CN113055990B - Energy saving and consumption reducing method and system for wireless base station based on big data mining and AI scheduling - Google Patents
Energy saving and consumption reducing method and system for wireless base station based on big data mining and AI scheduling Download PDFInfo
- Publication number
- CN113055990B CN113055990B CN202110394904.7A CN202110394904A CN113055990B CN 113055990 B CN113055990 B CN 113055990B CN 202110394904 A CN202110394904 A CN 202110394904A CN 113055990 B CN113055990 B CN 113055990B
- Authority
- CN
- China
- Prior art keywords
- energy
- saving
- model
- base station
- consumption
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Abstract
The invention relates to the technical field of communication, and discloses a method and a system for saving energy and reducing consumption of a wireless base station based on big data mining and AI scheduling, which are used for improving the accuracy of energy conservation and consumption reduction and mainly comprise the following steps: carrying out big data acquisition and mining on network data of a network; training an energy-saving model based on a model algorithm according to the network data, wherein the energy-saving model is a correlation model of a user behavior model, an energy consumption model and a KPI performance model; and the energy-saving strategy system determines an energy-saving strategy according to the energy-saving model and executes energy-saving operation corresponding to the energy-saving strategy. The invention improves the accuracy of energy conservation and consumption reduction, and can greatly save energy and reduce consumption on the premise of ensuring the network performance.
Description
Technical Field
The invention relates to the technical field of communication, in particular to an energy-saving and consumption-reducing method and system for a wireless base station.
Background
At present, energy saving technology is more a scheme for energy saving and consumption reduction in a communication base station system according to the consumption condition of base station resources and the network coverage condition, and mainly comprises the following steps: the energy saving is controlled according to the time period policy, for example, a start-stop time period of energy saving is set, in which the energy saving operation is performed, the time period being set mainly according to a special period such as working time, rest time, home time, and outgoing time. Although the purpose of energy saving can be achieved to a certain extent by the mode, the energy saving effect is poor because the travel and the work arrangement of each user cannot be known every time.
Application number CN201711491977.8 discloses an energy-saving method, device, equipment and medium for a base station cell, specifically disclosing: acquiring service data of a cell in real time; calculating the service data of the cell at the next moment according to the acquired service data of the cell at the current moment through a pre-established service data model; classifying the cells according to a preset algorithm according to the service data of the cell at the next moment obtained by calculation, and determining the energy-saving class of the cell at the next moment; and controlling the energy-saving time period of the cell according to the energy-saving category of the cell. Although the scheme can predict the service data at the future moment according to the service data model, network data such as user behaviors and network performance are not fully considered, the energy-saving effect and the network performance are difficult to balance, and the accuracy of the energy-saving scheme is poor.
Disclosure of Invention
The invention aims to provide an energy-saving and consumption-reducing method and system of a wireless base station based on big data mining and AI scheduling, so as to balance the performance and energy-saving effect of an energy-saving and consumption-reducing solution.
The technical scheme adopted by the invention for solving the technical problems is as follows: the energy saving and consumption reducing method of the wireless base station based on big data mining and AI scheduling comprises the following steps:
carrying out big data acquisition and mining on network data of a network;
training an energy-saving model based on a model algorithm according to the network data, wherein the energy-saving model is a correlation model of a user behavior model, an energy consumption model and a KPI performance model;
and the energy-saving strategy system determines an energy-saving strategy according to the energy-saving model and executes energy-saving operation corresponding to the energy-saving strategy.
Further, in the energy saving model, the user behavior model is used to indicate a mapping relationship between each time segment in the specified area and the user behavior data, the energy consumption model is used to indicate a mapping relationship between each time segment in the specified area and the base station energy consumption data, and the KPI performance model is used to indicate a mapping relationship between the energy saving parameters and at least one KPI of the network in which the specified area is located.
Further, the designated area is one or more cells.
Further, the energy-saving policy system determines an energy-saving policy according to the energy-saving model, and the method for executing the energy-saving operation corresponding to the energy-saving policy includes:
predicting user behaviors in a future time period according to the user behavior model, predicting base station energy consumption in the future time period according to the energy consumption model, determining an energy-saving strategy according to the predicted user behaviors and the base station energy consumption, and optimizing energy-saving parameters in the energy-saving strategy according to the KPI performance model;
and executing energy-saving operation corresponding to the energy-saving strategy after the energy-saving parameters are optimized on the designated area in the future time period.
Further, the network data includes: user behavior data over historical time periods.
Further, the method for constructing the user behavior model comprises the following steps:
training the neural network by taking each historical time period and corresponding user behavior data as a sample data set to obtain a user behavior model.
Further, the user behavior data includes at least: user access frequency, packet usage size, location mobility, and service slice content.
Further, the network data includes: base station energy consumption data for each historical time period.
Further, the method for constructing the energy consumption model comprises the following steps:
and training the neural network by taking each historical time period and the corresponding base station energy consumption data as sample data sets to obtain an energy consumption model.
Further, the base station energy consumption data at least comprises: base station power, base station current, and base station voltage.
Further, the neural network is a recurrent neural network.
Further, the energy saving strategy at least comprises: AI flow control strategy and time control energy-saving strategy, the AI flow control strategy at least comprises: the method comprises a regional cooperation strategy, a cross-network cooperation strategy and a distribution strategy, wherein the regional cooperation strategy is used for indicating cooperation distribution between adjacent regions, the cross-network cooperation strategy is used for indicating cooperation distribution between different network types, and the distribution strategy is used for indicating cooperation distribution between different frequency bands.
Further, the energy saving operation corresponding to the energy saving strategy at least comprises: symbol off, channel off, and carrier off.
Further, still include: and performing model iterative training on the user behavior model and the energy consumption model according to a preset period and based on the latest obtained user behavior data and the latest obtained base station energy consumption data, and completing the updating of the user behavior model and the energy consumption model.
On the other hand, the invention also provides an energy saving and consumption reduction system of the wireless base station based on big data mining and AI scheduling, which comprises the following steps:
the data processing unit is used for carrying out big data acquisition and mining on network data of a network;
the model training unit is used for training an energy-saving model based on a model algorithm according to the network data, wherein the energy-saving model is a correlation model of a user behavior model, an energy consumption model and a KPI performance model;
and the energy-saving strategy system is used for determining an energy-saving strategy according to the energy-saving model and executing energy-saving operation corresponding to the energy-saving strategy.
The invention has the beneficial effects that: according to the energy saving and consumption reducing method of the wireless base station based on big data mining and AI scheduling, the association model among the user behavior model, the energy consumption model and the KPI performance model is constructed by deeply mining the big data of the network, and the association model can generate the energy saving strategy which meets the mutual balance between the energy saving effect and the KPI performance by analyzing the association among the user behavior, the base station energy consumption and the KPI performance, so that the accuracy of the energy saving and consumption reducing solution is improved, and the energy saving and consumption reducing can be greatly performed on the premise of ensuring the network performance.
Drawings
Fig. 1 is a schematic flowchart of an energy saving and consumption reduction method for a wireless base station based on big data mining and AI scheduling according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of an energy saving and consumption reducing system of a wireless base station based on big data mining and AI scheduling according to an embodiment of the present invention.
Detailed Description
The following describes embodiments of the present invention in detail with reference to examples.
The invention relates to an energy-saving and consumption-reducing method of a wireless base station based on big data mining and AI scheduling, which comprises the following steps: carrying out big data acquisition and mining on network data of a network; training an energy-saving model based on a model algorithm according to the network data, wherein the energy-saving model is a correlation model of a user behavior model, an energy consumption model and a KPI performance model; and the energy-saving strategy system determines an energy-saving strategy according to the energy-saving model and executes energy-saving operation corresponding to the energy-saving strategy.
Firstly, big data acquisition and mining are carried out on historical data such as base station energy consumption and user behaviors, then a user behavior model used for predicting the user behavior model and an energy consumption model used for predicting the base station energy consumption are obtained according to the acquired and mined historical network data training, and a correlation model of the user behavior model, the energy consumption model and a KPI performance model is constructed; when energy-saving operation is required, user behavior and base station energy consumption data in a future time period are respectively predicted through a user behavior model and an energy consumption model, a corresponding energy-saving strategy is determined through the predicted user behavior and base station energy consumption, after the energy-saving strategy is determined in a correlation model, energy-saving parameters in the energy-saving strategy are optimized through a KPI performance model, and an energy-saving area is promoted to achieve the aim of maximizing an energy-saving effect on the premise of ensuring at least one KPI index by means of the cooperation of the three models.
Example 1
The energy saving and consumption reduction method of the wireless base station based on big data mining and AI scheduling, as shown in FIG. 1, includes the following steps:
step S1, collecting and mining big data of network data;
specifically, the network data therein is network data in a designated area, and the designated area may be one or more cells, or all places in a certain area, in this embodiment, big data collection and mining may be performed on service statistical data of a 5G network, 5G test report data, service statistical data of a 4G network, and MR measurement report data, where the 5G network service statistical data includes AAU power consumption, BBU power consumption, user traffic, access performance index, maintenance performance index, and integrity performance index of the designated area. And acquiring user behavior data and base station energy consumption data corresponding to each historical time period according to the acquired and mined network data.
In this embodiment, the user behavior data may include: user access frequency, packet usage size, location mobility, and service slice content. The user access frequency is used for indicating the number of times that user equipment accesses a network in unit time, the data packet usage size is used for indicating the user usage network traffic volume, the location mobility is used for indicating the geographical location change characteristic of the user equipment in a wireless resource environment, the service slice content is used for indicating that network services are classified to form slices, and resources of different slices are given according to service requirements of different services.
In this embodiment, the base station energy consumption data may include: base station power, base station current, and base station voltage. And the energy consumption data of the base station in the area can be reflected through the data such as the electric quantity of the base station, the current of the base station, the voltage of the base station and the like.
Step S2, training an energy-saving model based on a model algorithm according to the network data, wherein the energy-saving model is a correlation model of a user behavior model, an energy consumption model and a KPI performance model;
specifically, the user behavior model is used for indicating a mapping relationship between each time segment in the designated area and user behavior data, the energy consumption model is used for indicating a mapping relationship between each time segment in the designated area and base station energy consumption data, and the KPI performance model is used for indicating a mapping relationship between an energy saving parameter and at least one KPI of a network in which the designated area is located.
In this embodiment, a machine learning algorithm in the AI technology is applied to train an energy-saving model, such as a recurrent neural network.
Specifically, the method for constructing the user behavior model comprises the following steps: training the neural network by taking each historical time period and corresponding user behavior data as sample data sets, namely taking each historical time period as input and taking corresponding user behavior data as output to train the recurrent neural network, and further obtaining a user behavior model. And inputting the future time period into the user behavior model to predict user behavior data corresponding to the time period to be measured in the specified area.
The method for constructing the energy consumption model comprises the following steps: training the neural network by taking each historical time period and the corresponding base station energy consumption data as sample data sets, namely taking each historical time period as input and taking the corresponding base station energy consumption data as output to train the cyclic neural network, thereby obtaining an energy consumption model. And inputting the future time period into the energy consumption model to predict the energy consumption data of the base station corresponding to the time period to be measured in the specified area.
The historical time period and the future time period may be set according to actual conditions, for example, the duration of each time period is 1 hour, 2 hours, 1 day, and the like.
According to different application scenarios, the energy consumption model of the present embodiment may include a region-level energy consumption model, a scene-level energy consumption model, and a cell-level energy consumption model. Wherein. The cell-level energy consumption model is to obtain an energy-saving selection time period according to energy consumption data of a single cell. The scene level energy consumption model is used for giving an energy-saving selection time period according to scene specificity of the geographic position of the cell, the area level energy consumption model is used for constructing a base station cooperative network according to network topological relation among base stations, obtaining cell clusters with close cooperative relation in the base station cooperative network through Glangey causal relation inspection, and finally selecting energy-saving cells in the cell clusters with close cooperative relation.
It can be understood that after the user behavior model and the energy consumption model are constructed, the correlation among the user behavior model, the energy consumption model and the KPI performance model is established, wherein the KPI performance model can be established by performing comparative analysis on KPI indexes before and after energy saving operation is implemented according to history, and the function of the KPI performance model is to avoid the influence of the energy saving operation on the KPI indexes as much as possible and ensure that the user perception is kept above a certain horizontal line while saving energy and reducing consumption.
According to different practical situations, the KPI indicators may include: network connection rate, network disconnection rate, network switching success rate, network traffic and the like.
And step S3, the energy-saving strategy system determines an energy-saving strategy according to the energy-saving model and executes energy-saving operation corresponding to the energy-saving strategy.
In this embodiment, step S3 may specifically include: predicting user behaviors in a future time period according to the user behavior model, predicting base station energy consumption in the future time period according to the energy consumption model, determining an energy-saving strategy according to the predicted user behaviors and the base station energy consumption, and optimizing energy-saving parameters in the energy-saving strategy according to the KPI performance model; and executing the energy-saving strategy after the energy-saving parameters are optimized for the region in the future time period.
Specifically, when energy-saving operation needs to be performed on the specified area, a future time period needing energy saving is input into the user behavior model, so that user behavior data in the future time period can be predicted, a future time period needing energy saving is input into the energy consumption model, so that base station energy consumption data in the future time period can be predicted, the predicted base station energy consumption data can be subjected to error analysis and verification through the predicted user behavior data, if the predicted user behavior data is not matched with the predicted base station energy consumption data, namely the error between the predicted user behavior data and the predicted base station energy consumption data is large, the user behavior model and the energy consumption model can be selected to be reconstructed, prediction of the base station energy consumption data can be performed again, and finally, an energy-saving strategy is determined according to the verified base station energy consumption data.
In this embodiment, the energy saving policy at least includes: AI flow control strategy and time control energy-saving strategy, the AI flow control strategy at least comprises: a regional cooperation strategy, a cross-network cooperation strategy and a distribution strategy, wherein the regional cooperation strategy is used for indicating cooperation distribution between adjacent regions, for example, cooperation distribution between a cell and an adjacent cell; the cross-network cooperation policy is used for indicating cooperation distribution among different network types, for example, cooperation distribution between a 4G network and a 5G network; the shunting strategy is used for indicating the cooperative shunting among different frequency bands. The time control energy-saving strategy specifies the energy-saving operation time period of the target area, for example, during the period of 12: 00-14: 00, the network use requirement is increased due to the change of the user behavior, and then the real-time power supply activation and the cell activation are carried out according to the real-time current monitoring result of the base station, so as to deal with the change of the user behavior.
In order to avoid the influence of energy-saving operation on KPI (key performance indicator) as much as possible, ensure that the user perception is kept above a certain horizontal line while saving energy and reducing consumption, and after an energy-saving strategy is determined, energy-saving parameters are optimized according to a KPI performance model, the realization principle is as follows:
the method comprises the steps that a corresponding energy-saving parameter value range is set for a designated area based on user behavior data predicted by a user behavior model, the energy-saving parameter value range is used for indicating an energy-saving parameter value range which can meet user requirements and achieve the optimal energy-saving effect, in other words, the actual energy consumption of a base station can meet the predicted base station energy consumption requirements and achieve the energy-saving parameter value range in the energy-saving strategy with the optimal solution of at least one KPI in the energy-saving parameter value range as an optimization target, the optimal energy-saving parameter of the energy-saving strategy is obtained, and optimization of the energy-saving parameter is completed.
After the energy-saving parameters are optimized, and when the corresponding future time period comes, the energy-saving strategy after the energy-saving parameters are optimized is executed, specifically, the energy-saving strategy can be issued to each target base station, and after the base station executes the energy-saving strategy, the KPI performance indexes and the energy-saving ratio before and after energy saving can be counted, and the feasibility and the effectiveness of the energy-saving strategy can be evaluated. In this embodiment, the energy saving operation in the energy saving policy may include: symbol off, channel off, and carrier off. For example, activating the factory equipment in the network specifically includes performing cell deactivation (soft-off) through an instruction, thereby reducing the transmission power of the 5G AAU and the 4G RRU, and may further include reducing the standby power by a hardware switching mechanism that performs soft-off and then hard-off.
In order to reflect the latest user behavior and network conditions, the method for saving energy and reducing consumption of a radio base station based on big data mining and AI scheduling according to this embodiment further includes: and performing model iterative training on the user behavior model and the energy consumption model according to a preset period and based on the latest obtained user behavior data and the latest obtained base station energy consumption data, and completing the updating of the user behavior model and the energy consumption model. The data range and the time range of model training can be manually set according to the requirements of an operator.
Based on the above technical solution, the present embodiment further provides an energy saving and consumption reduction system for a wireless base station based on big data mining and AI scheduling, as shown in fig. 2, including:
the data processing unit is used for carrying out big data acquisition and mining on network data of a network;
the model training unit is used for training an energy-saving model based on a model algorithm according to the network data, wherein the energy-saving model is a correlation model of a user behavior model, an energy consumption model and a KPI performance model;
and the energy-saving strategy system is used for determining an energy-saving strategy according to the energy-saving model and executing energy-saving operation corresponding to the energy-saving strategy.
It can be understood that, since the energy saving and consumption reduction system for a radio base station based on big data mining and AI scheduling according to the embodiment of the present invention is a system for implementing the energy saving and consumption reduction method for a radio base station based on big data mining and AI scheduling according to the embodiment, for the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is simple, and for relevant points, reference may be made to the partial description of the method.
Example 2
In this embodiment, after applying the energy saving and consumption reducing method for a wireless base station based on big data mining and AI scheduling to a 5G network in a certain area for inter-network cooperative energy saving operation, the power statistics data are shown in the following table:
it can be seen that after the inter-network cooperative energy saving operation is performed by applying the energy saving and consumption reduction method for the wireless base station based on big data mining and AI scheduling, the average energy saving effect of the 5G network in the area reaches 32.35%.
After the energy saving and consumption reduction method of the wireless base station based on big data mining and AI scheduling is applied to all networks in a certain area, the power statistics data are shown in the following table:
it can be seen that after different data are used to train the energy-saving model, different strategy targets are set, and the energy-saving and consumption-reducing method for the wireless base station based on big data mining and AI scheduling is applied to all networks in a certain area, the average energy-saving effect of the area reaches 64.17%.
In summary, the invention relies on the cooperation of three models, and through the relevance analysis of the user behavior, the base station energy consumption and the KPI performance, an energy-saving strategy which satisfies the mutual balance between the energy-saving effect and the KPI performance can be generated, so that the energy-saving region is promoted to achieve the goal of maximizing the energy-saving effect on the premise of ensuring at least one KPI index, and further, the accuracy of the energy-saving and consumption-reducing solution is improved, so that the energy-saving and consumption-reducing can be performed more greatly on the premise of ensuring the network performance.
Claims (13)
1. The energy saving and consumption reduction method of the wireless base station based on big data mining and AI scheduling is characterized by comprising the following steps:
carrying out big data acquisition and mining on network data of a network;
training an energy-saving model based on a model algorithm according to the network data, wherein the energy-saving model is a correlation model of a user behavior model, an energy consumption model and a KPI performance model; in the energy-saving model, a user behavior model is used for indicating the mapping relation between each time period in a specified area and user behavior data, an energy consumption model is used for indicating the mapping relation between each time period in the specified area and base station energy consumption data, and a KPI performance model is used for indicating the mapping relation between energy-saving parameters and at least one KPI of a network in which the specified area is located;
the energy-saving strategy system determines an energy-saving strategy according to the energy-saving model, and executes energy-saving operation corresponding to the energy-saving strategy, and the method specifically comprises the following steps: predicting user behaviors in a future time period according to the user behavior model, predicting base station energy consumption in the future time period according to the energy consumption model, determining an energy-saving strategy according to the predicted user behaviors and the base station energy consumption, and optimizing energy-saving parameters in the energy-saving strategy according to the KPI performance model; and executing energy-saving operation corresponding to the energy-saving strategy after the energy-saving parameters are optimized on the designated area in the future time period, wherein the turn-off operation in the energy-saving operation at least comprises soft turn-off.
2. The method for saving energy and reducing consumption of a radio base station based on big data mining and AI scheduling of claim 1, wherein the designated area is one or more cells.
3. The method for saving energy and reducing consumption of a radio base station based on big data mining and AI scheduling of claim 1, wherein the network data comprises: user behavior data over historical time periods.
4. The energy saving and consumption reduction method for the wireless base station based on big data mining and AI scheduling as claimed in claim 3, wherein the method for constructing the user behavior model comprises:
training the neural network by taking each historical time period and corresponding user behavior data as a sample data set to obtain a user behavior model.
5. The method as claimed in claim 3 or 4, wherein the user behavior data at least comprises: user access frequency, packet usage size, location mobility, and service slice content.
6. The method for saving energy and reducing consumption of a radio base station based on big data mining and AI scheduling of claim 1, wherein the network data comprises: base station energy consumption data for each historical time period.
7. The method for saving energy and reducing consumption of a wireless base station based on big data mining and AI scheduling as claimed in claim 6, wherein the method for constructing the energy consumption model comprises:
and training the neural network by taking each historical time period and the corresponding base station energy consumption data as sample data sets to obtain an energy consumption model.
8. The method as claimed in claim 6 or 7, wherein the base station energy consumption data at least comprises: base station power, base station current, and base station voltage.
9. The method for saving energy and reducing consumption of a wireless base station based on big data mining and AI scheduling as claimed in claim 4 or 7, wherein the neural network is a recurrent neural network.
10. The method for saving energy and reducing consumption of a wireless base station based on big data mining and AI scheduling as claimed in claim 1, wherein the energy saving strategy at least comprises: AI flow control strategy and time control energy-saving strategy, the AI flow control strategy at least comprises: the method comprises a regional cooperation strategy, a cross-network cooperation strategy and a distribution strategy, wherein the regional cooperation strategy is used for indicating cooperation distribution between adjacent regions, the cross-network cooperation strategy is used for indicating cooperation distribution between different network types, and the distribution strategy is used for indicating cooperation distribution between different frequency bands.
11. The method as claimed in claim 1, wherein the energy saving operation corresponding to the energy saving strategy at least comprises: symbol off, channel off, and carrier off.
12. The method for saving energy and reducing consumption of a radio base station based on big data mining and AI scheduling of claim 1, further comprising: and performing model iterative training on the user behavior model and the energy consumption model according to a preset period and based on the latest obtained user behavior data and the latest obtained base station energy consumption data, and completing the updating of the user behavior model and the energy consumption model.
13. Big data mining and AI scheduling-based energy saving and consumption reduction system for wireless base station, comprising:
the data processing unit is used for carrying out big data acquisition and mining on network data of a network;
the model training unit is used for training an energy-saving model based on a model algorithm according to the network data, wherein the energy-saving model is a correlation model of a user behavior model, an energy consumption model and a KPI performance model; in the energy-saving model, a user behavior model is used for indicating the mapping relation between each time period in a specified area and user behavior data, an energy consumption model is used for indicating the mapping relation between each time period in the specified area and base station energy consumption data, and a KPI performance model is used for indicating the mapping relation between energy-saving parameters and at least one KPI of a network in which the specified area is located;
the energy-saving strategy system is used for determining an energy-saving strategy according to the energy-saving model and executing energy-saving operation corresponding to the energy-saving strategy, and specifically comprises: predicting user behaviors in a future time period according to the user behavior model, predicting base station energy consumption in the future time period according to the energy consumption model, determining an energy-saving strategy according to the predicted user behaviors and the base station energy consumption, and optimizing energy-saving parameters in the energy-saving strategy according to the KPI performance model; and executing energy-saving operation corresponding to the energy-saving strategy after the energy-saving parameters are optimized on the designated area in the future time period, wherein the turn-off operation in the energy-saving operation at least comprises soft turn-off.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010730662.XA CN111918370A (en) | 2020-07-27 | 2020-07-27 | Energy saving and consumption reducing method of wireless base station based on big data mining and AI scheduling |
| CN202010730662X | 2020-07-27 |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113055990A CN113055990A (en) | 2021-06-29 |
| CN113055990B true CN113055990B (en) | 2021-11-30 |
Family
ID=73281480
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010730662.XA Pending CN111918370A (en) | 2020-07-27 | 2020-07-27 | Energy saving and consumption reducing method of wireless base station based on big data mining and AI scheduling |
| CN202110394904.7A Active CN113055990B (en) | 2020-07-27 | 2021-04-13 | Energy saving and consumption reducing method and system for wireless base station based on big data mining and AI scheduling |
Family Applications Before (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010730662.XA Pending CN111918370A (en) | 2020-07-27 | 2020-07-27 | Energy saving and consumption reducing method of wireless base station based on big data mining and AI scheduling |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN111918370A (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116114317A (en) * | 2020-12-14 | 2023-05-12 | 华为技术有限公司 | Communication method, device and system |
| CN112566226B (en) * | 2020-12-16 | 2023-03-17 | 北京电信规划设计院有限公司 | Intelligent energy-saving method for 5G base station |
| CN112866021B (en) * | 2021-01-12 | 2021-11-09 | 中移(成都)信息通信科技有限公司 | AI intelligent energy-saving dynamic control method based on deep reinforcement learning |
| CN115278832A (en) * | 2021-04-30 | 2022-11-01 | 华为技术有限公司 | Energy-saving method and device |
| CN115551055A (en) * | 2021-06-30 | 2022-12-30 | 中国电信股份有限公司 | Energy saving method and system for base station and producer network element |
| WO2023087138A1 (en) * | 2021-11-16 | 2023-05-25 | 株式会社Ntt都科摩 | Network energy consumption management system and method, and storage medium |
| CN116192637A (en) * | 2021-11-29 | 2023-05-30 | 上海华为技术有限公司 | Equipment energy saving method and network equipment |
| CN116209046B (en) * | 2023-04-28 | 2023-07-21 | 浙江省公众信息产业有限公司 | Real-time energy-saving mobile communication method, device, network side equipment and medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101841859A (en) * | 2009-03-20 | 2010-09-22 | 中兴通讯股份有限公司 | Base station state control method and base station energy-saving control system |
| CN103024761A (en) * | 2011-09-26 | 2013-04-03 | 艾默生网络能源有限公司 | Establishing method for energy consumption model of base station, and energy consumption predicating method and device |
| CN108235415A (en) * | 2018-02-07 | 2018-06-29 | 武汉大学 | A kind of base station energy-saving method for considering user experience |
| CN110298488A (en) * | 2019-05-31 | 2019-10-01 | 武汉烽火富华电气有限责任公司 | A kind of multi-energy data analysis method and system based on data mining |
| CN110650518A (en) * | 2018-06-27 | 2020-01-03 | 上海华为技术有限公司 | Energy-saving method and equipment for base station equipment |
| CN111148118A (en) * | 2019-12-18 | 2020-05-12 | 福建省南鸿通讯科技有限公司 | Flow prediction and carrier turn-off method and system based on time sequence |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2721904B1 (en) * | 2011-06-20 | 2016-02-24 | Telefonaktiebolaget LM Ericsson (publ) | Methods and arrangements to save energy consumption in a network node |
| EP2842371B1 (en) * | 2012-04-27 | 2018-01-03 | Nokia Solutions and Networks Oy | Method and apparatus |
| CN103702401B (en) * | 2013-12-17 | 2016-08-17 | 无锡清华信息科学与技术国家实验室物联网技术中心 | Mobile network's power-economizing method based on user behavior analysis |
| US9432901B1 (en) * | 2015-07-24 | 2016-08-30 | Cisco Technology, Inc. | System and method to facilitate radio access point load prediction in a network environment |
| US11252664B2 (en) * | 2018-09-28 | 2022-02-15 | Lg Electronics Inc. | Method and apparatus for entering a connected state with a network for continuing transmission in wireless communication system |
-
2020
- 2020-07-27 CN CN202010730662.XA patent/CN111918370A/en active Pending
-
2021
- 2021-04-13 CN CN202110394904.7A patent/CN113055990B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101841859A (en) * | 2009-03-20 | 2010-09-22 | 中兴通讯股份有限公司 | Base station state control method and base station energy-saving control system |
| CN103024761A (en) * | 2011-09-26 | 2013-04-03 | 艾默生网络能源有限公司 | Establishing method for energy consumption model of base station, and energy consumption predicating method and device |
| CN108235415A (en) * | 2018-02-07 | 2018-06-29 | 武汉大学 | A kind of base station energy-saving method for considering user experience |
| CN110650518A (en) * | 2018-06-27 | 2020-01-03 | 上海华为技术有限公司 | Energy-saving method and equipment for base station equipment |
| CN110298488A (en) * | 2019-05-31 | 2019-10-01 | 武汉烽火富华电气有限责任公司 | A kind of multi-energy data analysis method and system based on data mining |
| CN111148118A (en) * | 2019-12-18 | 2020-05-12 | 福建省南鸿通讯科技有限公司 | Flow prediction and carrier turn-off method and system based on time sequence |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113055990A (en) | 2021-06-29 |
| CN111918370A (en) | 2020-11-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113055990B (en) | Energy saving and consumption reducing method and system for wireless base station based on big data mining and AI scheduling | |
| CN103002459B (en) | A kind of method and apparatus of WCDMA network capacity extensions planning | |
| CN105636056A (en) | Spectrum resource self-optimization energy-saving method, apparatus and system | |
| CN105376089A (en) | Network planning method and device | |
| CN114071661A (en) | Base station energy-saving control method and device | |
| CN113573340A (en) | Control method, device, medium and electronic equipment for base station cell | |
| CN112235804A (en) | Base station remote unit dynamic grouping method and device, and cell networking method and system | |
| CN115422260A (en) | Base station activity analysis method and device, electronic equipment and readable storage medium | |
| WO2018184667A1 (en) | Apparatus and method for performing network optimization | |
| CN114339971A (en) | Base station energy-saving control method and device, storage medium and electronic equipment | |
| CN106998563B (en) | Indoor distribution system early warning method and device based on network performance | |
| CN103596205A (en) | Method and apparatus for determining network states | |
| 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 | |
| CN116209046B (en) | Real-time energy-saving mobile communication method, device, network side equipment and medium | |
| US20130102301A1 (en) | Control apparatus and method, and node apparatus | |
| CN117221987A (en) | Base station energy saving method, base station pool and core network | |
| CN105493543A (en) | Information processing apparatus, radio communication system, and terminal position estimation method | |
| CN104918270A (en) | Wireless network parameter obtaining method, apparatus and terminal | |
| CN115243349A (en) | Base station energy saving method and device, electronic equipment and storage medium | |
| CN103532233B (en) | Based on the power information acquisition abnormity Precise Position System of GPRS technology | |
| CN115086986A (en) | Policy adjustment method and related device | |
| CN104754617A (en) | Wireless network optimization method and device | |
| CN114339962B (en) | Base station energy saving method, device and system | |
| CN103596216A (en) | Method and apparatus for determining cell capacity enhancing capability | |
| WO2022257670A1 (en) | Base station energy saving method, base station energy saving system, base station, and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |