cell for the target network in the target time period based on the network coverage type of the serving cell, the user type distribution information of the serving cell in the target time period, the service type distribution information of each user in the target time period, and the terminal type used by each stable user in the serving cell includes:
determining the number of stable users corresponding to different terminal types in the target time period based on the terminal type used by each stable user in the serving cell and the user type distribution information of the serving cell at the target time;
predicting the number of users migrating to the target network in the serving cell after the target network is opened based on the number of stable users corresponding to different terminal types in the target time period;
determining the total RB resource number occupied by the serving cell in the target time period based on the service type distribution information of each user in the target time period and the required RB resource number corresponding to each service type in the serving cell;
inputting a resource utilization rate prediction model into a network coverage type of the serving cell, user type distribution information of the serving cell in a target time period, the number of users of the serving cell migrating to the target network after the target network is started, and the total RB resource number occupied by the serving cell in the target time period, so as to obtain the resource utilization rate of the serving cell to the target network in the target time period;
the resource utilization rate prediction model is obtained by training a network coverage type of a sample cell, user type distribution information in a specified time period, the number of users who migrate to the target network after the target network is switched on and the total RB resource number occupied in the target time period by using the sample cell as a label in the specified time period.
Optionally, the resource utilization rate prediction model is obtained by training in the following manner:
taking the network coverage type of the sample cell, user type distribution information in a specified time period, the number of users who migrate to the target network after the target network is started and the total RB resource number occupied in the target time period as input layers, and taking the resource utilization rate of the sample cell to the target network in the specified time period as an output layer;
and optimizing the neural network based on a preset loss function and a back propagation algorithm to obtain the resource utilization rate prediction model.
In a second aspect, an embodiment of the present application further provides an apparatus for predicting network resource utilization of a serving cell, including:
a first determining unit, configured to determine a network coverage type of a serving cell;
an obtaining unit, configured to obtain user type distribution information of the serving cell in a target time period and service type distribution information of each user in the target time period, where the user types include a stable user and an unstable user;
a second determining unit, configured to determine a terminal type used by each stable user in the serving cell;
and the predicting unit is used for predicting the resource utilization rate of the serving cell to the target network in the target time period based on the network coverage type of the serving cell, the user type distribution information of the serving cell in the target time period, the service type distribution information of each user and the terminal type used by each stable user in the serving cell.
Optionally, the first determining unit is specifically configured to:
determining a scene type of the serving cell based on network engineering parameters;
determining a network coverage type of the serving cell based on the scene category to which the serving cell belongs and planning construction information of the target network, wherein the network coverage type includes: target network overlay, other network overlay, target network and other network joint overlay, potential target network overlay.
Optionally, the user type distribution information includes a user type to which each user belongs and a proportion of each user type;
the obtaining unit is specifically configured to:
acquiring call information of each user in a service cell in a specified historical time period matched with a target time period based on S1-U interface signaling data;
for each user in the serving cell, determining the user type to which the user belongs based on the call information of the user in the specified historical time period;
determining the proportion of each user type of the service cell in the designated historical time period based on the user type of each user of the service cell;
and predicting the proportion of each user type of the serving cell in the target time period based on the ratio of each user type of the serving cell in the designated historical time period.
Optionally, the obtaining unit is specifically configured to:
acquiring service type distribution information of each user in the serving cell in a specified historical time period matched with the target time period based on S1-U interface signaling data;
and predicting the service type distribution information of each user in the target time period based on the service type distribution information of each user in the designated historical time period in the service cell.
Optionally, the prediction unit is specifically configured to:
determining the number of stable users corresponding to different terminal types in the target time period based on the terminal type used by each stable user in the serving cell and the user type distribution information of the serving cell at the target time;
predicting the number of users migrating to the target network in the serving cell after the target network is opened based on the number of stable users corresponding to different terminal types in the target time period;
determining the total RB resource number occupied by the serving cell in the target time period based on the service type distribution information of each user in the target time period and the required RB resource number corresponding to each service type in the serving cell;
inputting a resource utilization rate prediction model into a network coverage type of the serving cell, user type distribution information of the serving cell in a target time period, the number of users of the serving cell migrating to the target network after the target network is started, and the total RB resource number occupied by the serving cell in the target time period, so as to obtain the resource utilization rate of the serving cell to the target network in the target time period;
the resource utilization rate prediction model is obtained by training a network coverage type of a sample cell, user type distribution information in a specified time period, the number of users who migrate to the target network after the target network is switched on and the total RB resource number occupied in the target time period by using the sample cell as a label in the specified time period.
Optionally, the apparatus further comprises:
and the model training unit is used for taking the network coverage type of the sample cell, the user type distribution information in a specified time period, the number of users who migrate to the target network after the target network is started and the total RB resource number occupied in the target time period as input layers, taking the resource utilization rate of the sample cell to the target network in the specified time period as an output layer, and optimizing the neural network based on a preset loss function and a back propagation algorithm to obtain the resource utilization rate prediction model.
In a third aspect, an embodiment of the present application further provides an electronic device, including:
a processor;
a memory for storing the processor-executable instructions;
wherein the processor is configured to execute the instructions to implement the method of the first aspect.
Fourth aspect embodiments of the present application also provide a computer-readable storage medium, where instructions, when executed by a processor of an electronic device, enable the electronic device to perform the method of the first aspect.
The embodiment of the application adopts at least one technical scheme which can achieve the following beneficial effects:
when the resource utilization rate of the serving cell to the target network is predicted, the network coverage type of the serving cell, user type distribution information, service characteristic information of each user and the type of a terminal used by each stable user are considered at the same time, and because the factors can accurately reflect the resource utilization trend of the serving cell to the target network, the resource utilization rate of the serving cell in the future can be predicted accurately in advance based on the factors, so that the network resources can be planned more purposefully, the network quality is ensured, and the network traffic is improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
fig. 1 is a flow diagram illustrating a method for network resource utilization prediction for a serving cell in accordance with an example embodiment;
FIG. 2 is a flow diagram illustrating a method of determining traffic type distribution information for a user in accordance with an exemplary embodiment;
fig. 3 is a schematic structural diagram illustrating a network resource utilization predicting apparatus for a serving cell according to an exemplary embodiment;
fig. 4 is a schematic structural diagram illustrating another network resource utilization predicting apparatus for a serving cell according to an example embodiment;
fig. 5 is a schematic structural diagram of an electronic device according to an exemplary embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be described in detail and completely with reference to the following specific embodiments of the present application and the accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The technical solutions provided by the embodiments of the present application are described in detail below with reference to the accompanying drawings.
Referring to fig. 1, fig. 1 is a flowchart illustrating a method for predicting network resource utilization of a serving cell according to an exemplary embodiment. As shown in fig. 1, the method comprises the steps of:
and S11, determining the network coverage type of the serving cell.
In the embodiment of the application, the serving cell is a cell accessed by the terminal, which provides better coverage and resource guarantee for the terminal user and can meet the service access and high-experience use of the terminal user.
The network coverage types may include: target network overlay, other network overlay, target network and other network joint overlay, potential target network overlay.
The target network may be, for example, a 5G network, the other network may be a 4G network, etc.
The target time period may be any time period in the future. In practical applications, the time period may be a certain day, such as 12 months and 12 days, friday, etc.; alternatively, the time period may be a certain time period of a certain day, such as 12:00-14:00 in the morning; alternatively, the time period may be a month, such as 1 month, 2 months, etc.; alternatively, the time period may be a year, such as 2021.
S12, obtaining the user type distribution information of the service cell in the target time period and the service type distribution information of each user in the target time period.
The user types include stable users and unstable users, the stable users refer to users with higher frequency in the serving cell, and the unstable users refer to users with lower frequency in the serving cell.
The user type distribution information of the serving cell is used for reflecting the distribution situation of different types of users. The user type distribution information of the serving cell may include, but is not limited to, a user type to which each user belongs, a total number of users, a number of users and a ratio corresponding to each user type in the serving cell, and the like.
The service type distribution information of the user is used for reflecting the use condition of the user to different types of services. The service type distribution information of the user may include, but is not limited to: the service type of each service used by the user, the proportion of each service type and the like.
And S13, determining the terminal type used by each stable user under the serving cell.
Illustratively, terminals can be classified into the following types according to the model and network type of the terminal used by the corresponding stable user: 5G terminal, change machine and exceed 4G medium and high-end terminal in a year, just change machine 4G medium and high-end terminal, 4G low-end terminal, function machine etc..
S14, predicting resource utilization of the target network by the serving cell in the target time period based on the network coverage type of the serving cell, the user type distribution information of the serving cell in the target time period and the service type distribution information of each user, and the terminal type used by each stable user in the serving cell.
In the above steps, the execution order of S11, S12, and S13 is not limited.
By adopting the technical scheme of the embodiment of the application, when the resource utilization rate of the serving cell to the target network is predicted, the network coverage type of the serving cell, the user type distribution information, the service characteristic information of each user and the terminal type used by each stable user are considered at the same time, and because the factors can accurately reflect the resource utilization trend of the serving cell to the target network, the resource utilization rate of the serving cell in the future can be predicted in advance and accurately based on the factors, so that the network resources can be planned more purposefully and the allocation can be optimized, the network quality is ensured, the network traffic is improved, and the practical value is higher.
The implementation process of the embodiment of the present application is described below with reference to specific examples.
In one embodiment, for step S11, the network coverage type of the serving cell may be obtained as follows:
step A1, determining the scene type of the service cell based on the network engineering parameters.
Specifically, the context class to which the serving cell belongs may be determined based on context fields in the network infrastructure engineering parameters. Therein, scene categories may for example include, but are not limited to, the following analogy: urban roads, rural areas, main lines of transportation, towns, industrial parks, scenic spots, institutions, enterprises, residential areas, suburban areas, transit schools, primary and secondary schools, universities, transportation hubs, private networks for high-speed rails, private networks for subways and the like, which are not limited in the embodiments of the present application.
Step A2, determining the network coverage type of the serving cell based on the scene type of the serving cell and the planning construction information of the target network.
For example, after determining the scene type to which the serving cell belongs, it may be determined whether the serving cell is an anchor point station of the target network based on the target network cell engineering parameters, and if so, it may be determined that the network coverage type of the serving cell is target network coverage; otherwise, further based on the scene category to which the serving cell belongs and the planning construction information of the target network, it is determined whether the serving cell co-base station site has a plan for constructing a target network base station (such as a non-independent networking NSA base station or an independent networking SA base station) in the target time period. If yes, determining the network coverage type of the serving cell as potential target network coverage; otherwise, further judging whether a plan for constructing the target network base station exists in a preset range (such as within 1 kilometer) around the service cell in the target time period. If the target network base station is planned to be built in the target time period within the preset range around the service cell, the network coverage type of the service cell can be determined to be potential target network coverage.
In one embodiment, in step S12, the user type distribution information of the serving cell may include the user type of each user in the serving cell and the ratio of each user type. Accordingly, the user type distribution information of the serving cell in the target time period can be obtained by the following method:
and step B1, acquiring the call information of each user in the service cell in the designated historical time period matched with the target time period based on the S1-U interface signaling data.
The call information may include the number of calls, the call time, the residence time, and the like.
And step B2, aiming at each user in the service cell, determining the user type of the user based on the call information of the user in the appointed historical time period.
The specified historical time period matched with the target time period may be a historical time period in synchronization with the target time period, for example, if the target time period is 3 months of the year, the specified historical time period matched with the target time period may be 3 months of the last year; alternatively, the designated historical time period matching the target time period may be a historical time period adjacent to the target time period, for example, if the target time period is the next week, the designated historical time period matching the target time period may be the current week, and so on.
Specifically, the call information of all users appearing in the serving cell in the specified historical time period may be counted, and the users whose call information satisfies the preset condition are screened out as stable users and the other users are unstable users in a PN decision manner. For example, the preset condition may be that more than D days occur within a specified period of time and that the average residence time per day exceeds H hours.
And step B3, determining the proportion of each user type in the designated historical time period by the serving cell based on the user type of each user under the serving cell.
The proportion of the user types of the service cell in the specified historical time period specification can be obtained by counting the users of all the user types in the service cell. Of course, the ring ratio variation of the total number of users, the number of stable users, and the proportion of stable users can also be obtained. For example, table 1 shows statistics for user types under cell a.
TABLE 1
And step B4, predicting the proportion of each user type of the service cell in the target time period based on the proportion of each user type of the service cell in the appointed historical time period.
Specifically, the stable user number in the designated historical time period can be used as a sample data set, the sample data set is divided into a training data set and a test data set according to a preset division rule, the periodicity and the trend of the training data set are analyzed based on a time series analysis algorithm, the time series analysis algorithm is modified according to an analysis result based on the test data set, and finally the proportion of different user types of the service cell in the target time period is predicted based on the modified time series analysis algorithm.
For example, different time series fitting models such as a seamental ARIMA model, a Holt-Winter model, and an STL Decomposition model can be used to fit the training data set to obtain the periodicity and trend prediction results. And then, verifying the prediction results of all the time sequence fitting models based on the test data set, and selecting the model with the minimum Mean Square Error (MSE) as the final time sequence fitting model. Further, the proportion of different user types of the serving cell in a specified historical time period is input into the time series fitting model to obtain the proportion of different user types of the serving cell in a target time period.
It should be noted that, since the total number of users and the number of stable users in the serving cell generally have a relatively obvious trend and/or periodicity, the selected time series fitting model may be a time series fitting model that effectively handles the periodicity and the trend.
In the method for predicting the proportion of each user type of the serving cell in the target time period based on the S1-U interface signaling data provided in this embodiment, the S1-U interface signaling data does not depend on the manufacturer and the scene type to which the serving cell belongs, so that the method has a basis for universal application in the whole network.
In one embodiment, for step S12, the service type distribution information of each user in the serving cell in the target time period may be obtained through the following steps:
and C1, acquiring the service type distribution information of each user in the designated historical time period matched with the target time period under the service cell based on the S1-U interface signaling data.
Specifically, as shown in fig. 2, the usage of APPs by each user in a specified historical time period may be identified based on the APP field in the S1-U interface signaling data, and further, the ratio of different service types of each user in the specified historical time period may be determined based on the service type to which each APP used by each user belongs.
The service types may include a large packet service, a medium packet service, and a small packet service. The large packet service refers to a service occupying more RB resources, and includes, but is not limited to: tencent video, love art, etc.; the packet service refers to a service occupying less RB resources, and includes, but is not limited to: WeChat, QQ, etc.; the RB resources occupied by the medium packet service are located between the large packet service and the small packet service, including but not limited to: green microblog, fox searching news and the like.
And C2, predicting the service type distribution information of each user in the target time period based on the service type distribution information of each user in the appointed historical time period under the service cell.
Specifically, for each user, fitting analysis may be performed based on the proportion of different service types of the user in the specified historical time period, so as to obtain the proportion of different service types of the user in the target time period.
In the method for predicting the service type distribution information of each user in the target time period based on the S1-U interface signaling data provided in this embodiment, the S1-U interface signaling data does not depend on the scenario types of the manufacturer and the serving cell, so that the method has a basis for universal application in the whole network.
In one embodiment, for step S13, the type of the terminal used by each stable user in the serving cell may be determined by the model number indicated by the first eight bits (TAC) of the IMEI (International Mobile Equipment Identity) of the terminal used by the user. For example, terminal models may include, for example, but are not limited to: the machine comprises a 5G terminal, a 4G middle-high terminal just exchanged, a 4G middle-high terminal exchanged for more than one year, a 4G low-end terminal, a functional machine (such as a POS machine) and the like.
In one embodiment, for the above step S14, the resource utilization rate of the serving cell to the target network in the target time period can be predicted by the following steps:
and D1, determining the number of stable users corresponding to different terminal types in the target time period based on the terminal type used by each stable user in the serving cell and the user type distribution information of the serving cell at the target time.
For example, the user type distribution information of the serving cell at the target time may include a total number of users and a number of stable users of the serving cell at the target time, and the number of stable users of the serving cell is classified and integrated according to the type of the used terminal, so that the number of stable users corresponding to different terminal types in the target time period may be further counted.
D2, predicting the number of users of the target network to which the serving cell migrates after the target network is opened based on the number of stable users corresponding to different terminal types in the target time period.
Specifically, the number f of users migrating to the target network corresponding to different terminal types after the target network is opened can be obtained by fitting the number of stable users corresponding to different terminal types in the target time periodi(t) further determining the number of users migrating to the target network in the serving cell after the target network is opened, based on the number of users migrating to the target network corresponding to different terminal types, that is, f (t) Σifi(t), wherein t is the number of opening days of the target network base station.
It should be noted that, in consideration of the fact that the user migration volume is large at the initial stage of opening the target network and the subsequent accounts are stable, a Logistic curve and a Gompertz curve can be adopted for fitting.
In addition, when curve fitting is performed, data to be fitted can be divided into a training data set and a test data set according to a preset dividing rule, fitting is performed on the training data set based on a preset fitting curve, the fitting curve is corrected based on the test data set and a fitting result, and finally the number of users, corresponding to different terminal types, migrating to the target network after the target network is opened is obtained.
D3, determining the total RB resource number occupied by the serving cell in the target time period based on the service type distribution information of each user in the target time period and the required RB resource number corresponding to each service type in the serving cell.
Illustratively, table 2 shows a correspondence between service types and required RB resources, where X < Y < Z.
Table 2:
| APP applications | Type of service | Number of occupied RB resources |
| Packet service | X | |
| Love art | Big packet service | Z |
| Mobile phone hundred degrees | Packet service | X |
| Tremble sound | Middle packet service | Y |
| Payment device | Packet service | X |
D4, inputting the network coverage type of the serving cell, the user type distribution information of the serving cell in a target time period, the number of users of the serving cell migrating to the target network after the target network is opened, and the total RB resource number occupied by the serving cell in the target time period into a resource utilization rate prediction model, so as to obtain the resource utilization rate of the serving cell to the target network in the target time period.
The resource utilization rate prediction model is obtained by training a network coverage type of a sample cell, user type distribution information in a specified time period, the number of users who migrate to the target network after the target network is switched on and the total RB resource number occupied in the target time period by using the sample cell as a label in the specified time period.
In this embodiment, the resource utilization rate of the serving cell to the target network can be quickly and accurately obtained by taking the above-mentioned four-dimensional factors as input and predicting the resource utilization rate based on the input by using the resource utilization rate prediction model established based on the machine learning algorithm.
In one embodiment, the resource utilization prediction model may be trained by:
e1, taking the network coverage type of the sample cell, the user type distribution information in the specified time period, the number of users who migrate to the target network after the target network is opened and the total number of RB resources occupied in the target time period as input layers, and taking the resource utilization rate of the sample cell to the target network in the specified time period as an output layer.
E2, optimizing the neural network based on a preset loss function and a back propagation algorithm to obtain the resource utilization rate prediction model.
Considering that the factors of the four dimensions have complex incidence relation, the characteristics of an arbitrary function which can be infinitely approximated by a neural network can be utilized to carry out analysis fitting.
In particular, the predetermined loss function may be a cross-entry function.
It should be noted that, in order to continuously optimize the resource utilization rate prediction model and improve the accuracy of the output result of the resource utilization rate prediction model, the model may be corrected based on the resource utilization rate of the target network and the actual resource utilization rate of the target network in the target time period by the obtained serving cell.
In this embodiment, the characteristic that the neural network can infinitely approximate any function is used to perform analysis fitting on corresponding data of the sample cell, so that the accuracy of the resource utilization rate prediction model can be improved, and further, the prediction result of the resource utilization rate of the serving cell in the future can be more accurate, so that network resources can be planned more purposefully, optimized adjustment can be performed on the network resources, the network quality is ensured, and the network traffic is improved.
Referring to fig. 3, fig. 3 is a schematic structural diagram illustrating a network resource utilization predicting apparatus 300 for a serving cell according to an exemplary embodiment. As shown in fig. 3, the apparatus 300 includes:
a first determining unit 301, configured to determine a network coverage type of a serving cell.
An obtaining unit 302, configured to obtain user type distribution information of the serving cell in a target time period and service type distribution information of each user in the target time period, where the user types include a stable user and an unstable user.
A second determining unit 303, configured to determine a terminal type used by each stable user in the serving cell.
A predicting unit 304, configured to predict resource utilization rate of the serving cell for a target network in a target time period based on a network coverage type of the serving cell, user type distribution information of the serving cell in the target time period, service type distribution information of each user, and a terminal type used by each stable user in the serving cell.
Optionally, the first determining unit 301 is specifically configured to:
determining a scene type of the serving cell based on network engineering parameters;
determining a network coverage type of the serving cell based on the scene category to which the serving cell belongs and planning construction information of the target network, wherein the network coverage type includes: target network overlay, other network overlay, target network and other network joint overlay, potential target network overlay.
Optionally, the user type distribution information includes a user type to which each user belongs and a proportion of each user type;
the obtaining unit 302 is specifically configured to:
acquiring call information of each user in a service cell in a specified historical time period matched with a target time period based on S1-U interface signaling data;
for each user in the serving cell, determining the user type to which the user belongs based on the call information of the user in the specified historical time period;
determining the proportion of each user type of the service cell in the designated historical time period based on the user type of each user of the service cell;
and predicting the proportion of each user type of the serving cell in the target time period based on the ratio of each user type of the serving cell in the designated historical time period.
Optionally, the obtaining unit 302 is specifically configured to:
acquiring service type distribution information of each user in the serving cell in a specified historical time period matched with the target time period based on S1-U interface signaling data;
and predicting the service type distribution information of each user in the target time period based on the service type distribution information of each user in the designated historical time period in the service cell.
Optionally, the prediction unit 304 is specifically configured to:
determining the number of stable users corresponding to different terminal types in the target time period based on the terminal type used by each stable user in the serving cell and the user type distribution information of the serving cell at the target time;
predicting the number of users migrating to the target network in the serving cell after the target network is opened based on the number of stable users corresponding to different terminal types in the target time period;
determining the total RB resource number occupied by the serving cell in the target time period based on the service type distribution information of each user in the target time period and the required RB resource number corresponding to each service type in the serving cell;
inputting a resource utilization rate prediction model into a network coverage type of the serving cell, user type distribution information of the serving cell in a target time period, the number of users of the serving cell migrating to the target network after the target network is started, and the total RB resource number occupied by the serving cell in the target time period, so as to obtain the resource utilization rate of the serving cell to the target network in the target time period;
the resource utilization rate prediction model is obtained by training a network coverage type of a sample cell, user type distribution information in a specified time period, the number of users who migrate to the target network after the target network is switched on and the total RB resource number occupied in the target time period by using the sample cell as a label in the specified time period.
Optionally, as shown in fig. 4, the apparatus 300 further includes:
the model training unit 305 is configured to use the network coverage type of the sample cell, the user type distribution information in a specified time period, the number of users who migrate to the target network after the target network is turned on, and the total number of RB resources occupied in the target time period as input layers, use the resource utilization rate of the sample cell to the target network in the specified time period as an output layer, and optimize the neural network based on a preset loss function and a back propagation algorithm to obtain the resource utilization rate prediction model.
With regard to the apparatus in the above-described embodiment, the specific manner in which each unit performs the operation has been described in detail in the embodiment related to the method, and will not be described in detail here.
Fig. 5 is a block diagram illustrating an electronic device 500 in accordance with an example embodiment. For example, the electronic device 500 may be provided as a server. Referring to fig. 5, the electronic device 500 comprises a processor 522, which may be one or more in number, and a memory 532 for storing computer programs executable by the processor 522. The computer programs stored in memory 532 may include one or more modules that each correspond to a set of instructions. Further, the processor 522 may be configured to execute the computer program to perform the network resource utilization prediction method of the serving cell described above.
Additionally, the electronic device 500 may also include a power component 526 and a communication component 550, the power component 526 may be configured to perform power management of the electronic device 500, and the communication component 550 may be configured to enable communication, e.g., wired or wireless communication, of the electronic device 500. In addition, the electronic device 500 may also include input/output (I/O) interfaces 558. The electronic device 500 may operate based on an operating system stored in memory 532, such as Windows Server, Mac OS XTM, UnixTM, Linux, and the like.
In another exemplary embodiment, a computer readable storage medium including program instructions, which when executed by a processor, implement the steps of the network resource utilization prediction method of the serving cell described above is also provided. For example, the computer readable storage medium may be the memory 532 including program instructions executable by the processor 522 of the electronic device 500 to perform the network resource utilization prediction method for the serving cell described above.
Of course, besides the software implementation, the electronic device of the present application does not exclude other implementations, such as a logic device or a combination of software and hardware, and the like, that is, the execution subject of the following processing flow is not limited to each logic unit, and may also be hardware or a logic device.
Embodiments of the present application also provide a computer-readable storage medium storing one or more programs, where the one or more programs include instructions, which when executed by a portable electronic device including a plurality of application programs, enable the portable electronic device to perform the method of the embodiment shown in fig. 1, and are specifically configured to:
determining a network coverage type of a serving cell;
acquiring user type distribution information of the serving cell in a target time period and service type distribution information of each user in the target time period, wherein the user types comprise stable users and unstable users;
determining the type of a terminal used by each stable user in the service cell;
and predicting the resource utilization rate of the serving cell to a target network in the target time period based on the network coverage type of the serving cell, the user type distribution information of the serving cell in the target time period, the service type distribution information of each user and the terminal type used by each stable user in the serving cell.
In short, the above description is only a preferred embodiment of the present application, and is not intended to limit the scope of the present application. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
Claims (10)
1. A method for predicting network resource utilization of a serving cell, comprising:
determining a network coverage type of a serving cell;
acquiring user type distribution information of the serving cell in a target time period and service type distribution information of each user in the target time period, wherein the user types comprise stable users and unstable users;
determining the type of a terminal used by each stable user in the service cell;
and predicting the resource utilization rate of the serving cell to a target network in the target time period based on the network coverage type of the serving cell, the user type distribution information of the serving cell in the target time period, the service type distribution information of each user and the terminal type used by each stable user in the serving cell.
2. The method of claim 1, wherein determining the network coverage type of the serving cell comprises:
determining a scene type of the serving cell based on network engineering parameters;
determining a network coverage type of the serving cell based on the scene category to which the serving cell belongs and planning construction information of the target network, wherein the network coverage type includes: target network overlay, other network overlay, target network and other network joint overlay, potential target network overlay.
3. The method according to claim 1, wherein the user type distribution information includes a user type to which each user belongs and a ratio of each user type;
acquiring user type distribution information of the serving cell in a target time period, wherein the user type distribution information comprises:
acquiring call information of each user in a service cell in a specified historical time period matched with a target time period based on S1-U interface signaling data;
for each user in the serving cell, determining the user type to which the user belongs based on the call information of the user in the specified historical time period;
determining the proportion of each user type of the service cell in the designated historical time period based on the user type of each user of the service cell;
and predicting the proportion of each user type of the serving cell in the target time period based on the ratio of each user type of the serving cell in the designated historical time period.
4. The method of claim 1, wherein obtaining the service type distribution information of each user in the serving cell in the target time period comprises:
acquiring service type distribution information of each user in the serving cell in a specified historical time period matched with the target time period based on S1-U interface signaling data;
and predicting the service type distribution information of each user in the target time period based on the service type distribution information of each user in the designated historical time period in the service cell.
5. The method of claim 1, wherein the predicting resource utilization of the serving cell for the target network in the target time period based on the network coverage type of the serving cell, the user type distribution information of the serving cell in the target time period and the traffic type distribution information of each user in the target time period, and the terminal type used by each stable user in the serving cell comprises:
determining the number of stable users corresponding to different terminal types in the target time period based on the terminal type used by each stable user in the serving cell and the user type distribution information of the serving cell at the target time;
predicting the number of users migrating to the target network in the serving cell after the target network is opened based on the number of stable users corresponding to different terminal types in the target time period;
determining the total RB resource number occupied by the serving cell in the target time period based on the service type distribution information of each user in the target time period and the required RB resource number corresponding to each service type in the serving cell;
inputting a resource utilization rate prediction model into a network coverage type of the serving cell, user type distribution information of the serving cell in a target time period, the number of users of the serving cell migrating to the target network after the target network is started, and the total RB resource number occupied by the serving cell in the target time period, so as to obtain the resource utilization rate of the serving cell to the target network in the target time period;
the resource utilization rate prediction model is obtained by training a network coverage type of a sample cell, user type distribution information in a specified time period, the number of users who migrate to the target network after the target network is switched on and the total RB resource number occupied in the target time period by using the sample cell as a label in the specified time period.
6. The method of claim 5, wherein the resource utilization prediction model is trained by:
taking the network coverage type of the sample cell, user type distribution information in a specified time period, the number of users who migrate to the target network after the target network is started and the total RB resource number occupied in the target time period as input layers, and taking the resource utilization rate of the sample cell to the target network in the specified time period as an output layer;
and optimizing the neural network based on a preset loss function and a back propagation algorithm to obtain the resource utilization rate prediction model.
7. An apparatus for predicting network resource utilization of a serving cell, comprising:
a first determining unit, configured to determine a network coverage type of a serving cell;
an obtaining unit, configured to obtain user type distribution information of the serving cell in a target time period and service type distribution information of each user in the target time period, where the user types include a stable user and an unstable user;
a second determining unit, configured to determine a terminal type used by each stable user in the serving cell;
and the predicting unit is used for predicting the resource utilization rate of the serving cell to the target network in the target time period based on the network coverage type of the serving cell, the user type distribution information of the serving cell in the target time period, the service type distribution information of each user and the terminal type used by each stable user in the serving cell.
8. The apparatus of claim 7, wherein the prediction unit is specifically configured to:
determining the number of stable users corresponding to different terminal types in the target time period based on the terminal type used by each stable user in the serving cell and the user type distribution information of the serving cell at the target time;
predicting the number of users migrating to the target network in the serving cell after the target network is opened based on the number of stable users corresponding to different terminal types in the target time period;
determining the total RB resource number occupied by the serving cell in the target time period based on the service type distribution information of each user in the target time period and the required RB resource number corresponding to each service type in the serving cell;
inputting a resource utilization rate prediction model into a network coverage type of the serving cell, user type distribution information of the serving cell in a target time period, the number of users of the serving cell migrating to the target network after the target network is started, and the total RB resource number occupied by the serving cell in the target time period, so as to obtain the resource utilization rate of the serving cell to the target network in the target time period;
the resource utilization rate prediction model is obtained by training a network coverage type of a sample cell, user type distribution information in a specified time period, the number of users who migrate to the target network after the target network is switched on and the total RB resource number occupied in the target time period by using the sample cell as a label in the specified time period.
9. An electronic device, comprising:
a processor;
a memory for storing the processor-executable instructions;
wherein the processor is configured to execute the instructions to implement the network resource utilization prediction method of the serving cell according to any one of claims 1 to 6.
10. A computer readable storage medium, wherein instructions, when executed by a processor of an electronic device, enable the electronic device to perform the network resource utilization prediction method of a serving cell of any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010490415.7A CN113766523B (en) | 2020-06-02 | 2020-06-02 | Method and device for predicting network resource utilization rate of serving cell and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010490415.7A CN113766523B (en) | 2020-06-02 | 2020-06-02 | Method and device for predicting network resource utilization rate of serving cell and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113766523A true CN113766523A (en) | 2021-12-07 |
| CN113766523B CN113766523B (en) | 2023-08-01 |
Family
ID=78782815
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010490415.7A Active CN113766523B (en) | 2020-06-02 | 2020-06-02 | Method and device for predicting network resource utilization rate of serving cell and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113766523B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115001559A (en) * | 2022-03-17 | 2022-09-02 | 中国科学院计算技术研究所 | User terminal distribution model construction method suitable for satellite network |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105227369A (en) * | 2015-10-19 | 2016-01-06 | 南京华苏科技股份有限公司 | Based on the mobile Apps of mass-rent pattern to the analytical method of the Wi-Fi utilization of resources |
| CN107426759A (en) * | 2017-08-09 | 2017-12-01 | 广州杰赛科技股份有限公司 | The Forecasting Methodology and system of newly-increased base station data portfolio |
| CN107426721A (en) * | 2016-05-24 | 2017-12-01 | 中国移动通信集团广东有限公司 | A kind of wireless network resource regulates and controls method and device |
| CN108965024A (en) * | 2018-08-01 | 2018-12-07 | 重庆邮电大学 | A kind of virtual network function dispatching method of the 5G network slice based on prediction |
| CN109462853A (en) * | 2018-11-05 | 2019-03-12 | 武汉虹信技术服务有限责任公司 | A kind of network capacity prediction technique based on neural network model |
| CN109803285A (en) * | 2017-11-17 | 2019-05-24 | 中国移动通信有限公司研究院 | A kind of cell processing method, device and the network equipment |
| WO2019241589A1 (en) * | 2018-06-13 | 2019-12-19 | Cohere Technologies, Inc. | Reciprocal calibration for channel estimation based on second-order statistics |
-
2020
- 2020-06-02 CN CN202010490415.7A patent/CN113766523B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105227369A (en) * | 2015-10-19 | 2016-01-06 | 南京华苏科技股份有限公司 | Based on the mobile Apps of mass-rent pattern to the analytical method of the Wi-Fi utilization of resources |
| CN107426721A (en) * | 2016-05-24 | 2017-12-01 | 中国移动通信集团广东有限公司 | A kind of wireless network resource regulates and controls method and device |
| CN107426759A (en) * | 2017-08-09 | 2017-12-01 | 广州杰赛科技股份有限公司 | The Forecasting Methodology and system of newly-increased base station data portfolio |
| CN109803285A (en) * | 2017-11-17 | 2019-05-24 | 中国移动通信有限公司研究院 | A kind of cell processing method, device and the network equipment |
| WO2019241589A1 (en) * | 2018-06-13 | 2019-12-19 | Cohere Technologies, Inc. | Reciprocal calibration for channel estimation based on second-order statistics |
| CN108965024A (en) * | 2018-08-01 | 2018-12-07 | 重庆邮电大学 | A kind of virtual network function dispatching method of the 5G network slice based on prediction |
| CN109462853A (en) * | 2018-11-05 | 2019-03-12 | 武汉虹信技术服务有限责任公司 | A kind of network capacity prediction technique based on neural network model |
Non-Patent Citations (1)
| Title |
|---|
| 尼俊红: "超密集部署下以用户为中心的分簇与资源分配", 《科学技术与工程》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115001559A (en) * | 2022-03-17 | 2022-09-02 | 中国科学院计算技术研究所 | User terminal distribution model construction method suitable for satellite network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113766523B (en) | 2023-08-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8412234B1 (en) | Clustering location and time for location prediction | |
| US8433329B2 (en) | System and method for prioritizing user communications | |
| CN111385800B (en) | Carrier scheduling method and device for LTE capacity equalization | |
| Cui et al. | Machine Learning‐Based Resource Allocation Strategy for Network Slicing in Vehicular Networks | |
| CN110505650B (en) | Intelligent evaluation method and device for capacity of random heterogeneous hierarchical network | |
| Ma et al. | Context-aware proactive 5G load balancing and optimization for urban areas | |
| US20210337400A1 (en) | Identification and prioritization of optimum capacity solutions in a telecommunications network | |
| CN114007225A (en) | BWP allocation method, apparatus, electronic device and computer readable storage medium | |
| Bonadio et al. | Performance analysis of an edge computing SaaS system for mobile users | |
| Romanov et al. | The method of redistributing traffic in mobile network | |
| Sadreddini et al. | Dynamic resource sharing in 5G with LSA: Criteria‐based management framework | |
| CN110677854A (en) | Method, apparatus, device and medium for carrier frequency capacity adjustment | |
| Zhao et al. | Performance analysis and optimization for cognitive radio networks with classified secondary users and impatient packets | |
| CN103561103B (en) | The control method of business migration and device | |
| CN113766523B (en) | Method and device for predicting network resource utilization rate of serving cell and electronic equipment | |
| Atawia et al. | Utilization of stochastic modeling for green predictive video delivery under network uncertainties | |
| CN117202319A (en) | Base station selection method and device, electronic equipment and storage medium | |
| Bejarano-Luque et al. | A context-aware data-driven algorithm for small cell site selection in cellular networks | |
| Singh et al. | A learning based mobile user traffic characterization for efficient resource management in cellular networks | |
| CN113132136A (en) | Satisfaction degree prediction model establishment method, satisfaction degree prediction device and electronic equipment | |
| Balieiro et al. | An evolutionary scheme for secondary virtual networks mapping onto cognitive radio substrate | |
| CN114928849B (en) | Base station deployment method and device, electronic equipment and storage medium | |
| CN113487148B (en) | Method and device for obtaining network evaluation result | |
| Xiao et al. | 5G construction efficiency enhancement based on LSTM algorithm | |
| Sánchez‐García et al. | 2G/3G connect: An educational software for teaching 2G/3G mobile communications to engineering students |
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 |