Method and device for measuring energy saving amount of base station equipment, and computing device

Abstract

The application discloses an energy-saving amount measuring and calculating method and device of a base station equipment and a calculating device, and the method comprises the following steps: acquiring index data of a plurality of time periods of a cell corresponding to a to-be-measured equipment; the index data comprises network management performance data and configuration parameter data; the index data in the plurality of time periods is respectively input into a first energy consumption model for processing, so as to obtain a plurality of first powers corresponding to the plurality of time periods in the case that energy-saving shutdown does not take effect; the index data in the plurality of time periods is respectively input into a second energy consumption model for processing, so as to obtain a plurality of second powers corresponding to the plurality of time periods in the case that energy-saving shutdown takes effect; and the energy-saving amount of the to-be-measured equipment is calculated according to the plurality of first powers and the plurality of second powers. In the above manner, the equipment power consumption in the case that energy-saving shutdown takes effect and does not take effect in each time period of the equipment can be restored, the influence of cell load change on the energy-saving amount can be eliminated, the energy-saving amount can be accurately calculated, and the accuracy of the energy-saving amount measuring and calculating can be improved.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and specifically to a method, apparatus, and computing device for calculating the energy savings of base station equipment. Background Technology

[0002] With the rapid development of mobile communication services, major operators have accelerated the pace of network construction, resulting in a significant increase in the number of base stations. This has brought about new problems, namely, the rapid increase in base station energy consumption, which has increased the cost for operators. Therefore, it is imperative to reduce base station energy consumption and save energy and reduce emissions.

[0003] Currently, the main methods for reducing power consumption and achieving energy conservation and emission reduction are hardware-based energy saving and software-based energy saving. Hardware-based energy saving refers to reducing power consumption by using more advanced chip technology, more integrated functional chips, or higher power amplifier efficiency. Software-based energy saving refers to software flexibly shutting down some devices or carriers based on cell load while meeting certain wireless performance requirements, in order to save energy. Software-based energy saving shutdown techniques include symbol shutdown, channel shutdown, and carrier shutdown, etc. In addition, cell shutdown is also a commonly used shutdown method, which involves migrating the traffic of the cell to be shut down to a compensating cell. In this case, the energy consumption of the equipment in the shut-down cell decreases due to the reduction in traffic, and at the same time, the energy-saving shutdown takes effect because the reduced traffic meets the conditions for energy saving shutdown, thus reducing energy consumption.

[0004] In existing technologies, the method for evaluating the effectiveness of energy-saving shutdown is to statistically analyze the average power of equipment when energy saving is not enabled for several days, and the average power of equipment after energy saving is enabled. The difference between the two is then multiplied by the duration of energy saving to obtain the energy saving. However, this evaluation method does not take into account the changes in equipment power consumption caused by changes in cell load before and after energy saving is enabled. In terms of calculating the energy saving of communication main equipment, it lacks rigor and is prone to errors. Summary of the Invention

[0005] In view of the above problems, the present invention is proposed to provide a method, apparatus and computing device for calculating the energy saving of base station equipment that overcomes or at least partially solves the above problems.

[0006] According to one aspect of the present invention, a method for calculating the energy saving of a base station device is provided, comprising:

[0007] Obtain indicator data for multiple time periods for the cell corresponding to the device under test; the indicator data includes network management performance data and configuration parameter data;

[0008] The index data for multiple time periods are input into the first energy consumption model for processing to obtain multiple first power values ​​for the same time period when energy-saving shutdown is ineffective.

[0009] The index data for multiple time periods are input into the second energy consumption model for processing to obtain multiple second power values ​​under the conditions of energy-saving shutdown for multiple time periods.

[0010] The energy saving of the device under test is calculated based on multiple first power and multiple second power.

[0011] Optionally, network management performance data includes at least one of the following:

[0012] Average uplink and downlink PRB utilization, maximum number of users established for connection establishment, average number of users established for connection establishment, uplink and downlink traffic, radio utilization, PDCCH resource utilization, and VoLTE voice traffic.

[0013] The configuration parameter data includes at least one of the following: number of carriers, number of channels, and power per channel.

[0014] Optionally, the method further includes:

[0015] Based on the manufacturer information, model information, and energy-saving shutdown technology information of the device under test, the corresponding first energy consumption model and second energy consumption model are matched.

[0016] Optionally, the method further includes:

[0017] Obtain sample indicator data; the sample indicator data includes: network management performance data, configuration parameter dimension data, and average power data;

[0018] The sample indicator data is classified into sample indicator data of the shutdown effective category and sample indicator data of the shutdown ineffective category.

[0019] The first energy consumption model is trained based on the sample index data of the ineffective shutdown category;

[0020] The second energy consumption model was trained based on the sample index data of the shutdown effective class.

[0021] Optionally, classifying the sample indicator data further includes:

[0022] The sample indicator data are classified according to the number of symbol shutdown subframes, carrier shutdown duration, and / or channel shutdown duration of the corresponding cell of the sample equipment.

[0023] Optionally, the sample indicator data can be further classified according to the number of symbol shutdown subframes, carrier shutdown duration, and / or channel shutdown duration of the cell corresponding to the sample equipment, including:

[0024] If the carrier shutdown duration reaches the first preset value, the channel shutdown duration reaches the second preset value, or the proportion of symbol shutdown subframes reaches the third preset value, then the sample index data will be classified as shutdown effective sample index data.

[0025] If the carrier shutdown duration is zero, the channel shutdown duration is zero, and the number of shutdown subframes is zero, then the sample index data will be classified as sample index data of the shutdown ineffective category.

[0026] Optionally, the method further includes:

[0027] Preprocess the indicator data of the device under test; preprocess the indicator data of the sample.

[0028] The preprocessing includes: normalizing the network management performance data and performing one-hot encoding on the configuration parameter data.

[0029] According to another aspect of the present invention, an energy-saving measurement device for a base station equipment is provided, comprising:

[0030] The data acquisition module is suitable for acquiring indicator data for multiple time periods of the cell corresponding to the device under test; among which, the indicator data includes network management performance data and configuration parameter data;

[0031] The model processing module is suitable for inputting index data from multiple time periods into a first energy consumption model for processing to obtain multiple first power values ​​under the condition that energy-saving shutdown is ineffective for multiple time periods; and for inputting index data from multiple time periods into a second energy consumption model for processing to obtain multiple second power values ​​under the condition that energy-saving shutdown is effective for multiple time periods.

[0032] The calculation module is suitable for calculating the energy saving of the device under test based on multiple first power and multiple second power.

[0033] Optionally, network management performance data includes at least one of the following:

[0034] Average uplink and downlink PRB utilization, maximum number of users established for connection establishment, average number of users established for connection establishment, uplink and downlink traffic, radio utilization, PDCCH resource utilization, and VoLTE voice traffic.

[0035] The configuration parameter data includes at least one of the following: number of carriers, number of channels, and power per channel.

[0036] Optionally, the device further includes:

[0037] The matching module is suitable for matching the corresponding first energy consumption model and second energy consumption model based on the manufacturer information, model information and energy-saving shutdown technology information of the device under test.

[0038] Optionally, the device further includes:

[0039] The model training module is suitable for acquiring sample indicator data, which includes network management performance data, configuration parameter dimension data, and average power data. The sample indicator data is classified to obtain sample indicator data for the shutdown effective category and sample indicator data for the shutdown ineffective category. Based on the sample indicator data for the shutdown ineffective category, a first energy consumption model is trained. Based on the sample indicator data for the shutdown effective category, a second energy consumption model is trained.

[0040] Optionally, the model training module is further adapted to classify the sample index data according to the number of symbol shutdown subframes, carrier shutdown duration and / or channel shutdown duration of the cell corresponding to the sample device.

[0041] Optionally, the model training module is further adapted to:

[0042] If the carrier shutdown duration reaches the first preset value, the channel shutdown duration reaches the second preset value, or the proportion of symbol shutdown subframes reaches the third preset value, then the sample index data will be classified as shutdown effective sample index data.

[0043] If the carrier shutdown duration is zero, the channel shutdown duration is zero, and the number of shutdown subframes is zero, then the sample index data will be classified as sample index data of the shutdown ineffective category.

[0044] Optionally, the device further includes:

[0045] The preprocessing module is suitable for preprocessing the indicator data of the device under test and preprocessing the sample indicator data. The preprocessing includes: normalizing the network management performance data and performing one-hot encoding on the configuration parameter data.

[0046] According to another aspect of the present invention, a computing device is provided, comprising: a processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other via the communication bus;

[0047] The memory is used to store at least one executable instruction, which causes the processor to perform the operation corresponding to the energy saving calculation method of the base station equipment.

[0048] According to another aspect of the present invention, a computer storage medium is provided, the storage medium storing at least one executable instruction, the executable instruction causing a processor to perform an operation corresponding to the energy saving calculation method of the base station device described above.

[0049] According to the energy-saving calculation method, apparatus, and computing device of the present invention, multiple time-period index data of the cell corresponding to the device under test are acquired; wherein, the index data includes network management performance data and configuration parameter data; the index data in the multiple time periods are respectively input into a first energy consumption model for processing to obtain multiple first power under the condition that energy-saving shutdown is ineffective in the multiple time periods; the index data in the multiple time periods are respectively input into a second energy consumption model for processing to obtain multiple second power under the condition that energy-saving shutdown is effective in the multiple time periods; the energy saving of the device under test is calculated based on the multiple first power and multiple second power. Through the above method, the power consumption of the device at each moment under the condition that energy-saving shutdown is effective and ineffective can be restored, the influence of cell load changes on energy saving can be eliminated, thereby accurately calculating energy saving, and at the same time, the error introduced by unquantifiable factors can be eliminated, thereby improving the accuracy of energy saving measurement.

[0050] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it in accordance with the contents of the specification, and in order to make the above and other objects, features and advantages of the present invention more apparent and understandable, specific embodiments of the present invention are described below. Attached Figure Description

[0051] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0052] Figure 1 A flowchart of the energy-saving calculation method for base station equipment provided in an embodiment of the present invention is shown;

[0053] Figure 2 A flowchart of a method for calculating the energy savings of a base station device according to another embodiment of the present invention is shown;

[0054] Figure 3 A schematic diagram of the energy-saving measurement device for base station equipment provided in an embodiment of the present invention is shown;

[0055] Figure 4 A schematic diagram of the structure of a computing device provided in an embodiment of the present invention is shown. Detailed Implementation

[0056] Exemplary embodiments of the invention will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this invention will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.

[0057] Figure 1 A flowchart of the energy-saving calculation method for base station equipment provided in an embodiment of the present invention is shown, as follows: Figure 1 As shown, the method includes the following steps:

[0058] Step S110: Obtain indicator data for multiple time periods for the cell corresponding to the device under test; wherein, the indicator data includes network management performance data and configuration parameter data.

[0059] Among them, multiple time periods are consecutive time periods with equal duration. For example, they can be multiple time periods divided into the smallest time period within the time period to be tested.

[0060] Verification using traffic volume data and single-board power consumption data in the network management system revealed that the power consumption of the main communication equipment largely depends on network load (performance data) and configuration parameters. Network management performance data includes: average uplink and downlink PRB utilization, maximum number of users establishing a connection, average number of users establishing a connection, uplink and downlink traffic, wireless utilization, PDCCH resource utilization, and VoLTE voice traffic. Configuration parameter data includes: number of carriers, number of channels, and single-channel power.

[0061] Step S120: Input the index data for multiple time periods into the first energy consumption model for processing to obtain multiple first power values ​​for the time periods when energy saving shutdown is ineffective.

[0062] The first energy consumption model is used to calculate power consumption when energy-saving shutdown is ineffective. It is pre-trained based on sample data. For any given time period, the indicator data is input into the first energy consumption model for calculation to obtain the power consumption during that time period when energy-saving shutdown is ineffective.

[0063] Step S130: Input the index data for multiple time periods into the second energy consumption model for processing to obtain multiple second power values ​​under the conditions of energy-saving shutdown for multiple time periods.

[0064] The second energy consumption model is used to calculate power consumption when energy-saving shutdown is in effect, and it is pre-trained based on sample data. For any given time period, the index data is input into the second energy consumption model for calculation to obtain the power consumption under the condition that energy-saving shutdown is in effect during that time period.

[0065] Step S140: Calculate the energy saving of the device under test based on multiple first power and multiple second power.

[0066] In one alternative approach, the first and second power values ​​corresponding to the same time period are subtracted to obtain the power difference value. Then, based on the power difference values ​​corresponding to each time period and the duration of each time period, the energy saving of the device under test during the test period is calculated. For example, if the duration of the time period is 1 hour, the energy saving of the device under test during the test period is obtained by summing up the power differences.

[0067] In one alternative approach, the first power consumption under the condition that energy-saving shutdown is ineffective is calculated based on the first power corresponding to each time period. Simultaneously, the second power consumption under the condition that energy-saving shutdown is effective is calculated based on the second power corresponding to each time period. Finally, the difference between the first power consumption and the second power consumption is calculated, which yields the energy saving of the device under test during the test period.

[0068] Therefore, the concept of the energy-saving calculation method in the embodiments of the present invention is as follows:

[0069] C = ∑(D - D')

[0070] Wherein, the duration of the time period is 1 hour, D is the power of the equipment when the energy-saving shutdown is not effective during the time period, and D' is the power of the equipment when the energy-saving shutdown is effective during the time period.

[0071] The power D under the condition that energy-saving shutdown is ineffective and the power D' under the condition that energy-saving shutdown is effective are calculated using algorithm fitting, respectively, as follows:

[0072] D = k1X1 + k2X2 + y

[0073] D'=k1'X1+k2'X2+y

[0074] Where matrix X1 is the network management performance matrix, matrix X2 is the configuration parameter matrix, matrices k1, k2, k1', and k2' are the algorithm fitting coefficients, and matrix y represents the power consumption caused by unquantifiable factors. Based on the formula for calculating energy savings, we can obtain:

[0075] C=∑(k1X1+k2X2+y-k1'X1-k2'X2-y)=∑(k1X1+k2X2-k1'X1-k2'X2)

[0076] In existing technologies, the energy-saving algorithm is: C = (AB) * T, where A is the average power of the equipment during the period when energy saving is not enabled, B is the average power of the equipment during the period when energy saving is enabled, and T is the time when energy saving is enabled. However, the load of the community changes before and after energy saving is enabled, and the change in community load will directly or indirectly cause the change in the power consumption of the equipment. Therefore, the energy saving calculated by this method also includes the energy saving caused by the change in community load, and not all of it is caused by the energy saving shutdown taking effect, thus causing errors in the evaluation of the energy saving effect of the shutdown technology.

[0077] According to the energy-saving calculation method for base station equipment provided in this embodiment, indicator data for multiple time periods of the cell corresponding to the device under test are obtained. The indicator data includes network management performance data and configuration parameter data. The indicator data for multiple time periods are input into a first energy consumption model for processing to obtain multiple first powers under the condition that energy saving shutdown is effective for multiple time periods. The indicator data for multiple time periods are input into a second energy consumption model for processing to obtain multiple second powers under the condition that energy saving shutdown is ineffective for multiple time periods. A first power consumption is calculated based on the multiple first powers, and a second power consumption is calculated based on the multiple second powers. The difference between the first power consumption and the second power consumption is calculated to obtain the energy saving of the device under test. Through the above method, by using different energy consumption models, the power consumption of the device in each time period can be obtained, restoring the power consumption of the device at each moment under the condition that energy saving shutdown is effective and ineffective, eliminating the influence of cell load changes on power saving, thereby accurately calculating power saving, and eliminating errors introduced by unquantifiable factors, thus improving the accuracy of power saving measurement.

[0078] Figure 2 A flowchart of a method for calculating the energy savings of a base station device according to another embodiment of the present invention is shown, as follows: Figure 2 As shown, the method includes the following steps:

[0079] Step S210: Obtain sample indicator data; wherein, the sample indicator data includes: network management performance data, configuration parameter dimension data, and average power data.

[0080] Specifically, pilot sites served by the sample equipment are selected, and sample indicator data of the corresponding cells served by the sample equipment in the pilot sites are collected at a preset time interval, that is, sample indicator data for each time period are collected.

[0081] Optionally, the preset duration can be 1 hour, or it can be set to a shorter duration, which can be flexibly set according to the accuracy requirements in practical applications. Further optionally, the time granularity of the sample indicator data is consistent with the time granularity of the indicator data collected from the device under test.

[0082] The sample metrics data specifically include network management performance data, configuration parameter dimension data, and average power data. Network management performance data includes: average uplink / downlink PRB utilization, maximum number of users establishing a connection, average number of users establishing a connection, uplink / downlink traffic, radio utilization, PDCCH resource utilization, and VoLTE voice traffic. Configuration parameter data includes: number of carriers, number of channels, and single-channel power. Average power data is the device's average power over an hour.

[0083] In one alternative approach, the sample indicator data is dimensionality reduced to select the modeling indicator data, for example, through chi-square test, Pearson correlation analysis, analysis of variance, etc.

[0084] Step S220: Classify the sample indicator data to obtain sample indicator data of the shutdown effective category and sample indicator data of the shutdown ineffective category.

[0085] Specifically, the sample index data are classified according to the three phase indicators: the number of symbol shutdown subframes, the channel shutdown duration, and the carrier shutdown duration.

[0086] If the duration of carrier shutdown reaches the first preset value, the duration of channel shutdown reaches the second preset value, or the proportion of symbol shutdown subframes reaches the third preset value within a time period, then the sample index data corresponding to that time period will be classified as sample index data of the shutdown effective category.

[0087] If the carrier shutdown duration is zero, the channel shutdown duration is zero, and the number of shutdown subframes is zero within a given time period, then the corresponding sample index data within that time period will be classified as sample index data of the shutdown ineffective category.

[0088] Step S230: Train the first energy consumption model based on the sample index data of the ineffective shutdown class; train the second energy consumption model based on the sample index data of the effective shutdown class.

[0089] In one optional approach, the sample indicator data is preprocessed before training the model. Specifically, this includes: performing null value imputation and normalization on network management performance data; null value imputation can use the median, and data with null values ​​is discarded if the data volume exceeds a predetermined value. Configuration parameter data is encoded using one-hot encoding. For average power data, outliers are analyzed to determine their correlation with various fields in the network management performance data. If the average power within a time period is outside the standard range, and the difference in network management performance data within that time period compared to other time periods is within a preset range, it is considered dirty data. If the average power is outside the standard range, but the performance data also changes accordingly, it is considered usable data.

[0090] Optionally, for each type of sample indicator data, the sample indicator data set is divided according to a preset ratio to obtain a training set for training the machine learning model and a test set for verifying the accuracy of the machine learning model.

[0091] In one alternative approach, the GBRT (gradient boosting regression tree) algorithm is used to build both the first and second energy-consuming models. GBRT reduces the residuals of the previous model through further calculations, and a new model is built on the gradient resulting from the reduced residuals. This process is iterated continuously, with each calculation accumulated to obtain the final result. The specific training method is as follows:

[0092] (1) Data sample {x i ,y i}, i∈[1,n], matrix x i To input network management performance data and configuration parameter data, matrix y i This represents the average power of the network management equipment.

[0093] (2) Initialize the loss function, which is as follows:

[0094]

[0095] Among them, y i The average power of the equipment. Predict power for the model.

[0096] (3) Given an initial value β:

[0097]

[0098] (4) For the number of iterations m, find the reciprocal of the model at iteration m-1 (the gradient direction of the residual):

[0099]

[0100] (5) Using the result of the previous step as a pseudo dependent variable, fit the sample set {x} i y i}, and obtain the parameter α m The fitted model is:

[0101] h{x i α m}

[0102] (6) Based on the principle of minimizing the loss function, obtain the new step size β of the model. m As weights in the current model:

[0103]

[0104] (7) Update the model:

[0105] f m (x)=f m-1 (x)+β m h(x i ,α m )

[0106] (8) After M iterations, the regression tree is obtained:

[0107]

[0108] Of course, in practical applications, other algorithms can also be used to train the first energy consumption model and the second energy consumption model.

[0109] Step S240: Based on the manufacturer information, model information, and energy-saving shutdown technology information of the device under test, match the corresponding first energy consumption model and second energy consumption model.

[0110] In one optional approach, a first energy consumption model and a second energy consumption model are trained separately for base station equipment from different manufacturers, models, and using different shutdown technologies. In subsequent calculations, the appropriate energy consumption model is selected based on the manufacturer, model, and energy-saving shutdown technology of the equipment under test. This method can further improve the accuracy of energy saving calculations.

[0111] Based on the manufacturer, model, and energy-saving shutdown technology of the device under test, find the first and second energy consumption models corresponding to the same manufacturer, model, and shutdown technology.

[0112] Step S250: Input the index data for multiple time periods into the first energy consumption model for processing to obtain multiple first power values ​​for the time periods when energy saving shutdown is ineffective.

[0113] Among them, multiple time periods are multiple consecutive time periods of equal duration within the time period to be tested.

[0114] For any given time period, the index data is input into the first energy consumption model for calculation. The first energy consumption model outputs the first power under the condition that energy-saving shutdown is ineffective for that time period.

[0115] Step S260: Input the index data for multiple time periods into the second energy consumption model for processing to obtain multiple second power values ​​under the conditions of energy-saving shutdown for multiple time periods.

[0116] For any given time period, the index data is input into the second energy consumption model for calculation. The second energy consumption model outputs the second power under the condition that energy-saving shutdown is effective for that time period.

[0117] Step S270: Calculate the energy saving of the device under test based on multiple first power and multiple second power.

[0118] Based on the first power corresponding to multiple time periods, the power consumption under the condition that energy-saving shutdown is ineffective during the test period is calculated. Based on the second power corresponding to multiple time periods, the power consumption under the condition that energy-saving shutdown is effective during the test period is calculated. Finally, the energy saving of the device under test during the test period is calculated as a result of the difference.

[0119] Existing energy-saving calculation methods calculate energy savings by subtracting the power consumption of equipment during periods when energy saving is not enabled and those during periods when it is enabled. However, traffic volume varies across different time periods, affecting energy consumption. Therefore, existing technologies cannot accurately calculate the energy savings resulting from energy-saving shutdown. In this embodiment, machine learning modeling is used to reconstruct the power consumption of the equipment during different time periods when energy saving is enabled and disabled, thereby calculating energy savings. This eliminates the error introduced by varying traffic volume between energy-saving and non-energy-saving periods, resulting in more accurate energy-saving calculations.

[0120] In energy-saving methods for cell shutdown, after the traffic of the shut-down cell is migrated to the compensating cell, the energy consumption of the equipment in the shut-down cell decreases due to the reduction in traffic. Simultaneously, because the reduction in traffic meets the conditions for soft energy-saving shutdown, the software shutdown takes effect, further reducing energy consumption. Therefore, existing energy-saving calculation methods cannot eliminate the impact of traffic changes on energy savings. However, the method in this embodiment can calculate only the equipment energy savings resulting from carrier shutdown, channel shutdown, and symbol shutdown after traffic migration, eliminating errors introduced by traffic changes and providing more accurate energy-saving calculation results.

[0121] In summary, the energy-saving calculation method for base station equipment provided in this embodiment uses machine learning modeling to reconstruct the power consumption of the equipment when energy-saving shutdown is effective and ineffective in various time periods, thus reconstructing the energy consumption of the equipment at each moment and accurately calculating the energy saving. This eliminates the error introduced by different service volumes, making the energy saving calculation results more accurate. Furthermore, by establishing a power consumption model, it can meet the calculation needs of massive amounts of data, improve the efficiency of energy saving calculation, and has strong reusability.

[0122] Figure 3 A schematic diagram of the energy-saving measurement device for base station equipment provided in an embodiment of the present invention is shown, as follows: Figure 3 As shown, the device includes:

[0123] The data acquisition module 31 is suitable for acquiring indicator data for multiple time periods of the cell corresponding to the device under test; wherein, the indicator data includes network management performance data and configuration parameter data;

[0124] The model processing module 32 is adapted to input the index data of multiple time periods into the first energy consumption model for processing to obtain multiple first power values ​​under the condition that the energy-saving shutdown is ineffective for multiple time periods; and to input the index data of multiple time periods into the second energy consumption model for processing to obtain multiple second power values ​​under the condition that the energy-saving shutdown is effective for multiple time periods.

[0125] The calculation module 33 is adapted to calculate the energy saving of the device under test based on multiple first power and multiple second power.

[0126] In one alternative approach, network management performance data includes at least one of the following:

[0127] Average uplink and downlink PRB utilization, maximum number of users established for connection establishment, average number of users established for connection establishment, uplink and downlink traffic, radio utilization, PDCCH resource utilization, and VoLTE voice traffic.

[0128] The configuration parameter data includes at least one of the following: number of carriers, number of channels, and power per channel.

[0129] In one alternative embodiment, the device further includes:

[0130] The matching module is suitable for matching the corresponding first energy consumption model and second energy consumption model based on the manufacturer information, model information and energy-saving shutdown technology information of the device under test.

[0131] In one alternative embodiment, the device further includes:

[0132] The model training module is suitable for acquiring sample indicator data, which includes network management performance data, configuration parameter dimension data, and average power data. The sample indicator data is classified to obtain sample indicator data for the shutdown effective category and sample indicator data for the shutdown ineffective category. Based on the sample indicator data for the shutdown ineffective category, a first energy consumption model is trained. Based on the sample indicator data for the shutdown effective category, a second energy consumption model is trained.

[0133] In an alternative approach, the model training module is further adapted to classify the sample index data according to the number of symbol shutdown subframes, carrier shutdown duration, and / or channel shutdown duration of the cell corresponding to the sample device.

[0134] In one alternative approach, the model training module is further adapted to:

[0135] If the carrier shutdown duration reaches the first preset value, the channel shutdown duration reaches the second preset value, or the proportion of symbol shutdown subframes reaches the third preset value, then the sample index data will be classified as shutdown effective sample index data.

[0136] If the carrier shutdown duration is zero, the channel shutdown duration is zero, and the number of shutdown subframes is zero, then the sample index data will be classified as sample index data of the shutdown ineffective category.

[0137] In one alternative embodiment, the device further includes:

[0138] The preprocessing module is suitable for preprocessing the indicator data of the device under test and preprocessing the sample indicator data. The preprocessing includes: normalizing the network management performance data and performing one-hot encoding on the configuration parameter data.

[0139] By using the above methods and different energy consumption models, the power consumption of the equipment in each time period can be obtained, and the power consumption of the equipment at each moment under the conditions of energy saving shutdown being effective and ineffective can be restored. This can eliminate the impact of changes in community load on power saving, thereby accurately calculating power saving. At the same time, it can eliminate the error introduced by unquantifiable factors and improve the accuracy of power saving measurement.

[0140] This invention provides a non-volatile computer storage medium storing at least one executable instruction that can execute the energy-saving calculation method for base station equipment in any of the above method embodiments.

[0141] Figure 4 The diagram shows a structural schematic of an embodiment of the computing device of the present invention. The specific embodiments of the present invention do not limit the specific implementation of the computing device.

[0142] like Figure 4 As shown, the computing device may include: a processor 402, a communications interface 404, a memory 406, and a communications bus 408.

[0143] The processor 402, communication interface 404, and memory 406 communicate with each other via communication bus 408. Communication interface 404 is used to communicate with other network elements, such as clients or other servers. Processor 402 executes program 410, specifically performing the relevant steps in the above-described embodiment of the energy-saving measurement method for base station equipment used in computing devices.

[0144] Specifically, program 410 may include program code that includes computer operation instructions.

[0145] Processor 402 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention. The computing device includes one or more processors, which may be processors of the same type, such as one or more CPUs; or processors of different types, such as one or more CPUs and one or more ASICs.

[0146] Memory 406 is used to store program 410. Memory 406 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0147] The algorithms or displays provided herein are not inherently related to any particular computer, virtual system, or other device. Various general-purpose systems can also be used in conjunction with the teachings herein. The required structure for constructing such systems is apparent from the above description. Furthermore, the embodiments of the present invention are not directed to any particular programming language. It should be understood that the content of the invention described herein can be implemented using various programming languages, and the above description of specific languages ​​is for the purpose of disclosing the best mode of implementation of the invention.

[0148] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0149] Similarly, it should be understood that, in order to simplify the invention and aid in understanding one or more of the various inventive aspects, features of the embodiments of the invention are sometimes grouped together in a single embodiment, figure, or description thereof in the above description of exemplary embodiments of the invention. However, this disclosure should not be construed as reflecting an intention that the claimed invention requires more features than are expressly recited in each claim. Rather, as reflected in the following claims, inventive aspects lie in fewer than all features of a single foregoing disclosed embodiment. Therefore, the claims following the detailed description are hereby expressly incorporated into this detailed description, wherein each claim itself is a separate embodiment of the invention.

[0150] Those skilled in the art will understand that modules in the device of the embodiments can be adaptively changed and placed in one or more devices different from that embodiment. Modules, units, or components in the embodiments can be combined into a single module, unit, or component, and further, they can be divided into multiple sub-modules, sub-units, or sub-components. Except where at least some of such features and / or processes or units are mutually exclusive, any combination can be used to combine all features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all processes or units of any method or device so disclosed. Unless expressly stated otherwise, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) may be replaced by an alternative feature that serves the same, equivalent, or similar purpose.

[0151] Furthermore, those skilled in the art will understand that although some embodiments herein include certain features included in other embodiments but not others, combinations of features from different embodiments are intended to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments can be used in any combination.

[0152] The various component embodiments of the present invention can be implemented in hardware, or as software modules running on one or more processors, or a combination thereof. Those skilled in the art will understand that microprocessors or digital signal processors (DSPs) can be used in practice to implement some or all of the functions of some or all of the components according to the embodiments of the present invention. The present invention can also be implemented as a device or apparatus program (e.g., a computer program and computer program product) for performing part or all of the methods described herein. Such programs implementing the present invention can be stored on a computer-readable medium, or can be in the form of one or more signals. Such signals can be downloaded from an Internet website, provided on a carrier signal, or provided in any other form.

[0153] It should be noted that the above embodiments are illustrative of the invention and not restrictive, and that those skilled in the art can devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses should not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention can be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third, etc., does not indicate any order. These words can be interpreted as names. The steps in the above embodiments, unless otherwise specified, should not be construed as limiting the order of execution.

Claims

1. A method for calculating the energy savings of base station equipment, comprising: Obtain sample indicator data; wherein, the sample indicator data includes: network management performance data, configuration parameter dimension data, and average power data; classify the sample indicator data to obtain sample indicator data of the shutdown effective category and sample indicator data of the shutdown ineffective category; train a first energy consumption model based on the sample indicator data of the shutdown ineffective category; train a second energy consumption model based on the sample indicator data of the shutdown effective category. The classification of the sample indicator data further includes: classifying the sample indicator data according to the number of symbol shutdown subframes, carrier shutdown effective duration, and / or channel shutdown effective duration of the cell corresponding to the sample device; if the carrier shutdown effective duration reaches a first preset value, the channel shutdown effective duration reaches a second preset value, or the proportion of symbol shutdown subframes reaches a third preset value, then the sample indicator data is classified as shutdown effective sample indicator data; if the carrier shutdown effective duration is zero, the channel shutdown effective duration is zero, and the number of shutdown subframes is zero, then the sample indicator data is classified as shutdown ineffective sample indicator data. Acquire indicator data for multiple time periods within the testing period for the cell corresponding to the device under test; wherein, the indicator data includes network management performance data and configuration parameter data; the network management performance data includes at least one of the following: average uplink and downlink PRB utilization, maximum number of users establishing a connection, average number of users establishing a connection, uplink and downlink traffic, radio utilization, PDCCH resource utilization, and VoLTE voice traffic; the configuration parameter data includes at least one of the following: number of carriers, number of channels, and single-channel power; The index data for the multiple time periods are respectively input into the first energy consumption model for processing to obtain multiple first power values ​​under the condition that energy-saving shutdown is ineffective for the multiple time periods; wherein, the first energy consumption model is pre-trained based on sample data; The index data for the multiple time periods are respectively input into the second energy consumption model for processing to obtain multiple second power values ​​under the energy-saving shutdown conditions corresponding to the multiple time periods; wherein, the second energy consumption model is pre-trained based on sample data; Based on the plurality of first power and the plurality of second power, the energy saving of the device under test during the test period is calculated.

2. The method according to claim 1, characterized in that, The method further includes: Based on the manufacturer information, model information, and energy-saving shutdown technology information of the device under test, the corresponding first energy consumption model and second energy consumption model are matched.

3. The method according to claim 1, characterized in that, The method further includes: The indicator data of the device under test are preprocessed; the sample indicator data are preprocessed. The preprocessing includes: normalizing the network management performance data and performing one-hot encoding on the configuration parameter data.

4. An energy-saving calculation device for base station equipment, comprising: The model training module is suitable for acquiring sample indicator data, which includes: network management performance data, configuration parameter dimension data, and average power data. The sample indicator data is classified to obtain sample indicator data of the shutdown effective category and sample indicator data of the shutdown ineffective category. Based on the sample indicator data of the shutdown ineffective category, a first energy consumption model is trained; based on the sample indicator data of the shutdown effective category, a second energy consumption model is trained. The model training module is further adapted to: classify sample indicator data according to the number of symbol shutdown subframes, carrier shutdown duration, and / or channel shutdown duration of the cell corresponding to the sample device; wherein, if the carrier shutdown duration reaches a first preset value, the channel shutdown duration reaches a second preset value, or the proportion of symbol shutdown subframes reaches a third preset value, the sample indicator data is classified as shutdown effective sample indicator data; if the carrier shutdown duration is zero, the channel shutdown duration is zero, and the number of shutdown subframes is zero, the sample indicator data is classified as shutdown ineffective sample indicator data. The data acquisition module is adapted to acquire indicator data for multiple time periods within the test period of the cell corresponding to the device under test; wherein, the indicator data includes network management performance data and configuration parameter data; the network management performance data includes at least one of the following: average uplink and downlink PRB utilization, maximum number of users establishing a connection, average number of users establishing a connection, uplink and downlink traffic, radio utilization, PDCCH resource utilization, and VoLTE voice traffic; the configuration parameter data includes at least one of the following: number of carriers, number of channels, and single-channel power; The model processing module is adapted to input the index data within the multiple time periods into a first energy consumption model for processing to obtain multiple first power values ​​under the condition that energy-saving shutdown is ineffective for the multiple time periods; and to input the index data within the multiple time periods into a second energy consumption model for processing to obtain multiple second power values ​​under the condition that energy-saving shutdown is effective for the multiple time periods; wherein, the first energy consumption model is pre-trained based on sample data, and the second energy consumption model is pre-trained based on sample data; The calculation module is adapted to calculate the energy saving of the device under test during the test period based on the plurality of first power and the plurality of second power.

5. A computing device, comprising: The processor, memory, communication interface, and communication bus are provided, wherein the processor, memory, and communication interface communicate with each other via the communication bus. The memory is used to store at least one executable instruction, which causes the processor to perform the operation corresponding to the energy saving calculation method of the base station equipment as described in any one of claims 1-3.

6. A computer storage medium storing at least one executable instruction that causes a processor to perform an operation corresponding to the energy-saving calculation method of a base station device as described in any one of claims 1-3.

Images