CN113656267A

CN113656267A - Method and device for calculating energy efficiency of equipment, electronic equipment and storage medium

Info

Publication number: CN113656267A
Application number: CN202110860028.2A
Authority: CN
Inventors: 易存道
Original assignee: Beijing Baolande Software Co ltd
Current assignee: Beijing Baolande Software Co ltd
Priority date: 2021-07-28
Filing date: 2021-07-28
Publication date: 2021-11-16
Anticipated expiration: 2041-07-28
Also published as: CN113656267B

Abstract

The invention provides a method and a device for calculating energy efficiency of equipment, electronic equipment and a storage medium, wherein the method comprises the following steps: acquiring data values of a plurality of operation indexes and data values of a plurality of asset attributes of equipment to be predicted; and calculating to obtain an energy efficiency result of the equipment by using a pre-constructed equipment energy efficiency calculation model based on the data values of the operation indexes and the data values of the asset attributes. The method can determine the energy efficiency of the equipment in a multi-index, multi-dimension and high-efficiency manner, has accurate energy efficiency results, and can provide an effective reference basis for equipment management.

Description

Method and device for calculating energy efficiency of equipment, electronic equipment and storage medium

Technical Field

The invention relates to the technical field of informatization energy conservation, in particular to a method and a device for calculating equipment energy efficiency, electronic equipment and a storage medium.

Background

The evaluation of energy efficiency of various assets and equipment when green and low carbon are promoted begins to be gradually emphasized by enterprises and all relevant parties. The device energy efficiency is generally related to the device operation condition and the asset attribute of the device, wherein the device operation condition can be represented by a plurality of operation indexes. For example, if the equipment has good operation conditions (various operation indexes are normal, etc.) and the equipment asset attributes are good (the equipment is newer or has no maintenance record, etc.), the energy efficiency of the equipment is normal; if the equipment is poor in operation condition (some operation indexes are abnormal and the like) and the equipment asset attribute is poor (the equipment is older and has more maintenance records), the energy efficiency of the equipment is low; if the device is not operating directly or the device asset attributes are too old, the device energy efficiency is not valid.

The traditional management method for various computer devices is to store the basic device management data in the manually established EXCEL form file, and then to manually record and check the difference between the data in the data form and the actual device data one by one to find out the problems existing in each device and determine the energy efficiency of each device. However, this approach has a number of disadvantages: 1. the data table has large and complicated data quantity and fast data updating, and the manual query operation is complex, time-consuming, labor-consuming and low in efficiency; 2. when the energy efficiency of the equipment is manually evaluated, the factors or dimensionalities which can be considered are too few, and the evaluation integrity and accuracy are poor.

There is a method for determining the energy efficiency of a device: the method comprises the steps of collecting real-time data of an operation index of equipment to be detected aiming at each operation index, correspondingly comparing the real-time data of the operation index with a preset threshold value of the operation index, judging that the operation index is abnormal if the real-time data exceeds the preset threshold value, and judging that the energy efficiency of the equipment is low at the moment.

The method can only perform single judgment on the result of direct comparison between each operation index and the threshold, and the accuracy of determining the energy efficiency is low. Moreover, one operation index is only instantly embodied on one side of the equipment, and the energy efficiency of the equipment is generally influenced by various comprehensive operation indexes related to the overall performance of the equipment. For example, the CPU utilization of the device in a time period is particularly high and exceeds the CPU utilization threshold, and according to the method, it is determined that the device is in the high-energy-consumption operating state, and the energy efficiency of the device is low. This judgment is apparently one-sided. The reason why the CPU utilization rate is particularly high in the period of time is that actually, a large amount of service TPS enters in the period of time, so that both the CPU utilization rate and the IO utilization rate exceed their own thresholds, but after a period of time, the CPU utilization rate and the IO utilization rate can be recovered to be normal, and thus the situation belongs to normal fluctuation of the device operation index when the server processes the service request. Obviously, the judgment result of the method is wrong in this case.

Therefore, a more effective solution is not available at present for the problems of poor accuracy, few evaluation dimensions, low efficiency and the like in the energy efficiency determination method in the prior art.

Disclosure of Invention

The invention provides a method and a device for calculating the energy efficiency of equipment, electronic equipment and a storage medium, which are used for overcoming the defects of poor accuracy, few evaluation dimensionalities, low efficiency and the like in an energy efficiency determination method in the prior art and can accurately and efficiently determine the energy efficiency of the equipment in multiple indexes and multiple dimensionalities.

The invention provides a method for calculating equipment energy efficiency, which comprises the following steps:

acquiring data values of a plurality of operation indexes and data values of a plurality of asset attributes of equipment to be predicted;

and calculating to obtain an energy efficiency result of the equipment by using a pre-constructed equipment energy efficiency calculation model based on the data values of the operation indexes and the data values of the asset attributes.

According to the method for calculating the energy efficiency of the equipment, the energy efficiency result of the equipment is calculated and obtained by applying a pre-constructed equipment energy efficiency calculation model based on the data values of the operation indexes and the data values of the asset attributes, and the method specifically comprises the following steps:

performing calculation according to a calculation strategy of each level energy efficiency calculation scene in the equipment energy efficiency calculation model based on data values of a plurality of operation indexes and data values of a plurality of asset attributes, and respectively obtaining each level energy efficiency result of the equipment;

performing calculation according to the calculation strategy of each secondary energy efficiency calculation scene in the equipment energy efficiency calculation model based on the data values of a plurality of operation indexes and the data values of a plurality of asset attributes to respectively obtain each secondary energy efficiency result of the equipment;

the equipment energy efficiency calculation model aggregates each primary energy efficiency result and each secondary energy efficiency result according to a result aggregation strategy to obtain an energy efficiency result of the equipment;

and when the energy efficiency result of the equipment is that the equipment is invalid or the equipment is inefficient, the method for calculating the energy efficiency of the equipment further comprises the step of determining the elimination level of the equipment by combining a preset elimination strategy.

According to the method for calculating the energy efficiency of the equipment, the construction process of the equipment energy efficiency calculation model comprises the following steps:

periodically acquiring data values of a plurality of operation indexes and data values of a plurality of asset attributes of each device in a plurality of devices;

performing calculation on data values of a plurality of operation indexes and data values of a plurality of asset attributes of each device according to preset calculation strategies of each level energy efficiency calculation scene to obtain each level energy efficiency result of each device;

performing calculation on data values of a plurality of operation indexes and data values of a plurality of asset attributes of each device according to preset calculation strategies of each secondary energy efficiency calculation scene to obtain each secondary energy efficiency result of each device;

aggregating each primary energy efficiency result and each secondary energy efficiency result of each device according to a result aggregation strategy to obtain an energy efficiency calculation result of each device;

collecting the data in the steps to be used as basic data for modeling;

and performing machine learning training by using an xgboost algorithm based on the basic data to construct the equipment energy efficiency calculation model.

According to the method for calculating the energy efficiency of the equipment, the primary energy efficiency calculation scene comprises the following steps: at least one of an equipment maintenance scene, an equipment maintenance overdue scene, an equipment bearing analysis scene, an equipment elimination scene and an equipment product overdue scene;

and, the secondary energy efficiency calculation scenario includes: at least one of a high-maintenance scenario, a high-failure scenario, a low-utilization scenario, and a high-energy consumption scenario.

According to the method for calculating the energy efficiency of the equipment, the operation index comprises the following steps: at least one of a CPU utilization rate, a memory utilization rate, an IO utilization rate, a connection channel utilization rate and a storage space utilization rate;

and/or, the asset attributes, including: at least one of a maintenance manufacturer, maintenance time and maintenance period, bearing component condition, a manufacturer and equipment model, equipment on-line date and equipment expiration date, maintenance cost, equipment type, failure alarm times and equipment use power.

According to the method for calculating the energy efficiency of the equipment, the calculation strategy of the equipment maintenance scene comprises the following steps: judging whether the equipment meets the requirement of a manufacturer with a maintenance based on the data value of the maintenance manufacturer in the asset attribute of the current equipment; if so, the first-level energy efficiency result of the equipment under the equipment maintenance scene is the equipment inefficiency; if not, the equipment is normal;

and/or the calculation strategy of the equipment maintenance overdue scene comprises the following steps: judging whether the equipment exceeds the maintenance time limit or not based on the data value of the maintenance time and the maintenance time limit in the asset attribute of the current equipment; if so, the first-level energy efficiency result of the equipment under the condition of the equipment maintenance overdue scene is low efficiency of the equipment; if not, the equipment is normal;

and/or the equipment bears the calculation strategy of the analysis scene, and the calculation strategy comprises the following steps: judging whether the equipment meets the requirement of bearing the component or not based on the data value of the condition of the bearing component in the asset attribute of the current equipment; if so, the primary energy efficiency result of the equipment under the equipment bearing analysis scene is that the equipment is invalid; if not, the equipment is normal;

and/or the calculation strategy of the equipment elimination scene comprises the following steps: judging whether the equipment is in a obsolete equipment catalog or not based on data values of manufacturers and equipment models in the asset attributes of the current equipment and the pre-acquired obsolete equipment catalog; if the situation is true, the first-level energy efficiency result of the equipment in the equipment elimination scene is that the equipment is invalid; if not, the equipment is normal;

and/or the calculation strategy of the equipment product expiration scene comprises the following steps: judging whether the equipment meets the condition that the equipment use date exceeds the equipment validity period or not based on the data value of the equipment on-line date and the equipment validity period in the asset attribute of the current equipment; if so, the first-level energy efficiency result of the equipment in the equipment product overdue scene is the equipment inefficiency; if not, the equipment is normal;

and/or the calculation strategy of the high-maintenance scene comprises the following steps: based on the data value of the maintenance cost in the asset attribute of the current equipment, judging whether the maintenance cost of the current equipment meets a preset reference value exceeding the maintenance cost of the equipment or whether the maintenance cost of the current equipment meets a preset multiple exceeding the average maintenance cost of each equipment under the same equipment type; if the first energy efficiency is met, the secondary energy efficiency result of the equipment under the high-maintenance scene is that the equipment is low in efficiency; if the conditions are not met, the equipment is normal;

and/or the calculation strategy of the high fault scene comprises the following steps: judging whether the average value of the fault alarm times of the current equipment meets a preset reference value exceeding the fault alarm times or whether the average value of the fault alarm times of the current equipment meets a preset multiple exceeding the average fault alarm times of each equipment under the same equipment type or not based on the data value of the fault alarm times in the asset attribute of the current equipment in a preset time period; if the first condition is met, the secondary energy efficiency result of the equipment under the high fault scene is that the equipment is invalid; if the conditions are not met, the equipment is normal;

and/or the calculation strategy of the low utilization rate scene comprises the following steps: judging whether the data value of the operation index of the current equipment meets a preset reference value lower than the operation index or not based on the data value of each operation index of the current equipment in a preset time period, or judging whether the data value of the operation index of the current equipment meets a preset multiple lower than the average value of the operation indexes of the equipment in the same equipment type or not; if all the operation indexes of the current equipment meet one of the operation indexes, the secondary energy efficiency result of the equipment under the low-utilization-rate scene is that the equipment is low in efficiency; otherwise, the equipment is normal;

and/or the calculation strategy of the high energy consumption scene comprises the following steps: and an operation index judgment step: judging whether the data value of the operation index of the current equipment meets a preset reference value lower than the operation index or not based on the data value of each operation index of the current equipment in a preset time period, or judging whether the data value of the operation index of the current equipment meets a preset multiple lower than the average value of the operation indexes of the equipment in the same equipment type or not; asset attribute judging step: based on the data value of each asset attribute of the current equipment, judging whether the data value of the asset attribute of the current equipment meets a preset reference value exceeding the asset attribute, or judging whether the data value of the asset attribute of the current equipment meets a preset multiple exceeding the average value of the asset attribute of each equipment in the same equipment type; if all the operation indexes of the current equipment meet one of the operation indexes, or any asset attribute of the current equipment meets one of the operation indexes, the secondary energy efficiency result of the equipment under the high-energy-consumption scene is that the equipment is low in efficiency; otherwise, the device is normal.

According to the method for calculating the energy efficiency of the device provided by the invention, the result aggregation strategy comprises the following steps: analyzing each primary energy efficiency result and each secondary energy efficiency result of each device, and if at least one result is that the device is invalid, determining that the energy efficiency result of the device is that the device is invalid; if no equipment is invalid but at least one result is that the equipment is inefficient, the energy efficiency result of the equipment is that the equipment is inefficient; and if all the results are normal, the energy efficiency result of the equipment is normal.

The invention also provides a device for calculating the energy efficiency of equipment, which comprises:

the data acquisition module is used for acquiring data values of a plurality of operation indexes and data values of a plurality of asset attributes of the equipment to be predicted;

and the energy efficiency calculation module is used for calculating and obtaining an energy efficiency result of the equipment by applying a pre-constructed equipment energy efficiency calculation model based on the data values of the operation indexes and the data values of the asset attributes.

The invention also provides an electronic device, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein when the processor executes the computer program, all or part of the steps of the method for calculating the energy efficiency of the device are realized.

The invention also provides a computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out all or part of the steps of the method for calculating the energy efficiency of a device according to any one of the above.

The invention provides a method and a device for calculating the energy efficiency of equipment, electronic equipment and a storage medium, wherein the method obtains the energy efficiency result of the equipment by acquiring data values of a plurality of operation indexes and data values of a plurality of asset attributes of the equipment to be predicted and combining a pre-constructed equipment energy efficiency calculation model, can determine the energy efficiency of the equipment in a multi-index, multi-dimension and high-efficiency manner, has accurate energy efficiency result and can provide an effective reference basis for equipment management.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.

FIG. 1 is a flow chart of a method for calculating energy efficiency of a device according to the present invention;

FIG. 2 is a second flowchart of the method for calculating energy efficiency of a device according to the present invention;

FIG. 3 is a third schematic flow chart of a method for calculating energy efficiency of a device according to the present invention;

FIG. 4 is a schematic flow chart of a process for constructing a device energy efficiency calculation model in the method for calculating device energy efficiency according to the present invention;

FIG. 5 is a second flowchart illustrating a process of constructing a device energy efficiency calculation model in the method for calculating device energy efficiency according to the present invention;

FIG. 6 is a schematic diagram of a computing device for energy efficiency of the apparatus provided by the present invention;

fig. 7 is a schematic structural diagram of an electronic device provided by the present invention.

Reference numerals:

610: a data acquisition module; 620: an energy efficiency calculation module; 710: a processor;

720: a communication interface; 730: a memory; 740: a communication bus.

Detailed Description

In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be described in detail below with reference to the accompanying drawings, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

The following describes a method, an apparatus, an electronic device, and a storage medium for calculating device energy efficiency according to the present invention with reference to fig. 1 to 7.

The invention provides a method for calculating equipment energy efficiency, fig. 1 is one of flow diagrams of the method for calculating equipment energy efficiency provided by the invention, and as shown in fig. 1, the method comprises the following steps:

210. acquiring data values of a plurality of operation indexes and data values of a plurality of asset attributes of equipment to be predicted;

220. and calculating to obtain an energy efficiency result of the equipment by using a pre-constructed equipment energy efficiency calculation model based on the data values of the operation indexes and the data values of the asset attributes.

Modern enterprises introduce a large number of assets for their business expansion and to meet various new service requirements, such as: a server, a network device, a storage device, an application device, a host device, and the like. Due to the complex manual management and the reasons of untimely management, elimination and updating, a large amount of inefficient or invalid devices may exist, which may not only play a good role in enterprise services, but also occupy the space and management resources of enterprises, so that further analysis of these assets is urgently needed to find out inefficient or invalid devices from the assets for effective classification management and elimination and updating.

A plurality of devices of each device type are usually stored in the same AMDB system resource pool, and one device that needs energy efficiency calculation is obtained from the AMDB system resource pool according to a service demand to be predicted, that is, one device of one device type is used as a device to be predicted. Of course, if a plurality of devices all need to perform energy efficiency calculation, one device is selected each time to perform energy efficiency calculation, and the currently selected device is used as a device to be predicted, which is also referred to as a current device. And acquiring data values of a plurality of operation indexes of the current equipment and data values of a plurality of asset attributes of the current equipment. The operation indexes comprise one or more of CPU utilization rate, memory utilization rate, IO utilization rate, connection channel utilization rate and storage space utilization rate, and the asset attributes comprise one or more of maintenance manufacturer, maintenance time and maintenance duration, bearing component condition, manufacturer and equipment model, equipment on-line date and equipment validity period, maintenance cost, equipment type, failure alarm times and equipment use power. The specific adjustment can be made according to the type of the device to which the current device belongs or according to the specific situation of the current device. And then inputting the obtained data values of a plurality of operation indexes of the current equipment and the obtained data values of a plurality of asset attributes of the current equipment into a pre-constructed equipment energy efficiency calculation model, and obtaining an energy efficiency result of the current equipment through calculation of the equipment energy efficiency calculation model. The energy efficiency result of the current device may include three situations, where the current device is invalid, or the current device is inefficient, or the current device is normal. And directly judging whether the current equipment is low-efficiency or invalid equipment according to the energy efficiency condition of the current equipment indicated in the finally obtained energy efficiency result of the current equipment so as to be conveniently managed by related management personnel.

The invention provides a method for calculating the energy efficiency of equipment, which is characterized in that the method obtains the energy efficiency result of the equipment by acquiring the data values of a plurality of operation indexes and the data values of a plurality of asset attributes of the equipment to be predicted and combining with a pre-constructed equipment energy efficiency calculation model, can determine the energy efficiency of the equipment in a multi-index, multi-dimension and high-efficiency manner, has accurate energy efficiency result and can provide an effective reference basis for equipment management.

According to the method for calculating the energy efficiency of the equipment provided by the present invention, fig. 2 is a second schematic flow chart of the method for calculating the energy efficiency of the equipment provided by the present invention, and as shown in fig. 2, the step 220 of calculating the energy efficiency result of the equipment by using a pre-constructed equipment energy efficiency calculation model based on data values of a plurality of operation indexes and data values of a plurality of asset attributes specifically includes:

221. performing calculation according to a calculation strategy of each level energy efficiency calculation scene in the equipment energy efficiency calculation model based on data values of a plurality of operation indexes and data values of a plurality of asset attributes, and respectively obtaining each level energy efficiency result of the equipment;

222. performing calculation according to the calculation strategy of each secondary energy efficiency calculation scene in the equipment energy efficiency calculation model based on the data values of a plurality of operation indexes and the data values of a plurality of asset attributes to respectively obtain each secondary energy efficiency result of the equipment;

223. and the equipment energy efficiency calculation model aggregates the primary energy efficiency results and the secondary energy efficiency results according to a result aggregation strategy to obtain the energy efficiency results of the equipment.

After the obtained data values of a plurality of operation indexes of the current equipment and the data values of a plurality of asset attributes of the current equipment are input into a pre-constructed equipment energy efficiency calculation model, the energy efficiency calculation model can be divided into a simpler primary energy efficiency calculation scene and a more complex secondary energy efficiency calculation scene, each scene is an energy efficiency calculation scene preset according to historical experience data, and each scene corresponds to an independent calculation strategy. And determining which energy efficiency calculation scenes are suitable for the current equipment according to the obtained data values of the plurality of operation indexes of the current equipment and the obtained data values of the plurality of asset attributes of the current equipment, wherein the operation indexes are specific and the asset attributes are specific, and correspondingly executing the calculation of one or more energy efficiency calculation scenes according to actual calculation requirements. Of course, only the calculation of the primary energy efficiency calculation scenario may be performed, or both the calculation of the primary energy efficiency calculation scenario and the calculation of the secondary energy efficiency calculation scenario may be performed. Moreover, when computing a plurality of energy efficiency computing scenarios for the current device, it is also necessary to correspondingly combine the results obtained in each energy efficiency computing scenario, for example, aggregate the results according to a preset result aggregation policy.

Specifically, firstly, based on data values of a plurality of operation indexes and data values of a plurality of asset attributes, performing calculation according to a calculation strategy of each level energy efficiency calculation scene in the equipment energy efficiency calculation model to respectively obtain each level energy efficiency result of the equipment; performing calculation according to the calculation strategy of each secondary energy efficiency calculation scene in the equipment energy efficiency calculation model based on the data values of a plurality of operation indexes and the data values of a plurality of asset attributes to respectively obtain each secondary energy efficiency result of the equipment; and finally, the equipment energy efficiency calculation model can aggregate each primary energy efficiency result and each secondary energy efficiency result according to a result aggregation strategy to obtain the comprehensive energy efficiency result of the current equipment.

Each level of energy efficiency calculation scene preset in the model comprises the following steps: one or more of an equipment maintenance scene, an equipment maintenance overdue scene, an equipment bearing analysis scene, an equipment elimination scene and an equipment product overdue scene. The preset secondary energy efficiency calculation scene in the model comprises the following steps: one or more of a high-maintenance scenario, a high-failure scenario, a low-utilization scenario, and a high-energy-consumption scenario. The secondary energy efficiency calculation scene is usually used for judging the energy efficiency from the angles of a plurality of asset attributes and/or a plurality of operation indexes, and the judgment result is more accurate. And for each energy efficiency calculation scene and the specific calculation strategy thereof, the detailed introduction content of the subsequent model construction process can be referred.

And wherein the result aggregation policy comprises: analyzing each primary energy efficiency result and each secondary energy efficiency result of each device, and if at least one result is that the device is invalid, determining that the energy efficiency result of the device is that the device is invalid; if no equipment is invalid but at least one result is that the equipment is inefficient, the energy efficiency result of the equipment is that the equipment is inefficient; and if all the results are normal, the energy efficiency result of the equipment is normal.

Energy efficiency calculation scenes of different levels are preset in the equipment energy efficiency calculation model, simple primary energy efficiency calculation scenes are calculated according to equipment conditions, or secondary energy efficiency calculation scenes are calculated in a combined mode, and finally energy efficiency results calculated by the energy efficiency calculation scenes are combined and aggregated to obtain total energy efficiency evaluation of the current equipment, so that various defects of single angle and large error of energy efficiency evaluation results when the energy efficiency is evaluated manually can be effectively avoided.

And when the energy efficiency result of the equipment is that the equipment is invalid or the equipment is inefficient, the method for calculating the energy efficiency of the equipment further comprises the step of determining the elimination level of the equipment by combining a preset elimination strategy. Fig. 3 is a third schematic flow chart of the method for calculating energy efficiency of equipment according to the present invention, as shown in fig. 3, that is, based on the embodiment shown in fig. 2, the method further includes the following steps:

230. and when the energy efficiency result of the equipment is that the equipment is invalid or the equipment is inefficient, determining the elimination level of the equipment by combining a preset elimination strategy.

When the energy efficiency result of the current device finally determined in step 223 is that the device is invalid or the device is inefficient, the elimination level of the current device is also determined according to the elimination policy. Specifically, according to a elimination strategy comprising three items of a high elimination level, a medium elimination level and a low elimination level, the elimination level to which the current equipment belongs is determined, and the elimination level is marked to the current equipment in the form of a label for relevant management personnel to check and refer.

In the elimination strategy, corresponding elimination conditions are respectively set for each elimination level, and the specific content of the elimination conditions is the elimination limited range of each asset attribute and each operation index of the equipment, such as the limitation of the asset attributes of manufacturers, attribution scenes, maintenance cost, service life, failure alarm frequency and the like, or the limitation of elimination threshold values of each operation index and the like.

For the current equipment, comparing the asset attribute and the operation index of the current equipment with the corresponding elimination condition of the elimination level according to the elimination level from high to low, if the elimination condition of the high elimination level is met, the elimination level of the current equipment is the high elimination level, otherwise, the elimination level of the current equipment is continuously compared with the corresponding elimination condition of the medium elimination level, if the elimination condition of the medium elimination level is met, the elimination level of the current equipment is the medium elimination level, and so on, if the elimination conditions corresponding to the three elimination levels are not met, the elimination level of the current equipment is defaulted to be 0, namely, the elimination is not needed.

According to any equipment energy efficiency calculation method provided by the present invention, that is, on the basis of the embodiment shown in any one of fig. 1 to fig. 3, fig. 4 is one of the flow diagrams of the process for constructing an equipment energy efficiency calculation model in the equipment energy efficiency calculation method provided by the present invention, as shown in fig. 4, the process for constructing the equipment energy efficiency calculation model specifically includes:

110. periodically acquiring data values of a plurality of operation indexes and data values of a plurality of asset attributes of each device in a plurality of devices;

120. performing calculation on data values of a plurality of operation indexes and data values of a plurality of asset attributes of each device according to preset calculation strategies of each level energy efficiency calculation scene to obtain each level energy efficiency result of each device;

130. performing calculation on data values of a plurality of operation indexes and data values of a plurality of asset attributes of each device according to preset calculation strategies of each secondary energy efficiency calculation scene to obtain each secondary energy efficiency result of each device;

140. aggregating each primary energy efficiency result and each secondary energy efficiency result of each device according to a result aggregation strategy to obtain an energy efficiency calculation result of each device;

150. collecting the data in the steps to be used as basic data for modeling;

160. and performing machine learning training by using an xgboost algorithm based on the basic data to construct the equipment energy efficiency calculation model.

In order to increase the accuracy of the constructed equipment energy efficiency calculation model, a model basic data collection stage, a model training stage and a model testing stage need to be controlled respectively.

A model basic data collection stage:

a plurality of data values for a plurality of operational indicators for a plurality of devices and a plurality of data values for a plurality of asset attributes for the same device are collected. Wherein, each equipment is collected one by one, or a plurality of equipment are collected alternately.

After a large amount of data of a large amount of equipment are collected, the collected data are subjected to data aggregation according to each operation index of each equipment and a large amount of data values of different time sequences of each operation index, and data aggregation according to different time dimensions such as a day dimension, a week dimension and a month dimension is carried out, so that the efficiency of modeling can be effectively improved through the preprocessing process.

The specific data aggregation algorithm is to sum all original values of the data values of each operation index of each device in a plurality of devices within a period of time, and take the maximum value of the summed values as a new data value. And then, adding a new data value every time, needing to carry out data aggregation again, comparing the maximum value in all original values of all data values of the time with the maximum value obtained by the last aggregation every time of data aggregation, and if the maximum value is smaller than the maximum value obtained by the last aggregation, still obtaining the maximum value obtained by the last aggregation; and taking the maximum value in each original value of all the data values aggregated at this time under other conditions. The maximum value is taken as a new data value of the operation index, so that the maximum utilization rate of the operation index of the current equipment in the period of time can be reflected more accurately, and the maximum utilization rate of the operation index is compared with a set reference value of the operation index and the like in the process of participating in the calculation of the equipment energy efficiency model, so that the energy efficiency of the equipment can be estimated more accurately.

And meanwhile, counting the number of data values of the operation index, summing all the original values, and dividing the sum by the number to obtain a data average value corresponding to the operation index for subsequent steps.

Of course, the data can be stored in a relational database, so that management and calling are facilitated.

Defining a plurality of energy efficiency calculation scenes in advance, wherein the energy efficiency calculation scenes mainly comprise two types, one type is a simple scene, such as a primary energy efficiency calculation scene of an equipment maintenance scene, an equipment maintenance overdue scene, an equipment bearing analysis scene, an equipment elimination scene, an equipment product overdue scene and the like; the other type is slightly complex, such as secondary energy efficiency calculation scenes including high-dimensional protection scenes, high-failure scenes, low-utilization scenes and high-energy-consumption scenes. The secondary energy efficiency calculation scene is usually used for judging the energy efficiency from the angles of a plurality of asset attributes and/or a plurality of operation indexes, and the judgment result is more accurate. And each energy efficiency calculation scene has its own independent calculation strategy, so that it can judge the energy efficiency of the equipment according to different standards or angles. Of course, for each energy efficiency calculation scenario and its specific calculation strategy, reference may be made to the detailed description of the subsequent model building process.

And respectively executing calculation according to the preset calculation strategy of each level energy efficiency calculation scene by using the data values of the plurality of operation indexes and the data values of the plurality of asset attributes of each device to obtain each level energy efficiency result of each device. And then, carrying out calculation on the data values of the plurality of operation indexes and the data values of the plurality of asset attributes of each device according to the preset calculation strategy of each secondary energy efficiency calculation scene to obtain each secondary energy efficiency result of each device. And aggregating each primary energy efficiency result and each secondary energy efficiency result of each device according to a result aggregation strategy to obtain the energy efficiency result of each device. This is performed for each device, whereby the energy efficiency result for each device is determined.

Of course, a step of verification and confirmation by the enterprise user may be added, that is, the comprehensive energy efficiency result of each device is displayed to the enterprise user, and the enterprise user finally confirms whether the energy efficiency result is evaluated accurately. The enterprise user marks the approved energy efficiency result as an accurate energy efficiency result, and the enterprise user marks the unapproved energy efficiency result as an inaccurate energy efficiency result. Therefore, the steps of confirming and screening by enterprise users are added to the energy efficiency results of all the devices, and only the relevant data with accurate energy efficiency results can be screened out to construct a device energy efficiency calculation model. And each device corresponding to each energy efficiency result which is not approved by the enterprise user needs to be replaced into the resource pool, and the energy efficiency result is determined again in the following process.

And then collecting various data in the steps, including a large amount of data values of a plurality of operation indexes and data values of a plurality of asset attributes of each device, data of each primary energy efficiency calculation scene, a calculation strategy and each corresponding primary energy efficiency result, each secondary energy efficiency calculation scene, a calculation strategy and each corresponding secondary energy efficiency result, a comprehensive energy efficiency result of each corresponding device and the like, and using the data as basic data for modeling. It can also be understood that the data of each device and each collected operation index before energy efficiency determination, the data of each asset attribute, the data of each operation index or the reference value/threshold value of each asset attribute, and the like, as well as the intermediate energy efficiency result, each energy efficiency calculation scenario, the calculation strategy, and the final energy efficiency result are collected and collectively used as basic data for modeling.

And serializing all data in the basic data into json character strings, inputting the json character strings into an AI (artificial intelligence) model through a RESTful Api programmable program, and performing machine learning training by using a higher-order xgboost algorithm and combining a cross verification method and a parameter grid search method to construct and optimize a required equipment energy efficiency calculation model.

The secondary energy efficiency calculation scene is usually judged by the angles of a plurality of asset attributes and/or a plurality of operation indexes, and the judgment result is more accurate. And each energy efficiency calculation scene has its own independent calculation strategy, so that it can judge the energy efficiency of the equipment according to different standards or angles.

According to the method for calculating the energy efficiency of the equipment provided by the present invention, before step 160, before the machine learning training is performed by using the xgboost algorithm based on the basic data to construct the equipment energy efficiency calculation model, the method further includes a step of performing data conversion processing on the basic data, and specifically includes:

determining each Chinese field in data values of a plurality of operation indexes and data values of a plurality of asset attributes of each device in the basic data;

and performing data conversion processing on each Chinese field based on a one-hot coding feature extraction method to convert each Chinese field into a plurality of corresponding variable values.

That is, between step 150 and step 160, a step of performing data conversion processing on the basic data is further included, which in turn specifically includes the following steps:

there may be multiple data types, such as string type, Chinese character segment type, etc., after the initial acquisition of the basic data for modeling. And the underlying data may also have missing or outliers. Therefore, it is necessary to perform data stuffing or exception removal preprocessing on the basic data, and even to perform uniform conversion processing on the data types of the basic data, for example, all the chinese character segment type data can be converted into string type data.

(1) Carrying out data filling or exception removal preprocessing on the basic data:

and (1-1) summarizing and analyzing missing values in each field of the basic data, and filling the missing values in the fields with 0 on the basis of conventional business knowledge for equipment operation and maintenance management. And (1-2) summarizing and analyzing abnormal values in each piece of data of the basic data, and averaging the data with the quantiles of more than 99% by using an averaging method to remove the abnormal values.

The acquired basic data includes a large amount of Chinese character segment type data, such as 'equipment manufacturer', 'equipment holder', etc. The use of machine learning algorithms typically requires that all input data must be numerical. Therefore, it is necessary to perform a unified conversion process on the basic data, which mainly means to convert all the data of the chinese character segment type in the basic data into data of the character string type.

(2) Data conversion processing is carried out by adopting a one-hot coding feature extraction method (named as OneHot method for short):

(2-1) introduction of OneHot method:

the OneHot method belongs to a method of 'dummy variable' conversion to convert one variable into a plurality of columns. Taking a "manufacturer" as an example, according to its data values (the data values may be hua shi, cisco, and wave tide), the data values are converted into three variables of "whether the manufacturer is hua shi", "whether the manufacturer is cisco", and "whether the manufacturer is wave tide", that is, the data values are converted into the number of variables according to each unique value of the data values, and the number of unique values is converted into the number of variables. For the same reason, for example: the "manufacturer" has 1000 different data values, of which there are 10 unique values, and then there are 10 variables after conversion, one of which occupies one column. However, in some operation indexes or asset attributes, the data values have more unique values, so that the variables of the operation indexes or asset attributes are more after the operation indexes or asset attributes are converted by the OneHot method, and thus the features are sparse. In this case, it is necessary to perform summary statistics on each unique value of the data value, select TOP-N unique values, and perform data conversion processing on the data value according to the TOP-N unique values to obtain N variables. For example, N is 10, when the unique values of the data value have 100, the first 10 unique values of the 100 unique values are selected as conversion targets, the data value is subjected to data conversion processing to obtain 10 variables, and the other variables after conversion of the remaining 90 data values are all recorded as "other". See table 1 below for details.

TABLE 1

Manufacturer of the product	Whether the manufacturers are luxurious	Whether the manufacturer thinks or not	Whether the producer is in the tide
				Huawei	1	0	0
Huawei	1	0	0
				Cisco	0	1	0
Tide	0	0	1
				......	......	......	......

(2-2) determining data of all Chinese fields in data values of a plurality of operation indexes and data values of a plurality of asset attributes of each device in the basic data, and performing data conversion processing on the Chinese fields based on the OneHot method in (2-1) to convert each Chinese field into a plurality of corresponding variable values.

And (2-3) performing feature derivation processing on the basic data based on the conventional business knowledge of the device operation and maintenance management, for example, taking the data of "IOThreshold" and "IOResult" as an example, deriving a feature of whether the current device IO utilization is greater than the IO utilization reference value based on the conventional business knowledge of the device operation and maintenance management.

And (3) taking the basic data processed in the steps (1) and (2) as new basic data for constructing a device energy efficiency calculation model.

According to the method for calculating the energy efficiency of the equipment provided by the present invention, fig. 5 is a second schematic flow chart of a process for constructing an energy efficiency calculation model of the equipment in the method for calculating the energy efficiency of the equipment provided by the present invention, as shown in fig. 5, and based on the embodiment shown in fig. 4, step 160, which is based on the basic data and uses an xgboost algorithm to perform machine learning training, so as to construct the energy efficiency calculation model of the equipment, specifically includes the following steps:

161. dividing the basic data into K sub-samples based on a K-fold cross verification method;

162. performing machine learning training on a training data set formed by K-1 sub-samples by using an xgboost algorithm to construct an equipment energy efficiency calculation model;

163. verifying the equipment energy efficiency calculation model based on a verification data set formed by 1 sub-sample;

164. and repeatedly executing K times of cross training and verification to obtain a final equipment energy efficiency calculation model.

The model training process further includes steps 161-164 as follows. The basic idea of the cross-validation method is to divide the raw data (dataset) into groups in a certain sense, one group is used as a training data set (train set), and the other group is used as a validation set or test set). The method comprises the steps of firstly learning and training an AI classifier by using a training data set, then verifying and testing a model (model) obtained by previous training by using a verification data set, and taking the model as a performance index of an evaluation classifier, and optimizing the model according to the performance index. In this embodiment, a K-fold cross validation method (K-fold cross-validation) is used for cross validation, specifically, 10-fold cross validation is used for cross validation, and in this embodiment, the original data refers to basic data used for model training.

The initially sampled basic data is divided into K sub-samples, i.e. into 10 sub-samples. Wherein, each subsample can be obtained by random division.

And reserving 1 single sub sample as data of a subsequent verification model, forming a training data set by using other K-1 sub samples, specifically, other 9 sub samples, and performing machine learning training on the training data set by using a high-order xgboost algorithm to construct a preliminary equipment energy efficiency calculation model.

And verifying and testing the preliminary equipment energy efficiency calculation model based on a verification data set formed by the pre-reserved 1 subsample, and adjusting parameters of an xgboost algorithm and the like according to the verification and testing results to optimize the model.

And, repeatedly performing 10 times of cross training and verification, namely performing 10 times, selecting 1 different sub sample as a verification data set each time, and using the remaining 9 sub samples as training data sets, performing training and verifying, and … …, performing 10 times, namely performing verification once for each sub sample, averaging 10 times of results, and obtaining a final optimized equipment energy efficiency calculation model.

The K-fold cross-validation method has the advantages that different randomly generated sub-samples are repeatedly used for training and validation at the same time, and the result of each time can be validated once, so that a more optimized and accurate result is obtained.

It should be added that, when the cross-validation is performed by using 10-fold cross-validation for cross-training and validation in this embodiment, a parameter grid search method may be further introduced in the model training process to adjust the xgboost algorithm parameters.

The introduction of the parameter grid search method is as follows:

the parameter grid search method refers to that in the selection of all candidate parameters, each parameter possibility is tried through loop traversal, and finally the best-performing parameter is taken as the final result. In order to improve the learning efficiency of the xgboost algorithm, in general, the max _ depth parameter and the learning _ rate parameter of the xgboost algorithm are selected for emphasis adjustment and optimization, and the search spaces of the two parameters are shown in table 2 below.

TABLE 2

Parameter name	Search space
		max_depth	3、4、5
learning_rate	0.001、0.01、0.02、0.05

A plurality of operational metrics for each plant, comprising: any one or more of a CPU usage rate, a memory usage rate, an IO usage rate, a connection channel usage rate, and a storage space usage rate. And/or, a number of asset attributes for each device, including: any one or more of a maintenance manufacturer, maintenance time and maintenance period, bearing component conditions, a manufacturer and a device model, a device number, a device on-line date and a device expiration date, maintenance cost, a device type, a device large class, a device small class, a device id, a device ip, failure alarm times, device use power, a device holder and the like.

and/or the equipment bears the calculation strategy of the analysis scene, and the calculation strategy comprises the following steps: judging whether the equipment meets the condition of bearing the components or not based on the data value of the condition of the bearing components in the asset attributes of the current equipment, wherein the components comprise one or more of sub-components, instances and applications; if so, the primary energy efficiency result of the equipment under the equipment bearing analysis scene is that the equipment is invalid; if not, the equipment is normal;

the relation that each operation index meeting one of the two conditions belongs to is that each operation index meets one of the two conditions, the low efficiency of the equipment can be judged, otherwise, the equipment is normal. Such as: and observing two operation indexes of the CPU utilization rate and the memory utilization rate of the equipment A. The data value of the CPU utilization rate selects the maximum value after data aggregation as a new data value, and the data value of the memory utilization rate also selects the maximum value after data aggregation as a new data value. And judging that the new data value of the CPU utilization rate of the equipment A is lower than the preset reference value of the operation index, but the memory utilization rate of the equipment A is the new data value and is higher than the threshold value. At this time, if the data value of each operation index is not lower than the preset reference value, the energy efficiency result of the equipment a in the scene is that the equipment a is normal.

The results of the operation index judging step and the asset attribute judging step are in an OR relationship, and if only one step judges that the equipment is low in efficiency, the comprehensive result is that the equipment is low in efficiency.

According to the method for calculating the energy efficiency of the equipment, for each result respectively obtained by each primary energy efficiency calculation scene and each secondary energy efficiency calculation scene, the result aggregation strategy comprises the following steps: analyzing each primary energy efficiency result and each secondary energy efficiency result of each device, and if at least one result is that the device is invalid, determining that the energy efficiency result of the device is that the device is invalid; if no equipment is invalid but at least one result is that the equipment is inefficient, the energy efficiency result of the equipment is that the equipment is inefficient; and if all the results are normal, the energy efficiency result of the equipment is normal.

The device energy efficiency calculating apparatus provided by the present invention is described below, and the device energy efficiency calculating apparatus can be understood as an apparatus for executing the device energy efficiency calculating method, and the application principles of the apparatus energy efficiency calculating apparatus and the device energy efficiency calculating apparatus are the same and can be referred to each other, which are not described herein again.

The invention also provides a device for calculating the energy efficiency of equipment, which comprises: a data acquisition module 610 and an energy efficiency calculation module 620, wherein,

the data obtaining module 610 is configured to obtain data values of a plurality of operation indexes and data values of a plurality of asset attributes of the device to be predicted;

the energy efficiency calculation module 620 is configured to calculate an energy efficiency result of the device by using a pre-established device energy efficiency calculation model based on data values of a plurality of operation indexes and data values of a plurality of asset attributes.

The invention provides a device for calculating the energy efficiency of equipment, which comprises a data acquisition module 610 and an energy efficiency calculation module 620, wherein the modules are matched with each other, so that the device can determine the energy efficiency of the equipment in a multi-index, multi-dimension and high-efficiency manner, the energy efficiency result is accurate, and an effective reference basis can be provided for equipment management.

Fig. 7 is a schematic structural diagram of the electronic device provided in the present invention, and as shown in fig. 7, the electronic device may include: a processor (processor)710, a communication Interface (Communications Interface)720, a memory (memory)730, and a communication bus 740, wherein the processor 710, the communication Interface 720, and the memory 730 communicate with each other via the communication bus 740. Processor 710 may invoke logic instructions in memory 730 to perform all or a portion of the steps of the device energy efficiency calculation method, comprising:

In addition, the logic instructions in the memory 730 can be implemented in the form of software functional units and stored in a computer readable storage medium when the software functional units are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to perform all or part of the steps of the method for calculating the energy efficiency of the device according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.

In another aspect, the present invention further provides a computer program product including a computer program stored on a non-transitory computer-readable storage medium, the computer program including program instructions, when the program instructions are executed by a computer, the computer being capable of executing all or part of the steps of the method for calculating the energy efficiency of the device according to the above embodiments, the method including:

In yet another aspect, the present invention also provides a non-transitory computer-readable storage medium having stored thereon a computer program, which when executed by a processor, implements all or part of the steps of the method for calculating the energy efficiency of a device according to the above embodiments, the method including:

The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the embodiment of the present invention. One of ordinary skill in the art can understand and implement it without inventive effort.

Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. Based on the understanding, the above technical solutions may be essentially or partially implemented in the form of a software product, which may be stored in a computer-readable storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the device energy efficiency calculation method according to the embodiments or some parts of the embodiments.

Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.

Claims

1. A method for calculating energy efficiency of equipment is characterized by comprising the following steps:

2. The method according to claim 1, wherein the step of obtaining the energy efficiency result of the equipment by computing based on the data values of the plurality of operation indexes and the data values of the plurality of asset attributes by using a pre-established equipment energy efficiency computation model specifically comprises:

3. The method for calculating the energy efficiency of the equipment according to claim 1 or 2, wherein the construction process of the equipment energy efficiency calculation model comprises the following steps:

collecting the data in the steps to be used as basic data for modeling;

4. The method for calculating the energy efficiency of the equipment according to claim 3, wherein the primary energy efficiency calculation scenario comprises: at least one of an equipment maintenance scene, an equipment maintenance overdue scene, an equipment bearing analysis scene, an equipment elimination scene and an equipment product overdue scene;

5. The method according to claim 4, wherein the operation index includes: at least one of a CPU utilization rate, a memory utilization rate, an IO utilization rate, a connection channel utilization rate and a storage space utilization rate;

6. The method of computing plant energy efficiency according to claim 5,

the calculation strategy of the equipment maintenance scene comprises the following steps: judging whether the equipment meets the requirement of a manufacturer with a maintenance based on the data value of the maintenance manufacturer in the asset attribute of the current equipment; if so, the first-level energy efficiency result of the equipment under the equipment maintenance scene is the equipment inefficiency; if not, the equipment is normal;

7. The method according to claim 6, wherein the result aggregation policy comprises: analyzing each primary energy efficiency result and each secondary energy efficiency result of each device, and if at least one result is that the device is invalid, determining that the energy efficiency result of the device is that the device is invalid; if no equipment is invalid but at least one result is that the equipment is inefficient, the energy efficiency result of the equipment is that the equipment is inefficient; and if all the results are normal, the energy efficiency result of the equipment is normal.

8. An apparatus for computing energy efficiency of a device, comprising:

9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements all or part of the steps of the method for computing the energy efficiency of the device according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out all or part of the steps of a method for computing energy efficiency for a device according to any one of claims 1 to 7.