CN117336833A

CN117336833A - Energy-saving time period determining method, device and storage medium

Info

Publication number: CN117336833A
Application number: CN202311302908.3A
Authority: CN
Inventors: 吕婷; 曹亘; 李福昌
Original assignee: China United Network Communications Group Co Ltd
Current assignee: China United Network Communications Group Co Ltd
Priority date: 2023-10-09
Filing date: 2023-10-09
Publication date: 2024-01-02

Abstract

The application provides a method, equipment and storage medium for determining energy-saving time period. Relates to the field of communication. The method comprises the following steps: acquiring a service load predicted value and a predicted error of the energy-saving cell in a preset future time according to a first prediction model; judging whether the prediction error is larger than a preset error threshold value, if so, determining a pre-turn-off time period of the energy-saving cell according to a business load statistic value and an energy-saving threshold value in a preset historical time; if the traffic load is not greater than the preset future time, determining a pre-turn-off time period of the energy-saving cell according to the traffic load predicted value and the energy-saving threshold value in the preset future time; and determining a target energy-saving time period of the energy-saving cell according to the business performance statistic value of the same coverage cell of the energy-saving cell and the pre-turn-off time period. The energy-saving device can solve the problem that the energy-saving effect is not ideal in the prior art.

Description

Energy-saving time period determining method, device and storage medium

Technical Field

The present disclosure relates to the field of communications, and in particular, to a method, an apparatus, and a storage medium for determining an energy saving time period.

Background

With the development of mobile communication networks, the energy consumption of wireless networks is increasing, and the requirements of operators for energy conservation and consumption reduction are urgent. In the energy consumption constitution of the wireless network, the energy consumption ratio of the base station equipment is the highest, the base station energy saving is the basis of the wireless network energy saving, and the base station energy saving technology is also a research hot spot in the industry. The cell shutdown technology is mainly used in a scene that a plurality of base stations are simultaneously covered in the same area, wherein one base station is used as a basic coverage layer base station, and other base stations are planned as capacity layer base stations. When the service load of a base station of a certain capacity layer is lower, all radio frequency channels of the base station are turned off so as to achieve the purpose of energy conservation; and the base station of the basic coverage layer is in a normal working state and is used for providing network service for the UE in the area.

In order to reduce the energy consumption of the base station equipment, the industry proposes energy-saving technologies such as cell shutdown and the like, and the basic principle is that when the cell service load is smaller than a preset shutdown threshold value, part of hardware resources of the base station are shut down, so that the energy consumption of the base station is reduced, and the energy-saving effect is achieved.

In the prior art, a time period in which a service load predicted value is smaller than a preset threshold value is generally determined as an energy-saving time period based on cell service load prediction, and an energy-saving effect is achieved by enabling an energy-saving cell to enter an off state in the energy-saving time period; the inaccuracy of the service load predicted value often reduces the turn-off time length and influences the energy-saving effect because the cells are not turned off in time; therefore, the existing energy-saving period determining method may affect the service performance and energy-saving effect of the energy-saving area; the invention further provides a method, equipment and storage medium for determining the energy-saving time period.

Disclosure of Invention

The application provides an energy-saving time period determining method, energy-saving time period determining equipment and a storage medium, which are used for solving the problem that an energy-saving effect is not ideal in the prior art.

In a first aspect, the present application provides a method for determining a power saving period,

the energy-saving management module is used for managing a plurality of cells in a preset area, wherein the cells comprise energy-saving cells, and the method comprises the following steps:

Acquiring a service load predicted value and a predicted error of the energy-saving cell in a preset future time according to a first prediction model;

judging whether the prediction error is larger than a preset error threshold value, if so, determining a pre-turn-off time period of the energy-saving cell according to a business load statistic value and an energy-saving threshold value in a preset historical time; if the traffic load is not greater than the preset future time, determining a pre-turn-off time period of the energy-saving cell according to the traffic load predicted value and the energy-saving threshold value in the preset future time;

and determining a target energy-saving time period of the energy-saving cell according to the business performance statistic value of the same coverage cell of the energy-saving cell and the pre-turn-off time period.

In one possible design, the preset historical time includes a plurality of preset energy-saving periods before the current time, and the preset energy-saving periods include a plurality of preset periods; the determining the target energy-saving time period of the energy-saving cell according to the preset historical time business load statistic value and the energy-saving threshold value comprises the following steps:

acquiring continuous T low-load time periods as candidate energy-saving time periods; the low-load time period is a preset period in which the service load statistical value is smaller than the energy-saving threshold value;

And determining any N continuous preset periods in the candidate energy-saving time period as a pre-turn-off time period.

In one possible design, the preset future time includes a preset energy saving period after the current time, the preset energy saving period including a plurality of preset periods; the determining the target energy-saving time period of the energy-saving cell according to the preset predicted value of the service load in the future time and the energy-saving threshold value comprises the following steps:

acquiring continuous T low-load time periods as candidate energy-saving time periods; the low-load time period is a preset period in which the predicted value of the service load is smaller than the energy-saving threshold value;

In one possible design, the determining the target energy saving time period of the energy saving cell according to the service performance statistics of the same coverage cell of the energy saving cell and the pre-turn-off time period includes:

acquiring a service performance statistic value of the same coverage cell of the energy-saving cell in the pre-turn-off time period in a first preset energy-saving period as a first statistic value, wherein the service performance comprises one of a call completing rate, a switching success rate, a service transmission instantaneity and a service transmission rate, and the service transmission instantaneity is the inverse of a service transmission time delay;

In the same coverage cell of the energy-saving cell, if the same coverage cell with the first statistic value smaller than the corresponding preset service threshold value does not exist; determining a target energy-saving time period as the pre-turn-off time period in a second preset energy-saving period; the first preset energy-saving period is the first preset energy-saving period after the current time; the second preset period is a second preset energy-saving period after the current time or any one of the preset energy-saving periods after the current time.

In one possible design, the energy-saving cell has at least one of the same coverage cells, and before the determining whether the prediction error is greater than a preset error threshold, the method further includes:

determining the same coverage cell of the energy-saving cell in a plurality of cells in the preset area;

for each same coverage cell, determining a service load threshold of the same coverage cell according to a service performance threshold of the same coverage cell, and acquiring the available capacity of the same coverage cell according to the difference between the service load threshold and the service load average value of the same coverage cell;

acquiring the sum of the available capacities according to the sum of the available capacities of all the cells covered by the same cover, and determining the minimum value in the preset value of the sum of the available capacities as an energy-saving threshold value of the energy-saving cell;

In one possible design, the determining the traffic load threshold according to the traffic performance threshold of the same coverage cell includes:

performing function fitting on the business load statistic value of the preset historical time of the same coverage cell and the business performance according to a second prediction model to obtain a fitting function of the business performance-business load of the same coverage cell;

inputting a preset service performance threshold according to the fitting function, and acquiring a service load threshold of the same coverage cell; the preset service performance threshold is a minimum value of service performance parameters acceptable by the same coverage cell; the service performance comprises one of a call completing rate, a switching success rate, a service transmission real-time property and a service transmission rate, wherein the service transmission real-time property is the inverse of a service transmission time delay.

In one possible design, the obtaining, according to a first prediction model, a traffic load predicted value and a predicted error of the energy-saving cell in a preset future time includes:

inputting the preset future time into a trained first prediction model to obtain a service load predicted value output by the first prediction model, wherein the first prediction model comprises one of ARIMA, PROPHET, LSTM and a neural network model;

And acquiring one of a mean square error, a root mean square error, an average absolute error and an average absolute relative error of the first prediction model as the prediction error.

In one possible design, before the obtaining, according to the first prediction model, a traffic load predicted value and a predicted error of the energy-saving cell in a preset future time, the method further includes:

acquiring performance data of each cell in the preset area in the preset historical time, wherein the historical performance data comprises one or more of a call completing rate average value, a switching success rate average value, a service transmission real-time average value, a service transmission rate average value, a service load average value and an energy consumption average value of a base station where the cell is located, and the service load comprises any one of PRB (resource utilization), RRC (radio resource control) connection number and traffic;

determining the ratio of the first average value to the second average value as a turn-off weight; wherein the first average value is the energy consumption average value; the second average value is one or more weighted average values of the call completing rate average value, the switching success rate average value, the service transmission real-time average value and the service load average value;

And determining that the cell with the turn-off weight larger than a preset turn-off threshold is the energy-saving cell.

In a second aspect, the present application provides an energy-saving time period determining apparatus for managing a plurality of cells within a preset area, where the plurality of cells includes an energy-saving cell, the apparatus including:

the acquisition module is used for acquiring a service load predicted value and a predicted error of the energy-saving cell in a preset future time according to a first predicted model;

the judging module is used for judging whether the prediction error is larger than a preset error threshold value, and if so, determining a pre-turn-off time period of the energy-saving cell according to a service load statistic value and an energy-saving threshold value in a preset historical time; if the traffic load is not greater than the preset future time, determining a pre-turn-off time period of the energy-saving cell according to the traffic load predicted value and the energy-saving threshold value in the preset future time;

and the determining module is used for determining a target energy-saving time period of the energy-saving cell according to the business performance statistic value of the same coverage cell of the energy-saving cell and the pre-turn-off time period.

In one possible design, the preset historical time includes a plurality of preset energy-saving periods before the current time, and the preset energy-saving periods include a plurality of preset periods; the judging module is specifically configured to:

In one possible design, the preset future time includes a preset energy saving period after the current time, the preset energy saving period including a plurality of preset periods; the judging module is specifically configured to:

In one possible design, the determining module is specifically further configured to:

In one possible design, the acquisition module is specifically further configured to:

In a third aspect, the present application provides an electronic device, comprising: a processor, and a memory communicatively coupled to the processor;

the memory stores computer-executable instructions;

The processor executes the computer-executable instructions stored in the memory to implement a method for determining a power saving time period as described above.

In a fourth aspect, the present application provides a computer-readable storage medium having stored therein computer-executable instructions that, when executed by a processor, are configured to implement a power saving time period determination method as described above.

According to the energy-saving time period determining method, the energy-saving time period determining device and the storage medium, different energy-saving strategies are dynamically selected based on the accuracy of service load prediction to determine the energy-saving time period, the energy-saving time period can be matched with the cell low service load time period, the problems of error shutdown or shutdown duration reduction and the like caused by inaccurate service load prediction can be avoided, the accuracy of energy-saving time period determination is improved, the energy-saving effect is improved, and the service performance of an energy-saving area is guaranteed.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.

Fig. 1 is an application scenario schematic diagram of a method for determining an energy-saving time period according to an embodiment of the present application;

fig. 2 is a schematic flow chart of a method for determining an energy saving time period according to an embodiment of the present application;

fig. 3 is a second schematic flow chart of a method for determining an energy-saving time period according to an embodiment of the present application;

fig. 4 is a schematic flow chart of S320 in a method for determining an energy saving time period according to an embodiment of the present application;

fig. 5 is a schematic structural diagram of an energy-saving time period determining device according to an embodiment of the present application;

fig. 6 is a schematic hardware structure of an electronic device according to an embodiment of the present application.

Detailed Description

Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples are not representative of all implementations consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present application, rather than all embodiments, as detailed in the accompanying claims. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.

It should be noted that, in the embodiments of the present application, words such as "exemplary" or "such as" are used to denote examples, illustrations, or descriptions. Any embodiment or design described herein as "exemplary" or "for example" should not be construed as preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "such as" is intended to present related concepts in a concrete fashion.

It should be noted that the terms "first," "second," "third," "fourth," and the like in the description and claims of the invention and in the above figures, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented, for example, in sequences other than those illustrated or otherwise described herein.

The term "at … …" in the embodiment of the present application may be instantaneous when a certain situation occurs, or may be a period of time after a certain situation occurs, which is not particularly limited in the embodiment of the present application.

Fig. 1 is an application scenario schematic diagram of a method for determining an energy saving time period according to an embodiment of the present application, as shown in fig. 1, where a preset area is any area in a network, and includes one or more cells in the preset area, each cell is covered with a network device (base station) where the cell is located, each cell manages one or more terminals (UEs), and an energy saving management end performs information interaction with each network device to obtain data such as configuration data, historical performance data, measurement reports, handover data, service load and the like of the cell.

The energy-saving management end is used for determining an energy-saving cell and a corresponding energy-saving period in a preset area, and can be integrated in any one of a base station, a base station operation maintenance platform and core network equipment in the preset area, or can be positioned in an independent physical entity; a message interaction interface exists between each base station in the preset area;

according to the method provided by the embodiment, different energy-saving strategies are dynamically selected based on the accuracy of the traffic load prediction to determine the energy-saving time period, so that the energy-saving time period can be matched with the cell low traffic load time period, the problems of wrong turn-off or decrease of turn-off duration and the like caused by inaccurate traffic load prediction can be avoided, the accuracy of determining the energy-saving time period is improved, the energy-saving effect is improved, and the service performance of an energy-saving area is ensured.

A method for determining an energy saving time period according to an embodiment of the present application will be described in detail with reference to the accompanying drawings.

Fig. 2 is a schematic flow chart of a method for determining an energy saving time period according to an embodiment of the present application; as shown in fig. 2, the method is used for an energy-saving management end, and the energy-saving management module is used for managing a plurality of cells in a preset area, wherein the plurality of cells comprise energy-saving cells, and the method comprises the following steps:

s210, acquiring a service load predicted value and a predicted error of an energy-saving cell in a preset future time according to a first prediction model;

specifically, the preset future time includes a preset energy-saving period after the current time, and the preset energy-saving period includes a plurality of preset periods; the method comprises the steps of taking a traffic load statistical value in a preset historical time as a training set to train a first model after the first model training is completed, and predicting a preset future time by using the first model training to obtain a traffic load predicted value and a prediction error.

S220, judging whether the prediction error is larger than a preset error threshold value, and if so, determining a pre-turn-off time period of the energy-saving cell according to the service load statistic value and the energy-saving threshold value in the preset historical time; if the traffic load is not greater than the preset traffic load predicted value and the energy-saving threshold value in the future time, determining a pre-turn-off time period of the energy-saving cell;

Specifically, the prediction error is used for indicating the accuracy of the prediction method, different energy-saving strategies are dynamically selected based on the accuracy of the prediction of the service load to determine an energy-saving period, and if the prediction error is greater than a preset error threshold, a pre-shutdown period of the energy-saving cell is determined according to the service load statistic value and the energy-saving threshold in a preset history time; if the traffic load is not greater than the preset traffic load predicted value and the energy-saving threshold value in the future time, determining a pre-turn-off time period of the energy-saving cell; and further judging the pre-turn-off time period to determine the target energy-saving time period of the energy-saving cell.

S230, determining a target energy-saving time period of the energy-saving cell according to the business performance statistic value and the pre-turn-off time period of the same coverage cell of the energy-saving cell.

Specifically, the service performance of the same coverage cell comprises one of a call completing rate, a switching success rate, a service transmission instantaneity and a service transmission rate, wherein the service transmission instantaneity is the inverse of a service transmission time delay; the target energy-saving time period is dynamically determined according to the service performance requirements of the same coverage cell, and the low-load time period meeting the service performance requirements is determined as the target energy-saving time period, so that the service performance in the energy-saving area after the energy-saving cell is turned off is ensured while energy is saved.

According to the method, according to the service load prediction accuracy of the energy-saving cell, different energy-saving strategies are adopted to determine target energy-saving time periods respectively, and after the energy-saving management end determines the target energy-saving time periods corresponding to the energy-saving cell, information of the target energy-saving time periods is sent to the energy-saving cell in a message sending mode; the energy-saving cell can periodically enter the turn-off state in a plurality of future energy-saving periods to achieve the energy-saving effect, the problems of error turn-off or decrease of turn-off duration and the like caused by inaccurate service load prediction can be avoided, the energy-saving effect can be improved, and the service performance in the energy-saving area can be guaranteed.

Fig. 3 is a second schematic flow chart of a method for determining an energy-saving time period according to an embodiment of the present application; as shown in fig. 3, the method is used for an energy-saving management end, and the energy-saving management module is used for managing a plurality of cells in a preset area, wherein the plurality of cells comprise energy-saving cells, and the method comprises the following steps:

s310, determining an energy-saving cell in a plurality of cells in a preset area;

as an example: determining according to performance data of historical time preset by a plurality of cells; the method specifically comprises the following steps:

a. acquiring performance data of each cell in a preset area at preset historical time, wherein the historical performance data comprises one or more of a call completing rate average value, a switching success rate average value, a service transmission real-time average value, a service transmission rate average value, a service load average value and an energy consumption average value of a base station where the cell is located; wherein, the service load comprises any one of PRB resource utilization rate, RRC connection number and traffic;

b. Determining the ratio of the first average value to the second average value as a turn-off weight; the first average value is an energy consumption average value; the second average value is one or more weighted average values of a call completing rate average value, a switching success rate average value, a service transmission real-time average value, a service transmission rate average value and a service load average value;

c. and determining the cell with the turn-off weight larger than the preset turn-off threshold as the energy-saving cell.

For example, taking a service transmission rate and a service transmission real-time parameter mean value as an example, a calculation method of a combined value of a plurality of parameters is described:

the combined value of the service transmission rate average value and the service transmission real-time parameter average value can be defined as (service transmission rate average value/preset rate value), (service transmission real-time parameter average value/preset time value), or a (service transmission rate average value/preset rate value) +b (service transmission real-time parameter average value/preset time delay value), wherein a and b are weighting coefficients, and the value is 0-1, and a+b=1;

as another embodiment, a power-saving cell is determined according to preset configuration data, and a cell with the preset configuration data as a specified value is determined as a power-saving cell in a preset area; the preset configuration data comprises one or more of preset energy-saving attributes, preset frequency bands and preset network modes. The preset energy-saving attribute comprises a turn-off state and a turn-off state, the preset frequency band is a certain preset frequency band, and the preset network modes comprise 3G, 4G, 5G and other network modes.

According to the embodiment, the energy-saving cell is determined according to the cell configuration data, and the cells of a specified frequency band and a network system can be turned off preferentially or certain specified cells are not allowed to be turned off so as to meet the differentiated energy-saving requirement; the energy-saving cell is determined according to the historical performance data, and the cell with high energy consumption, poor service performance and low load can be determined as the energy-saving cell to be turned off preferentially, so that the total energy consumption of a preset area can be reduced, and the service performance can be improved.

S320, determining an energy-saving threshold according to the service performance of the same coverage cell of the energy-saving cell;

specifically, if the energy-saving threshold corresponding to the energy-saving cell is preset in the base station where the energy-saving cell is located, the energy-saving management end can acquire the energy-saving threshold through message interaction with the base station where the energy-saving cell is located;

specifically, the purpose of setting the energy-saving threshold is to enable the same coverage cell to completely accept the service to be migrated in the energy-saving cell when the energy-saving cell is in the target energy-saving time period, so as to ensure the service performance requirement of the energy-saving area after the energy-saving cell is turned off; and the occurrence of migration failure is avoided.

Further, as a preferred embodiment, fig. 4 is a schematic flow chart of S320 in a method for determining an energy saving time period according to an embodiment of the present application; as shown in fig. 4, S320 specifically includes:

S321, determining the same coverage cell of the energy-saving cell in a plurality of cells in a preset area;

specifically, when the energy-saving cell enters the energy-saving cell and enters the target energy-saving period, the same coverage cell is used for receiving the cell of the terminal in the energy-saving cell, and the method for determining the same coverage cell comprises the following steps: determining the same coverage cell corresponding to the energy-saving cell according to any one of the industrial parameter (method one), the measurement report (method two) and the switching data (method three) of each cell, wherein:

the method comprises the following steps: determining the same coverage cell according to the industrial parameters:

specifically, the industrial parameter information of each cell includes longitude and latitude, azimuth angle and other information of the base station where the cell is located, and can be preset in the energy-saving management end; the distance between two cells can be calculated according to the longitude and latitude of the base station;

if the distance between the energy-saving cell and the base station (network equipment) where a certain neighboring cell of the energy-saving cell is located is smaller than a preset distance threshold value and the difference of azimuth angles is smaller than a preset angle threshold value, determining the neighboring cell as the same coverage cell corresponding to the energy-saving cell;

the second method is as follows: determining the same coverage cell according to the measurement report:

the measurement reports are generated by the terminal measurement and sent to the base station, and each measurement report comprises information such as the signal strength of the energy-saving cell and the adjacent cell;

Acquiring a plurality of measurement reports of a plurality of terminals which are accessed into an energy-saving cell in a preset historical time, wherein each measurement report carries the signal strength of the energy-saving cell and other adjacent cells;

if the difference value between the signal intensity of a certain neighbor cell and the signal intensity of the energy-saving cell is smaller than a preset threshold value, determining the measurement report as a target measurement report corresponding to the neighbor cell;

if the ratio of the number of the target measurement reports corresponding to a certain neighbor cell to the total number of the measurement reports is larger than a preset value, determining the neighbor cell as the same coverage cell of the energy-saving cell;

and a third method: determining the same coverage cell according to the switching data:

acquiring switching data of an energy-saving cell in a preset historical time, and if a source cell or a target cell in a certain piece of switching data comprises a certain neighbor cell, determining the switching data as target switching data of the neighbor cell; if the ratio of the number of the target switching data corresponding to a certain neighbor cell to the total number of the switching data of the energy-saving cells is larger than a preset value, determining the neighbor cell as the same coverage cell of the energy-saving cells;

the execution main body of the steps can be an energy-saving management end or network equipment where an energy-saving cell is located; if the execution main body is an energy-saving management end, the energy-saving management end acquires switching data of the energy-saving cell in a preset history time through information interaction with network equipment where the energy-saving cell is located; if the execution subject is the network equipment of the energy-saving cell, the network equipment of the energy-saving cell determines the same coverage cell and then sends the same coverage cell information to the energy-saving management end in a mode of sending a message to the energy-saving management end.

S322, determining a service load threshold value of the same coverage cell according to the service performance threshold value of the same coverage cell for each same coverage cell, and acquiring the available capacity of the same coverage cell according to the difference value between the service load threshold value and the service load average value of the same coverage cell;

specifically, performing function fitting on a service load statistical value and service performance of a preset historical time of the same coverage cell according to a second prediction model to obtain a fitting function of the service performance-service load of the same coverage cell; inputting a preset service performance threshold according to the fitting function, and acquiring a service load threshold of the same coverage cell; the preset service performance threshold is a minimum value of service performance parameters acceptable by the same coverage cell; the service performance comprises one of a call completing rate, a switching success rate, a service transmission real-time property and a service transmission rate, wherein the service transmission real-time property is the inverse of a service transmission time delay;

further, the second prediction model adopts the existing random forest, xgboost and other algorithm models, acquires a plurality of service load statistic values and corresponding service performances in a preset historical time as a training set to train the second prediction model, and the acquired trained second prediction model is a fitting function of the service performance-service load of the same coverage cell and is used for reflecting the functional relation between the service performance and the service load value.

Further, the service performance threshold is the minimum value of the tolerable service performance parameters of the same coverage cell, and can be preset in the affiliated base station, and the service load average value is defined as the average value of a plurality of service load statistical values in the preset historical time. The available capacity of the same coverage cell is used to indicate the currently most admissible traffic load of that cell.

Alternatively, the available capacity of the same coverage cell may be obtained by the same coverage cell or the network device where the same coverage cell is located according to the step and sent to the energy-saving management end, or may be obtained by the energy-saving management end through the method.

S323, obtaining the sum of the available capacities according to the sum of the available capacities of all the same coverage cells, and determining the minimum value in the preset value of the sum of the available capacities as an energy-saving threshold value of the energy-saving cell;

specifically, if the available capacity is obtained by the coverage cells, receiving an available capacity indication message sent by each coverage cell, wherein the available capacity indication message carries the same coverage cell identifier and the available capacity information of the cell;

further, the sum of the available capacities of all the same coverage cells of the energy-saving cell is obtained, namely the available capacity which can be migrated when the energy-saving cell enters the target energy-saving time period.

S324, the minimum value of the sum of the available capacity and the traffic load threshold values of all the same coverage cells is determined as the energy-saving threshold value of the energy-saving cell.

Specifically, the preset value is an initial energy-saving threshold value preset in the base station where the energy-saving cell is located, namely, the maximum value of the energy-saving threshold value when the service performance requirement of the energy-saving cell is met; if the energy saving threshold of the cell is set to be larger than the preset value, when the service load of the cell is smaller than the energy saving threshold, shutting down the cell will cause service performance deterioration;

in the method, the energy-saving threshold value is determined based on the available capacity information interacted with the coverage cells, so that the available capacity of the coverage cells meets the service migration requirement under the energy-saving cells, the service load of the energy-saving cells can be completely migrated to other coverage cells after the energy-saving cells are closed, the problems of insufficient capacity, service migration failure and the like of the coverage cells are avoided, and the service performance of the energy-saving area after the cells are closed is ensured.

S330, inputting a preset future time into a trained first prediction model to obtain a service load predicted value output by the first prediction model, wherein the first prediction model comprises one of ARIMA, PROPHET, LSTM and a neural network model; one of a Mean Square Error (MSE), a Root Mean Square Error (RMSE), a Mean Absolute Error (MAE), and a mean absolute relative error (MAPE) of the first prediction model is obtained as a prediction error.

Specifically, a service load statistical value of a plurality of preset periods of each cell in a preset history time is obtained as a training set, the preset history time comprises a plurality of preset energy-saving periods, and the preset history time is 24 x 7 hours, the preset energy-saving period is 24 hours, and the preset period is 15 minutes as an example; training through the first prediction model to obtain a trained first prediction model; and inputting the preset future time into the trained first prediction model to obtain a service load predicted value of the first prediction model output the preset future time, wherein the service load predicted value of the preset future time is a service load predicted value of a preset energy-saving period after the current time.

Specifically, the prediction error is used for reflecting the deviation between the predicted value and the actual value of the service load so as to evaluate the accuracy of time sequence prediction, and the prediction error can be determined according to sample data in a preset historical time; dividing sample data into training data in a first historical time and verification data in a second historical time, wherein the first historical time and the second historical time are a period of time in a preset historical time and are not overlapped in time; training the prediction model according to the training data, obtaining a predicted value corresponding to the second historical time, and determining the deviation between the predicted value and the true value according to the verification data in the second historical time.

For example, if the prediction error is determined according to the Mean Absolute Percentage Error (MAPE), the prediction error is:

wherein,representing predicted value, y _i Representing a true value, n representing the number of data contained in the verification data;

s340, judging whether the prediction error is larger than a preset error threshold value, and if so, executing S350; if not, executing S360;

specifically, whether the prediction error is greater than a preset error threshold value is judged, if so, the accuracy and the reliability of the obtained predicted value service load predicted value are not high, the predicted value cannot be used as a basis for determining the pre-turn-off time, and the pre-turn-off time period of the energy-saving cell is determined according to the service load statistical value and the energy-saving threshold value in the preset history time, and the specific method is specifically described in S340;

further, if not greater than the preset threshold, determining that the obtained predicted value service load predicted value can be used as a basis for determining the pre-turn-off time, and determining a pre-turn-off time period of the energy-saving cell according to the predicted value of the service load and the energy-saving threshold in the preset future time, wherein the specific method is specifically described in S350;

s350, acquiring continuous T low-load time periods as candidate energy-saving time periods; the low load time period is a preset period in which the service load statistical value is smaller than the energy-saving threshold value; and determining any N continuous preset periods in the candidate energy-saving time period as a pre-turn-off time period. And then S370 is performed.

Specifically, the preset historical time includes a plurality of preset energy-saving periods before the current time, and the preset energy-saving periods include a plurality of preset periods;

optionally, the service load statistics value may be a service load statistics value of a plurality of preset periods in a preset energy-saving period before the present time, or may be an average value of service load statistics values of a plurality of preset periods in a preset energy-saving period before the present time;

for example, for a certain preset period, acquiring a service load statistical value of a certain preset period in a preset energy-saving period of the current time, if the service load statistical value is smaller than an energy-saving threshold value, determining that the corresponding preset period in a preset energy-saving period in the future of the current time is a low-load time period;

for another example, for a certain preset period, acquiring a service load statistical value of a certain preset period in a plurality of preset energy-saving periods before the current time, and acquiring a plurality of service load statistical values of the preset period; and acquiring the average value of the service load statistical values of a plurality of preset periods, and if the average value of the service load statistical values is smaller than the energy-saving threshold value, determining that the corresponding preset period in a preset energy-saving period in the future of the current time is the low-load time period.

Illustratively, the preset energy saving period is 24 hours and the preset period is 15 minutes;

further, T is the number of low-load time periods included in the candidate energy-saving time period; n is the number of preset periods contained in the pre-turn-off time period, N is less than or equal to T, and the pre-turn-off time period can be located at any position in the candidate energy-saving time period. N is a preset number or the product of a preset ratio and T, and the preset ratio is not more than 1;

s360, obtaining continuous T low-load time periods as candidate energy-saving time periods; the low load time period is a preset period in which the predicted value of the service load is smaller than the energy-saving threshold value; and determining any N continuous preset periods in the candidate energy-saving time period as a pre-turn-off time period. And then S370 is performed.

Specifically, according to the service load predicted values of a plurality of preset periods in the future period acquired in the method of S330, if the service load predicted value is smaller than the energy-saving threshold, the preset period of the preset future time of the service load predicted value is the low-load time period.

Specifically, other steps in this step are similar to S350, and will not be described in detail.

S370, acquiring a service performance statistic value of a same coverage cell of an energy-saving cell in a pre-turn-off time period in a first preset energy-saving period as a first statistic value, wherein the service performance comprises a connection rate, a switching success rate, a service transmission real-time property and a service transmission rate, and the service transmission real-time property is one of the inverse of a service transmission time delay; in the same coverage cell of the energy-saving cell, if the same coverage cell with the first statistic value smaller than the corresponding preset service threshold value does not exist; and determining the target energy saving time period as a pre-turn-off time period in a second preset energy saving period.

The first preset energy-saving period is the first preset energy-saving period after the current time; the second preset period is a second preset energy-saving period after the current time or any preset energy-saving period after the current time;

specifically, after determining a pre-turn-off period, entering a turn-off state, and in the turn-off state, obtaining first statistics values of all same coverage cells for all same coverage cells of the energy-saving cell, wherein the first statistics values are service performance statistics values of the same coverage cell in a pre-turn-off period in a first preset energy-saving period, and the service performance comprises one of a turn-on rate, a switching success rate, service transmission instantaneity and service transmission rate, and the service transmission instantaneity is the inverse of service transmission time delay;

specifically, if the first statistical values of all the same coverage cells are not smaller than the corresponding preset service threshold values, determining that the target energy-saving time period is a pre-turn-off time period in a second preset energy-saving period; the target energy saving period includes a start time and an end time.

Correspondingly, if the same coverage cell exists, the service performance statistic value in the first preset period of the same coverage cell is smaller than the corresponding preset service threshold value; determining that the energy-saving cell does not have a target energy-saving time period; i.e. not sending the first message.

Further, after determining a target energy-saving time period of the energy-saving cell, sending a first message to a base station where the energy-saving message is located, where the first message is used for indicating that the target energy-saving time period is a pre-turn-off time period in a second preset energy-saving period;

in response, the energy-saving cell enters an off state at the beginning time of the target energy-saving period according to the indication of the first message, and resumes the working state at the ending time of the target energy-saving period; before the energy-saving cell enters the off state, the energy-saving cell can instruct each UE to re-access the same coverage cell by sending an air interface message to each UE accessed to the energy-saving cell so as to keep network connection.

According to the method provided by the embodiment, a service load predicted value and a predicted error of an energy-saving cell in a preset future time are obtained according to a first prediction model; judging whether the prediction error is larger than a preset error threshold value, if so, determining a pre-turn-off time period of the energy-saving cell according to the traffic load statistic value and the energy-saving threshold value in the preset historical time; if the traffic load is not greater than the preset traffic load predicted value and the energy-saving threshold value in the future time, determining a pre-turn-off time period of the energy-saving cell; and determining a target energy-saving time period of the energy-saving cell according to the business performance statistic value and the pre-turn-off time period of the same coverage cell of the energy-saving cell. The method has the following technical effects:

Based on the accuracy of the service load prediction, different energy-saving strategies are dynamically selected to determine an energy-saving period, so that the energy-saving period can be matched with a cell low service load period, the problems of error shutdown or shutdown duration reduction and the like caused by inaccurate service load prediction can be avoided, the accuracy of determining the energy-saving period is improved, the energy-saving effect can be improved, and the service performance of an energy-saving area is ensured;

the method comprises the steps of determining a pre-turn-off period according to a service load statistic value of an energy-saving cell in a preset historical time, and executing pre-turn-off of the energy-saving cell, wherein a target energy-saving period can be dynamically determined according to service performance requirements of the same coverage cell, so that the service performance in an energy-saving area after the energy-saving cell is turned off is ensured while energy is saved;

determining a target energy-saving period according to a service load predicted value of the energy-saving cell in a preset future time, and determining the energy-saving period according to the service load of the energy-saving cell in the preset future time, so that the energy-saving period is accurately matched with a low-load period, and the energy-saving effect is maximized on the premise of ensuring the service performance;

after the energy-saving management module determines a target energy-saving period corresponding to the energy-saving cell, the energy-saving management module sends the information of the target energy-saving period to the energy-saving cell in a message sending mode; the energy-saving cell can periodically enter an off state in a plurality of future energy-saving periods, so that the energy-saving effect is achieved;

The energy-saving threshold value is determined based on the available capacity information interacted with the coverage cells, so that the available capacity of the same coverage cells meets the service migration requirement under the energy-saving cells, the service load of the energy-saving cells can be completely migrated to other same coverage cells after the energy-saving cells are closed, the problems of insufficient capacity, service migration failure and the like of the same coverage cells are avoided, and the service performance of the energy-saving area after the cells are closed is ensured;

determining energy-saving cells according to the cell configuration data, and preferentially switching off cells of a specified frequency band and a network system or not switching off certain specified cells so as to meet differentiated energy-saving requirements; according to the performance data of each cell in the preset historical time, the energy-saving cell is determined, and the cell with high energy consumption, poor service performance and low load is preferentially determined as the energy-saving cell and is preferentially turned off, so that the total energy consumption of a preset area can be reduced, and the service performance can be improved.

The embodiment of the invention can divide the functional modules of the electronic device or the main control device according to the method example, for example, each functional module can be divided corresponding to each function, and two or more functions can be integrated in one processing unit. The integrated units may be implemented in hardware or in software functional modules. It should be noted that, in the embodiment of the present invention, the division of the modules is schematic, which is merely a logic function division, and other division manners may be implemented in actual implementation.

Fig. 5 is a schematic structural diagram of an energy-saving time period determining device according to an embodiment of the present application; the device is a virtual device corresponding to the energy-saving management end, and is used for implementing the energy-saving time period determining method, and can be integrated in any one of a base station, a base station operation maintenance platform and a core network device in a preset area, or can be located in an independent physical entity. As shown in fig. 5, the apparatus 50 includes:

an obtaining module 510, configured to obtain, according to the first prediction model, a traffic load predicted value and a predicted error of the energy-saving cell in a preset future time;

a judging module 520, configured to judge whether the prediction error is greater than a preset error threshold, and if so, determine a pre-shutdown time period of the energy-saving cell according to the traffic load statistic value and the energy-saving threshold in a preset history time; if the traffic load is not greater than the preset traffic load predicted value and the energy-saving threshold value in the future time, determining a pre-turn-off time period of the energy-saving cell;

a determining module 530, configured to determine a target energy saving time period of the energy saving cell according to the traffic performance statistics and the pre-shutdown time period of the same coverage cell of the energy saving cell.

Further, the preset historical time includes a plurality of preset energy-saving periods before the current time, and the preset energy-saving periods include a plurality of preset periods; the judging module 520 is specifically further configured to:

Acquiring continuous T low-load time periods as candidate energy-saving time periods; the low load time period is a preset period in which the service load statistical value is smaller than the energy-saving threshold value;

Further, the preset future time includes a preset energy-saving period after the current time, and the preset energy-saving period includes a plurality of preset periods; the judging module 520 is specifically further configured to:

acquiring continuous T low-load time periods as candidate energy-saving time periods; the low load time period is a preset period in which the predicted value of the service load is smaller than the energy-saving threshold value;

Further, the determining module 530 is specifically configured to:

acquiring a service performance statistic value of a same coverage cell of an energy-saving cell in a pre-turn-off time period in a first preset energy-saving period as a first statistic value, wherein the service performance comprises one of a call completing rate, a switching success rate, a service transmission instantaneity and a service transmission rate, and the service transmission instantaneity is the inverse of a service transmission time delay;

in the same coverage cell of the energy-saving cell, if the same coverage cell with the first statistic value smaller than the corresponding preset service threshold value does not exist; determining the target energy-saving time period as a pre-turn-off time period in a second preset energy-saving period; the first preset energy-saving period is the first preset energy-saving period after the current time; the second preset period is a second preset energy-saving period after the current time, or any preset energy-saving period after the current time.

Further, the judging module 520 is specifically further configured to:

determining the same coverage cell of the energy-saving cell in a plurality of cells in a preset area;

for each same coverage cell, determining a service load threshold of the same coverage cell according to the service performance threshold of the same coverage cell, and acquiring the available capacity of the same coverage cell according to the difference between the service load threshold and the service load average value of the same coverage cell;

acquiring the sum of the available capacities according to the sum of the available capacities of all the same coverage cells, and determining the minimum value in the preset value of the sum of the available capacities as an energy-saving threshold value of the energy-saving cell;

further, the judging module 520 is specifically further configured to:

performing function fitting on the business load statistic value and the business performance of the same coverage cell at the preset historical time according to the second prediction model to obtain a fitting function of the business performance-business load of the same coverage cell;

inputting a preset service performance threshold according to the fitting function, and acquiring a service load threshold of the same coverage cell; the preset service performance threshold is a minimum value of service performance parameters acceptable by the same coverage cell; the service performance comprises one of a call completing rate, a switching success rate, a service transmission real-time property and a service transmission rate, and the service transmission real-time property is the inverse of a service transmission time delay.

Further, the obtaining module 510 is specifically further configured to:

inputting a preset future time into a trained first prediction model to obtain a business load predicted value output by the first prediction model, wherein the first prediction model comprises one of ARIMA, PROPHET, LSTM and a neural network model;

and acquiring one of a mean square error, a root mean square error, an average absolute error and an average absolute relative error of the first prediction model as a prediction error.

Further, the obtaining module 510 is specifically further configured to:

acquiring performance data of each cell in a preset area at a preset historical time, wherein the historical performance data comprises one or more of a call completing rate average value, a switching success rate average value, a service transmission real-time average value, a service load average value and an energy consumption average value of a base station where the cell is located, and the service load comprises any one of PRB (resource utilization) resource utilization rate, RRC (radio resource control) connection number and traffic;

determining the ratio of the first average value to the second average value as a turn-off weight; the first average value is an energy consumption average value; the second average value is one or more weighted average values of a call completing rate average value, a switching success rate average value, a service transmission real-time average value and a service load average value;

And determining the cell with the turn-off weight larger than the preset turn-off threshold as the energy-saving cell.

The energy-saving time period determining device provided in this embodiment may perform the energy-saving time period determining method described above, and its implementation principle and technical effects are similar, and this embodiment will not be described herein again.

In a specific implementation of the foregoing energy-saving period determining apparatus, each module may be implemented as a processor, and the processor may execute computer-executable instructions stored in the memory, so that the processor performs the foregoing energy-saving period determining method.

Fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present application. As shown in fig. 6, the electronic device 60 includes: at least one processor 601 and a memory 602. The electronic device 60 further comprises a communication component 603. The processor 601, the memory 602, and the communication section 603 are connected via a bus 604.

In a specific implementation, the at least one processor 601 executes computer-executable instructions stored in the memory 602, such that the at least one processor 601 performs a power saving time period determination method as performed on the electronic device side above.

The specific implementation process of the processor 601 may refer to the above-mentioned method embodiment, and its implementation principle and technical effects are similar, and this embodiment will not be described herein again.

In the above embodiment, it should be understood that the processor may be a central processing unit (english: central Processing Unit, abbreviated as CPU), or may be other general purpose processors, digital signal processors (english: digital Signal Processor, abbreviated as DSP), application specific integrated circuits (english: application Specific Integrated Circuit, abbreviated as ASIC), or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the present invention may be embodied directly in a hardware processor for execution, or in a combination of hardware and software modules in a processor for execution.

The memory may comprise high speed RAM memory or may further comprise non-volatile storage NVM, such as at least one disk memory.

The bus may be an industry standard architecture (Industry Standard Architecture, ISA) bus, an external device interconnect (Peripheral Component, PCI) bus, or an extended industry standard architecture (Extended Industry Standard Architecture, EISA) bus, among others. The buses may be divided into address buses, data buses, control buses, etc. For ease of illustration, the buses in the drawings of the present application are not limited to only one bus or one type of bus.

The scheme provided by the embodiment of the invention is introduced aiming at the functions realized by the electronic equipment and the main control equipment. It will be appreciated that the electronic device or the master device, in order to implement the above-described functions, includes corresponding hardware structures and/or software modules that perform the respective functions. The present embodiments can be implemented in hardware or a combination of hardware and computer software in combination with the various exemplary elements and algorithm steps described in connection with the embodiments disclosed in the embodiments of the present invention. Whether a function is implemented as hardware or computer software driven hardware depends upon the particular application and design constraints imposed on the solution. Those skilled in the art may implement the described functionality using different approaches for each particular application, but such implementation is not to be considered as beyond the scope of the embodiments of the present invention.

The present application also provides a computer-readable storage medium having stored therein computer-executable instructions that, when executed by a processor, implement the above-described energy-saving time period determination method.

The computer readable storage medium described above may be implemented by any type of volatile or non-volatile memory device or combination thereof, such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk. A readable storage medium can be any available medium that can be accessed by a general purpose or special purpose computer.

An exemplary readable storage medium is coupled to the processor such the processor can read information from, and write information to, the readable storage medium. In the alternative, the readable storage medium may be integral to the processor. The processor and the readable storage medium may reside in an application specific integrated circuit (Application Specific Integrated Circuits, ASIC for short). The processor and the readable storage medium may reside as discrete components in an electronic device or a master device.

The present application also provides a computer program product comprising: a computer program stored in a readable storage medium, from which at least one processor of an electronic device can read, the at least one processor executing the computer program causing the electronic device to perform the solution provided by any one of the embodiments described above.

Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the method embodiments described above may be performed by hardware associated with program instructions. The foregoing program may be stored in a computer readable storage medium. The program, when executed, performs steps including the method embodiments described above; and the aforementioned storage medium includes: various media that can store program code, such as ROM, RAM, magnetic or optical disks.

Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the invention.

Claims

1. The energy-saving time period determining method is characterized by being used for an energy-saving management end, wherein the energy-saving management module is used for managing a plurality of cells in a preset area, and the plurality of cells comprise energy-saving cells, and the method comprises the following steps:

2. The method of claim 1, wherein the preset historical time comprises a plurality of preset energy saving periods prior to a current time, the preset energy saving periods comprising a plurality of preset periods; the determining the target energy-saving time period of the energy-saving cell according to the preset historical time business load statistic value and the energy-saving threshold value comprises the following steps:

3. The method of claim 1, wherein the predetermined future time comprises a predetermined energy saving period after the current time, the predetermined energy saving period comprising a plurality of predetermined periods; the determining the target energy-saving time period of the energy-saving cell according to the preset predicted value of the service load in the future time and the energy-saving threshold value comprises the following steps:

4. A method according to claim 2 or 3, wherein said determining a target energy saving time period for said energy saving cell based on said pre-shutdown time period and a traffic performance statistic for same coverage cells of said energy saving cell comprises:

5. The method of claim 1, wherein at least one of the same coverage cells is present in the energy saving cell, the method further comprising, prior to the determining whether the prediction error is greater than a preset error threshold:

and obtaining the sum of the available capacities according to the sum of the available capacities of all the cells covered by the same cover, and determining the minimum value in the preset value of the sum of the available capacities as the energy-saving threshold value of the energy-saving cell.

6. The method of claim 5, wherein said determining said traffic load threshold from traffic performance thresholds of co-coverage cells comprises:

7. The method according to claim 1, wherein the obtaining, according to a first prediction model, a traffic load predicted value and a predicted error of the energy-saving cell in a preset future time includes:

8. The method of claim 1, wherein prior to the obtaining, according to the first predictive model, traffic load predictions and prediction errors for the energy-efficient cell over a preset future time, the method further comprises:

Acquiring performance data of each cell in the preset area in the preset historical time, wherein the historical performance data comprises one or more of a call completing rate average value, a switching success rate average value, a service transmission real-time average value, a service transmission rate average value, a service load average value and an energy consumption average value of a base station where the cell is located; the traffic load comprises any one of PRB resource utilization rate, RRC connection number and traffic;

determining the ratio of the first average value to the second average value as a turn-off weight; wherein the first average value is the energy consumption average value; the second average value is one or more weighted average values of the call completing rate average value, the switching success rate average value, the service transmission real-time average value, the service transmission rate average value and the service load average value;

9. An energy saving time period determining apparatus for managing a plurality of cells within a preset area, the plurality of cells including an energy saving cell therein, the apparatus comprising:

10. The apparatus of claim 9, wherein the preset historical time comprises a plurality of preset energy saving periods prior to a current time, the preset energy saving periods comprising a plurality of preset periods; the judging module is specifically configured to:

11. The apparatus of claim 9, wherein the preset future time comprises a preset energy saving period after the current time, the preset energy saving period comprising a plurality of preset periods; the judging module is specifically configured to:

12. The device according to claim 10 or 11, characterized in that the determining module is further specifically configured to:

13. The apparatus of claim 9, wherein the determining module is further specifically configured to:

14. The apparatus of claim 13, wherein the determining module is further specifically configured to:

15. The device according to claim 9, wherein the acquisition module is further configured to:

16. The device according to claim 9, wherein the acquisition module is further configured to:

17. An electronic device, comprising: a processor, and a memory communicatively coupled to the processor;

the memory stores computer-executable instructions;

the processor executes computer-executable instructions stored in the memory to implement the method of any one of claims 1 to 8.

18. A computer readable storage medium having stored therein computer executable instructions which when executed by a processor are adapted to carry out the method of any one of claims 1 to 8.