CN115038148A - Energy-saving threshold determination method, device, equipment and storage medium - Google Patents

Abstract

The application discloses a method, a device, equipment and a storage medium for determining an energy-saving threshold. The method comprises the following steps: acquiring characteristic data of a current set time length of a target cell; predicting the feature data of the next set duration based on the feature data of the current set duration; determining a scene state corresponding to the next set time length of the target cell based on the predicted characteristic data and a cell state base which is constructed in advance; determining a target energy-saving threshold corresponding to the next set time length of the target cell based on the scene state and a pre-constructed energy-saving threshold library; the cell state library comprises corresponding scene states determined based on the engineering parameters of the cells and historical user distribution, and the scene states can indicate first results of space dimension classification corresponding to the cells and second results of continuous classification based on time dimension on the basis of the space dimension classification. The target energy-saving threshold determined by the embodiment of the application can adapt to the change of the user distribution of the target cell based on the time dimension, and the energy-saving effect is better.

Description

Energy saving threshold determination method, device, equipment and storage medium

technical field

The present application relates to wireless communication, and in particular, to a method, apparatus, device and storage medium for determining an energy saving threshold.

Background technique

For wireless communication networks, relevant energy-saving techniques include: cell shutdown, carrier shutdown, channel shutdown, and symbol shutdown. The principle is that when the network load is relatively light, some wireless resources are turned off, and the remaining resources are used to provide services to achieve the purpose of energy saving.

The energy-saving solution mainly includes two basic processes: energy-saving activation and energy-saving deactivation. Among them, energy-saving activation refers to the purpose of saving energy by closing cells or restricting the use of some physical resources, and the corresponding base station enters the energy-saving state; energy-saving deactivation is the Refers to: opening a closed cell or restoring the use of restricted physical resources to meet increased service requirements and QoS (Quality of Service, quality of service) requirements, and the corresponding base station is restored from an energy-saving state to a normal state.

In the related art, whether a cell enters an energy-saving state is often determined according to a preset energy-saving parameter value (ie, an energy-saving threshold). However, the preset energy-saving parameter values are determined according to specified scenarios, and it is necessary to manually analyze different network scenarios, and then set the energy-saving parameter values, resulting in high labor costs. In addition, the specific scene of the cell will change, which may easily cause problems such as unreasonable configuration of preset energy-saving parameter values and low accuracy, thereby reducing the energy-saving effect of the base station and failing to meet dynamic environmental changes and energy-saving needs.

SUMMARY OF THE INVENTION

In view of this, the embodiments of the present application provide a method, apparatus, device, and storage medium for determining an energy saving threshold, which aim to optimize the energy saving effect of the base station.

The technical solutions of the embodiments of the present application are implemented as follows:

An embodiment of the present application provides a method for determining an energy saving threshold, including:

Obtain characteristic data of the current set duration of the target cell, where the characteristic data is used to indicate the user distribution of the target cell;

Based on the feature data of the current set duration, predict the feature data of the next set duration;

Determine, based on the predicted feature data and a pre-built cell state database, the scene state corresponding to the target cell in the next set duration;

determining a target energy saving threshold corresponding to the next set duration of the target cell based on the scene state and a pre-built energy saving threshold library;

Wherein, the cell state database includes corresponding scene states determined based on the engineering parameters of the cell and historical user distribution, and the scene state can indicate the first result of the spatial dimension classification corresponding to the cell and based on the spatial dimension classification The second result of the continued classification in the time dimension, the energy-saving threshold database includes corresponding energy-saving thresholds determined based on historical operating parameters in each scene state in the cell state database.

The embodiment of the present application also provides a device for determining an energy saving threshold, including:

an acquisition module, configured to acquire feature data of the currently set duration of the target cell, where the feature data is used to indicate the user distribution of the target cell;

a prediction module for predicting the feature data of the next set duration based on the feature data of the current set duration;

a first determining module, configured to determine the scene state corresponding to the target cell in the next set duration based on the predicted feature data and a pre-built cell state library;

a second determining module, configured to determine, based on the scene state and a pre-built energy-saving threshold library, a target energy-saving threshold corresponding to the target cell in the next set duration;

Wherein, the cell state database includes corresponding scene states determined based on the engineering parameters of the cell and historical user distribution, and the scene state can indicate the first result of the spatial dimension classification corresponding to the cell and based on the spatial dimension classification The second result of the continued classification in the time dimension, the energy-saving threshold database includes corresponding energy-saving thresholds determined based on historical operating parameters in each scene state in the cell state database.

An embodiment of the present application further provides a device for determining an energy saving threshold, including: a processor and a memory for storing a computer program that can be executed on the processor, wherein the processor is configured to execute this program when running the computer program. The steps of the method described in the application examples.

The embodiments of the present application further provide a storage medium, where a computer program is stored on the storage medium, and when the computer program is executed by a processor, the steps of the methods described in the embodiments of the present application are implemented.

The technical solution provided by the embodiment of the present application predicts the feature data of the next set duration based on the feature data of the current set duration of the target cell, and determines, based on the predicted feature data and the pre-built cell state database, that the target cell is in the next set duration. The scene state corresponding to the timing length, the scene state can indicate the first result of the spatial dimension classification of the cell and the second result of the continuous classification based on the time dimension on the basis of the spatial dimension classification, so that the predicted scene state of the target cell is in The classification results in the spatial dimension and the time dimension; and then determine the target energy-saving threshold corresponding to the next set duration of the target cell based on the scene state and the pre-built energy-saving threshold library, so that the determined target energy-saving threshold can adapt to the target cell based on the time dimension. The change of user distribution, and then the energy-saving control strategy can be changed based on the change of user distribution, and the energy-saving effect is better.

Description of drawings

FIG. 1 is a schematic flowchart of a method for determining an energy saving threshold according to an embodiment of the present application;

2 is a schematic flowchart of a method for determining a threshold in an application example of the present application;

3 is a schematic structural diagram of an apparatus for determining an energy saving threshold according to an embodiment of the present application;

FIG. 4 is a schematic structural diagram of a device for determining an energy saving threshold according to an embodiment of the present application.

Detailed ways

The present application will be further described in detail below with reference to the accompanying drawings and embodiments.

Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the technical field to which this application belongs. The terms used herein in the specification of the application are for the purpose of describing specific embodiments only, and are not intended to limit the application.

In the related art, the energy-saving state of a cell is often determined according to preset energy-saving parameter values, and the preset energy-saving parameter configuration is often only based on the scene classification of the cell in the spatial dimension (for example, scenarios such as hospitals, factories, schools, etc.) To set, the granularity of scene classification is coarse, resulting in low configuration accuracy of energy-saving parameter values, and cannot adapt to dynamic environmental changes, resulting in limited energy-saving effect.

Based on this, various embodiments of the present application provide a method for individually configuring the energy saving threshold of a cell based on the classification results of the cell in the two dimensions of time and space, so that the determined energy saving threshold not only adapts to the spatial dimension of the cell It can also adapt to the change of user distribution based on the time dimension, and then change the energy-saving control strategy based on the change of user distribution, and the energy-saving effect is better.

This embodiment of the present application provides a method for determining an energy saving threshold. The method for determining an energy saving threshold can be applied to a base station or to a network device (for example, an energy-saving operation and maintenance platform) that is communicatively connected to the base station, which is not covered in this application. Specific restrictions. As shown in Figure 1, the energy saving threshold determination method includes:

Step 101: Acquire characteristic data of a currently set duration of a target cell, where the characteristic data is used to indicate user distribution of the target cell.

Step 102: Based on the feature data of the current set duration, predict the feature data of the next set duration.

Step 103: Determine, based on the predicted feature data and a pre-built cell state database, a scene state corresponding to the target cell in the next set duration.

Step 104: Determine a target energy saving threshold corresponding to the next set duration of the target cell based on the scene state and a pre-built energy saving threshold library.

In the embodiment of the present application, the cell state database includes corresponding scene states determined based on the engineering parameters of the cells and historical user distribution, and the scene states can indicate the first result of the classification of the cell corresponding to the spatial dimension and the classification in the spatial dimension. On the basis of the second result of continuing classification based on the time dimension, the energy-saving threshold library includes corresponding energy-saving thresholds determined based on the historical working parameters of each scene state in the cell state library.

In the embodiment of the present application, based on the feature data of the current set duration of the target cell, the feature data of the next set duration is predicted, and based on the predicted feature data and the pre-built cell state database, it is determined that the target cell corresponds to the next set duration The scene state can indicate the first result of the classification of the cell corresponding to the spatial dimension and the second result of the classification based on the time dimension on the basis of the spatial dimension classification, so that the predicted scene state of the target cell is in the spatial dimension and The classification results in the time dimension; and then determine the target energy-saving threshold corresponding to the next set duration of the target cell based on the scene state and the pre-built energy-saving threshold library, so that the determined target energy-saving threshold can adapt to the target cell based on the user distribution in the time dimension. change, and then the energy-saving control strategy can be changed based on the change of user distribution, and the energy-saving effect is better.

Exemplarily, the characteristic data may be MR (Measurement Report, measurement report) data of the cell. The set duration may be reasonably set according to the update requirement of the energy saving threshold. For example, the set duration may be one hour, or may be greater or less than one hour, which is not specifically limited in this application. The energy-saving threshold can be understood as a parameter value used for energy-saving control.

Exemplarily, a cell state library and an energy saving threshold library may be pre-built based on an offline algorithm, the feature data of the next set duration of the target cell may be predicted based on an online algorithm, and the scene state of the target cell and the corresponding target energy saving threshold may be determined.

Exemplarily, the energy saving threshold determination method further includes:

Based on the engineering parameters of the cells and the historical user distribution, the cell state database is generated by clustering.

Taking the energy saving threshold determination method applied to a network device as an example, the network device can collect engineering parameters of a cell and historical user distribution, and cluster to generate a cell state database.

Exemplarily, the cell state database is generated by clustering based on the engineering parameters of the cell and the historical user distribution, including:

Clustering and dividing each cell based on the engineering parameters of the cell to obtain the first result;

Clustering and dividing the user distributions of different set durations of the cell histories of the various types of cells divided by the first result to obtain the second result;

The scene state is determined based on the first result and the second result.

Here, the engineering parameters of the cell may include index data for indicating the cell's own coverage and geographic scene, for example, including: site height, downtilt angle, total number of configured neighboring cells, average site spacing, weak coverage, and overlapping coverage. By clustering and dividing the engineering parameters of each cell, the first result representing the scene classification of the cell in the spatial dimension can be obtained. Here, a K-means clustering algorithm may be used for the clustering division, so that the cells are divided into the first type based on the engineering parameters of the cells. Exemplarily, the results of the first type of division are shown in Table 1:

Table 1

Cell ID scene state label Cell-1 Cluster#Scenario A Cell-2 Cluster#Scenario B Cell-3 Cluster#Scenario C … …

It should be noted that the engineering parameters of the cells may also include indicators such as coverage scenarios, building names, etc., that is, when performing the above-mentioned first type of clustering, the coverage scenarios and building names of each cell may also be considered.

Here, on the basis of the first type of division, clustering may also be continued based on the various types of cells divided by the first type of division. Exemplarily, for the aforementioned scenario A, clustering is performed based on historical user distributions with different set durations, such as hour-level MR data based on cell history, to obtain user distribution classifications 1, 2, 3, and 4. ..., to synthesize the same optimized groupings, for example, A1, A2, A3, A4..., B1, B2, B3, B4...etc.

Exemplarily, the scene states determined based on the first result and the second result are shown in Table 2:

Table 2

Cell ID User distribution scene state label Cell-1 MR1 Cluster#Scenario A1 Cell-1 MR2 Cluster#Scenario A2 Cell-1 MR3 Cluster#Scenario A3 Cell-1 MR4 Cluster#Scenario A4

It can be known from Table 2 that the scene state can indicate the cell corresponds to the first result of the spatial dimension classification and the second result of the continuous classification based on the time dimension on the basis of the spatial dimension classification.

In this way, a cell state database can be established by performing joint clustering analysis on the scene in the space dimension and the user distribution in the time dimension.

Further, in order to achieve experience sharing, the energy saving threshold can be optimized for the same optimization group (ie, the same scene state) according to the classification results in the cell state database, which reduces the amount of computation and facilitates online determination of the energy saving threshold corresponding to each scene state. Based on this, the energy saving threshold determination method further includes:

Based on the historical performance management (PM) data and network key performance indicator (Key Performance Indicator, KPI) data in each scene state in the cell state database, a corresponding energy saving threshold is determined, and the energy saving threshold database is generated.

Exemplarily, the PM data may include: the maximum number of RRC (Radio Resource Control, radio resource control) connections, uplink traffic, downlink traffic, uplink PRB (Physical Resource Block, physical resource block) utilization, and downlink PRB utilization. The network KPI data may include: RRC establishment success rate, ERAB (Evolved Radio Access Bearer, evolved radio access bearer) establishment success rate, wireless connection rate, wireless drop rate, and handover success rate.

Exemplarily, the determining the corresponding energy saving threshold based on the historical PM data and network KPI data under each scene state in the cell state database includes:

Based on the historical PM data and network KPI data in each scene state in the cell state database, determine the limit value of the PM data corresponding to the network KPI data that meets the set requirements, and set the limit value of the PM data as the corresponding energy-saving threshold.

Here, the limit value of the PM data for which the network KPI data meets the set requirements refers to the parameter value for which the network KPI of the solution cell is kept stable and the shutdown load threshold is the highest (the most energy saving).

Here, for each scene state in the cell state database generated by the aforementioned clustering, the PM data that keeps the network KPI stable and saves the most energy can be obtained as the energy saving threshold corresponding to the corresponding scene state, thereby constructing the energy saving threshold database. In this way, through the clustering analysis of the cell scene and the information related to the user distribution, the cells can be clustered and divided, and the division of the spatial and temporal granularity can be obtained, that is, the division of a cell under a certain user distribution, and through the analysis Based on historical PM data and network KPI data, the corresponding energy-saving thresholds are determined for groups of similar optimizations to form an energy-saving threshold library, which provides conditions and basis for the subsequent adaptive optimization of time-space granularity parameters.

In some embodiments, the historical PM data and network KPI data in each scene state in the cell state database can be numerically analyzed to obtain the highest shutdown load threshold at which the network KPI begins to deteriorate, and the corresponding energy saving threshold can be obtained. Here, the deterioration of the network KPI may be that the change difference of the network KPI data reaches a set requirement or the network KPI data is lower than a set threshold, which is not limited in this application.

In some embodiments, determining the limit value of the PM data corresponding to the network KPI data that meets the set requirements based on the historical PM data and network KPI data in each scene state in the cell state database, include:

Using the historical PM data and network KPI data under each scene state in the community state database as training data to train the initial model to obtain a trained model;

Using an optimization search algorithm, the trained model is used to obtain the limit value of the PM data corresponding to the network KPI data satisfying the set requirements.

Exemplarily, a machine learning algorithm is used to mine the relationship between the PM data and the network KPI data, so as to solve the highest shutdown load threshold at which the network KPI begins to deteriorate. The initial model established is as follows:

Y=f(X)

Among them, the input data X is PM data (maximum number of RRC connections, uplink traffic, downlink traffic, uplink PRB utilization, downlink PRB utilization), and output data Y is the network KPI data predicted by function f (RRC establishment success rate, ERAB establishment success rate, wireless connection rate, wireless drop rate, handover success rate). Exemplarily, the data in the input data X is read row by row and converted into a column matrix, which is used as the input of the neural network. Similarly, the output data Y matrix is converted into a column matrix and used as the output of the neural network.

Here, the RELU function is used as the activation function in the neural network, the output Y of the regression problem contains multiple variables, and the design cost function is:

Among them, _yi is the sample data, _yi ' is the predicted value calculated by the neural network, and l is the number of samples. That is, the average value of the mean squared error (MSE, mean squared error) of each variable is used as the loss function. By training the model, the weights and biases are adjusted to minimize the cost function of the network.

For the trained model, an optimized search algorithm is used to select the highest shutdown load threshold at which the network KPI begins to deteriorate. For example, a genetic algorithm can be used to search the resulting training model to find the highest shutdown load threshold at which the network KPI begins to deteriorate. In this way, the energy saving threshold corresponding to each scene state can be obtained, as shown in Table 3 below.

table 3

Cell ID User distribution scene state label Optimal Threshold Parameters Cell-1 MR1 Cluster#Scenario A1 Parameter combination 1: Numerical value Cell-1 MR2 Cluster#Scenario A2 Parameter combination 2: Numerical value Cell-1 MR3 Cluster#Scenario A3 Parameter combination 3: Numerical value Cell-1 MR4 Cluster#Scenario A4 Parameter combination 4: Numerical value Cell-2 MR1 Cluster#Scenario B1 Parameter combination 5: Numerical value Cell-2 MR2 Cluster#Scenario B2 Parameter combination 6: Numerical value Cell-2 MR3 Cluster#Scenario B3 Parameter combination 7: Numerical value Cell-2 MR4 Cluster#Scenario B4 Parameter combination 8: Numerical value … … … …

It can be understood that Table 3 shows the optimal threshold parameters (ie, energy saving thresholds) corresponding to each optimization group, which is convenient to determine the optimization group to which the cell belongs based on the predicted user distribution of the cell, and then determine the energy saving threshold corresponding to the cell. Among them, the optimal threshold parameters corresponding to each optimization group can be constructed offline to realize experience sharing, which can reduce the amount of online computation, so that the online part can directly use the experience library obtained by offline computation, which greatly reduces the amount of online computation, which is beneficial to implementation and application. deployment.

In some embodiments, predicting the feature data of the next set duration based on the feature data of the currently set duration includes: performing an analysis on the currently set duration based on a Long Short-Term Memory (LSTM) network. The feature data is predicted, and the feature data of the next set duration is obtained.

Here, because LSTM has a unique memory mode and forgetting mode, the network can fully mine the time series features of time series data and learn the time dependency between input data, so that it can predict the next time based on the historical MR data with a set duration. MR data for a set duration.

It can be understood that, in practical applications, the classification result of the cell in the spatial dimension can be determined based on the cell identifier, that is, the aforementioned first result (scenario A, B, C, etc.), based on the predicted MR data. Set the scene state corresponding to the duration. Combined with the aforementioned Table 3, assuming that the cell identifier is Cell-1, the predicted user distribution falls into MR2, and the scene state label is A2, the energy saving threshold corresponding to parameter combination 2 is selected as the target energy saving threshold.

The present application will be further described in detail below with reference to application examples.

As shown in Figure 2, in this application example, the overall process includes two parts: offline and online: offline data mining refers to the use of historical data to perform joint clustering analysis on cell scenes and user distribution to form a scene and user distribution state database (equivalent to in the aforementioned cell state database). According to each division, the relationship between historical energy-saving threshold parameters and network KPIs and energy consumption is mined, and the parameters that keep network KPIs stable and have the highest shutdown load threshold (the most energy-saving) are obtained to form a parameter library corresponding to scenarios and user distribution (equivalent to the aforementioned energy saving threshold library). The online part refers to using real-time cell data to predict the user distribution of the cell at the next time granularity, classifying the predicted user distribution according to the prediction results, and combining the cell scene information to find the scene and user distribution corresponding to the cell at the next moment, and Energy saving thresholds corresponding to scenarios and user distribution.

Exemplarily, the offline part performs preprocessing such as normalization on the collected data by collecting historical network status data (data such as engineering parameters, PM, network KPI, MR, overlapping coverage scenarios, etc.) On the joint clustering, build a scene and user distribution state library, and establish a similar optimization group from the spatial granularity and time granularity, which can realize the sharing of experience and reduce the amount of calculation. Based on the scene and user distribution state library, parameter optimization can be carried out through modeling and training. For example, the genetic algorithm is used to search for the highest shutdown load threshold that makes the network KPI begin to deteriorate in the obtained training model, and the state of each scene can be obtained. The corresponding energy-saving threshold can be obtained to obtain personalized energy-saving parameter configuration suggestions. Compared with manual experience, the AI (artificial intelligence)-based method is beneficial to improve the quality and efficiency of energy-saving threshold parameter optimization, and achieve refined parameter optimization.

It can be understood that, with the accumulation of existing network testing and experience, the scene and user distribution state library, and the parameter library corresponding to the scene and user distribution can be continuously updated. The new users distribute the control requirements of the corresponding energy-saving strategies, thereby realizing refined energy-saving control.

对应的标签为{y⁽¹⁾,y⁽²⁾,...,y⁽ⁱ⁾,...,y^(p)}，其中，x⁽ⁱ⁾表示第i个样本，

表示第i个样本的第t个数据，y⁽ⁱ⁾表示第i个样本对应的标签，即第i个样本预测的下一个时刻的MR值。Illustratively, the online part may predict the distribution of users at the next temporal granularity (eg, hourly level) based on the LSTM. For example, the original data set can be preprocessed to obtain p training set samples, and each sample has T MR data, which is

The corresponding labels are {y ⁽¹⁾ ,y ⁽²⁾ ,...,y ⁽ⁱ⁾ ,...,y ^(p) }, where x ⁽ⁱ⁾ represents the ith sample,

represents the t-th data of the ith sample, and y ⁽ⁱ⁾ represents the label corresponding to the ith sample, that is, the MR value at the next moment predicted by the ith sample.

The MR value y ⁽ⁱ⁾ of the wireless network at the next moment is predicted by using the ith sample x ⁽ⁱ⁾ as the input of the long short-term memory network. A network training on a sample requires T time steps, and each time step corresponds to an LSTM cell. The long short-term memory network adopts a self-looping method, and only one data can be input into the network at each moment. Exemplarily, the historical data and the LSTM model can be used to train a model that predicts the future 1 hour every 1 hour, and the data of the previous 3 hours can be used to predict the value of the next 1 hour. Then, based on the predicted MR data for the next hour, combined with the cell identifier, determine the scene category to which the target cell belongs in the scene and user distribution state database, and determine the corresponding target energy saving threshold based on the energy saving threshold corresponding to the scene category, so that the base station can The energy saving strategy is adjusted based on the newly determined target energy saving threshold.

In order to implement the method for determining an energy saving threshold according to an embodiment of the present application, an embodiment of the present application further provides an apparatus for determining an energy saving threshold, where the apparatus for determining an energy saving threshold corresponds to the foregoing method for determining an energy saving threshold. It is completely applicable to this embodiment of the apparatus for determining the energy saving threshold.

As shown in FIG. 3 , the apparatus for determining an energy saving threshold includes: an acquisition module 301 , a prediction module 302 , a first determination module 303 and a second determination module 304 . Wherein, the acquisition module 301 is used to acquire the feature data of the current set duration of the target cell, the feature data is used to indicate the user distribution of the target cell; the prediction module 302 is used to predict the current set duration based on the feature data of the current set duration. The feature data of the next set duration; the first determination module 303 is configured to determine the scene state corresponding to the target cell in the next set duration based on the predicted feature data and the pre-built cell state library; The second determining module 304 is configured to determine a target energy saving threshold corresponding to the next set duration of the target cell based on the scene state and a pre-built energy saving threshold library. The cell state library includes corresponding scene states determined based on the engineering parameters of the cell and historical user distribution, and the scene states can indicate the first result of the cell corresponding spatial dimension classification and the time dimension based on the spatial dimension classification. Continuing with the second result of the classification, the energy-saving threshold database includes corresponding energy-saving thresholds determined based on historical operating parameters in each scene state in the cell state database.

In some embodiments, the apparatus for determining an energy saving threshold further includes: a clustering module 305, configured to generate the cell state database by clustering based on the engineering parameters of the cell and the historical user distribution.

In some embodiments, the clustering module 305 is specifically configured to: cluster and divide the cells based on the engineering parameters of the cells to obtain the first result; set different histories of the various types of cells divided by the first result The user distribution of the duration is divided into clusters to obtain the second result; the scene state is determined based on the first result and the second result.

In some embodiments, the energy-saving threshold determining apparatus further includes: an energy-saving parameter optimization module 306, which determines a corresponding energy-saving threshold based on the historical performance management PM data and network key performance indicator KPI data in the cell state database in each scenario state, and generates a the energy saving threshold library.

In some embodiments, the energy saving parameter optimization module 306 is specifically configured to: based on the historical PM data and network KPI data in the cell state database in each scene state, determine all the parameters corresponding to the network KPI data that meet the set requirements. The limit value of the PM data is used as the corresponding energy saving threshold.

In some embodiments, the energy-saving parameter optimization module 306 is specifically configured to: use the historical PM data and network KPI data under each scene state in the cell state database as training data to train the initial model to obtain a trained model; The search algorithm is optimized, and the trained model is used to obtain the limit value of the PM data corresponding to the network KPI data satisfying the set requirements.

In some embodiments, the prediction module 302 is specifically configured to: predict the feature data of the current set duration based on the long short-term memory network, and obtain the feature data of the next set duration.

In practical application, the acquisition module 301 , the prediction module 302 , the first determination module 303 , the second determination module 304 , the clustering module 305 and the energy saving parameter optimization module 306 may be implemented by a processor in the energy saving threshold determination device. Of course, the processor needs to run a computer program in memory to perform its functions.

It should be noted that: when the energy-saving threshold determination device provided in the above-mentioned embodiment performs the energy-saving threshold determination, only the division of the above program modules is used as an example for illustration. In practical applications, the above processing may be allocated to different program modules as required. Completion means dividing the internal structure of the device into different program modules to complete all or part of the processing described above. In addition, the device for determining an energy saving threshold provided by the above embodiment and the method for determining an energy saving threshold belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

Based on the hardware implementation of the above program modules, and in order to implement the method of the embodiment of the present application, the embodiment of the present application further provides a device for determining an energy saving threshold. The energy-saving threshold determination device may be a base station, or may be a network device communicatively connected to the base station. FIG. 4 only shows an exemplary structure but not the whole structure of the energy saving threshold determination device, and part or all of the structure shown in FIG. 4 may be implemented as required.

As shown in FIG. 4 , the device 400 for determining an energy saving threshold provided by this embodiment of the present application includes: at least one processor 401 , a memory 402 , a user interface 403 , and at least one network interface 404 . The various components in the power saving threshold determination device 400 are coupled together by a bus system 405 . It will be understood that the bus system 405 is used to implement the connection communication between these components. In addition to the data bus, the bus system 405 also includes a power bus, a control bus, and a status signal bus. However, for clarity of illustration, the various buses are labeled as bus system 405 in FIG. 4 .

The user interface 403 may include a display, a keyboard, a mouse, a trackball, a click wheel, keys, buttons, a touch pad or a touch screen, and the like.

The memory 402 in this embodiment of the present application is used to store various types of data to support the operation of the device for determining the energy saving threshold. Examples of such data include: any computer program used to operate on an energy saving threshold determination device.

The energy saving threshold determination method disclosed in the embodiments of the present application may be applied to the processor 401 or implemented by the processor 401 . The processor 401 may be an integrated circuit chip with signal processing capability. In the implementation process, each step of the method for determining the energy saving threshold may be completed by an integrated logic circuit of hardware in the processor 401 or instructions in the form of software. The above-mentioned processor 401 may be a general-purpose processor, a digital signal processor (DSP, Digital Signal Processor), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, and the like. The processor 401 may implement or execute the methods, steps, and logical block diagrams disclosed in the embodiments of this application. A general purpose processor may be a microprocessor or any conventional processor or the like. The steps of the method disclosed in the embodiments of the present application can be directly embodied as being executed by a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software module may be located in a storage medium, and the storage medium is located in the memory 402, and the processor 401 reads the information in the memory 402, and completes the steps of the energy saving threshold determination method provided by the embodiment of the present application in combination with its hardware.

In an exemplary embodiment, the power-saving threshold determination device may be implemented by one or more application-specific integrated circuits (ASIC, Application Specific Integrated Circuits), DSPs, Programmable Logic Devices (PLDs, Programmable Logic Devices), complex programmable logic devices ( CPLD, Complex Programmable Logic Device), Field Programmable Gate Array (FPGA, Field Programmable Gate Array), general-purpose processor, controller, microcontroller (MCU, Micro Controller Unit), microprocessor (Microprocessor), or other electronic Element implementation for performing the aforementioned method.

It will be appreciated that the memory 402 may be either volatile memory or non-volatile memory, and may include both volatile and non-volatile memory. Among them, the non-volatile memory may be a read-only memory (ROM, Read Only Memory), a programmable read-only memory (PROM, Programmable Read-Only Memory), an erasable programmable read-only memory (EPROM, Erasable Programmable Read-only memory) Only Memory), Electrically Erasable Programmable Read-Only Memory (EEPROM, Electrically Erasable Programmable Read-Only Memory), Magnetic Random Access Memory (FRAM, ferromagnetic random access memory), Flash Memory (Flash Memory), Magnetic Surface Memory , CD-ROM, or Compact Disc Read-Only Memory (CD-ROM, Compact Disc Read-Only Memory); the magnetic surface memory can be a magnetic disk memory or a tape memory. The volatile memory may be Random Access Memory (RAM), which is used as an external cache memory. By way of example and not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Synchronous Static Random Access Memory (SSRAM), Dynamic Random Access Memory Memory (DRAM, Dynamic Random Access Memory), Synchronous Dynamic Random Access Memory (SDRAM, SynchronousDynamic Random Access Memory), Double Data Rate Synchronous Dynamic Random Access Memory (DDRSDRAM, Double Data Rate Synchronous Dynamic Random Access Memory), Enhanced Synchronous Dynamic Random Access Memory (ESDRAM, Enhanced Synchronous Dynamic Random Access Memory), Synchronous Link Dynamic Random Access Memory (SLDRAM, SyncLink Dynamic Random Access Memory), Direct Memory Bus Random Access Memory (DRRAM, Direct Rambus Random Access Memory) . The memories described in the embodiments of the present application are intended to include, but not be limited to, these and any other suitable types of memories.

In an exemplary embodiment, an embodiment of the present application further provides a storage medium, that is, a computer storage medium, which may be a computer-readable storage medium, for example, including a memory 402 that stores a computer program, and the computer program can be determined by the energy-saving threshold determination device The processor 401 of the embodiment executes the steps described in the method of the embodiment of the present application. The computer-readable storage medium may be memory such as ROM, PROM, EPROM, EEPROM, Flash Memory, magnetic surface memory, optical disk, or CD-ROM.

It should be noted that "first", "second", etc. are used to distinguish similar objects, and are not necessarily used to describe a specific sequence or sequence.

In addition, the technical solutions described in the embodiments of the present application may be combined arbitrarily unless there is a conflict.

The above are only specific embodiments of the present application, but the protection scope of the present application is not limited to this. should be covered within the scope of protection of this application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims (10)

1. An energy saving threshold determining method is characterized by comprising the following steps:

acquiring feature data of a current set time length of a target cell, wherein the feature data is used for indicating user distribution of the target cell;

predicting the feature data of the next set duration based on the feature data of the current set duration;

determining a scene state corresponding to the next set time length of the target cell based on the predicted characteristic data and a pre-constructed cell state library;

determining a target energy-saving threshold corresponding to the next set time length of the target cell based on the scene state and a pre-constructed energy-saving threshold library;

the cell state library comprises corresponding scene states determined based on engineering parameters of cells and historical user distribution, the scene states can indicate first results of space dimension classification corresponding to the cells and second results of continuous classification based on time dimension on the basis of the space dimension classification, and the energy-saving threshold library comprises corresponding energy-saving thresholds determined based on historical working parameters of the scene states in the cell state library.

2. The method of claim 1, further comprising:

and clustering to generate the cell state library based on the engineering parameters of the cell and historical user distribution.

3. The method of claim 2, wherein clustering generates the cell state base based on engineering parameters and historical user distribution of the cell, and comprises:

clustering and dividing each cell based on the engineering parameters of the cell to obtain the first result;

clustering and dividing the user distribution of different set durations of the various types of cell histories obtained by dividing the first result to obtain a second result;

determining the scene state based on the first result and the second result.

4. The method of claim 1, further comprising:

and determining corresponding energy-saving thresholds based on historical performance management PM data and network key performance indicator KPI data in each scene state in the cell state library, and generating the energy-saving threshold library.

5. The method according to claim 4, wherein the determining the corresponding energy saving threshold based on the historical PM data and network KPI data in each scenario state in the cell state base comprises:

and determining a limit value of the PM data corresponding to the network KPI data meeting the setting requirement based on the historical PM data and the network KPI data in each scene state in the cell state library, and taking the limit value of the PM data as a corresponding energy-saving threshold.

6. The method according to claim 5, wherein the determining, based on the historical PM data and network KPI data in each scene state in the cell state library, the limit value of the PM data corresponding to the network KPI data meeting the setting requirement comprises:

training an initial model by taking historical PM data and network KPI data in each scene state in the cell state library as training data to obtain a trained model;

and solving the trained model by adopting an optimization search algorithm to obtain the limit value of the PM data corresponding to the network KPI data meeting the set requirement.

7. The method of claim 1, wherein predicting the profile of the next set duration based on the profile of the current set duration comprises:

and predicting the characteristic data of the current set duration based on a long-term and short-term memory network to obtain the characteristic data of the next set duration.

8. An energy saving threshold determination apparatus, comprising:

the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring characteristic data of a current set time length of a target cell, and the characteristic data is used for indicating user distribution of the target cell;

the prediction module is used for predicting the characteristic data of the next set time length based on the characteristic data of the current set time length;

a first determining module, configured to determine, based on the predicted feature data and a pre-constructed cell state library, a scene state of the target cell corresponding to the next set duration;

a second determining module, configured to determine, based on the scene state and a pre-constructed energy saving threshold library, a target energy saving threshold corresponding to the next set duration for the target cell;

the cell state library comprises corresponding scene states determined based on engineering parameters of cells and historical user distribution, the scene states can indicate first results of space dimension classification corresponding to the cells and second results of continuous classification based on time dimension on the basis of the space dimension classification, and the energy-saving threshold library comprises corresponding energy-saving thresholds determined based on historical working parameters of the scene states in the cell state library.

9. An energy saving threshold determination device, comprising: a processor and a memory for storing a computer program capable of running on the processor, wherein,

the processor, when executing the computer program, is adapted to perform the steps of the method of any of claims 1 to 7.

10. A storage medium having a computer program stored thereon, the computer program, when executed by a processor, implementing the steps of the method of any one of claims 1 to 7.

Images