CN115915364A

CN115915364A - Energy-saving method and device for communication base station, computer readable medium and equipment

Info

Publication number: CN115915364A
Application number: CN202211254349.9A
Authority: CN
Inventors: 高志斌; 郭怡洋; 罗漫漫; 黄联芬; 李王明卉; 施芝元
Original assignee: Xiamen University
Current assignee: Xiamen University
Priority date: 2022-10-13
Filing date: 2022-10-13
Publication date: 2023-04-04

Abstract

The embodiment of the application provides an energy-saving method and device of a communication base station, a computer readable medium and equipment. The method comprises the following steps: determining a target base station set corresponding to a target landmark building according to the position information of the target landmark building, acquiring an environment data set corresponding to the target landmark building according to each target base station and the position information of the target landmark building contained in the target base station set, inputting the environment data set into an environment energy consumption identification model to determine an energy consumption requirement level corresponding to the environment where the target landmark building is located, inputting the base station energy consumption data of each target base station into the base station energy consumption identification model if the target base station set has an energy-saving space to determine an energy consumption level corresponding to each target base station, performing energy consumption load analysis on the target base station with the energy-saving space, determining the energy consumption state of each energy consumption unit, and further determining an energy-saving strategy. The energy-saving efficiency of the communication base station can be improved on the premise of not influencing user experience.

Description

Energy-saving method and device for communication base station, computer readable medium and equipment

Technical Field

The present application relates to the field of computer and communication technologies, and in particular, to an energy saving method and apparatus for a communication base station, a computer-readable medium, and a device.

Background

With the development of communication technology, new services are emerging endlessly, application scenes are emerging continuously, data transmission rate is higher, and the development trend of equipment connection to massive connection causes the phenomenon-level increase of communication requirements. The deployment and maintenance of a large number of base stations are accompanied by huge energy consumption, and in addition, the development of society requires a green low-carbon trend, and the base station energy-saving technology also becomes a hot research field accompanied with the development of communication technology. In the current technical solution, most energy-saving ideas are simple and rough site-level energy-saving strategy implementation in a preset time period, however, the method stops the whole base station from providing corresponding services, and further affects user experience. Therefore, how to improve the energy saving efficiency of the communication base station on the premise of not influencing the user experience becomes a technical problem to be solved urgently.

Disclosure of Invention

Embodiments of the present application provide an energy saving method and apparatus for a communication base station, a computer-readable medium, and a device, so that energy saving efficiency of the communication base station can be improved at least to a certain extent without affecting user experience.

Other features and advantages of the present application will be apparent from the following detailed description, or may be learned by practice of the application.

According to an aspect of an embodiment of the present application, there is provided a method for saving energy of a communication base station, the method including:

determining a target base station set corresponding to a target landmark building according to the position information of the target landmark building;

acquiring an environment data set corresponding to the target landmark building according to the target base stations and the position information of the target landmark building, wherein the position information of the target landmark building is contained in the target base station set, and the environment data set is used for describing the energy consumption requirement of the environment where the target landmark building is located;

inputting the environment data set into a pre-trained environment energy-consumption recognition model so that the environment energy-consumption recognition model outputs an energy consumption requirement level corresponding to the environment where the target landmark building is located;

if the energy consumption demand level is a first target level, acquiring base station energy consumption data of each target base station, wherein the first target level indicates that the target base station set has an energy-saving space;

inputting the base station energy consumption data of each target base station into a base station energy consumption recognition model trained in advance, so that the base station energy consumption recognition model outputs energy consumption grades corresponding to each target base station, wherein the energy consumption grades are used for describing the energy consumption of the target base stations;

carrying out energy utilization load analysis on the target base station with the energy utilization level being a second target level to determine the energy utilization state of each energy consumption unit, wherein the second target level indicates that the target base station has an energy-saving space;

and determining a corresponding energy-saving strategy according to the energy utilization state of each energy consumption unit in the target base station with the energy utilization level as a second target level.

According to an aspect of an embodiment of the present application, there is provided an energy saving apparatus for a communication base station, the apparatus including:

the first determining module is used for determining a target base station set corresponding to a target landmark building according to the position information of the target landmark building;

a first obtaining module, configured to obtain an environment data set corresponding to the target landmark building according to the target base stations included in the target base station set and the location information of the target landmark building, where the environment data set is used to describe an energy consumption requirement of an environment where the target landmark building is located;

the first identification module is used for inputting the environment data set into a pre-trained environment energy-consumption identification model so as to enable the environment energy-consumption identification model to output the energy consumption requirement level corresponding to the environment where the target landmark building is located;

a second obtaining module, configured to obtain base station energy consumption data of each target base station if the energy consumption requirement level is a first target level, where the first target level indicates that the target base station set has an energy saving space;

the second identification module is used for inputting the base station energy consumption data of each target base station into a base station energy consumption identification model trained in advance so as to enable the base station energy consumption identification model to output energy consumption grades corresponding to each target base station, wherein the energy consumption grades are used for describing the energy consumption of the target base stations;

a second determining module, configured to perform energy consumption load analysis on the target base station with the energy consumption level being a second target level, and determine an energy consumption state of each energy consumption unit of the target base station, where the second target level indicates that the target base station has an energy saving space;

and the processing module is used for determining a corresponding energy-saving strategy according to the energy utilization state of each energy consumption unit in the target base station with the energy utilization level being the second target level.

According to an aspect of the embodiments of the present application, there is provided a computer-readable medium on which a computer program is stored, the computer program, when executed by a processor, implementing the energy saving method of the communication base station as described in the above embodiments.

According to an aspect of an embodiment of the present application, there is provided an electronic device including: one or more processors; a storage device for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to implement the method for energy saving of a communication base station as described in the above embodiments.

According to an aspect of an embodiment of the present application, there is provided a computer program product or a computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the energy saving method of the communication base station provided in the above embodiments.

In the technical solutions provided in some embodiments of the present application, a target base station set corresponding to a target landmark building is determined according to position information of the target landmark building, an environment data set corresponding to the target landmark building is obtained according to each target base station and position information of the target landmark building included in the target base station set, the environment data set is input into an environment energy consumption identification model to determine an energy consumption requirement level corresponding to an environment in which the target landmark building is located, if the target base station set has an energy saving space, base station energy consumption data of each target base station is input into the base station energy consumption identification model to determine an energy consumption level corresponding to each target base station, if a certain target base station has the energy saving space, energy consumption load analysis is performed on the target base station to determine an energy consumption state of each energy consumption unit of the target base station, and an energy saving strategy is further determined.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and, together with the description, serve to explain the principles of the application. It is obvious that the drawings in the following description are only some embodiments of the application, and that for a person skilled in the art, other drawings can be derived from them without inventive effort. In the drawings:

fig. 1 shows a flow diagram of a method for energy saving of a communication base station according to an embodiment of the present application;

fig. 2 is a schematic diagram illustrating an application scenario of an energy saving method of a communication base station according to an embodiment of the present application;

FIG. 3 illustrates a schematic diagram of an HMM statistical model according to one embodiment of the present application;

fig. 4 shows a block diagram of an energy saving arrangement of a communication base station according to an embodiment of the present application;

FIG. 5 illustrates a schematic structural diagram of a computer system suitable for use in implementing the electronic device of an embodiment of the present application.

Detailed Description

Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many different forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art.

Furthermore, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the application. One skilled in the relevant art will recognize, however, that the embodiments of the present application can be practiced without one or more of the specific details, or with other methods, components, devices, steps, and so forth. In other instances, well-known methods, devices, implementations, or operations have not been shown or described in detail to avoid obscuring aspects of the application.

The block diagrams shown in the figures are functional entities only and do not necessarily correspond to physically separate entities. I.e. these functional entities may be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor means and/or microcontroller means.

The flow charts shown in the drawings are merely illustrative and do not necessarily include all of the contents and operations/steps, nor do they necessarily have to be performed in the order described. For example, some operations/steps may be decomposed, and some operations/steps may be combined or partially combined, so that the actual execution sequence may be changed according to the actual situation.

Fig. 1 is a flowchart illustrating an energy saving method of a communication base station according to an embodiment of the present application, where the method may be applied to servers, where the servers may be physical servers or cloud servers, and the number of the servers may be one or any number of two or more, for example, a single server or a server cluster composed of multiple servers, and the like, and is not limited in particular.

Referring to fig. 1, the energy saving method of the communication base station at least includes steps S110 to S170, which are described in detail as follows:

in step S110, a target base station set corresponding to a target landmark building is determined according to the position information of the target landmark building.

The landmark building may be a building capable of representing an electricity utilization scene of an area where the landmark building is located, and the landmark building may have different categories, such as a school, a mall, an institution, a station, a hospital, an amusement park, a factory, and the like.

In this embodiment, the server may obtain location information of a target landmark building, and determine a base station within an area range where the target landmark building is located according to the location information to serve as a target base station, so as to obtain a target base station set, where the target base station may be any type of base station, such as a site-level base station, a room-based base station, and the like. In one example, an area range may be set in advance, for example, a base station within 500m of a square circle may be used as a target base station around the position information of the target landmark building. It should be noted that the area range may be set to have different values according to different types of landmark buildings, and it should be understood that the influence ranges of the landmark buildings of different types are different, for example, a large factory has a large floor area and a large predetermined range corresponding to the large factory, a school has a small floor area and a small predetermined range corresponding to the large factory, and the like.

In step S120, an environment data set corresponding to the target landmark building is obtained according to the target base stations included in the target base station set and the location information of the target landmark building, where the environment data set is used to describe the energy consumption requirement of the environment where the target landmark building is located.

In this embodiment, the server may obtain, according to each target base station included in the target base station set and the location information of the target landmark building, an environment data set corresponding to the target landmark building from a third party organization or a data center of the third party organization or the data center of the third party organization, where the environment data set may be used to describe an energy consumption requirement of an environment in which the target landmark building is located. It should be noted that the present application is not limited to the selection of the environment data set, and the selection of the environment data set should consider the regional energy demand and the scenario-related data set, including but not limited to other resource consumption-related data sets of the region such as hydroelectric data sets, data sets showing population aggregation degree such as population mobility and density, and the like.

Taking a target landmark building as a station as an example, the environment data set may include people traffic data sets of different periods, traffic access data sets of streaming media enterprises and operators in the area, mobility index data sets of a target base station, and the like. The mobility index data set of the target base station can be inter-frequency handover, handover between NR and LTE, redirection from 5G to 4G, data coverage triggering from 5G, and the like, because some measures related to different frequency bands are provided in the sleep technology of the base station, the mobility index data can help to judge whether a corresponding sleep means can be adopted, and help to positioning the target base station in an early stage.

In step S130, the environment data set is input to the environment recognition model trained in advance, so that the environment recognition model outputs the energy consumption demand level corresponding to the environment where the landmark building is located.

In this embodiment, the environment energy use recognition model may be a neural network model that is constructed and trained in advance, and is used to recognize the energy use requirement of the environment where the target landmark building is located. The server can call the locally stored environment energy-consumption recognition model and input the environment data set into the environment energy-consumption recognition model, and the environment energy-consumption recognition model can perform data analysis based on the environment data set, so that the energy consumption requirement level of the environment where the target landmark building is located is output. It should be understood that a higher level of energy consumption requirement indicates that the environment has a higher demand for energy, and therefore energy conservation measures are not appropriate, whereas a lower level of energy consumption requirement indicates that the environment has a lower demand for energy, and therefore energy conservation measures can be taken.

In one example, the energy consumption demand level can be divided into high, medium and low, it should be understood that high represents that the environment of the target landmark building has high energy demand and is not suitable for energy saving measures, and medium represents that the energy saving measures can be performed, and in other examples, the energy saving measures can be performed only when the energy consumption demand level is low. It should be noted that the above grade division is only an exemplary example, and those skilled in the art may also divide the energy consumption demand grade according to the actual implementation needs, for example, the energy consumption demand grade may be divided into only high and low, or into five grades, i.e., high, medium, low and low, etc., which is not limited in particular.

In an embodiment of the present application, a Back Propagation (BP) neural network may be used to perform enhanced training on an environment recognition model, where the commonly used BP neural network has a three-layer structure including an input layer, an output layer, and an implied layer, where the number of neurons in the implied layer may be selected by reference according to a kolmogrow empirical formula:

wherein p is the number of neurons in the hidden layer, n is the number of neurons in the input layer, q is the number of neurons in the output layer, and a is a constant between 0 and 1.

The one-time learning process of the BP neural network consists of two processes of forward propagation of signals and backward propagation of errors, wherein the input is input from an input layer and is transmitted to an output layer after being processed by a hidden layer. If the actual output of the output layer does not match the expected output, the error back-propagation phase is entered. The error back propagation is to make the output error back propagate to the input layer through the hidden layer in some form, and distribute the error to all units of each layer, so as to obtain the error signal of each layer unit, and this error signal is used as the basis for correcting the weight of each unit. Until the output error meets a certain condition or the iteration number reaches a certain number.

In one embodiment of the present application, the environment recognition model may be retrained and updated according to the actual environment change speed, for example, it may be a quarterly update, a semiannually update or an annual update. In another example, a data set change determination mechanism may be added, and feature values of each data set may be calculated periodically (for example, weekly update or monthly update) and compared with a preset threshold, and if the feature values exceed the threshold, an environment recognizable model update operation may be triggered. Therefore, the accuracy of the environment recognition model recognition result can be ensured.

In step S140, if the energy consumption requirement level is a first target level, base station energy consumption data of each target base station is obtained, where the first target level indicates that the target base station set has an energy saving space.

In this embodiment, the first target level indicates that the target base station has energy saving space, for example, the first target level may be a medium or low of the aforementioned energy consumption requirement levels, or the first target level may be only a low. According to the energy consumption requirement level output by the environment energy consumption identification model, if the energy consumption requirement level is a first target level, base station energy consumption data of each target base station in the target base station set can be obtained, the base station energy consumption data can be used for describing the energy consumption of the target base station, for example, the base station energy consumption data can be energy consumption data of each energy consumption unit in the target base station, and the like.

In step S150, the base station energy consumption data of each target base station is input to the base station energy consumption recognition model trained in advance, so that the base station energy consumption recognition model outputs an energy consumption level corresponding to each target base station, where the energy consumption level is used to describe the energy consumption of the target base station.

In this embodiment, the base station energy recognition model may be a neural network model that is constructed and trained in advance and is used for recognizing the base station energy size. The server can call the trained base station energy consumption recognition model from the local storage, and input the base station energy consumption data of each target base station into the base station energy consumption recognition model, so that the base station energy consumption recognition model can output the energy consumption level corresponding to each target base station. In one example, the skilled person can classify the energy usage levels into high, medium and low in advance, wherein the high energy usage level indicates that the energy usage of the target base station is high, the medium energy usage level indicates that the energy usage of the target base station is medium, and the low energy usage level indicates that the energy usage of the target base station is low. In other embodiments, the skilled person can also classify the energy use level into other forms, and this is not limited specifically.

In step S160, an energy consumption load analysis is performed on the target base station with the energy consumption level being a second target level, and an energy consumption state of each energy consumption unit is determined, where the second target level indicates that the target base station has an energy saving space.

In this embodiment, the second target level indicates that the target base station has an energy saving space, and it should be understood that if the energy consumption requirement level corresponding to the target base station set is the first target level, for example, medium or low as mentioned in the foregoing example, then the energy consumption requirement corresponding to the target base station set is moderate or low, and if the energy consumption level of a certain target base station in the target base station set is inconsistent with that (i.e., the second target level), for example, the energy consumption requirement level corresponding to the target base station set is medium, and the energy consumption requirement level corresponding to a certain target base station is high, or the energy consumption requirement level corresponding to the target base station set is low, and the energy consumption level of a certain target base station is high, or the energy consumption requirement corresponding to the target base station set is low, and the energy consumption level of a certain target base station is medium. Therefore, when the energy consumption level of a certain target base station is inconsistent with the energy consumption demand level of the target base station set, it indicates that energy-saving measures can be performed on the target base station.

When it is determined that energy saving measures need to be performed on a certain target base station (that is, the energy utilization level corresponding to the target base station is the second target level), the server may determine the energy utilization states of the energy consumption units in the target base station, for example, the on-off states of the loads in the energy consumption units.

In step S170, a corresponding energy saving policy is determined according to the energy consumption state of each energy consumption unit in the target base station with the energy consumption level being the second target level.

In this embodiment, the server may analyze the energy consumption states of the energy consumption units in the target base station to generate a corresponding energy saving policy, for example, the energy consumption units that do not need to operate simultaneously or the loads in the energy consumption units may be controlled to switch states, and the like.

Therefore, according to the embodiment shown in fig. 1, a target base station set corresponding to a target landmark building is determined according to position information of the target landmark building, an environment data set corresponding to the target landmark building is obtained according to position information of each target base station and the target landmark building included in the target base station set, the environment data set is input into an environment energy consumption recognition model to determine an energy consumption requirement level corresponding to the environment where the target landmark building is located, if the target base station set has an energy saving space, base station energy consumption data of each target base station is input into a base station energy consumption recognition model to determine an energy consumption level corresponding to each target base station, if a certain target base station has the energy saving space, energy consumption load analysis is performed on the target base station to determine an energy consumption state of each energy consumption unit of the target base station, and an energy saving strategy is determined.

Based on the embodiment shown in fig. 1, in an embodiment of the present application, determining a target base station set corresponding to a target landmark building according to location information of the target landmark building includes:

according to the position information of the target landmark building, acquiring the position information of a base station to be selected in the area where the target landmark building is located;

and clustering the base stations to be selected by adopting a clustering algorithm according to the position information of the base stations to be selected in the area where the target landmark building is located to obtain a target base station set corresponding to the target landmark building.

In this embodiment, the server may determine the range of the area where the target landmark building is located according to the location information of the target landmark building, for example, the area within a predetermined range centering on the location information of the target landmark building, and the like. The server can compare the pre-stored position information of each base station with the area, so as to determine the base station located in the area where the target landmark building is located as a base station to be selected, and acquire the position information of each base station to be selected.

The server may cluster the base stations to be selected by using a clustering algorithm (e.g., a DBSCAN algorithm, etc.) according to the location information of the base stations to be selected, thereby obtaining a target base station set corresponding to the target landmark building. In the clustering process, the target landmark building can be used as a clustering center, and the base station to be selected which is clustered with the target landmark building and is the same as the target landmark building is determined as the target base station, so that a target base station set is obtained.

Therefore, in the embodiment, the base stations to be selected in the area where the target landmark building is located are clustered through the clustering algorithm, so that the target base station is determined, the association degree between the determined target base station and the target landmark building can be improved, and the effectiveness of implementation of subsequent energy-saving measures is further ensured.

Based on the foregoing embodiment, in an embodiment of the present application, according to location information of a base station to be selected in an area where a target landmark building is located, clustering the base station to be selected by using a clustering algorithm to obtain a target base station set corresponding to the target landmark building, includes:

determining a first distance between each base station to be selected and the target landmark building and a second distance between every two base stations to be selected according to the position information of the target landmark building and the position information of each base station to be selected;

determining a distance threshold corresponding to the target landmark building according to a first distance and a second distance corresponding to each base station to be selected;

and selecting the base stations to be selected with the first distance smaller than or equal to the distance threshold value from all the base stations to be selected as target base stations to obtain a target base station set corresponding to the target landmark building.

In this embodiment, the server may determine, according to the location information of the target landmark building and the location information of each candidate base station, a first distance between each candidate base station and the target landmark building, and a second distance between any two candidate base stations, where each candidate base station corresponds to one first distance and a plurality of second distances. The server may determine a distance threshold corresponding to the target landmark building according to the first distance and the second distance corresponding to each candidate base station, where the distance threshold is used to limit that the maximum distance between the target base station and the target landmark building, that is, the first distance, should be smaller than or equal to the distance threshold. In an example, the server may use a first distance corresponding to a certain base station to be selected as a vertical coordinate, and use a plurality of second distances corresponding to the base station to be selected as horizontal coordinates, respectively, to obtain a plurality of coordinate points corresponding to the base station to be selected. The server may select the corresponding largest first distance from the set of minimum points as the distance threshold, thereby ensuring the reasonableness of the distance threshold determination.

In other examples, the server may also perform a weighted sum operation according to the first distance and the second distance corresponding to each base station to be selected to obtain a preselected threshold corresponding to each base station to be selected, and then perform an average value or a median according to the preselected threshold corresponding to each base station to be selected to obtain a corresponding distance threshold, and so on.

It should be noted that, a person skilled in the art may select a corresponding distance threshold determination method according to actual implementation needs, as long as the association degree between the determined target base station and the target landmark building can be improved, and this is not particularly limited.

After the distance threshold is determined, the server can select the base stations to be selected, of which the first distance is smaller than or equal to the distance threshold, from the base stations to be selected as the target base station, so that a target base station set is obtained, the reasonability of the determined target base station can be improved, and the effectiveness of implementation of subsequent energy-saving measures is improved.

Based on the embodiment shown in fig. 1, in an embodiment of the present application, acquiring an environment data set corresponding to the target landmark building according to the target base stations included in the target base station set and the location information of the target landmark building includes:

determining an energy application scene corresponding to the target landmark building according to the category information of the target landmark building;

and acquiring an environment data set corresponding to the energy utilization scene in the environment where the target landmark building is located according to the position information of the target landmark building and each target base station contained in the target base station set.

In this embodiment, the server may determine the corresponding energy usage scenario according to the category information of the target landmark building, and may know the energy usage characteristics of the target landmark building according to the energy usage scenario, for example, the energy usage characteristics may include, but are not limited to, a peak energy usage period, a peak energy usage duration, a service object, a people movement situation, a valley energy usage period, a valley energy usage duration, and the like.

After determining the energy-use scenario, the server may obtain an environment data set corresponding to the energy-use scenario in the target landmark building according to the location information of the target landmark building and each target base station included in the target base station set.

Therefore, different types of environment data sets are adopted under different energy utilization scenes, the rationality of the input data of the recognizable model for the input environment can be improved, and the correctness of the output result of the recognizable model for the environment is ensured.

Based on the foregoing embodiments, in an embodiment of the present application, a federal learning framework is adopted to train a pre-constructed environment energy use recognition model, and during training, corresponding weights are set for different types of environment data sets participating in training according to energy use scenarios corresponding to various landmark buildings.

In the embodiment, the federal learning architecture is adopted to train the pre-constructed environment recognizable model, so that the privacy and the safety of data in different regions can be ensured, and meanwhile, the richness of the training data of the environment recognizable model can be ensured.

In addition, in the training process, different weights can be set for different types of environment data sets aiming at energy utilization scenes corresponding to landmark buildings, and it should be understood that the weight corresponding to the environment data set with higher energy utilization scene correlation degree is higher, and the weight corresponding to the environment data set with lower correlation degree is lower, so that the accuracy of the identification result of the environment energy utilization identification model aiming at different energy utilization scenes can be ensured.

Based on the embodiment shown in fig. 1, in an embodiment of the present application, the obtaining base station energy consumption data of each target base station includes:

and based on a non-invasive load monitoring technology, energy consumption monitoring is carried out on each target base station, a real-time load statistical model corresponding to each target base station is constructed to serve as base station energy consumption data corresponding to each target base station, and the real-time load statistical model comprises a single-source multi-dimensional statistical model described by energy consumption information of the target base station and a multi-source multi-dimensional statistical model described by energy consumption information of other base stations adjacent to the target base station.

In this embodiment, when obtaining the base station energy consumption data of each target base station, a non-intrusive load monitoring technique may be adopted to monitor the energy consumption of the target base station. It should be understood that the traditional measurement needs additional devices such as sensors to be connected to the nodes of the load for measurement, i.e. invasive measurement, and the non-invasive load monitoring technology is to analyze and process the total load electric meter data, and identify each electric device and the working state thereof by using a mathematical physical method through a load decomposition model, so that the method can be widely applied to the fields of buildings, energy conservation, smart cities, smart power grids and the like to reduce the resource consumption during monitoring.

During monitoring, the server may construct a real-time load statistical model corresponding to each target base station as base station energy consumption data corresponding to each target base station, where the real-time load statistical model may include a single-source multi-dimensional statistical model described by energy information of the target base station (for example, described by parameters such as a load mean value and a fluctuation condition of each energy consumption unit in the target base station), and a multi-source multi-dimensional statistical model described by energy information of other base stations adjacent to the target base station.

It should be understood that when a user moves, a communication base station can enable service to be switched between adjacent target base stations, and therefore, the energy utilization situation of a service scene can be better reflected according to the multi-source multi-dimensional statistical model described by the energy utilization information of other base stations adjacent to the target base station, and the energy utilization level of the target base station for subsequent identification is more accurate.

Based on the embodiment shown in fig. 1, in an embodiment of the present application, determining a corresponding energy saving policy according to an energy usage state of each energy consuming unit in a target base station of which the energy usage level is a second target level includes:

determining a total load power sequence corresponding to the target base station according to the energy utilization state of the target base station with the energy utilization level being a second target level, wherein the total load power sequence comprises a state sequence of each energy consumption unit in the target base station at each moment;

determining an optimized electric equipment state sequence corresponding to the total load power sequence based on an improved Viterbi algorithm;

and generating a corresponding energy-saving strategy according to the optimized electric equipment state sequence.

In this embodiment, according to the energy utilization state of the target base station with the energy utilization level being the second target level, it should be understood that the energy utilization state may be counted in real time and have a certain time duration, and therefore, the server may determine a total load power sequence corresponding to the target base station, where the total load power sequence includes a state sequence of each energy consuming unit in the target base station at each time. Therefore, according to the total load power sequence, the energy utilization condition of the target base station can be known, such as the switch state or energy utilization fluctuation condition of each load.

And the server determines an optimized electric equipment state sequence corresponding to the total load power sequence by adopting an improved Viterbi algorithm, wherein the Viterbi algorithm is a dynamic programming algorithm based on an HMM statistical model, and the optimal state sequence is searched by traversing all state transition conditions. The algorithm can search the optimal of all observation sequences, not only can improve the efficiency of optimizing the calculation of the state sequence of the electric equipment, but also can ensure the accuracy of the calculation.

Therefore, according to the calculated state sequence corresponding to each energy consumption unit in the optimized electric equipment state sequence, energy-saving measures corresponding to the target base station are generated, such as the time when a certain energy consumption unit is started and the time when the certain energy consumption unit is closed, and the like, so that energy-saving control of the target base station is realized, the whole target base station does not need to be closed, and user experience is improved.

Based on the technical solution of the above embodiment, a specific application scenario of the embodiment of the present application is introduced as follows:

fig. 2 is a schematic view of an application scenario of an energy saving method of a communication base station according to an embodiment of the present application, and the following description takes a target landmark building as a station as an example.

Referring to fig. 2, there are several base stations around the station, such as a ground macro station, a floor macro station, a micro station in a city, a building room division, a large-scale building room division, a tunnel room division, and so on. According to the energy-saving method of the communication base station, the service base station (namely the target base station) related to the station can be screened out by adopting a clustering algorithm.

Specifically, firstly, the base station position points and the landmark building geographical position points in the area are normalized to a d-dimensional space, STING grid division is performed, the original data points are replaced by the statistical information of grid unit data, the number of grid units is n, and a grid unit set E = { E } is obtained ₁ ,e ₂ ,…,e _n An attribute value of a grid data point is a spatial distance (i.e., a first distance) from a landmark building, and it should be noted that each grid unit may include at least one base station. The parameters commonly used for grid cells are shown in table 1 below:

TABLE 1

Grid parameters	Physical meaning of the parameter
		Count	Number of objects in the grid
Mean	Average of all values in the grid
		stdev	Standard deviation of attribute values in a grid
min	Minimum value of attribute values in a grid
		max	Maximum value of attribute values in a grid
distribution	Distribution type of attribute value coincidence in grid

Next, the density ρ of the grid cell is calculated _i Wherein the density ρ _i Describing the space distance between the grid cells and the target landmark building, and enabling each grid cell to be in accordance with the density rho _i The relative distance sigma of any two grid unit elements is calculated by adopting a distance formula between two points _i (i.e., second distance), specifically, point a in two grid cells is used first _di And b _di Calculating the Euclidean distance dis of two grid cells a and b _ab ：

And then according to the relative distance sigma between two grid cells _bi ：

Density rho corresponding to grid cell _i And a relative distance σ _i After visualization, a first distance corresponding to a certain grid unit may be used as a vertical coordinate, and a plurality of second distances corresponding to the grid unit may be used as horizontal coordinates, respectively, so as to obtain a plurality of coordinate points corresponding to the grid unit, and the coordinate points obtained by each grid unit may be displayed in a coordinate system. Determining the maximum value point of the coordinate points displayed in the coordinate system, determining the minimum value point on the connecting line of the two maximum value points to obtain a minimum value point set, and selecting the maximum density rho from the minimum value point set _i As a density threshold (i.e., distance threshold), a target base station, i.e., a corresponding density ρ, is thus determined from the respective base stations based on the density threshold _i And the base stations are smaller than or equal to the density threshold value, so that a target base station set is obtained.

Then, according to the characteristics (i.e. energy-using scene) of the area where the station is located, the environment data set is used as a people flow data set, a flow access data set and a mobility index data set of the target base station of the streaming media enterprise and the operator in the area of the station at different time periods. It should be understood that the selection of the environmental data set should be related to the energy consumption characteristics of the region.

And identifying the environment data set by adopting an environment energy-consumption identification model obtained by the Federal learning architecture training so as to output the energy consumption requirement grade corresponding to the target base station set. And when the target base station set is determined to have the energy-saving space, namely the corresponding energy consumption demand level is the first target level, acquiring base station energy consumption data corresponding to each target base station in the target base station set aiming at each target base station in the target base station set, and inputting the base station energy consumption data into the base station energy consumption identification model, so that the base station energy consumption identification model outputs the energy consumption level corresponding to each target base station. And if the energy utilization level is a second target level, carrying out energy utilization load analysis on the target base station, and determining the energy utilization state of each energy consumption unit so as to determine a corresponding energy-saving strategy.

Specifically, according to the energy utilization state of each energy consumption unit in the target base station, a corresponding total load power sequence is determined, and the total load power sequence Y = { Y = { ₁ ,y ₂ ,…y _n The number of load time contained is N, wherein the occurrence time of the nth load time is t _n ，

N belongs to {1,2, \ 8230;, N }. The total load power sequence Y is decomposed into D (D = N + 1) segments using N load events. Let t ₀ ＝1、t _N+1 = T +1, i.e. T ∈ {1,2, \8230;, T }, then the starting point of the d-th segment total load power sequence is T _d-1 End point is t _d -1, length l _d ＝t _d -t _d-1 Wherein D belongs to {1,2, \8230; D }. The Viterbi algorithm only considers that the electric equipment changes when a load event occurs, so that the Viterbi algorithm is suitable for occasions with more electric equipment or electric states.

First, a state set S = { S) =isdefined ₁ ,s ₂ ,…,s _k Where k is the number of states of the model, s _i The model is represented in the ith state, i belongs to {1,2, \8230;, K }, and assuming that the number of electric devices in the total load is M and the number of states of the electric devices M is K ^(m) Then, then

Representing a sequence of states q for a Viterbi variable of length T of the sequence of states (observation sequence) ₁ ,q ₂ ,……q _t And q is _t ＝s _i Will generate an observation sequence y ₁ ,y ₂ ,……y _t The maximum probability of (c).

The Viterbi variable is defined as follows:

in the formula, λ is a parameter of a given HMM model and can be obtained through historical electricity consumption data training.

The HMM model is a statistical model developed on the basis of a Markov chain, has double random processes, wherein one random process describes a transition rule between states and is an unobservable homogeneous Markov chain; another random state describes the statistical relationship between the individual states and the observations it produces and is observable. FIG. 3 is a schematic diagram of an HMM statistical model, wherein q is _t Representing the state of the model at time t, o _t Representing the observation of the model at time t.

The HMM model consists of the following 5 parts:

set of states S = { S = { S = } ₁ ,s ₂ ,…,s _k Where k is the number of states of the model, s _i Representing the ith state of the model.

An observation set V, V being discrete for discrete observations; for continuous observation, V is continuous.

State transition probability a = { a = _ij In which a is _ij Representing the slave state s of the model _i Is transferred to s _j Probability of (a) _ij ＝P(q _i+1 ＝s _j |q _i ＝s _i )。

Observation probability (or observation probability density) B = { B = { B } _i (o) }, in which b _i (o) represents in the state s _i Under the condition(s) of (a), the probability (or observed probability density) of o (o ∈ V) observed, i.e., b _i (o)＝P(o|s _i ). For discrete observations, b _i (o) probability of observation; for continuous observation, b _i (o) is the observed probability density.

Initial state probability pi = { pi = _i In which pi _i Indicates that the initial state is s _i Probability of (i.e. pi) _i ＝P(q ₁ ＝s _i )。

The method comprises the following concrete steps:

step1 for the auxiliary variable parameter delta _d ' (i) and psi _d ' (i) initialization. Delta _d ' (i) denotes along path (state sequence) Q ₁ ,Q ₂ …,Q _d And Q _d ＝s _i Generating an observation sequence y ₁ ,y ₂ ,…y _t Of (2), wherein Q _d Denotes the status of the d-th sequence, ψ' _d (i) Represents the maximum delta _d ' (i) state of the d-1 st sequence: psi ₁ '(i)＝0，

In the above formula, pi = { pi = _i Is the initial state probability, pi _i Indicates that the initial state is s _i Probability of (i.e. pi) _i ＝P(q ₁ ＝s _i )；a _ij Representing the slave state s of the model _i Is transferred to s _j Probability of (a) _ij ＝P(q _i+1 ＝s _j |q _i ＝s _i ) Then there is a state transition probability set a = { a = { a } _ij }；b _i For the observation probability (or observation probability density) parameter, there is a set B = { B = { _i (y _t ) In which b is _i (y _t ) Is shown in the state s _i Under the conditions of (1), observed as y _t Probability (or observed probability density) of (i.e. b) _i (y _t )＝P(y _t |s _i ). For discrete observations, b _i (y _t ) For continuous observation, b for probability of observation _i (y _t ) To observe the probability density.

And Step2, performing recursive calculation. Updating parameters

Wherein D belongs to {2,3, \8230; D };

step3, termination. Updating parameters

Step4, backtracking path (state sequence) and updating parameters

Wherein D = D-1, D-2, \ 8230, 1.

Finally obtaining the optimal electric equipment state sequence corresponding to the given total load power sequence Y through the steps

Wherein->

d∈{1,2，…D}。

Therefore, the energy-saving strategy corresponding to the target base station can be determined according to the optimal electric equipment state sequence (namely, the optimized electric equipment state sequence) so as to ensure the reasonability of the energy-saving strategy.

The following describes embodiments of an apparatus of the present application, which may be used to perform the energy saving method of the communication base station in the above embodiments of the present application. For details that are not disclosed in the embodiments of the apparatus of the present application, please refer to the embodiments of the energy saving method of the communication base station described above in the present application.

Fig. 4 shows a block diagram of an energy saving arrangement of a communication base station according to an embodiment of the present application.

Referring to fig. 4, an energy saving apparatus of a communication base station according to an embodiment of the present application includes:

a first determining module 410, configured to determine, according to location information of a target landmark building, a target base station set corresponding to the target landmark building;

a first obtaining module 420, configured to obtain, according to location information of each target base station and the target landmark building included in the target base station set, an environment data set corresponding to the target landmark building, where the environment data set is used to describe an energy consumption requirement of an environment where the target landmark building is located;

the first identification module 430 is configured to input the environment data set to a pre-trained environment recognition model, so that the environment recognition model outputs an energy consumption requirement level corresponding to an environment where the target landmark building is located;

a second obtaining module 440, configured to obtain base station energy consumption data of each target base station if the energy consumption requirement level is a first target level, where the first target level indicates that the target base station set has an energy saving space;

a second identification module 450, configured to input base station energy consumption data of each target base station into a base station energy consumption identification model trained in advance, so that the base station energy consumption identification model outputs an energy consumption level corresponding to each target base station, where the energy consumption level is used to describe an energy consumption size of the target base station;

a second determining module 460, configured to perform energy consumption load analysis on the target base station whose energy consumption level is a second target level, and determine an energy consumption state of each energy consumption unit of the target base station, where the second target level indicates that the target base station has an energy saving space;

and a processing module 470, configured to determine a corresponding energy saving policy according to the energy consumption state of each energy consumption unit in the target base station with the energy consumption level being the second target level.

In one embodiment of the present application, the first determining module 410 is configured to: according to the position information of the target landmark building, acquiring the position information of a base station to be selected in the area where the target landmark building is located; and clustering the base stations to be selected by adopting a clustering algorithm according to the position information of the base stations to be selected in the area where the target landmark building is located to obtain a target base station set corresponding to the target landmark building.

In one embodiment of the present application, the first determining module 410 is configured to: determining a first distance between each base station to be selected and the target landmark building and a second distance between every two base stations to be selected according to the position information of the target landmark building and the position information of each base station to be selected; determining a distance threshold corresponding to the target landmark building according to a first distance and a second distance corresponding to each base station to be selected; and selecting the base stations to be selected with the first distance smaller than or equal to the distance threshold value from all the base stations to be selected as target base stations to obtain a target base station set corresponding to the target landmark building.

In an embodiment of the present application, the first obtaining module 420 is configured to: determining an energy application scene corresponding to the target landmark building according to the category information of the target landmark building; and acquiring an environment data set corresponding to the energy utilization scene in the environment where the target landmark building is located according to the position information of the target landmark building and each target base station contained in the target base station set.

In an embodiment of the application, a federal learning architecture is adopted to train a pre-constructed environment energy use recognition model, and during training, corresponding weights are set for environment data sets of different types participating in training according to energy use scenes corresponding to various landmark buildings.

In an embodiment of the present application, the second obtaining module 440 is configured to: and based on a non-invasive load monitoring technology, energy consumption monitoring is carried out on each target base station, a real-time load statistical model corresponding to each target base station is constructed to serve as base station energy consumption data corresponding to each target base station, and the real-time load statistical model comprises a single-source multi-dimensional statistical model described by energy consumption information of the target base station and a multi-source multi-dimensional statistical model described by energy consumption information of other base stations adjacent to the target base station.

In one embodiment of the present application, the processing module 470 is configured to: determining a total load power sequence corresponding to the target base station according to the energy utilization state of the target base station with the energy utilization level being a second target level, wherein the total load power sequence comprises a state sequence of each energy consumption unit in the target base station at each moment; determining an optimized electric equipment state sequence corresponding to the total load power sequence based on a Viterbi algorithm; and generating a corresponding energy-saving strategy according to the optimized electric equipment state sequence.

It should be noted that the computer system of the electronic device shown in fig. 5 is only an example, and should not bring any limitation to the functions and the application scope of the embodiments of the present application.

As shown in fig. 5, the computer system includes a Central Processing Unit (CPU) 501, which can perform various appropriate actions and processes, such as performing the methods described in the above embodiments, according to a program stored in a Read-Only Memory (ROM) 502 or a program loaded from a storage section 508 into a Random Access Memory (RAM) 503. In the RAM 503, various programs and data necessary for system operation are also stored. The CPU 501, ROM 502, and RAM 503 are connected to each other through a bus 504. An Input/Output (I/O) interface 505 is also connected to bus 504.

The following components are connected to the I/O interface 505: an input portion 506 including a keyboard, a mouse, and the like; an output section 507 including a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, a speaker, and the like; a storage portion 508 including a hard disk and the like; and a communication section 509 including a Network interface card such as a LAN (Local Area Network) card, a modem, or the like. The communication section 509 performs communication processing via a network such as the internet. The driver 510 is also connected to the I/O interface 505 as necessary. A removable medium 511 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 510 as necessary, so that a computer program read out therefrom is mounted into the storage section 508 as necessary.

In particular, according to embodiments of the application, the processes described above with reference to the flow diagrams may be implemented as computer software programs. For example, embodiments of the present application include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising a computer program for performing the method illustrated by the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 509, and/or installed from the removable medium 511. The computer program executes various functions defined in the system of the present application when executed by a Central Processing Unit (CPU) 501.

It should be noted that the computer readable medium shown in the embodiments of the present application may be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a Read-Only Memory (ROM), an Erasable Programmable Read-Only Memory (EPROM), a flash Memory, an optical fiber, a portable Compact Disc Read-Only Memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present application, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In this application, however, a computer readable signal medium may include a propagated data signal with a computer program embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. The computer program embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. Each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units described in the embodiments of the present application may be implemented by software, or may be implemented by hardware, and the described units may also be disposed in a processor. Wherein the names of the elements do not in some way constitute a limitation on the elements themselves.

As another aspect, the present application also provides a computer-readable medium, which may be contained in the electronic device described in the above embodiments; or may exist separately without being assembled into the electronic device. The computer readable medium carries one or more programs, which when executed by one of the electronic devices, cause the electronic device to implement the method described in the above embodiments.

It should be noted that although in the above detailed description several modules or units of the device for action execution are mentioned, such a division is not mandatory. Indeed, the features and functions of two or more modules or units described above may be embodied in one module or unit according to embodiments of the application. Conversely, the features and functions of one module or unit described above may be further divided into embodiments by a plurality of modules or units.

Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein may be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solution according to the embodiments of the present application may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (which may be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which may be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the embodiments of the present application.

Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the embodiments disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains.

It will be understood that the present application is not limited to the precise arrangements that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the application is limited only by the appended claims.

Claims

1. A method for saving power in a communication base station, comprising:

and determining a corresponding energy-saving strategy according to the energy utilization state of each energy consumption unit in the target base station with the energy utilization level as the second target level.

2. The method of claim 1, wherein determining a set of target base stations corresponding to a target landmark building according to the location information of the target landmark building comprises:

3. The method according to claim 2, wherein the step of clustering the base stations to be selected according to the position information of the base stations to be selected in the area where the landmark building is located by using a clustering algorithm to obtain a target base station set corresponding to the landmark building comprises the steps of:

4. The method of claim 1, wherein obtaining the environment data set corresponding to the target landmark building according to the position information of each target base station and the target landmark building included in the target base station set comprises:

5. The method according to claim 4, characterized in that a pre-constructed environment energy use recognition model is trained by adopting a federal learning architecture, and during training, corresponding weights are set for environment data sets of different types participating in training according to energy use scenes corresponding to various landmark buildings.

6. The method of claim 1, wherein obtaining base station energy consumption data for each of the target base stations comprises:

and based on a non-intrusive load monitoring technology, energy consumption monitoring is carried out on each target base station, a real-time load statistical model corresponding to each target base station is constructed to serve as base station energy consumption data corresponding to each target base station, and the real-time load statistical model comprises a single-source multi-dimensional statistical model described by energy consumption information of the target base station and a multi-source multi-dimensional statistical model described by energy consumption information of other base stations adjacent to the target base station.

7. The method of claim 1, wherein determining the corresponding energy saving policy according to the energy usage status of each energy consuming unit in the target base station with the energy usage level being a second target level comprises:

8. An energy saving apparatus for a communication base station, comprising:

9. A computer-readable medium, on which a computer program is stored which, when being executed by a processor, carries out the method for energy saving of a communication base station according to any one of claims 1 to 7.

10. An electronic device, comprising:

one or more processors;

storage means for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to implement the method for energy saving of a communication base station according to any one of claims 1 to 7.