CN113141616B - Method, device and system for selecting energy-saving base station and energy-saving mode through adaptive identification of O + B domain data + service scene - Google Patents
Method, device and system for selecting energy-saving base station and energy-saving mode through adaptive identification of O + B domain data + service scene Download PDFInfo
- Publication number
- CN113141616B CN113141616B CN202110424578.XA CN202110424578A CN113141616B CN 113141616 B CN113141616 B CN 113141616B CN 202110424578 A CN202110424578 A CN 202110424578A CN 113141616 B CN113141616 B CN 113141616B
- Authority
- CN
- China
- Prior art keywords
- energy
- saving
- base station
- service
- module
- 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
- H04W52/00—Power management, e.g. TPC [Transmission Power Control], power saving or power classes
- H04W52/02—Power saving arrangements
- H04W52/0203—Power saving arrangements in the radio access network or backbone network of wireless communication networks
- H04W52/0206—Power saving arrangements in the radio access network or backbone network of wireless communication networks in access points, e.g. base stations
-
- 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
- H04W16/18—Network planning tools
-
- 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
-
- 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)
- Mobile Radio Communication Systems (AREA)
Abstract
The invention belongs to the technical field of wireless communication, and particularly relates to a method, a device and a system for selecting an energy-saving base station and an energy-saving mode by self-adaptive identification of O + B domain data and a service scene. The energy-saving base station selection and energy-saving mode selection system with the functions of O + B domain data + service scene self-adaptive identification is disclosed, and is characterized in that: the intelligent energy-saving system comprises a data acquisition module, a service trend prediction module, a service scene recognition module, an intelligent energy-saving output module, an energy-saving scheme scheduling execution module, an execution process monitoring module, a performance monitoring module and an energy-saving proportion adjusting module; the data acquisition module is used for acquiring work parameter data, a mapping map or a network map, O domain performance data, MR data, ticket service data and B domain user package data; and the service trend prediction module intelligently predicts the service trend by using an AI algorithm model according to the utilization rate of the base station and the historical information of the user number.
Description
Technical Field
The invention belongs to the technical field of wireless communication, and particularly relates to a method, a device and a system for selecting an energy-saving base station and an energy-saving mode by self-adaptive identification of O + B domain data and a service scene.
Background
In 2020, more than 70 thousands of 5G basic buildings are established in an accumulative way, and wireless communication networks of various large operators form an 2/3/4/5G multi-system coexistence situation. The stacking of network equipment causes the power consumption to rise year by year, 5G is 2.5 times of the power consumption of a traditional 4G base station due to ultra-dense networking and the use of a special large-scale array active antenna, the proportion of electricity consumption in the expenditure of operators is further improved according to the calculation of the power consumption of a 5G single base station, and well-known experts predict that 20% of the power is consumed in the whole world in 2025 years, so that the energy conservation, the consumption reduction and the network energy efficiency improvement are necessary ways for the sustainable development of the mobile communication industry. In the network operation, the service loads of different base stations are different, the loads of the same base station at different time periods in one day are also different, the wave crest and the wave trough change is presented, if partial resources or all resources of the base station in service idle time can be predicted and closed in advance under the condition of not influencing the network operation quality, the electric energy saved by the whole mobile communication system all the year around is considerable.
At present, the base station saves energy consumption through a plurality of energy saving modes in a certain fixed time period or certain fixed time periods. In the existing energy-saving scheme of the base station, a cell static tide feature library is constructed by performing linear statistics on hourly service load data in historical n × 24 hours, such as: and counting that X days meet high load or Y days meet low load within a certain hour within a period of time, marking different cell time segments into a high-low service feature library, and then extracting a fixed starting point and an end point of the energy-saving time segment according to the state value continuity. When the power-saving starting time is reached, the base station starts all power-saving function modes, and the optimal energy-saving mode is not selected; when the power-saving termination moment is reached, the power-saving mode is terminated, and the energy-saving mode functions of the power-saving start are all closed.
The energy-saving method has the characteristic of good electricity-saving real-time performance. But there are 3 more significant disadvantages: firstly, the identification of a coverage scene of a base station is not obvious, the coverage scene in the base station business parameter data of an operator is seriously depended, and the business scene can not be accurately distinguished through B-domain user subscription data and core network ticket business data; secondly, the lack of predictability is embodied in that a cell feature library is constructed, and cells of one type are collected only when the same time interval is more than a certain number of days in historical n days, so that the prediction of the future service fluctuation of the cells is insufficient; thirdly, after the base station feature library is determined, the energy-saving mode cannot realize hierarchical management, namely the energy-saving mode cannot be used accurately within a 24-hour period all day, and the maximization of the energy-saving amount cannot be realized.
Due to the difference of the coverage scenes of each base station, the influence of the surrounding environment on the traffic is different, and the situation of each time interval cannot be accurately predicted, so that a relatively fixed energy-saving time interval is configured, when the surrounding environment changes or a special date scene or a major holiday scene changes and a service model changes, the electricity-saving time interval is not matched with the actual traffic, the electricity-saving effect is poor, and even the network quality of a user is seriously influenced.
Disclosure of Invention
In view of the problems raised by the background art described above, the present invention has an object to: the method, the device and the system aim at providing the energy-saving base station selection and the energy-saving mode selection of the O + B domain data + service scene self-adaptive identification.
In order to achieve the technical purpose, the technical scheme adopted by the invention is as follows:
1. the energy-saving base station selection and energy-saving mode selection method based on O + B domain data + service scene adaptive identification is characterized in that: the method comprises the following steps:
s1: acquiring work parameter data, a mapping map or a network map, O domain performance data, MR data, ticket service data and B domain user package data through a data acquisition module;
s2: the service trend prediction module uses an AI algorithm model and intelligently predicts the service trend according to the utilization rate of the base station and the historical information of the user number;
s3: the service scene identification module obtains a typical coverage characteristic base station library through association and combination of base station work parameters and map layers, identifies the coverage scenes of the rest base stations through MR coverage association degree, and completes identification of user packages and secondary modification of service data;
the specific operation steps of the method are as follows,
s301: the method comprises the steps that through crawling of a longitude and latitude set of an area covering a typical landmark in a map layer, an algorithm is built to judge that a first batch of sites located in a typical coverage area in base station engineering parameter information are marked with coverage scene labels, and a typical coverage scene feature base station library is built; the map layer comprises a network map and a measuring and drawing layer;
S302: further judging the coverage scenes of base stations around the landmark area according to the coverage labels of the base stations in the landmark area marked in the step S301, and completing coverage collection of the base stations;
s303: in S302, the MR correlation degrees of the remaining base stations and the typical coverage scene base station are correlated, and the coverage scenes of the remaining base stations are obtained according to the sorting of the MR correlation degrees; introducing the service type of a base station or a cell in a core network ticket, wherein the service type of the base station comprises a video service; the B domain user package data of the base station comprises high-grade VIP users; evaluating the user value of the base station or the cell, secondarily correcting the coverage and service scene of the base station, identifying the service scene of the base station, and managing the base station which can be brought into energy-saving prediction;
s4: the intelligent energy-saving output module integrates the network influence and the energy-saving effect of the strategy, constructs a 6-level energy-saving strategy, obtains a grading threshold value through learning, and obtains a selected implementation strategy through a coverage scene and a user value;
s5: the energy-saving scheme scheduling execution module schedules and automatically issues and executes the energy-saving tasks;
the specific operation is as follows:
s501 a: configuring a set of initial values of energy-saving hierarchical management strategy parameters, and setting interval ranges of different service scenes and energy-saving modes, wherein the initial values and the maximum and minimum values of the intervals can be configured;
S502 a: according to a fixed step length, learning threshold values in the energy-saving strategies from small to large from initial values, evaluating energy-saving effects and network performance effect changes of each group of energy-saving strategies, and presetting a certain weight proportion on the energy-saving effects and the network performance;
s503 a: in the learning process, when the energy-saving effect and the network performance evaluation are reduced by 3 continuous step length thresholds, terminating the subsequent threshold learning, and entering S504 a;
s504, 504 a: continuously learning the threshold values in the energy-saving strategies from small to large according to the fixed step length, evaluating the energy-saving effect and the network performance effect change of each group of energy-saving strategies, and stopping the learning process when the energy-saving effect and the network performance evaluation are reduced when 3 step length threshold values are continuously obtained;
s505 a: comprehensively comparing different base station service scenes with energy-saving effect and performance index influence conditions in an energy-saving mode, and selecting an energy-saving management strategy under the optimal effect;
s6: monitoring is carried out through the execution process monitoring module and the performance monitoring module, a scene grading energy-saving strategy model is established, an energy-saving task is manually intervened through the energy-saving proportion adjusting module, the experience of the strategy model is backfilled, and the cell attribute and the strategy are adjusted;
The specific operation is as follows:
s601 a: after the service prediction results of 24 hours all day of the base station and the cell, judging which type of network energy-saving strategy is used by the base station network type param1, then selecting the energy-saving strategy of the use scene according to the judged service scene of the base station, and selecting the available energy-saving mode through the parameter of an energy-saving switch param 2;
s602 a: judging whether the PRB utilization rate, the number of RRC users and the compensation PRB utilization rate meet the threshold values of Thr1, Thr2 and Thr3 or not according to the base station hour granularity service data meeting the effective time period param4 from large to small according to the energy-saving mode weight, and temporarily bringing the time period of the cell into an energy-saving mode meeting the condition if 3 threshold values all meet a certain energy-saving mode; under a certain energy-saving mode, if a certain threshold value is not met, circularly judging the next energy-saving mode until all the modes are judged to be finished, and judging that the time interval is not energy-saving;
s603 a: after the base station or the cell finishes the judging process of S602a 24 hours all day long, judging whether the continuous time period of a certain energy-saving mode of the base station meets the effective duration param3, and if the effective duration param3 is greater than or equal to param3, generating the energy-saving mode and the energy-saving time period of the base station; if the weight value is less than param3, repeating S602a again, and judging the energy-saving mode with relatively small weight value;
S604 a: and after the judgment is finished, generating an energy-saving scheme for the time period meeting the energy-saving condition, and not saving energy for the time period not meeting the condition.
As a preferred scheme of the present invention, in the step S302, the coverage scene of the base stations around the landmark region is determined by determining the correlation between the MR of the surrounding base stations and the coverage of the base stations in the first exemplary coverage feature library; the judging method comprises the following steps:
if A is a base station in a typical coverage feature library and B is a peripheral base station of the base station, acquiring the number of sampling points of which the RSRP in the MR is larger than the Y value when A is used as a B neighboring cell or when B is used as an A neighboring cell in the acquisition of the coverage information of the neighboring cells of the MR, and calculating the proportion of the sampling points of the type to the total MR sampling points of all the neighboring cells when A is used as the B neighboring cell or when B is used as the A neighboring cell to obtain a series of MR correlation degrees of a certain base station and a plurality of typical service coverage scene base stations; the calculation formula is as follows:
the number n of the adjacent cells and the level threshold Y of the adjacent cells can be configured and adjusted according to the actual situation.
The energy-saving base station selection and energy-saving mode selection system comprises a data acquisition module, a service trend prediction module, a service scene recognition module, an intelligent energy-saving output module, an energy-saving scheme scheduling execution module, an execution process monitoring module, a performance monitoring module and an energy-saving proportion adjusting module, wherein each module is used for executing the corresponding steps of the energy-saving base station selection and energy-saving mode selection method of the O + B domain data + service scene self-adaptive recognition.
A device comprises an energy-saving base station selection and energy-saving mode selection system for self-adaptive identification of O + B domain data + service scenes.
The invention has the beneficial effects that:
according to input O-domain base station parameters, historical performance data, MR data, core network user ticket service data and B-domain user account opening data, a network map (mapping map) is combined; intelligently identifying a service scene and predicting a future service trend; combining a scene grading energy-saving strategy to intelligently select an energy-saving base station and an energy-saving mode, and then automatically scheduling and executing a subsequent energy-saving task, and performing all links of monitoring, subsequent performance monitoring and energy consumption evaluation in the process; the intellectualization and the automation of the energy saving of the base station are realized.
The invention discloses a business scene self-adaptive identification energy-saving base station selection and energy-saving mode selection method based on machine learning, which is used for completing training and learning of historical data of at least N24 hours at hundred thousand levels of cells, wherein each cell prediction task in a single process is about 2s, so that the method is more advanced and efficient, the accuracy of prediction data and the accuracy of an intelligent energy-saving task are improved no matter the business scene self-adaptive identification method or the intelligent AI business trend prediction method is adopted, the average error of data verified by the business scene self-adaptive identification energy-saving base station selection and energy-saving mode selection method based on machine learning is about 0.02-0.03%, and the initial accuracy of the energy-saving task is over 93%.
Drawings
The invention is further illustrated by the non-limiting examples given in the accompanying drawings;
fig. 1 is a schematic structural diagram of an embodiment of an energy-saving base station selection and energy-saving mode selection system for adaptive identification of O + B domain data + service scenarios according to the present invention;
FIG. 2 is a schematic view of a full flow of an embodiment of the present invention;
FIG. 3 is a schematic diagram of intelligent service scene recognition according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a hierarchical energy-saving strategy learning according to an embodiment of the present invention;
FIG. 5 is a schematic diagram illustrating a decision flow of an intelligent energy-saving strategy scheme according to the present invention;
Detailed Description
In order that those skilled in the art can better understand the present invention, the following technical solutions are further described with reference to the accompanying drawings and examples.
As shown in fig. 1, the system for selecting an energy-saving base station and an energy-saving mode based on O + B domain data + service scene adaptive identification of the present invention includes a data acquisition module, a service trend prediction module, a service scene identification module, an intelligent energy-saving output module, an energy-saving scheme scheduling execution module, an execution process monitoring module, a performance monitoring module, and an energy-saving ratio adjustment module; each module is used for executing the steps corresponding to the energy-saving base station selection and energy-saving mode selection method of O + B domain data + service scene self-adaptive identification.
As shown in fig. 2, a method for selecting an energy-saving base station and an energy-saving mode for adaptive identification of O + B domain data + service scenario includes the following steps:
s1: acquiring work parameter data, a mapping map or a network map, O domain performance data, MR data, ticket service data and B domain user package data through a data acquisition module;
s2: the service trend prediction module uses an AI algorithm model and intelligently predicts the service trend according to the utilization rate of the base station and the historical information of the user number;
s3: the service scene identification module obtains a typical coverage characteristic base station library through association and combination of base station work parameters and map layers, identifies the coverage scenes of the rest base stations through MR coverage association degree, and completes identification of user packages and secondary modification of service data;
s4: the intelligent energy-saving output module integrates the network influence and the energy-saving effect of the strategy, constructs a 6-level energy-saving strategy, obtains a grading threshold value through learning, and obtains a selected implementation strategy through a coverage scene and a user value;
s5: the energy-saving scheme scheduling execution module schedules and automatically issues and executes the energy-saving tasks;
s6: monitoring is carried out through an execution process monitoring module and a performance monitoring module, a scene grading energy-saving strategy model is established, an energy-saving task is manually intervened through an energy-saving proportion adjusting module, and the strategy model experience is backfilled to optimize the cell attribute and the strategy;
As shown in fig. 3, the specific operation steps of S3 are,
s301: the method comprises the steps that through crawling of a longitude and latitude set of an area covering a typical landmark in a map layer, an algorithm is built to judge that a first batch of sites located in a typical coverage area in base station engineering parameter information are marked with coverage scene labels, and a typical coverage scene feature base station library is built; wherein the map layer comprises a network map or a measuring and drawing layer;
s302: further judging the coverage scenes of the base stations around the landmark area by using the coverage labels of the base stations in the landmark area marked in the step S301 to complete coverage collection of the base stations;
s303: in S302, the MR correlation degrees of the remaining base stations and the typical coverage scene base station are correlated, and the coverage scenes of the remaining base stations are obtained according to the sorting of the MR correlation degrees; introducing the service type of a base station or a cell in a core network ticket, wherein the service type of the base station comprises a video service; the B domain user package data of the base station comprises high-grade VIP users; evaluating the user value of the base station or the cell, secondarily correcting the coverage and service scene of the base station, identifying the service scene of the base station, and managing the base station which can be brought into energy-saving prediction;
in the step S302, the coverage scenes of the base stations around the landmark region are judged by adopting the correlation degree of the MR of the surrounding base stations and the same coverage of the base stations in the first typical coverage feature library; the judging method comprises the following steps:
If A is a base station in a typical coverage feature library and B is a peripheral base station of the base station, acquiring the number of sampling points of which the RSRP in the MR is larger than the Y value when A is used as a B neighboring cell or when B is used as an A neighboring cell in the acquisition of the coverage information of the neighboring cells of the MR, and calculating the proportion of the sampling points of the type to the total MR sampling points of all the neighboring cells when A is used as the B neighboring cell or when B is used as the A neighboring cell to obtain a series of MR correlation degrees of a certain base station and a plurality of typical service coverage scene base stations; the calculation formula is as follows:
the number n of the adjacent cells and the level threshold Y of the adjacent cells can be configured and adjusted according to the actual situation.
As shown in fig. 4, the specific operation of S5 is:
s501 a: configuring a set of initial values of energy-saving hierarchical management strategy parameters, and setting interval ranges of different service scenes and energy-saving modes, wherein the initial values and the maximum and minimum values of the intervals can be configured;
s502 a: according to a fixed step length, learning threshold values in the energy-saving strategies from small to large from initial values, evaluating energy-saving effects and network performance effect changes of each group of energy-saving strategies, and presetting a certain weight proportion on the energy-saving effects and the network performance;
s503 a: in the learning process, when the energy-saving effect and the network performance evaluation are reduced by 3 continuous step length thresholds, terminating the subsequent threshold learning, and entering S504 a;
S504, 504 a: continuing to learn the threshold values in the energy-saving strategies from the beginning to the end of the initial value according to the fixed step length, evaluating the energy-saving effect and the network performance effect change of each group of energy-saving strategies, and terminating the learning process when the energy-saving effect and the network performance evaluation decline when 3 step length threshold values are continuously obtained;
s505 a: and comprehensively comparing the service scenes of different base stations with the energy-saving effect and performance index influence conditions in the energy-saving mode, and selecting an energy-saving management strategy under the optimal effect.
As shown in fig. 5, the specific operations of S6 are:
s601 a: after the service prediction results of 24 hours all day of the base station and the cell, judging which type of network energy-saving strategy is used by the base station network type param1, then selecting the energy-saving strategy of the use scene according to the judged service scene of the base station, and selecting the available energy-saving mode through the parameter of an energy-saving switch param 2;
s602 a: judging whether the PRB utilization rate, the number of RRC users and the compensation PRB utilization rate meet the threshold values of Thr1, Thr2 and Thr3 or not according to the base station hour granularity service data meeting the effective time period param4 from large to small according to the energy-saving mode weight, and temporarily bringing the time period of the cell into an energy-saving mode meeting the condition if 3 threshold values all meet a certain energy-saving mode; under a certain energy-saving mode, if a certain threshold value is not met, circularly judging the next energy-saving mode until all the modes are judged to be finished, and judging that the time interval is not energy-saving;
S603 a: after the base station or the cell finishes the judging process of S602a 24 hours all day long, judging whether the continuous time period of a certain energy-saving mode of the base station meets the effective duration param3, and if the effective duration param3 is greater than or equal to param3, generating the energy-saving mode and the energy-saving time period of the base station; if the weight value is less than param3, repeating S602a again, and judging the energy-saving mode with relatively small weight value;
s604 a: and after the judgment is finished, generating an energy-saving scheme for the time period meeting the energy-saving condition, and not saving energy for the time period not meeting the condition.
A device comprises an energy-saving base station selection and energy-saving mode selection system for self-adaptive identification of O + B domain data and service scenes.
The invention combines network map (mapping map) according to input O-domain base station parameters, historical performance data, MR data, core network user ticket service data, B-domain user account opening data. Intelligently identifying a service scene and predicting a future service trend; and intelligently selecting an energy-saving base station and an energy-saving mode by combining a scene grading energy-saving strategy, and then automatically scheduling and executing a subsequent energy-saving task, and performing all links of monitoring, subsequent performance monitoring and energy consumption evaluation in the process. The intellectualization and the automation of the energy saving of the base station are realized.
The invention discloses a business scene self-adaptive identification energy-saving base station selection and energy-saving mode selection method based on machine learning, which is used for completing training and learning of historical data of at least N24 hours at hundred thousand levels of cells, wherein each cell prediction task in a single process is about 2s, so that the method is more advanced and efficient, the accuracy of prediction data and the accuracy of an intelligent energy-saving task are improved no matter the business scene self-adaptive identification method or the intelligent AI business trend prediction method is adopted, the average error of data verified by the business scene self-adaptive identification energy-saving base station selection and energy-saving mode selection method based on machine learning is about 0.02-0.03%, and the initial accuracy of the energy-saving task is over 93%.
The foregoing embodiments are merely illustrative of the principles of the present invention and its efficacy, and are not to be construed as limiting the invention. Any person skilled in the art can modify or change the above-mentioned embodiments without departing from the spirit and scope of the present invention. Accordingly, it is intended that all equivalent modifications or changes which can be made by those skilled in the art without departing from the spirit and technical spirit of the present invention be covered by the claims of the present invention.
Claims (4)
1. An energy-saving base station selection and energy-saving mode selection method for self-adaptive identification of O + B domain data and service scenes is characterized by comprising the following steps: the method comprises the following steps:
S1: acquiring work parameter data, a mapping map or a network map, O domain performance data, MR data, ticket service data and B domain user package data through a data acquisition module;
s2: the service trend prediction module intelligently predicts the service trend by using an AI algorithm model according to the utilization rate of the base station and the historical information of the user number;
s3: the service scene identification module obtains a typical coverage characteristic base station library through association and combination of base station work parameters and map layers, identifies the coverage scenes of the rest base stations through MR coverage association degree, and completes identification of user packages and secondary modification of service data;
the specific operation steps of the method are as follows,
s301: the method comprises the steps that through crawling of a longitude and latitude set of an area covering a typical landmark in a map layer, an algorithm is built to judge that a first batch of sites located in a typical coverage area in base station engineering parameter information are marked with coverage scene labels, and a typical coverage scene feature base station library is built; the map layer comprises a network map and a measuring and drawing layer;
s302: further judging the coverage scenes of the base stations around the landmark area by using the coverage labels of the base stations in the landmark area marked in the step S301 to complete coverage collection of the base stations;
s303: in S302, the MR correlation degrees of the remaining base stations and the typical coverage scene base station are correlated, and the coverage scenes of the remaining base stations are obtained according to the sorting of the MR correlation degrees; introducing the service type of a base station or a cell in a core network ticket, wherein the service type of the base station comprises a video service; the B domain user package data of the base station comprises high-grade VIP users; evaluating the user value of the base station or the cell, secondarily correcting the coverage and service scene of the base station, identifying the service scene of the base station, and managing the base station which can be brought into energy-saving prediction;
S4: the intelligent energy-saving output module integrates the network influence and the energy-saving effect of the strategy, constructs a 6-level energy-saving strategy, obtains a grading threshold value through learning, and obtains a selected implementation strategy through a coverage scene and a user value;
s5: the energy-saving scheme scheduling execution module schedules and automatically issues and executes the energy-saving tasks;
the specific operation is as follows:
s501 a: configuring a set of initial values of energy-saving hierarchical management strategy parameters, and setting interval ranges of different service scenes and energy-saving modes, wherein the initial values and the maximum and minimum values of the intervals can be configured;
s502 a: according to a fixed step length, learning threshold values in the energy-saving strategies from small to large from initial values, evaluating energy-saving effects and network performance effect changes of each group of energy-saving strategies, and presetting a certain weight proportion on the energy-saving effects and the network performance;
s503 a: in the learning process, when the energy-saving effect and the network performance evaluation are reduced by 3 continuous step length thresholds, terminating the subsequent threshold learning, and entering S504 a;
s504, 504 a: continuously learning the threshold values in the energy-saving strategies from small to large according to the fixed step length, evaluating the energy-saving effect and the network performance effect change of each group of energy-saving strategies, and stopping the learning process when the energy-saving effect and the network performance evaluation are reduced when 3 step length threshold values are continuously obtained;
S505 a: comprehensively comparing different base station service scenes with energy-saving effect and performance index influence conditions in an energy-saving mode, and selecting an energy-saving management strategy under the optimal effect;
s6: monitoring is carried out through the execution process monitoring module and the performance monitoring module, a scene grading energy-saving strategy model is established, an energy-saving task is manually intervened through the energy-saving proportion adjusting module, the experience of the strategy model is backfilled, and the cell attribute and the strategy are adjusted;
the specific operation is as follows:
s601 a: after the service prediction results of 24 hours all day of the base station and the cell, judging which type of network energy-saving strategy is used by the base station network type param1, then selecting the energy-saving strategy of the use scene according to the judged service scene of the base station, and selecting the available energy-saving mode through the parameter of an energy-saving switch param 2;
s602 a: judging whether the PRB utilization rate, the number of RRC users and the compensation PRB utilization rate meet the threshold values of Thr1, Thr2 and Thr3 or not according to the base station hour granularity service data meeting the effective time period param4 from large to small according to the energy-saving mode weight, and temporarily bringing the time period of the cell into an energy-saving mode meeting the condition if 3 threshold values all meet a certain energy-saving mode; under a certain energy-saving mode, if a certain threshold value is not met, circularly judging the next energy-saving mode until all the modes are judged to be finished, and judging that the time interval is not energy-saving;
S603 a: after the base station or the cell finishes the judging process of S602a 24 hours all day long, judging whether the continuous time period of a certain energy-saving mode of the base station meets the effective duration param3, and if the effective duration param3 is greater than or equal to param3, generating the energy-saving mode and the energy-saving time period of the base station; if the weight value is less than param3, repeating S602a again, and judging the energy-saving mode with relatively small weight value;
s604 a: and after the judgment is finished, generating an energy-saving scheme for the time period meeting the energy-saving condition, and not saving energy for the time period not meeting the condition.
2. The method of claim 1, wherein: in the step S302, the coverage scenes of the base stations around the landmark region are judged by adopting the correlation degree of the MR of the surrounding base stations and the same coverage of the base stations in the first typical coverage feature library; the judging method comprises the following steps:
if A is a base station in a typical coverage feature library and B is a peripheral base station of the base station, acquiring the number of sampling points of which the RSRP in the MR is larger than the Y value when A is used as a B neighboring cell or when B is used as an A neighboring cell in the acquisition of the coverage information of the neighboring cells of the MR, and calculating the proportion of the sampling points of the type to the total MR sampling points of all the neighboring cells when A is used as the B neighboring cell or when B is used as the A neighboring cell to obtain a series of MR correlation degrees of a certain base station and a plurality of typical service coverage scene base stations; the calculation formula is as follows:
The number n of the adjacent cells and the level threshold Y of the adjacent cells can be configured and adjusted according to the actual situation.
3. An energy-saving base station selection and energy-saving mode selection system based on the adaptive identification of O + B domain data and service scene in claim 1 is characterized in that: the method comprises a data acquisition module, a service trend prediction module, a service scene recognition module, an intelligent energy-saving output module, an energy-saving scheme scheduling execution module, an execution process monitoring module, a performance monitoring module and an energy-saving proportion adjusting module, wherein each module is used for executing the corresponding steps of the method according to claim 1.
4. An apparatus, characterized by: energy-saving base station selection and energy-saving mode selection system comprising adaptive identification of O + B domain data + service scenarios as claimed in claim 3.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110424578.XA CN113141616B (en) | 2021-04-20 | 2021-04-20 | Method, device and system for selecting energy-saving base station and energy-saving mode through adaptive identification of O + B domain data + service scene |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110424578.XA CN113141616B (en) | 2021-04-20 | 2021-04-20 | Method, device and system for selecting energy-saving base station and energy-saving mode through adaptive identification of O + B domain data + service scene |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113141616A CN113141616A (en) | 2021-07-20 |
CN113141616B true CN113141616B (en) | 2022-07-29 |
Family
ID=76813202
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110424578.XA Active CN113141616B (en) | 2021-04-20 | 2021-04-20 | Method, device and system for selecting energy-saving base station and energy-saving mode through adaptive identification of O + B domain data + service scene |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113141616B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115175288A (en) * | 2022-07-20 | 2022-10-11 | 中国联合网络通信集团有限公司 | Matching method, device and equipment of energy-saving strategy and storage medium |
CN115314909B (en) * | 2022-10-09 | 2022-12-16 | 南通翁海电气有限公司 | Big data-based residential community mobile network base station planning method and system |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101431790A (en) * | 2007-11-09 | 2009-05-13 | 联想(北京)有限公司 | Control method and control device for terminal sleep in relay network |
CN104812035A (en) * | 2015-05-12 | 2015-07-29 | 东南大学 | Method for controlling energy conservation of base station in self-adaptation manner |
CN105357692A (en) * | 2015-09-28 | 2016-02-24 | 北京拓明科技有限公司 | Multi-network cooperative network optimization and energy saving method and system |
CN108200584A (en) * | 2016-12-08 | 2018-06-22 | 中国移动通信集团四川有限公司 | A kind of screening technique and device of WLAN websites yet to be built |
CN109886533A (en) * | 2019-01-07 | 2019-06-14 | 中国联合网络通信集团有限公司 | A kind of analysis method and device of base station construction |
CN109982366A (en) * | 2017-12-28 | 2019-07-05 | 中国移动通信集团河北有限公司 | Target value area analysis method, device, equipment and medium based on big data |
CN111355628A (en) * | 2020-02-12 | 2020-06-30 | 深圳市博瑞得科技有限公司 | Model training method, business recognition device and electronic device |
WO2020215783A1 (en) * | 2019-04-25 | 2020-10-29 | 华为技术有限公司 | Locating method and apparatus, and storage medium |
CN112118617A (en) * | 2020-09-02 | 2020-12-22 | 中国联合网络通信集团有限公司 | Base station energy saving method, device and storage medium |
CN112367700A (en) * | 2020-12-14 | 2021-02-12 | 中国联合网络通信集团有限公司 | Energy-saving control method and device for base station, electronic equipment and storage medium |
CN112566226A (en) * | 2020-12-16 | 2021-03-26 | 北京电信规划设计院有限公司 | Intelligent energy-saving method for 5G base station |
-
2021
- 2021-04-20 CN CN202110424578.XA patent/CN113141616B/en active Active
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101431790A (en) * | 2007-11-09 | 2009-05-13 | 联想(北京)有限公司 | Control method and control device for terminal sleep in relay network |
CN104812035A (en) * | 2015-05-12 | 2015-07-29 | 东南大学 | Method for controlling energy conservation of base station in self-adaptation manner |
CN105357692A (en) * | 2015-09-28 | 2016-02-24 | 北京拓明科技有限公司 | Multi-network cooperative network optimization and energy saving method and system |
CN108200584A (en) * | 2016-12-08 | 2018-06-22 | 中国移动通信集团四川有限公司 | A kind of screening technique and device of WLAN websites yet to be built |
CN109982366A (en) * | 2017-12-28 | 2019-07-05 | 中国移动通信集团河北有限公司 | Target value area analysis method, device, equipment and medium based on big data |
CN109886533A (en) * | 2019-01-07 | 2019-06-14 | 中国联合网络通信集团有限公司 | A kind of analysis method and device of base station construction |
WO2020215783A1 (en) * | 2019-04-25 | 2020-10-29 | 华为技术有限公司 | Locating method and apparatus, and storage medium |
CN111355628A (en) * | 2020-02-12 | 2020-06-30 | 深圳市博瑞得科技有限公司 | Model training method, business recognition device and electronic device |
CN112118617A (en) * | 2020-09-02 | 2020-12-22 | 中国联合网络通信集团有限公司 | Base station energy saving method, device and storage medium |
CN112367700A (en) * | 2020-12-14 | 2021-02-12 | 中国联合网络通信集团有限公司 | Energy-saving control method and device for base station, electronic equipment and storage medium |
CN112566226A (en) * | 2020-12-16 | 2021-03-26 | 北京电信规划设计院有限公司 | Intelligent energy-saving method for 5G base station |
Non-Patent Citations (3)
Title |
---|
5G+AI,智慧运营系统关键能力研发与应用;张乐;《中国无线电》;20200826;全文 * |
5G与AI技术的合作发展方式及应用研究;赵茂伸 等;《电子测试》;20210305;全文 * |
人工智能在5G无线网络中的标准与应用进展;易芝玲;《信息通信技术与政策》;20200915;全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN113141616A (en) | 2021-07-20 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113055903B (en) | Method, apparatus, and medium for power save shutdown of a base station | |
WO2021209024A1 (en) | Energy-saving method, base station, control unit, and storage medium | |
CN113141616B (en) | Method, device and system for selecting energy-saving base station and energy-saving mode through adaptive identification of O + B domain data + service scene | |
CN105636056A (en) | Spectrum resource self-optimization energy-saving method, apparatus and system | |
CN113055990B (en) | Energy saving and consumption reducing method and system for wireless base station based on big data mining and AI scheduling | |
CN103650571B (en) | Performing measurements in a digital cellular wireless telecommunication network | |
Vallero et al. | Greener RAN operation through machine learning | |
CN102917446B (en) | Environmental protection and energy conservation oriented dynamic cell dormancy method | |
CN113891377B (en) | Automatic maintenance and optimization method for 5G small base station equipment | |
Zhu et al. | Joint traffic prediction and base station sleeping for energy saving in cellular networks | |
CN103929752B (en) | Dynamic cooperation covering method between base station | |
CN104822162B (en) | Green base station shunt method and device in a kind of energy mix network | |
Gao et al. | Machine learning based energy saving scheme in wireless access networks | |
CN113573340A (en) | Control method, device, medium and electronic equipment for base station cell | |
CN114339971A (en) | Base station energy-saving control method and device, storage medium and electronic equipment | |
CN105407520B (en) | A kind of centralized base station suspend mode decision-making technique and sleeping system | |
WO2022257670A1 (en) | Base station energy saving method, base station energy saving system, base station, and storage medium | |
CN103139825A (en) | Method, device and base station for dividing limbic users in long term evolution (LTE) system | |
Rumeng et al. | Intelligent energy saving solution of 5G base station based on artificial intelligence technologies | |
CN103327505A (en) | Method and device for determining physical cellular identification | |
CN102595566A (en) | Energy saving concentration resource scheduling method and apparatus thereof | |
CN109660995B (en) | AP intelligent energy-saving control method and device in WiFi system based on machine learning algorithm | |
WO2024021571A1 (en) | Energy saving method, and electronic device and storage medium | |
Wang et al. | A Base Station Sleeping Strategy in Heterogeneous Cellular Networks Based on User Traffic Prediction | |
CN114339962B (en) | Base station energy saving method, device and system |
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 |